Sign data detection method, device and storage medium

Abstract

The application discloses a kind of sign data detection method, equipment and storage medium, to solve the problem of low accuracy of human sign data obtained in sleep detection scene in the related art. First, according to the radar signal collected, the human distance point information is periodically acquired, if it is determined that there are greater than or equal to n historical periods before the current period, according to the human distance point information in the last n historical periods of the current period, the most densely populated area of human distance point distribution in the last n historical periods is determined, the human distance detection range corresponding to the current period is obtained, and the human distance point information corresponding to the current period is acquired, the human distance point in the human distance detection range corresponding to the current period is selected as the target point, finally, the sign data of the target human corresponding to the current period is obtained based on the radar signal at the target point. In the detection process, the radar detection accuracy can be improved, and the human sign data obtained is more accurate.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, and in particular relates to a method, device and storage medium for detecting vital signs data. Background Technology

[0002] In recent years, with increasing awareness of family privacy protection, millimeter-wave radar devices have been increasingly used in sleep monitoring scenarios. How to achieve more comprehensive sleep monitoring based on millimeter-wave radar and provide users with a better experience has become a hot research topic.

[0003] In related technologies, methods for acquiring vital sign data require the use of depth cameras to first obtain human location information. The use of depth cameras increases the cost of radar, and the acquisition of human information by depth cameras poses a risk of user privacy leakage. Alternatively, methods for acquiring vital sign data require beamforming technology to concentrate the beam at a location, which requires the use of at least two radar transmitting devices. This is not suitable for single-transmitter, single-receiver radar equipment, increasing the cost of use and making it unsuitable for home scenarios and sleep detection scenarios.

[0004] Therefore, how to accurately acquire human vital signs data in sleep monitoring scenarios has become a concern in the industry. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, and storage medium for detecting vital signs data, in order to solve the problem of low accuracy of human vital signs data obtained in sleep detection scenarios in related technologies.

[0006] In a first aspect, this application provides a method for detecting vital sign data, the method comprising:

[0007] Based on the collected radar signals, the distance information of the human body is periodically acquired;

[0008] If it is determined that there are more than or equal to n historical periods before the current period, the human distance detection range corresponding to the current period is obtained by determining the area with the densest distribution of human distance points in the n most recent historical periods based on the human distance point information in the n most recent historical periods.

[0009] Obtain human body distance point information corresponding to the current cycle, and select human body distance points within the human body distance detection range corresponding to the current cycle as target points;

[0010] Based on the radar signal at the target point, the vital signs data of the target human body corresponding to the current cycle are obtained.

[0011] In one possible implementation, the step of determining the region with the densest distribution of human distance points in the previous n historical periods based on the human distance point information in the current period, and obtaining the human distance detection range corresponding to the current period, includes:

[0012] For the human distance point information in the n most recent historical periods of the current period, the weight of each human distance point is determined according to the total number of human distance points in each historical period.

[0013] If the total number of human distance points obtained in a historical period is determined to be 1, the weight of the human distance points in that historical period is determined to be a preset value, and all human distance points with the preset weight are placed in the same coordinate system for filtering. The filtered human distance points with the preset weight and the human distance points with the non-preset weight are summarized to obtain the human detection distance point set.

[0014] Based on the set of human body detection distance points and the weights corresponding to the human body distance points in the set, the region with the densest distribution of human body distance points in the previous n historical periods is determined, and the human body distance detection range corresponding to the current period is obtained.

[0015] In one possible implementation, the weights corresponding to each human body distance point are determined using the following weight determination formula:

[0016]

[0017] Where i represents the i-th historical period, ω_n i ω_n represents the weight of the nth distance point within the i-th historical period. i_max ω_n represents the maximum value of the weight. i_min num represents the minimum value of the weight. i This represents the total number of human distance points obtained within the i-th historical period.

[0018] In one possible implementation, all human distance points with preset weights are placed in the same coordinate system for filtering. The filtered human distance points with preset weights are then merged with human distance points with non-preset weights to obtain a set of human detection distance points, including:

[0019] Take any human body distance point with a preset weight as the starting point, and determine the offset distance between each human body distance point other than the starting point and the starting point.

[0020] Based on the offset distance between each human body distance point (excluding the starting point) and the starting point, determine the offset point until the offset distance between the offset point and the starting point is less than a preset first threshold, and then take the offset point as the center point.

[0021] All human distance points with a preset weight and a distance greater than a preset second threshold from the center point are deleted. The filtered human distance points with a preset weight and human distance points with a weight other than the preset weight are merged to obtain a set of human detection distance points.

[0022] In one possible implementation, the offset distance between the human body distance point and the starting point is determined using the following offset distance formula:

[0023] z ij =d ij -d0

[0024] Among them, z ij d represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. ij d0 represents the x-coordinate of the j-th person's distance point within the i-th historical period, and d0 represents the x-coordinate of the starting point.

[0025] The offset point is determined using the following formula:

[0026]

[0027] Where d1 represents the offset point, z ij d represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. ij d0 represents the x-coordinate of the j-th distance point within the i-th historical period, d0 represents the x-coordinate of the starting point or the x-coordinate of the nearest previous offset point of the current offset point, k represents the total number of distance points with a preset weight, and S0 represents the set of distance points with a preset weight.

[0028] In one possible implementation, the step of determining the region with the densest distribution of human distance points in the previous n historical periods based on the human detection distance point set and the weights corresponding to the human distance points in the human detection distance point set, and obtaining the human distance detection range corresponding to the current period, includes:

[0029] The distance points in the human body detection distance point set are grouped in the same coordinate system to obtain a set of multiple vital sign points containing a preset number of human body detection distance points.

[0030] The density of the set of vital sign points is determined using the following density formula:

[0031]

[0032] Where ρ represents the density of the set of vital signs, and ω_n k d represents the weight of the k-th human detection distance point in the set of n-th physical characteristics points.m The x-coordinate of the m-th human detection distance point in the set of vital signs points is given, and N represents the preset number of human detection distance points in the set of vital signs points.

