A radar-based method, system, and product for nursing behavior compliance auditing

Abstract

The application provides a radar-based nursing behavior compliance auditing method, system and product, the method comprising: target detection on collected radar echo data, and generating a target 2D point cloud based on the target detection result; human target recognition based on the target 2D point cloud; trajectory tracking on the recognized human target, obtaining a trajectory coordinate sequence; extracting a nursing behavior characteristic parameter based on the trajectory coordinate sequence, and determining the nursing behavior compliance based on the nursing behavior characteristic parameter; and generating a nursing behavior compliance auditing report based on the nursing behavior compliance determination result. The nursing behavior compliance auditing method provided by the application does not need to collect actual image data, can identify personnel in the scene without infringing privacy, and can simultaneously identify nursing behavior, can monitor the whole process of nursing, effectively improves the effectiveness of nursing process supervision, and effectively reduces the auditing time cost of nursing work orders.

Description

Technical Field

[0001] This application relates to the field of radar technology, and in particular to a radar-based method, system, and product for auditing compliance of nursing behaviors. Background Technology

[0002] With the aging of the population, home-based elderly care has become a major social necessity. In recent years, the development of internet information technology has brought new opportunities to the elderly care field. How to leverage technology to build new home-based elderly care service models has become a key focus for both academia and industry. However, current home-based elderly care services face many challenges: on the one hand, there is room for improvement in service satisfaction rates; on the other hand, it is difficult to effectively obtain service quality evaluations when caregivers provide services, leading to low management efficiency. Currently, the most common method for supervising home-based elderly care services is computer vision technology, employing solutions including video recording and facial recognition. However, while these methods can record the care process, the costs of equipment purchase, deployment, and maintenance are high, video analysis consumes significant computing resources, and there is a risk of privacy leaks. Some solutions also utilize Bluetooth beacon technology and satellite positioning technology; however, these technologies can only locate personnel and cannot effectively supervise the care process.

[0003] Therefore, there is an urgent need for a nursing behavior compliance auditing method that combines privacy-free image collection, recognition of nursing actions, and effective supervision of the nursing process. Summary of the Invention

[0004] The purpose of this application is to provide a radar-based method, system, and product for auditing compliance of nursing behaviors, which can at least solve the problem of difficulty in effectively supervising the nursing process without privacy breaches in related technologies.

[0005] To address the aforementioned technical problems, the first aspect of this application provides a radar-based method for auditing compliance of nursing behaviors, comprising:

[0006] Target detection is performed on the collected radar echo data, and a 2D point cloud of the target is generated based on the target detection results;

[0007] Human target recognition is performed based on the target's 2D point cloud.

[0008] The identified human target is tracked to obtain a sequence of trajectory coordinates;

[0009] Nursing behavior feature parameters are extracted based on the trajectory coordinate sequence, and the compliance of nursing behavior is determined based on the nursing behavior feature parameters.

[0010] A nursing behavior compliance audit report is generated based on the nursing behavior compliance assessment results.

[0011] A second aspect of this application provides a radar-based nursing behavior compliance audit system, comprising:

[0012] The point cloud generation module is used to perform target detection on the collected radar echo data and generate a 2D point cloud of the target based on the target detection results.

[0013] The target recognition module is used to perform human target recognition based on the target's 2D point cloud;

[0014] The trajectory tracking module is used to track the trajectory of the identified human target and obtain the trajectory coordinate sequence;

[0015] The behavior determination module is used to extract nursing behavior feature parameters based on the trajectory coordinate sequence, and to determine the compliance of nursing behavior based on the nursing behavior feature parameters.

[0016] The report generation module is used to generate nursing behavior compliance audit reports based on the nursing behavior compliance assessment results.

[0017] A third aspect of this application provides a radar, including a memory and a processor, wherein the processor is used to execute a computer program stored in the memory, and when the processor executes the computer program, it implements the steps in the nursing behavior compliance audit method described in the first aspect of the embodiments of this application.

[0018] The fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the nursing behavior compliance audit method described in the first aspect of the embodiments of this application.

[0019] As described above, the embodiments of this application first perform target detection on the collected radar echo data and generate a 2D point cloud of the target based on the target detection results. Then, human target recognition is performed based on the 2D point cloud of the target, followed by trajectory tracking of the recognized human target to obtain a trajectory coordinate sequence. Next, nursing behavior feature parameters are extracted based on the trajectory coordinate sequence, and nursing behavior compliance is determined based on the nursing behavior feature parameters. Finally, a nursing behavior compliance audit report is generated based on the nursing behavior compliance determination result. The nursing behavior compliance audit method proposed in this invention does not require the collection of actual image data, can identify personnel in the scene without infringing on privacy, and can simultaneously identify nursing behaviors. It can monitor the entire nursing process, effectively improving the effectiveness of nursing process supervision. Furthermore, it can effectively judge the compliance of nursing behaviors and provide an audit report, which can effectively reduce the audit time cost of nursing work orders.

[0020] It should be understood that the description in this section is not intended to identify key or important features of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the related technologies or the technical solutions in the embodiments of this application, the drawings used in the description of the related technologies or the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application, and not all embodiments. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating the nursing behavior compliance audit method provided in this application embodiment;

[0023] Figure 2 A detailed flowchart illustrating the nursing behavior compliance audit method provided in this application embodiment;

[0024] Figure 3 A schematic diagram of the program modules of the nursing behavior compliance audit system provided in this application embodiment;

[0025] Figure 4 A block diagram of a radar provided in an embodiment of this application;

[0026] Figure 5 A block diagram of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application more apparent and understandable, this application will be clearly and completely described below in conjunction with its embodiments and accompanying drawings. Throughout, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions. It should be understood that the various embodiments of this application described below are merely illustrative of this application and are not intended to limit this application. That is, all other embodiments obtained by those skilled in the art based on the various embodiments of this application without creative effort are within the scope of protection of this application. Furthermore, the technical features involved in the various embodiments of this application described below can be combined with each other as long as they do not conflict with each other.

[0028] With the aging population, home-based elderly care has become a major social necessity. However, several challenges remain: firstly, the service satisfaction rate for home-based elderly care is low; secondly, it is difficult to effectively obtain service quality evaluations from caregivers, leading to low management efficiency. In recent years, the rapid development of "Internet + information technology" has impacted many industries and also brought opportunities to the elderly care sector. How to utilize "Internet + technology" to create a new service model for "Internet + home-based elderly care" has become a topic of great concern to academia and relevant departments.

[0029] Currently, the main technologies for supervising home-based elderly care services include computer vision-based human behavior recognition technology (such as law enforcement recorder recording at the nursing site, facial recognition, etc.), Bluetooth beacon technology, and GPS / BeiDou positioning technology. Each of these technologies has its own advantages and disadvantages. While law enforcement recorders can record the nursing process, the purchase, deployment, and maintenance costs of the equipment are high, video analysis costs are high, and there is a risk of privacy leakage. On the other hand, technologies such as facial recognition, Bluetooth beacons, and GPS / BeiDou positioning can only locate the location of caregivers and cannot effectively supervise the nursing process.

[0030] Therefore, there is an urgent need for a nursing behavior compliance auditing method that combines privacy-free image collection, recognition of nursing actions, and effective supervision of the nursing process.

