Processing method of motion data, movement disorder assessment method and related devices thereof

Abstract

The application provides a motion data processing method, a movement disorder evaluation method and related devices. The motion data processing method includes: segmenting a motion signal sequence of a target object to obtain a plurality of signal segments corresponding to the motion signal sequence, wherein the motion signal sequence is obtained by detecting a process in which the target object moves according to a set motion; and determining a signal segment that meets a set requirement in terms of motion effectiveness from the plurality of signal segments to evaluate a movement disorder. Based on the technical solutions provided in the application, at least one signal segment that meets the set requirement in terms of periodicity, correlation with the set motion, and effective motion proportion can be extracted from the plurality of signal segments, and a movement disorder is evaluated based on the signal segment, so that the evaluation result is more reliable.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a motion data processing method, a motion disorder assessment method, and related devices. Background Art

[0002] When assessing a patient's movement disorder, the patient typically performs repetitive, prescribed movements. The motion data from a specific area during these movements is analyzed to determine if the patient has a movement disorder. However, in actual assessments, patients often fail to consistently perform the prescribed movements due to factors such as fatigue. Analyzing the motion data in these situations may not yield reliable results for the movement disorder assessment. Summary of the Invention

[0003] Based on the above needs, the present application proposes a motion data processing method, a movement disorder assessment method and related devices to solve the problem that reliable movement disorder assessment results cannot be obtained in the prior art.

[0004] The technical solutions proposed in this application are as follows:

[0005] This application provides a method for processing motion data, including:

[0006] Segmenting the target object's motion signal sequence to obtain a plurality of signal segments corresponding to the motion signal sequence; wherein the motion signal sequence is obtained by detecting the target object's motion according to a set motion;

[0007] Determine from the multiple signal segments a signal segment whose action effectiveness meets the set requirements for movement disorder assessment; wherein, the signal segment whose action effectiveness meets the set requirements is a signal segment whose periodicity, correlation with the set action, and effective action ratio meet the set requirements.

[0008] Furthermore, in the above method, the number of the target object's motion signal sequences is multiple; the method further includes:

[0009] During the process of the target object moving according to the set action, detecting the actions of multiple parts of the target object to obtain multiple groups of action signal sequences;

[0010] And / or, multiple groups of motion signal sequences are obtained by analyzing motion data generated by the target object during the process of moving according to the set motion using multiple motion signal sequence generation algorithms.

[0011] Furthermore, in the above method, segmenting the target object's motion signal sequence to obtain a plurality of signal segments corresponding to the motion signal sequence includes:

[0012] A signal of a set length in the action signal sequence is intercepted at each interval of a set step length to obtain a plurality of signal segments corresponding to the action signal sequence.

[0013] Furthermore, in the above method, the number of the target object's motion signal sequences is multiple; and determining, from the multiple signal segments, a signal segment whose motion validity meets the set requirements for movement disorder assessment includes:

[0014] Determining a signal segment with the highest amplitude from the multiple signal segments of each action signal sequence as a valid signal segment of each action signal sequence;

[0015] From the valid signal segments of multiple motion signal sequences, a signal segment whose motion validity meets the set requirements is selected for movement disorder assessment.

[0016] Furthermore, in the above method, determining the signal segment with the highest amplitude from the multiple signal segments of each action signal sequence as the valid signal segment of each action signal sequence includes:

[0017] Detecting the main frequency amplitude of each signal segment; the main frequency amplitude is the highest amplitude of each signal segment;

[0018] The effective signal segment of each action signal sequence is determined as the signal segment with the highest main frequency amplitude among the multiple signal segments of each action signal sequence.

[0019] Furthermore, in the above method, detecting the main frequency amplitude of each signal segment includes:

[0020] Detect the amplitude of each signal segment at each frequency value in a set frequency interval, and determine the highest amplitude as the main frequency amplitude of each signal segment; the set frequency interval is the frequency interval corresponding to the set action performed by the target object during the movement.

[0021] Furthermore, in the above method, selecting a signal segment whose motion validity meets the set requirements from the valid signal segments of the plurality of motion signal sequences for movement disorder assessment includes:

[0022] Calculate the action effectiveness of the effective signal segment of each action signal sequence;

[0023] The effective signal segment with the highest action effectiveness is determined as the target signal segment from the effective signal segments of multiple action signal sequences for movement disorder assessment.

[0024] Further, in the method described above, the action effectiveness of the effective signal segment of each action signal sequence is calculated, including:

[0025] The periodicity of the effective signal segment of each action signal sequence is determined by calculating the main frequency amplitude of the effective signal segment of each action signal sequence, the effective action proportion of the effective signal segment of each action signal sequence is determined by calculating the main frequency proportion of the effective signal segment of each action signal sequence, and the correlation between the effective signal segment of each action signal sequence and the set action is determined by calculating the difference between the main frequency of the action signal of each action signal sequence and the main frequency of the action signal of the set action.

[0026] The weighted sum of the periodicity, the effective action proportion, and the correlation with the set action of the effective signal segment of each action signal sequence is calculated as the action effectiveness of the effective signal segment of each action signal sequence.

[0027] The main frequency amplitude is the highest amplitude of the effective signal segment of each action signal sequence, the main frequency of the action signal is the frequency corresponding to the main frequency amplitude of the effective signal segment of each action signal sequence, and the main frequency proportion is the ratio of the main frequency amplitude to the sum of the amplitudes at each frequency value in the set frequency interval.

[0028] On the other hand, the present application provides a movement disorder evaluation method, comprising:

[0029] The movement parameters of the target object are obtained by analyzing the movement signal segment of the target object; the movement parameters of the target object include at least one of the movement amplitude, the movement speed, the movement frequency, and the action amplitude decay of the target object.

[0030] The movement disorder is evaluated based on the movement parameters of the target object.

[0031] The determination method of the movement signal segment is: the action signal sequence of the target object is segmented to obtain a plurality of signal segments corresponding to the action signal sequence, the action signal sequence is obtained by detecting the movement process of the target object according to the set action; at least one signal segment that meets the set requirements in periodicity, correlation with the set action, and effective action proportion is determined from the plurality of signal segments as the movement signal segment.

[0032] On the other hand, the present application provides a movement data processing device, comprising:

[0033] The segmentation module is configured to segment the action signal sequence of the target object to obtain a plurality of signal segments corresponding to the action signal sequence, wherein the action signal sequence is obtained by detecting a process in which the target object performs a set action.

[0034] The determination module is configured to determine a signal segment with a motion validity degree meeting a set requirement from the plurality of signal segments for motion disorder evaluation, wherein the signal segment with the motion validity degree meeting the set requirement is a signal segment with at least one of periodicity, correlation with the set action, and effective action proportion meeting the set requirement.

[0035] In another aspect, the present application provides a motion disorder evaluation device, comprising:

[0036] The analysis module is configured to analyze the motion signal segment of the target object to obtain a motion parameter of the target object, wherein the motion parameter of the target object comprises at least one of a motion amplitude, a motion speed, a motion frequency, and an action amplitude decay of the target object.

[0037] The evaluation module is configured to perform motion disorder evaluation based on the motion parameter of the target object.

[0038] The determination manner of the motion signal segment is that the action signal sequence of the target object is segmented to obtain a plurality of signal segments corresponding to the action signal sequence, and the action signal sequence is obtained by detecting a process in which the target object performs a set action; and the motion signal segment is determined as a signal segment with at least one of periodicity, correlation with the set action, and effective action proportion meeting a set requirement from the plurality of signal segments.

[0039] In another aspect, the present application provides an electronic device, comprising:

[0040] a memory and a processor;

[0041] The memory is configured to store a program.

[0042] The processor is configured to realize the motion data processing method of any one of the above aspects and / or realize the motion disorder evaluation method of any one of the above aspects by running the program in the memory.