[0033] The set with the highest density is determined from multiple sets of vital signs, and the area of ​​the set with the highest density of vital signs is taken as the human body distance detection range for the current period.

[0034] In one possible implementation, the human distance detection range corresponding to the current cycle is optimized using the following boundary optimization formula:

[0035]

[0036] Where, d max d represents the upper limit of the human body distance detection range. min d represents the lower limit of the human body distance detection range. l d represents the left boundary of the set of vital signs points, which is the point with the smallest x-coordinate in the set of vital signs points. r d represents the right boundary of the set of vital signs points, which is the point with the largest x-coordinate in the set of vital signs points. m The x-coordinate of the m-th human detection distance point in the set of vital signs points is represented by ρ, N represents the preset number of human detection distance points in the set of vital signs points, and ρ represents the density of the set of vital signs points.

[0037] In one possible implementation, the step of periodically acquiring human body distance point information based on the collected radar signals includes:

[0038] The radar signal is periodically processed by a fast Fourier transform to obtain the frequency domain curve data of the radar signal within one period.

[0039] The maximum points of the frequency domain curve data within one period are determined, and the maximum points of the object are filtered out using the following conditional formula to obtain the object distance point information within one period:

[0040]

[0041] Where l(f) represents the frequency domain curve signal after Fourier transform, f n f represents the x-coordinate of the nth maximum point. n_max f n_min h represents the distance range corresponding to the nth maximum point. n Let k1 and k2 represent the ordinate of the nth maximum point, where k1 and k2 are constants.

[0042] Human body detection processing is performed on the signals at different object distance points in the object distance point information within the one period. If it is determined that the signal at any distance point meets the preset conditions, then it is determined that there is a human body at the distance point, and human body distance point information is obtained.

[0043] Secondly, this application also provides a vital sign data detection device, the device comprising:

[0044] The information acquisition module is configured to periodically acquire human distance point information based on the collected radar signals;

[0045] The human body distance detection range determination module is configured to, if it is determined that there are more than or equal to n historical periods before the current period, determine the area with the densest distribution of human body distance points in the n most recent historical periods based on the human body distance point information in the n most recent historical periods, and obtain the human body distance detection range corresponding to the current period.

[0046] The target point determination module is configured to acquire human distance point information corresponding to the current cycle and select human distance points within the human distance detection range corresponding to the current cycle as target points.

[0047] The vital signs data acquisition module is configured to obtain the vital signs data of the target human body corresponding to the current cycle based on the radar signal at the target point.

[0048] In one possible implementation, the process of determining the region with the densest distribution of human distance points within the previous n historical periods based on the human distance point information within the current period is performed to obtain the human distance detection range corresponding to the current period. The human distance detection range determination module is configured as follows:

[0049] For the human distance point information in the n most recent historical periods of the current period, the weight of each human distance point is determined according to the total number of human distance points in each historical period.

[0050] If the total number of human distance points obtained in a historical period is determined to be 1, the weight of the human distance points in that historical period is determined to be a preset value, and all human distance points with the preset weight are placed in the same coordinate system for filtering. The filtered human distance points with the preset weight and the human distance points with the non-preset weight are summarized to obtain the human detection distance point set.

[0051] Based on the set of human body detection distance points and the weights corresponding to the human body distance points in the set, the region with the densest distribution of human body distance points in the previous n historical periods is determined, and the human body distance detection range corresponding to the current period is obtained.

[0052] In one possible implementation, the human body distance detection range determination module is configured to determine the weight corresponding to each human body distance point using the following weight determination formula:

[0053]

[0054] Where i represents the i-th historical period, ω_n i ω_n represents the weight of the nth distance point within the i-th historical period. i_max ω_n represents the maximum value of the weight. i_min num represents the minimum value of the weight. i This represents the total number of human distance points obtained within the i-th historical period.

[0055] In one possible implementation, the process of placing all human distance points with preset weights in the same coordinate system for filtering is performed. The filtered human distance points with preset weights are then combined with those without preset weights to obtain a set of human detection distance points. The human distance detection range determination module is configured as follows:

[0056] Take any human body distance point with a preset weight as the starting point, and determine the offset distance between each human body distance point other than the starting point and the starting point.

[0057] Based on the offset distance between each human body distance point (excluding the starting point) and the starting point, determine the offset point until the offset distance between the offset point and the starting point is less than a preset first threshold, and then take the offset point as the center point.

[0058] All human distance points with a preset weight and a distance greater than a preset second threshold from the center point are deleted. The filtered human distance points with a preset weight and human distance points with a weight other than the preset weight are then combined to obtain a set of human detection distance points.

[0059] In one possible implementation, the human body distance detection range determination module is configured to determine the offset distance between the human body distance point and the starting point using the following offset distance formula:

[0060] z ij =d ij -d0

[0061] Among them, z ij d represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. ij d0 represents the x-coordinate of the j-th person's distance point within the i-th historical period, and d0 represents the x-coordinate of the starting point.

[0062] The offset point is determined using the following formula:

[0063]

[0064] Where d1 represents the offset point, z ij d represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. ij d0 represents the x-coordinate of the j-th distance point within the i-th historical period, d0 represents the x-coordinate of the starting point or the x-coordinate of the nearest previous offset point of the current offset point, k represents the total number of distance points with a preset weight, and S0 represents the set of distance points with a preset weight.

[0065] In one possible implementation, the process of determining the region with the densest distribution of human distance points in the previous n historical periods based on the human detection distance point set and the weights corresponding to the human distance points in the human detection distance point set is executed to obtain the human distance detection range corresponding to the current period. The human distance detection range determination module is configured to:

[0066] The distance points in the human body detection distance point set are grouped in the same coordinate system to obtain a set of multiple vital sign points containing a preset number of human body detection distance points.

[0067] The density of the set of vital sign points is determined using the following density formula:

[0068]

[0069] Where ρ represents the density of the set of vital signs, and ω_n k d represents the weight of the k-th human detection distance point in the set of n-th physical characteristics points. m The x-coordinate of the m-th human detection distance point in the set of vital signs points is given, and N represents the preset number of human detection distance points in the set of vital signs points.