[0031] In summary, this application provides a method for auditing compliance of nursing practices. For details, please refer to [link / reference needed]. Figure 1 , Figure 1 This is a flowchart illustrating a radar-based nursing behavior compliance audit method provided in an embodiment of this application. The nursing behavior compliance audit method includes the following steps 101 to 105.

[0032] Step 101: Detect targets from the collected radar echo data and generate a 2D point cloud of the target based on the target detection results.

[0033] Multi-channel millimeter-wave radar is used to collect spatial electromagnetic wave reflection signals. The echo data is processed for target detection. Then, by analyzing multi-dimensional features such as distance, velocity, and angle in the signal, the position information of effective target points is extracted, thereby generating 2D point cloud data that represents the spatial distribution of the target. This point cloud data contains the target's coordinate information, providing a basic input for subsequent human target recognition.

[0034] In this embodiment of the application, target detection is performed on the collected radar echo data, and a 2D point cloud of the target is generated based on the target detection result. This includes: preprocessing the collected radar echo signal to obtain a multi-dimensional echo signal containing information in the range dimension, velocity dimension, and angle dimension; performing target detection based on the multi-dimensional echo signal; and generating a 2D point cloud of the target based on the target detection result.

[0035] Specifically, a multi-channel millimeter-wave radar continuously transmits electromagnetic waves into the monitoring space and receives echo signals reflected from objects. After signal preprocessing such as signal amplification, mixing, and analog-to-digital conversion, a multi-dimensional echo signal containing information in the range, velocity, and angle dimensions is obtained. Then, power spectrum analysis is performed on the multi-dimensional echo signal, and target detection algorithms such as constant false alarm rate are used to determine the existence of the target and parameters such as range and velocity. For the effective target points detected, angle and range information are obtained, and the range, velocity, and angle information are mapped into two-dimensional coordinates to generate a 2D point cloud representing the spatial distribution of the target.

[0036] In this embodiment, the acquired radar echo signal is preprocessed to obtain a multidimensional echo signal containing range, velocity, and angle dimensions. This includes: preprocessing the acquired raw radar echo signal to obtain a first discrete echo signal y(m,n,k); where m is the slow time dimension, representing the m-th linear frequency modulated continuous wave signal, n is the fast time dimension, representing the n-th sampling point, and k is the antenna dimension, representing the received signal of the k-th channel; performing a fast Fourier transform on the first discrete echo signal in the fast time dimension to obtain a second discrete echo signal y′(m,r,k); where the second discrete echo signal is a range-slow time-antenna dimension signal, r∈[1,N], representing range cell sampling; and performing range clutter suppression and coherent accumulation on the second discrete echo signal to obtain an initial multidimensional echo signal. The final multidimensional echo signal is obtained by performing a Fast Fourier Transform on the initial multidimensional echo signal in the slow time dimension. Among them, the multidimensional echo signal is a range-Doppler-antenna dimensional signal, v∈[1,M], which represents Doppler element sampling.

[0037] Specifically, firstly, the radar continuously transmits electromagnetic wave signals into space. After being reflected by objects, the signals are received by the radar receiver. Then, after being sampled by a signal amplifier, mixer, and ADC, a discrete echo signal containing the distance, velocity, and angle dimensions is obtained, which is the first discrete echo signal.

[0038] The first discrete echo signal can be represented as y(m,n,k), where m is the slow time dimension, representing the m-th linear frequency modulated continuous wave signal; n is the fast time dimension, representing the n-th sampling point; and k is the antenna dimension, representing the received signal of the k-th channel.

[0039] Then, based on the first discrete echo signal, a Fast Fourier Transform is first performed in the fast time dimension to convert the signal from the time domain to the frequency domain, resulting in the second discrete echo signal. The second discrete echo signal, also known as the range-slow time-antenna dimension signal, can be represented as y′(m,r,k), where r∈[1,N], representing range cell sampling.

[0040] Furthermore, range-dimensional clutter suppression and coherent accumulation are performed on the second discrete echo signal. Environmental noise and non-target echo interference are filtered out using methods such as moving average algorithms or time-domain accumulation, resulting in the multidimensional signal after clutter suppression and coherent accumulation, i.e., the initial multidimensional echo signal, which can be expressed as:

[0041] Finally, a Fast Fourier Transform is performed on the initial multidimensional echo signal in the slow time dimension to further extract the target velocity information, resulting in the final multidimensional echo signal, i.e., the range-Doppler-antenna dimension signal, which can be expressed as: Where v∈[1,M], it represents Doppler unit sampling.

[0042] It is understood that the embodiments of this application use multi-channel millimeter-wave radar for second-level compliance audit of nursing behavior. It can be either a single-transmitter multi-receiver radar or a multi-transmitter multi-receiver radar. This application does not make any specific limitation on this.

[0043] In this embodiment of the application, target detection based on the multidimensional echo signal includes: acquiring the Doppler power spectrum of the multidimensional echo signal; extracting peaks from the Doppler power spectrum based on a constant false alarm rate algorithm, and performing target detection on the extracted peak points to obtain target detection results; wherein, the target detection results include valid target points.

[0044] Specifically, the multidimensional echo signal contains information in the range dimension r, velocity dimension v, and antenna dimension k, taking the range-Doppler-antenna dimension signal. The power spectrum of the signal can be used to obtain the Doppler power spectrum. By analyzing the Doppler power spectrum of the signal, the presence of a target within the radar detection range and the target's distance and velocity information can be directly reflected. Then, the peak values ​​in the power spectrum are extracted using the Constant False Alarm Rate (CFAR) algorithm. The CFAR algorithm specifically includes Cell-Averaging Constant False Alarm Rate (CA-CFAR) and Ordered Statistics Constant False Alarm Rate (OS-CFAR). By setting a detection threshold that matches the intensity of environmental clutter, the peak points corresponding to the real target are screened out, noise and interference are eliminated, and valid target points are obtained, thereby determining the existence of the target and its preliminary position and velocity parameters.

[0045] Furthermore, a target 2D point cloud is generated based on the target detection results, including: extracting the range-Doppler index of the effective target points; performing beamforming based on the multidimensional echo signal corresponding to the range-Doppler index to extract the angle index of the effective target points; establishing a spatial coordinate system based on the radar installation method, and obtaining the 2D coordinates of the effective target points based on the range-Doppler index and the angle index to generate the target 2D point cloud.

[0046] Specifically, firstly, the range-Doppler (v,r) index of the effective target point is extracted. This index corresponds to the range and velocity characteristics of the target in the multidimensional echo signal. Then, the index corresponding to the above index is taken... The antenna-dimensional signal is used for beamforming, and the peak power spectrum energy index after beamforming is taken as the angle index corresponding to the effective points. Thus, the distance, velocity, angle, and energy information of each effective point of the target are known, enabling precise target location. Commonly used beamforming methods include Digital Beamforming (DBF), Multiple Signal Classification (MUSIC), and Minimum Variance Distortionless Response (MVDR) algorithm (also known as the Capon algorithm). Finally, a spatial coordinate system is established according to the millimeter-wave radar installation method (the spatial coordinate system varies depending on the installation method; common installation methods include side mounting at 45°, side mounting, top mounting, etc.). In the spatial coordinate system, the coordinates (x, y, y) of all effective points of the target can be obtained using the distance and angle information. i ,y i ), that is, the coordinates of all point cloud imaging points. All coordinate points constitute the target 2D point cloud, which intuitively represents the spatial distribution of the human body within the radar detection range.