[0043] In another aspect, the present application provides a storage medium, comprising: a computer program stored on the storage medium, wherein the computer program is executed by a processor to realize the motion data processing method of any one of the above aspects and / or realize the motion disorder evaluation method of any one of the above aspects.

[0044] The motion data processing method proposed in the present application obtains multiple signal segments corresponding to the motion signal sequence by segmenting the motion signal sequence of the target object, wherein the above-mentioned motion signal sequence is obtained by detecting the process of the target object moving according to the set motion. Then, the signal segment whose motion effectiveness meets the set requirements is determined from the multiple signal segments to perform motion disorder assessment. Based on the technical solution provided by the present application, it is possible to extract a signal segment whose periodicity, correlation with the set motion, and at least one of the effective motion ratios that meet the set requirements from the multiple signal segments, and perform motion disorder assessment based on the signal segment, so that the obtained assessment result is more reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0046] Figure 1 This is a flow chart of a method for processing motion data provided by an embodiment of the present application;

[0047] Figure 2 This is a schematic diagram of key points of the human skeleton in the palm of the human body provided in an embodiment of the present application;

[0048] Figure 3 This is a flow chart of a signal segment for determining whether an action effectiveness meets set requirements, provided by an embodiment of the present application;

[0049] Figure 4 This is another flowchart of a signal segment for determining whether the effectiveness of an action meets set requirements, provided by an embodiment of the present application;

[0050] Figure 5 This is a schematic diagram of an action signal sequence obtained by using an algorithm provided in an embodiment of the present application;

[0051] Figure 6 This is a schematic diagram of an action signal sequence obtained by using another algorithm provided in an embodiment of the present application;

[0052] Figure 7 1 is a flow chart of a movement disorder assessment method provided in an embodiment of the present application;

[0053] Figure 8 Schematic diagram of a motion data processing device provided in an embodiment of the present application;

[0054] Figure 9is a structural schematic diagram of a movement disorder assessment device provided in an embodiment of the present application;

[0055] Figure 10 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] Application Overview

[0057] Movement disorder assessment is of great medical significance and can be used for disease diagnosis, disease progression determination, efficacy assessment, and rehabilitation program development. Assessments typically involve the subject performing simple, repetitive movements, such as squats, finger tapping, or toe tapping. In clinical practice, doctors often conduct movement disorder assessments based on physical examinations, manual measurements, and subjective assessments. However, this approach is not only inefficient but also subjective, resulting in unreliable assessment results.

[0058] With the continuous development of science and technology, people can now use smart devices to detect the motion data of target objects during repetitive movements, and determine the results of movement disorder assessment by analyzing the motion data, thereby improving the reliability of the assessment results to a certain extent. For example, the image data of the target object during repetitive movements can be captured by devices such as cameras or depth sensors. The impact data can be analyzed through a deep learning model to determine the key points of the human skeleton. According to the changes in the distance between the key points of the human skeleton, or the changes between the key points of the human skeleton and the set reference object (such as the ground), a motion signal sequence is generated. The motion signal sequence is filtered, peak extracted, and the start and end of the movement are detected to obtain quantifiable kinematic parameters such as speed, amplitude, attenuation, etc. Through machine learning or deep learning methods, combined with the doctor's diagnosis results, the model is trained to achieve movement disorder assessment.

[0059] However, the above schemes often have high requirements on the target subject's movements. The target subject is required to strictly follow the scale or doctor's requirements to perform the specified movements after the movement collection begins. The target subject's failure to quickly understand the requirements, interference from others, visual deviation, limb occlusion, excessive movement fatigue, etc. often have a certain impact on the evaluation results. Re-measuring the target subject who does not understand the requirements can alleviate the evaluation deviation to a certain extent, but multiple measurements are a heavy burden for the target subject, which can easily cause fatigue and other problems. The evaluation results will also be biased. In addition, some target subjects are objectively unable to always strictly follow the regulations due to illness. Analyzing the motion data under such circumstances may not produce reliable movement disorder assessment results.

[0060] Based on this, the present application proposes a motion data processing method, a motion disorder assessment method and related devices. In the application scenario of motion disorder assessment, this technical solution can extract the signal segment with the highest motion effectiveness from all motion signal sequences generated by the target object during movement, and perform motion disorder assessment based on this signal segment. The obtained motion disorder assessment result is more reliable.

[0061] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0062] Exemplary Methods

[0063] The present application provides a method for processing motion data, which can be executed by an electronic device. The electronic device can be any device with data and instruction processing functions, such as a computer, an intelligent terminal, a server, etc. Figure 1 As shown, the method includes:

[0064] S101 : Segment a motion signal sequence of a target object to obtain a plurality of signal segments corresponding to the motion signal sequence.

[0065] The target object is the subject for movement disorder assessment. The target object is generally a living being, which can be a human or an animal, but this embodiment does not limit this. To facilitate understanding of the technical solution of this application by those skilled in the art, this embodiment is described using a human as the target object.

[0066] The above-mentioned action signal sequence is obtained by detecting the process of the target object moving according to the set action. Specifically, in the process of the target object moving according to the set action, the present embodiment detects the action data of the target object's action part, and generates an action signal sequence based on the action data of the target object's action part. The set action refers to the action part of the target object during the movement disorder assessment, and the action that the action part should perform. The action part and the action that the action part should perform can be specified by medical staff or obtained by querying the movement disorder assessment scale, and this embodiment does not limit this. For example, if the current action part is the toes, and the action that should be performed is tapping the ground, then when the target object moves according to the set action of tapping the ground with the toes, the action data of the target object's action parts such as the middle finger, the little toe or the sole of the foot can be detected, and the action signal sequence is generated based on the action data of the action parts such as the middle finger, the little toe or the sole of the foot.

[0067] Specifically, in generating the action signal sequence, image data of the action part of the target object during the process of performing the set action can be collected by using a camera or a depth sensor or the like, and the image data is taken as the action data of the action part of the target object. Then, human skeleton key point detection is performed on the action part in the image data. The human skeleton key point generally refers to a joint with a certain degree of freedom on the human body. It should be noted that, in addition to the joint part, the joint in the embodiment also includes the fingertip and the toe tip. In the actual detection process, the person skilled in the art can specify a proper number of joints from all the joints of the action part as the human skeleton key point according to the actual situation, for example, one or more can be selected, and the embodiment does not make any limitation. For example, 21 human skeleton key points can be determined from the palm part of the human body as shown in FIG. 8. Figure 2

[0068] After the human skeleton key points of the action part in the image data are determined, the action signal sequence is generated according to the position change of the human skeleton key points. Specifically, the distance change of the human skeleton key points from the set reference position during the process of performing the set action by the target object can be used to draw a time-distance curve, and the time-distance is taken as the action signal sequence. The ground can be taken as the set reference position. For example, when the set action is a stamping action, the ankle joint and / or the knee joint are taken as the human skeleton key points, and the distance change of the human skeleton key points from the ground is used to draw a time-ground distance curve, and the time-ground distance is taken as the action signal sequence. A certain part of the human body can also be set as the reference position. For example, when the set action is a fist clenching and opening action, the fingertip of the index finger is taken as the human skeleton key point, and the wrist part is set as the reference position, and the distance change of the human skeleton key point from the wrist part is used to draw a time-wrist distance curve, and the time-wrist distance is taken as the action signal sequence.

[0069] In the embodiment, the number of action signal sequences can be one group or multiple groups, which is not limited here. Generally, if only one human skeleton key point of a single part in the action part is determined, and the human skeleton key point is determined from the image data by using only one human skeleton key point detection algorithm and the action signal sequence is generated, then the number of action signal sequences is one group. If multiple human skeleton key points of multiple parts in the action part are determined, and / or multiple human skeleton key point detection algorithms in the prior art are used to determine the human skeleton key points from the image data and generate the action signal sequence for each part, then the number of action signal sequences is multiple groups.

