Parameter identification method, device and equipment for standing and walking test, medium and product

Abstract

The invention discloses a parameter identification method and device for a standing and walking test, equipment, a medium and a product. The method comprises the following steps: acquiring human body characteristic data of a tested object in a standing and walking test process; wherein the human body feature data comprises time sequence modal features corresponding to a plurality of human body sampling points respectively, the time sequence modal features comprise a time sequence positioning sequence, and the time sequence positioning sequence comprises position coordinates corresponding to a plurality of sampling moments respectively; determining a time sequence centroid sequence and a time sequence height sequence according to the human body feature data; wherein the time sequence centroid sequence comprises the position coordinates of the centroid of the tested object at each sampling moment, and the time sequence height sequence comprises the maximum height of the tested object at each sampling moment; according to the time sequence centroid sequence and the time sequence height sequence, the completion time of the test task of the tested object in the standing and walking test process is determined, and the accuracy of the test result of the standing and walking test is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method, device, equipment, medium and product for parameter recognition in a sit-to-stand and walk test. Background Art

[0002] The Time Up and Go (TUG) test is a test method used to evaluate lower limb function, balance ability, gait stability, and fall risk. It is usually used for the elderly, patients in the post-rehabilitation period, or people with movement disorders to observe their movement ability and risk in daily activities.

[0003] The parameter recognition methods for the TUG test can be divided into two categories: one is the manual timing method, where an observer holds a timer to record the time taken by the test subject to complete the TUG test. However, the test results obtained by this method are easily affected by the subjectivity of the observer and have low accuracy. The other is the wearable sensor method, but wearable sensors impose a physical burden on the test subject and cannot guarantee the accuracy of the test results either. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, equipment, medium and product for parameter recognition in a sit-to-stand and walk test to solve the problem that traditional parameter recognition methods are subject to subjective influence or impose a physical burden on the test subject, and to improve the accuracy of the test results of the sit-to-stand and walk test.

[0005] According to an embodiment of the present invention, a method for parameter recognition in a sit-to-stand and walk test is provided. The method includes:

[0006] Obtain the human characteristic data of the test subject during the sit-to-stand and walk test; wherein, the human characteristic data includes the temporal modal features corresponding to multiple human sampling points, and the temporal modal features include a temporal positioning sequence, and the temporal positioning sequence contains the position coordinates corresponding to multiple sampling moments.

[0007] Determine a temporal centroid sequence and a temporal height sequence according to the human characteristic data; wherein, the temporal centroid sequence contains the position coordinates of the centroid of the test subject at each sampling moment, and the temporal height sequence contains the maximum height of the test subject at each sampling moment.

[0008] Determine the completion time of the test task of the test subject during the sit-to-stand and walk test according to the temporal centroid sequence and the temporal height sequence.

[0009] According to another embodiment of the present invention, a device for parameter recognition in a sit-to-stand and walk test is provided. The device includes:

[0010] A human feature data acquisition module for acquiring the human feature data of the test subject during the standing and walking test; wherein, the human feature data includes the temporal modal features corresponding to multiple human sampling points, and the temporal modal features include a temporal positioning sequence, and the temporal positioning sequence contains the position coordinates corresponding to multiple sampling moments respectively;

[0011] A temporal height sequence determination module for determining a temporal centroid sequence and a temporal height sequence according to the human feature data; wherein, the temporal centroid sequence contains the position coordinates of the centroid of the test subject at each sampling moment, and the temporal height sequence contains the maximum height of the test subject at each sampling moment;

[0012] A completion time determination module for determining the completion time of the test task of the test subject during the standing and walking test according to the temporal centroid sequence and the temporal height sequence.

[0013] According to another embodiment of the present invention, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the parameter identification method for the standing and walking test according to any embodiment of the present invention.

[0017] According to another embodiment of the present invention, there is provided a computer-readable storage medium, which stores computer instructions for causing a processor to implement the parameter identification method for the standing and walking test according to any embodiment of the present invention when executed.

[0018] According to another embodiment of the present invention, there is provided a computer program product, including a computer program, which implements the parameter identification method for the standing and walking test according to any embodiment of the present invention when executed by a processor.

[0019] The technical solution of the embodiment of the present invention determines the temporal centroid sequence and the temporal height sequence according to the human feature data of the test subject during the standing and walking test, and determines the completion time of the test task of the test subject during the standing and walking test according to the temporal centroid sequence and the temporal height sequence, solving the problem that the traditional parameter identification method is subject to subjective influence or causes a physical burden on the test subject, and improving the accuracy of the test result of the standing and walking test.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0022] Figure 1 A flowchart of a parameter recognition method for a sit-to-stand and walk test provided by an embodiment of the present invention;

[0023] Figure 2 A flowchart of another parameter recognition method for a sit-to-stand and walk test provided by an embodiment of the present invention;

[0024] Figure 3 A flowchart of a specific example of a parameter recognition method for a sit-to-stand and walk test provided by an embodiment of the present invention;

[0025] Figure 4 A schematic structural diagram of a parameter recognition device for a sit-to-stand and walk test provided by an embodiment of the present invention;

[0026] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] It should be noted that the terms "first", "second", "third", "target", "reference", etc. in the specification, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data used can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] Figure 1 The flowchart of a parameter identification method for a sit-to-stand and walk test provided by an embodiment of the present invention. This embodiment is applicable to the situation of identifying test parameters for a sit-to-stand and walk test. This method can be executed by a parameter identification device for a sit-to-stand and walk test. The parameter identification device for a sit-to-stand and walk test can be implemented in the form of hardware and / or software, and the parameter identification device for a sit-to-stand and walk test can be configured in a terminal device. As Figure 1 shown, the method includes:

[0030] S110. Obtain the human body feature data of the test subject during the sit-to-stand and walk test.

[0031] Specifically, according to the types of human actions, the sit-to-stand and walk test can be divided into 5 stages, namely the standing-up stage, the first 3-meter straight-walking stage, the turning stage, the second 3-meter straight-walking stage, and the sitting-down stage. During the sit-to-stand and walk test, the initial state of the test subject is sitting on a chair or stool. After receiving the test start instruction, the test subject stands up, walks straight forward for 3 meters, turns at the 3-meter mark point, walks straight backward for 3 meters, and then sits on the chair or stool.

[0032] In this embodiment, the human body feature data includes the time-series modal features corresponding to multiple human body sampling points. The time-series modal features include a time-series positioning sequence, and the time-series positioning sequence contains the position coordinates corresponding to multiple sampling moments. Specifically, the position coordinates represent the positioning positions of the human body sampling points at the sampling moments.

[0033] In an alternative embodiment, obtaining the human body feature data of the test subject during the sit-to-stand and walk test includes: obtaining the test video data during the sit-to-stand and walk test collected by an optical sensor; performing human body recognition on the test video data to obtain the human body video data of the test subject; and determining the human body feature data according to the human body video data.

[0034] Exemplarily, the algorithms used for human body recognition include, but are not limited to, machine learning algorithms or deep learning algorithms. For example, the machine learning algorithm can be the HOG algorithm (Histogram of Oriented Gradients) combined with the SVM algorithm (Support Vector Machine).