[0047] Step 102: Perform human target recognition based on the target's 2D point cloud.

[0048] The generated 2D point cloud of the target is analyzed, and human targets are identified through spatial distribution characteristics and motion characteristics. This step can realize the existence judgment, quantity estimation and position differentiation of human targets within the detection range, and enable trajectory tracking processing in subsequent steps for further identification of nursing actions.

[0049] In this embodiment of the application, human target recognition based on target 2D point cloud includes: clustering the target 2D point cloud; determining the number of human targets based on the number of point clouds and centroid distance in the clustering results based on boundary prior information; and identifying the caregiver and the person being cared for when there are two human targets.

[0050] Specifically, after the point cloud data is generated, the radar point cloud needs to be clustered. Clustering algorithms include, but are not limited to, DBSCAN (Density-Based Spatial Clustering of Applications with Noise), as well as K-means, Divisive Clustering, etc. Based on the spatial distribution characteristics of the point cloud, adjacent points are aggregated into clusters, thereby separating point cloud sets of different targets. In detail, taking the DBSCAN clustering algorithm as an example, clustering can be divided into three steps: 1) Find the number of samples in the neighborhood of each sample. If the number is greater than or equal to the set minimum number, then the sample is a core point; 2) Find the samples that are directly reachable and density-reachable from each core sample, and these samples are also core samples. All non-core samples are temporarily ignored; 3) If a non-core sample is within the -neighborhood of a core sample, then the non-core sample is a boundary sample; otherwise, it is noise.

[0051] Then, prior information about the scene boundary is introduced. Combined with the point cloud quantity and centroid distance features from the clustering results, the number of human targets is determined. Furthermore, when the number of targets is determined to be two, the identity of the person is identified based on the positional relationship between the target point cloud and the boundary. The person being cared for is usually located near or inside the boundary (e.g., the bed), and their point cloud distribution is closer to the boundary center area. The caregiver, as the service provider, usually has their point cloud distribution located outside the boundary or in the surrounding activity area. Therefore, by calculating the distance between the centroid of the two point cloud clusters and the boundary center, combined with the point cloud quantity distribution features, the identity attributes of the two targets can be determined. It is understood that in this embodiment, the boundary information is set as the bed boundary in the home-based elderly care scenario.

[0052] Furthermore, in this embodiment of the application, based on boundary prior information, the number of human targets is determined by the number of point clouds and centroid distance in the clustering results, including:

[0053] When the number of clusters in the clustering result is one, the point cloud in the cluster is divided into an inbound point cloud set and an outbound point cloud set based on the boundary prior information. If the number of points in the inbound point cloud set is greater than the first threshold and the number of points in the outbound point cloud set is greater than the second threshold, then the number of human targets is determined to be two; otherwise, the number of human targets is determined to be one.

[0054] When there are two clusters in the clustering result, the distance between the centroids of the two clusters is calculated. If the distance between the centroids is greater than the preset centroid distance threshold, the number of human targets is determined to be two; otherwise, the number of human targets is determined to be one.

[0055] When the number of clusters in the clustering results is greater than two, the number of human targets is determined to be two.

[0056] Specifically, based on the clustering results, multiple human targets inside and outside the boundary can be separated and clustered. In this embodiment, the boundary prior information is specifically set as the boundary of the bed. With the radar as the origin, the bed boundary information should be the left boundary d. l Right boundary d r , front boundary d f , back boundary d b Since radar positions are often located from the head of the bed to the foot of the bed, the rear boundary d b The value is often 0. Separation and clustering of multiple human targets inside and outside the bed are performed. Based on the clustering results, several cases are mainly identified:

[0057] When the clustering result is 1, that is, when the number of clusters in the clustering result is one, the point cloud in the cluster is divided into an in-bed point cloud set and an out-of-bed point cloud set based on the boundary prior information. If the number of point clouds in the in-bed point cloud set is n in Greater than the first threshold N in And the number n of point clouds concentrated outside the bed out Greater than the second threshold N out If the condition is met, the number of human targets is determined to be two; otherwise, the number of human targets is determined to be one.

[0058] When the clustering result is 2, that is, when there are two clusters in the clustering result, the centroid distance between the two clusters is calculated. If the centroid distance is greater than the preset centroid distance threshold d, the cluster centroid distance is considered. T If the condition is met, the number of human targets is determined to be two; otherwise, the number of human targets is determined to be one.

[0059] When the clustering result is greater than 2, that is, when the number of clusters in the clustering result is greater than two, the number of human targets is directly determined to be two.

[0060] It is understandable that when the clustering result is 0, that is, when the number of clusters in the clustering result is 0, it means that there is no one at present.

[0061] In this embodiment of the application, when there are two human targets, identifying the caregiver and the person being cared for includes:

[0062] When the number of clusters in the clustering result is one and the number of human targets is two, calculate the first centroid coordinates of the point cloud set inside the boundary and the second centroid coordinates of the point cloud set outside the boundary; calculate the first distance between each point cloud coordinate and the first centroid coordinate and the second distance between each point cloud coordinate and the second centroid coordinate. If the first distance is greater than or equal to the second distance, the point cloud is assigned to the first centroid, and the cluster formed by all the point clouds assigned to the first centroid is identified as the person being cared for; if the first distance is less than the second distance, the point cloud is assigned to the second centroid, and the cluster formed by all the point clouds assigned to the second centroid is identified as the person being cared for.

[0063] When there are two clusters in the clustering results and two human targets are identified, the third and fourth centroid coordinates of the two clusters are calculated respectively. The boundary center coordinates are calculated based on the boundary prior information, and the third distance between the third centroid coordinate and the boundary center coordinate and the fourth distance between the fourth centroid coordinate and the boundary center coordinate are calculated respectively. If the third distance is greater than or equal to the fourth distance, the cluster corresponding to the third centroid coordinate is identified as a caregiver, and the cluster corresponding to the fourth centroid coordinate is identified as a person being cared for. If the third distance is less than the fourth distance, the cluster corresponding to the third centroid coordinate is identified as a person being cared for, and the cluster corresponding to the fourth centroid coordinate is identified as a caregiver.

[0064] When the number of clusters in the clustering results is greater than two, the two clusters with the most point clouds are selected, and the fifth and sixth centroid coordinates of each cluster are calculated. The fifth distance between each point cloud coordinate and the fifth centroid coordinate, and the sixth distance between each point cloud coordinate and the sixth centroid coordinate are calculated. If the fifth distance is greater than or equal to the sixth distance, the point cloud is assigned to the fifth centroid, and the seventh centroid coordinates of all point clouds assigned to the fifth centroid are calculated. If the fifth distance is less than the sixth distance, the point cloud is assigned to the sixth centroid, and the seventh centroid coordinates of all point clouds assigned to the sixth centroid are calculated. The eighth centroid coordinates of the cluster are calculated; the boundary center coordinates are calculated based on the boundary prior information, and the seventh distance between the seventh centroid coordinates and the boundary center coordinates and the eighth distance between the eighth centroid coordinates and the boundary center coordinates are calculated respectively; the first identification parameter is calculated based on the seventh distance and the corresponding cluster, and the second identification parameter is calculated based on the eighth distance and the corresponding cluster; the first identification parameter and the second identification parameter are compared, and the cluster with the larger identification parameter value in the comparison result is identified as the person being cared for, and the cluster with the smaller identification parameter value in the comparison result is identified as the caregiver.