[0070] ​After obtaining the action signal sequence of the target object, the action signal sequence can be band-pass filtered to remove non-action interference. Specifically, when a person moves according to a set action, the action frequency should be within a normal frequency range. Actions outside the normal frequency range may be too different from the set action and can become interference actions affecting the assessment results of movement disorders. Therefore, in the embodiments of the present application, such interference actions are filtered out by band-pass filtering. It should be noted that different set actions can correspond to different frequency ranges. For example, the frequencies of the actions of stamping feet and opening fists can not be the same when a person performs the actions of stamping feet and opening fists. In the embodiments of the present application, the normal frequency range of a set action is determined according to the set action performed by the target object, and the normal frequency range of the set action is determined as the effective frequency range of band-pass filtering, so as to filter out frequencies outside the normal frequency range of the set action when band-pass filtering.

[0071] When determining the normal frequency ranges corresponding to different set actions, the normal frequency ranges corresponding to different set actions can be obtained by data set statistical analysis or determined by using existing medical conclusions, which are not limited in the embodiments. Generally, the data set statistical analysis is to collect a large amount of action data of different objects performing various set actions, and to determine the normal frequency ranges corresponding to different set actions by analyzing the action data.

[0072] For example, if it is determined that the normal frequency range of the action of stamping feet is 1-4 Hz, during the movement of the target object according to the action of stamping feet, it can be determined that actions outside 1-4 Hz are non-action interference, and the non-action interference outside 1-4 Hz is filtered out by band-pass filtering. If it is determined that the normal frequency range of the action of opening fists is 0.5-6 Hz, during the movement of the target object according to the action of opening fists, it can be determined that actions outside 0.5-6 Hz are non-action interference, and the non-action interference outside 0.5-6 Hz is filtered out by band-pass filtering.

[0073] Further, if the action signal sequence is subjected to band-pass filtering processing, the action signal sequence subjected to band-pass filtering processing can be subjected to segmentation processing; if the action signal sequence is not subjected to band-pass filtering processing, the action signal sequence can be directly subjected to segmentation processing. If the action signal sequence of the target object is a group, the action signal sequence of the target object can be subjected to segmentation processing, and if the action signal sequence of the target object is multiple groups, each group of the action signal sequence of the target object can be subjected to segmentation processing.

[0074] When segmenting a set of action signal sequences, overlapping signal segmentation can be performed using a fixed-size window. The window size can be determined based on the number of times the target object performs the set action. For example, if the action is set to stomping and the target object is required to perform the stomping action 10 times, the window size can be defined as 10*fps, where fps is the sampling frequency. The step size for each segmentation can be determined based on the actual efficiency and accuracy requirements. When efficiency requirements are high and accuracy requirements are low, a larger step size can be used. When efficiency requirements are low and accuracy requirements are high, a smaller step size can be used. For example, if the highest accuracy is required and efficiency requirements are low, the step size can be set to 1. For example, if the window size is defined as 10*fps and the step size is 1, then every 1 unit of signal at 10*fps can be intercepted from the action signal sequence to obtain multiple signal segments corresponding to the action signal sequence.

[0075] S102: Determine, from a plurality of signal segments, a signal segment whose movement effectiveness meets set requirements and perform movement disorder assessment.

[0076] The action effectiveness of a signal segment refers to the degree to which the actual action of the target object corresponding to the signal segment meets the movement disorder assessment requirements. The closer the actual action of the target object is to the set action, the higher the degree to which the actual action of the target object meets the movement disorder assessment requirements. A signal segment whose action effectiveness meets the set requirements means that the actual action of the target object corresponding to the signal segment meets the movement disorder assessment requirements to a high degree and meets the set standards. In an embodiment of the present application, the degree to which the actual action of the target object corresponding to each signal segment meets the movement disorder assessment requirements is evaluated by at least one of the periodicity of each signal segment, the correlation with the set action, and the proportion of effective actions to determine whether the set standards are met.

[0077] Among them, the set action during movement disorder assessment is a repetitive action, so the stronger the periodicity of the signal segment, the more the actual action of the target object corresponding to the signal segment meets the movement disorder assessment requirements; the set action is the standard action that the target object refers to when performing movement disorder assessment, and the signal segment represents the actual action of the target object, so the stronger the correlation between the actual action corresponding to the signal segment and the set action, the closer the actual action of the target object is to the set action, and the more the actual action of the target object corresponding to the signal segment meets the movement disorder assessment requirements; effective action refers to an action that meets the movement disorder assessment requirements, and the higher the proportion of effective actions in the signal segment, the more effective actions there are in the signal segment, and the more the actual action of the target object corresponding to the signal segment meets the movement disorder assessment requirements.

[0078] In the embodiments of the present application, the value corresponding to the periodicity of each signal segment, the value corresponding to the correlation with the set action, and the value corresponding to the effective action proportion can be determined. Then, the action effectiveness of the signal segment is calculated according to at least one of the value corresponding to the periodicity of each signal segment, the value corresponding to the correlation with the set action, and the value corresponding to the effective action proportion.

[0079] For example, the sum of the value corresponding to the periodicity of each signal segment, the value corresponding to the correlation with the set action, and the value corresponding to the effective action proportion can be calculated as the action effectiveness of the signal segment. The signal segment with the highest action effectiveness is determined as the signal segment with the action effectiveness meeting the set requirement for the movement disorder assessment.

[0080] For another example, the importance of the periodicity, the correlation with the set action, and the effective action proportion can also be determined according to the actual situation, respectively. The weight of the periodicity, the correlation with the set action, and the effective action proportion is determined based on the importance. The weighted sum of the value corresponding to the periodicity of each signal segment, the value corresponding to the correlation with the set action, and the value corresponding to the effective action proportion is calculated as the action effectiveness. The signal segment with the highest action effectiveness is determined as the signal segment with the action effectiveness meeting the set requirement for the movement disorder assessment.

[0081] In determining the value of the periodicity, in an optional embodiment, the periodicity detection model can be pre-trained. Each signal segment is input into the periodicity detection model to obtain the value corresponding to the periodicity of the signal segment. During the training of the periodicity detection model, a large number of signal segments can be used as training samples, and the value corresponding to each training sample can be used as a training label. In the training process, the training sample is input into the periodicity detection model to obtain the result output by the periodicity detection model. The loss value of the periodicity detection model is determined by the result output by the periodicity detection model and the training label. The parameters of the periodicity detection model are adjusted to reduce the loss value. The above training process is repeated until the loss value of the periodicity detection model is less than a set value. It should be noted that the set value can be set according to the actual situation, which is not limited in the present embodiment.

[0082] In determining the correlation with the set action, in an optional embodiment, a standard set action can be performed by a staff. The standard action signal sequence is obtained by monitoring the process of the staff performing the standard set action. The standard action signal sequence is processed according to the processing method of the action signal sequence in the above embodiments to obtain a plurality of standard signal segments corresponding to the standard action signal sequence. In determining the correlation of a signal segment with the set action, the similarity between the signal segment and each standard signal segment can be calculated. The standard signal segment with the highest similarity is determined as the standard signal segment with the strongest correlation with the signal segment. The highest similarity is determined as the correlation of the signal segment with the set action.

[0083] When determining the effective action ratio, in an optional embodiment, the signal portion corresponding to the effective action in each signal segment can be determined according to the movement disorder assessment requirements. The ratio of the length of the signal portion corresponding to the effective action to the total length of the signal segment is determined as the effective action ratio. For example, if the action is set to tapping the ground with the toes, the action with a distance between the toes and the ground of X1-X2 can be determined as the effective action, then the signal corresponding to the action with a distance between the toes and the ground of X1-X2 can be determined as the signal corresponding to the effective action, and the ratio of the signal length corresponding to the effective action in the signal segment to the total signal length is calculated as the effective action ratio.