[0035] In an alternative embodiment, the human body sampling points are the human body joint points of the test subject. For example, multiple human body sampling points include the shoulder joint, elbow joint, wrist joint, cervical vertebra, lumbar vertebra, hip joint, knee joint, and ankle joint, etc., but are not limited to the example situation.

[0036] In this embodiment, exemplarily, the human body feature data can be expressed as P = {P 1 ,..., P i ,..., P N}, where P i represents the temporal positioning sequence corresponding to the i-th human body sampling point, N represents the number of human body sampling points, represents the position coordinate corresponding to the j-th sampling moment in the i-th temporal positioning sequence, and s represents the number of sampling moments.

[0037] S120. Determine the temporal centroid sequence and the temporal height sequence according to the human body feature data.

[0038] In this embodiment, the temporal centroid sequence contains the position coordinates of the centroid of the test subject at each sampling moment, and the temporal height sequence contains the maximum height of the test subject at each sampling moment.

[0039] In an alternative embodiment, determining the temporal centroid sequence and the temporal height sequence according to the human body feature data includes: obtaining the human body positioning features corresponding to each sampling moment in the human body feature data; determining the temporal centroid sequence and the temporal height sequence according to multiple human body positioning features.

[0040] In this embodiment, the human body positioning features include the position coordinates of all human body sampling points.

[0041] Specifically, determining the temporal centroid sequence according to multiple human body positioning features includes: for each sampling moment, obtaining the sampling point mass corresponding to each human body sampling point; determining the position coordinate of the centroid at the sampling moment according to multiple sampling point masses and the human body positioning features corresponding to the sampling moment; determining the temporal centroid sequence according to the position coordinates of the centroids corresponding to multiple sampling moments respectively.

[0042] Exemplarily, the position coordinate c j of the centroid corresponding to the j-th sampling moment t j satisfies the following formula:

[0043]

[0044] wherein, m i represents the sampling point quality corresponding to the i-th human body sampling point.

[0045] Specifically, according to multiple human body positioning features, a temporal height sequence is determined, including: obtaining the maximum height in the human body positioning features corresponding to each sampling moment; wherein, the human body positioning features and the maximum height correspond one by one; according to the maximum heights respectively corresponding to multiple sampling moments, the temporal height sequence is determined.

[0046] S130. Determine the completion time of the test task of the object under test during the standing and walking test according to the temporal centroid sequence and the temporal height sequence.

[0047] In an alternative embodiment, the test task includes at least one of a start-stop task, a standing-up task, a turning task, a walking task, and a sitting-down task.

[0048] In an alternative embodiment, determining the completion time of the test task of the object under test during the standing and walking test according to the temporal centroid sequence and the temporal height sequence includes: when the test task includes a start-stop task, determining the farthest position coordinate according to the temporal centroid sequence, and using the sampling moment corresponding to the farthest position coordinate as the reference sampling moment; obtaining a first centroid sequence before the reference sampling moment in the temporal centroid sequence and a first height sequence before the reference sampling moment in the temporal height sequence; obtaining a second centroid sequence after the reference sampling moment in the temporal centroid sequence and a second height sequence after the reference sampling moment in the temporal height sequence; determining the completion time of the start-stop task according to the first time window length, the first centroid sequence, the first height sequence, the second centroid sequence, and the second height sequence.

[0049] Specifically, the start-stop task represents the process of the standing and walking test from the start of the test to the end of the test.

[0050] Specifically, the farthest position coordinate represents the position coordinate farthest from the reference position coordinate. Determining the farthest position coordinate according to the temporal centroid sequence includes: determining a plurality of position distances according to the temporal centroid sequence and the reference position coordinate; wherein, the position coordinates in the temporal centroid sequence and the position distances correspond one by one; using the position coordinate corresponding to the farthest position distance as the farthest position coordinate.

[0051] Exemplarily, the reference position coordinate can be the positioning coordinate of the stool or chair placed for the standing and walking test, or the positioning coordinate of the placement position of the data acquisition device, wherein the data acquisition device can be an optical sensor. The reference positioning position is not limited herein, and can be specifically set according to actual needs.

[0052] Specifically, with reference to the sampling moment, the standing and walking test process is roughly divided into two sub-processes. The first sub-process is the standing-up stage, the first 3-meter straight walking stage, and the early turning stage. The second sub-process is the late turning stage, the second 3-meter straight walking stage, and the sitting-down stage. Exemplarily, the reference sampling moment is denoted as t m .

[0053] Exemplarily, the time-sequence centroid sequence C is denoted as [c 1 , c s , where c 1 represents the position coordinates of the centroid corresponding to the sampling moment t 1 , and c s represents the position coordinates of the centroid corresponding to the sampling moment t s . The first centroid sequence C 1 is denoted as [c 1 , c m-1 , the second centroid sequence C 2 is denoted as [c m+1 , c s , where c m-1 represents the position coordinates of the centroid at the previous sampling moment t m before the reference sampling moment t m-1 , and c m+1 represents the position coordinates of the centroid at the next sampling moment t m after the reference sampling moment t m+1 .

[0054] Exemplarily, the time-sequence height sequence H is denoted as [h 1 , h s , where h 1 represents the maximum height corresponding to the sampling moment t 1 , and h s represents the maximum height corresponding to the sampling moment t s . The first height sequence H 1 is denoted as [h 1 , h m-1 , the second height sequence H 2 is denoted as [h m+1 , h s , where h m-1 represents the maximum height at the previous sampling moment t m before the reference sampling moment t m-1 , and h m+1 represents the maximum height at the next sampling moment t m after the reference sampling moment t m+1 .

[0055] At the beginning and end of the test, the position coordinates and maximum height of the centroid of the object under test are in a relatively stable state. In the reverse time sequence corresponding to the first sub-process, the first centroid sequence and the first height sequence gradually change from an unstable state to a relatively stable state. In the forward time sequence corresponding to the second sub-process, the second centroid sequence and the second height sequence also gradually change from an unstable state to a relatively stable state.

[0056] In an optional embodiment, according to the first time window length, the first centroid sequence, the first height sequence, the second centroid sequence, and the second height sequence, the completion time of the start and end tasks is determined, including: according to the first time window length, performing reverse variance traversal on the first centroid sequence and the first height sequence respectively to obtain the first centroid variance and the first height variance; until the first centroid variance is less than the first centroid variance threshold and the first height variance is less than the first height variance threshold, determining the start time of the start and end tasks according to the current traversal time range corresponding to the first time window length; according to the first time window length, performing forward variance traversal on the second centroid sequence and the second height sequence respectively to obtain the second centroid variance and the second height variance; until the second centroid variance is less than the first centroid variance threshold and the second height variance is less than the first height variance threshold, determining the end time of the start and end tasks according to the current traversal time range corresponding to the first time window length; determining the completion time of the start and end tasks according to the start time and end time of the start and end tasks.

[0057] Specifically, the first time window length represents a period of time. Exemplarily, the first time window length can be 300 ms or 500 ms, but is not limited to the example situation.

