Breathing detection method, device and equipment and storage medium

Abstract

The invention discloses a respiration detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining first respiration movement data in a first time period based on an inertial measurement unit arranged on a target object; performing joint processing on data of multiple dimensions in the first respiratory movement data to obtain respiratory reference data; acquiring second respiratory movement data of the target object at the current detection moment; performing data statistical processing based on the first respiratory movement data and the second respiratory movement data to obtain a data statistical value of each dimension; determining breathing feature data based on the data statistical value and the second breathing motion data; and determining the breathing state of the target object at the current moment based on the breathing characteristic data and the breathing reference data. The breathing motion data of the target object is obtained based on the inertial measurement unit, the breathing state of the target object at the current moment is determined by weighting the breathing motion data, and the accuracy of breathing state detection can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to a breathing detection method, device, equipment and storage medium. Background Art

[0002] Respiration is an important physiological activity of the human body, and respiratory monitoring plays an important role in many fields such as medicine, health, and entertainment. In the prior art, the monitoring of human respiration mainly relies on image monitoring, and the respiratory state is judged by the image fluctuations in the monitoring device or the fluctuations of human respiration in the monitoring video. This method has the disadvantages of poor monitoring accuracy, the need to equip multiple monitoring devices, and dependence on shooting angles. Summary of the invention

[0003] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is to improve the accuracy and convenience of respiratory state detection.

[0004] In order to solve at least one of the technical problems mentioned above, the present invention discloses a breathing detection method, device, equipment and storage medium.

[0005] According to one aspect of the present disclosure, there is provided a breathing detection method, comprising:

[0006] Acquire first respiratory motion data of a target object within a first time period; the first respiratory motion data is acquired based on an inertial measurement unit disposed on the target object; the first respiratory motion data includes motion data of multiple dimensions;

[0007] Jointly processing motion data of multiple dimensions in the first respiratory motion data to obtain respiratory reference data of the target object in the first time period;

[0008] Acquire second respiratory motion data of the target object at a current detection time; the current detection time is a detection time after the first time period, and the second respiratory motion data includes motion data of multiple dimensions;

[0009] Performing data statistical processing based on the motion data of the first respiratory motion data and the second respiratory motion data in each dimension to obtain a data statistical value corresponding to each dimension;

[0010] Determining respiratory characteristic data of the target object based on the data statistics corresponding to each dimension and the second respiratory motion data;

[0011] The breathing state of the target object at the current detection moment is determined based on the breathing feature data and the breathing reference data.

[0012] In some possible embodiments, the jointly processing the motion data of multiple dimensions in the first respiratory motion data to obtain the respiratory reference data of the target object in the first time period includes:

[0013] Based on the motion data of the first respiratory motion data in each dimension, a data change value corresponding to each dimension is obtained; the data change value is the difference between the maximum value and the minimum value of the motion data in the same dimension;

[0014] Based on the data change value corresponding to each dimension, calculating the respiratory data weight of the corresponding dimension;

[0015] The breathing data weight of each dimension is determined as the breathing reference data of the target object in the first time period.

[0016] In some possible embodiments, the data statistics include the data mean and data variance of each dimension;

[0017] The determining, based on the data statistics corresponding to each dimension and the second respiratory motion data, the respiratory characteristic data of the target object includes:

[0018] Determine a respiratory data difference corresponding to each dimension based on the motion data of the second respiratory motion data in each dimension and the data average value of the corresponding dimension;

[0019] The ratio between the respiratory data difference of each dimension and the data variance of the corresponding dimension is calculated to obtain the respiratory feature data corresponding to each dimension of the target object.

[0020] In some possible embodiments, determining the breathing state of the target object at the current detection moment based on the breathing feature data and the breathing reference data includes:

[0021] Calculating the product of the breathing feature data of each dimension and the breathing reference data of the corresponding dimension to obtain a weighted feature value corresponding to each dimension of the target object;

[0022] Summing the weighted characteristic values ​​corresponding to each dimension to obtain a total breathing characteristic value of the target object at the current detection moment;

[0023] Based on the total value of the breathing feature, the breathing state of the target object at the current detection moment is determined.

[0024] In some possible embodiments, determining the breathing state of the target object at the current detection moment based on the total value of the breathing feature includes:

[0025] When the total value of the breathing feature is greater than the breathing feature threshold, determining that the target object is in an exhalation state at the current detection moment;

[0026] When the total breathing feature value is less than the breathing feature threshold, it is determined that the target object is in an inhalation state at the current detection moment.

[0027] In some possible embodiments, there are multiple inertial measurement units; the first respiratory motion data includes multiple groups of data corresponding to each inertial measurement unit; the second respiratory data includes multiple groups of data corresponding to each inertial measurement unit; and the method includes:

[0028] Determining measurement weight data for each inertial measurement unit; the measurement weight data is determined based on a measurement position of the inertial measurement unit on the target object;

[0029] Calculating a total value of the breathing characteristics associated with each of the inertial measurement units;

[0030] Determining a weighted total breathing feature value of each inertial measurement unit based on the measurement weight data of each inertial measurement unit and the total breathing feature value of the inertial measurement unit;

[0031] The breathing state of the target object is determined based on the weighted breathing feature sum value of each inertial measurement unit.

[0032] In some possible embodiments, the first time period includes a plurality of detection time nodes;

[0033] After acquiring the second respiratory motion data of the target object at the current detection moment, the method includes:

[0034] Based on the second respiratory motion data corresponding to the current detection moment and the respiratory motion data corresponding to the multiple adjacent detection time nodes before the current detection moment, the first respiratory motion data is updated to obtain updated first respiratory motion data; the number of detection time nodes corresponding to the updated first respiratory motion data is consistent with the number of detection time nodes included in the first time period.

[0035] In some possible embodiments, after acquiring the second respiratory motion data of the target object at the current detection moment, the method includes:

[0036] Calculate the minimum distance between the first respiratory motion data and the second respiratory motion data in each dimension;

[0037] When there is a minimum distance value in at least one dimension that is greater than a preset distance threshold, the first respiratory motion data is corrected.

[0038] In some possible embodiments, when there is a minimum distance value in at least one dimension greater than a preset distance threshold, correcting the first respiratory motion data includes:

[0039] Calculate the motion data of the second respiratory motion data in each dimension and the difference between the motion data of the corresponding dimension at the previous detection time node of the current detection moment to obtain a data offset value corresponding to each dimension;

[0040] The first respiratory motion data is corrected based on the motion data of the first respiratory motion data in each dimension and the data offset value corresponding to each dimension.