[0084] In the above embodiments, the action signal sequence of the target object is segmented to obtain multiple signal segments corresponding to the action signal sequence, wherein the above action signal sequence is obtained by detecting the process of the target object moving according to the set action. Then, the signal segment whose action effectiveness meets the set requirements is determined from the multiple signal segments to perform movement disorder assessment. Based on the technical solution provided in the present application, it is possible to extract from the multiple signal segments a signal segment whose periodicity, correlation with the set action, and at least one of the effective action ratios that meet the set requirements, and perform movement disorder assessment based on the signal segment, and the obtained assessment result is more reliable.

[0085] As an optional implementation, another embodiment of the present application discloses that the method of the above embodiment may specifically include the following steps:

[0086] During the process of the target object moving according to the set action, the movements of multiple parts of the target object are detected to obtain multiple groups of motion signal sequences; and / or, the motion data generated by the target object during the process of moving according to the set action are analyzed by adopting multiple motion signal sequence generation algorithms to obtain multiple groups of motion signal sequences.

[0087] In this embodiment, the number of the target object's motion signal sequences is multiple groups.

[0088] Specifically, while the target object is performing a set action, the movements of multiple parts of the target object's action parts can be detected, and multiple sets of action signal sequences can be generated based on the position changes of each part. For example, if the set action is a fist-clenching and opening action, and the action part is the target object's palm, the key points of the target object's thumb, middle finger, and little finger can be determined as human skeletal key points. The key points of the thumb, middle finger, and little finger can be determined from the image data using a human skeletal key point detection algorithm, and the action signal sequences corresponding to each part can be generated.

[0089] In addition, there are a variety of mature human skeleton key point detection algorithms in the prior art, all of which can obtain motion signal sequences by analyzing image data. Examples include Kinect-based skeleton algorithms and point cloud-based toe segmentation algorithms. Therefore, in the embodiments of the present application, if a certain action part is to be detected, a variety of human skeleton key point detection algorithms can be used to perform human skeleton key point detection on each part, generating multiple motion signal sequences corresponding to the part.

[0090] Furthermore, you can also choose to detect the movements of multiple parts of the target object, and then use multiple human skeleton key point detection algorithms to detect human skeleton key points for each part to generate multiple motion signal sequences corresponding to the part. This embodiment does not limit this.

[0091] In the above embodiments, multiple groups of motion signal sequences can be generated so that a large number of signal segments can be obtained based on the multiple groups of motion signal sequences. The signal segments for movement disorder assessment determined from these signal segments can determine signal segments with higher motion effectiveness for movement disorder assessment, thereby improving the reliability of the movement disorder assessment results.

[0092] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment segment the action signal sequence of the target object to obtain multiple signal segments corresponding to the action signal sequence, which may specifically include the following steps:

[0093] A signal of a set length in the action signal sequence is intercepted at each interval of a set step length to obtain a plurality of signal segments corresponding to the action signal sequence.

[0094] In an embodiment of the present application, a signal of a set length can be intercepted from the action signal sequence at intervals of a set step length, and the intercepted signal of the set length is determined as the signal segment corresponding to the action signal sequence. The set length and step size can be determined based on actual conditions and are not limited in this embodiment.

[0095] If the action signal sequence is a group, the group of action signal sequences can be directly segmented to obtain multiple signal segments corresponding to the group of action signal sequences; if the action signal sequence is multiple groups, each group of action signal sequences can be segmented separately to obtain signal segments corresponding to each group of action signal sequences.

[0096] In the above embodiments, by segmenting the motion signal sequence, multiple signal segments can be obtained, and the signal segments whose motion effectiveness meets the set requirements are determined from the multiple signal segments to perform movement disorder assessment. Compared with performing movement disorder assessment based on the entire motion signal sequence, this can avoid the influence of interfering motions and improve the effectiveness of the movement disorder assessment results.

[0097] As an optional implementation, another embodiment of the present application discloses that: Figure 3 As shown, the steps of the above embodiment are to determine a signal segment whose action effectiveness meets the set requirements from multiple signal segments to perform movement disorder assessment, which may specifically include the following steps:

[0098] S301 : Determine a signal segment with the highest amplitude from multiple signal segments of each action signal sequence as a valid signal segment of each action signal sequence.

[0099] In this embodiment, there are multiple groups of action signal sequences.

[0100] In this embodiment, the valid signal segment of each motion signal sequence is first determined from the multiple signal segments of each motion signal sequence, and then the signal segment whose motion validity meets the set requirements is selected from the valid signal segments of the multiple motion signal sequences to perform movement disorder assessment.

[0101] When determining the valid signal segment from the multiple signal segments of each action signal sequence, in the embodiment of the present application, all the signal segments are first subjected to discrete Fourier transform, and all the signal segments are converted from the time domain to the frequency domain to obtain the amplitude of each signal segment at different frequencies. Since the purpose of this embodiment is to evaluate the movement disorder of the target object, the action content of the set action is the action required by the medical movement disorder assessment test item, such as the action required by the movement disorder assessment test item in the UPDRS scale. These actions are all repetitions of simple actions, and the action amplitude of each repetition may be the same or different. When evaluating movement disorders, the maximum action amplitude is generally determined as the action amplitude of the target object. Therefore, in the embodiment of the present application, the signal segment with the highest amplitude in each action signal sequence is determined as the valid signal segment of the action signal sequence.

[0102] S302: Select a signal segment whose motion validity meets the set requirements from the valid signal segments of multiple motion signal sequences to perform movement disorder assessment.

[0103] After determining the valid signal segments of each motion signal sequence, in this embodiment, the motion effectiveness of the valid signal segments of each motion signal sequence can be calculated according to the description of the above embodiment, and the signal segments whose motion effectiveness meets the set requirements can be selected from the valid signal segments of multiple motion signal sequences for movement disorder assessment.

[0104] In the above embodiments, the valid signal segment of each motion signal sequence can be first determined from the multiple signal segments of each motion signal sequence, and then the signal segment whose motion validity meets the set requirements can be selected from the valid signal segments of the multiple motion signal sequences for movement disorder assessment. This not only avoids calculating the motion validity of all signal segments and improves the assessment efficiency, but also selects the signal segment with the highest amplitude in the motion signal sequence for movement disorder assessment, which can meet the requirement of determining the maximum motion amplitude as the motion amplitude of the target object when evaluating movement disorders, thereby improving the reliability of the assessment results.

[0105] As an optional implementation, another embodiment of the present application discloses that: Figure 4 As shown, the steps of the above embodiment may include determining the signal segment with the highest amplitude from the multiple signal segments of each action signal sequence as the valid signal segment of each action signal sequence, which may specifically include the following steps:

[0106] S401: Detect the main frequency amplitude of each signal segment.

[0107] The above main frequency amplitude is the highest amplitude of each signal segment.

[0108] For example, the amplitudes of each signal segment corresponding to different frequencies may be detected in the frequency domain, and the highest amplitude may be determined as the main frequency amplitude of the signal segment.

[0109] As another example, the amplitude of each signal segment at each frequency value in a set frequency interval may be detected, and the highest amplitude among them may be determined as the main frequency amplitude of each signal segment.

[0110] The above-mentioned set frequency ranges are the frequency ranges corresponding to the set actions performed by the target subject during exercise. The frequency ranges corresponding to different set actions can be determined through statistical analysis of data sets or based on existing medical findings, and this embodiment does not limit this. Generally, the frequency ranges used by people to perform various set actions are between 1 Hz and 15 Hz.

