A gait evaluation method and device, electronic equipment and storage medium

Abstract

The application discloses a gait evaluation method and device, electronic equipment and storage medium, and relates to the technical field of gait analysis. In the application, gait data of a person with motor dysfunction in adjacent multiple walking cycles is obtained; the gait data comprises a gait phase parameter set and a posture angle parameter set of the person with motor dysfunction; from the gait phase parameter set and the posture angle parameter set included in the gait data, a gait phase parameter subset and a posture angle parameter subset corresponding to each of multiple gait evaluation dimensions are determined; based on the gait phase parameter subset and the posture angle parameter subset corresponding to each of the multiple gait evaluation dimensions, gait evaluation of the person with motor dysfunction is performed in the multiple gait evaluation dimensions to obtain multiple gait evaluation values; and based on the multiple gait evaluation values and gait evaluation weight values corresponding to the multiple gait evaluation values respectively, a comprehensive gait evaluation value of the person with motor dysfunction is determined. In this way, the gait data of the person with motor dysfunction is comprehensively quantified, and the accuracy of gait evaluation is improved.

Description

[0001] This application is a divisional application of Chinese application filed on November 12, 2025, with application number 202511652805.9 and invention title "A gait evaluation method, device and electronic device". Technical Field

[0002] This application relates to the field of gait analysis technology, and in particular to a gait evaluation method, device, electronic device and storage medium. Background Technology

[0003] Gait typically refers to the posture and behavioral characteristics of the lower limbs of a target individual (e.g., a pedestrian) during walking, reflecting their level of walking function. Therefore, by analyzing gait data such as gait phase parameters and posture angles of individuals with motor dysfunction (or patients), it is possible to assess their motor function recovery. Gait phase parameters include the lower limb characteristics of the individual during each gait phase within the corresponding walking cycle.

[0004] Currently, existing gait assessment methods mainly compare the gait data of individuals with motor dysfunction with those of individuals with normal motor function to assess whether the gait of the individuals with motor dysfunction has recovered to normal. For example, by comparing the gait phase parameters of individuals with motor dysfunction with those of individuals with normal motor function, the deviation of the gait phase parameters is obtained. Then, by combining this deviation with a set range, it is determined whether the gait of the individuals with motor dysfunction has recovered to normal.

[0005] However, the aforementioned gait assessment method suffers from low accuracy because it simply compares gait data with data from individuals with motor dysfunction without comprehensively quantifying their gait characteristics. Therefore, improving the accuracy of gait assessment is a pressing issue that needs to be addressed. Summary of the Invention

[0006] This application provides a gait evaluation method, device, electronic device, and storage medium to comprehensively quantify gait data of individuals with motor dysfunction, thereby improving the accuracy of gait assessment.

[0007] In a first aspect, embodiments of this application provide a gait evaluation method, the method comprising: Gait data of individuals with motor dysfunction within multiple adjacent walking cycles is acquired. This gait data includes a set of gait phase parameters and a set of posture angle parameters. Acquiring this data involves: using motion data acquisition modules fixed to multiple lower limb sites on the individual to collect motion data of the lower limbs within multiple walking cycles, obtaining lower limb motion data corresponding to each lower limb site. Each lower limb motion data includes multiple motion parameters for that specific lower limb site. Based on this lower limb motion data and a human kinematic model constructed for the individual with motor dysfunction, gait data is obtained. From the gait temporal parameter set and posture angle parameter set included in the gait data, determine the gait temporal parameter subset and posture angle parameter subset corresponding to various gait evaluation dimensions respectively; Based on subsets of gait temporal parameters and posture angle parameters corresponding to various gait evaluation dimensions, gait evaluations are performed on individuals with motor dysfunction across multiple gait evaluation dimensions, yielding multiple gait evaluation values. Specifically, for each gait evaluation dimension, the following operations are performed: determining each gait evaluation index corresponding to the first gait evaluation dimension; determining the index evaluation value for each gait evaluation index based on the subsets of gait temporal parameters, posture angle parameters, and the calculation methods corresponding to each gait evaluation index; and determining the index evaluation value based on each index evaluation value and the corresponding index weight. The first gait evaluation dimension is defined as follows: The first gait evaluation dimension can be any one of multiple gait evaluation dimensions. If the first gait evaluation dimension is gait symmetry evaluation, then the various gait evaluation indicators are determined, including the temporal symmetry index, stride length symmetry index, and lower limb asymmetry coefficient. Based on subsets of gait temporal parameters, subsets of posture angle parameters, and the calculation methods corresponding to each gait evaluation indicator, the evaluation values ​​corresponding to each gait evaluation indicator are determined. These include: determining the first evaluation value corresponding to the temporal symmetry index based on the single support time, single swing time, and gait cycle corresponding to individuals with and without motor function, respectively; and determining the second evaluation value corresponding to the stride length symmetry index based on the stride length and single swing time corresponding to individuals with and without motor function, respectively. Based on multiple gait evaluation values ​​and their corresponding gait evaluation weight values, the comprehensive gait evaluation value of individuals with motor dysfunction is determined.

[0008] Secondly, embodiments of this application also provide a gait evaluation device, the device comprising: The data acquisition module is used to acquire gait data of individuals with motor dysfunction within multiple adjacent walking cycles. The gait data includes a set of gait phase parameters and a set of posture angle parameters. Acquiring gait data within multiple adjacent walking cycles involves: using motion data acquisition modules fixed to multiple lower limb sites on the individual to collect motion data of the lower limbs within multiple walking cycles, obtaining lower limb motion data corresponding to each lower limb site; each lower limb motion data includes multiple motion parameters for the corresponding lower limb site; based on the lower limb motion data corresponding to each lower limb site and a human kinematic model constructed for the individual with motor dysfunction, gait data is obtained. The parameter determination module is used to determine the subsets of gait time-phase parameters and the subsets of posture angle parameters corresponding to various gait evaluation dimensions from the gait time-phase parameter set and posture angle parameter set included in the gait data. Specifically, based on the subsets of gait time-phase parameters and the subsets of posture angle parameters corresponding to various gait evaluation dimensions, gait evaluations are performed on individuals with motor dysfunction across various gait evaluation dimensions, resulting in multiple gait evaluation values. This includes: for each of the various gait evaluation dimensions, the following operations are performed: determining each gait evaluation index corresponding to the first gait evaluation dimension; determining the index evaluation value corresponding to each gait evaluation index based on the subsets of gait time-phase parameters, the subsets of posture angle parameters, and the calculation methods corresponding to each gait evaluation index; and determining the index evaluation value based on each index evaluation value and the index weight corresponding to each gait evaluation index. The first gait evaluation dimension is defined as follows: The first gait evaluation dimension can be any one of multiple gait evaluation dimensions. If the first gait evaluation dimension is gait symmetry evaluation, then the various gait evaluation indicators are determined, including the temporal symmetry index, stride length symmetry index, and lower limb asymmetry coefficient. Based on subsets of gait temporal parameters, subsets of posture angle parameters, and the calculation methods corresponding to each gait evaluation indicator, the evaluation values ​​corresponding to each gait evaluation indicator are determined. These include: determining the first evaluation value corresponding to the temporal symmetry index based on the single support time, single swing time, and gait cycle corresponding to individuals with and without motor function, respectively; and determining the second evaluation value corresponding to the stride length symmetry index based on the stride length and single swing time corresponding to individuals with and without motor function, respectively. The multidimensional evaluation module is used to evaluate the gait of individuals with motor dysfunction based on subsets of gait phase parameters and subsets of posture angle parameters corresponding to multiple gait evaluation dimensions, and obtain multiple gait evaluation values. The comprehensive evaluation module is used to determine the comprehensive gait evaluation value of individuals with motor dysfunction based on multiple gait evaluation values ​​and their corresponding gait evaluation weight values.

[0009] In an optional embodiment, if the first gait evaluation dimension is gait variability evaluation, then each gait evaluation index is determined to include gait variability index, gait deviation index, and gait data sample entropy; gait data sample entropy is used to measure the data complexity of gait data. When determining the evaluation values ​​of each gait evaluation index based on subsets of gait temporal parameters, subsets of posture angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module is specifically used for: The first comprehensive substitute parameter for multiple gait phase parameters corresponding to the gait variability index is determined, and the fourth index evaluation value corresponding to the gait variability index is determined based on the first difference between the first comprehensive substitute parameter and the mean of the first substitute parameter corresponding to individuals with normal motor function. A second comprehensive alternative parameter is determined for multiple posture angle parameters corresponding to the gait deviation index. Based on the second difference between the second comprehensive alternative parameter and the mean of the second alternative parameter corresponding to individuals with normal motor function, the fifth index evaluation value corresponding to the gait deviation index is determined. Based on the parameter time series corresponding to at least one gait phase parameter and at least one attitude angle parameter corresponding to the gait data sample entropy, the parameter sample entropy corresponding to multiple parameter time series is determined, and the sixth index evaluation value corresponding to the gait data sample entropy is determined based on the multiple parameter sample entropy.