[0041] According to a second aspect of the present disclosure, a breathing detection device is provided, the device comprising:

[0042] A first data acquisition module is used to acquire first respiratory motion data of a target object within a first time period; the first respiratory motion data is acquired based on an inertial measurement unit arranged on the target object; the first respiratory motion data includes motion data of multiple dimensions;

[0043] a data weight determination module, configured to jointly process the motion data of multiple dimensions in the first respiratory motion data to obtain the respiratory reference data of the target object in the first time period;

[0044] A second data acquisition module is used to acquire second respiratory motion data of the target object at a current detection time; the current detection time is a detection time after the first time period, and the second respiratory motion data includes motion data of multiple dimensions;

[0045] A respiratory data statistics module, used for performing data statistics processing based on the motion data of the first respiratory motion data and the second respiratory motion data in each dimension to obtain a data statistical value corresponding to each dimension;

[0046] A breathing feature calculation module, used to determine the breathing feature data of the target object based on the data statistics corresponding to each dimension and the second respiratory motion data;

[0047] A breathing state determination module is used to determine the breathing state of the target object at the current detection moment based on the breathing characteristic data and the breathing reference data.

[0048] According to a third aspect of the present disclosure, an electronic device is provided, the device comprising a processor and a memory, the memory storing at least one instruction and at least one program, the at least one instruction and the at least one program being loaded and executed by the processor to implement the breathing detection method as described above.

[0049] According to a fourth aspect of the present disclosure, a computer storage medium is provided, in which at least one instruction and at least one program are stored, and the at least one instruction and the at least one program are loaded and executed by a processor to implement the breathing detection method as described above.

[0050] The implementation of the present invention has the following beneficial effects:

[0051] The present invention realizes breathing detection of the target object by arranging an inertial measurement unit on the body part of the target object, which can improve the convenience of breathing detection; before performing breathing detection, first breathing movement data within a period of time is collected to calculate the breathing reference data of the target object, which can realize personalized breathing detection of the target object; second breathing movement data at the current detection moment is obtained, and data statistics are calculated in combination with the first breathing movement data, and breathing characteristic data is calculated based on the data statistics, which can reduce the interference of data errors on the calculation results of breathing characteristic data, thereby improving the accuracy of breathing detection results; the breathing characteristic data and the breathing reference data are combined to confirm the breathing state of the target object at the current detection moment, which can improve the accuracy of breathing detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a flow chart corresponding to the breathing detection method provided in an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of a corresponding flow chart for determining respiratory reference data provided by an embodiment of the present invention;

[0055] Figure 3 A schematic diagram of a corresponding process for determining respiratory characteristic data provided by an embodiment of the present invention;

[0056] Figure 4 A schematic diagram of a corresponding process for determining a respiratory state provided in an embodiment of the present invention;

[0057] Figure 5A schematic diagram of a flow chart corresponding to another breathing detection method provided by an embodiment of the present invention;

[0058] Figure 6 A schematic diagram of a process flow corresponding to the detection position determination provided by an embodiment of the present invention;

[0059] Figure 7 A schematic diagram of a process flow corresponding to respiratory data correction provided by an embodiment of the present invention;

[0060] Figure 8 A schematic diagram of a process flow corresponding to breathing detection provided in a specific embodiment of the present invention;

[0061] Fig. 9 A schematic diagram of the structure of a breathing detection device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0064] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0065] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0066] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0067] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0068] Figure 1 The flowchart corresponding to the breathing detection method provided by the embodiment of the present invention is shown; the execution subject may be a breathing detection system that can be equipped with an inertial measurement unit and can execute the breathing detection method; please refer to Figure 1 , a breathing detection method, comprising:

[0069] Step S101: acquiring first respiratory motion data of a target object within a first time period; the first respiratory motion data is acquired based on an inertial measurement unit arranged on the target object; the first respiratory motion data includes motion data of multiple dimensions;

[0070] In a specific embodiment, in order to improve the correlation between breathing detection and users and realize personalized breathing detection for different users, before detecting the breathing state of the user at a certain moment, it is necessary to first obtain the breathing reference data of the user, and combine the breathing movement data with the breathing reference data to judge the breathing state of the user; the breathing reference data can be manually input by the user according to his own condition, or it can be pre-calculated according to different users before breathing detection; to calculate the breathing reference data, it is necessary to obtain the breathing movement data of the user within a preset time period, that is, to obtain the first breathing movement data of the target object within the first time period.

[0071] Specifically, the inertial measurement unit can be set at any body part of the target user, such as the head, chest and abdomen, and the inertial measurement unit is used to obtain and save the respiratory motion data; the first respiratory motion data includes motion data of multiple dimensions, and the motion data can be position data or speed data. In the present embodiment, the respiratory motion data is position data; the multiple dimensions can be three-dimensional, X represents the dimension corresponding to the left and right direction, Y represents the dimension corresponding to the front and back direction, and Z represents the dimension corresponding to the up and down direction; the motion data of multiple dimensions in the first time period is obtained, that is, multiple groups (X, Y, Z) are obtained, and the data recording frequency can be 30Hz-90Hz, wherein the origin is (0,0,0), and the origin can be selected at any point in the space, and the position determination of the origin is not limited in the embodiment of the present invention.

[0072] Step S102: jointly processing the motion data of multiple dimensions in the first respiratory motion data to obtain respiratory reference data of the target object in the first time period;

[0073] In a specific embodiment, after obtaining multiple groups (X, Y, Z), determine in which direction the target object changes more obviously during breathing according to the multiple groups (X, Y, Z) data, and assign a higher weight factor to the direction with obvious changes, that is, calculate breathing reference data of different dimensions according to the multiple groups (X, Y, Z), and the breathing reference data is represented by W, where W includes Wx, Wy and Wz. For example, when user 1 breathes, the head has obvious periodic movement in the Z direction, the movement in the x direction is smaller than the change in the Z direction, and there is basically no movement in the Y direction. Therefore, a higher weight factor Wz is assigned to the breathing of user 1 in the Z direction, that is, Wz>Wx>Wy.