[0111] In this embodiment, the amplitude of each signal segment is detected at each frequency value within a set frequency range. For example, if the set frequency range is 1 Hz to 15 Hz, the amplitude of each signal segment at 1 Hz, 2 Hz, 3 Hz, 4 Hz, 5 Hz, 6 Hz, 7 Hz, 8 Hz, 9 Hz, 10 Hz, 11 Hz, 12 Hz, 13 Hz, 14 Hz, and 15 Hz can be calculated respectively, and the highest amplitude among them is determined as the main frequency amplitude of the signal end.

[0112] It should be noted that if the action signal sequence has been bandpass filtered in the previous step, the amplitude corresponding to the filtered frequencies will be 0. For example, if the action is set to clenching and opening a fist, the bandpass filtering will have already filtered out the movements outside the 0.5-6 Hz range. When calculating the amplitude of each signal segment from 1 Hz to 15 Hz, the movements corresponding to 7 Hz to 15 Hz have already been filtered out, so the amplitude corresponding to the signal segment from 7 Hz to 15 Hz is 0.

[0113] The above example can quickly determine the main frequency amplitude of each signal segment, so as to determine the valid signal segment from multiple signal segments of the action signal sequence.

[0114] S402 : Determine a valid signal segment of each action signal sequence using a signal segment having the highest main frequency amplitude among the multiple signal segments of each action signal sequence.

[0115] The main frequency amplitudes of the multiple signal segments in each action signal sequence are further compared, and the signal segment with the highest main frequency amplitude among the multiple signal segments in each action signal sequence is determined as the valid signal segment of each action signal sequence.

[0116] In the above embodiments, by detecting the main frequency amplitude of each signal segment, the effective signal segment of each motion signal sequence can be quickly determined, so that the signal segment used for movement disorder assessment can be determined based on the effective signal segment of each group of motion signal sequences.

[0117] As an optional implementation, another embodiment of the present application discloses that: Figure 4 As shown, the steps of the above embodiment are to select a signal segment whose motion validity meets the set requirements from the valid signal segments of multiple motion signal sequences to perform movement disorder assessment, which may specifically include the following steps:

[0118] S403: Calculate the action effectiveness of the effective signal segment of each action signal sequence.

[0119] In an embodiment of the present application, when selecting a signal segment whose motion validity meets the set requirements from valid signal segments of multiple motion signal sequences for movement disorder assessment, the motion validity of the valid signal segment of each motion signal sequence can be first calculated. In addition to calculating the motion validity of the valid signal segment of each motion signal sequence according to the description of the above embodiment, the embodiment of the present application also provides the following calculation method to calculate the motion validity of the valid signal segment of each motion signal sequence:

[0120] By calculating the main frequency amplitude of the effective signal segment of each action signal sequence, the periodicity of the effective signal segment of each action signal sequence is determined; by calculating the main frequency ratio of the effective signal segment of each action signal sequence, the effective action ratio of the effective signal segment of each action signal sequence is determined; and by calculating the difference between the main frequency of the action signal of the effective signal segment of each action signal sequence and the main frequency of the action signal of the set action, the correlation between the effective signal segment of each action signal sequence and the set action is determined; the weighted sum of the periodicity, effective action ratio and correlation with the set action of the effective signal segment of each action signal sequence is calculated as the action effectiveness of the effective signal segment of each action signal sequence.

[0121] Specifically, the main frequency amplitude is the highest amplitude of the valid signal segment of each action signal sequence. According to the description of the above embodiment, the amplitude of the valid signal segment of each action signal sequence at each frequency value in the set frequency range can be determined, and the highest amplitude is determined as the main frequency amplitude of the valid signal segment of the action signal sequence.

[0122] The above-mentioned action signal main frequency is the frequency corresponding to the main frequency amplitude of the effective signal segment of each action signal sequence. For example, if there is an action signal sequence, the amplitude of the action signal sequence at each frequency value in the set frequency range is calculated respectively. If the highest amplitude of the effective signal segment of the action signal sequence is the amplitude corresponding to the frequency X, and the amplitude is Y, then the main frequency amplitude of the effective signal segment of the action signal sequence is Y, and the action signal main frequency is X.

[0123] The above-mentioned main frequency ratio is the ratio of the main frequency amplitude to the sum of the amplitudes at each frequency value in the set frequency interval. For example, if there is an action signal sequence, the amplitude of the action signal sequence at each frequency value in the set frequency interval [X1, X2, X3, X4] is calculated respectively, where the corresponding amplitude at the frequency X1 is Y1, the corresponding amplitude at the frequency X2 is Y2, the corresponding amplitude at the frequency X3 is Y3, and the corresponding amplitude at the frequency X4 is Y4, where X3 is the main frequency of the action signal and Y3 is the main frequency amplitude. Then the main frequency ratio is Y3 / (Y1+Y2+Y3+Y4).

[0124] Specifically, the formulas for determining the main frequency amplitude, the main frequency of the action signal, and the main frequency ratio are as follows:

[0125] xf ij =fft(x ij )

[0126] xfp ij =abs(xf ij )

[0127] freqsij =np.linspace(0,sample_rate / 2,int(x ij .shape[0] / 2)+1)

[0128] freqsBin ij =[fre k ,fre k _m]

[0129] fre k =1, 2, ....15

[0130] fre k _m=sum(xfp ij [fre k _range])

[0131] fre k _range=np.where((freqs ij >=fre k -1)&(freqs ij <fre k ))[0]

[0132] freMain ij =freqsBin ij [np.arg max(freqsBin ij [:,1]),0)]

[0133] freMainMod ij =max(freqsBin ij [:,1])

[0134]

[0135] In the above formula, x ij represents the jth signal segment in the i-th action signal sequence; xf ij Indicates x ij Frequency-amplitude signal curve converted to frequency domain after discrete Fourier transform; xfp ij Represents x ij The X-axis in the frequency-amplitude signal curve represents the amplitude; freqs ij Represents x ij The Y-axis in the frequency-amplitude signal curve represents the frequency; freqsBini j Indicates the calculation of x ij The amplitude at each frequency value in the set frequency range; fre kIndicates that the frequency range is set to 1Hz, 2Hz, 3Hz, ..., 14Hz, 15Hz; fre k _m represents x ij The amplitude corresponding to different frequencies in the set frequency range; freMain ij Represents x ij The main frequency of the action signal; freMainMod ij Represents x ij The main frequency amplitude, freMainCoe ij Represents x ij The main frequency ratio.

[0136] In this embodiment, the main frequency amplitude is used to characterize the periodicity of the effective signal segment. Generally speaking, the better the periodicity of the effective signal segment, the larger the main frequency amplitude; the larger the main frequency amplitude, the greater the effectiveness of the action. Usually, the occurrence of noise is irregular and has poor periodicity. Selecting an effective signal segment with a high main frequency amplitude for movement disorder assessment can suppress the interference of noise. When the accuracy of the human skeleton key point detection algorithm is low, it can also improve the accuracy of the detection results to a certain extent.

[0137] In this embodiment, the dominant frequency percentage of a valid signal segment is used to represent the effective motion percentage of each valid signal segment. A higher dominant frequency percentage indicates fewer non-action signals, less interference, and greater motion effectiveness. The dominant frequency percentage of a valid signal segment can also characterize the periodicity and signal-to-noise ratio of the target object's actual motion, directly reflecting the waveform quality.