[0058] Specifically, the reverse variance traversal means obtaining the window centroid sequence or window height sequence that satisfies the first time window length in sequence from the end sampling moment t 1 corresponding to the first centroid sequence C 1 or the first height sequence H m-1 to the start sampling moment t 1 and calculating the first centroid variance or the first height variance. The forward variance traversal means obtaining the window centroid sequence or window height sequence that satisfies the first time window length in sequence from the start sampling moment t 2 corresponding to the second centroid sequence C 2 or the second height sequence H m+1 to the end sampling moment t s and calculating the second centroid variance or the second height variance.

[0059] Specifically, the first centroid variance or the second centroid variance represents the variance of the position coordinates of the centroids within the window centroid sequence, which is used to characterize the fluctuation of the position coordinates of the centroids within the window centroid sequence. The first height variance or the second height variance represents the variance of the maximum height within the window height sequence, which is used to characterize the fluctuation of the maximum height within the window height sequence.

[0060] In an alternative embodiment, according to the current traversal time range corresponding to the first time window length, determining the start time of the start and end task includes: using the start sampling time, the end sampling time, or the median sampling time corresponding to the current traversal time range of the first time window length as the start time of the start and end task.

[0061] In an alternative embodiment, according to the current traversal time range corresponding to the first time window length, determining the end time of the start and end task includes: using the start sampling time, the end sampling time, or the median sampling time corresponding to the current traversal time range of the first time window length as the end time of the start and end task.

[0062] Exemplarily, assume that the current traversal time range is [t i , t i+r1 . Then t i represents the start sampling time, t i+r1 represents the end sampling time, and r1 represents the number of sampling times covered by the first time window length.

[0063] In a specific embodiment, the start time of the start and end task is the start sampling time corresponding to the current traversal time range of the first time window length for reverse variance traversal, and the end time of the start and end task is the end sampling time corresponding to the current traversal time range of the first time window length for forward variance traversal.

[0064] Specifically, the time difference between the end time and the start time of the start and end task is used as the completion time of the start and end task.

[0065] Among them, the completion time of the start and end task can be used to evaluate the fall risk of the object under test. Exemplarily, according to the balance function of an individual, the fall risk can be divided into 4 levels, namely good, slightly impaired, significantly impaired, and severely impaired. Among them, the completion time ranges corresponding to each level of the start and end task are [0, 10s], [10s, 20s], [20s, 30s], and more than 30s, respectively.

[0066] In an alternative embodiment, determining the completion time of a test task of a subject during a standing-up and walking test according to a timing centroid sequence and a timing height sequence includes: when the test task includes a standing-up task and / or a sitting-down task, performing a difference operation on the timing height sequence to obtain a height difference sequence; performing a difference summation operation on the height difference sequence according to a second time window length to obtain a plurality of difference summation results; determining the completion time of the standing-up task and / or the sitting-down task according to a third time window length, the timing height sequence, and the plurality of difference summation results.

[0067] Specifically, the standing-up task represents the process of the subject from starting to stand up to completing the standing-up, the sitting-down task represents the process of the subject from starting to sit down to completing the sitting-down, the difference operation represents determining the difference between two adjacent maximum heights, and the height difference sequence includes the difference heights corresponding to a plurality of sampling moments.

[0068] In an alternative embodiment, performing a difference operation on the timing height sequence to obtain a height difference sequence includes: segmenting the timing height sequence according to the start time and the end time of the start-stop task to obtain a segmented height sequence, and performing a difference operation on the segmented height sequence to obtain a height difference sequence.

[0069] Exemplarily, the start time of the start-stop task is denoted as t a , and the end time of the start-stop task is denoted as t b , then the segmented height sequence can be expressed as [h a , h b , where h a represents the maximum height corresponding to the start time h a of the start-stop task, and h b represents the maximum height corresponding to the end time h b of the start-stop task.

[0070] The advantage of such a setting is that it can reduce the computational complexity of parameter identification, thereby improving the execution efficiency of parameter identification.

[0071] Specifically, the difference summation result represents the summation result of the plurality of difference heights in the window height difference sequence corresponding to the second time window length.

[0072] In an alternative embodiment, according to the second time window length, differential summation processing is performed on the height difference sequence to obtain a plurality of differential summation results, including: determining the farthest position coordinate according to the time sequence centroid sequence, and using the sampling moment corresponding to the farthest position coordinate as the reference sampling moment; when the test task includes a standing-up task, obtaining a first difference sequence in the height difference sequence before the reference sampling moment, and performing differential summation processing on the first difference sequence according to the second time window length to obtain a plurality of differential summation results; when the test task includes a sitting-down task, obtaining a second difference sequence in the height difference sequence after the reference sampling moment, and performing differential summation processing on the second difference sequence according to the second time window length to obtain a plurality of differential summation results.

[0073] The advantage of such a setting is that when the test task includes one of the standing-up task and the sitting-down task, the calculation amount of the differential summation result can be reduced, thereby further improving the execution efficiency of parameter identification.

[0074] Specifically, the second time window length and the third time window length may be the same or different, which is not limited here.

[0075] In the standing-up stage of the standing-up and walking test, there will be obvious height changes in the maximum height of the test subject and it shows an increasing trend.

[0076] In an alternative embodiment, according to the third time window length, the time sequence height sequence, and a plurality of differential summation results, the completion time of the standing-up task and / or the sitting-down task is determined, including: when the test task includes a standing-up task, determining a standing-up reference moment according to the traversal moment range of the second time window length corresponding to the largest differential summation result; obtaining a third height sequence in the time sequence height sequence before the standing-up reference moment and a fourth height sequence after the standing-up reference moment; performing reverse variance traversal on the third height sequence according to the third time window length to obtain a third height variance until the third height variance is less than the second height variance threshold, and determining the start moment of the standing-up task according to the current traversal moment range corresponding to the third time window length; performing forward variance traversal on the fourth height sequence according to the third time window length to obtain a fourth height variance until the fourth height variance is less than the second height variance threshold, and determining the end moment of the standing-up task according to the current traversal moment range corresponding to the third time window length; determining the completion time of the standing-up task according to the start moment and the end moment of the standing-up task.

[0077] In an alternative embodiment, determining the standing-up reference moment according to the traversal moment range of the second time window length corresponding to the maximum differential summation result includes: obtaining the traversal moment range of the second time window length corresponding to the maximum differential summation result, and using the starting sampling moment, the ending sampling moment, or the median sampling moment corresponding to the traversal moment range as the standing-up reference moment. Exemplarily, assuming the traversal moment range is [t i t i+r2 , then t i represents the starting sampling moment, t i+r2 represents the ending sampling moment, and r2 represents the number of sampling moments covered by the second time window length.

[0078] Specifically, reverse variance traversal means obtaining the window height sequences that meet the third time window length in sequence from the ending sampling moment to the starting sampling moment corresponding to the third height sequence, and calculating the third height variance. Forward variance traversal means obtaining the window height sequences that meet the third time window length in sequence from the starting sampling moment to the ending sampling moment corresponding to the fourth height sequence, and calculating the fourth height variance. Among them, the third height variance and the fourth height variance are used to characterize the fluctuation of the maximum height within the window height sequence.