[0074] Step S103: acquiring second respiratory motion data of the target object at a current detection time; the current detection time is a detection time after the first time period, and the second respiratory motion data includes motion data of multiple dimensions;

[0075] In a specific embodiment, after confirming the breathing characteristic data of the target object, in order to detect the breathing state of the target object at the current detection time, it is necessary to obtain a set of breathing motion data (Xm, Ym, Zm) of the target object, where m represents the current detection time, that is, the second breathing motion data of the target object at the current detection time is obtained; the second breathing motion data includes motion data of multiple dimensions, and the motion data can be position data or speed data. In this embodiment, the breathing motion data is position data; the current detection time can be any time after the first time period, that is, the current detection time can be any time after confirming the breathing characteristic data of the target object.

[0076] Step S104: performing data statistical processing based on the motion data of the first respiratory motion data and the second respiratory motion data in each dimension to obtain a data statistical value corresponding to each dimension;

[0077] In a specific embodiment, after obtaining the second respiratory motion data (Xm, Ym, Zm) of the target object at the current detection time, it is necessary to calculate the mean and variance of each dimension in combination with the first respiratory motion data, that is, calculate the mean μ and variance σ of (Xm, Ym, Zm) and multiple groups (X, Y, Z); the mean μ includes μ x , μ y and μ z , the variance σ includes σ x , σ y and σ z .

[0078] in

[0079] Specifically, before calculating the mean μ and the variance σ, the second respiratory motion data (Xm, Ym, Zm) needs to be processed, and the data processing may be filtering processing and / or smoothing processing; the filtering processing utilizes a Butterworth low-pass filter to filter the data, thereby filtering out the noise caused by non-respiratory motion, the normal breathing rate is 12-20 times / minute, and the cutoff frequency of the low-pass filter is set to 0.5Hz; the smoothing processing is: setting a window value, and smoothing the data, and the smoothing processing can be implemented by a weighted sliding average method; the embodiment of the present invention does not make any special limitation on the data processing method of the second respiratory motion data, and any processing method that can eliminate data deviation can be used.

[0080] In a specific embodiment, the multiple groups (X, Y, Z) in the first respiratory motion data may include 7 groups of motion data, including (x 1 ,y 1 ,z 1 )、(x 2 ,y 2 ,z 2 )···to(x 7 ,y 7 ,z 7 ), the second respiratory motion data is (x 0 ,y 0 ,z 0 ), with a mean value of μ 1 , with variance σ 1 .

[0081]

[0082]

[0083]

[0084]

[0085]

[0086] Step S105: determining the respiratory characteristic data of the target object based on the data statistics corresponding to each dimension and the second respiratory motion data;

[0087] In a specific embodiment, based on the second respiratory motion data (Xm, Ym, Zm), the mean μ and the variance σ, the respiratory characteristic data in the X direction, the respiratory characteristic data in the Y direction and the respiratory characteristic data in the Z direction of the target object at the current detection moment are calculated respectively, and the respiratory characteristic data is represented by Q, where Q includes Qx, Qy and Qz.

[0088] Step S106: Determine the breathing state of the target object at the current detection moment based on the breathing feature data and the breathing reference data.

[0089] In a specific embodiment, the breathing state of the target object at the current detection moment is determined based on the above-mentioned breathing reference data W and breathing characteristic data Q.

[0090] In an embodiment of the present invention, the present invention realizes breathing detection of the target object by setting an inertial measurement unit on the body part of the target object, which can improve the convenience of breathing detection; before performing breathing detection, first breathing movement data within a period of time is collected to calculate the breathing reference data of the target object, which can realize personalized breathing detection of the target object; second breathing movement data at the current detection moment is obtained, and data statistics are calculated in combination with the first breathing movement data, and breathing characteristic data is calculated based on the data statistics, which can reduce the interference of data errors on the calculation results of breathing characteristic data, thereby improving the accuracy of breathing detection results; the breathing characteristic data and the breathing reference data are combined to confirm the breathing state of the target object at the current detection moment, which can improve the accuracy of breathing detection.

[0091] Figure 2 A schematic diagram of a corresponding flow chart for determining respiratory reference data provided by an embodiment of the present invention; Figure 2 As shown, the joint processing of the motion data of multiple dimensions in the first respiratory motion data to obtain the respiratory reference data of the target object in the first time period includes:

[0092] Step S201: based on the motion data of each dimension of the first respiratory motion data, obtaining a data change value corresponding to each dimension; the data change value is the difference between the maximum value and the minimum value of the motion data in the same dimension;

[0093] In a specific embodiment, since the breathing reference data W is used to represent the variation range of the user's breathing in a certain dimension, to calculate the breathing reference data W, it is necessary to calculate the data variation value of each dimension based on multiple groups (X, Y, Z) in the first respiratory motion data, and the data variation value is represented by R, and R includes Rx, Ry and Rz;

[0094] Where Rx = X max -X min ; Ry=Y max -Y min ; Rz=Z max -Z min .

[0095] Step S202: Calculating the respiratory data weight of the corresponding dimension based on the data change value corresponding to each dimension;

[0096] In a specific embodiment, the breathing data weight of the target user in the X direction is calculated according to the data change value R. Weight of breathing data in the Y direction And the breathing data weight in the Z direction

[0097] Step S203: Determine the breathing data weight of each dimension as breathing reference data of the target object in the first time period.

[0098] In a specific embodiment, the breathing data weight is the breathing reference data W.

[0099] in And Wx+Wy+Wz=1.

[0100] In an embodiment of the present invention, the breathing weight data is calculated to determine the breathing characteristic data, and the breathing characteristic data can reflect the change range of the user's breathing during the breathing process. The breathing state is determined according to the breathing change range, which can improve the accuracy of breathing detection.

[0101] Figure 3 A schematic diagram of a corresponding flow chart for determining respiratory characteristic data provided by an embodiment of the present invention; Figure 3 As shown, the determining of the respiratory characteristic data of the target object based on the data statistics corresponding to each dimension and the second respiratory motion data includes:

[0102] Step S301: determining a respiratory data difference corresponding to each dimension based on the motion data of the second respiratory motion data in each dimension and the data average value of the corresponding dimension;

[0103] In a specific embodiment, the breathing data difference Xm-μx in the X direction and the breathing data difference Ym-μx in the Y direction of the target object at the current detection time are calculated according to the second respiratory motion data (Xm, Ym, Zm) and the mean μ. y And the breathing data difference Zm-μ in the Z direction z .

[0104] Step S302: Calculate the ratio between the respiratory data difference of each dimension and the data variance of the corresponding dimension to obtain the respiratory feature data corresponding to each dimension of the target object.

