Motion feature screening method and device for identifying lower limb motion state

Abstract

The embodiment of the invention provides a motion feature screening method and device for recognizing the motion state of a lower limb. The motion feature screening method for identifying the lower limb motion state comprises the following steps: constructing a sample data set based on various motion features and corresponding lower limb motion state labels; determining a first correlation score and a second correlation score of each motion feature and the target lower limb motion state; performing weighted summation on the first correlation score and the second correlation score corresponding to each motion feature to obtain a comprehensive score corresponding to each motion feature; and based on the comprehensive score corresponding to each motion feature, determining a target motion feature for representing the motion state of the target lower limb. The comprehensive score of each motion is comprehensively determined through different correlation analysis methods, so that the scoring result of the comprehensive score is more in line with the actual situation, and the finally selected target motion features are more reasonable.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data mining, and in particular to a motion feature screening method and device for identifying the motion state of lower limbs. Background Art

[0002] As exoskeleton robots are increasingly used in military, industrial, medical and other fields, the recognition of human lower limb motion state has become an important research field in order to achieve more coordinated and smooth exoskeleton assistance to human movements. Due to the advantages of the inertial measurement unit itself, such as reliability, easy access, low weight, low power consumption, and low noise, motion state recognition based on inertial measurement unit measurement data is one of the mainstream technologies in the industry.

[0003] Based on the inertial measurement signal obtained by inertial measurement unit detection, a large amount of motion feature data can be obtained. Directly applying all motion features to construct the lower limb motion state model will cause a huge consumption of resources and may cause overfitting, high model complexity and excessive solution delay during use. In order to solve the above problems, it is necessary to reasonably screen the motion features used for model construction. At present, the motion feature screening methods used for lower limb motion state recognition are mostly correlation analysis methods based on machine learning models similar to those for constructing lower limb motion state models. The above methods may have systematic error problems due to problems with the machine learning method itself. Summary of the invention

[0004] In order to solve the problem that systematic errors may occur in the existing motion feature screening using machine learning methods, the embodiments of the present disclosure provide a motion feature screening method and device for identifying the motion state of lower limbs.

[0005] In a first aspect, an embodiment of the present disclosure provides a motion feature screening method for identifying a lower limb motion state, comprising:

[0006] Based on the inertial measurement signals collected during various lower limb motion states, the corresponding multiple motion features are respectively determined, and a sample data set is constructed based on the multiple motion features and the corresponding lower limb motion state labels, wherein the sample data in the sample data set includes positive samples and negative samples, the labels of the positive samples are target lower limb motion state labels, and the labels of the negative samples are non-target lower limb motion state labels;

[0007] Using a machine learning model to perform correlation analysis based on the label of the sample data and a motion feature, respectively, to determine a first correlation score between various motion features and the target lower limb motion state;

[0008] A plurality of target samples are randomly selected from the sample data set, and M adjacent positive samples that are closest to each of the target samples in a motion feature dimension are determined in the positive samples, and N adjacent negative samples that are closest to each of the target samples in the motion feature dimension are determined in the negative samples;

[0009] Calculating a first average distance between the target sample and the nearest M adjacent positive samples in the one motion feature dimension, and calculating a second average distance between the target sample and the nearest N adjacent negative samples in the one motion feature dimension, calculating a distance difference between the first average distance and the second average distance, and determining a second correlation score of the one motion feature according to the distance differences corresponding to all target samples;

[0010] Taking a weighted sum of the first correlation score and the second correlation score corresponding to each motion feature to obtain a comprehensive score corresponding to each motion feature;

[0011] Based on the comprehensive scores corresponding to the various motion features, the target motion features for characterizing the motion state of the target lower limbs are determined.

[0012] Optionally, the step of determining the target motion feature for characterizing the motion state of the target lower limb based on the comprehensive score corresponding to each motion feature includes:

[0013] Determine the motion features to be selected based on the comprehensive scores corresponding to the various motion features;

[0014] Performing pairwise correlation analysis on the motion features to be selected, determining irrelevant motion features and relevant motion features, and determining selected relevant motion features from the relevant motion features;

[0015] Using the irrelevant motion features and the selected relevant motion features as the target motion features; or,

[0016] Performing pairwise correlation analysis on each motion feature to determine irrelevant motion features and relevant motion features, and determining selected relevant motion features among the relevant motion features;

[0017] The target motion feature is determined from among the irrelevant motion features and the selected relevant motion features according to the comprehensive scores of the irrelevant motion features and the selected relevant motion features.

[0018] Optionally, the adopting of a machine learning model to perform correlation analysis based on the label of the sample data and a motion feature to determine a first correlation score between various motion features and the target lower limb motion state includes:

[0019] A logistic regression model is used to perform correlation analysis based on the label of the sample data and the one motion feature, to determine the characteristic coefficient corresponding to the one motion feature in the logistic regression model, and the absolute value of the characteristic coefficient is used as the first correlation score between the one motion feature and the target lower limb motion state.

[0020] Optionally, the machine learning model is used to perform correlation analysis based on the label of the sample data and a motion feature to determine a first correlation score between various motion features and the target lower limb motion state,

[0021] Using a Gaussian Naive Bayes model, a correlation analysis is performed based on the label of the sample data and the one motion feature, and the standard deviations in the target lower limb motion state and the non-target lower limb motion state are determined respectively;

[0022] The average value of the standard deviations of the target lower limb state and the non-target lower limb state corresponding to the one motion feature is calculated as the first correlation score between the one motion feature and the target lower limb motion state.

[0023] Optionally, determining the second correlation score of the one motion feature according to the distance differences of all target samples includes:

[0024] When the distance difference is a positive value, the initial weight is adjusted down to obtain a corresponding reduced weight; and when the distance difference is a negative value, the initial weight is adjusted up to obtain a corresponding increased weight; the average of all the reduced weights and the increased weight is calculated as the second correlation score of the one motion feature.