[0079] In an alternative embodiment, determining the start moment of the standing-up task according to the current traversal moment range corresponding to the third time window length includes: using the starting sampling moment, the ending sampling moment, or the median sampling moment corresponding to the current traversal moment range of the third time window length as the start moment of the standing-up task.

[0080] In an alternative embodiment, determining the end moment of the standing-up task according to the current traversal moment range corresponding to the third time window length includes: using the starting sampling moment, the ending sampling moment, or the median sampling moment corresponding to the current traversal moment range of the third time window length as the end moment of the standing-up task.

[0081] Exemplarily, assuming the current traversal moment range is [t i t i+r3 , then t i represents the starting sampling moment, t i+r3 represents the ending sampling moment, and r3 represents the number of sampling moments covered by the third time window length.

[0082] In a specific embodiment, the start moment of the standing-up task is the starting sampling moment corresponding to the current traversal moment range of the third time window length of the reverse variance traversal, and the end moment of the standing-up task is the ending sampling moment corresponding to the current traversal moment range of the third time window length of the forward variance traversal.

[0083] Specifically, the time difference between the end moment and the start moment of the standing-up task is used as the completion time of the standing-up task.

[0084] During the sitting-down stage of the standing-up and walking test, there are significant height changes in the maximum height of the test subject, and the height shows a decreasing trend.

[0085] In an alternative embodiment, based on the third time window length, the time series height sequence, and multiple differential summation results, determining the completion time of the standing-up task and / or the sitting-down task includes: when the test task includes the sitting-down task, determining the sitting-down reference time according to the traversal time range of the second time window length corresponding to the minimum differential summation result; obtaining the fifth height sequence before the sitting-down reference time and the sixth height sequence after the sitting-down reference time in the time series height sequence; performing reverse variance traversal on the fifth height sequence according to the third time window length to obtain the fifth height variance until the fifth height variance is less than the third height variance threshold, and determining the start time of the sitting-down task according to the current traversal time range corresponding to the third time window length; performing forward variance traversal on the sixth height sequence according to the third time window length to obtain the sixth height variance until the sixth height variance is less than the third height variance threshold, and determining the end time of the sitting-down task according to the current traversal time range corresponding to the third time window length; determining the completion time of the sitting-down task according to the start time and the end time of the sitting-down task.

[0086] In an alternative embodiment, determining the sitting-down reference time according to the traversal time range of the second time window length corresponding to the minimum differential summation result includes: obtaining the traversal time range of the second time window length corresponding to the minimum differential summation result, and using the start sampling time, the end sampling time, or the median sampling time corresponding to the traversal time range as the sitting-down reference time. Exemplarily, assuming the traversal time range is [t i , t i+r2 , then t i represents the start sampling time, t i+r2 represents the end sampling time, and r2 represents the number of sampling times covered by the second time window length.

[0087] Specifically, reverse variance traversal means sequentially obtaining the window height sequences that meet the third time window length from the end sampling time to the start sampling time corresponding to the fifth height sequence and calculating the fifth height variance. Forward variance traversal means sequentially obtaining the window height sequences that meet the third time window length from the start sampling time to the end sampling time corresponding to the sixth height sequence and calculating the sixth height variance. Among them, the fifth height variance and the sixth height variance are used to characterize the fluctuation of the minimum height within the window height sequence.

[0088] In an alternative embodiment, determining the start time of the sitting task according to the current traversal time range corresponding to the third time window length includes: using the start sampling time, the end sampling time, or the median sampling time corresponding to the current traversal time range of the third time window length as the start time of the sitting task.

[0089] In an alternative embodiment, determining the end time of the sitting task according to the current traversal time range corresponding to the third time window length includes: using the start sampling time, the end sampling time, or the median sampling time corresponding to the current traversal time range of the third time window length as the end time of the sitting task.

[0090] Exemplarily, assuming the current traversal time range is [t i , t i+r3 , then t i represents the start sampling time, t i+r3 represents the end sampling time, and r3 represents the number of sampling times covered by the third time window length.

[0091] In a specific embodiment, the start time of the sitting task is the start sampling time corresponding to the current traversal time range of the third time window length of the reverse variance traversal, and the end time of the sitting task is the end sampling time corresponding to the current traversal time range of the third time window length of the forward variance traversal.

[0092] Specifically, the time difference between the end time and the start time of the sitting task is used as the completion time of the sitting task.

[0093] The technical solution of this embodiment determines the time series centroid sequence and the time series height sequence according to the human body characteristic data of the test subject during the standing-up and walking test, and determines the completion time of the test task of the test subject during the standing-up and walking test according to the time series centroid sequence and the time series height sequence, solving the problem that the traditional parameter identification method is subject to subjective influence or causes physical burden to the test subject, and improving the accuracy of the test results of the standing-up and walking test.

[0094] Figure 2 This is a flowchart of another parameter identification method for the standing-up and walking test provided by an embodiment of the present invention. This embodiment further refines the "acquiring the human body characteristic data of the test subject during the standing-up and walking test" in the above embodiment. Acquiring the human body characteristic data of the test subject during the standing-up and walking test includes: acquiring the radar signal data during the standing-up and walking test collected by the radar device; determining the spatial range-Doppler image of the test space corresponding to the standing-up and walking test according to the radar signal data; determining the human body signal data of the test subject according to the spatial range-Doppler image, and determining the human body characteristic data of the test subject according to the human body signal data. As Figure 2 shown, the method includes:

[0095] S210. Obtain the radar signal data during the standing and walking test collected by the radar device.

[0096] Exemplarily, the radar device can be a millimeter-wave radar, a lidar, or a three-dimensional imaging radar. For example, the millimeter-wave radar can be a 3-transmit 4-receive MIMO (Multiple-Input Multiple-Output) radar, but it is not limited to the above exemplary situations.

[0097] Taking the radar device as a millimeter-wave radar as an example, the millimeter-wave radar continuously emits electromagnetic wave signals into the test space through the transmitting module. After being scattered or reflected by an object, they are received by the receiving module of the millimeter-wave radar, and then after being sampled by a signal amplifier, a mixer, and an ADC (Analog-to-Digital Converter), radar signal data is obtained.

[0098] Among them, the radar signal data is a discrete echo signal, which can be expressed as y(m,n,k). Among them, m is the slow time dimension, representing the mth linear frequency modulation continuous wave signal, characterizing the accumulation of the echo signal in time and reflecting the change situation of the echo signal; n is the fast time dimension, representing the sampling sequence of the nth echo signal; k is the antenna dimension, representing the echo signal corresponding to the kth receiving channel.

[0099] S220. Determine the spatial range-Doppler image of the test space corresponding to the standing and walking test according to the radar signal data.

[0100] Specifically, perform Fourier transform on the signal data in the slow time dimension of the radar signal data to obtain Doppler data, perform Fourier transform on the signal data in the fast time dimension of the radar signal data to obtain range data, and after performing static clutter suppression on the Doppler data and the range data, obtain the spatial range-Doppler image.

[0101] S230. Determine the human body signal data of the tested object according to the spatial range-Doppler image, and determine the human body characteristic data of the tested object according to the human body signal data.