[0070] The set with the highest density is determined from multiple sets of vital signs, and the area of ​​the set with the highest density of vital signs is taken as the human body distance detection range for the current period.

[0071] In one possible implementation, the human body distance detection range determination module is configured to optimize the human body distance detection range corresponding to the current period using the following boundary optimization formula:

[0072]

[0073] Where, d max d represents the upper limit of the human body distance detection range. min d represents the lower limit of the human body distance detection range. ld represents the left boundary of the set of vital signs points, which is the point with the smallest x-coordinate in the set of vital signs points. r d represents the right boundary of the set of vital signs points, which is the point with the largest x-coordinate in the set of vital signs points. m The x-coordinate of the m-th human detection distance point in the set of vital signs points is represented by ρ, N represents the preset number of human detection distance points in the set of vital signs points, and ρ represents the density of the set of vital signs points.

[0074] In one possible implementation, the process of periodically acquiring human body distance point information based on the collected radar signals is performed, wherein the information acquisition module is configured to:

[0075] The radar signal is periodically processed by a fast Fourier transform to obtain the frequency domain curve data of the radar signal within one period.

[0076] The maximum points of the frequency domain curve data within one period are determined, and the maximum points of the object are filtered out using the following conditional formula to obtain the object distance point information within one period:

[0077]

[0078] Where l(f) represents the frequency domain curve signal after Fourier transform, f n f represents the x-coordinate of the nth maximum point. n_max f n_min h represents the distance range corresponding to the nth maximum point. n Let k1 and k2 represent the ordinate of the nth maximum point, where k1 and k2 are constants.

[0079] Human body detection processing is performed on the signals at different object distance points in the object distance point information within the one period. If it is determined that the signal at any distance point meets the preset conditions, then it is determined that there is a human body at the distance point, and human body distance point information is obtained.

[0080] Thirdly, embodiments of this application provide an electronic device, including:

[0081] Memory is used to store the processor's executable instructions;

[0082] A processor is configured to execute the executable instructions to implement the vital sign data detection method as provided in any of the first aspects of this application.

[0083] Fourthly, one embodiment of this application also provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the vital sign data detection method as described in any of the first aspects of this application.

[0084] Fifthly, one embodiment of this application provides a computer program product, including a computer program that, when executed by a processor, implements the vital sign data detection method as described in any of the claims provided in the first aspect of this application.

[0085] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0086] In this application, firstly, based on the collected radar signals, human body distance point information is periodically acquired. If it is determined that there are n or more historical periods prior to the current period, the area with the densest distribution of human body distance points within the n most recent historical periods is determined based on the human body distance point information of the current period, thus obtaining the human body distance detection range corresponding to the current period. Human body distance point information corresponding to the current period is then acquired, and human body distance points within the detection range corresponding to the current period are selected as target points. Finally, based on the radar signal at the target point, the vital signs data of the target human body corresponding to the current period are obtained. Compared to related technologies that utilize auxiliary equipment to acquire vital signs data, this application continuously narrows the detection range of the millimeter-wave radar based on the acquired human body distance point information from different periods during the detection process, thereby improving radar detection accuracy. It can eliminate interference from other factors, resulting in more accurate acquired human body vital signs data. Furthermore, this application is applicable to single-transmitter, single-receiver millimeter-wave radar devices, has a lower cost, and can protect user privacy and improve user experience when applied to sleep monitoring scenarios.

[0087] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application. Based on common knowledge in the art, the above preferred conditions can be combined arbitrarily to obtain various preferred embodiments of this application. Attached Figure Description

[0088] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0089] Figure 1 This is a schematic diagram illustrating an application scenario of a vital sign data detection method provided in an embodiment of this application.

[0090] Figure 2 A flowchart illustrating a vital sign data detection method provided in an embodiment of this application;

[0091] Figure 3 A flowchart illustrating step 201 provided in an embodiment of this application;

[0092] Figure 4 A schematic diagram of the frequency domain curve obtained after Fast Fourier Transform processing according to an embodiment of this application;

[0093] Figure 5 This is a schematic diagram of the maximum points in the frequency domain curve provided in the embodiments of this application;

[0094] Figure 6 A radar scanning schematic diagram provided for an embodiment of this application;

[0095] Figure 7 Another schematic diagram of the maximum point in the frequency domain curve provided in the embodiments of this application;

[0096] Figure 8 Another radar scanning schematic diagram provided for an embodiment of this application;

[0097] Figure 9 Another schematic diagram of the maximum point in the frequency domain curve provided in the embodiments of this application;

[0098] Figure 10 Another radar scanning schematic diagram provided for embodiments of this application;

[0099] Figure 11 A flowchart illustrating step 202 provided in an embodiment of this application;

[0100] Figure 12 A flowchart illustrating step 1102 provided in an embodiment of this application;

[0101] Figure 13 A schematic diagram of human body distance points provided in the embodiments of this application;

[0102] Figure 14 A schematic diagram of the offset points provided in the embodiments of this application;

[0103] Figure 15 A schematic diagram illustrating the positional relationship between the center point and the distance point to the human body, provided in an embodiment of this application;

[0104] Figure 16 A flowchart illustrating step 1103 provided in an embodiment of this application;

[0105] Figure 17 A schematic diagram illustrating the effect of the human body detection distance point set in the same coordinate system provided in the embodiments of this application;

[0106] Figure 18 A schematic diagram illustrating the effect of a radar scan diagram including a human body distance detection range provided in an embodiment of this application;

[0107] Figure 19This is a schematic diagram of the structure of the vital sign data detection device provided in the embodiments of this application;

[0108] Figure 20 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0109] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. The described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0110] Furthermore, in the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0111] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0112] The method for detecting vital signs data provided in this application will be described below with reference to embodiments.