[0065] In simple terms, when the clustering result contains only one cluster, the centroid will be recalculated based on the point clouds inside and outside the bed to obtain the centroid inside and outside the bed (x). in ,y in ), (x out ,y out After clustering, the point cloud will have its distance calculated between it and the two centroids, and then redistributed based on the distance. The distance formula is as follows:

[0066]

[0067] After the allocation is completed, the two types of point clouds are the point clouds of two people. Since the person being cared for is often closer to the center of the bed, the point cloud obtained by the allocation outside the centroid of the bed can be directly identified as the caregiver, and the point cloud obtained by the allocation inside the centroid of the bed can be identified as the person being cared for.

[0068] When the clustering results contain two clusters, the centroids of the two clusters are calculated, and the coordinates of the bed center are also calculated. The coordinates of the bed center are expressed as follows:

[0069] (x center ,y center )=((d l +d r ) / 2,(d f +d b ) / 2),

[0070] Based on the distance from the centroid of the cluster to the center of the bed, clusters that are closer to the center are identified as caregivers, and clusters that are farther away are identified as caregivers.

[0071] When the number of clusters in the clustering result is greater than two, find the two largest cluster centroids (x1, y1) and (x2, y2). Then, redistribute all the clustered point clouds according to their distance from the two centroids to obtain the point clouds of two individuals, and recalculate the centroids (x1, y1) and (x2, y2). p1 ,y p1 ), (x p2 ,y p2 The number of point clouds within the bed in the clustered class is n. in The number of point clouds outside the bed is n out If the distance from the center of mass to the center of the bed is d, then the two types of judgments about the person being cared for depend on the following formula:

[0072]

[0073] Among them, those with a larger T value were the people being cared for.

[0074] Step 103: Track the trajectory of the identified human target to obtain the trajectory coordinate sequence.

[0075] For the identified human target, the movement trajectory of the target is continuously tracked by associating point cloud data over time, and a trajectory coordinate sequence containing timestamps is obtained. This trajectory sequence records the target's movement path in space, and can be used to extract nursing behavior features in subsequent steps to provide data support.

[0076] Specifically, after obtaining the clustering results in the aforementioned steps, the clusters are assigned using a clustering assignment algorithm, and then a trajectory tracking algorithm is used for trajectory tracking, including trajectory creation, trajectory updating, and trajectory deletion. Commonly used clustering assignment algorithms include, but are not limited to, the Munkres' Assignment Algorithm and the Joint Probabilistic Data Association algorithm, used to assign point cloud clustering results to different trajectories. Commonly used trajectory tracking algorithms include, but are not limited to, Stanley Control, Model Predictive Control (MPC), Extended Kalman Filter (EKF), and Particle Filter algorithms. Finally, based on the tracking results, a decision is made on whether to create, update, or delete a trajectory.

[0077] Step 104: Extract nursing behavior feature parameters based on trajectory coordinate sequence, and determine the compliance of nursing behavior based on nursing behavior feature parameters.

[0078] Specifically, based on the target trajectory coordinate sequence, feature parameters representing nursing behavior are extracted, and then the feature parameters are fused and analyzed through preset judgment rules. After comparison with the compliance threshold, the compliance judgment result of nursing behavior is generated.

[0079] In this embodiment, the nursing behavior feature parameters include nursing large displacement parameters, nursing target existence parameters, nursing large movement parameters, and nursing movement continuity parameters; the nursing behavior feature parameters are extracted based on the trajectory coordinate sequence, including: obtaining the trajectory coordinate sequence corresponding to the human target outside the boundary; setting a sliding time window to continuously record the maximum displacement within each time window; wherein, the maximum displacement D max The expression is:

[0080] D max =max t＜i＜j<t+Twin D ij ,

[0081] Where t is the starting point of the time window, Twin is the length of the sliding time window, i and j are any two points in the trajectory coordinate sequence within the sliding time window, and D is the starting point of the time window. ij D represents the displacement between i and j. ij The expression is:

[0082]

[0083] The nursing displacement parameter σ1 is extracted based on the maximum displacement; the expression for the nursing displacement parameter σ1 is:

[0084]

[0085] Where N is the duration of the nursing action, Twin is the sliding time window length, u is the step function, and Dthre is the preset distance threshold; the number of targets in the radar detection space is obtained based on the trajectory coordinate sequence, and the nursing target existence parameter σ2 is extracted; the expression for the nursing target existence parameter σ2 is:

[0086]

[0087] Where Pt is the number of targets in the radar detection space at time t; the body motion index is obtained based on the radar echo signal, and the nursing gross motion parameter σ3 is extracted; where the expression of the nursing gross motion parameter σ3 is:

[0088]

[0089] Among them, B t Let t be the body movement index, and Bthre be the preset body movement index threshold. When there are two targets in the radar detection space, the algorithm is used to determine whether the nursing actions of the targets within the preset time threshold meet the continuity condition, and the nursing action continuity parameter σ4 is extracted based on the judgment result.

[0090] Specifically, the nursing behavior characteristic parameters further include four main parameters: nursing displacement parameters, nursing goal existence parameters, nursing gross motor parameters, and nursing action continuity parameters. Nursing displacement parameters are used to reflect the intensity of nursing staff's activities in the area outside the bed. Nursing goal existence parameters are used to characterize the effectiveness of the number of goals in the monitoring space. Nursing gross motor parameters are used to quantify the intensity of actions during the nursing process. Nursing action continuity parameters are used to reflect the continuity of two-person nursing behavior.

[0091] (1) Nursing large displacement parameters:

[0092] Obtain the trajectory coordinate sequence corresponding to the human target outside the boundary. Using a sliding time window (usually several seconds to tens of seconds) and the point cloud sampling time as the step time, calculate the maximum displacement for each time window. Use the number of maximum displacements throughout the entire nursing process as the displacement parameter. The N coordinate values ​​of the target trajectory outside the bed during the nursing process can be represented as follows:

[0093] P={(x t ,y t )|t∈(1,N)},

[0094] Assuming the sliding time window length is Twin, then the maximum displacement Dmax The expression is:

[0095] D max =max t＜i＜j＜t+Twin D ij ,

[0096] Where t is the starting point of the time window, i and j are any two points in the trajectory coordinate sequence within the sliding time window, and D ij D represents the displacement between i and j. ij The expression is:

[0097]

[0098] The nursing displacement parameter σ1 is extracted based on the maximum displacement; the expression for the nursing displacement parameter σ1 is:

[0099]

[0100] Where N is the duration of the nursing action, Twin is the length of the sliding time window, u is the step function, and Dthre is the preset distance threshold, which is generally set to tens to hundreds of centimeters.

[0101] (2) Nursing goals have parameters:

[0102] Trajectory tracking can identify the number of targets within the radar detection space, while nursing parameter extraction involves statistically analyzing the number of targets within the radar detection space. Let Pt be the number of targets monitored by the radar at time t, then the nursing parameter σ² can be expressed by the following formula:

[0103]

[0104] Where N is the duration of the nursing action, and u is the step function.