[0025] Optionally, the inertial measurement signals collected based on various lower limb motion states respectively determine corresponding multiple motion features, including:

[0026] According to a preset sliding time window, inertial measurement signals collected during various lower limb motion states are sampled respectively, and a kinematic feature sequence is determined to be sorted within the sliding time window; wherein the preset sliding time window is greater than the lower limb motion cycle period;

[0027] Based on various sorted kinematic feature sequences, at least one of the following parameters is calculated as the multiple motion features: mean, maximum, minimum, median, variance, peak-to-peak difference, signal energy, skewness, kurtosis, maximum slope, root mean square, absolute mean, pulse factor, root amplitude, margin index, waveform factor, crest factor, vector and amplitude, absolute area.

[0028] Optionally, the inertial measurement signal includes a thigh inertial measurement signal collected by an inertial measurement unit located on the thigh, and includes a calf inertial measurement signal collected by an inertial measurement unit located on the calf;

[0029] The method comprises: sampling the thigh inertial measurement signals and the calf inertial measurement signals collected during various lower limb movement states according to a preset sliding time window, and determining the thigh kinematic characteristics and the calf sorting kinematic characteristics sequence within the sliding time window; wherein the preset sliding time window is greater than the lower limb movement cycle period; wherein the preset sliding time window is greater than the lower limb movement cycle period;

[0030] Based on the sorted kinematic feature sequences of the thigh in each dimension, the thigh motion features of the corresponding dimension are obtained; and based on the sorted kinematic feature sequences of the calf in each dimension, the calf motion features of the corresponding dimension are obtained;

[0031] Calculate the ratio of the thigh motion feature and the calf motion feature of the corresponding dimension, and / or the signal energy of the thigh motion feature and the calf motion feature of the corresponding dimension;

[0032] The ratio and / or the signal energy are used as at least part of the motion characteristic.

[0033] In a second aspect, the present disclosure provides a motion feature screening device for identifying the motion state of lower limbs, which is characterized by comprising:

[0034] A sample data set construction unit, used to determine the corresponding multiple motion features based on the inertial measurement signals collected during various lower limb motion states, and to construct a sample data set based on the multiple motion features and the corresponding lower limb motion state labels, wherein the sample data in the sample data set includes positive samples and negative samples, the labels of the positive samples are target lower limb motion state labels, and the labels of the negative samples are non-target lower limb motion state labels;

[0035] A first scoring unit is used to use a machine learning model to perform correlation analysis based on the label of the sample data and a motion feature, and determine a first correlation score between various motion features and the target lower limb motion state;

[0036] A second scoring unit is used to randomly select multiple target samples in the sample data set, and determine the M adjacent positive samples in the positive samples that are closest to each of the target samples in a motion feature dimension, and determine the N adjacent negative samples in the negative samples that are closest to each of the target samples in the one motion feature dimension; and calculate a first average distance between the target sample and the M nearest adjacent positive samples in the one motion feature dimension, and calculate a second average distance between the target sample and the N nearest adjacent negative samples in the one motion feature dimension, calculate a distance difference between the first average distance and the second average distance, and determine a second correlation score of the one motion feature according to the distance difference corresponding to all target samples;

[0037] a comprehensive scoring unit, configured to perform a weighted summation of the first correlation score and the second correlation score corresponding to each motion feature to obtain a comprehensive score corresponding to each motion feature;

[0038] The feature selection unit is used to determine the target motion feature for characterizing the motion state of the target lower limb based on the comprehensive score corresponding to each motion feature.

[0039] In a third aspect, an embodiment of the present disclosure provides a computing device, comprising a processor and a memory, wherein the memory is used to store a computer program; when the computer program is loaded by the processor, the processor executes the motion feature screening method for identifying the motion state of the lower limbs as described above.

[0040] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program. When the computer program is executed by a processor, the processor implements the motion feature screening method for identifying the motion state of the lower limbs as described above.

[0041] The embodiment scheme of the present disclosure is adopted, a first correlation score of each motion feature is determined based on a machine learning method, a second correlation score of each motion feature is determined based on a clustering idea, and then the first correlation score and the second correlation score are weighted and summed to determine a comprehensive score of each motion feature, and a target motion feature characterizing the motion state of the target lower limb is determined based on the comprehensive score of each motion feature. By comprehensively determining the comprehensive score of each motion using different correlation analysis methods, the scoring result of the comprehensive score is more in line with the actual situation, thereby making the target motion feature finally selected more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor, including

[0044] Figure 1 is a flow chart of a motion feature screening method for identifying lower limb motion status provided by an embodiment of the present disclosure;

[0045] Figure 2 is a flow chart of determining motion characteristics based on inertial measurement signals provided by some embodiments;

[0046] Figure 3 is a flow chart of determining motion characteristics based on inertial measurement signals provided by some other embodiments;

[0047] Figure 4 is a flow chart of a method for determining target motion characteristics in some embodiments;

[0048] Figure 5 is a flow chart of a method for determining target motion characteristics in some other embodiments;

[0049] Figure 6 is a schematic diagram of a motion feature screening device for identifying the motion state of lower limbs provided by an embodiment of the present disclosure;

[0050] Figure 7 It is a schematic diagram of the structure of a computing device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0051] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0052] The term "including" and its variations used in this document are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. In this document, relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0053] In order to solve the problem of systematic errors that may occur in existing feature screening methods based on machine learning models, the embodiments of the present disclosure provide a new motion feature screening method for identifying the motion state of lower limbs.

[0054] Figure 1 FIG. 1 is a flow chart of a method for screening motion characteristics for identifying the motion state of lower limbs provided by an embodiment of the present disclosure. Figure 1 As shown, the motion feature screening method provided by the embodiment of the present disclosure includes S110 to S160. The motion feature screening method provided by the embodiment of the present disclosure is executed by a computing device.