[0113] The inventive concept of this application can be summarized as follows: First, based on the collected radar signals, human body distance point information is periodically acquired. If it is determined that there are more than or equal to n historical periods before the current period, the area with the densest distribution of human body distance points in the previous n historical periods is determined based on the human body distance point information of the most recent n historical periods, thus obtaining the human body distance detection range corresponding to the current period. Human body distance point information corresponding to the current period is then acquired, and human body distance points within the human body distance detection range corresponding to the current period are selected as target points. Finally, based on the radar signal at the target point, the vital signs data of the target human body corresponding to the current period are obtained. Compared with related technologies that utilize auxiliary equipment to acquire vital signs data, this application continuously narrows the detection range of the millimeter-wave radar based on the acquired human body distance point information of different periods during the detection process, thereby improving radar detection accuracy. It can eliminate interference from other factors, resulting in more accurate acquired human body vital signs data. Moreover, this application is applicable to single-transmitter, single-receiver millimeter-wave radar devices, has a lower cost, and can protect user privacy and improve user experience when applied to sleep monitoring scenarios.

[0114] After introducing the main inventive concepts of the embodiments of this application, the following is a brief description of the application scenarios to which the technical solutions of the embodiments of this application are applicable. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.

[0115] refer to Figure 1 This is a schematic diagram illustrating the application scenario of the vital sign data detection method provided in the embodiments of this application.

[0116] The diagram includes: network 10, server 20, storage device 30, and radar device. Server 20 is connected to the radar device via the network. Using the vital sign data detection method provided in this application embodiment, this radar device can be used to collect vital sign data of the human body in a sleep scenario, enabling analysis and research on the user's sleep and physical condition.

[0117] The description in this application focuses on a single server only. However, those skilled in the art should understand that the illustrated radar device, robot, network 10, server 20, and memory 30 are intended to illustrate the operation of the radar device, robot, server, and memory involved in the technical solutions of this application. The detailed description of a single server and memory is at least for ease of explanation and does not imply any limitation on the number, type, or location of servers. It should be noted that adding additional modules to or removing individual modules from the illustrated environment does not change the underlying concept of the exemplary embodiments of this application. Furthermore, although detailed descriptions are provided for ease of explanation... Figure 1The diagram shows a bidirectional arrow from memory 30 to server 20, but those skilled in the art will understand that the sending and receiving of the aforementioned data also needs to be achieved through network 10.

[0118] It should be noted that the memory in the embodiments of this application can be, for example, a cache system, hard disk storage, memory storage, etc. Of course, the methods provided in the embodiments of this application are not limited to... Figure 1 The application scenarios shown can also be used in other possible application scenarios. This application does not limit the scope of these applications. Figure 1 The functions that each device in the application scenario shown can achieve will be described in subsequent method embodiments, and will not be elaborated on here.

[0119] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation steps as shown in the following embodiments or drawings, the method may include more or fewer operation steps based on conventional or non-inventive methods. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application.

[0120] Based on the above description, this application provides a method for detecting vital signs data, the flowchart of which is shown below. Figure 2 As shown, the following steps may be included:

[0121] In step 201, the distance point information of the human body is periodically acquired based on the collected radar signals.

[0122] In one possible implementation, in step 201, the distance point information of the human body is periodically acquired based on the collected radar signals, as illustrated in the flowchart below. Figure 3 As shown, it can be implemented as follows:

[0123] In step 301, the radar signal is periodically processed by Fast Fourier Transform to obtain the frequency domain curve data of the radar signal within one period.

[0124] In this application, after activating the millimeter-wave radar, the radar signal is periodically processed using Fast Fourier Transform (FFT). This period includes multiple operations of transmitting and receiving echo signals from the millimeter-wave radar. Therefore, this embodiment performs FFT processing on all radar signals acquired within this period to obtain the frequency domain curve data of the radar signal within one period. For example, the frequency domain curve obtained after FFT processing is as follows: Figure 4 As shown, it can be expressed as the following formula (1):

[0125] h=l(f) (1)

[0126] Where l represents the frequency domain curve after Fourier transform, f represents the horizontal axis of the curve, i.e., the distance between the location point and the millimeter-wave radar, and h represents the vertical axis of the curve.

[0127] In step 302, the maximum points of the frequency domain curve data within one period are determined, and the maximum points of the object are filtered out using the following conditional formula to obtain the object distance point information within one period.

[0128] In one possible embodiment, the maximum point of the frequency domain curve within one period can be obtained by the following maximum formula (2):

[0129] p n =(f n ,h n (2)

[0130] Where, p n Let f represent the nth maximum point. n h represents the x-coordinate of the nth maximum point. n This represents the ordinate of the nth maximum point.

[0131] like Figure 5 As shown, the maximum point is marked by the black circle in the frequency domain curve diagram, and its corresponding radar scan diagram is as follows. Figure 6 As shown in the image, the locations marked by the black circles indicate the positions where objects exist. Figure 5 The maximum points in the equation correspond to the locations of objects, and each indicates the presence of an object at that location. Figure 6 The position of the black circle marker is equidistant from the center of the sector area. Figure 5 The x-coordinates of the maximum points in the graph represent the distance between that location and the radar. Figure 6 The two arcs in the middle are equivalent to Figure 5 The vertical solid lines at both ends of the maximum point represent the distance range corresponding to that maximum point. If there are multiple maximum points in the frequency domain curve data within one period, the schematic diagram is as follows. Figure 7 As shown, the corresponding radar scan diagram is as follows: Figure 8 As shown, if the distance range corresponding to the maximum point is the same as the above... Figure 5 The distance range corresponding to the maximum point in the diagram is different, so the diagram is as follows: Figure 9 As shown, the corresponding radar scan diagram is as follows: Figure 10 As shown, based on the frequency domain curve diagram and the corresponding radar scan diagram, the actual location of the maximum point corresponds one-to-one with the location marked by the black circle in the radar scan diagram. Both are locations where objects exist, which can clearly display the information of the maximum point and facilitate user filtering.

[0132] However, due to environmental interference and other factors in the radar detection process, the maximum point obtained by solving the above formula (2) may not be the radar signal returned by the actual object. Therefore, in this embodiment, it is necessary to select the relatively prominent maximum point as the maximum point corresponding to the actual detected object. The condition formula (3) is as follows:

[0133]

[0134] Where l(f) represents the frequency domain curve signal after Fourier transform, f n f represents the x-coordinate of the nth maximum point. n_max f n_min h represents the distance range corresponding to the nth maximum point. n This represents the ordinate of the nth maximum point. k1 and k2 are constants. The maximum points selected under condition 1 need to have a certain range of maximum values. k1 is generally taken as 50. The maximum points selected under condition 2 have a certain degree of prominence. k2 is generally taken as 10.