[0105] (3) Nursing gross motor parameters:

[0106] First, the motion index is obtained based on the radar echo signal. The motion index is used to calculate the intensity of motion of moving targets within the radar detection range at each moment. Commonly used motion index methods are divided into time-domain analysis methods and frequency-domain analysis methods. Time-domain analysis methods include amplitude threshold detection methods, energy spectrum methods, integral methods, root mean square error methods, and optimized combinations of these methods. Frequency-domain analysis methods mainly characterize the motion index by the ratio of the number of spectral energy values ​​greater than a set threshold to the total number of signals. The nursing large motion parameter is to count the motion index exceeding the set threshold. Let the motion index at time t be B. t The extraction of the body motion parameter σ3 can be expressed by the following formula:

[0107]

[0108] Among them, Bt Let t be the body movement index, and Bthre be the preset body movement index threshold, which is generally set to 30-50.

[0109] (4) Nursing action continuity parameters:

[0110] For cases involving two nurses, the position sequence of each nurse is calculated based on their tracking trajectory over a certain period of time at the current moment. It is then determined whether both nurses are within a specific area. If this condition is met, the current nursing action is considered continuous; otherwise, it is considered discontinuous. The sequence of continuous states generated each second during the nursing process is accumulated using a sliding window and its validity is assessed. A valid result is assigned a value of 1, and an invalid result is assigned a value of 0. The validity results are then summed to obtain the nursing action continuity parameter σ4.

[0111] In this embodiment of the application, the compliance determination of nursing behavior based on nursing behavior feature parameters includes: fusing nursing displacement parameters, nursing goal existence parameters, nursing large movement parameters, and nursing movement continuity parameters based on preset weights to obtain a nursing behavior score; wherein, the expression for the nursing behavior score is:

[0112] score=(w1σ1+w2σ2+w3σ3+w4σ4)*100 / (4*N), where w1, w2, w3, and w4 are preset weight parameters, and w1+w2+w3+w4=1; nursing behavior compliance is determined based on nursing behavior score.

[0113] Specifically, after obtaining the parameters, the four extracted parameters need to be weighted and fused to obtain the nursing behavior score. The expression for the nursing behavior score is:

[0114] score=(w1σ1+w2σ2+w3σ3+w4σ4)*100 / (4*N), where w1, w2, w3, and w4 are preset weight parameters, and w1+w2+w3+w4=1, N is the duration of the nursing behavior, and the denominator 4N is used to normalize the score to the interval [0, 100] for easy and intuitive evaluation. The specific values ​​of these four weight parameters are determined by training and learning with actual data samples.

[0115] If the work order determination result is called result, then it can be expressed as:

[0116] result = u(score - thre),

[0117] In the formula, thre is the set work order judgment threshold, which needs to be generated based on the statistical analysis of the caregiver's actions and behaviors during the actual nursing process.

[0118] Step 105: Generate a nursing behavior compliance audit report based on the nursing behavior compliance determination results.

[0119] Specifically, based on the compliance assessment results of nursing behaviors, an audit report is generated that includes the target trajectory, statistical analysis of characteristic parameters, and compliance conclusions. This report can be used for nursing service quality assessment and work order auditing, providing data support for elderly care service management.

[0120] As described above, the embodiments of this application first perform target detection on the collected radar echo data and generate a 2D point cloud of the target based on the target detection results. Then, human target recognition is performed based on the 2D point cloud of the target, followed by trajectory tracking of the recognized human target to obtain a trajectory coordinate sequence. Next, nursing behavior feature parameters are extracted based on the trajectory coordinate sequence, and nursing behavior compliance is determined based on the nursing behavior feature parameters. Finally, a nursing behavior compliance audit report is generated based on the nursing behavior compliance determination result. The nursing behavior compliance audit method proposed in this invention does not require the collection of actual image data, can identify personnel in the scene without infringing on privacy, and can simultaneously identify nursing behaviors. It can monitor the entire nursing process, effectively improving the effectiveness of nursing process supervision. Furthermore, it can effectively judge the compliance of nursing behaviors and provide an audit report, which can effectively reduce the audit time cost of nursing work orders.

[0121] It should be understood that the sequence number of each step in this embodiment does not imply the order in which the steps are executed. The execution order of each step should be determined by its function and internal logic, and should not constitute a unique limitation on the implementation process of this application embodiment.

[0122] In summary, the detailed process of the nursing behavior compliance audit method involved in the embodiments of this application can be found in [reference needed]. Figure 2 Specifically:

[0123] Step 201: Perform signal preprocessing on the collected radar echo signal to obtain a multidimensional echo signal containing information in the range dimension, velocity dimension, and angle dimension;

[0124] Step 202: Perform target detection based on multidimensional echo signals, and generate a 2D point cloud of the target based on the target detection results;

[0125] Step 203: Cluster the target 2D point cloud;

[0126] Step 204: Based on the boundary prior information, determine the number of human targets by the number of point clouds and the centroid distance in the clustering results;

[0127] Step 205: When there are two human targets, identify the caregiver and the person being cared for;

[0128] Step 206: Track the identified human target to obtain a trajectory coordinate sequence;

[0129] Step 207: Extract nursing large displacement parameters, nursing target existence parameters, nursing large movement parameters, and nursing movement continuity parameters based on the trajectory coordinate sequence;

[0130] Step 208: Based on preset weights, the nursing displacement parameters, nursing goal existence parameters, nursing major movement parameters, and nursing movement continuity parameters are fused and judged to obtain the nursing behavior score;

[0131] Step 209: Determine the compliance of nursing behaviors based on nursing behavior scores;

[0132] Step 210: Generate a nursing behavior compliance audit report based on the nursing behavior compliance determination results.

[0133] For a more detailed process of each step in steps 201 to 210, please refer to the relevant sections shown above. The embodiments of this application will not be repeated here.

[0134] Please see Figure 3 , Figure 3 This application provides a radar-based nursing behavior compliance audit system. This system can be used to implement the nursing behavior compliance audit method involved in this application. The radar-based nursing behavior compliance audit system 300 mainly includes:

[0135] The point cloud generation module 301 is used to perform target detection on the collected radar echo data and generate a 2D point cloud of the target based on the target detection results.

[0136] Target recognition module 302 is used for human target recognition based on target 2D point cloud;

[0137] The trajectory tracking module 303 is used to track the trajectory of the identified human target and obtain a trajectory coordinate sequence;

[0138] The behavior determination module 304 is used to extract nursing behavior feature parameters based on the trajectory coordinate sequence, and to determine the compliance of nursing behavior based on the nursing behavior feature parameters.

[0139] The report generation module 305 is used to generate a nursing behavior compliance audit report based on the nursing behavior compliance determination results.

[0140] In some embodiments of this example, when the point cloud generation module 301 performs the function of detecting targets from collected radar echo data and generating a 2D point cloud of the target based on the target detection results, it is used to: perform signal preprocessing on the collected radar echo signals to obtain multidimensional echo signals containing range, velocity, and angle information; perform target detection based on the multidimensional echo signals; and generate a 2D point cloud of the target based on the target detection results.

