ADL ability training data management system based on neurological disease patients

Abstract

The invention relates to the technical field of medical informatics, in particular to an ADL ability training data management system based on neurological disease patients. The system comprises a memory and a processor, and the processor executes computer programs stored in the memory so as to realize the following steps: acquiring attitude images and scales of normal personnel and neurological disease patients in the ADL ability training process; according to the position difference, the depth difference and the time difference between the joint points in the to-be-evaluated image and the joint points in the reference image, evaluating the possibility value that the to-be-evaluated image and the reference image are in the same action, and screening a contrast image; synthesizing the possibility value that the to-be-evaluated image and all the contrast images are in the same action and the acquisition time of the to-be-evaluated image to obtain a motion completion index; and determining an effective evaluation value of training according to the difference between the change characteristics of each type of indexes of the neurological disease patient at each moment and other indexes and each type of indexes. According to the invention, an accurate comprehensive result of ADL capability training data can be obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of medical informatics, and particularly to an ADL ability training data management system based on patients with neurological diseases. Background Art

[0002] Due to factors such as decreased muscle control ability and impaired balance ability in patients with neurological diseases, they have certain motor function disorders and cannot complete daily life activities stably and smoothly. Therefore, it is usually necessary to improve the fine motor ability of patients through ADL ability training to restore or improve the daily life ability of patients. ADL ability training usually includes training such as enhancing muscle and endurance, dressing, and eating. By managing and analyzing the data of each ADL training of patients (such as the data corresponding to each functional scale), the dynamic monitoring of the ADL ability of patients is realized, which is convenient for medical staff to intervene in the rehabilitation training plan of patients in a timely manner according to the changes in ADL ability to ensure that the plan meets the actual needs of patients.

[0003] When analyzing the ADL ability of patients with neurological diseases by existing methods, the recovery of patients is usually evaluated based on the scale method (for example, the upper limb simplified FMA score scale is used to evaluate the upper limb movements of patients), enabling patients to complete specified training actions, and the current ADL ability recovery of patients is evaluated by the observation method on the degree of completion of patients' actions. However, this method cannot accurately obtain the subtle changes in limb control of patients and is difficult to comprehensively evaluate the ADL ability training data of patients with neurological diseases. Summary of the Invention

[0004] In order to solve the problem that it is difficult to comprehensively evaluate the ADL ability training data of patients with neurological diseases by existing methods, the purpose of the present invention is to provide an ADL ability training data management system based on patients with neurological diseases, and the specific technical solutions adopted are as follows: The present invention provides an ADL ability training data management system based on patients with neurological diseases, including a memory and a processor. The processor executes the computer program stored in the memory to implement the following steps: Obtain the posture images and different types of scales during the ADL ability training process of normal persons and patients with neurological diseases; Evaluate the possibility value that the image to be evaluated and the reference image are the same action according to the differences in the position distribution, depth difference, and the difference in the corresponding relative occurrence time between the joint points in the image to be evaluated and the joint points in the reference image. The image to be evaluated is the posture image of a patient with a neurological disease, and the reference image is the posture image of a normal person; use the possibility value to screen the control image of the image to be evaluated; Combining the possibility value that the image to be evaluated and all reference images are of the same action and the acquisition time of the image to be evaluated, the movement completion index of the neurological disease patient at each moment is obtained; according to the differences in the change characteristics between each type of index and other indexes of the neurological disease patient at each moment and each type of index, the coordination coefficient at each moment is determined, where the indexes include the movement completion index and the scoring values of different types of scales; According to the change situation of the coordination coefficient during the ADL ability training process of the neurological disease patient, the effective evaluation value of the training is determined.

[0005] Preferably, the evaluation of the possibility value that the image to be evaluated and the reference image are of the same action according to the differences in the position distribution, depth difference, and corresponding relative occurrence time difference between the joint points in the image to be evaluated and the joint points in the reference image includes: For any joint point: the ratio of the Euclidean distance between the any joint point and the coordinate center point of its human body area to the Euclidean distance between the two joint points with the farthest distance in the human body area is determined as the distance index of the any joint point; the direction vector pointing from the any joint point to its adjacent joint point is used as the direction vector of the any joint point; the ratio of the depth value of the any joint point to the average depth of all joint points in the image where the any joint point is located is determined as the depth index of the any joint point; According to the cosine value between the direction vector of the candidate joint point and the direction vector of each joint point in the reference image, the difference in the distance index between the candidate joint point and each joint point in the reference image, and the difference in the depth index, the matching value between the candidate joint point and each joint point in the reference image is obtained. The cosine value is positively correlated with the matching value, and both the difference in the distance index and the difference in the depth index are negatively correlated with the matching value; the joint point in the reference image with the largest matching value with the candidate joint point is determined as the matching joint point of the candidate joint point; the candidate joint point is any joint point in the image to be evaluated; According to the difference in the relative occurrence time corresponding to the image to be evaluated and the reference image where the candidate joint point is located, and the matching values of all matching joint point pairs between the image to be evaluated and the reference image where the candidate joint point is located, the possibility value that the image to be evaluated and the reference image are of the same action is obtained; where the matching joint point pair is composed of the joint point in the image to be evaluated and the joint point in the reference image that matches the joint point in the image to be evaluated.