[0135] After filtering out the maximum points of objects and obtaining the object distance point information within a period, in step 303, human body detection processing is performed on the signals at different object distance points in the object distance point information within a period. If it is determined that the signal at any distance point meets the preset conditions, it is determined that there is a human body at the distance point, and human body distance point information is obtained.

[0136] In one possible embodiment, since the small displacement and vibration of an object will cause phase changes in the radar echo signal, this embodiment of the application calculates the phase angle of the signal at different object distance points. The phase angle of a stationary object will remain basically unchanged, while the periodic breathing and heartbeat of a human body will cause the phase angle to change periodically. Therefore, it can be determined whether the object at the distance is a human body by whether there is a significant change in the phase angle, thereby determining the distance point where a human body exists, and finally obtaining the human body distance point information.

[0137] In step 202, if it is determined that there are more than or equal to n historical periods before the current period, the area with the densest distribution of human distance points in the previous n historical periods is determined based on the human distance point information of the most recent n historical periods, and the human distance detection range corresponding to the current period is obtained.

[0138] In one possible implementation, statistics are compiled based on the detected human distance point information each time. If a human distance point frequently appears in the detection range of multiple cycles, this application can consider that the human distance point to be a stable target human position. However, due to the high accuracy of millimeter-wave radar, even slight movements of the human body can cause the human distance point information in different cycles to be inconsistent. Therefore, a single human distance point cannot be simply used as a judgment criterion; a judgment needs to be made within a certain cycle range. Therefore, in step 202, based on the human distance point information in the n most recent historical cycles of the current cycle, the region with the densest distribution of human distance points in the n most recent historical cycles is determined, and the human distance detection range corresponding to the current cycle is obtained. The flowchart is as follows. Figure 11 As shown, it includes the following:

[0139] In step 1101, for the human body distance point information in the n most recent historical periods of the current period, the weight corresponding to each human body distance point is determined according to the total number of human body distance points in each historical period.

[0140] In one possible implementation, the weights corresponding to each human body distance point are determined using the following weight determination formula (4):

[0141]

[0142] Where i represents the i-th historical period, ω_n i ω_n represents the weight of the nth distance point within the i-th historical period. i_max ω_n represents the maximum value of the weight. i_min num represents the minimum value of the weight. i This represents the total number of human distance points obtained within the i-th historical period.

[0143] It should be noted that the embodiments of this application can set the maximum value of the weight and the maximum value of the weight, and use these two to limit the weight range.

[0144] In step 1102, if the total number of human distance points obtained in a historical period is determined to be 1, the weight of the human distance points in the historical period is determined to be a preset value, and all human distance points with the preset weight are placed in the same coordinate system for filtering. The filtered human distance points with the preset weight and the human distance points with the non-preset weight are summarized to obtain a set of human detection distance points.

[0145] In one possible implementation, all human distance points with preset weights are placed in the same coordinate system for filtering. The filtered human distance points with preset weights are then merged with human distance points with non-preset weights to obtain a set of human detection distance points. The flowchart is shown below. Figure 12As shown, it includes the following:

[0146] In step 1201, any human body distance point with a preset weight is taken as the starting point, and the offset distance between each human body distance point and the starting point is determined.

[0147] In one possible implementation, the offset distance between the human body distance point and the starting point is determined using the following offset distance formula (5):

[0148] z ij =d ij -d0 (5)

[0149] Among them, z ij d represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. i d represents the x-coordinate of the j-th person's distance point within the i-th historical period, and d0 represents the x-coordinate of the starting point.

[0150] For example, such as Figure 13 As shown, there are 6 human body distance points with preset weights (e.g., ...). Figure 13 (As shown by the black dot in the middle), if the human body distance point labeled 1 is taken as the starting point, then the offset distance formula (5) above is used to determine the offset distance between the other 5 human body distance points and the starting point, that is, the difference between the horizontal coordinate of the other 5 human body distance points and the horizontal coordinate of the starting point is taken as the offset distance.

[0151] It should be noted that the positional relationship between the human body and the points is not limited to... Figure 13 The diagram provided in this application illustrates the positional relationship of elements on the same horizontal straight line for ease of understanding.

[0152] In step 1202, offset points are determined based on the offset distances between each human body distance point and the starting point, except for the starting point, until the offset distance between the offset point and the starting point is less than a preset first threshold, and the offset point is taken as the center point.

[0153] In one possible implementation, the offset point is determined using the following offset point formula (6):

[0154]

[0155] Where d1 represents the offset point, z ij d represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. ij d0 represents the x-coordinate of the j-th distance point within the i-th historical period, d0 represents the x-coordinate of the starting point or the x-coordinate of the nearest previous offset point of the current offset point, k represents the total number of distance points with preset weights, and S0 represents the set of distance points with preset weights.

[0156] For example, such as Figure 14 As shown, there are 6 human body distance points with preset weights (e.g., ...). Figure 13 (As shown by the black dot in the middle), take the human body distance point labeled 1 as the starting point, and determine the offset distances of the other 5 human body distance points from the starting point. Then, use the above offset point formula (6) to determine the offset points respectively, that is, add the x-coordinate of the starting point to the average value of the 5 offset distances to obtain the first offset point. Figure 14 The hollow circle is the offset point. If the offset distance between the first offset point and the starting point is greater than the preset first threshold, for example, if the offset distance between the first offset point and the starting point is greater than 0.1, then the first offset point is taken as d0. The second offset point d1 is determined according to the above offset point formula (6), and so on, until the offset distance between the offset point and the starting point is less than the preset first threshold, for example, 5 offset points are obtained. The offset point is taken as the center point, that is... Figure 14 The offset point marked as D is used as the center point.

[0157] It should be noted that, Figure 14 Mid-offset point and Figure 13 The human body distance points are not the same. In this embodiment, the offset point is determined by the offset distance between the human body distance point and the starting point.