[0138] In this embodiment, the difference between the main frequency of the action signal of the effective signal segment and the main frequency of the action signal of the set action is used to characterize the correlation between the effective signal segment and the set action, wherein the main frequency of the action signal of the set action refers to the main frequency of the action signal when a normal person performs the set action in a relatively standard manner, which is usually obtained by statistical analysis of the action data of normal people without movement disorders. The specific calculation method can refer to the method of determining the main frequency of the action signal of the effective signal segment in the above embodiment, which is not limited in this embodiment. The smaller the difference between the main frequency of the action signal of the effective signal segment and the main frequency of the action signal of the set action, the closer the main frequency of the action signal is to the main frequency of the action signal of the set action, and the closer the action of the target object is to the set action. Using an effective signal segment with a small difference between the main frequency of the action signal and the main frequency of the action signal of the set action to perform movement disorder assessment can reduce the interference caused by non-action signals.

[0139] After obtaining the periodicity of the effective signal segment of each action signal sequence, the proportion of effective actions, and the correlation with the set action, the weighted sum of the periodicity of the effective signal segment of each action signal sequence, the proportion of effective actions, and the correlation with the set action can be calculated according to the set weights as the action effectiveness of the effective signal segment of each action signal sequence. The weights of the periodicity of the effective signal segment of each action signal sequence, the proportion of effective actions, and the correlation with the set action can be defined artificially or the optimal parameters can be obtained through sample training based on a machine learning method, which is not limited in this embodiment. In general, the weights of the periodicity of the effective signal segment of each action signal sequence, the proportion of effective actions, and the correlation with the set action should be at the same order of magnitude.

[0140] Exemplarily, the weights of the periodicity of the effective signal segment of each action signal sequence, the effective action ratio, and the correlation with the set action may all be 1.

[0141] Specifically, the calculation formula for the action effectiveness of the valid signal segment of each action signal sequence is as follows:

[0142] S i =freMainMod i *λ0-abs(freMain i -freCent)*λ1+freMainCoe i *λ2

[0143] Among them, S i is the action validity of the i-th action signal sequence, freMainMod i Indicates the main frequency amplitude of the i-th action signal sequence; freMain i Indicates the main frequency of the action signal of the i-th action signal sequence; freCent indicates the main frequency of the action signal of the set action; freMainCoe i represents the main frequency ratio of the i action signal sequence; λ0, λ1 and λ2 are weights.

[0144] S404: Determine the valid signal segment with the highest motion validity from the valid signal segments of the multiple motion signal sequences as the target signal segment to perform movement disorder assessment.

[0145] After determining the motion effectiveness of the effective signal segments of multiple motion signal sequences, the effective signal segment with the highest motion effectiveness is selected as the target signal segment for movement disorder assessment.

[0146] In the above embodiments, a signal segment that meets at least one of the set requirements in terms of periodicity, correlation with the set action, and effective action ratio can be extracted from multiple signal segments, and movement disorder assessment is performed based on the signal segment, so that the obtained assessment result is more reliable.

[0147] In a specific embodiment, the set action is the target subject performing a toe tapping action. The target subject is a normal person (without movement disorder), and the doctor assesses the movement disorder level as 0.

[0148] The toes of the target object are detected, and image data of the toes is obtained. Key points of the human skeleton are detected using the Kinect skeleton algorithm and the point cloud toe segmentation algorithm, respectively, to obtain two motion signal sequences. The Kinect skeleton algorithm is highly accurate and fast, and experiments show that it performs well for 85% of the data, making it the primary skeleton recognition algorithm. However, its performance is poor on small amounts of data. The point cloud toe segmentation algorithm has high requirements for depth map quality. When the depth map has too many invalid points, the accuracy is poor. Experiments show that it performs well for 76% of the data.

[0149] According to the above embodiment, effective action segments are extracted from two groups of action signal sequences respectively, wherein: Figure 5 is the valid action segment in the action signal sequence obtained using the Kinect skeleton algorithm. Figure 6 It is a valid action segment in the action signal sequence obtained by using the toe segmentation algorithm of point cloud.

[0150] Data statistics determined that the dominant frequency of the toe motion signal was 2.8 Hz. The motion validity of the valid motion segments in the motion signal sequence obtained using the Kinect skeleton algorithm was 1.09, while the motion validity of the valid motion segments in the motion signal sequence obtained using the point cloud toe segmentation algorithm was 19.06. Therefore, in this embodiment, the movement disorder assessment using the valid motion segments in the motion signal sequence obtained using the point cloud toe segmentation algorithm resulted in a movement disorder level of 0, which is consistent with the doctor's rating.

[0151] It should be noted that if movement disorder assessment is performed using valid motion segments in the motion signal sequence obtained using the Kinect skeleton algorithm, the resulting movement disorder grade is 3, which is inconsistent with the doctor's score. Therefore, using valid signal segments with higher motion validity for movement disorder assessment can produce more accurate assessment results.

[0152] The present application also provides a method for evaluating movement disorders, which can be performed by an electronic device. The electronic device can be any device with data and instruction processing capabilities, such as a computer, an intelligent terminal, a server, etc. Figure 7 As shown, the method includes:

[0153] S701: Analyze the motion signal segments of the target object to obtain motion parameters of the target object.

[0154] The target object's motion signal segments are determined by segmenting the target object's motion signal sequence to obtain multiple signal segments corresponding to the motion signal sequence, where the motion signal sequence is obtained by detecting the target object moving according to a predetermined motion. From the multiple signal segments, a signal segment that meets at least one of the following requirements: periodicity, correlation with the predetermined motion, and effective motion ratio is determined as a motion signal segment. The specific determination method can be referenced to the motion data processing method described in the above embodiment, and will not be elaborated on in detail in this embodiment.

[0155] The motion parameters of the target object include at least one of the target object's motion amplitude, motion speed, motion frequency, and motion amplitude attenuation. In this embodiment, the target object's motion signal segments are analyzed to obtain motion-related kinematic parameters, such as amplitude, speed, frequency, motion amplitude attenuation, and other quantitative indicators. The specific method for generating the target object's motion parameters based on the target object's motion signal segments can be referred to the prior art, and will not be elaborated here.

[0156] S702: Perform movement disorder assessment based on the movement parameters of the target object.

[0157] Specifically, based on the target subject's motion parameters and the doctor's diagnosis, a model is trained using machine learning or deep learning methods such as decision trees and support vector machines (SVMs). Finally, an indicator corresponding to the level of movement disorder is obtained. Those skilled in the art can refer to existing documentation for specific evaluation methods, which will not be detailed here.

[0158] In the above embodiments, a signal segment that meets at least one of the set requirements, including periodicity, correlation with the set action, and effective action ratio, can be extracted from multiple signal segments as the motion signal segment of the target object, and movement disorder assessment is performed based on the motion signal segment of the target object, so that the obtained assessment result is more reliable.

[0159] In addition, when evaluating movement disorders in the prior art, a method that may be used is to input the collected image data of the target object during movement into a pre-trained movement disorder evaluation model to obtain a movement disorder evaluation result. However, the movement disorder evaluation model requires a relatively large amount of data, and this data is usually patient data with different degrees of movement disorders, which is difficult to collect. The generalization ability of the model trained with a small amount of data is poor, and the model has poor interpretability, and it is impossible to obtain kinematic parameters that are also very important in medicine. Compared with such an evaluation method, the evaluation method provided by the present application does not require the collection of a large amount of data, the evaluation method is simple, and the evaluation results are highly accurate.

[0160] Exemplary devices

[0161] Corresponding to the above-mentioned method for processing motion data, the present application also discloses a motion data processing device, see Figure 8 As shown, the device includes:

[0162] The segmentation module 100 is used to segment the target object's motion signal sequence to obtain a plurality of signal segments corresponding to the motion signal sequence; wherein the motion signal sequence is obtained by detecting the target object's motion according to the set motion;

[0163] The determination module 110 is used to determine a signal segment whose action effectiveness meets the set requirements from multiple signal segments to perform movement disorder assessment; wherein the signal segment whose action effectiveness meets the set requirements is a signal segment whose periodicity, correlation with the set action, and effective action ratio meet the set requirements.