[0141] In some embodiments of this example, when the point cloud generation module 301 performs the function of preprocessing the acquired radar echo signal to obtain a multidimensional echo signal containing range, velocity, and angle dimensions, it is used to: preprocess the acquired original radar echo signal to obtain a first discrete echo signal y(m,n,k); where m is the slow time dimension, representing the m-th linear frequency modulated continuous wave signal, n is the fast time dimension, representing the n-th sampling point, and k is the antenna dimension, representing the received signal of the k-th channel; perform a fast Fourier transform on the first discrete echo signal in the fast time dimension to obtain a second discrete echo signal y′(m,r,k); where the second discrete echo signal is a range-slow time-antenna dimension signal, r∈[1,N], representing range cell sampling; and perform range clutter suppression and coherent accumulation on the second discrete echo signal to obtain an initial multidimensional echo signal. The final multidimensional echo signal is obtained by performing a Fast Fourier Transform on the initial multidimensional echo signal in the slow time dimension. Among them, the multidimensional echo signal is a range-Doppler-antenna dimensional signal, v∈[1,M], which represents Doppler element sampling.

[0142] In some embodiments of this example, when the point cloud generation module 301 performs the function of target detection based on the multidimensional echo signal, it is used to: acquire the Doppler power spectrum of the multidimensional echo signal; extract the peaks of the Doppler power spectrum based on the constant false alarm rate algorithm, and perform target detection on the extracted peak points to obtain the target detection result; wherein, the target detection result includes valid target points.

[0143] In some embodiments of this example, when the point cloud generation module 301 performs the function of generating a target 2D point cloud based on the target detection result, it is used to: extract the range-Doppler index of the effective target point; perform beamforming based on the multidimensional echo signal corresponding to the range-Doppler index, and extract the angle index of the effective target point; establish a spatial coordinate system based on the radar installation method, and obtain the 2D coordinates of the effective target point based on the range-Doppler index and the angle index, thereby generating a target 2D point cloud.

[0144] In some embodiments of this example, when the target recognition module 302 performs the function of human target recognition based on the target 2D point cloud, it is used to: cluster the target 2D point cloud; determine the number of human targets based on the number of point clouds and centroid distance in the clustering results based on boundary prior information; and identify the caregiver and the person being cared for when there are two human targets.

[0145] Furthermore, in some embodiments of this example, when the target recognition module 302 performs the function of determining the number of human targets based on boundary prior information and the number of point clouds and centroid distance in the clustering results, it is specifically used as follows: when the number of clusters in the clustering results is one, the point clouds in the cluster are divided into an in-boundary point cloud set and an out-of-boundary point cloud set based on boundary prior information. If the number of point clouds in the in-boundary point cloud set is greater than a first threshold and the number of point clouds in the out-of-boundary point cloud set is greater than a second threshold, then the number of human targets is determined to be two; otherwise, the number of human targets is determined to be one. When the number of clusters in the clustering results is two, the centroid distance between the centroids of the two clusters is calculated. If the centroid distance is greater than a preset centroid distance threshold, then the number of human targets is determined to be two; otherwise, the number of human targets is determined to be one. When the number of clusters in the clustering results is greater than two, the number of human targets is determined to be two.

[0146] Furthermore, in some embodiments of this example, when the target recognition module 302 performs the function of identifying caregivers and caregivers when there are two human targets, it is specifically used to: when the number of clusters in the clustering result is one and the number of human targets is determined to be two, calculate the first centroid coordinates of the point cloud set within the boundary and the second centroid coordinates of the point cloud set outside the boundary; calculate the first distance between each point cloud coordinate and the first centroid coordinate and the second distance between each point cloud coordinate and the second centroid coordinate; if the first distance is greater than or equal to the second distance, then assign the point cloud to the first centroid and identify the cluster formed by all point clouds assigned to the first centroid as caregivers; if the first distance is less than the second centroid coordinate, then... If the distance is two, the point cloud is assigned to the second centroid, and the clusters formed by all point clouds assigned to the second centroid are identified as nursing staff. When there are two clusters in the clustering result and two human targets are identified, the third and fourth centroid coordinates of the two clusters are calculated respectively. The boundary center coordinates are calculated based on the boundary prior information, and the third distance between the third centroid coordinates and the boundary center coordinates and the fourth distance between the fourth centroid coordinates and the boundary center coordinates are calculated respectively. If the third distance is greater than or equal to the fourth distance, the cluster corresponding to the third centroid coordinates is identified as nursing staff, and the cluster corresponding to the fourth centroid coordinates is identified as the person being cared for. If the third distance is less than the fourth distance... If the cluster corresponding to the third centroid coordinate is identified as the person being cared for, and the cluster corresponding to the fourth centroid coordinate is identified as the caregiver, then when the number of clusters in the clustering result is greater than two, the two clusters with the most point clouds are obtained, and the fifth and sixth centroid coordinates of the two clusters are calculated respectively. The fifth distance between each point cloud coordinate and the fifth centroid coordinate and the sixth distance between each point cloud coordinate and the sixth centroid coordinate are calculated respectively. If the fifth distance is greater than or equal to the sixth distance, the point cloud is assigned to the fifth centroid, and the seventh centroid coordinate of the cluster formed by all point clouds assigned to the fifth centroid is calculated. If the fifth distance is less than the sixth distance, the point cloud is assigned to the sixth centroid, and the seventh centroid coordinate of the cluster formed by all point clouds assigned to the fifth centroid is calculated. The coordinates of the eighth centroid of the clusters formed by point clouds assigned to the sixth centroid are determined. The coordinates of the boundary center are calculated based on the boundary prior information, and the seventh distance between the seventh centroid coordinates and the boundary center coordinates and the eighth distance between the eighth centroid coordinates and the boundary center coordinates are calculated respectively. If the seventh distance is greater than or equal to the eighth distance, the clusters formed by all point clouds assigned to the seventh centroid are identified as nursing staff, and the clusters formed by all point clouds assigned to the eighth centroid are identified as nursing staff. If the seventh distance is less than the eighth distance, the clusters formed by all point clouds assigned to the seventh centroid are identified as nursing staff, and the clusters formed by all point clouds assigned to the eighth centroid are identified as nursing staff.

[0147] In some embodiments of this example, the nursing behavior feature parameters in the behavior determination module 304 include nursing large displacement parameters, nursing target existence parameters, nursing large movement parameters, and nursing movement continuity parameters; when the trajectory tracking module 303 performs the function of extracting nursing behavior feature parameters based on trajectory coordinate sequences, it is used to: obtain the trajectory coordinate sequence corresponding to the human target outside the boundary; set a sliding time window to continuously record the maximum displacement within each time window; wherein, the maximum displacement D max The expression is:

[0148] D max =max t<i<j<t+Twin D ij ,

[0149] Where t is the starting point of the time window, Twin is the length of the sliding time window, i and j are any two points in the trajectory coordinate sequence within the sliding time window, and D is the starting point of the time window. ij D represents the displacement between i and j. ij The expression is:

[0150]

[0151] The nursing displacement parameter σ1 is extracted based on the maximum displacement; the expression for the nursing displacement parameter σ1 is:

[0152]

[0153] Where N is the duration of the nursing action, Twin is the sliding time window length, u is the step function, and Dthre is the preset distance threshold; the number of targets in the radar detection space is obtained based on the trajectory coordinate sequence, and the nursing target existence parameter σ2 is extracted; the expression for the nursing target existence parameter σ2 is:

[0154]

[0155] Where Pt is the number of targets in the radar detection space at time t; the body motion index is obtained based on the radar echo signal, and the nursing gross motion parameter σ3 is extracted; where the expression of the nursing gross motion parameter σ3 is:

[0156]

[0157] Among them, B t Let t be the body movement index, and Bthre be the preset body movement index threshold. When there are two targets in the radar detection space, the algorithm is used to determine whether the nursing actions of the targets within the preset time threshold meet the continuity condition, and the nursing action continuity parameter σ4 is extracted based on the judgment result.