[0010] In an optional embodiment, if the first gait evaluation dimension is gait coordination evaluation, then the various gait evaluation indicators are determined to include ankle-knee phase difference, knee-hip phase difference, and ankle-hip phase difference. When determining the evaluation values ​​of each gait evaluation index based on subsets of gait temporal parameters, subsets of posture angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module is specifically used for: Hilbert transform was performed on the posture angle data corresponding to the ankle, knee and hip joints respectively to obtain the transformation results corresponding to the ankle, knee and hip joints respectively; Based on the transformation results corresponding to the ankle, knee and hip joints respectively, the first continuous relative phase between the ankle and knee joints, the second continuous relative phase between the knee and hip joints, and the third continuous relative phase between the ankle and hip joints are determined for each gait phase. The seventh index evaluation value corresponding to the phase difference of the ankle and knee joint is determined based on each first continuous relative phase, the eighth index evaluation value corresponding to the phase difference of the knee and hip joint is determined based on each second continuous relative phase, and the ninth index evaluation value corresponding to the phase difference of the ankle and hip joint is determined based on each third continuous relative phase.

[0011] In an optional embodiment, if the first gait evaluation dimension is gait stability evaluation, then each gait evaluation index is determined to include a first dynamic stability and a second dynamic stability; wherein, the first dynamic stability characterizes the walking stability of a person with motor dysfunction along a first direction, and the second dynamic stability characterizes the walking stability of a person with motor dysfunction along a second direction. When determining the evaluation values ​​of each gait evaluation index based on subsets of gait temporal parameters, subsets of posture angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module is specifically used for: Based on the inverted pendulum model of the human body constructed for people with motor dysfunction, and the displacement and speed of the center of gravity of people with motor dysfunction at the current moment, the position of the center of gravity of people with motor dysfunction is determined. The first boundary position is determined based on the stride length of the person with motor dysfunction, and the second boundary position is determined based on the stride width of the person with motor dysfunction. The tenth index evaluation value corresponding to the first dynamic stability is determined based on the center of gravity position and the first boundary position, and the eleventh index evaluation value corresponding to the second dynamic stability is determined based on the center of gravity position and the second boundary position.

[0012] Thirdly, embodiments of this application also provide an electronic device, including: Processor; and Stored program memory, The program includes instructions that, when executed by the processor, cause the processor to perform the gait evaluation method as described in the first aspect.

[0013] Fourthly, embodiments of this application also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the gait evaluation method as described in the first aspect.

[0014] Fifthly, this application provides a computer program product that, when invoked by a computer, causes the computer to execute the gait evaluation method steps as described in the first aspect.

[0015] The beneficial effects of this application are as follows: In the gait evaluation method provided in this application embodiment, gait data of a person with motor dysfunction within multiple adjacent walking cycles is acquired. The gait data includes a set of gait temporal parameters and a set of posture angle parameters for the person with motor dysfunction. Then, from the gait temporal parameter set and posture angle parameter set included in the gait data, subsets of gait temporal parameters and subsets of posture angle parameters corresponding to various gait evaluation dimensions are determined. Further, based on the subsets of gait temporal parameters and posture angle parameters corresponding to various gait evaluation dimensions, gait evaluation of the person with motor dysfunction is performed according to various gait evaluation dimensions, resulting in multiple gait evaluation values. Finally, based on the multiple gait evaluation values ​​and their corresponding gait evaluation weight values, a comprehensive gait evaluation value for the person with motor dysfunction is determined. By performing gait evaluation of the person with motor dysfunction according to multiple gait evaluation dimensions, the gait data of the person with motor dysfunction is comprehensively quantified, improving the accuracy of gait assessment.

[0016] Furthermore, other features and advantages of this application will be set forth in the following description and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described herein are used to provide a further understanding of this application, constitute a part of this application, and do not constitute an improper limitation of this application. In the accompanying drawings: Figure 1 This is a schematic diagram of the system architecture of a gait evaluation system applicable to the embodiments of this application; Figure 2 A schematic diagram of the system architecture of another gait evaluation system provided in this application embodiment; Figure 3 A schematic diagram illustrating the implementation process of a gait evaluation method provided in this application embodiment; Figure 4 This application provides a schematic diagram of an application scenario for selecting gait phase parameters and attitude angle parameters. Figure 5 A schematic diagram illustrating the implementation process of a method for determining gait evaluation values ​​provided in this application embodiment; Figure 6 This application provides an illustration of an application scenario for determining a comprehensive gait evaluation value. Figure 7 This is a schematic diagram of the structure of a gait evaluation device provided in an embodiment of this application; Figure 8This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While some embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of this application are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0019] It should be understood that the steps described in the method embodiments of this application may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this application is not limited in this respect.

[0020] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this application are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0021] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of this application are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0023] The following explanations of some terms used in the embodiments of this application are provided to facilitate understanding by those skilled in the art.

[0024] (1) Z-score (z - score): is a common term for standard scores, used to measure the relative position of a data point to the mean. The formula is: z = (raw score - mean) / standard deviation.

[0025] (2) Continuous relative phase (CRP) is a biomechanical method for analyzing limb coordination. It assesses the synchronicity of movement between limbs by calculating the phase difference (0° - 360°) between joint angles and angular velocities.

[0026] (3) Singular value decomposition (SVD): It is a matrix factorization method and is the basis of principal component analysis (PCA).

[0027] Based on the above explanations of terms and related terminology, the design concept of the embodiments of this application will be briefly introduced below: Due to the large number of people suffering from motor dysfunction caused by neurological diseases such as stroke and cerebral palsy, the restoration of walking function is a crucial aspect of their motor rehabilitation. Gait is an important indicator reflecting the level of walking function, and evaluating various aspects such as gait spatiotemporal parameters and joint angles is a necessary means to objectively understand the patient's overall walking ability, develop targeted rehabilitation training programs, and evaluate rehabilitation effects. Currently, clinical gait assessment mainly involves testing single indicators such as gait spatiotemporal parameters and joint angles, comparing the test results with the range of normal individuals to assess whether the patient's gait is normal.

[0028] However, the aforementioned gait assessment method, by simply comparing gait data without comprehensively quantifying the gait data of individuals with motor dysfunction, fails to fully reflect the gait characteristics of these individuals, resulting in low accuracy in gait assessment. Therefore, to improve the accuracy of gait assessment, this application provides a gait evaluation method, which specifically includes: acquiring gait data of an individual with motor dysfunction over multiple adjacent walking cycles; wherein the gait data includes a set of gait phase parameters and a set of posture angle parameters for the individual with motor dysfunction; then, determining subsets of gait phase parameters and posture angle parameters corresponding to various gait evaluation dimensions from the gait phase parameter set and posture angle parameter set included in the gait data; further, performing gait evaluation on the individual with motor dysfunction based on the subsets of gait phase parameters and posture angle parameters corresponding to various gait evaluation dimensions, obtaining multiple gait evaluation values; finally, determining a comprehensive gait evaluation value for the individual with motor dysfunction based on the multiple gait evaluation values ​​and their corresponding gait evaluation weight values. In this way, by conducting gait evaluations on individuals with motor dysfunction across multiple gait assessment dimensions, and by comprehensively quantifying their gait data, the accuracy of gait assessment is improved.

[0029] In particular, the preferred embodiments of this application will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments of this application and the features in the embodiments can be combined with each other unless otherwise specified.

[0030] See Figure 1 The diagram shown illustrates the system architecture of a gait evaluation system applicable to an embodiment of this application. The gait evaluation system may include: a data acquisition terminal 11, a main controller 12, and a human-computer interaction unit 13. Each of the data acquisition terminal 11, the main controller 12, and the human-computer interaction unit 13 can interact with each other via a communication network.