[0164] As an optional implementation, another embodiment of the present application discloses that the number of the target object's action signal sequences in the above embodiment is multiple groups;

[0165] The motion data processing device of the above embodiment further includes:

[0166] The sequence generation module is used to detect the movements of multiple parts of the target object during the process of the target object moving according to the set movement, thereby obtaining multiple sets of movement signal sequences; and / or, to analyze the movement data generated by the target object during the process of moving according to the set movement by adopting multiple movement signal sequence generation algorithms to obtain multiple sets of movement signal sequences.

[0167] As an optional implementation, another embodiment of the present application discloses that the segmentation module 100 segments the action signal sequence of the target object to obtain multiple signal segments corresponding to the action signal sequence, specifically for:

[0168] A signal of a set length in the action signal sequence is intercepted at each interval of a set step length to obtain a plurality of signal segments corresponding to the action signal sequence.

[0169] As an optional implementation, another embodiment of the present application discloses that the number of the target object's action signal sequences in the above embodiment is multiple groups;

[0170] The determination module 110 includes:

[0171] a determining unit, configured to determine a signal segment having a highest amplitude from a plurality of signal segments of each action signal sequence as a valid signal segment of each action signal sequence;

[0172] The selection unit is used to select a signal segment whose action validity meets the set requirements from the valid signal segments of multiple action signal sequences to perform movement disorder assessment.

[0173] As an optional implementation, another embodiment of the present application discloses that when the determination unit of the above embodiment determines the signal segment with the highest amplitude from multiple signal segments of each action signal sequence as the valid signal segment of each action signal sequence, it is specifically configured to:

[0174] The main frequency amplitude of each signal segment is detected; the main frequency amplitude is the highest amplitude of each signal segment; the signal segment with the highest main frequency amplitude among the multiple signal segments of each action signal sequence is determined as the effective signal segment of each action signal sequence.

[0175] As an optional implementation, another embodiment of the present application discloses that when the determination unit of the above embodiment detects the main frequency amplitude of each signal segment, it is specifically used to:

[0176] Detect the amplitude of each signal segment at each frequency value in the set frequency interval, and determine the highest amplitude as the main frequency amplitude of each signal segment; the set frequency interval is the frequency interval corresponding to the set action performed by the target object during the movement.

[0177] As an optional implementation, another embodiment of the present application discloses that when the selection unit of the above embodiment selects a signal segment whose motion validity meets the set requirements from the valid signal segments of multiple motion signal sequences for movement disorder assessment, it is specifically used to:

[0178] The motion validity of the valid signal segment of each motion signal sequence is calculated; and the valid signal segment with the highest motion validity is determined as the target signal segment for movement disorder assessment from the valid signal segments of multiple motion signal sequences.

[0179] As an optional implementation, another embodiment of the present application discloses that the selection unit of the above embodiment calculates the action effectiveness of the valid signal segment of each action signal sequence, specifically for:

[0180] Determine the periodicity of the effective signal segments of each action signal sequence by calculating the main frequency amplitude of the effective signal segments of each action signal sequence; determine the effective action ratio of the effective signal segments of each action signal sequence by calculating the main frequency ratio; and determine the correlation between the effective signal segments of each action signal sequence and the set action by calculating the difference between the main frequency of the action signal of the effective signal segments of each action signal sequence and the main frequency of the action signal of the set action;

[0181] Calculate the weighted sum of the periodicity, effective action ratio, and correlation with the set action of the effective signal segment of each action signal sequence as the action effectiveness of the effective signal segment of each action signal sequence;

[0182] Among them, the main frequency amplitude is the highest amplitude of the valid signal segment of each action signal sequence, the main frequency of the action signal is the frequency corresponding to the main frequency amplitude of the valid signal segment of each action signal sequence, and the main frequency ratio is the ratio of the main frequency amplitude to the sum of the amplitudes at each frequency value in the set frequency range.

[0183] Specifically, for the specific working contents of each unit of the above-mentioned motion data processing device, please refer to the contents of the above-mentioned motion data processing method embodiment, which will not be repeated here.

[0184] Corresponding to the above-mentioned movement disorder assessment method, the present application embodiment also discloses a movement disorder assessment device, see Figure 9 As shown, the device includes:

[0185] The analysis module 200 is configured to obtain motion parameters of the target object by analyzing the motion signal segments of the target object; the motion parameters of the target object include at least one of the motion amplitude, motion speed, motion frequency, and motion amplitude attenuation of the target object;

[0186] An evaluation module 210 for performing movement disorder evaluation based on movement parameters of the target object;

[0187] Among them, the method for determining the motion signal segment is: segmenting the action signal sequence of the target object to obtain multiple signal segments corresponding to the action signal sequence, and the action signal sequence is obtained by detecting the process of the target object moving according to the set action; from multiple signal segments, determine at least one of the periodicity, correlation with the set action, and effective action ratio that meets the set requirements as the motion signal segment.

[0188] Specifically, for the specific working contents of each unit of the above-mentioned movement disorder assessment device, please refer to the contents of the above-mentioned movement disorder assessment method embodiment, which will not be repeated here.

[0189] Exemplary electronic devices, computer program products, and storage media

[0190] Another embodiment of the present application further provides an electronic device, see Figure 10 As shown, the electronic device includes:

[0191] Memory 300 and processor 310;

[0192] The memory 300 is connected to the processor 310 and is used to store programs;

[0193] The processor 310 is configured to implement the motion data processing method and / or movement disorder assessment method disclosed in any of the above embodiments by running the program stored in the memory 300 .

[0194] Specifically, the electronic device may further include: a bus, a communication interface 320 , an input device 330 and an output device 340 .

[0195] The processor 310, the memory 300, the communication interface 320, the input device 330 and the output device 340 are interconnected via a bus.

[0196] A bus may include a pathway that transfers information between components of a computer system.

[0197] Processor 310 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, or the like, or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.

[0198] The processor 310 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0199] The memory 300 stores a program for executing the technical solution of the present application, and may also store an operating system and other key services. Specifically, the program may include program code, and the program code includes computer operating instructions. More specifically, the memory 300 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, disk storage, flash, etc.

[0200] The input device 330 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0201] Output device 340 may include devices that allow information to be output to a user, such as a display screen, printer, speakers, etc.

[0202] The communication interface 320 may include any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0203] The processor 310 executes the program stored in the memory 300 and calls other devices, which can be used to implement the various steps of the motion data processing method and / or movement disorder assessment method provided in the above embodiments of the present application.

[0204] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by the processor 310, the processor 310 executes the various steps of the motion data processing method and / or movement disorder assessment method provided in the above-mentioned embodiments.

[0205] The computer program product may be written in any combination of one or more programming languages ​​to implement the program code of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0206] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by the processor, the processor 310 executes the various steps of the motion data processing method and / or movement disorder assessment method provided in the above embodiments.

[0207] The computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0208] Specifically, the specific working contents of each part of the above-mentioned electronic device, computer program product and storage medium, as well as the specific processing contents of the computer program product or the computer program on the above-mentioned storage medium when being executed by the processor, can be found in the contents of the various embodiments of the above-mentioned motion data processing method and / or movement disorder assessment method, and will not be repeated here.

[0209] For simple description, each of the foregoing method embodiments is described as a combination of a series of actions, but those skilled in the art shall understand that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art shall understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0210] It should be noted that each of the embodiments in the specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between each embodiment can be understood by referring to each other. For device embodiments, because they are basically similar to method embodiments, they are described more simply, and the relevant parts refer to the part of the method embodiment.

[0211] The steps in the method of each embodiment of the present application can be adjusted in sequence, combined and reduced according to actual needs. The technical features recorded in each embodiment can be replaced or combined.