[0105] In a specific embodiment, the breathing characteristic data Qx in the X direction, the breathing characteristic data Qy in the Y direction, and the breathing characteristic data Qz in the Z direction of the target object at the current detection moment are calculated according to the breathing data difference and variance σ in each direction.

[0106] in

[0107] Specifically, Q>0, i.e. Qx>0 and / or Qy>0 and / or Qz>0, represents a first breathing state, which includes the exhalation state and may also include the moment at the end of exhalation and the beginning of inhalation; Q<0, i.e. Qx<0 and / or Qy<0 and / or Qz<0, represents a second breathing state, which includes the inhalation state and may also include the moment at the end of inhalation and the beginning of respiration.

[0108] In another embodiment, the breathing characteristic data Q may also be calculated using the following formula:

[0109] First, determine the maximum data value L and the minimum data value T of each dimension in the first respiratory motion data and the second respiratory motion data; the maximum data value L includes Lx, Ly and Lz, and the minimum data value T includes Tx, Ty and Tz;

[0110]

[0111] Specifically, Q>1 / 2, i.e. Qx>1 / 2 and / or Qy>1 / 2 and / or Qz>1 / 2, represents a first breathing state, which includes the exhalation state and may also include the moment at the end of exhalation and the beginning of inhalation; Q<1 / 2, i.e. Qx<1 / 2 and / or Qy<1 / 2 and / or Qz<1 / 2, represents a second breathing state, which includes the inhalation state and may also include the moment at the end of inhalation and the beginning of breathing.

[0112] In the embodiment of the present invention, the breathing characteristic data is calculated according to the variance and the mean, which can eliminate the interference of error data and abnormal data on breathing detection, thereby improving the accuracy of breathing detection.

[0113] Figure 4 FIG. 2 is a schematic diagram showing a corresponding flow chart of determining the respiratory state provided by an embodiment of the present invention; Figure 4 As shown, the determining the breathing state of the target object at the current detection moment based on the breathing characteristic data and the breathing reference data includes:

[0114] Step S401: Calculate the product of the breathing feature data of each dimension and the breathing reference data of the corresponding dimension to obtain the weighted feature value corresponding to each dimension of the target object;

[0115] In a specific embodiment, the weighted characteristic value of the corresponding dimension is calculated according to the respiratory feature data and respiratory reference data corresponding to each dimension, that is, Q*W is calculated according to Q and W. Specifically, Q*W includes Qx*Wx, Qy*Wy and Qz*Wz.

[0116] Step S402: summing the weighted characteristic values ​​corresponding to each dimension to obtain a total breathing characteristic value of the target object at the current detection moment;

[0117] In a specific embodiment, each weighted characteristic value is summed to obtain the total breathing characteristic value at the current detection moment, and the total breathing characteristic value is represented by S, where S=Qx*Wx+Qy*Wy+Qz*Wz.

[0118] Step S403: Determine the breathing state of the target object at the current detection moment based on the total value of the breathing feature.

[0119] In a specific embodiment, the breathing characteristic data Q can characterize the breathing state of a certain dimension of the target object, that is, Qx is used to represent the breathing state of the target object in the X direction, Qy is used to represent the breathing state of the target object in the Y direction, and Qz is used to represent the breathing state of the target object in the Z direction; since each user has different breathing habits, judging the breathing state of the target object according to a certain dimension / direction cannot obtain an accurate judgment result, so it is necessary to combine the breathing habits of the target object, that is, the above-mentioned predetermined breathing reference data W, to determine the breathing state of the target object, which can improve the accuracy of breathing state detection.

[0120] In an embodiment of the present invention, the breathing feature data of each dimension and the breathing reference data are combined to further judge the breathing state of the target object at the current detection moment. The breathing characteristics of the target user in each dimensional direction can be combined to improve the accuracy of the detection result, and improve the correlation between the breathing detection and the target object, thereby realizing personalized breathing detection for different users and improving the matching degree between the detection result and the user.

[0121] Further, determining the breathing state of the target object at the current detection moment based on the total value of the breathing feature includes:

[0122] When the total value of the breathing feature is greater than the breathing feature threshold, determining that the target object is in an exhalation state at the current detection moment;

[0123] In a specific embodiment, the breathing characteristic threshold is 0, and the total breathing characteristic value is greater than the breathing characteristic threshold, that is, S>0, indicating an exhalation state, that is, a first breathing state. The first breathing state may also include the moment when exhalation ends and inhalation begins.

[0124] When the total breathing feature value is less than the breathing feature threshold, it is determined that the target object is in an inhalation state at the current detection moment.

[0125] Specifically, if the total value of the breathing feature is less than the breathing feature threshold value, ie, S<0, it indicates an inhalation state, ie, a second breathing state. The second breathing state may also include the moment when inhalation ends and breathing begins.

[0126] In the embodiment of the present invention, the breathing state at the current detection moment is judged by the relationship between the total breathing feature value and the breathing feature threshold, which can reduce the breathing detection differences caused by different users and realize standardized breathing detection.

[0127] Figure 5 A flow chart corresponding to another breathing detection method provided by an embodiment of the present invention; wherein the number of the inertial measurement units is multiple; the first respiratory motion data includes multiple groups of data corresponding to each inertial measurement unit; the second respiratory data includes multiple groups of data corresponding to each inertial measurement unit; Figure 5 As shown, the method includes:

[0128] Step S501: determining measurement weight data of each inertial measurement unit; the measurement weight data is determined based on the measurement position of the inertial measurement unit on the target object;

[0129] In a specific embodiment, in order to further improve the accuracy of breathing judgment, multiple inertial measurement units can be set on the target object. Since users have different breathing methods, different breathing methods will produce different position changes in the three-dimensional direction of the user's body parts. Therefore, when judging the breathing state, the inertial measurement units in different parts should also be assigned different weights, that is, measurement weight data H. The determination of the measurement weight data follows the size of the measurement weight data based on the change amplitude, that is, in a set of change amplitude data, the measurement weight data corresponding to the inertial measurement unit with a large change amplitude is greater than the inertial measurement unit with a small change amplitude. In addition, the method for determining the measurement weight data is not limited in the embodiment of the present invention.