[0031] The communication network described above can employ communication methods including wireless communication and wired communication. For example, the data acquisition terminal 11 can access the network via cellular mobile communication technology to communicate with the main controller 12 and the human-machine interface unit 13. The cellular mobile communication technology may include, for example, 5G (5th generation mobile networks) or next-generation mobile communication technology. Optionally, the data acquisition terminal 11 can access the network via short-range wireless communication to communicate with the main controller 12 and the human-machine interface unit 13. The short-range wireless communication technology may include, for example, Wi-Fi (wireless fidelity) technology.

[0032] Still Figure 1 As shown or see Figure 2 As shown, the data acquisition terminal 11 includes multiple inertial sensors 11A that can be attached to different parts of the human body and a data transmission module 11B. The main controller 12 includes a data processing module 12A, a gait parameter calculation module 12B, an evaluation index extraction module 12C, and an evaluation calculation module 12D. The data analysis and processing module 12A preprocesses the raw acceleration, angular velocity, and other inertial sensor data collected by the inertial sensor 11A. The gait parameter calculation module 12B uses inertial sensor data attached to different parts of the lower limbs to calculate gait phase parameters and posture angle parameters through a built-in human kinematics model. The evaluation index extraction module 12C has built-in gait evaluation algorithms for gait evaluation dimensions such as gait symmetry, gait variability, gait coordination, and gait stability. It inputs the various gait phase parameters and posture angle data calculated by the gait parameter calculation module 12B into the evaluation index extraction module 12C to obtain the calculation results corresponding to each gait evaluation dimension. The evaluation calculation module 12D contains a gait comprehensive evaluation model, which is used to comprehensively evaluate gait function based on the calculation results corresponding to each gait evaluation dimension obtained by the evaluation index extraction module 12C.

[0033] The human-computer interaction unit 13 includes a display component 13A, a command input component 13B, and interaction software 13C for human-computer interaction. The interaction software 13C includes a database management interface 13C1, a data acquisition interface 13C2, a gait parameter display interface 13C3, and an evaluation report interface 13C4. The gait parameter display interface 13C3 displays the temporal parameters and angular parameters of each gait. The evaluation report interface 13C4 displays the calculation results corresponding to each gait evaluation dimension, such as a topological diagram of the scores for gait symmetry, gait variability, gait coordination, and gait stability, as well as the overall gait evaluation score.

[0034] The gait evaluation method provided by the exemplary embodiments of this application will be described below with reference to the above system architecture and the following accompanying drawings. It should be noted that the above system architecture is only shown for the purpose of understanding the spirit and principles of this application, and the embodiments of this application are not limited in any way.

[0035] See Figure 3 As shown, this is a schematic diagram of the implementation process of a gait evaluation method provided in an embodiment of this application. The executing entity is... Figure 1 Taking the main controller shown as an example, the specific implementation process of this method is as follows: S301: Acquire gait data of individuals with motor dysfunction over multiple adjacent walking cycles.

[0036] The aforementioned gait data may include: a set of gait phase parameters and a set of posture angle parameters for individuals with motor dysfunction. Optionally, the gait phase parameter set includes multiple gait phase parameters for each gait phase, such as stride length, step duration, single swing phase, single support phase, single swing time, and single support time. The posture angle parameter set includes multiple posture angle parameters for each gait phase, such as: roll and pitch angles of the foot, lower leg, and thigh, as well as angles of the ankle, knee, and hip joints.

[0037] It should be noted that each gait cycle can be divided into eight gait phases, which are as follows: initial contact (IC), loading response (LR), mid stance (MS), terminal stance (TS), pre-swing (PS), initial swing (IS), mid swing (MS), and terminal swing (TS). Specifically, the initial contact, loading response, mid stance, terminal stance, and pre-swing all belong to the stance phase of the gait cycle, while the pre-swing, mid swing, and terminal swing all belong to the swing phase.

[0038] In one alternative implementation, during step S301, the main controller can utilize motion data acquisition modules (e.g., fixed to multiple lower limb sites of the person with motor dysfunction) to acquire motion data. Figure 2 The inertial sensor shown collects motion data of the lower limbs of a person with motor dysfunction over multiple walking cycles (e.g., 15 walking cycles), obtaining lower limb motion data corresponding to multiple lower limb parts. Based on the lower limb motion data corresponding to multiple lower limb parts and a human kinematic model constructed for the person with motor dysfunction, gait data of the person with motor dysfunction is obtained. Each lower limb motion data includes multiple motion parameters for the corresponding lower limb part, such as linear velocity, angular velocity, and acceleration.

[0039] It should be understood that the above-mentioned human kinematic model can be constructed based on the physical characteristics data (such as leg length) of people with motor dysfunction, that is, the constructed human kinematic model can better replicate the gait of people with motor dysfunction.

[0040] Based on the above approach, by using a human kinematic model constructed specifically for individuals with motor dysfunction to calculate gait phase parameters and posture angle parameters from multiple lower limb movement data collected, not only is the efficiency of gait data acquisition improved, but the accuracy of the acquired gait data is also enhanced due to the targeted construction of the human kinematic model.

[0041] S302: From the gait temporal parameter set and posture angle parameter set included in the gait data, determine the gait temporal parameter subset and posture angle parameter subset corresponding to various gait evaluation dimensions respectively.

[0042] Optionally, the aforementioned gait evaluation dimensions may include, but are not limited to: gait symmetry evaluation, gait variability evaluation, gait coordination evaluation, and gait stability evaluation. For example, see [link to relevant documentation]. Figure 4As shown, the main controller can determine the subsets of gait time-phase parameters and the subsets of attitude angle parameters corresponding to the four gait evaluation dimensions (i.e., Eva.dim.1: gait symmetry evaluation, Eva.dim.2: gait variability evaluation, Eva.dim.3: gait coordination evaluation, and Eva.dim.4: gait stability evaluation) from the gait data Gait.data, which includes the gait time-phase parameter set Gait.phase.Set and the attitude angle parameter set Posture.angle.Set. Specifically, Eva.dim.1 corresponds to... The gait phase parameter subset Phase.Subset.1 and the attitude angle parameter subset Angle.Subset.1, Eva.dim.2 correspond to the gait phase parameter subset Phase.Subset.2 and the attitude angle parameter subset Angle.Subset.2, Eva.dim.3 corresponds to the gait phase parameter subset Phase.Subset.3 and the attitude angle parameter subset Angle.Subset.3, and Eva.dim.4 corresponds to the gait phase parameter subset Phase.Subset.4 and the attitude angle parameter subset Angle.Subset.4.

[0043] It should be noted that a certain gait evaluation dimension may only require gait temporal parameters, that is, the subset of attitude angle parameters corresponding to the gait evaluation dimension may be empty, or a certain gait evaluation dimension may only require attitude angle parameters, that is, the subset of gait temporal parameters corresponding to the gait evaluation dimension may be empty. The embodiments of this application do not limit this.

[0044] S303: Based on the subsets of gait phase parameters and posture angle parameters corresponding to various gait evaluation dimensions, gait evaluation is performed on individuals with motor dysfunction using multiple gait evaluation dimensions to obtain multiple gait evaluation values.

[0045] In this way, by using the subset of gait phase parameters and the subset of posture angle parameters corresponding to each gait evaluation dimension, it is possible to perform gait evaluation of individuals with motor dysfunction using multiple gait evaluation dimensions.

[0046] In one optional implementation, when executing step S303, the main controller can execute the reference for any one of the multiple gait evaluation dimensions, such as the first gait evaluation dimension. Figure 5 The method for determining gait evaluation values, using the main controller as an example, is implemented as follows: S501: Determine the gait evaluation indicators corresponding to the first gait evaluation dimension.

[0047] Taking the four gait evaluation dimensions of gait symmetry evaluation, gait variability evaluation, gait coordination evaluation, and gait stability evaluation as an example, when executing step S501, if the first gait evaluation dimension is gait symmetry evaluation, the main controller can determine each gait evaluation index, including the temporal symmetry index, stride length symmetry index, and lower limb asymmetry coefficient.

[0048] If the first gait evaluation dimension is gait variability evaluation, then the main controller can determine each gait evaluation index, including gait variability index, gait deviation index, and gait data sample entropy.

[0049] The gait variability index quantifies the fluctuation of gait spatiotemporal parameters by comparing the deviations of the gait phase parameters of the assessed subject (i.e., those with motor dysfunction) from the reference values ​​of healthy samples (i.e., the gait phase parameters of those with normal motor function), thus reflecting gait consistency. The gait deviation index quantifies the degree of gait abnormality by comparing the deviations of the assessed subject's posture angle parameters from the average values ​​of healthy samples (i.e., the posture angle parameters of those with normal motor function). Gait data sample entropy measures the data complexity of gait data; it is a non-linear indicator that measures the regularity and predictability of time series data. A higher value indicates a more complex sequence, i.e., more complex gait data.