[0055] S110: Determine the corresponding multiple motion features based on the inertial measurement signals collected during various lower limb motion states, and construct a sample data set based on the multiple motion features and the corresponding lower limb motion state labels. The sample data in the sample data set includes positive samples and negative samples.

[0056] Because the movement of the lower limbs of the human body is the coordinated movement of the thigh and calf, there are usually two inertial measurement units used in actual acquisition and motion recognition. The two inertial measurement units are fixed relative to the thigh and calf, respectively, to collect the movement status of the thigh and calf, and obtain the corresponding inertial measurement signals.

[0057] In the embodiment of the present disclosure, after obtaining the inertial measurement signal collected by the inertial measurement unit fixed on the thigh and the calf, the computing device determines multiple motion features based on the inertial measurement signal. The following is an analysis of how to determine multiple motion features based on the inertial measurement signal in the embodiment of the present disclosure.

[0058] Figure 2 FIG. 4 is a flow chart of determining motion characteristics based on inertial measurement signals provided by some embodiments. Figure 2 As shown, in some embodiments, the computing device may determine at least some of the multiple motion features using the following S111 - S112 .

[0059] S111: sampling the inertial measurement signals collected during various lower limb motion states according to a preset sliding time window, and determining a kinematic feature sequence sorted within the sliding time window.

[0060] The inertial measurement unit includes an accelerometer and a gyroscope, wherein the accelerometer can measure the acceleration of three axes, and the gyroscope can measure the angular velocity of three axes. After obtaining the original three-axis acceleration and original three-axis angular velocity measured by an inertial measurement unit, the computing device can obtain the three-axis acceleration and three-axis angular velocity in the reference coordinate system through data processing, and then obtain the corresponding roll angle, pitch angle and yaw angle through Euler angle calculation after obtaining the three-axis acceleration and three-axis angular velocity. Because the aforementioned technical content is already a common practice in this field, the aforementioned content will not be analyzed in detail here.

[0061] As analyzed above, when two inertial measurement units are used to obtain the kinematic characteristics of the thigh and calf respectively, 18 kinematic characteristics can be obtained based on the inertial measurement signal at one time point, which are the three-axis acceleration, three-axis angular velocity, and roll angle, pitch angle, and yaw angle of the thigh and calf after attitude solution. Since the inertial measurement signal may be affected by the background noise of the inertial measurement unit and the environmental noise, a low-pass filter (such as a fourth-order Butterworth low-pass filter) can be used in practical applications to smooth the inertial measurement signal, and the smoothed inertial measurement signal can be used to determine the above 18 kinematic characteristics.

[0062] In practical applications, the motion state cannot be determined by the kinematic features of a single time point, but by the kinematic features of enough time points. To this end, it is necessary to sample the inertial measurement signals collected for various lower limb motion states using a preset sliding time window, and determine each kinematic feature within the sliding time window according to the aforementioned method, and sort each kinematic feature according to the timestamp to obtain a sorted kinematic feature sequence.

[0063] In order to fully obtain a complete sequence of kinematic features of the lower limb movement state, it is necessary to ensure that the size of the preset sliding time window is larger than the lower limb movement cycle. Considering that the normal walking frequency of a typical human body is 0.6-1.0Hz (corresponding to 0.6s to complete a step, and the lower limb movement cycle is 1.2s-2.0s), the preset sliding time window can be set to 2s to obtain the sequence of kinematic features within the 2s sliding time window.

[0064] It should be noted that in order to ensure that the inertial measurement signal and kinematic features that characterize sufficient motion details are obtained, the correlation measurement unit should be sampled at a higher sampling frequency. For example, in a specific application, the sampling frequency of the inertial measurement unit is set to 50Hz. In addition, in order to obtain as many sorted kinematic feature sequences as possible in a motion state, the sliding window step size of the preset sliding time window cannot be too small. In one embodiment, the sliding step size of the preset sliding time window is set to 0.02s, that is, the preset sliding time window completes 50 sliding windows within 1s, and 50 sorted kinematic feature sequences are obtained.

[0065] S112: Calculate corresponding multiple motion features based on various motion kinematic feature sequences respectively.

[0066] After obtaining a sorting kinematic feature sequence, at least one of the following parameters can be obtained as the corresponding multiple motion features for a single sorting kinematic feature sequence: mean, maximum, minimum, median, variance, peak-to-peak difference, signal energy, skewness, kurtosis, maximum slope, root mean square, absolute mean, pulse factor, root amplitude, margin index, waveform factor, crest factor, vector and amplitude, absolute area.

[0067] The mean represents the average value of all data in a time series; the maximum represents the maximum value of all data in a time series; the minimum represents the minimum value of all data in a time series; the median represents the median of all data in a time series; the variance represents the degree of dispersion of data in a time series; the peak-to-peak difference represents the difference between the maximum and minimum values ​​in a time series; the signal energy represents the sum of squares of all data in a time series; the skewness represents the degree of asymmetry of all data in a time series; the kurtosis represents the degree of peak distribution of all data in a time series; the maximum slope represents the difference between the maximum and minimum values ​​in a time series and the corresponding time The ratio of intervals; the root mean square is used to characterize the effective amplitude of data in a time series; the absolute value mean is the average of the absolute values ​​of all data in a time series; the impulse factor is the ratio of the maximum value to the root mean square in a time series; the root mean amplitude is the square root of the root mean square value in a time series and the length of the sequence; the margin index is the ratio of the maximum value to the root mean amplitude in a time series; the waveform factor characterizes the peak characteristics of the data in the time series, which is the ratio of the peak value to the root mean square; the crest factor is the peak characteristic of the data in a time series, which is the ratio of the data peak value to the mean; the vector sum amplitude is the amplitude of all values ​​in a time series added directly. The absolute value area is the sum of the absolute values ​​of all data in a time series.