[0130] Step S502: Calculating the total value of the breathing characteristics of each inertial measurement unit;

[0131] In a specific embodiment, for each inertial measurement unit arranged at different parts of the body, the total breathing characteristic value S is calculated according to the above steps S101 to S106; the breathing state of the target object detected at different positions can be obtained according to the total breathing characteristic value of each inertial measurement unit.

[0132] Step S503: determining a weighted total breathing feature value of each inertial measurement unit based on the measurement weight data of each inertial measurement unit and the total breathing feature value of the inertial measurement unit;

[0133] In a specific embodiment, the weighted total breathing feature value is the product of the measurement weight data and the total breathing feature value, H*S.

[0134] Step S504: Determine the breathing state of the target object based on the total weighted breathing feature value of each inertial measurement unit.

[0135] In a specific embodiment, the weighted breathing feature total value S 总 That is, the sum of H*S of each inertial measurement unit is combined with the measurement weight data of each inertial measurement unit on the basis of the total value of the breathing feature to further judge the breathing state of the target, which can improve the accuracy of breathing detection.

[0136] Specifically, the number of inertial measurement units may be 4, which are respectively set on the head, chest, abdomen and hand of the target object, and their measurement weight data correspond to H 1 , H 2 , H 3 and H 4 , the total value of breathing characteristics corresponds to S 1 , S 2 , S 3 and S 4 , S总 =H 1 *S 1 +H 2 *S 2 +H 3 *S 3 +H 4 *S 4 , according to S 总 Determine the breathing state of the target object, for example, in S 总 If it is greater than 0, the target object is judged to be in the first breathing state, S 总 When it is less than 0, the target object is judged to be in the second breathing state. 总 The method for determining the respiratory state is not limited in the embodiment of the present invention and can be determined according to actual conditions.

[0137] In an embodiment of the present invention, multiple inertial measurement units are arranged at different parts of the user's body, and the user's breathing state is judged by combining data from the multiple inertial measurement units, which can further improve the accuracy of breathing detection.

[0138] Furthermore, the first time period includes a plurality of detection time nodes;

[0139] After acquiring the second respiratory motion data of the target object at the current detection moment, the method includes:

[0140] Based on the second respiratory motion data corresponding to the current detection moment and the respiratory motion data corresponding to the multiple adjacent detection time nodes before the current detection moment, the first respiratory motion data is updated to obtain updated first respiratory motion data; the number of detection time nodes corresponding to the updated first respiratory motion data is consistent with the number of detection time nodes included in the first time period.

[0141] In a specific embodiment, the pre-acquired first respiratory motion data includes multiple groups of motion data of multiple dimensions, that is, multiple groups (X, Y, Z), and each group (X, Y, Z) corresponds to a detection time node; the first respiratory motion data is updated based on the newly acquired second respiratory motion data corresponding to the current detection moment, specifically: the first acquired motion data in the first respiratory motion data is deleted, and the second respiratory motion data is added to obtain the updated first respiratory motion data; for the update of the first respiratory motion data, it is necessary to always keep the number of detection time nodes corresponding to the updated first respiratory motion data consistent with the number of detection time nodes included in the first time period.

[0142] Specifically, as described in the above embodiment, the multiple groups (X, Y, Z) in the first respiratory motion data may include 7 groups of motion data, including (x1 ,y 1 ,z 1 )、(x 2 ,y 2 ,z 2 )···to(x 7 ,y 7 ,z 7 ), (x 1 ,y 1 ,z 1 ) corresponds to the detection time node t 1 ,(x 2 ,y 2 ,z 2 ) corresponds to the detection time node t 2 ···To(x 7 ,y 7 ,z 7 ) corresponds to the detection time node t 7 , the time sequence is t 1 to 7 ; The second respiratory motion data is (x 0 ,y 0 ,z 0 ), the corresponding detection time node is t 0 ; and t 0 Time is t 7 The next moment of the moment; get (x 0 ,y 0 ,z 0 ) and then delete the first respiratory motion data. 1 The motion data corresponding to the moment (x 1 ,y 1 ,z 1 ), and add t 0 The second respiratory motion data corresponding to the moment (x 0 ,y 0 ,z 0 ), obtain the updated first respiratory motion data;

[0143] The updated first respiratory motion data includes seven groups of motion data, which are arranged in chronological order as follows: 2 ,y 2 ,z 2 ),(x 3 ,y 3 ,z 3 ),(x 4 ,y 4 ,z 4 ),(x 5 ,y 5 ,z),(x 6 ,y 6 ,z6 ),(x 7 ,y 7 ,z 7 ),(x 0 ,y 0 ,z 0 ).

[0144] In the embodiment of the present invention, the first respiratory motion data is updated in real time according to the first-in-first-out principle, so as to obtain mean data and variance data that are closer to the current respiratory state, so as to improve the real-time performance and accuracy of respiratory detection.

[0145] Figure 6 FIG. 2 is a schematic diagram showing a flow chart corresponding to the detection position determination provided by an embodiment of the present invention; Figure 6 As shown, after obtaining the second respiratory motion data of the target object at the current detection moment, the method includes:

[0146] Step S601: calculating the minimum distance between the first respiratory motion data and the second respiratory motion data in each dimension;

[0147] In a specific embodiment, the distances corresponding to each dimension between the second respiratory motion data (Xm, Ym, Zm) and multiple groups (X, YZ) of the first respiratory motion data are calculated respectively, so as to determine the minimum distance between the first respiratory motion data and the second respiratory motion data in each dimension, and determine whether the position deviation of the target object during breathing obviously exceeds the normal respiratory activity.

[0148] Step S602: when there is a minimum distance value in at least one dimension that is greater than a preset distance threshold, correct the first respiratory motion data.

[0149] In a specific embodiment, the preset distance threshold can be set in advance, and the preset distance threshold can be 0.01m. When the minimum distance value of at least one dimension is greater than the preset distance threshold, it is determined that the target object has undergone a position shift during the breathing process due to an abnormal breathing process, and the first respiratory motion data needs to be modified.

[0150] In the embodiment of the present invention, when the user moves the body violently during breathing, the detection of the breathing state may be biased, and therefore it is necessary to correct and adjust the measurement position according to the breathing data to improve the accuracy of breathing detection.