[0050] If the first gait evaluation dimension is gait coordination evaluation, then the main controller can determine various gait evaluation indicators, including ankle-knee phase difference, knee-hip phase difference, and ankle-hip phase difference.

[0051] If the first gait evaluation dimension is gait stability evaluation, then the main controller can determine the various gait evaluation indicators, including the first dynamic stability and the second dynamic stability. The first dynamic stability characterizes the walking stability of the person with motor dysfunction along a first direction, and the second dynamic stability characterizes the walking stability of the person with motor dysfunction along a second direction. The first direction can be forward / backward, while the second direction can be left / right.

[0052] S502: Based on the subset of gait phase parameters, the subset of posture angle parameters, and the calculation methods corresponding to each gait evaluation index, determine the index evaluation value corresponding to each gait evaluation index.

[0053] In one optional implementation, when executing step S502, if each gait evaluation index includes a time symmetry index, a stride length symmetry index, and a lower limb asymmetry coefficient, i.e., the first gait evaluation dimension is gait symmetry evaluation, then the main controller can determine the first index evaluation value corresponding to the time symmetry index based on the single support time, single swing time, and gait cycle corresponding to individuals with motor dysfunction and individuals with normal motor function, respectively.

[0054] Specifically, the formula for calculating the evaluation value of the first indicator corresponding to the time symmetry index can be expressed as follows:

[0055] in, The first indicator evaluation value corresponding to the time symmetry index. This represents the average gait cycle of individuals with normal motor function. The gait cycle of the subject (i.e., the person with motor dysfunction). and These are the minimum and maximum values ​​of the single support time. and The minimum and maximum values ​​for the single swing time are 0.62 and 0.38, respectively, determined based on practical experience. It should be noted that if the gait of a person with motor dysfunction tends towards normalization, then... The value is 1.

[0056] The main controller can also determine the second indicator evaluation value corresponding to the stride length symmetry index based on the stride length and single swing time corresponding to individuals with motor dysfunction and those with normal motor function, respectively. Specifically, the calculation formula for the second indicator evaluation value corresponding to the stride length symmetry index can be expressed as follows:

[0057] in, This is the evaluation value of the second index corresponding to the step-size symmetry index. and These represent the stride lengths on the left and right sides of individuals with motor dysfunction. and These are the stride lengths for the left and right sides of an individual with normal motor function. For example, the stride length for the left side is 1.377m, and the stride length for the right side is 1.384m. and These represent the swing time on the left and right sides, respectively, for individuals with motor dysfunction. It should be noted that if the gait of an individual with motor dysfunction tends towards normality, then... The value is 1.

[0058] Optionally, for ease of comparison, you can... and Convert to deviation value (| -1|) and (| -1|), if the deviation value (| -1|) and (| The smaller the value of -1|, the better the gait symmetry of the person with motor dysfunction.

[0059] The main controller can also determine the third index evaluation value corresponding to the lower limb asymmetry coefficient based on the single support time of the individual with motor dysfunction. Specifically, the calculation formula for the third index evaluation value corresponding to the lower limb asymmetry coefficient can be expressed as follows:

[0060] in, This is the third indicator evaluation value corresponding to the lower limb asymmetry coefficient. and These represent the single-support time for the left and right sides of the individual with motor dysfunction, respectively. It should be noted that if the gait of the individual with motor dysfunction tends towards normal, then... It is 0.

[0061] In another optional implementation, when executing step S502, if each gait evaluation index includes gait variability index, gait deviation index and gait data sample entropy, the main controller can determine the first comprehensive substitute parameter of multiple gait phase parameters corresponding to the gait variability index, and determine the fourth index evaluation value corresponding to the gait variability index based on the first difference between the first comprehensive substitute parameter and the mean of the first substitute parameter corresponding to a person with normal motor function.

[0062] For example, the process of determining the fourth indicator evaluation value corresponding to the gait variability index includes: parameter selection, weight assignment, and distance calculation. Parameter selection includes using 12 gait phase parameters, such as stride length, gait duration, single support phase, single swing phase, single support time, and single swing time, corresponding to the left and right lower limbs respectively, as the basic parameters for calculating the gait variability index. Optionally, the main controller standardizes the data of each gait phase parameter to unify the dimensions. For example, the dimension unification of the original parameters corresponding to a certain gait phase parameter for a person with motor dysfunction can be expressed as follows:

[0063] in, For the first step phase parameter mentioned above, the corresponding step phase parameter is the first step phase ... Group original parameters, For the first Within-group average parameter For the first step phase parameter mentioned above, the corresponding step phase parameter is the first step phase ... Group standardized parameters.

[0064] Next, calculate the absolute difference between the continuous values ​​corresponding to the gait phase parameters:

[0065] in, For the first The standardized values ​​for each sampling point within the group total One sampling point, For the first A sequence of absolute differences.

[0066] Calculate the average of the absolute difference sequence and standard deviation This constitutes a substitute parameter for the gait phase parameters, that is, the substitute exponents of the 12 gait parameters are uniformly denoted as... The surrogate indicators of N healthy samples constitute a surrogate parameter matrix (12*N).

[0067] The weighting process includes: using principal component analysis to determine the principal components in the alternative parameter matrix that contribute the most to gait variability, and using the correlation coefficient between each alternative parameter and the principal component as its weight.

[0068] Distance calculation: The weighted sum of the substitution parameters, i.e., the calculation formula for the first comprehensive substitution parameter, is as follows:

[0069] in, For the first One alternative parameter, This indicates the weight of the alternative parameter.

[0070] The distance between the first comprehensive substitute parameter of individuals with motor dysfunction and the mean of the first comprehensive substitute parameter of individuals with normal motor function is calculated. Therefore, the calculation method for the first difference between the first comprehensive substitute parameter and the mean of the first substitute parameter corresponding to individuals with normal motor function can be specifically expressed as follows:

[0071]

[0072]

[0073] in, The first difference mentioned above, As the primary comprehensive replacement parameter for individuals with normal motor function, The mean of the first surrogate parameter for individuals with normal motor function.

[0074] Furthermore, the original gait variability index is generated, as follows:

[0075] Furthermore, calculation Fractions are then converted to exponents, as follows:

[0076]

[0077] in, This is the final gait variability index, i.e., the fourth indicator evaluation value corresponding to the gait variability index. Optional, A score less than 100 indicates gait abnormality, and the lower the score, the higher the degree of abnormality.

[0078] The main controller can also determine the second comprehensive alternative parameter of multiple posture angle parameters corresponding to the gait deviation index, and determine the fifth index evaluation value corresponding to the gait deviation index based on the second difference between the second comprehensive alternative parameter and the mean of the second alternative parameter corresponding to normal motor function.

[0079] Optionally, singular value decomposition (SVD) can be used to determine the fifth indicator evaluation value corresponding to the gait deviation index. The process of determining the fifth indicator evaluation value of the gait deviation index includes parameter selection, weight assignment, and distance calculation. Parameter selection involves using 18 posture angle parameters—the sagittal and coronal plane angles of the left and right lower limbs (foot, calf, and thigh respectively), and the flexion-extension angles of the ankle, knee, and hip joints—as the basic parameters for calculating the gait deviation index. For example, three data points are taken from each side of each subject, with five consecutive gait cycles taken for each segment, and the average is calculated, resulting in a total of six data points from both sides. The data period is standardized by downsampling, resulting in 100 sampling points within a complete gait cycle. The nine posture angle data from one side are arranged into a 900*1 column vector, and the data from N TD children are concatenated into a 900*6N control group matrix. Specifically, it is expressed as follows:

[0080] Next, obtain the gait feature vector: for the control group matrix The singular value decomposition is performed using the following formula:

[0081] in, These represent left singular vectors, forming a set of eigenvalues ​​orthogonal bases (f-basis). Since the first 15 vectors can explain 98% of the variability, they are retained as an orthogonal base, denoted as . .

[0082]

[0083] Original data matrix Projected to The aforementioned projection process can be specifically represented as follows:

[0084] in, This indicates that the individual's raw gait data is in The projection of the gait features is used to obtain the gait feature vector. This represents the gait data for each sample in the original control group matrix.