[0068] Figure 3is a flowchart of determining motion features based on inertial measurement signals provided by other embodiments. In another embodiment, when the inertial measurement signals include a thigh inertial measurement signal collected by an inertial measurement unit located on the thigh, and a calf inertial measurement signal collected by an inertial measurement unit located on the calf, the computing device may use the following S113-S116 to determine at least some of the multiple motion features.

[0069] S113: sampling the thigh inertial measurement signals and the calf inertial measurement signals collected during various lower limb motion states according to a preset sliding time window, and determining the thigh kinematic characteristics and the calf sorting kinematic characteristics sequence within the sliding time window.

[0070] S114: Based on the sorted kinematic feature sequences of the thigh in each dimension, obtain the thigh motion features of the corresponding dimension; and, based on the sorted kinematic feature sequences of the calf in each dimension, obtain the calf motion features of the corresponding dimension.

[0071] In a specific implementation, S113-S114 can be executed according to S111-S112 in the previous text, and will not be analyzed in detail here.

[0072] S115: Obtain the ratio of the thigh motion feature and the calf motion feature of the corresponding dimension, and / or the signal energy of the thigh motion feature and the calf motion feature of the corresponding dimension.

[0073] S116: Use the ratio and / or signal energy as at least part of the motion feature.

[0074] After obtaining the thigh motion features and calf motion features of a certain motion dimension within a preset sliding time window, the ratio of the thigh motion features and the calf motion features can be subsequently calculated, or the signal energy of the thigh motion features and the calf motion features of the corresponding dimension can be calculated. The aforementioned ratio represents the ratio of the motion features of the same kinematic dimension, such as the thigh and calf, and the aforementioned signal energy is the sum of the squares of the same motion features.

[0075] After following the aforementioned S111 - S112 and S113 - S116 , the computing device may then determine all motion features.

[0076] In one embodiment, in order to identify whether filtering the inertial measurement signal affects the correlation between the motion characteristics and the motion state of the lower limbs, this scheme obtains the corresponding kinematic characteristics based on the inertial measurement signal before filtering and the inertial measurement signal after filtering, and determines the corresponding motion characteristics according to the above method.

[0077] After obtaining a plurality of motion features, the computing device then associates the aforementioned plurality of motion features with corresponding lower limb motion state labels to form sample data, and constructs a sample data set based on the sample data.

[0078] In the disclosed embodiment, the aforementioned sample data includes positive samples and negative samples, the label of the positive sample is the target lower limb motion state label, and the label of the negative sample is the non-target lower limb motion state label. For example, in an application, it is necessary to determine the sample associated with the walking state, the corresponding target lower limb motion state is the walking state, and the corresponding sample data with the label of the walking state is the positive sample; correspondingly, the sample data with labels such as squatting, jumping, going upstairs, going downstairs, running, etc. are negative samples.

[0079] S120: Using a machine learning model to perform correlation analysis based on the label of the sample data and a motion feature, respectively, to determine a first correlation score between various motion features and the target lower limb motion state.

[0080] After obtaining the sample data set, the labels of the sample data in the sample data set and each motion feature can be used to perform correlation analysis to determine a first correlation score between each motion feature and the target lower limb motion state.

[0081] In a specific implementation, the computing device uses a predetermined machine learning model to perform the aforementioned correlation analysis to obtain a first correlation score. The machine learning model can be any one of a logistic regression model, a latent Dirichlet distribution model, a K nearest neighbor algorithm model, a decision tree model, a Gaussian naive Bayes analysis model, an extreme gradient boosting tree model, a lightweight gradient boosting machine model, a decision tree model based on gradient boosting, a random forest model, and a generalized additive model, and the embodiments of the present disclosure are not particularly limited.

[0082] In some embodiments, the computing device uses a logistic regression model to perform a correlation analysis on a motion feature and a label of sample data to determine a first correlation score between a motion feature and a target lower limb motion state, specifically including the following S121-S122.

[0083] S121: Using a logistic regression model, performing correlation analysis based on the label of the sample data and a motion feature, and determining a feature coefficient corresponding to the motion feature in the logistic regression model.

[0084] The basic form of the logistic regression model is Where X f Characterize a motion feature, w f is the characteristic coefficient, which represents a motion feature X f The sample data label is the degree of influence on the target lower limb motion state, w fThe larger the absolute value of is, the greater the influence of a motion feature on the output result is.

[0085] S122: Using the absolute value of the characteristic coefficient as a first correlation score between a motion feature and the target lower limb motion state.

[0086] As analyzed above, the larger the absolute value of wf is, the greater the influence of a motion feature on the output result is. Therefore, the absolute value of the feature coefficient can be used as the first correlation score between a motion feature and the target lower limb motion state, that is, MLscore (X f )=|w f |.

[0087] In some other embodiments, the computing device uses a Gaussian Naive Bayes model to perform a correlation analysis on a motion feature and a label of sample data to determine a first correlation score between a motion feature and a target lower limb motion state, specifically including the following S123-S124.

[0088] S123: A Gaussian Naive Bayes model is used to perform correlation analysis based on the label of the sample data and a motion feature to determine the standard deviation in the target lower limb motion state and the non-target lower limb motion state, respectively.

[0089] S124: Calculate the average value of the standard deviations of the target lower limb state and the non-target lower limb state corresponding to a motion feature, as a first correlation score between the motion feature and the target lower limb motion state.

[0090] For a motion feature X f , in a given lower limb motion state C k The conditional probability under the Gaussian distribution where μ k,f Category C k Lower Movement Feature X f The mean value of k,f Category C k Lower Movement Feature X f The standard deviation of the motion feature X f For classification of lower limb movement status C k The importance of can be measured by the change in conditional probability, so by calculating the conditional probability P(X f |C k ), and the standard deviation is used to characterize the importance of motion characteristics in determining the motion state of the lower limbs. Therefore, by taking the mean of each standard deviation, A first relevance score is determined.