[0151] Figure 7 FIG. 2 is a schematic diagram showing a flow chart corresponding to the respiratory data correction provided by an embodiment of the present invention; Figure 7 As shown, in the case where there is a minimum distance value of at least one dimension greater than a preset distance threshold, correcting the first respiratory motion data includes:

[0152] Step S701: calculating the motion data of the second respiratory motion data in each dimension and the difference between the motion data of the corresponding dimension at the previous detection time node of the current detection moment, and obtaining the data offset value corresponding to each dimension;

[0153] In a specific embodiment, the first respiratory motion data includes multiple groups (X, Y, Z), and the second respiratory motion data is (Xm, Ym, Zm), where m is the current detection moment, and the detection time node corresponding to the last group of motion data in the first respiratory motion data is the previous moment of the current detection moment, represented by a, that is, the last group of motion data in the first respiratory motion data is (Xa, Ya, Za); when it is determined that the respiratory position of the target object is significantly offset, it is necessary to calculate the data offset Δ of each dimension, Δ includes ΔX, ΔY and ΔZ, so as to correct and adjust the first respiratory motion data; wherein, ΔX=Xm-Xa, ΔY=Ym-Ya, ΔZ=Zm-Za.

[0154] Specifically, the data correction method adopted in the embodiment of the present invention selects the motion data corresponding to a moment closest to the current detection moment, and calculates the difference between the motion data and the motion data corresponding to the current detection moment. This can ensure that the offset of the target object during the breathing process is minimized to the greatest extent. The data offset calculated between the two motion data closest in time is more accurate than other data offset calculation methods.

[0155] Step S702: correcting the first respiratory motion data based on the motion data of the first respiratory motion data in each dimension and the data offset value corresponding to each dimension.

[0156] In a specific embodiment, data offsets in corresponding dimensions are added to multiple groups (X, Y, Z) in the first respiratory motion data respectively, so as to achieve correction of the first respiratory motion data. The corrected first respiratory motion data includes multiple groups with positions of (X+ΔX, Y+ΔY, Z+ΔZ).

[0157] In another specific embodiment, the first respiratory motion data includes multiple groups (X, Y, Z), and the second respiratory motion data is (Xm, Ym, Zm), where m is the current detection time, and the detection time node corresponding to the last group of motion data in the first respiratory motion data is the previous moment of the current detection time, represented by a, that is, the last group of motion data in the first respiratory motion data is (Xa, Ya, Za); the calculation of the corresponding data offset Δ can also be carried out by the following method:

[0158] Δx=x m -μ x ,Δy=ym -μ x ,Δz=z m -μ z ; where μ x ,μ y and μ z is the mean value of the first respiratory motion data and the second respiratory motion data in each dimension;

[0159] or in as well as is the mean value of the respiratory motion data in each dimension at the previous moment.

[0160] Since multiple groups of data in the first respiratory motion data are used in the calculation of the data offset, but the respiratory position of the target object at the current detection moment has obviously shifted, the result obtained by this data offset calculation method is less accurate than the data offset calculation method used in the embodiment of the present invention.

[0161] In another specific embodiment, the method for correcting the first respiratory motion data further includes:

[0162] When it is determined that the target object has a position shift due to an abnormal breathing process during the breathing process, the breathing detection of the target object is suspended, and according to the above steps S101-S106, a set of first breathing motion data that matches the current position of the target object and the second breathing motion data corresponding to the time to be detected are reacquired, and the breathing state of the target object at the time to be detected is judged by the reacquired first breathing motion data and the second breathing motion data. This correction method will cause the breathing detection to be interrupted, and the breathing detection needs to be restarted after a preset time, which will bring a poor user experience.

[0163] In an embodiment of the present invention, when the second respiratory motion data is offset beyond a threshold value compared with the first respiratory motion data, it is necessary to calculate the data offset and correct the first respiratory motion data based on the data offset to ensure the real-time and accuracy of the first respiratory motion data, thereby improving the real-time and accuracy of respiratory detection.

[0164] Figure 8 A schematic diagram of a process flow corresponding to a breathing detection provided by a specific embodiment of the present invention; Figure 8As shown, in a specific embodiment, multiple groups of breathing position data of the target user within a preset time period are obtained, each group of breathing position data includes position data in a three-dimensional direction; the multiple groups of breathing position data are stored in a data cache group; the breathing weight factor of the target user in the three-dimensional direction is determined according to the multiple groups of breathing position data; the breathing position data at the current moment is obtained and stored in the data cache group, the breathing position data at the current moment includes position data in the three-dimensional direction; the data mean and data variance of each dimension in the data cache group are calculated, that is, the data mean and data variance corresponding to each dimension of the multiple groups of breathing position data and the breathing position data at the current moment are calculated, the breathing index in each dimension at the current moment is determined according to the data mean and data variance, and the breathing index of each dimension is combined with the corresponding breathing weight factor to determine the breathing state of the target user at the current moment.

[0165] In another specific embodiment, the first respiratory motion data and the second respiratory motion data may further include speed data of multiple dimensions, that is, the first respiratory motion data includes multiple groups (Vx, Vy, Vz), and the second respiratory motion data includes Where n is the current detection time; first calculate the data change value R and the breathing weight factor, that is, the breathing feature data W;

[0166]

[0167]

[0168] According to the respiratory characteristic data W and the second respiratory motion data Calculate the mean μ v and variance σ v , where μ v include as well as σ v include as well as

[0169]

[0170] According to the mean μ v and variance σ v Determine the breathing index of each dimension, i.e., breathing feature data Q;

[0171]

[0172] Calculate the total breathing characteristic value S according to the breathing reference data W and the breathing characteristic data Q;

[0173]

[0174] The total breathing characteristic value S is compared with the breathing characteristic threshold, where the breathing characteristic threshold is 0. The total breathing characteristic value is greater than the breathing characteristic threshold, that is, S>0, indicating an exhalation state, that is, a first breathing state, and the first breathing state may also include the moment when exhalation ends and inhalation begins; the total breathing characteristic value is less than the breathing characteristic threshold, that is, S<0, indicating an inhalation state, that is, a second breathing state, and the second breathing state may also include the moment when inhalation ends and exhalation begins.