[0158] In some embodiments of this example, when the behavior determination module 304 performs the function of determining the compliance of nursing behavior based on nursing behavior feature parameters, it is used to: fuse and determine the nursing large displacement parameters, nursing target existence parameters, nursing large movement parameters, and nursing movement continuity parameters based on preset weights to obtain a nursing behavior score; wherein, the expression for the nursing behavior score is:

[0159] score=(w1σ1+w2σ2+w3σ3+w4σ4)*100 / (4*N),

[0160] Among them, w1, w2, w3, and w4 are preset weight parameters, and w1+w2+w3+w4=1; the compliance of nursing behavior is determined based on the nursing behavior score.

[0161] In detail, each module in the radar-based nursing behavior compliance audit system 300 provided in this embodiment of the invention adopts the same approach as described above during use. Figure 1 The same technical means are used for the compliance audit of nursing behavior in China, and can produce the same technical effects, so I will not go into details here.

[0162] Please see Figure 4 , Figure 4 A block diagram of a radar provided in an embodiment of this application.

[0163] like Figure 4 As shown, this application embodiment also provides a radar that can be used to implement the nursing behavior compliance audit method in the foregoing embodiments. The radar includes a memory 401, at least one processor 402, a signal generator 403, and a signal receiver 404. The memory 401 is used to store at least one program, and when the at least one program is executed by the at least one processor 402, the at least one processor 402 executes the nursing behavior compliance audit method provided in this application embodiment.

[0164] Please see Figure 5 , Figure 5 A block diagram of a computer-readable storage medium provided in an embodiment of this application.

[0165] like Figure 5 As shown, this application embodiment also provides a computer-readable storage medium 500, on which executable instructions 510 are stored. When the executable instructions 510 are executed, the nursing behavior compliance audit method provided in this application embodiment is executed.

[0166] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, compact disc read-only memory (CD-ROM), or any other form of storage medium known in the art.

[0167] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., Digital Video Disk, DVD), or a semiconductor medium (e.g., Solid State Disk).

[0168] It should be noted that the various embodiments in this application are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For product-related embodiments, since they are similar to method-related embodiments, the descriptions are relatively simple, and relevant parts can be referred to the descriptions of the method-related embodiments.

[0169] It should also be noted that, in this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0170] The above description of the disclosed embodiments enables those skilled in the art to implement or use the content of this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined in this application may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A radar-based method for auditing compliance of nursing behaviors, characterized in that, include: Target detection is performed on the collected radar echo data, and a 2D point cloud of the target is generated based on the target detection results; Cluster the target 2D point cloud; Based on boundary prior information, the number of human targets is determined by the number of point clouds and centroid distance in the clustering results. When there are two human targets, the caregiver and the person being cared for are identified. The identified human target is tracked to obtain a sequence of trajectory coordinates; Nursing behavior feature parameters are extracted based on the trajectory coordinate sequence, and the compliance of nursing behavior is determined based on the nursing behavior feature parameters; wherein, the nursing behavior feature parameters include nursing large displacement parameters, nursing goal existence parameters, nursing large movement parameters, and nursing movement continuity parameters; A nursing behavior compliance audit report is generated based on the nursing behavior compliance assessment results; The step of extracting nursing behavior feature parameters based on the trajectory coordinate sequence includes: Obtain the trajectory coordinate sequence corresponding to the human target outside the boundary; A sliding time window is set to continuously record the maximum displacement within each time window; wherein, the maximum displacement... The expression is: ， in, The time starting point of the time window is... To extend the sliding time window, and These are any two points in the trajectory coordinate sequence within the sliding time window. for and Displacement between The expression is: ； The nursing large displacement parameters are extracted based on the maximum displacement. Among them, the nursing large displacement parameters The expression is: ， in, N The duration of the nursing care activity. To extend the sliding time window, u It is a step function. Dthre The preset distance threshold; The number of targets within the radar detection space is obtained based on the trajectory coordinate sequence, and the existence parameters of the nursing targets are extracted. The nursing goals include parameters. The expression is: ， in, for The number of targets detected by radar in the space at any given time; The body movement index is obtained based on the radar echo signal, and the parameters of the nursing gross movements are extracted. Among them, the nursing major action parameters The expression is: ， in, for Motion index at all times. The preset body movement index threshold is used; When there are two targets in the radar detection space, a preset algorithm is used to determine whether the nursing actions of the targets within a preset time threshold meet the continuity condition, and the continuity parameters of the nursing actions are extracted based on the determination result. ; The step of determining compliance of nursing behavior based on the nursing behavior characteristic parameters includes: The nursing behavior score is obtained by fusing the nursing displacement parameters, nursing goal existence parameters, nursing major movement parameters, and nursing movement continuity parameters based on preset weights; wherein, the nursing behavior score The expression is: ， in, For preset weight parameters, and + + = 1; The compliance of nursing behaviors is determined based on the nursing behavior scores.

2. The nursing behavior compliance auditing method according to claim 1, characterized in that, The step of performing target detection on the acquired radar echo data and generating a 2D point cloud of the target based on the target detection results includes: The collected radar echo signals are preprocessed to obtain multidimensional echo signals containing information in the range, velocity, and angle dimensions. Target detection is performed based on the multidimensional echo signal, and a 2D point cloud of the target is generated based on the target detection results.

3. The nursing behavior compliance auditing method according to claim 2, characterized in that, The process of preprocessing the acquired radar echo signals to obtain multidimensional echo signals containing information in the range, velocity, and angle dimensions includes: The acquired raw radar echo signal is preprocessed to obtain the first discrete echo signal. ;in, Let be the slow time dimension, indicating the th A linear frequency modulated continuous wave signal For fast time dimension, it means the first... One sampling point, Let be the antenna dimension, and let represent the th . Received signals from each channel; The second discrete echo signal is obtained by performing a Fast Fourier Transform on the first discrete echo signal in a fast time dimension. The second discrete echo signal is a range-slow time-antenna dimension signal. , indicating distance cell sampling; Based on the second discrete echo signal, range clutter suppression and coherent accumulation are performed to obtain the initial multidimensional echo signal. ; Based on the initial multidimensional echo signal, a Fast Fourier Transform is performed in the slow time dimension to obtain the final multidimensional echo signal. The multidimensional echo signal is a range-Doppler-antenna dimensional signal. , indicating Doppler unit sampling.

4. The nursing behavior compliance auditing method according to claim 2, characterized in that, The target detection based on the multidimensional echo signal includes: Obtain the Doppler power spectrum of the multidimensional echo signal; The peak values ​​of the Doppler power spectrum are extracted based on the constant false alarm rate algorithm, and the extracted peak values ​​are used for target detection to obtain target detection results; wherein, the target detection results include valid target points.