[0006] Preferably, the evaluation of the possibility value that the image to be evaluated and the reference image are of the same action according to the difference in the relative occurrence time corresponding to the image to be evaluated and the reference image where the candidate joint point is located, and the matching values of all matching joint point pairs between the image to be evaluated and the reference image where the candidate joint point is located includes: The ratio of the duration from the initial moment to the acquisition moment of the image where the joint point is located to the total duration of completing the current ADL ability training is denoted as the duration ratio of the corresponding image. Based on the difference in the duration ratios between the to-be-evaluated image where the candidate joint point is located and the reference image, and the average value of the matching values of all matching joint point pairs formed by the joint points in the to-be-evaluated image and the reference image where the candidate joint point is located, a possibility value that the to-be-evaluated image and the reference image are of the same action is obtained. The average value of the matching values has a positive correlation with the possibility value, and the difference in the duration ratios has a negative correlation with the possibility value.

[0007] Preferably, the screening of the reference image of the to-be-evaluated image using the possibility value includes: For any normal person: The reference image corresponding to the maximum possibility value is determined as the reference image of the to-be-evaluated image.

[0008] Preferably, the obtaining of the movement completion index of the neurological disease patient at each moment by comprehensively considering the possibility value that the to-be-evaluated image and all reference images are of the same action and the acquisition moment of the to-be-evaluated image includes: For any to-be-evaluated image: Calculate the first average value of the possibility values that the any to-be-evaluated image and all its reference images are of the same action. Calculate the product of the first average value and the number of frames of the reference image of the any to-be-evaluated image of the neurological disease patient; The ratio between the product and the detection duration corresponding to the pose image in the ADL ability training process of the neurological disease patient is determined as the movement completion index of the neurological disease patient at the acquisition moment of the any to-be-evaluated image.

[0009] Preferably, the determination of the coordination coefficient at each moment based on the difference in the change characteristics between each type of index and other indexes of the neurological disease patient at each moment and each type of index includes: For any type of index: The difference between the value of the any type of index at the next moment of the moment to be analyzed of the neurological disease patient and the value of the any type of index at the moment to be analyzed is used as the change value of the any type of index at the moment to be analyzed; If the change value is negative, the moment to be analyzed is determined as the abnormal fluctuation moment of the any type of index. Denote any type of index as the first type of index, and denote any other type of index except the first type of index as the second index; Denote the number of moments when the first type of index and the second index are both in the abnormal fluctuation moment before the moment to be analyzed and the moment to be analyzed as the first quantity, and denote the number of moments when the first type of index is in the abnormal fluctuation moment before the moment to be analyzed and the moment to be analyzed as the second quantity; The ratio of the first quantity to the second quantity is determined as the abnormal consistency coefficient of the first type of index and the second index at the moment to be analyzed. According to the abnormal consistency coefficient of the first type of index and each other type of index at the moment to be analyzed, and the difference in the change values between the first type of index and the corresponding other indexes when the first type of index and each other type of index are simultaneously in the abnormal fluctuation moment at the moment to be analyzed and before it, the correlation coefficient between the first type of index and all other indexes at the moment to be analyzed is obtained; According to the correlation coefficient between each type of index and all other indexes at the moment to be analyzed, and each type of index at the moment to be analyzed, the coordination coefficient at the moment to be analyzed is obtained; The moment to be analyzed is any moment during the ADL ability training process of the neurological disease patient.

[0010] Preferably, obtaining the coordination coefficient at the moment to be analyzed according to the correlation coefficient between each type of index and all other indexes at the moment to be analyzed, and each type of index at the moment to be analyzed includes: Denote the product of each type of index and the correlation coefficient between each type of index and all other indexes at the moment to be analyzed as the first eigenvalue of each type of index at the moment to be analyzed; Determine the sum of the accumulated first eigenvalues of all indexes at the moment to be analyzed as the coordination coefficient at the moment to be analyzed.