[0102] Exemplarily, use the Constant False Alarm Rate (CFAR) algorithm to perform human body recognition on the spatial range-Doppler image, and determine the human body signal data corresponding to the tested object in the radar signal data according to the human body recognition result. Exemplarily, use the Digital Beamforming (DBF) algorithm to perform speed estimation and coordinate transformation on the human body signal data to obtain the human body characteristic data of the tested object.

[0103] Specifically, the point cloud in the human body signal data is used to represent the human body sampling points.

[0104] In an alternative embodiment, the temporal modality features further include a temporal Doppler sequence and / or a temporal intensity sequence. The temporal Doppler sequence contains the motion speeds corresponding to multiple sampling moments respectively, and the temporal intensity sequence contains the point cloud intensities corresponding to multiple sampling moments respectively.

[0105] S240. Determine a temporal centroid sequence and a temporal height sequence according to the human body feature data.

[0106] In a specific embodiment, the temporal modality features include a temporal intensity sequence. Optionally, determining the temporal centroid sequence and the temporal height sequence according to multiple human body positioning features includes: obtaining the human body intensity feature and the human body positioning feature corresponding to each sampling moment in the human body feature data, and determining the temporal centroid sequence according to multiple human body intensity features and multiple human body positioning features; determining the temporal height sequence according to multiple human body positioning features.

[0107] In this embodiment, the human body intensity feature includes the point cloud intensities of all human body sampling points, and the human body positioning feature includes the position coordinates of all human body sampling points. Among them, the point cloud intensity is used to represent the sampling point quality of the human body sampling points in the centroid calculation.

[0108] Specifically, the human body positioning feature corresponds one-to-one with the position coordinates of the centroids in the temporal centroid sequence, and the human body positioning feature corresponds one-to-one with the maximum height in the temporal height sequence.

[0109] In another specific embodiment, the temporal modality features include a temporal Doppler sequence and a temporal intensity sequence. Optionally, determining the temporal centroid sequence and the temporal height sequence according to the human body feature data includes: obtaining the trunk positioning feature and the trunk intensity feature corresponding to each sampling moment in the trunk feature data, and determining the temporal centroid sequence according to multiple trunk positioning features and multiple trunk intensity features; obtaining the human body positioning feature corresponding to each sampling moment in the human body feature data, and determining the temporal height sequence according to multiple human body positioning features.

[0110] Among them, the trunk feature data is determined according to the human body feature data and includes the temporal modality features of the human body sampling points located in the trunk part of the test subject. The determination method of the trunk feature data will be explained in the following step embodiments.

[0111] In this embodiment, the trunk positioning feature includes the position coordinates of the human body sampling points located in the trunk part, and the trunk intensity feature includes the point cloud intensities of the human body sampling points located in the trunk part.

[0112] The advantage of setting the timing centroid sequence according to the torso feature data is to reduce the computational complexity of determining the timing centroid sequence and further improve the execution efficiency of parameter identification.

[0113] S250. Determine the completion time of the test task of the object under test during the standing-up and walking test according to the timing centroid sequence and the timing height sequence.

[0114] In an optional embodiment, the timing modal feature further includes a timing Doppler sequence. Determining the completion time of the test task of the object under test during the standing-up and walking test according to the timing centroid sequence and the timing height sequence includes: when the test task includes a turning task, determining the farthest position coordinate according to the timing centroid sequence, and using the sampling moment corresponding to the farthest position coordinate as the reference sampling moment; determining the target time range according to the reference sampling moment, and respectively obtaining the target human feature data, the target centroid sequence, and the target height sequence corresponding to the target time range from the human feature data, the timing centroid sequence, and the timing height sequence; inputting the target human feature data, the target centroid sequence, and the target height sequence into a pre-trained turning estimation model to obtain the output completion time of the turning task.

[0115] Specifically, the turning task represents the process of the object under test from starting to turn to completing the turn, and the reference sampling moment represents a certain sampling moment during the execution of the turning task.

[0116] Specifically, the target time range includes the reference sampling moment. The sampling moments corresponding to the first number of moments before the reference sampling moment are used as the target start moment of the target time range, and the sampling moments corresponding to the second number of moments after the reference sampling moment are used as the target end moment of the target time range. Among them, the first number of moments and the second number of moments can be the same or different. Exemplarily, assuming that the first number of moments and the second number of moments are respectively represented as n1 and n2, the target time range can be expressed as [t m-n1 , t m+n2 .

[0117] Exemplarily, the turning estimation model can be a recurrent neural model, a linear regression model, or an LSTM model (Long-Short Term Memory Network), but is not limited to the exemplary situation.

[0118] In another optional embodiment, determining the completion time of a test task of a subject during a stand-to-walk test according to a temporal centroid sequence and a temporal height sequence includes: when the test task includes a turning task, determining torso feature data according to human feature data; determining the farthest position coordinates according to the temporal centroid sequence, and using the sampling moment corresponding to the farthest position coordinates as a reference sampling moment; determining a target time range according to the reference sampling moment, and respectively obtaining target torso feature data, a target centroid sequence, and a target height sequence corresponding to the target time range from the torso feature data, the temporal centroid sequence, and the temporal height sequence; inputting the target torso feature data, the target centroid sequence, and the target height sequence into a pre-trained turning estimation model to obtain the completion time of the output turning task.

[0119] In this embodiment, the torso feature data includes the temporal modal features of human sampling points located at the torso part of the subject.

[0120] In an optional embodiment, determining the torso feature data according to the human feature data includes: performing clustering processing on the human feature data to obtain at least two clustering feature data; screening the at least two clustering feature data to obtain the torso feature data.

[0121] Exemplarily, the clustering algorithms used for clustering processing include, but are not limited to, density-based spatial clustering algorithm, k-nearest neighbor clustering algorithm, hierarchical clustering algorithm, Gaussian mixture clustering algorithm, and so on.

[0122] In an optional embodiment, screening the at least two clustering feature data to obtain the torso feature data includes: for each clustering feature data, using the summation result corresponding to the temporal intensity sequence in the clustering feature data as the clustering energy corresponding to the clustering feature data; using the clustering feature data corresponding to the maximum clustering energy as the torso feature data.

[0123] In another optional embodiment, screening the at least two clustering feature data to obtain the torso feature data includes: for each clustering feature data, determining the geometric feature data corresponding to the clustering feature data according to the temporal positioning sequence in the clustering feature data; using the clustering feature data whose geometric feature data meets the torso feature conditions as the torso feature data.

[0124] Exemplarily, the torso feature conditions include an aspect ratio range, a curvature range, etc., but are not limited to the exemplary situations.

[0125] In another alternative embodiment, at least two pieces of clustering feature data are screened to obtain trunk feature data, including: for each piece of clustering feature data, according to the time-series Doppler sequence in the clustering feature data, determining the Doppler frequency corresponding to the clustering feature data; and taking the clustering feature data whose Doppler frequency satisfies a preset frequency range as the trunk feature data.

[0126] Specifically, the movement speed of the trunk part is relatively slow compared to that of the limb parts. Therefore, the Doppler frequency of the trunk part is relatively lower than that of the limb parts.