[0091] In some embodiments, at least two machine learning models may be used to perform correlation analysis on a motion feature and a label of sample data to obtain corresponding correlation scores, and then weighted sum the corresponding correlation scores to obtain a corresponding first correlation score.

[0092] The aforementioned machine learning model is used to determine the first correlation score by analyzing the correlation between the motion features and the sample labels. The following S130-S140 determines the second correlation score based on whether the samples with different labels have significant differences.

[0093] S130: randomly selecting multiple target samples in the sample data set, and determining M adjacent positive samples in the positive samples that are closest to each target sample in a motion feature dimension, and determining N adjacent negative samples in the negative samples that are closest to each target sample in a motion feature dimension.

[0094] Through the numerical distribution characteristics of a large number of motion features that have a significant correlation with the label, as well as the numerical analysis of motion features that have no significant correlation with the label, it is found that the numerical characteristics of similar samples (similar positive samples, similar negative samples) of motion features that have a significant correlation with the label are relatively close, and the numerical characteristics of heterogeneous features are farther apart, while the similar features and heterogeneous features of motion features that have no significant correlation with the label do not have the aforementioned characteristics.

[0095] Based on the previous normal, the embodiment of the present disclosure can determine the correlation score between each motion feature and the label by whether the similar features and heterogeneous features have typical clustering characteristics. Specifically, in order to make the final correlation score typical and reliable, it is necessary to randomly select multiple target samples in the sample data set, and then for each target sample, determine the M adjacent samples closest to each target sample in a motion feature dimension in the positive sample, and determine the N adjacent samples closest to each target sample in a motion feature dimension in the negative sample. The aforementioned M and N can be the same or different, and the embodiment of the present disclosure does not limit this. In practical applications, M and N can be 1 or a positive integer greater than 1.

[0096] S140: Calculate a first average distance between the target sample and the nearest M adjacent positive samples in a motion feature dimension, and calculate a second average distance between the target sample and the nearest N adjacent negative samples in a motion feature dimension, calculate the distance difference between the first average distance and the second average distance, and determine a second correlation score of a motion feature based on the distance difference corresponding to all target samples.

[0097] Calculating the first average distance between the target sample and the nearest M adjacent positive samples in a motion feature dimension is to calculate the distance between the nearest M adjacent samples in a motion feature dimension and the target sample in a motion feature dimension, and then taking the average of the aforementioned distances to obtain the first average distance.

[0098] Similarly, calculating the first average distance between the target sample and the nearest M adjacent negative samples in a motion feature dimension is to calculate the distance between the nearest M adjacent samples in a motion feature dimension and the target sample in a motion feature dimension, and then taking the average of the aforementioned distances to obtain the first average distance.

[0099] After obtaining the first average distance and the second average distance, the distance difference between the first average distance and the second average distance may be calculated. After obtaining the distance difference, the computing device may determine a second correlation score of a motion feature based on the distance differences corresponding to all target samples in the following manner:

[0100] When the distance difference is a positive value, the initial weight is adjusted down to obtain a corresponding reduced weight; and when the distance difference is a negative value, the initial weight is adjusted up to obtain a corresponding increased weight; the average value of all reduced weights and increased weights is calculated as a second correlation score of a motion feature. The aforementioned initial weight can be 0 or a value greater than 0.

[0101] S150: Perform a weighted summation of the first correlation score and the second correlation score corresponding to each motion feature to obtain a comprehensive score corresponding to each motion feature.

[0102] The above method based on machine learning model correlation analysis and the method based on feature proximity analysis are used to determine the first correlation score and the second correlation score of each motion feature. Then, the first correlation score and the second correlation score can be weighted and summed to obtain the comprehensive score corresponding to each motion feature.

[0103] In some embodiments, in order to achieve better data comparison and thus make weight setting simpler, the computing device can normalize the first correlation score and the second correlation score respectively to obtain a first normalized score and a second normalized score, and then perform weighted summation based on the first normalized score and the second normalized score to obtain a comprehensive score corresponding to each motion feature.

[0104] Specifically, the computing device may use the formula Calculate the comprehensive score W mix,f , where w RFscore and w MLscore is a predetermined weight, RFscoref The first relevance score of the f-th motion feature, RFscore min is the minimum value of the first relevance score of all motion features, RFscore max is the maximum value of the first correlation score of all motion features, MLscore f The second correlation score of the f-th motion feature, MLscore min is the minimum value of the second correlation score of all motion features, MLscore max is the maximum value of the second correlation scores of all motion features.

[0105] S160: Determine a target motion feature for characterizing the motion state of the target lower limb based on the comprehensive score corresponding to each motion feature.

[0106] After obtaining the comprehensive scores corresponding to the various motion features, the computing device may sort the comprehensive scores by size, and then determine the sorting order corresponding to the various motion features. After determining the sorting order, the target motion features for characterizing the motion state of the target lower limb may be determined according to the sorting order and the predetermined selection criteria. For example, in some applications, the predetermined selection criteria is to select the first L motion features in the sorting order, and the first L motion features are used as the target motion features of the motion state of the target lower limb.

[0107] As previously analyzed, the disclosed embodiment scheme adopts a machine learning-based method to determine the first correlation score of each motion feature, adopts a clustering-based method to determine the second correlation score of each motion feature, and then weights and sums the first correlation score and the second correlation score to determine the comprehensive score of each motion feature, and determines the target motion feature that characterizes the motion state of the target lower limb based on the comprehensive score of each motion feature. The aforementioned method determines the comprehensive score of each motion by combining different correlation analysis methods, so that the scoring result of the comprehensive score is more in line with the actual situation, thereby making the target motion feature finally selected more reasonable.