[0011] Preferably, determining the effective evaluation value of the training according to the change situation of the coordination coefficient during the ADL ability training process of the neurological disease patient includes: Determine the coordination ability growth index as the ratio between the coordination coefficient at the moment to be analyzed and the coordination coefficient at the previous moment of the moment to be analyzed; if the coordination ability growth index is greater than 1, then regard the moment to be analyzed as the growth moment; if the coordination ability growth index is less than or equal to 1, then regard the moment to be analyzed as the decreasing moment; According to the time distribution of the growth period, and the relative magnitude relationship between the range of the growth index of the growth period and the range of the growth index of the decreasing period, obtain the recovery index; the growth period is composed of consecutive growth moments; the decreasing period is composed of consecutive decreasing moments; Combined with the relative magnitude relationship between the coordination coefficient at the initial moment of the ADL ability training and the coordination coefficient at the current moment and the recovery index, evaluate the effective evaluation value of the training.

[0012] Preferably, obtaining the recovery index according to the time distribution of the growth period, and the relative magnitude relationship between the range of the growth index of the growth period and the range of the growth index of the decreasing period includes: Calculate the first ratio between the average value of the ranges of the growth indexes of all growth periods and the average value of the ranges of the growth indexes of all decreasing periods, and the second ratio between the total duration of all growth periods and the total duration of the detection process of the neurological disease patient; Determine the recovery index according to the maximum time interval between adjacent growth periods, the first ratio, and the second ratio. Both the first ratio and the second ratio have a positive correlation with the recovery index, and the maximum time interval has a negative correlation with the recovery index.

[0013] Preferably, evaluate the effective evaluation value of the training based on the relative magnitude relationship between the coordination coefficient at the initial moment of the ADL ability training and the coordination coefficient at the current moment, and the recovery index, including: Calculate the third ratio between the coordination coefficient at the initial moment of the ADL ability training and the coordination coefficient at the current moment; Determine the product between the third ratio and the recovery index as the effective evaluation value of the training.

[0014] The present invention has at least the following beneficial effects: The present invention first evaluates the possibility value that the image to be evaluated and the reference image are of the same action according to the differences in the position distribution, depth difference, and corresponding relative occurrence time of the joint points in the posture image during the ADL ability training process of patients with neurological diseases and the joint points in the posture image of normal persons. That is, it comprehensively judges the possibility that the joint points in the posture image during the ADL ability training process of patients with neurological diseases and the posture image of normal persons belong to the same action by using the time series characteristics and the characteristics presented by the joint points in the image. It screens the control images that belong to the same action as the posture image during the ADL ability training process of patients with neurological diseases by using the possibility value, and then evaluates the movement completion situation of patients with neurological diseases, obtains the movement completion index at each moment, uses the movement completion index and the scoring values of different types of scales as different indicators, and determines the effective evaluation value of the training of patients with neurological diseases according to the difference in the change characteristics of each type of indicator and other indicators at each moment of patients with neurological diseases and the numerical distribution of each type of indicator, realizing the comprehensive evaluation of the ADL ability training data of patients with neurological diseases, improving the accuracy of the evaluation of the ADL ability training data of patients, and providing a reference for medical staff. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of a method executed by an ADL ability training data management system based on patients with neurological diseases provided by an embodiment of the present invention. Detailed implementation mode

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the ADL ability training data management system for neurological disease patients proposed based on the present invention in combination with the accompanying drawings and preferred embodiments.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] The following specifically describes the specific solution of the ADL ability training data management system for neurological disease patients provided by the present invention in combination with the accompanying drawings.

[0020] Embodiment of the ADL ability training data management system for neurological disease patients: The specific scenario targeted by this embodiment is: during the training of the ADL ability of neurological disease patients, the movement postures and scale data of patients during training are analyzed in combination with the posture change characteristics of normal people when doing corresponding actions, and the limb coordination ability of patients during training is evaluated according to the correlation between various indicators. Furthermore, the ADL training data of patients is comprehensively evaluated in combination with the fluctuation degree of the recovery of the patients' limb coordination ability, so as to provide reference for medical staff.

[0021] This embodiment proposes an ADL ability training data management system for neurological disease patients, which includes a memory and a processor. The processor executes the computer program stored in the memory to implement the steps as Figure 1 shown, and the specific steps are as follows: Step S1, obtain the posture images and different types of scales during the ADL ability training process of normal people and neurological disease patients.

[0022] First, use the Kinect sensor camera to capture the frontal posture image and depth image of the human body of a neurological disease patient during the ADL ability training process, and use the Kinect sensor camera to capture the posture images and depth images of multiple normal people during the process of doing the same action. Among them, the camera is calibrated based on the Zhang's calibration method. It should be noted that: normal people are those with good health and no neurological diseases, and the posture images collected in this embodiment are RGB images. In this embodiment, the number of normal people is 5. In specific applications, the implementer can set it according to the specific situation. The pixel points in the posture image and the depth image are in one-to-one correspondence. The depth image is collected in this embodiment to obtain the depth value of each position in the posture image.