[0127] The time-series Doppler sequence can reflect the dynamic characteristics of the human body sampling points of the tested object changing over time. The human body feature data contains the time-series Doppler sequences of all human body sampling points. However, for different tested objects, due to differences in factors such as height, body shape, body posture, and gait, the time-series Doppler sequences corresponding to the human body sampling points in the human body feature data will show obvious differences, especially the human body sampling points located on the limb parts.

[0128] Considering that the Doppler information of the trunk part is more stable than that of the limb parts, in this embodiment, by extracting the trunk feature data from the human body feature data, the influence of individual differences brought by the Doppler information of the limb parts is avoided, enabling the parameter identification method to be adapted to different tested populations, and further ensuring the accuracy of the test results of the sit-to-stand and walk test.

[0129] In an alternative embodiment, according to the time-series centroid sequence and the time-series height sequence, determining the completion time of the test task of the tested object during the sit-to-stand and walk test, including: when the test task includes a walking task, according to the time-series centroid sequence and the time-series height sequence, determining the end moment of the standing-up task, the start moment of the sitting-down task, and the completion time of the turning task; according to the end moment of the standing-up task and the start moment of the sitting-down task, determining the reference completion time of the walking task; and taking the difference time between the reference completion time and the completion time of the turning task as the completion time of the walking task.

[0130] Specifically, the walking task represents the walking process of the tested object in the sit-to-stand and walk test. For the determination methods of the end moment of the standing-up task, the start moment of the sitting-down task, and the completion time of the turning task, refer to the implementation methods given in the above embodiments, and they will not be elaborated in this embodiment.

[0131] Specifically, the reference completion time represents the completion time of the remaining tasks in the start-stop task excluding the standing-up task and the sitting-down task. Among them, the remaining tasks include the walking task and the turning task.

[0132] Figure 3Flowchart of a specific example of a parameter recognition method for a standing-up and walking test provided by an embodiment of the present invention. Specifically, based on the radar signal data collected by a radar device during the standing-up and walking test, human point cloud data is determined, where the human point cloud data includes point cloud features and movement speed, and the point cloud features include the position coordinates and point cloud intensity of the point cloud. Feature extraction is performed on the human point cloud data to obtain trunk feature data, a temporal centroid sequence, and a temporal height sequence. Parameter recognition is performed based on the trunk feature data, the temporal centroid sequence, and the temporal height sequence to obtain the completion times corresponding to the start and end tasks, the standing-up task, the sitting-down task, the turning task, and the walking task respectively.

[0133] Optical sensors cannot ensure the privacy and security of the test subjects, require professional equipment and complex algorithm processing, have a relatively high test cost, and are sensitive to environmental factors such as light, dust, and smoke.

[0134] The technical solution of this embodiment overcomes the above-mentioned defects of optical sensors by obtaining the radar signal data collected by the radar device during the standing-up and walking test, determining the spatial range-Doppler image of the test space corresponding to the standing-up and walking test according to the radar signal data, determining the human signal data of the test subject according to the spatial range-Doppler image, and determining the human feature data of the test subject according to the human signal data. The radar device has a certain penetration ability, thereby further ensuring the accuracy of the test results of the standing-up and walking test.

[0135] The following is an embodiment of a parameter recognition device for a standing-up and walking test provided by an embodiment of the present invention. This device and the parameter recognition method for a standing-up and walking test in the above embodiment belong to the same inventive concept. For the details not described in detail in the embodiment of the parameter recognition device for a standing-up and walking test, reference can be made to the content about the parameter recognition method for a standing-up and walking test in the above embodiment.

[0136] Figure 4 Schematic structural diagram of a parameter recognition device for a standing-up and walking test provided by an embodiment of the present invention. As Figure 4 shown, the device includes: a human feature data acquisition module 310, a temporal height sequence determination module 320, and a completion time determination module 330.

[0137] The human feature data acquisition module 310 is used to acquire the human feature data of the test subject during the standing-up and walking test; wherein, the human feature data includes temporal modal features corresponding to multiple human sampling points, and the temporal modal features include a temporal positioning sequence, and the temporal positioning sequence contains position coordinates corresponding to multiple sampling moments.

[0138] A timing height sequence determination module 320 is configured to determine a timing centroid sequence and a timing height sequence according to human body feature data. The timing centroid sequence includes the position coordinates of the centroid of the subject to be tested at each sampling moment, and the timing height sequence includes the maximum height of the subject to be tested at each sampling moment.

[0139] A completion time determination module 330 is configured to determine the completion time of the test task of the subject to be tested during the standing-up and walking test according to the timing centroid sequence and the timing height sequence.

[0140] The technical solution of this embodiment determines the timing centroid sequence and the timing height sequence according to the human body feature data of the subject to be tested during the standing-up and walking test, and determines the completion time of the test task of the subject to be tested during the standing-up and walking test according to the timing centroid sequence and the timing height sequence, which solves the problem that the traditional parameter identification method is subject to subjective influence or causes physical burden to the subject to be tested, and improves the accuracy of the test results of the standing-up and walking test.

[0141] In an optional embodiment, the completion time determination module 330 includes:

[0142] A reference sampling moment determination unit is configured to, when the test task includes a start-stop task, determine the farthest position coordinates according to the timing centroid sequence, and use the sampling moment corresponding to the farthest position coordinates as the reference sampling moment.

[0143] A first height sequence determination unit is configured to obtain a first centroid sequence in the timing centroid sequence before the reference sampling moment and a first height sequence in the timing height sequence before the reference sampling moment.

[0144] A second height sequence determination unit is configured to obtain a second centroid sequence in the timing centroid sequence after the reference sampling moment and a second height sequence in the timing height sequence after the reference sampling moment.

[0145] A start-stop time determination unit is configured to determine the completion time of the start-stop task according to the first time window length, the first centroid sequence, the first height sequence, the second centroid sequence, and the second height sequence.

[0146] In an optional embodiment, the start-stop time determination unit is specifically configured to:

[0147] Perform reverse variance traversal on the first centroid sequence and the first height sequence respectively according to the first time window length to obtain a first centroid variance and a first height variance.

[0148] Until the first centroid variance is less than the first centroid variance threshold and the first height variance is less than the first height variance threshold, determine the start moment of the start-stop task according to the current traversal moment range corresponding to the first time window length.

[0149] Perform forward variance traversals on the second centroid sequence and the second height sequence respectively according to the first time window length to obtain the second centroid variance and the second height variance;

[0150] Until the second centroid variance is less than the first centroid variance threshold and the second height variance is less than the first height variance threshold, determine the end time of the start and end tasks according to the current traversal time range corresponding to the first time window length;

[0151] Determine the completion time of the start and end tasks according to the start time and end time of the start and end tasks.

[0152] In an optional embodiment, the completion time determination module 330 includes:

[0153] A height difference sequence determination unit, configured to perform difference processing on the time-series height sequence to obtain a height difference sequence when the test task includes a standing-up task and / or a sitting-down task;

[0154] A difference summation result determination unit, configured to perform difference summation processing on the height difference sequence according to the second time window length to obtain a plurality of difference summation results;

[0155] A test time determination unit, configured to determine the completion time of the standing-up task and / or the sitting-down task according to the third time window length, the time-series height sequence, and the plurality of difference summation results.