[0158] In step 1203, all human distance points with a preset weight and a distance greater than a preset second threshold from the center point are deleted. The filtered human distance points with a preset weight and human distance points with a weight other than the preset weight are then combined to obtain a set of human detection distance points.

[0159] In one possible embodiment, after finding the center point, the distance between each human body distance point with a preset weight and the center point is determined. If the distance is too large, it is considered a point that generates a large error, and this embodiment of the application deletes such human body distance points. For example, Figure 15 As shown, there are 6 human body distance points with preset weights (e.g., ...). Figure 15 (As shown by the black dot in the middle), the human distance point labeled 1 is used as the center point. After determining the distance between each human distance point and the center point, human distance points with a distance greater than 0.5 are deleted, that is, human distance points labeled 5 and 6 are deleted, which reduces the error and makes the final human distance detection range more accurate.

[0160] In step 1103, based on the human body detection distance point set and the weights corresponding to the human body distance points in the human body detection distance point set, the region with the densest distribution of human body distance points in the previous n historical periods is determined, and the human body distance detection range corresponding to the current period is obtained.

[0161] In one possible implementation, in step 1103, based on the set of human body detection distance points and the weights corresponding to the human body distance points in the set, the region with the densest distribution of human body distance points in the previous n historical periods is determined, thus obtaining the human body distance detection range corresponding to the current period. The flowchart is as follows: Figure 16 As shown, it includes the following steps:

[0162] In step 1601, the distance points in the human body detection distance point set are grouped under the same coordinate system to obtain a set of multiple vital sign points containing a preset number of human body detection distance points.

[0163] For example, such as Figure 17 As shown, the set of human detection distance points in the same coordinate system includes 25 human detection distance points (e.g., Figure 17 (As shown in the black circle in the middle) The 25 human body detection distance points are grouped into groups of 5 points each, from left to right. For example, the first set of vital signs points includes human body detection distance points numbered 1, 2, 3, 4, and 5, the second set includes human body detection distance points numbered 1, 2, 3, 4, and 6, and so on. Each set of vital signs points includes the same number of human body detection distance points, but the specific human body detection distance points are not exactly the same.

[0164] It should be noted that, in this embodiment of the application, the preset number of human body detection distance points in the set of vital signs is determined based on the number n of the first n cycles.

[0165] In step 1602, the density of the set of vital sign points is determined using the following density formula (7):

[0166]

[0167] Where ρ represents the density of the set of vital signs, and ω_n k d represents the weight of the k-th human detection distance point in the set of n-th physical characteristics points. m The x-coordinate of the m-th human detection distance point in the set of vital signs points is represented, and N represents the preset number of human detection distance points in the set of vital signs points.

[0168] In step 1603, the set with the highest density is determined from multiple sets of vital signs, and the area of ​​the set with the highest density of vital signs is taken as the human body distance detection range for the current period.

[0169] For example, such as Figure 17As shown, the first set of vital sign points includes human detection distance points labeled 1, 2, 3, 4, and 5. Based on the weight of each human detection distance point determined by the formula (4) above, the density of the set of vital sign points is obtained. This process is repeated to obtain the density of all sets of vital sign points. The area of ​​the set of vital sign points with the highest density is taken as the human distance detection range corresponding to the current period. A radar scanning diagram is shown below. Figure 18 As shown, the area circled by the dashed line represents the human body distance detection range for the current cycle.

[0170] In another possible implementation, the set of vital signs with the highest density is found from multiple sets of vital sign points. The area of ​​this set of vital sign points can be considered as the location of the human body. However, considering the movement of the human body during the measurement process, this embodiment of the application further expands the human body distance detection range appropriately based on the density of the left and right boundaries of the area of ​​this set of vital sign points. This embodiment of the application uses the following boundary optimization formula (8) to optimize the human body distance detection range corresponding to the current cycle:

[0171]

[0172] Where, d max d represents the upper limit of the human body distance detection range. min d represents the lower limit of the human body distance detection range. l d represents the left boundary of the set of vital signs points, which is the point with the smallest x-coordinate in the set of vital signs points. r d represents the right boundary of the set of vital signs points, which is the point with the largest x-coordinate in the set of vital signs points. m ρ represents the x-coordinate of the m-th human detection distance point in the set of vital signs points, N represents the preset number of human detection distance points in the set of vital signs points, and ρ represents the density of the set of vital signs points.

[0173] The boundary optimization formula (8) fully considers the interference of human movement on the human distance detection range, optimizes the human distance detection range, avoids the error caused by human movement, and makes the final target human physical characteristics data more accurate.

[0174] In step 203, the human body distance point information corresponding to the current cycle is obtained, and the human body distance point within the human body distance detection range corresponding to the current cycle is selected as the target point.

[0175] In step 204, the vital signs data of the target human body corresponding to the current cycle are obtained based on the radar signal at the target point.

[0176] In one possible implementation, after obtaining the human body distance detection range, during the detection process, this range is used as a basis for judgment. A human body distance point within this range is selected as a target point, and the target human body's vital signs data for the current cycle are obtained based on the radar signal at the target point. If no suitable target point is found within this range, a new detection is performed over a larger area. This embodiment also stores the data collected in each cycle to more accurately determine the human body distance detection range for the current cycle.

[0177] In summary, this application, during the detection process using millimeter-wave radar, continuously narrows the detection range of the millimeter-wave radar based on the human body distance point information acquired at different cycles, thereby improving radar detection accuracy. It can eliminate interference from other factors, resulting in more accurate acquisition of human vital signs data. Furthermore, this application is applicable to single-transmitter, single-receiver millimeter-wave radar devices, has a low cost, and can protect user privacy and improve user experience when applied to sleep monitoring scenarios.

[0178] Based on the same inventive concept, this application also provides a vital sign data detection device, such as... Figure 19 As shown, the device 1900 includes:

[0179] The information acquisition module 1901 is configured to periodically acquire human body distance information based on the collected radar signals;

[0180] The human body distance detection range determination module 1902 is configured to, if it is determined that there are more than or equal to n historical periods before the current period, determine the area with the densest distribution of human body distance points in the n most recent historical periods based on the human body distance point information in the n most recent historical periods, and obtain the human body distance detection range corresponding to the current period.