[0108] In practical applications, some motion features are correlated (e.g., linear positive correlation). If all the above-mentioned correlated motion features are used for model training, not only will there be too many motion features in the subsequent model training, but it may also cause the model training to have poor fit. In order to minimize the number of target motion features, Figure 4 is a flow chart of a method for determining target motion characteristics in some embodiments. Figure 4 As shown, in some embodiments, the method for determining target motion characteristics based on the comprehensive score may include the following S161-S163.

[0109] S161: Determine the motion features to be selected based on the comprehensive scores corresponding to the various motion features.

[0110] The motion features to be selected are determined according to the comprehensive scores corresponding to the various motion features. The comprehensive scores of the various motion features may be sorted, and a preset number of motion features that are ranked first are used as the motion features to be selected.

[0111] S162: performing pairwise correlation analysis on the motion features to be selected, determining irrelevant motion features and relevant motion features, and determining selected relevant motion features among the relevant motion features.

[0112] In a specific implementation, the computing device may use a Pearson correlation coefficient analysis method to perform a pairwise correlation analysis on the selected motion features to obtain pairwise correlation coefficients of the selected motion features. The Pearson correlation coefficient r is calculated, where A and B are feature vectors constructed using a motion feature in the sample data set, and N is the length of the feature vector.

[0113] After calculating the pairwise correlation coefficients representing each of the motion features to be selected, the pairwise correlation coefficients can be compared with a preset correlation threshold. If the pairwise correlation coefficients are greater than the correlation threshold, the two motion features to be selected are determined to be related motion features, otherwise the two motion features to be selected are irrelevant features. In the case where the two motion features to be selected are determined to be related motion features, the motion feature to be selected with a better comprehensive score can be selected as the selected related motion feature.

[0114] S163: Using the irrelevant motion features and the selected relevant motion features as target motion features.

[0115] After determining irrelevant motion features and selecting relevant motion features, both can be used as target motion features.

[0116] Figure 5 is a flow chart of a method for determining target motion features in some other embodiments. In some other embodiments, the method for determining target motion features based on comprehensive scores may include the following S164-S165.

[0117] S164: performing pairwise correlation analysis based on the motion features, determining irrelevant motion features and relevant motion features, and determining selected relevant motion features among the relevant motion features.

[0118] Different from the above S161-S163, this embodiment first performs a pairwise correlation analysis on each motion feature to determine irrelevant motion features and selected relevant motion features among relevant motion features. In a specific implementation, the same method as the above S162 can be used to perform a correlation analysis to determine irrelevant motion features and relevant motion features, thereby obtaining irrelevant motion features and selected relevant motion features.

[0119] S165: Determine the target motion feature from the irrelevant motion features and the selected relevant motion features according to the comprehensive scores of the irrelevant motion features and the selected relevant motion features.

[0120] After determining irrelevant motion features and selecting relevant motion features, the aforementioned motion features may be sorted according to their comprehensive scores to determine a sorting order, and the motion features ranked first may be used as target motion features.

[0121] In addition to providing the aforementioned motion feature screening method for identifying the motion state of lower limbs, the embodiment of the present disclosure also provides a motion feature screening device for identifying the motion state of lower limbs. Figure 6 Schematic diagram of a motion feature screening device for identifying the motion state of lower limbs provided by an embodiment of the present disclosure. Figure 6 As shown, the motion feature screening device 600 for identifying the motion state of lower limbs includes a sample data set construction unit 601, a first scoring unit 602, a second scoring unit 603, a comprehensive scoring unit 604 and a feature selection unit 605.

[0122] The sample data set construction unit 601 is used to determine the corresponding multiple motion features based on the inertial measurement signals collected during various lower limb motion states, and to construct a sample data set based on the multiple motion features and the corresponding lower limb motion state labels. The sample data in the sample data set includes positive samples and negative samples. The label of the positive sample is the target lower limb motion state label, and the label of the negative sample is the non-target lower limb motion state label.

[0123] The first scoring unit 602 is used to use a machine learning model to perform correlation analysis based on the label of the sample data and a motion feature, and determine a first correlation score between various motion features and the target lower limb motion state.

[0124] The second scoring unit 603 is used to randomly select multiple target samples in the sample data set, and determine the M adjacent positive samples in the positive samples that are closest to each target sample in a motion feature dimension, and determine the N adjacent negative samples in the negative samples that are closest to each target sample in a motion feature dimension; and calculate the first average distance between the target sample and the nearest M adjacent positive samples in a motion feature dimension, and calculate the second average distance between the target sample and the nearest N adjacent negative samples in a motion feature dimension, calculate the distance difference between the first average distance and the second average distance, and determine a second correlation score of a motion feature according to the distance difference corresponding to all target samples.

[0125] The comprehensive scoring unit 604 is used to perform weighted summation of the first correlation score and the second correlation score corresponding to each motion feature to obtain a comprehensive score corresponding to each motion feature.

[0126] The feature selection unit 605 is used to determine the target motion feature for characterizing the motion state of the target lower limb based on the comprehensive scores corresponding to the various motion features.

[0127] In some embodiments, the feature selection unit 605 determines the motion features to be selected based on the comprehensive scores corresponding to the various motion features; performs pairwise correlation analysis on the selected motion features to determine irrelevant motion features and relevant motion features, and determines selected relevant motion features among the relevant motion features; and uses the irrelevant motion features and the selected relevant motion features as target motion features.

[0128] In some other embodiments, the feature selection unit 605 performs pairwise correlation analysis on each motion feature to determine irrelevant motion features and relevant motion features, and determines selected relevant motion features from the relevant motion features; and determines target motion features from the irrelevant motion features and the selected relevant motion features based on the comprehensive scores of the irrelevant motion features and the selected relevant motion features.