[0175] In another specific embodiment, the respiratory state can be determined in combination with the position data and the speed data. Specifically, after respectively acquiring the position data and the speed data, the weight Wp of the position data and the weight Wv of the speed data are determined according to the influence of the speed and the position on the respiratory state detection, and the respiratory weight data and the respiratory characteristic data of the position data, as well as the respiratory weight data and the respiratory characteristic data of the speed data are calculated respectively. Then, the total respiratory characteristic value S is calculated as follows:

[0176]

[0177] The embodiment of the present invention also provides a breathing detection device, such as Fig. 9 As shown, the device comprises:

[0178] A first data acquisition module 901 is used to acquire first respiratory motion data of a target object within a first time period; the first respiratory motion data is acquired based on an inertial measurement unit arranged on the target object; the first respiratory motion data includes motion data of multiple dimensions;

[0179] A data weight determination module 902 is used to jointly process the motion data of multiple dimensions in the first respiratory motion data to obtain the respiratory reference data of the target object in the first time period;

[0180] A second data acquisition module 903 is used to acquire second respiratory motion data of the target object at a current detection time; the current detection time is a detection time after the first time period, and the second respiratory motion data includes motion data of multiple dimensions;

[0181] A respiratory data statistics module 904 is used to perform data statistics processing based on the motion data of the first respiratory motion data and the second respiratory motion data in each dimension to obtain a data statistical value corresponding to each dimension;

[0182] A breathing feature calculation module 905, configured to determine the breathing feature data of the target object based on the data statistics corresponding to each dimension and the second respiratory motion data;

[0183] The breathing state determination module 906 is used to determine the breathing state of the target object at the current detection moment based on the breathing feature data and the breathing reference data.

[0184] In some other embodiments, the data weight determination module 902 further includes:

[0185] A data change value determination module, used to obtain a data change value corresponding to each dimension based on the motion data of the first respiratory motion data in each dimension; the data change value is the difference between the maximum value and the minimum value of the motion data in the same dimension;

[0186] A first data calculation module, configured to calculate the respiratory data weight of the corresponding dimension based on the data change value corresponding to each dimension;

[0187] The breathing reference data determination module is used to determine the breathing data weight of each dimension as the breathing reference data of the target object in the first time period.

[0188] In some other embodiments, the breathing feature calculation module 905 further includes:

[0189] A data difference determination module, used to determine the respiratory data difference corresponding to each dimension based on the motion data of the second respiratory motion data in each dimension and the data average value of the corresponding dimension;

[0190] The second data calculation module is used to calculate the ratio between the respiratory data difference of each dimension and the data variance of the corresponding dimension, so as to obtain the respiratory feature data corresponding to each dimension of the target object.

[0191] In some other embodiments, the respiratory state determination module 906 further includes:

[0192] A weighted eigenvalue determination module, used to calculate the product between the breathing feature data of each dimension and the breathing reference data of the corresponding dimension, to obtain the weighted eigenvalue corresponding to each dimension of the target object;

[0193] A third data calculation module is used to sum the weighted characteristic values ​​corresponding to each dimension to obtain a total breathing characteristic value of the target object at the current detection moment;

[0194] The first determination module is used to determine the breathing state of the target object at the current detection moment based on the total value of the breathing feature.

[0195] In some other embodiments, the first determining module further includes:

[0196] An exhalation state determination module, used for determining that the target object is in an exhalation state at a current detection moment when the total value of the respiratory characteristic is greater than a respiratory characteristic threshold;

[0197] The inhalation state determination module is used to determine that the target object is in the inhalation state at the current detection moment when the total value of the breathing feature is less than the breathing feature threshold.

[0198] In some other embodiments, the device further comprises:

[0199] A measurement weight determination module, used to determine measurement weight data of each inertial measurement unit; the measurement weight data is determined based on the measurement position of the inertial measurement unit on the target object;

[0200] A fourth data calculation module, used for calculating the total value of the breathing characteristics of each inertial measurement unit;

[0201] A weighted total value determination module, configured to determine a weighted total breathing feature value of each inertial measurement unit based on the measurement weight data of each inertial measurement unit and the total breathing feature value of the inertial measurement unit;

[0202] The second determination module is used to determine the breathing state of the target object based on the total value of the weighted breathing characteristics of each inertial measurement unit.

[0203] In some other embodiments, the device further comprises:

[0204] A respiratory data correction module is used to update the first respiratory motion data based on the second respiratory motion data corresponding to the current detection moment and the respiratory motion data corresponding to multiple adjacent detection time nodes before the current detection moment, so as to obtain updated first respiratory motion data; the number of the detection time nodes corresponding to the updated first respiratory motion data is consistent with the number of the detection time nodes included in the first time period.

[0205] In some other embodiments, the device further comprises:

[0206] A distance determination module, used for calculating a minimum distance between the first respiratory motion data and the second respiratory motion data in each dimension;

[0207] The position error correction module is used to correct the first respiratory motion data when there is a minimum distance value in at least one dimension that is greater than a preset distance threshold.

[0208] In some other embodiments, the position error correction module further includes:

[0209] An offset value determination module is used to calculate the difference between the motion data of the second respiratory motion data in each dimension and the motion data of the corresponding dimension at the previous detection time node of the current detection moment, so as to obtain a data offset value corresponding to each dimension;

[0210] The data correction module is used to correct the first respiratory motion data based on the motion data of the first respiratory motion data in each dimension and the data offset value corresponding to each dimension.

[0211] The device and method embodiments in the device embodiment are based on the same inventive concept and are used to implement the above-mentioned breathing detection method.

[0212] An embodiment of the present invention also provides a breathing detection device, which includes: a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement a breathing detection method as described in any one of the method embodiments.

[0213] An embodiment of the present invention also provides a storage medium, which can be set in a server to store at least one instruction, at least one program, a code set or an instruction set for implementing a data management method in a method embodiment. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement a breathing detection method as described in any one of the method embodiments.

[0214] Optionally, in an embodiment of the present invention, the above-mentioned storage medium may be located in at least one of a plurality of network servers of a computer network. Optionally, in an embodiment of the present invention, the above-mentioned storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0215] It can be seen from the embodiments provided by the present invention that the present invention realizes breathing detection of the target object by setting an inertial measurement unit on the body part of the target object, thereby improving the convenience of breathing detection; before performing breathing detection, first breathing movement data within a period of time is collected to calculate the breathing reference data of the target object, thereby realizing personalized breathing detection of the target object; second breathing movement data at the current detection moment is obtained, and data statistics are calculated in combination with the first breathing movement data, and breathing characteristic data is calculated based on the data statistics, thereby reducing the interference of data errors on the calculation results of breathing characteristic data, thereby improving the accuracy of breathing detection results; the breathing characteristic data and the breathing reference data are combined to confirm the breathing state of the target object at the current detection moment, thereby improving the accuracy of breathing detection.