[0085] Distance calculation: Calculate the average feature vector for individuals with normal motor function, i.e., the mean of the second alternative parameter corresponding to individuals with normal motor function. Optionally, the specific formula for calculating the mean of the second alternative parameter is as follows:

[0086] Calculate the evaluation object The Euclidean distance between the average feature vector of healthy samples and the average feature vector of healthy samples. Therefore, the second difference between the second comprehensive alternative parameter mentioned above and the mean of the second alternative parameter corresponding to individuals with normal motor function can be specifically expressed as follows:

[0087] Furthermore, the original gait deviation index is generated, as follows:

[0088] The z-score of the evaluated object is calculated and subjected to exponential transformation, as follows:

[0089]

[0090]

[0091]

[0092] in, This is the final gait deviation index, i.e., the fifth indicator evaluation value corresponding to the gait deviation index. Optional, A value less than 100 indicates gait abnormality, and the smaller the value, the higher the degree of abnormality.

[0093] The main controller can also determine the parameter sample entropy corresponding to multiple parameter time series based on the parameter time series corresponding to at least one gait phase parameter and at least one attitude angle parameter corresponding to the gait data sample entropy, and determine the sixth index evaluation value corresponding to the gait data sample entropy based on the multiple parameter sample entropy.

[0094] To quantitatively assess the complexity of gait signals, parameter sample entropy was calculated for the time series of 15 gait parameters, including gait phase parameters (e.g., stride length, gait duration, single support phase, single swing phase, single support time, and single swing time) and posture angle parameters (e.g., sagittal and coronal angles of the foot, lower leg, and thigh, as well as flexion and extension angles of the ankle, knee, and hip joints). The calculation process is as follows: 1. Setting parameters: Time series of a certain step-state parameter Set the embedding dimension and tolerance threshold .

[0095] 2. Construct an embedding vector of length m:

[0096] 3. Matching determination: For any two vectors and Calculate Chebyshev distance:

[0097] when When two vectors are considered to be matched.

[0098] 4. Calculate the matching probability:

[0099] in, This represents the number of matching pairs. Similarly, construct a structure with length... embedding vectors and calculating matching probabilities .

[0100] 5. Calculate sample entropy:

[0101] Among them, gait phase parameters are counted for each step, and attitude angles are measured according to sampling points.

[0102] In another optional implementation, when executing step S502, if the various gait evaluation indicators include ankle-knee joint phase difference, knee-hip joint phase difference, and ankle-hip joint phase difference, the main controller can perform Hilbert transformation on the posture angle data corresponding to the ankle, knee, and hip joints respectively to obtain the transformation results corresponding to the ankle, knee, and hip joints respectively. Then, based on the transformation results corresponding to the ankle, knee, and hip joints respectively, the first continuous relative phase between the ankle and knee joints, the second continuous relative phase between the knee and hip joints, and the third continuous relative phase between the ankle and hip joints are determined for each gait phase. Finally, based on each first continuous relative phase, the seventh indicator evaluation value corresponding to the ankle-knee joint phase difference is determined; based on each second continuous relative phase, the eighth indicator evaluation value corresponding to the knee-hip joint phase difference is determined; and based on each third continuous relative phase, the ninth indicator evaluation value corresponding to the ankle-hip joint phase difference is determined. Thus, since gait coordination reflects the motor control ability of gait, measuring the continuous relative phases between ankle-knee joint pairs, knee-hip joint pairs, and ankle-hip joint pairs can effectively reflect gait coordination.

[0103] For example, the specific calculation process can be as follows: transform the amplitude of the original data of the ankle, knee, and hip joint angles to a value centered at 0; perform a Hilbert transform on the original signal to create a complex signal; calculate the phase angle of the complex signal and the difference between the phase angles of the complex signal between any two joints; and transform the range of the difference to […]. The interval between π and π represents the continuous relative phase. A continuous relative phase value of 0 indicates that the joint movements are aligned in the same direction; while a continuous relative phase value close to 180° indicates that the joint movements are aligned in opposite directions. Taking one side (e.g., left or right) of a person with motor dysfunction as an example, the positive standard deviation of the continuous relative phase curve for each joint pair in n gait cycles is calculated. The gait cycle is further refined by dividing it into the initial ground contact phase (0-2%), weight-bearing response phase (3%-10%), mid-phase of the stance phase (11%-30%), late-phase of the stance phase (31%-50%), early-swing phase (51%-60%), early-swing phase (61%-73%), mid-swing phase (74%-87%), and late-swing phase (88%-100%). The average positive standard deviation (MARP) of the continuous relative phases of the ankle-knee pair, knee-hip pair, and ankle-hip pair within each gait cycle period is calculated to obtain the MARP for each joint pair at each period. This MARP reflects the changes in gait coordination at different stages of the entire gait cycle. A higher MARP indicates poorer gait coordination.

[0104] In another optional implementation, during step S502, if the gait evaluation indicators include a first dynamic stability and a second dynamic stability, the main controller can determine the center of gravity position of the person with motor dysfunction based on the human inverted pendulum model constructed for them, as well as their current center of gravity displacement and center of gravity movement speed. Then, it determines a first boundary position based on the stride length and a second boundary position based on the stride width. Finally, it determines the tenth indicator evaluation value corresponding to the first dynamic stability based on the center of gravity position and the first boundary position, and the eleventh indicator evaluation value corresponding to the second dynamic stability based on the center of gravity position and the second boundary position. In this way, by calculating the center of gravity position and boundary positions of the person with motor dysfunction, the controller can better reflect their ability to maintain stability in the face of changes or disturbances in the external environment.

[0105] For example, the calculation formula for the tenth indicator evaluation value corresponding to the first dynamic stability or the eleventh indicator evaluation value corresponding to the second dynamic stability can be specifically expressed as follows:

[0106]

[0107]

[0108] in, denoted as the natural frequency of the inverted human pendulum model, g is the acceleration due to gravity, and h is the vertical distance from the center of the human body to the ground. To calculate the position of the human body's center of gravity, and These represent the displacement of the center of gravity and the velocity of the center of gravity at a certain moment, respectively. This refers to the first dynamic stability or the second dynamic temperature at a certain moment. This refers to the maximum value of the safety boundary in a certain direction (i.e., the first direction or the second direction) of the support surface. For example, both the first and second directions can be taken as half the step length of the gait cycle. It should be noted that, A value greater than 0 indicates stable gait, and the larger the value, the better the stability.

[0109] Based on the above methods, a comprehensive gait evaluation model was established according to the above 87 gait evaluation indicators, including: 3 indicators to measure gait symmetry (time-relative symmetry index, stride length symmetry index, and asymmetry coefficient); 34 gait variability indicators (left and right gait variability index, left and right gait deviation index, and left and right stride length, gait duration, swing phase, stance phase, swing time, stance time, plantar pitch angle, plantar roll angle, thigh pitch angle, thigh roll angle, lower leg pitch angle, lower leg roll angle, ankle sagittal angle, knee sagittal angle, and hip sagittal angle); 48 gait coordination indicators (MARP of 8 periods: first contact period between left and right ankle and knee joints, ankle and hip joints, and hip and knee joints; weight-bearing reaction period; mid-stance period; late-stance period; early stepping period; early stepping period; mid-stepping period; and late-stepping period); and 2 gait stability indicators (first dynamic stability and second dynamic temperature).

[0110] S503: Determine the gait evaluation value under the first gait evaluation dimension based on the evaluation values ​​of each indicator and the corresponding indicator weights of each gait evaluation indicator.

[0111] For example, the weights of the time symmetry index, stride length symmetry index, and asymmetry coefficient included in the gait symmetry index can all be 1 / 3.

[0112] The specific method for determining the weights of each indicator in gait variability is as follows: Step A.1: Determine the weights of the gait variability index, gait deviation index, and gait data sample entropy for each subclass, with each index weight being 1 / 3.

[0113] Step B.1: Use principal component analysis to analyze multiple gait parameters (e.g., 30 gait parameters) corresponding to the gait data sample entropy, determine their respective variance contribution rates, normalize the variance contribution rates, and use them as the weights of each gait parameter. w_Sam_j Therefore, when evaluating the sixth indicator corresponding to the entropy of the gait data samples, a weighted average is used, as follows:

[0114] in, Samj For the first j The sample entropy corresponding to each gait parameter The sixth index evaluation value corresponds to 30 gait parameters.

[0115] The specific weighting method for each indicator in gait coordination is as follows: Step A.2: Determine that the index weights corresponding to the phase differences of the ankle and knee joints, the phase differences of the knee and hip joints, and the phase differences of the ankle and hip joints on the left and right sides are all 1 / 6.