[0129] In some embodiments, the first scoring unit 602 uses a logistic regression model to perform correlation analysis based on the label of the sample data and a motion feature, determine the characteristic coefficient corresponding to a motion feature in the logistic regression model, and use the absolute value of the characteristic coefficient as a first correlation score between the motion feature and the target lower limb motion state.

[0130] In some other embodiments, the first scoring unit 602 uses a Gaussian naive Bayes model to perform correlation analysis based on the label of the sample data and a motion feature to respectively determine the standard deviation of the target lower limb motion state and the non-target lower limb motion state; and calculates the average value of the standard deviation of the target lower limb state and the non-target lower limb state corresponding to a motion feature as a first correlation score between a motion feature and the target lower limb motion state.

[0131] In some embodiments, when the distance difference is a positive value, the second scoring unit 603 decreases the initial weight to obtain a corresponding decreased weight; and when the distance difference is a negative value, the second scoring unit 603 increases the initial weight to obtain a corresponding increased weight; the average of all decreased weights and increased weights is calculated as a second correlation score for a motion feature.

[0132] In some embodiments, the sample data set construction unit 601 samples the inertial measurement signals collected during various lower limb motion states according to a preset sliding time window, and determines a kinematic feature sequence sorted within the sliding time window; wherein the preset sliding time window is greater than the lower limb motion cycle period; based on various sorted kinematic feature sequences, at least one of the following parameters is calculated as multiple motion features: mean, maximum, minimum, median, variance, peak-to-peak difference, signal energy, skewness, kurtosis, maximum slope, root mean square, absolute mean, pulse factor, root amplitude, margin index, waveform factor, crest factor, vector and amplitude, absolute area.

[0133] In some other embodiments, the inertial measurement signal includes a thigh inertial measurement signal collected by an inertial measurement unit located on the thigh, and includes a calf inertial measurement signal collected by an inertial measurement unit located on the calf. Correspondingly, the sample data set construction unit 601 samples the thigh inertial measurement signal and the calf inertial measurement signal collected during various lower limb motion states according to a preset sliding time window, and determines the thigh kinematic characteristics and the sorted kinematic characteristics sequence of the calf within the sliding time window; wherein the preset sliding time window is greater than the lower limb motion cycle; wherein the preset sliding time window is greater than the lower limb motion cycle; based on the sorted kinematic characteristics sequence of the thigh in each dimension, the thigh motion characteristics of the corresponding dimension are obtained; and, based on the sorted kinematic characteristics sequence of the calf in each dimension, the calf motion characteristics of the corresponding dimension are obtained; the ratio of the thigh motion characteristics and the calf motion characteristics of the corresponding dimension is obtained, and / or the signal energy of the thigh motion characteristics and the calf motion characteristics of the corresponding dimension is obtained; and the ratio and / or the signal energy are used as at least part of the motion characteristics.

[0134] The embodiment of the present disclosure also provides a computing device for implementing the aforementioned method. Figure 7 Schematic diagram of the structure of the computing device provided by the embodiment of the present disclosure. Figure 7 , which shows a schematic diagram of the structure of a computing device 700 suitable for implementing the embodiments of the present disclosure. Figure 7 The computing device shown is only an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present disclosure.

[0135] like Figure 7As shown, the computing device 700 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 702 or a program loaded from a storage device 708 to a random access memory RAM 703. Various programs and data required for the operation of the computing device 700 are also stored in the RAM 703. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output I / O interface 705 is also connected to the bus 704.

[0136] Typically, the following devices may be connected to the I / O interface 705: input devices 705 including, for example, a touch screen, a touch pad, a camera, a microphone, etc.; output devices 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 708 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 709. The communication devices 709 may allow the computing device 700 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The computing device 700 is shown with various devices, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead.

[0137] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 709, or installed from a storage device 708, or installed from a ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0138] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable storage medium, a computer-readable signal medium, or any combination of the above two.

[0139] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0140] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer readable program codes. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0141] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0142] The computer-readable medium may be included in the computing device, or may exist independently without being incorporated into the computing device.

[0143] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the tester computer, partially on the tester computer, as a separate software package, partially on the tester computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the tester computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0144] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system based on hardware that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0145] The units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The name of the unit does not, in some cases, constitute a limitation on the unit itself. The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0146] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A motion feature screening method for identifying the motion state of lower limbs, characterized in that: include: Based on the inertial measurement signals collected during various lower limb motion states, the corresponding multiple motion features are respectively determined, and a sample data set is constructed based on the multiple motion features and the corresponding lower limb motion state labels, wherein the sample data in the sample data set includes positive samples and negative samples, the labels of the positive samples are target lower limb motion state labels, and the labels of the negative samples are non-target lower limb motion state labels; Using a machine learning model to perform correlation analysis based on the label of the sample data and a motion feature, respectively, to determine a first correlation score between various motion features and the target lower limb motion state; A plurality of target samples are randomly selected from the sample data set, and M adjacent positive samples that are closest to each of the target samples in a motion feature dimension are determined in the positive samples, and N adjacent negative samples that are closest to each of the target samples in the motion feature dimension are determined in the negative samples; Calculating a first average distance between the target sample and the nearest M adjacent positive samples in the one motion feature dimension, and calculating a second average distance between the target sample and the nearest N adjacent negative samples in the one motion feature dimension, calculating a distance difference between the first average distance and the second average distance, and determining a second correlation score of the one motion feature according to the distance differences corresponding to all target samples; Taking a weighted sum of the first correlation score and the second correlation score corresponding to each motion feature to obtain a comprehensive score corresponding to each motion feature; Based on the comprehensive scores corresponding to the various motion features, the target motion features for characterizing the motion state of the target lower limbs are determined.