5. The nursing behavior compliance auditing method according to claim 4, characterized in that, The generation of a target 2D point cloud based on the target detection results includes: Extract the distance-Doppler index of the effective target points; Beamforming is performed based on the multidimensional echo signal corresponding to the range-Doppler index to extract the angle index of the effective target point; A spatial coordinate system is established based on the radar installation method, and the 2D coordinates of the effective target points are obtained based on the range-Doppler index and the angle index, thereby generating a target 2D point cloud.

6. The method for auditing compliance of nursing behavior according to claim 1, characterized in that, The method of determining the number of human targets based on boundary prior information and the number of point clouds and centroid distance in the clustering results includes: When the number of clusters in the clustering result is one, the point cloud in the cluster is divided into an inbound point cloud set and an outbound point cloud set based on the boundary prior information. If the number of points in the inbound point cloud set is greater than the first threshold and the number of points in the inbound point cloud set is greater than the second threshold, then the number of human targets is determined to be two; otherwise, the number of human targets is determined to be one. When there are two clusters in the clustering result, the centroid distance between the two clusters is calculated. If the centroid distance is greater than the preset centroid distance threshold, the number of human targets is determined to be two; otherwise, the number of human targets is determined to be one. When the number of clusters in the clustering results is greater than two, the number of human targets is determined to be two.

7. The nursing behavior compliance auditing method according to claim 6, characterized in that, When there are two human targets, the identification of the caregiver and the person being cared for includes: When the number of clusters in the clustering result is one and the number of human targets is determined to be two, the first centroid coordinates of the point cloud set within the boundary and the second centroid coordinates of the point cloud set outside the boundary are calculated; the first distance between each point cloud coordinate and the first centroid coordinate and the second distance between each point cloud coordinate and the second centroid coordinate are calculated respectively. If the first distance is greater than or equal to the second distance, the point cloud is assigned to the first centroid, and the cluster formed by all the point clouds assigned to the first centroid is identified as the person being cared for; if the first distance is less than the second distance, the point cloud is assigned to the second centroid, and the cluster formed by all the point clouds assigned to the second centroid is identified as the person being cared for. When there are two clusters in the clustering results and two human targets are identified, the third centroid coordinates and the fourth centroid coordinates of the two clusters are calculated respectively; the boundary center coordinates are calculated based on the boundary prior information, and the third distance between the third centroid coordinates and the boundary center coordinates and the fourth distance between the fourth centroid coordinates and the boundary center coordinates are calculated respectively; if the third distance is greater than or equal to the fourth distance, the cluster corresponding to the third centroid coordinates is identified as a caregiver, and the cluster corresponding to the fourth centroid coordinates is identified as a person being cared for; if the third distance is less than the fourth distance, the cluster corresponding to the third centroid coordinates is identified as a person being cared for, and the cluster corresponding to the fourth centroid coordinates is identified as a caregiver. When the number of clusters in the clustering results is greater than two, the two clusters with the most point clouds are obtained, and the fifth centroid coordinates and sixth centroid coordinates of the two clusters are calculated respectively. The fifth distance between each point cloud coordinate and the fifth centroid coordinate, and the sixth distance between each point cloud coordinate and the sixth centroid coordinate are calculated respectively. If the fifth distance is greater than or equal to the sixth distance, the point cloud is assigned to the fifth centroid, and the seventh centroid coordinates of the clusters formed by all point clouds assigned to the fifth centroid are calculated. If the fifth distance is less than the sixth distance, the point cloud is assigned to the sixth centroid, and the seventh centroid coordinates of the clusters formed by all point clouds assigned to the sixth centroid are calculated. The coordinates of the eighth centroid of the cluster are calculated; the coordinates of the boundary center are calculated based on the boundary prior information, and the seventh distance between the seventh centroid coordinates and the boundary center coordinates and the eighth distance between the eighth centroid coordinates and the boundary center coordinates are calculated respectively; a first identification parameter is calculated based on the seventh distance and the corresponding cluster, and a second identification parameter is calculated based on the eighth distance and the corresponding cluster; the first identification parameter and the second identification parameter are compared, and the cluster with the larger identification parameter value in the comparison result is identified as the person being cared for, and the cluster with the smaller identification parameter value in the comparison result is identified as the caregiver.

8. A radar-based nursing behavior compliance audit system, characterized in that, include: The point cloud generation module is used to perform target detection on the collected radar echo data and generate a 2D point cloud of the target based on the target detection results. The target recognition module is used to: cluster the 2D point cloud of the target; determine the number of human targets based on the number of point clouds and centroid distance in the clustering results based on boundary prior information; and identify the caregiver and the person being cared for when there are two human targets. The trajectory tracking module is used to track the trajectory of the identified human target and obtain the trajectory coordinate sequence; The behavior determination module is used to extract nursing behavior feature parameters based on the trajectory coordinate sequence, and to determine the compliance of nursing behavior based on the nursing behavior feature parameters; wherein, the nursing behavior feature parameters include nursing large displacement parameters, nursing target existence parameters, nursing large movement parameters, and nursing movement continuity parameters; wherein, the extraction of nursing behavior feature parameters based on the trajectory coordinate sequence includes: obtaining the trajectory coordinate sequence corresponding to the human target outside the boundary; setting a sliding time window to continuously record the maximum displacement within each time window; wherein, the maximum displacement... The expression is: ， in, The time starting point of the time window is... To extend the sliding time window, and These are any two points in the trajectory coordinate sequence within the sliding time window. for and Displacement between The expression is: ； The nursing large displacement parameters are extracted based on the maximum displacement. Among them, the nursing large displacement parameters The expression is: ， in, N The duration of the nursing care activity. To extend the sliding time window, u It is a step function. Dthre The preset distance threshold; The number of targets within the radar detection space is obtained based on the trajectory coordinate sequence, and the existence parameters of the nursing targets are extracted. The nursing goals include parameters. The expression is: ， in, for The number of targets detected by radar in the space at any given time; The body movement index is obtained based on the radar echo signal, and the parameters of the nursing gross movements are extracted. Among them, the nursing major action parameters The expression is: ， in, for Motion index at all times. The preset body movement index threshold is used; When there are two targets in the radar detection space, a preset algorithm is used to determine whether the nursing actions of the targets within a preset time threshold meet the continuity condition, and the continuity parameters of the nursing actions are extracted based on the determination result. ; The step of determining compliance of nursing behavior based on the nursing behavior characteristic parameters includes: The nursing behavior score is obtained by fusing the nursing displacement parameters, nursing goal existence parameters, nursing major movement parameters, and nursing movement continuity parameters based on preset weights; wherein, the nursing behavior score The expression is: ， in, For preset weight parameters, and + + = 1; The compliance of nursing behaviors is determined based on the nursing behavior scores. The report generation module is used to generate nursing behavior compliance audit reports based on the nursing behavior compliance assessment results.

9. A radar, characterized in that, Includes memory and processor, of which: The processor is used to execute computer programs stored in the memory; When the processor executes the computer program, it implements the steps in the nursing behavior compliance audit method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the nursing behavior compliance audit method according to any one of claims 1 to 7.

Images