[0116] Step B.2: Use the entropy weight method to perform MARP analysis on the eight gait phases of each subclass on each side, and determine their respective weights. w_j The specific operation steps are as follows: Select n The test was conducted on 10 subjects, and a data matrix was constructed from MARP data at 8 different time points for each subclass. X ,in, X_ij Indicates the first i The first sample j The values ​​of each indicator ( i =1, 2, ..., n; j=1, 2, ..., 8). Use the following formula to... X_ij Positively adjust the indicators:

[0117] Data standardization is performed by calculating the proportion of each sample under each indicator, that is, converting the value of each indicator into the proportion of each sample under that indicator. For the first... j Each indicator is used to calculate the proportion of each sample. p_ij :

[0118] Calculate the entropy value for each indicator, for the th... j Each indicator, its entropy value e_j The calculation is as follows:

[0119] in, k = 1 / ln(m) , m This represents the number of samples. This ensures that 0 <= e_j<=1.

[0120] if p_ij =0, then it is stipulated p_ij *ln(p_ij) =0.

[0121] Calculate the difference coefficient for the first... j Each indicator, its coefficient of difference g_j for: g_j = 1 - e_j Calculate the weights, the first j Weight of each indicator w_j for:

[0122] When calculating the overall MARP score for each subclass, a weighted average is used:

[0123] in, MARPj For the first j MARP for each gait phase, This is the evaluation value of the index corresponding to this joint.

[0124] The weights of the first dynamic stability and the second dynamic stability included in the gait stability index are 0.4 and 0.6, respectively.

[0125] S304: Determine the comprehensive gait evaluation value for individuals with motor dysfunction based on multiple gait evaluation values ​​and their corresponding gait evaluation weight values.

[0126] For example, gait assessment weights can be determined based on the clinical emphasis on gait evaluation, corresponding to gait symmetry assessment, gait variability assessment, gait coordination assessment, and gait stability assessment, respectively. See, for example, [link to relevant documentation]. Figure 6 As shown, the stability weight is 0.35, the variability weight is 0.3, the symmetry weight is 0.2, and the coordination weight is 0.15.

[0127] The calculation method for the comprehensive gait evaluation value of individuals with motor dysfunction is as follows:

[0128] in, This represents the gait evaluation value corresponding to gait stability. This represents the gait evaluation value corresponding to gait variability. This represents the gait evaluation value corresponding to gait symmetry. This represents the gait evaluation value corresponding to gait coordination.

[0129] It should be noted that the gait evaluation values ​​corresponding to gait symmetry, gait variability, gait coordination, and gait stability are all standardized to the 0-1 range.

[0130] In summary, the gait evaluation method provided in this application involves acquiring gait data of a person with motor dysfunction within multiple adjacent walking cycles; then, determining subsets of gait phase parameters and subsets of posture angle parameters corresponding to various gait evaluation dimensions from the gait phase parameter set and posture angle parameter set included in the gait data; further, performing gait evaluation on the person with motor dysfunction based on the subsets of gait phase parameters and posture angle parameters corresponding to various gait evaluation dimensions to obtain multiple gait evaluation values; finally, determining the comprehensive gait evaluation value of the person with motor dysfunction based on the multiple gait evaluation values ​​and their corresponding gait evaluation weight values.

[0131] By employing the above method, gait assessment of individuals with motor dysfunction is conducted across multiple gait evaluation dimensions, comprehensively quantifying their gait data and improving the accuracy of gait evaluation.

[0132] Furthermore, based on the same technical concept, embodiments of this application provide a gait evaluation device for implementing the above-described method flow of embodiments of this application. See also... Figure 7 As shown, the gait evaluation device 700 includes: a data acquisition module 701, a parameter determination module 702, a multi-dimensional evaluation module 703, and a comprehensive evaluation module 704, wherein: The data acquisition module 701 is used to acquire gait data of a person with motor dysfunction in multiple adjacent walking cycles; wherein, the gait data includes: the gait phase parameter set and the posture angle parameter set of the person with motor dysfunction; The parameter determination module 702 is used to determine the subsets of gait time phase parameters and the subsets of attitude angle parameters corresponding to various gait evaluation dimensions from the gait time phase parameter set and attitude angle parameter set included in the gait data; The multidimensional evaluation module 703 is used to evaluate the gait of people with motor dysfunction based on the subsets of gait phase parameters and the subsets of posture angle parameters corresponding to multiple gait evaluation dimensions, and obtain multiple gait evaluation values. The comprehensive evaluation module 704 is used to determine the comprehensive gait evaluation value of a person with motor dysfunction based on multiple gait evaluation values ​​and their corresponding gait evaluation weight values.

[0133] In an optional embodiment, when acquiring gait data of a person with motor dysfunction over multiple adjacent walking cycles, the data acquisition module 701 is specifically used for: By using motion data acquisition modules fixed to multiple lower limb sites of individuals with motor dysfunction, motion data of the lower limbs of individuals with motor dysfunction is collected within multiple walking cycles, resulting in lower limb motion data corresponding to multiple lower limb sites; wherein, each lower limb motion data includes: multiple motion parameters of the corresponding lower limb site; Gait data is obtained based on lower limb movement data corresponding to multiple lower limb parts and human kinematic models constructed for individuals with motor dysfunction.

[0134] In an optional embodiment, when performing gait evaluations on individuals with motor dysfunction based on subsets of gait temporal parameters and subsets of posture angle parameters corresponding to multiple gait evaluation dimensions, resulting in multiple gait evaluation values, the multidimensional evaluation module 703 is specifically used for: For each of the various gait evaluation dimensions, perform the following operations: Determine the gait evaluation indicators corresponding to the first gait evaluation dimension; wherein, the first gait evaluation dimension can be any one of multiple gait evaluation dimensions; Based on the subset of gait phase parameters, the subset of posture angle parameters, and the calculation methods corresponding to each gait evaluation index, the evaluation values ​​of each gait evaluation index are determined. Based on the evaluation values ​​of each indicator and the corresponding weights of each gait evaluation indicator, the gait evaluation value under the first gait evaluation dimension is determined.

[0135] In an optional embodiment, when determining the various gait evaluation indicators corresponding to the first gait evaluation dimension, the multi-dimensional evaluation module 703 is specifically used for: If the first gait evaluation dimension is gait symmetry evaluation, then the various gait evaluation indicators are determined to include the temporal symmetry index, stride length symmetry index, and lower limb asymmetry coefficient. If the first gait evaluation dimension is gait variability evaluation, then the various gait evaluation indicators are determined to include gait variability index, gait deviation index, and gait data sample entropy; among which, gait data sample entropy is used to measure the data complexity of gait data; If the first gait evaluation dimension is gait coordination evaluation, then the various gait evaluation indicators are determined to include ankle-knee phase difference, knee-hip phase difference, and ankle-hip phase difference. If the first gait evaluation dimension is gait stability evaluation, then the various gait evaluation indicators are determined to include the first dynamic stability and the second dynamic stability; wherein, the first dynamic stability characterizes the walking stability of the person with motor dysfunction along the first direction, and the second dynamic stability characterizes the walking stability of the person with motor dysfunction along the second direction.

[0136] In one alternative embodiment, the various gait evaluation indices include a temporal symmetry index, a stride length symmetry index, and a lower limb asymmetry coefficient. When determining the evaluation values ​​of each gait evaluation index based on subsets of gait phase parameters, subsets of attitude angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module 703 is specifically used for: Based on the single support time, single swing time, and gait cycle of individuals with motor dysfunction and those with normal motor function, the first index evaluation value corresponding to the time symmetry index is determined. Based on the stride length and single swing time corresponding to individuals with motor dysfunction and those with normal motor function, the second index evaluation value corresponding to the stride length symmetry index is determined. Based on the single support time for individuals with motor dysfunction and those with normal motor function, the third indicator evaluation value corresponding to the lower limb asymmetry coefficient is determined.

[0137] In one optional embodiment, the various gait evaluation metrics include a gait variability index, a gait deviation index, and gait data sample entropy; When determining the evaluation values ​​of each gait evaluation index based on subsets of gait phase parameters, subsets of attitude angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module 703 is specifically used for: The first comprehensive substitute parameter for multiple gait phase parameters corresponding to the gait variability index is determined, and the fourth index evaluation value corresponding to the gait variability index is determined based on the first difference between the first comprehensive substitute parameter and the mean of the first substitute parameter corresponding to individuals with normal motor function. A second comprehensive alternative parameter is determined for multiple posture angle parameters corresponding to the gait deviation index. Based on the second difference between the second comprehensive alternative parameter and the mean of the second alternative parameter corresponding to individuals with normal motor function, the fifth index evaluation value corresponding to the gait deviation index is determined. Based on the parameter time series corresponding to at least one gait phase parameter and at least one attitude angle parameter corresponding to the gait data sample entropy, the parameter sample entropy corresponding to multiple parameter time series is determined, and the sixth index evaluation value corresponding to the gait data sample entropy is determined based on the multiple parameter sample entropy.