[0181] The target point determination module 1903 is configured to acquire human distance point information corresponding to the current cycle and select human distance points within the human distance detection range corresponding to the current cycle as target points.

[0182] The vital signs data acquisition module 1904 is configured to obtain the vital signs data of the target human body corresponding to the current cycle based on the radar signal at the target point.

[0183] In one possible implementation, the process of determining the region with the densest distribution of human distance points within the previous n historical periods based on the human distance point information within the current period is performed to obtain the human distance detection range corresponding to the current period. The human distance detection range determination module is configured as follows:

[0184] For the human distance point information in the n most recent historical periods of the current period, the weight of each human distance point is determined according to the total number of human distance points in each historical period.

[0185] If the total number of human distance points obtained in a historical period is determined to be 1, the weight of the human distance points in that historical period is determined to be a preset value, and all human distance points with the preset weight are placed in the same coordinate system for filtering. The filtered human distance points with the preset weight and the human distance points with the non-preset weight are summarized to obtain the human detection distance point set.

[0186] Based on the set of human body detection distance points and the weights corresponding to the human body distance points in the set, the region with the densest distribution of human body distance points in the previous n historical periods is determined, and the human body distance detection range corresponding to the current period is obtained.

[0187] In one possible implementation, the human body distance detection range determination module is configured to determine the weight corresponding to each human body distance point using the following weight determination formula:

[0188]

[0189] Where i represents the i-th historical period, ω_n i ω_n represents the weight of the nth distance point within the i-th historical period. i_max ω_n represents the maximum value of the weight. i_min num represents the minimum value of the weight. i This represents the total number of human distance points obtained within the i-th historical period.

[0190] In one possible implementation, the process of placing all human distance points with preset weights in the same coordinate system for filtering is performed. The filtered human distance points with preset weights are then combined with those without preset weights to obtain a set of human detection distance points. The human distance detection range determination module is configured as follows:

[0191] Take any human body distance point with a preset weight as the starting point, and determine the offset distance between each human body distance point other than the starting point and the starting point.

[0192] Based on the offset distance between each human body distance point (excluding the starting point) and the starting point, determine the offset point until the offset distance between the offset point and the starting point is less than a preset first threshold, and then take the offset point as the center point.

[0193] All human distance points with a preset weight and a distance greater than a preset second threshold from the center point are deleted. The filtered human distance points with a preset weight and human distance points with a weight other than the preset weight are then combined to obtain a set of human detection distance points.

[0194] In one possible implementation, the human body distance detection range determination module is configured to determine the offset distance between the human body distance point and the starting point using the following offset distance formula:

[0195] z ij =d ij -d0

[0196] Among them, z ij d represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. ij d0 represents the x-coordinate of the j-th person's distance point within the i-th historical period, and d0 represents the x-coordinate of the starting point.

[0197] The offset point is determined using the following formula:

[0198]

[0199] Where d1 represents the offset point, z ij d represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. ij d0 represents the x-coordinate of the j-th distance point within the i-th historical period, d0 represents the x-coordinate of the starting point or the x-coordinate of the nearest previous offset point of the current offset point, k represents the total number of distance points with a preset weight, and S0 represents the set of distance points with a preset weight.

[0200] In one possible implementation, the process of determining the region with the densest distribution of human distance points in the previous n historical periods based on the human detection distance point set and the weights corresponding to the human distance points in the human detection distance point set is executed to obtain the human distance detection range corresponding to the current period. The human distance detection range determination module is configured to:

[0201] The distance points in the human body detection distance point set are grouped in the same coordinate system to obtain a set of multiple vital sign points containing a preset number of human body detection distance points.

[0202] The density of the set of vital sign points is determined using the following density formula:

[0203]

[0204] Where ρ represents the density of the set of vital signs, and ω_n kd represents the weight of the k-th human detection distance point in the set of n-th physical characteristics points. m The x-coordinate of the m-th human detection distance point in the set of vital signs points is given, and N represents the preset number of human detection distance points in the set of vital signs points.

[0205] The set with the highest density is determined from multiple sets of vital signs, and the area of ​​the set with the highest density of vital signs is taken as the human body distance detection range for the current period.

[0206] In one possible implementation, the human body distance detection range determination module is configured to optimize the human body distance detection range corresponding to the current period using the following boundary optimization formula:

[0207]

[0208] Where, d max d represents the upper limit of the human body distance detection range. min d represents the lower limit of the human body distance detection range. l d represents the left boundary of the set of vital signs points, which is the point with the smallest x-coordinate in the set of vital signs points. r d represents the right boundary of the set of vital signs points, which is the point with the largest x-coordinate in the set of vital signs points. m The x-coordinate of the m-th human detection distance point in the set of vital signs points is represented by ρ, N represents the preset number of human detection distance points in the set of vital signs points, and ρ represents the density of the set of vital signs points.

[0209] In one possible implementation, the process of periodically acquiring human body distance point information based on the collected radar signals is performed, wherein the information acquisition module is configured to:

[0210] The radar signal is periodically processed by a fast Fourier transform to obtain the frequency domain curve data of the radar signal within one period.

[0211] The maximum points of the frequency domain curve data within one period are determined, and the maximum points of the object are filtered out using the following conditional formula to obtain the object distance point information within one period:

[0212]

[0213] Where l(f) represents the frequency domain curve signal after Fourier transform, f n f represents the x-coordinate of the nth maximum point. n_max f n_min h represents the distance range corresponding to the nth maximum point. n Let k1 and k2 represent the ordinate of the nth maximum point, where k1 and k2 are constants.

[0214] Human body detection processing is performed on the signals at different object distance points in the object distance point information within the one period. If it is determined that the signal at any distance point meets the preset conditions, then it is determined that there is a human body at the distance point, and human body distance point information is obtained.