2. The screening method according to claim 1, characterized in that The target motion feature for characterizing the motion state of the target lower limb is determined based on the comprehensive score corresponding to each motion feature, including: Determine the motion features to be selected based on the comprehensive scores corresponding to the various motion features; Performing pairwise correlation analysis on the motion features to be selected, determining irrelevant motion features and relevant motion features, and determining selected relevant motion features from the relevant motion features; Using the irrelevant motion features and the selected relevant motion features as the target motion features; or, Performing pairwise correlation analysis on each motion feature to determine irrelevant motion features and relevant motion features, and determining selected relevant motion features among the relevant motion features; The target motion feature is determined from among the irrelevant motion features and the selected relevant motion features according to the comprehensive scores of the irrelevant motion features and the selected relevant motion features.

3. The screening method according to claim 1 or 2, characterized in that The machine learning model is used to perform correlation analysis based on the label of the sample data and a motion feature to determine a first correlation score between various motion features and the target lower limb motion state, including: A logistic regression model is used to perform correlation analysis based on the label of the sample data and the one motion feature, to determine the characteristic coefficient corresponding to the one motion feature in the logistic regression model, and the absolute value of the characteristic coefficient is used as the first correlation score between the one motion feature and the target lower limb motion state.

4. The screening method according to claim 1 or 2, characterized in that The machine learning model is used to perform correlation analysis based on the label of the sample data and a motion feature to determine a first correlation score between various motion features and the target lower limb motion state, Using a Gaussian Naive Bayes model, a correlation analysis is performed based on the label of the sample data and the one motion feature, and the standard deviations in the target lower limb motion state and the non-target lower limb motion state are determined respectively; The average value of the standard deviations of the target lower limb state and the non-target lower limb state corresponding to the one motion feature is calculated as the first correlation score between the one motion feature and the target lower limb motion state.

5. The screening method according to claim 1 or 2, characterized in that The determining the second correlation score of the motion feature according to the distance differences of all target samples comprises: When the distance difference is a positive value, the initial weight is adjusted down to obtain a corresponding reduced weight; and when the distance difference is a negative value, the initial weight is adjusted up to obtain a corresponding increased weight; the average of all the reduced weights and the increased weight is calculated as the second correlation score of the one motion feature.

6. The screening method according to claim 1 or 2, characterized in that The inertial measurement signals collected based on various lower limb motion states respectively determine the corresponding multiple motion features, including: According to a preset sliding time window, inertial measurement signals collected during various lower limb motion states are sampled respectively, and a kinematic feature sequence is determined to be sorted within the sliding time window; wherein the preset sliding time window is greater than the lower limb motion cycle period; Based on various sorted kinematic feature sequences, at least one of the following parameters is calculated as the multiple motion features: mean, maximum, minimum, median, variance, peak-to-peak difference, signal energy, skewness, kurtosis, maximum slope, root mean square, absolute mean, pulse factor, root amplitude, margin index, waveform factor, crest factor, vector and amplitude, absolute area.

7. The screening method according to claim 1 or 2, characterized in that The inertial measurement signal includes a thigh inertial measurement signal collected by an inertial measurement unit located on the thigh, and a calf inertial measurement signal collected by an inertial measurement unit located on the calf; The method comprises: sampling the thigh inertial measurement signals and the calf inertial measurement signals collected during various lower limb movement states according to a preset sliding time window, and determining the thigh kinematic characteristics and the calf sorting kinematic characteristics sequence within the sliding time window; wherein the preset sliding time window is greater than the lower limb movement cycle period; wherein the preset sliding time window is greater than the lower limb movement cycle period; Based on the sorted kinematic feature sequences of the thigh in each dimension, the thigh motion features of the corresponding dimension are obtained; and based on the sorted kinematic feature sequences of the calf in each dimension, the calf motion features of the corresponding dimension are obtained; Calculate the ratio of the thigh motion feature and the calf motion feature of the corresponding dimension, and / or the signal energy of the thigh motion feature and the calf motion feature of the corresponding dimension; The ratio and / or the signal energy are used as at least part of the motion characteristic.

8. A motion feature screening device for identifying the motion state of lower limbs, characterized in that: include: A sample data set construction unit, used to determine the corresponding multiple motion features based on the inertial measurement signals collected during various lower limb motion states, and to construct a sample data set based on the multiple motion features and the corresponding lower limb motion state labels, wherein the sample data in the sample data set includes positive samples and negative samples, the labels of the positive samples are target lower limb motion state labels, and the labels of the negative samples are non-target lower limb motion state labels; A first scoring unit is used to use a machine learning model to perform correlation analysis based on the label of the sample data and a motion feature, and determine a first correlation score between various motion features and the target lower limb motion state; A second scoring unit is used to randomly select multiple target samples in the sample data set, and determine M adjacent positive samples in the positive samples that are closest to each of the target samples in a motion feature dimension, and determine N adjacent negative samples in the negative samples that are closest to each of the target samples in the one motion feature dimension; and calculating a first average distance between the target sample and the nearest M adjacent positive samples in the one motion feature dimension, and calculating a second average distance between the target sample and the nearest N adjacent negative samples in the one motion feature dimension, calculating a distance difference between the first average distance and the second average distance, and determining a second correlation score of the one motion feature according to the distance difference corresponding to all target samples; a comprehensive scoring unit, configured to perform a weighted summation of the first correlation score and the second correlation score corresponding to each motion feature to obtain a comprehensive score corresponding to each motion feature; The feature selection unit is used to determine the target motion feature for characterizing the motion state of the target lower limb based on the comprehensive score corresponding to each motion feature.

9. A computing device, characterized in that It includes a processor and a memory, wherein the memory is used to store a computer program; when the computer program is loaded by the processor, the processor executes the motion feature screening method for identifying the motion state of lower limbs as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the processor implements the motion feature screening method for identifying the motion state of lower limbs as described in any one of claims 1-7.

Images