[0138] In one alternative embodiment, the various gait evaluation metrics include ankle-knee phase difference, knee-hip phase difference, and ankle-hip phase difference; When determining the evaluation values ​​of each gait evaluation index based on subsets of gait phase parameters, subsets of attitude angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module 703 is specifically used for: Hilbert transform was performed on the posture angle data corresponding to the ankle, knee and hip joints respectively to obtain the transformation results corresponding to the ankle, knee and hip joints respectively; Based on the transformation results corresponding to the ankle, knee and hip joints respectively, the first continuous relative phase between the ankle and knee joints, the second continuous relative phase between the knee and hip joints, and the third continuous relative phase between the ankle and hip joints are determined for each gait phase. The seventh index evaluation value corresponding to the phase difference of the ankle and knee joint is determined based on each first continuous relative phase, the eighth index evaluation value corresponding to the phase difference of the knee and hip joint is determined based on each second continuous relative phase, and the ninth index evaluation value corresponding to the phase difference of the ankle and hip joint is determined based on each third continuous relative phase.

[0139] In one alternative embodiment, the gait evaluation metrics include a first dynamic stability and a second dynamic stability; When determining the evaluation values ​​of each gait evaluation index based on subsets of gait phase parameters, subsets of attitude angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module 703 is specifically used for: Based on the inverted pendulum model of the human body constructed for people with motor dysfunction, and the displacement and speed of the center of gravity of people with motor dysfunction at the current moment, the position of the center of gravity of people with motor dysfunction is determined. The first boundary position is determined based on the stride length of the person with motor dysfunction, and the second boundary position is determined based on the stride width of the person with motor dysfunction. The tenth index evaluation value corresponding to the first dynamic stability is determined based on the center of gravity position and the first boundary position, and the eleventh index evaluation value corresponding to the second dynamic stability is determined based on the center of gravity position and the second boundary position.

[0140] Based on the description of the method and apparatus embodiments above, an exemplary embodiment of the present invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, which, when executed by the at least one processor, causes the electronic device to perform the method according to an embodiment of the present invention.

[0141] This application also provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of this application.

[0142] This application also provides a computer program product, including a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of this application.

[0143] See Figure 8 The diagram shown below illustrates the structure of an electronic device 800 that can serve as a server or client in this application, and is an example of a hardware device that can be applied to various aspects of this application. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0144] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 may also store various programs and data required for the operation of the device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0145] Multiple components in electronic device 800 are connected to I / O interface 805, including: input unit 806, output unit 807, storage unit 808, and communication unit 809. Input unit 806 can be any type of device capable of inputting information to electronic device 800. Input unit 806 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device. Output unit 807 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 808 may include, but is not limited to, disks and optical discs. Communication unit 809 allows electronic device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and / or chipsets, such as Bluetooth devices, WiFi devices, worldwide interoperability for microwave access (WiMax) devices, cellular communication devices, and / or the like.

[0146] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above. For example, in some embodiments, the gait evaluation method described above can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 808.

[0147] In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. In some embodiments, computing unit 801 may be configured to perform the gait evaluation method described above by any other suitable means (e.g., by means of firmware).

[0148] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0149] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM) or flash memory, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0150] As used in this application, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device, PLD) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0151] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0152] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0153] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0154] Furthermore, it should be understood that the above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of the invention. Therefore, any equivalent variations made in accordance with the claims of this invention are still within the scope of this application.

Claims

1. A gait evaluation method, characterized in that, include: Gait data of a person with motor dysfunction within multiple adjacent walking cycles is acquired. The gait data includes a set of gait phase parameters and a set of posture angle parameters for the person with motor dysfunction. Acquiring the gait data within multiple adjacent walking cycles involves: using motion data acquisition modules fixed to multiple lower limb sites of the person with motor dysfunction to collect motion data of the lower limbs within the multiple walking cycles, obtaining lower limb motion data corresponding to each of the multiple lower limb sites; each lower limb motion data includes multiple motion parameters for the corresponding lower limb site; the gait data is obtained based on the lower limb motion data corresponding to each of the multiple lower limb sites and a human kinematic model constructed for the person with motor dysfunction. From the gait time phase parameter set and the posture angle parameter set included in the gait data, determine the gait time phase parameter subset and posture angle parameter subset corresponding to various gait evaluation dimensions respectively; Based on the subsets of gait phase parameters and the subsets of posture angle parameters corresponding to the various gait evaluation dimensions, gait evaluations are performed on the person with motor dysfunction using multiple gait evaluation dimensions to obtain multiple gait evaluation values. Specifically, the process of performing gait evaluations on the person with motor dysfunction using the subsets of gait phase parameters and the subsets of posture angle parameters corresponding to the various gait evaluation dimensions to obtain multiple gait evaluation values ​​includes: for each of the various gait evaluation dimensions, performing the following operations: determining each gait evaluation index corresponding to the first gait evaluation dimension; determining the index evaluation value corresponding to each gait evaluation index based on the subsets of gait phase parameters, the subsets of posture angle parameters, and the calculation methods corresponding to each gait evaluation index; and determining the index evaluation value based on each index evaluation value and the index weight corresponding to each gait evaluation index. The gait evaluation value under the first gait evaluation dimension; wherein, the first gait evaluation dimension is any one of the multiple gait evaluation dimensions, if the first gait evaluation dimension is gait symmetry evaluation, then the various gait evaluation indicators are determined to include the temporal symmetry index, stride length symmetry index, and lower limb asymmetry coefficient. The determination of the indicator evaluation value corresponding to each gait evaluation indicator based on the subset of gait temporal parameters, the subset of posture angle parameters, and the calculation methods corresponding to each gait evaluation indicator includes: determining the first indicator evaluation value corresponding to the temporal symmetry index based on the single support time, single swing time, and gait cycle corresponding to the person with motor dysfunction and the person with normal motor function, respectively; and determining the second indicator evaluation value corresponding to the stride length symmetry index based on the stride length and single swing time corresponding to the person with motor dysfunction and the person with normal motor function, respectively. Based on the multiple gait evaluation values ​​and their corresponding gait evaluation weight values, the comprehensive gait evaluation value of the person with motor dysfunction is determined.

2. The method as described in claim 1, characterized in that, If the first step of the gait evaluation dimension is gait variability evaluation, then the various gait evaluation indicators are determined to include gait variability index, gait deviation index, and gait data sample entropy; the gait data sample entropy is used to measure the data complexity of the gait data. The step of determining the evaluation value of each gait evaluation index based on the subset of gait phase parameters, the subset of posture angle parameters, and the calculation method corresponding to each gait evaluation index includes: A first comprehensive alternative parameter is determined for multiple gait phase parameters corresponding to the gait variability index, and a fourth index evaluation value corresponding to the gait variability index is determined based on the first difference between the first comprehensive alternative parameter and the mean of the first alternative parameter corresponding to the person with normal motor function. A second comprehensive alternative parameter is determined for multiple posture angle parameters corresponding to the gait deviation index, and a second difference is made between the second comprehensive alternative parameter and the mean of the second alternative parameter corresponding to the person with normal motor function, and a fifth index evaluation value corresponding to the gait deviation index is determined. Based on the parameter time series corresponding to at least one gait phase parameter and at least one attitude angle parameter corresponding to the gait data sample entropy, the parameter sample entropy corresponding to multiple parameter time series is determined, and the sixth index evaluation value corresponding to the gait data sample entropy is determined based on the multiple parameter sample entropy.