[0156] In an optional embodiment, the test time determination unit includes:

[0157] A standing-up time determination subunit, configured to determine a standing-up reference time according to the traversal time range of the second time window length corresponding to the largest difference summation result when the test task includes a standing-up task;

[0158] Obtain a third height sequence before the standing-up reference time and a fourth height sequence after the standing-up reference time in the time-series height sequence;

[0159] Perform reverse variance traversal on the third height sequence according to the third time window length to obtain a third height variance. Until the third height variance is less than the second height variance threshold, determine the start time of the standing-up task according to the current traversal time range corresponding to the third time window length;

[0160] Perform forward variance traversal on the fourth height sequence according to the third time window length to obtain a fourth height variance. Until the fourth height variance is less than the second height variance threshold, determine the end time of the standing-up task according to the current traversal time range corresponding to the third time window length;

[0161] Determine the completion time of the standing-up task according to the start time and end time of the standing-up task.

[0162] In an alternative embodiment, the test time determination unit includes:

[0163] A sitting down time determination subunit, configured to, when the test task includes a sitting down task, determine a sitting down reference time according to the traversal time range of the second time window length corresponding to the smallest differential sum result;

[0164] Obtain a fifth height sequence before the sitting down reference time and a sixth height sequence after the sitting down reference time in the time series height sequence;

[0165] Perform reverse variance traversal on the fifth height sequence according to a third time window length to obtain a fifth height variance, until the fifth height variance is less than a third height variance threshold, and determine the start time of the sitting down task according to the current traversal time range corresponding to the third time window length;

[0166] Perform forward variance traversal on the sixth height sequence according to the third time window length to obtain a sixth height variance, until the sixth height variance is less than the third height variance threshold, and determine the end time of the sitting down task according to the current traversal time range corresponding to the third time window length;

[0167] Determine the completion time of the sitting down task according to the start time and the end time of the sitting down task.

[0168] In an alternative embodiment, the time series modal feature further includes a time series Doppler sequence, and the time series Doppler sequence includes motion speeds corresponding to multiple sampling times respectively;

[0169] The completion time determination module 330 includes:

[0170] A turning time determination unit, configured to, when the test task includes a turning task, determine torso feature data according to the human body feature data; wherein, the torso feature data includes time series modal features of human body sampling points located at the torso part of the tested object;

[0171] Determine the farthest position coordinate according to the time series centroid sequence, and use the sampling time corresponding to the farthest position coordinate as the reference sampling time;

[0172] Determine a target time range according to the reference sampling time, and respectively obtain target torso feature data, a target centroid sequence, and a target height sequence corresponding to the target time range from the torso feature data, the time series centroid sequence, and the time series height sequence;

[0173] Input the target torso feature data, the target centroid sequence, and the target height sequence into a pre-trained turning estimation model to obtain the output completion time of the turning task.

[0174] In an optional embodiment, the human feature data acquisition module 310 is specifically configured to:

[0175] Obtain the radar signal data during the standing-up and walking test collected by the radar device;

[0176] Determine the spatial range-Doppler image of the test space corresponding to the standing-up and walking test according to the radar signal data;

[0177] Determine the human signal data of the test subject according to the spatial range-Doppler image, and determine the human feature data of the test subject according to the human signal data.

[0178] In an optional embodiment, the temporal mode feature further includes a temporal intensity sequence, and the temporal intensity sequence contains the point cloud intensities corresponding to multiple sampling moments. The temporal height sequence determination module 320 is specifically configured to:

[0179] Obtain the torso positioning feature and the torso intensity feature corresponding to each sampling moment in the torso feature data, and determine the temporal centroid sequence according to the multiple torso positioning features and the multiple torso intensity features; wherein, the torso positioning feature contains the position coordinates of the human sampling points located in the torso part, and the torso intensity feature contains the point cloud intensities of the human sampling points located in the torso part;

[0180] Obtain the human positioning feature corresponding to each sampling moment in the human feature data, and determine the temporal height sequence according to the multiple human positioning features; wherein, the human positioning feature contains the position coordinates of all human sampling points.

[0181] In an optional embodiment, the completion time determination module 330 includes:

[0182] A walking time determination unit, configured to determine the end moment of the standing-up task, the start moment of the sitting-down task, and the completion time of the turning task according to the temporal centroid sequence and the temporal height sequence when the test task includes a walking task;

[0183] Determine the reference completion time of the walking task according to the end moment of the standing-up task and the start moment of the sitting-down task;

[0184] Use the difference time between the reference completion time and the completion time of the turning task as the completion time of the walking task.

[0185] The parameter identification device for the standing-up and walking test provided by the embodiments of the present invention can execute the parameter identification method for the standing-up and walking test provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0186] Figure 5A schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0187] As Figure 5 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor 11. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0188] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information or data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0189] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the parameter identification method for the sit-to-stand and walk test provided in the above embodiments.

[0190] In some embodiments, the parameter identification method for the sit-to-stand and walk test provided in the above embodiments may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps in the parameter identification method for the sit-to-stand and walk test described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the parameter identification method for the sit-to-stand and walk test by any other suitable means (e.g., by means of firmware).

[0191] The various embodiments of the systems and techniques described above in this document may be implemented in the following systems or combinations thereof: digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), system on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0192] The computer programs for implementing the parameter identification method of the stand-to-walk test of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0193] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable storage medium. Examples of machine-readable storage media would include electrical connections based on at least one wire, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0194] To provide for interaction with a user, the systems and techniques described herein can be implemented on a terminal device having: a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the terminal device. Other kinds of devices can also provide for interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0195] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0196] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and virtual private servers (VPS).

[0197] It should be understood that various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0198] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A parameter identification method for a stand-up and walk test, characterized in that: include: Acquire human body feature data of the tested subject during the stand-up and walk test; wherein the human body feature data includes time series modal features corresponding to a plurality of human body sampling points, the time series modal features include a time series positioning sequence, and the time series positioning sequence includes position coordinates corresponding to a plurality of sampling moments; Determine a time series centroid sequence and a time series height sequence according to the human body feature data; wherein the time series centroid sequence includes the position coordinates of the centroid of the tested object at each sampling time, and the time series height sequence includes the maximum height of the tested object at each sampling time; The completion time of the test task of the test subject during the stand-up and walk test is determined according to the time-series centroid sequence and the time-series height sequence.

2. The method according to claim 1, characterized in that Determining the completion time of the test task of the test subject during the stand-up and walk test according to the time-series centroid sequence and the time-series height sequence includes: When the test task includes a start and stop task, the farthest position coordinates are determined according to the time series centroid sequence, and the sampling time corresponding to the farthest position coordinates is used as the reference sampling time; Acquire a first centroid sequence in the time series centroid sequence that is located before the reference sampling time and a first height sequence in the time series height sequence that is located before the reference sampling time; Acquire a second centroid sequence in the time series centroid sequence located after the reference sampling time and a second height sequence in the time series height sequence located after the reference sampling time; The completion time of the start and end tasks is determined according to the first time window length, the first centroid sequence, the first height sequence, the second centroid sequence and the second height sequence.