[0212] The modules and sub-modules in the devices and terminals in each embodiment of the present application can be combined, divided and reduced according to actual needs.

[0213] In several embodiments provided by the present application, it should be understood that the disclosed terminal, device and method can be implemented by other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or sub-modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of sub-modules or modules can be combined or integrated into another module, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interface, device or module, which can be electrical, mechanical or other forms.

[0214] The modules or sub-modules described as separate components can or can not be physically separated, and the components of the modules or sub-modules can or can not be physical modules or sub-modules, that is, they can be located in one place, or can be distributed to multiple network modules or sub-modules. According to actual needs, some or all of the modules or sub-modules can be selected to achieve the purpose of the present embodiment.

[0215] In addition, each functional module or submodule in each embodiment of the present application may be integrated into a processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into a single module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or software functional modules or submodules.

[0216] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0217] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, software units executed by a processor, or a combination of the two. The software units may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art.

[0218] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0219] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing motion data, characterized in that: include: Segmenting the target object's motion signal sequence to obtain a plurality of signal segments corresponding to the motion signal sequence; wherein the motion signal sequence is obtained by detecting the target object's motion according to a set motion; The main frequency amplitude of each signal segment is detected, and the main frequency amplitude is the highest amplitude of each signal segment. The signal segment with the highest main frequency amplitude among the multiple signal segments of each action signal sequence is determined as the valid signal segment of each action signal sequence, and the signal segment whose action effectiveness meets the set requirements is determined from the valid signal segments to perform movement disorder assessment; wherein, the signal segment whose action effectiveness meets the set requirements is a signal segment that meets at least one of the set requirements of periodicity, correlation with the set action, and effective action ratio.

2. The method according to claim 1, characterized in that The number of the target object's action signal sequences is multiple; the method further includes: During the process of the target object moving according to the set action, detecting the actions of multiple parts of the target object to obtain multiple groups of action signal sequences; And / or, multiple groups of motion signal sequences are obtained by analyzing motion data generated by the target object during the process of moving according to the set motion using multiple motion signal sequence generation algorithms.

3. The method according to claim 1, characterized in that Segmenting the target object's motion signal sequence to obtain multiple signal segments corresponding to the motion signal sequence includes: A signal of a set length in the action signal sequence is intercepted at each interval of a set step length to obtain a plurality of signal segments corresponding to the action signal sequence.

4. The method according to claim 1, wherein The target object has a plurality of motion signal sequences; and determining a signal segment whose motion validity meets set requirements from the valid signal segments to perform movement disorder assessment, including: From the valid signal segments of multiple motion signal sequences, a signal segment whose motion validity meets the set requirements is selected for movement disorder assessment.

5. The method according to claim 1, wherein Detect the main frequency amplitude of each signal segment, including: Detect the amplitude of each signal segment at each frequency value in a set frequency interval, and determine the highest amplitude as the main frequency amplitude of each signal segment; the set frequency interval is the frequency interval corresponding to the set action performed by the target object during the movement.

6. The method according to claim 4, characterized in that From the valid signal segments of multiple motion signal sequences, a signal segment whose motion validity meets the set requirements is selected for movement disorder assessment, including: Calculate the action effectiveness of the effective signal segment of each action signal sequence; The effective signal segment with the highest action effectiveness is determined as the target signal segment from the effective signal segments of multiple action signal sequences for movement disorder assessment.

7. The method according to claim 6, characterized in that Calculate the action effectiveness of the effective signal segment of each action signal sequence, including: Determining the periodicity of the effective signal segments of each action signal sequence by calculating the main frequency amplitude of the effective signal segments of each action signal sequence; determining the effective action ratio of the effective signal segments of each action signal sequence by calculating the main frequency ratio; and determining the correlation between the effective signal segments of each action signal sequence and the set action by calculating the difference between the main action signal frequency of the effective signal segments of each action signal sequence and the main action signal frequency of the set action; Calculating the weighted sum of the periodicity, effective action ratio, and correlation with the set action of the effective signal segment of each action signal sequence as the action effectiveness of the effective signal segment of each action signal sequence; Among them, the main frequency amplitude of the effective signal segment of each action signal sequence is the highest amplitude of the effective signal segment of each action signal sequence, the action signal main frequency is the frequency corresponding to the main frequency amplitude of the effective signal segment of each action signal sequence, and the main frequency ratio is the ratio of the main frequency amplitude of the effective signal segment of each action signal sequence to the sum of the amplitudes at each frequency value in the set frequency range.

8. A method for evaluating movement disorders, characterized in that: The movement disorder assessment method is performed by an electronic device, wherein the electronic device includes any device having data and instruction processing functions, and the movement disorder assessment method includes: By analyzing the motion signal segment of the target object, the motion parameter of the target object is obtained; the motion parameter of the target object includes at least one of the motion amplitude, motion speed, motion frequency, and motion amplitude attenuation of the target object; performing movement disorder assessment based on movement parameters of the target object; Among them, the method for determining the motion signal segment is: segmenting the action signal sequence of the target object to obtain multiple signal segments corresponding to the action signal sequence, and the action signal sequence is obtained by detecting the process of the target object moving according to the set action; detecting the main frequency amplitude of each signal segment, the main frequency amplitude is the highest amplitude of each signal segment, and determining the signal segment with the highest main frequency amplitude among the multiple signal segments of each action signal sequence as the valid signal segment of each action signal sequence, and determining from the valid signal segments that at least one of the periodicity, correlation with the set action and the effective action ratio meets the set requirements as the motion signal segment.

9. A motion data processing device, characterized in that: include: a segmentation module, configured to segment the target object's motion signal sequence to obtain a plurality of signal segments corresponding to the motion signal sequence; wherein the motion signal sequence is obtained by detecting the target object's motion according to a set motion; A determination module is used to detect the main frequency amplitude of each signal segment, where the main frequency amplitude is the highest amplitude of each signal segment, determine the signal segment with the highest main frequency amplitude among the multiple signal segments of each action signal sequence as the valid signal segment of each action signal sequence, and determine the signal segment whose action effectiveness meets the set requirements from the valid signal segments to perform movement disorder assessment; wherein the signal segment whose action effectiveness meets the set requirements is a signal segment whose periodicity, correlation with the set action, and effective action ratio meet the set requirements.

10. A movement disorder assessment device, characterized in that: include: an analysis module, configured to obtain motion parameters of the target object by analyzing the motion signal segments of the target object; the motion parameters of the target object include at least one of the motion amplitude, motion speed, motion frequency, and motion amplitude attenuation of the target object; an assessment module, configured to perform movement disorder assessment based on movement parameters of the target object; The motion signal segments are determined by segmenting a motion signal sequence of the target object to obtain a plurality of signal segments corresponding to the motion signal sequence, wherein the motion signal sequence is obtained by detecting the target object moving according to a set motion; The main frequency amplitude of each signal segment is detected, and the main frequency amplitude is the highest amplitude of each signal segment. The signal segment with the highest main frequency amplitude among the multiple signal segments of each action signal sequence is determined as the valid signal segment of each action signal sequence, and the signal segment with the highest amplitude is determined from the valid signal segments. The signal segment with the highest amplitude is determined from the signal segment with the highest amplitude, and at least one of the periodicity, the correlation with the set action, and the effective action ratio that meets the set requirements is determined as the motion signal segment.

11. An electronic device, characterized in that: include: memory and processor; Wherein, the memory is used to store programs; The processor is configured to implement the motion data processing method according to any one of claims 1 to 7 and / or the movement disorder assessment method according to claim 8 by running the program in the memory.

12. A storage medium, characterized in that: include: The storage medium stores a computer program, and when the computer program is executed by the processor, it implements the motion data processing method according to any one of claims 1 to 7 and / or the movement disorder assessment method according to claim 8.

Images