3. The method as described in claim 1, characterized in that, If the first step of the gait evaluation dimension is gait coordination evaluation, then the various gait evaluation indicators are determined to include ankle-knee phase difference, knee-hip phase difference, and ankle-hip phase difference; The step of determining the evaluation value of each gait evaluation index based on the subset of gait phase parameters, the subset of posture angle parameters, and the calculation method corresponding to each gait evaluation index includes: Hilbert transform is performed on the posture angle data corresponding to the ankle joint, knee joint and hip joint respectively to obtain the transformation results corresponding to the ankle joint, the knee joint and the hip joint respectively; Based on the transformation results corresponding to the ankle joint, the knee joint, and the hip joint, the first continuous relative phase between the ankle joint and the knee joint, the second continuous relative phase between the knee joint and the hip joint, and the third continuous relative phase between the ankle joint and the hip joint are determined for each gait phase. The seventh index evaluation value corresponding to the ankle-knee joint phase difference is determined based on each first continuous relative phase, the eighth index evaluation value corresponding to the knee-hip joint phase difference is determined based on each second continuous relative phase, and the ninth index evaluation value corresponding to the ankle-hip joint phase difference is determined based on each third continuous relative phase.

4. The method as described in claim 1, characterized in that, If the first step of the gait evaluation dimension is gait stability evaluation, then the various gait evaluation indicators are determined to include a first dynamic stability and a second dynamic stability; wherein, the first dynamic stability characterizes the walking stability of the person with motor dysfunction along a first direction, and the second dynamic stability characterizes the walking stability of the person with motor dysfunction along a second direction. The step of determining the evaluation value of each gait evaluation index based on the subset of gait phase parameters, the subset of posture angle parameters, and the calculation method corresponding to each gait evaluation index includes: Based on the inverted pendulum model of the human body constructed for the person with motor dysfunction, and the displacement and speed of the center of gravity of the person with motor dysfunction at the current moment, the position of the center of gravity of the person with motor dysfunction is determined. The first boundary position is determined based on the stride length of the person with motor dysfunction, and the second boundary position is determined based on the stride width of the person with motor dysfunction. The tenth index evaluation value corresponding to the first dynamic stability is determined based on the center of gravity position and the first boundary position, and the eleventh index evaluation value corresponding to the second dynamic stability is determined based on the center of gravity position and the second boundary position.

5. A gait assessment device, characterized in that, include: A data acquisition module is used to acquire gait data of a person with motor dysfunction within multiple adjacent walking cycles. The gait data includes a set of gait phase parameters and a set of posture angle parameters for the person with motor dysfunction. Acquiring the gait data within multiple adjacent walking cycles includes: acquiring motion data of the lower limbs of the person with motor dysfunction within the multiple walking cycles using a motion data acquisition module fixed to multiple lower limb sites, obtaining lower limb motion data corresponding to each of the multiple lower limb sites; each lower limb motion data includes multiple motion parameters for the corresponding lower limb site; and the gait data is obtained based on the lower limb motion data corresponding to each of the multiple lower limb sites and a human kinematic model constructed for the person with motor dysfunction. The parameter determination module is used to determine subsets of gait time-phase parameters and subsets of posture angle parameters corresponding to multiple gait evaluation dimensions from the gait time-phase parameter set and the posture angle parameter set included in the gait data; wherein, the step of performing gait evaluation on the person with motor dysfunction based on the subsets of gait time-phase parameters and subsets of posture angle parameters corresponding to the multiple gait evaluation dimensions to obtain multiple gait evaluation values ​​includes: for each of the multiple gait evaluation dimensions, performing the following operations respectively: determining each gait evaluation index corresponding to the first gait evaluation dimension; determining the index evaluation value corresponding to each gait evaluation index based on the subsets of gait time-phase parameters, the subsets of posture angle parameters, and the calculation methods corresponding to each gait evaluation index; and determining the index evaluation value based on each index evaluation value and the index weight corresponding to each gait evaluation index. The first gait evaluation dimension is described below; wherein, the first gait evaluation dimension is any one of the multiple gait evaluation dimensions. If the first gait evaluation dimension is gait symmetry evaluation, then the various gait evaluation indicators are determined to include a temporal symmetry index, a stride length symmetry index, and a lower limb asymmetry coefficient. The determination of the indicator evaluation values ​​corresponding to each gait evaluation indicator based on the subset of gait temporal parameters, the subset of posture angle parameters, and the calculation methods corresponding to each gait evaluation indicator includes: determining the first indicator evaluation value corresponding to the temporal symmetry index based on the single support time, single swing time, and gait cycle corresponding to the person with motor dysfunction and the person with normal motor function, respectively; and determining the second indicator evaluation value corresponding to the stride length symmetry index based on the stride length and single swing time corresponding to the person with motor dysfunction and the person with normal motor function, respectively. The multidimensional evaluation module is used to evaluate the gait of the person with motor dysfunction based on the subset of gait phase parameters and the subset of posture angle parameters corresponding to the multiple gait evaluation dimensions, and obtain multiple gait evaluation values. The comprehensive evaluation module is used to determine the comprehensive gait evaluation value of the person with motor dysfunction based on the multiple gait evaluation values ​​and their respective corresponding gait evaluation weight values.

6. The apparatus of claim 5, characterized in that, If the first step of the gait evaluation dimension is gait variability evaluation, then the various gait evaluation indicators are determined to include gait variability index, gait deviation index, and gait data sample entropy; the gait data sample entropy is used to measure the data complexity of the gait data. When determining the evaluation values ​​of each gait evaluation index based on the subset of gait phase parameters, the subset of posture angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module is specifically used for: A first comprehensive alternative parameter is determined for multiple gait phase parameters corresponding to the gait variability index, and a fourth index evaluation value corresponding to the gait variability index is determined based on the first difference between the first comprehensive alternative parameter and the mean of the first alternative parameter corresponding to the person with normal motor function. A second comprehensive alternative parameter is determined for multiple posture angle parameters corresponding to the gait deviation index, and a second difference is made between the second comprehensive alternative parameter and the mean of the second alternative parameter corresponding to the person with normal motor function, and a fifth index evaluation value corresponding to the gait deviation index is determined. Based on the parameter time series corresponding to at least one gait phase parameter and at least one attitude angle parameter corresponding to the gait data sample entropy, the parameter sample entropy corresponding to multiple parameter time series is determined, and the sixth index evaluation value corresponding to the gait data sample entropy is determined based on the multiple parameter sample entropy.

7. The apparatus as claimed in claim 5, characterized in that, If the first step of the gait evaluation dimension is gait coordination evaluation, then the various gait evaluation indicators are determined to include ankle-knee phase difference, knee-hip phase difference, and ankle-hip phase difference; When determining the evaluation values ​​of each gait evaluation index based on the subset of gait phase parameters, the subset of posture angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module is specifically used for: Hilbert transform is performed on the posture angle data corresponding to the ankle joint, knee joint and hip joint respectively to obtain the transformation results corresponding to the ankle joint, the knee joint and the hip joint respectively; Based on the transformation results corresponding to the ankle joint, the knee joint, and the hip joint, the first continuous relative phase between the ankle joint and the knee joint, the second continuous relative phase between the knee joint and the hip joint, and the third continuous relative phase between the ankle joint and the hip joint are determined for each gait phase. The seventh index evaluation value corresponding to the ankle-knee joint phase difference is determined based on each first continuous relative phase, the eighth index evaluation value corresponding to the knee-hip joint phase difference is determined based on each second continuous relative phase, and the ninth index evaluation value corresponding to the ankle-hip joint phase difference is determined based on each third continuous relative phase.

8. The apparatus of claim 5, characterized in that, If the first step of the gait evaluation dimension is gait stability evaluation, then the various gait evaluation indicators are determined to include a first dynamic stability and a second dynamic stability; wherein, the first dynamic stability characterizes the walking stability of the person with motor dysfunction along a first direction, and the second dynamic stability characterizes the walking stability of the person with motor dysfunction along a second direction. When determining the evaluation values ​​of each gait evaluation index based on the subset of gait phase parameters, the subset of posture angle parameters, and the calculation methods corresponding to each gait evaluation index, the multi-dimensional evaluation module is specifically used for: Based on the inverted pendulum model of the human body constructed for the person with motor dysfunction, and the displacement and speed of the center of gravity of the person with motor dysfunction at the current moment, the position of the center of gravity of the person with motor dysfunction is determined. The first boundary position is determined based on the stride length of the person with motor dysfunction, and the second boundary position is determined based on the stride width of the person with motor dysfunction. The tenth index evaluation value corresponding to the first dynamic stability is determined based on the center of gravity position and the first boundary position, and the eleventh index evaluation value corresponding to the second dynamic stability is determined based on the center of gravity position and the second boundary position.

9. An electronic device, comprising: processor; as well as Stored program memory, The program includes instructions that, when executed by the processor, cause the processor to perform the method as described in any one of claims 1-4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method as described in any one of claims 1-4.

Images