3. The method according to claim 2, characterized in that The step of determining the completion time of the start and end tasks according to the first time window length, the first centroid sequence, the first height sequence, the second centroid sequence, and the second height sequence includes: According to the first time window length, respectively perform reverse variance traversal on the first centroid sequence and the first height sequence to obtain a first centroid variance and a first height variance; Until the first centroid variance is less than a first centroid variance threshold and the first height variance is less than a first height variance threshold, determining the start time of the start and end tasks according to the current traversal time range corresponding to the first time window length; According to the first time window length, performing forward variance traversal on the second centroid sequence and the second height sequence respectively to obtain a second centroid variance and a second height variance; Until the second centroid variance is less than the first centroid variance threshold and the second height variance is less than the first height variance threshold, the end time of the start and end tasks is determined according to the current traversal time range corresponding to the first time window length; The completion time of the start and end tasks is determined according to the start and end times of the start and end tasks.

4. The method according to claim 1, characterized in that: Determining the completion time of the test task of the test subject during the stand-up and walk test according to the time-series centroid sequence and the time-series height sequence includes: When the test task includes a standing up task and / or a sitting down task, performing a difference process on the time series height sequence to obtain a height difference sequence; According to the second time window length, performing a difference summation process on the height difference sequence to obtain a plurality of difference summation results; The completion time of the standing up task and / or the sitting down task is determined according to the third time window length, the time-series height sequence and a plurality of difference summation results.

5. The method according to claim 4, characterized in that Determining the completion time of the standing up task and / or the sitting down task according to the third time window length, the time sequence height sequence and a plurality of difference summation results includes: When the test task includes a standing up task, determining a standing up reference time according to a traversal time range of the second time window length corresponding to the maximum difference summation result; Acquire a third height sequence located before the standing-up reference time and a fourth height sequence located after the standing-up reference time in the time series height sequence; According to the third time window length, reverse variance traversal is performed on the third height sequence to obtain a third height variance, until the third height variance is less than a second height variance threshold, and according to a current traversal time range corresponding to the third time window length, a start time of the standing task is determined; According to the third time window length, performing a forward variance traversal on the fourth height sequence to obtain a fourth height variance, until the fourth height variance is less than a second height variance threshold, and determining the end time of the standing task according to a current traversal time range corresponding to the third time window length; The completion time of the standing up task is determined according to the starting time and the ending time of the standing up task.

6. The method according to claim 4, characterized in that Determining the completion time of the standing up task and / or the sitting down task according to the third time window length, the time sequence height sequence and a plurality of difference summation results includes: When the test task includes a sitting task, determining a sitting reference time according to a traversal time range of a second time window length corresponding to a minimum difference sum result; Acquire a fifth height sequence before the sitting down reference time and a sixth height sequence after the sitting down reference time in the time series height sequence; According to the third time window length, reverse variance traversal is performed on the fifth height sequence to obtain a fifth height variance, until the fifth height variance is less than a third height variance threshold, and according to a current traversal time range corresponding to the third time window length, a start time of the sitting task is determined; According to the third time window length, performing a forward variance traversal on the sixth height sequence to obtain a sixth height variance, until the sixth height variance is less than a third height variance threshold, and determining an end time of the sit-down task according to a current traversal time range corresponding to the third time window length; The completion time of the sit-down task is determined according to the start time and the end time of the sit-down task.

7. The method according to claim 1, characterized in that The time series modal feature also includes a time series Doppler sequence, and the time series Doppler sequence includes movement speeds corresponding to a plurality of sampling moments respectively; Determining the completion time of the test task of the test subject during the stand-up and walk test according to the time-series centroid sequence and the time-series height sequence includes: When the test task includes a turning task, determining trunk feature data according to the human body feature data; wherein the trunk feature data includes temporal modal features of human body sampling points located at the trunk of the tested object; Determine the farthest position coordinates according to the time series centroid sequence, and use the sampling time corresponding to the farthest position coordinates as the reference sampling time; Determine a target time range according to the reference sampling time, and respectively obtain target torso feature data, target center of mass sequence and target height sequence corresponding to the target time range from the torso feature data, time series center of mass sequence and time series height sequence; The target torso feature data, target center of mass sequence and target height sequence are input into a pre-trained turn estimation model to obtain the output completion time of the turn task.

8. The method according to claim 7, characterized in that The step of obtaining the human body characteristic data of the subject being tested during the stand-up and walk test includes: Acquire radar signal data collected by the radar device during the stand-up and walk test; Determining a spatial range Doppler image of a test space corresponding to the Get Up and Go test according to the radar signal data; The human body signal data of the tested object is determined according to the spatial range Doppler image, and the human body feature data of the tested object is determined according to the human body signal data.

9. The method according to claim 8, characterized in that The temporal modal feature also includes a temporal intensity sequence, wherein the temporal intensity sequence includes point cloud intensities corresponding to a plurality of sampling moments, and the temporal centroid sequence and the temporal height sequence are determined according to the human body feature data, including: Obtaining a trunk positioning feature and a trunk strength feature corresponding to each sampling moment in the trunk feature data, and determining a temporal centroid sequence according to a plurality of trunk positioning features and a plurality of trunk strength features; wherein the trunk positioning feature includes the position coordinates of a human body sampling point located at the trunk position, and the trunk strength feature includes the point cloud intensity of a human body sampling point located at the trunk position; The human body positioning feature corresponding to each sampling moment in the human body feature data is obtained, and a time series height sequence is determined according to a plurality of human body positioning features; wherein the human body positioning feature includes the position coordinates of all human body sampling points.

10. The method according to claim 1, characterized in that Determining the completion time of the test task of the test subject during the stand-up and walk test according to the time-series centroid sequence and the time-series height sequence includes: When the test task includes a walking task, determining the end time of the standing task, the start time of the sitting task and the completion time of the turning task according to the time-series centroid sequence and the time-series height sequence; Determine a reference completion time of the walking task according to the end time of the standing up task and the start time of the sitting down task; The difference between the reference completion time and the completion time of the turning task is used as the completion time of the walking task.

11. A parameter identification device for a stand-up and walk test, characterized in that: include: A human feature data acquisition module is used to acquire human feature data of the subject being tested during the stand-up and walk test; wherein the human feature data includes time series modal features corresponding to a plurality of human sampling points, the time series modal features include a time series positioning sequence, and the time series positioning sequence includes position coordinates corresponding to a plurality of sampling moments; A time series height sequence determination module, used to determine a time series centroid sequence and a time series height sequence according to the human body feature data; wherein the time series centroid sequence includes the position coordinates of the centroid of the tested object at each sampling time, and the time series height sequence includes the maximum height of the tested object at each sampling time; The completion time determination module is used to determine the completion time of the test task of the test subject during the stand-up and walk test according to the time-series centroid sequence and the time-series height sequence.

12. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the parameter identification method for the Get Up and Walk test according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the parameter identification method for the stand-up and walk test according to any one of claims 1-10 when executed.

14. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the parameter identification method of the Get Up and Go test according to any one of claims 1 to 10.

Images