[0215] The following reference Figure 20 To describe an electronic device 130 according to this embodiment of the present application. Figure 20 The electronic device 130 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0216] like Figure 20 As shown, the electronic device 130 is presented in the form of a general-purpose electronic device. The components of the electronic device 130 may include, but are not limited to: at least one processor 131, at least one memory 132, and a bus 133 connecting different system components (including memory 132 and processor 131).

[0217] Bus 133 represents one or more of several bus structures, including a memory bus or memory controller, peripheral bus, processor, or local bus using any of the various bus structures.

[0218] The memory 132 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 1321 and / or cache memory 1322, and may further include read-only memory (ROM) 1323.

[0219] The memory 132 may also include a program / utility 1325 having a set (at least one) of program modules 1324, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0220] Electronic device 130 can also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), and with one or more devices that enable a user to interact with electronic device 130, and / or with any device that enables electronic device 130 to communicate with one or more other electronic devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 135. Furthermore, electronic device 130 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 136. As shown, network adapter 136 communicates with other modules used in electronic device 130 via bus 133. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 130, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0221] In an exemplary embodiment, this application also provides a computer-readable storage medium including instructions, such as a memory 132 including instructions, which can be executed by a processor 131 of an electronic device 130 to complete the above-described vital sign data detection method. Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0222] In an exemplary embodiment, a computer program product is also provided, including a computer program that, when executed by a processor 131, implements the vital sign data detection method provided in this application.

[0223] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0224] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0225] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0226] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0227] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for detecting vital signs data, characterized in that, The method includes: Based on the collected radar signals, the distance information of the human body is periodically acquired; If it is determined that there are more than or equal to n historical periods before the current period, for the human body distance point information in the n most recent historical periods of the current period, the weight corresponding to each human body distance point is determined according to the total number of human body distance points in each historical period. If the total number of human distance points obtained in a historical period is determined to be 1, the weight of the human distance points in that historical period is determined to be a preset value, and all human distance points with the preset weight are placed in the same coordinate system for filtering. The filtered human distance points with the preset weight and the human distance points with the non-preset weight are summarized to obtain the human detection distance point set. The distance points in the human body detection distance point set are grouped in the same coordinate system to obtain a set of multiple vital sign points containing a preset number of human body detection distance points. The density of the set of vital sign points is determined using the following density formula: Where ρ represents the density of the set of vital signs. d_m represents the weight of the k-th human detection distance point in the n-th set of physical signs, d_m represents the x-coordinate of the m-th human detection distance point in the set of physical signs, and N represents the preset number of human detection distance points in the set of physical signs. From multiple sets of vital signs, determine the set with the highest density, and use the area of ​​the set with the highest density of vital signs as the human body distance detection range for the current period; Obtain human body distance point information corresponding to the current cycle, and select human body distance points within the human body distance detection range corresponding to the current cycle as target points; Based on the radar signal at the target point, the vital signs data of the target human body corresponding to the current cycle are obtained.

2. The method according to claim 1, characterized in that, The weights corresponding to each distance point of the human body are determined using the following weighting formula: in, This indicates that it is the i-th historical cycle. This represents the weight of the nth distance point within the i-th historical period. This represents the maximum value of the weight. This represents the minimum value of the weight. This represents the total number of human distance points obtained within the i-th historical period.

3. The method according to claim 1, characterized in that, The process involves placing all human distance points with preset weights into the same coordinate system for filtering, resulting in a set of human detection distance points, including: Take any human body distance point with a preset weight as the starting point, and determine the offset distance between each human body distance point other than the starting point and the starting point. Based on the offset distance between each human body distance point (excluding the starting point) and the starting point, determine the offset point until the offset distance between the offset point and the starting point is less than a preset first threshold, and then take the offset point as the center point. All human distance points with a preset weight and a distance greater than a preset second threshold from the center point are deleted. The filtered human distance points with a preset weight and human distance points with a weight other than the preset weight are then combined to obtain a set of human detection distance points.

4. The method according to claim 3, characterized in that, The offset distance between the human body distance point and the starting point is determined using the following offset distance formula: in, This represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. This represents the x-coordinate of the j-th person's distance point within the i-th historical period. This represents the x-coordinate of the starting point; The offset point is determined using the following formula: in, Indicates the offset point. This represents the offset distance between the j-th person's distance point and the starting point within the i-th historical period. This represents the x-coordinate of the j-th distance point within the i-th historical period. This represents the x-coordinate of the starting point or the x-coordinate of the nearest previous offset point. This represents the total number of distance points with a preset weight. This represents the set of distance points with preset weights.

5. The method according to claim 1, characterized in that, The following boundary optimization formula is used to optimize the human body distance detection range for the current cycle: in, This indicates the upper limit of the human body distance detection range. This indicates the lower limit of the human body distance detection range. This represents the left boundary of the set of vital sign points, which is the point with the smallest x-coordinate in the set of vital sign points. This represents the right boundary of the set of vital sign points, which is the point with the largest x-coordinate in the set of vital sign points. This represents the x-coordinate of the m-th human detection distance point in the set of vital signs points. This indicates the preset number of human body detection distance points in the set of vital sign points. This indicates the density of the set of vital signs.

6. The method according to claim 1, characterized in that, The process of periodically acquiring human body distance information based on collected radar signals includes: The radar signal is periodically processed by a fast Fourier transform to obtain the frequency domain curve data of the radar signal within one period. The maximum points of the frequency domain curve data within one period are determined, and the maximum points of the object are filtered out using the following conditional formula to obtain the object distance point information within one period: in, This represents the frequency domain curve of the signal after Fourier transform. This represents the x-coordinate of the nth maximum point. , This represents the distance range corresponding to the nth maximum point. This represents the ordinate of the nth maximum point. , It is a constant; Human body detection processing is performed on the signals at different object distance points in the object distance point information within the one period. If it is determined that the signal at any distance point meets the preset conditions, then it is determined that there is a human body at the distance point, and human body distance point information is obtained.

7. An electronic device, characterized in that, include: Memory is used to store the processor's executable instructions; A processor for executing the executable instructions to implement the vital sign data detection method as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the vital sign data detection method as described in any one of claims 1-6.

Images