[0216] It should be noted that various embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used in this article is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A breathing detection method, characterized in that: The method comprises: Acquire first respiratory motion data of a target object within a first time period; the first respiratory motion data is acquired based on an inertial measurement unit disposed on the target object; the first respiratory motion data includes motion data of multiple dimensions; Jointly processing motion data of multiple dimensions in the first respiratory motion data to obtain respiratory reference data of the target object in the first time period; Acquire second respiratory motion data of the target object at a current detection time; the current detection time is a detection time after the first time period, and the second respiratory motion data includes motion data of multiple dimensions; Performing data statistical processing based on the motion data of the first respiratory motion data and the second respiratory motion data in each dimension to obtain a data statistical value corresponding to each dimension; Determining respiratory characteristic data of the target object based on the data statistics corresponding to each dimension and the second respiratory motion data; Based on the breathing characteristic data and the breathing reference data, the breathing state of the target object at the current detection moment is determined.

2. A breathing detection method according to claim 1, characterized in that: The step of jointly processing the motion data of multiple dimensions in the first respiratory motion data to obtain the respiratory reference data of the target object in the first time period includes: Based on the motion data of the first respiratory motion data in each dimension, a data change value corresponding to each dimension is obtained; the data change value is the difference between the maximum value and the minimum value of the motion data in the same dimension; Based on the data change value corresponding to each dimension, calculating the respiratory data weight of the corresponding dimension; The breathing data weight of each dimension is determined as the breathing reference data of the target object in the first time period.

3. A breathing detection method according to claim 1, characterized in that: The data statistics include the data mean and data variance of each dimension; The determining the respiratory characteristic data of the target object based on the data statistics corresponding to each dimension and the second respiratory motion data includes: Determine a respiratory data difference corresponding to each dimension based on the motion data of the second respiratory motion data in each dimension and the data average value of the corresponding dimension; The ratio between the respiratory data difference of each dimension and the data variance of the corresponding dimension is calculated to obtain the respiratory feature data corresponding to each dimension of the target object.

4. A breathing detection method according to claim 3, characterized in that: The step of determining the breathing state of the target object at the current detection moment based on the breathing characteristic data and the breathing reference data includes: Calculating the product of the breathing feature data of each dimension and the breathing reference data of the corresponding dimension to obtain a weighted feature value corresponding to each dimension of the target object; Summing the weighted characteristic values ​​corresponding to each dimension to obtain a total breathing characteristic value of the target object at the current detection moment; Based on the total value of the breathing feature, the breathing state of the target object at the current detection moment is determined.

5. A breathing detection method according to claim 4, characterized in that: The determining, based on the total value of the breathing feature, the breathing state of the target object at the current detection moment includes: When the total value of the breathing feature is greater than the breathing feature threshold, determining that the target object is in an exhalation state at the current detection moment; When the total breathing feature value is less than the breathing feature threshold, it is determined that the target object is in an inhalation state at the current detection moment.

6. A breathing detection method according to claim 4, characterized in that: There are multiple inertial measurement units; the first respiratory motion data includes multiple groups of data corresponding to each inertial measurement unit; The second breathing data includes a plurality of groups of data corresponding to each of the inertial measurement units; the method includes: Determining measurement weight data for each inertial measurement unit; the measurement weight data is determined based on a measurement position of the inertial measurement unit on the target object; Calculating a total value of the breathing characteristics associated with each of the inertial measurement units; Determining a weighted total breathing feature value of each inertial measurement unit based on the measurement weight data of each inertial measurement unit and the total breathing feature value of the inertial measurement unit; The breathing state of the target object is determined based on the weighted breathing feature sum value of each inertial measurement unit.

7. A breathing detection method according to claim 1, characterized in that: The first time period includes multiple detection time nodes; After acquiring the second respiratory motion data of the target object at the current detection moment, the method includes: Based on the second respiratory motion data corresponding to the current detection moment and the respiratory motion data corresponding to the multiple adjacent detection time nodes before the current detection moment, the first respiratory motion data is updated to obtain updated first respiratory motion data; the number of detection time nodes corresponding to the updated first respiratory motion data is consistent with the number of detection time nodes included in the first time period.

8. A breathing detection method according to claim 1, characterized in that: After acquiring the second respiratory motion data of the target object at the current detection moment, the method includes: Calculate the minimum distance between the first respiratory motion data and the second respiratory motion data in each dimension; When there is a minimum distance value in at least one dimension that is greater than a preset distance threshold, the first respiratory motion data is corrected.

9. A breathing detection method according to claim 8, characterized in that: The step of correcting the first respiratory motion data when the minimum distance value of at least one dimension is greater than a preset distance threshold comprises: Calculate the motion data of the second respiratory motion data in each dimension and the difference between the motion data of the corresponding dimension at the previous detection time node of the current detection moment to obtain a data offset value corresponding to each dimension; The first respiratory motion data is corrected based on the motion data of the first respiratory motion data in each dimension and the data offset value corresponding to each dimension.

10. A breathing detection device, characterized in that: The device comprises: A first data acquisition module is used to acquire first respiratory motion data of a target object within a first time period; the first respiratory motion data is acquired based on an inertial measurement unit arranged on the target object; the first respiratory motion data includes motion data of multiple dimensions; a data weight determination module, configured to jointly process the motion data of multiple dimensions in the first respiratory motion data to obtain the respiratory reference data of the target object in the first time period; A second data acquisition module is used to acquire second respiratory motion data of the target object at a current detection time; the current detection time is a detection time after the first time period, and the second respiratory motion data includes motion data of multiple dimensions; A respiratory data statistics module, used for performing data statistics processing based on the motion data of the first respiratory motion data and the second respiratory motion data in each dimension to obtain a data statistical value corresponding to each dimension; A breathing feature calculation module, used to determine the breathing feature data of the target object based on the data statistics corresponding to each dimension and the second respiratory motion data; A breathing state determination module is used to determine the breathing state of the target object at the current detection moment based on the breathing characteristic data and the breathing reference data.

11. An electronic device, comprising a processor and a memory, wherein the memory stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by the processor to implement the breathing detection method as described in any one of claims 1 to 9.

12. A computer storage medium, wherein at least one instruction and at least one program are stored in the computer storage medium, wherein the at least one instruction and the at least one program are loaded and executed by a processor to implement the breathing detection method according to any one of claims 1 to 9.

Images