[0023] Meanwhile, different scales of patients with neurological diseases and normal individuals during the ADL ability training are obtained. In this embodiment, the scales include the FMA scoring scale and the Barthel index scale. The FMA scoring scale is used to evaluate the limb function of the corresponding person, and the Barthel index scale is used to evaluate the daily living ability of the corresponding person. It should be noted that these scales are evaluated by medical staff, and multiple scale evaluations are performed on both patients with neurological diseases and normal individuals. The implementer sets the posture image acquisition frequency and the scale evaluation frequency according to specific circumstances.

[0024] So far, this embodiment has obtained the posture images, the depth values at each position in the posture images, and different types of scales of multiple normal individuals and patients with neurological diseases during the ADL ability training. It should be noted that this embodiment takes a patient with a neurological disease as an example for illustration, and the method provided in this embodiment can be used to process other patients with neurological diseases.

[0025] Step S2, evaluate the possibility value that the image to be evaluated and the reference image are the same action according to the differences in the position distributions, depth differences, and corresponding relative occurrence time differences between the joint points in the image to be evaluated and the joint points in the reference image. The image to be evaluated is the posture image of a patient with a neurological disease, and the reference image is the posture image of a normal individual; use the possibility value to screen the control image of the image to be evaluated.

[0026] For each collected posture image, the posture image is grayscale processed. Based on the grayscale result, the area where the human body is located is identified by semantic recognition, and the Canny operator is used to obtain the human body edge contour, that is, the outermost edge. It is recorded that all pixel points within the contour form the human body area, and the Kincet SDK is used to obtain multiple joint points within the human body area. By using the above method, multiple joint points in each posture image can be extracted. The number of joint points in different posture images is the same.

[0027] Patients with neurological diseases have a situation where due to the decline in joint and muscle coordination control ability and poor balance ability, the patient is unable to accurately and quickly complete the specified action, resulting in a large deviation of their movement trajectory from the target trajectory, an incoherent movement completion process, and a slow completion speed. Therefore, by combining the collected posture images, analyze the differences between the movement trajectories of patients with neurological diseases and the target trajectories to evaluate the compliance of the movement trajectories in patient detection. The target trajectory is the movement trajectory of a normal person without muscle movement damage.

[0028] Ideally, when different detectors perform the same action, the corresponding images have similar time sequences in the overall video of the detector. The relative positions and depth information of their different joints are relatively similar, and the limb rotation angles are also relatively similar. Therefore, based on the above analysis, the similarity between the pose images of patients with neurological diseases and those of normal people is analyzed, the possibility that two corresponding frames of images are of the same action is judged, and then the reference images belonging to the same action as each pose image of the patients with neurological diseases are screened out.

[0029] Specifically, for any joint point in any pose image: First, the ratio of the Euclidean distance between the joint point and the center point of the coordinate of its human body area to the Euclidean distance between the two joint points with the farthest distance in the human body area is determined as the distance index of the joint point; the direction vector pointing from the joint point to its adjacent joint point is used as the direction vector of the joint point; it should be noted that if the number of adjacent joint points of the joint point is greater than 1, the direction vectors pointing from the joint point to each of its adjacent joint points are obtained respectively, and the sum vector of these direction vectors is used as the direction vector of the joint point. Then, the ratio of the depth value of the joint point to the average depth of all joint points in the image where the joint point is located is determined as the depth index of the joint point; the average depth of all joint points in a pose image is the average value of the depth values of all joint points in the pose image. By using this method, the direction vector and depth index of each joint point in each collected pose image can be obtained.

[0030] For patients with neurological diseases, multiple pose images of them are collected, and multiple pose images of each normal person are also collected. All the pose images of the patients with neurological diseases are recorded as the images to be evaluated, and the pose images of normal people are recorded as the reference images, that is, there are multiple images to be evaluated and multiple reference images.

[0031] Next, this embodiment takes one image to be evaluated and one reference image as an example for illustration, and the method provided in this embodiment can be used to process other images to be evaluated and other reference images.

[0032] Specifically, any joint point in the image to be evaluated is denoted as the candidate joint point. According to the cosine value between the direction vector of the candidate joint point and the direction vector of each joint point in the reference image, the difference in the distance index between the candidate joint point and each joint point in the reference image, and the difference in the depth index, the matching value between the candidate joint point and each joint point in the reference image is obtained. The cosine value has a positive correlation with the matching value, and both the difference in the distance index and the difference in the depth index have a negative correlation with the matching value.

[0033] In this embodiment, the difference in the distance metrics of two joint points is the absolute value of the difference between the distance metrics of these two joint points, and the difference in the depth metrics of two joint points is the absolute value of the difference between the depth metrics of these two joint points.

[0034] Among them, a positive correlation means that the dependent variable increases as the independent variable increases and decreases as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by the actual application. A negative correlation means that the dependent variable decreases as the independent variable increases and increases as the independent variable decreases. It can be a subtractive relationship, a divisive relationship, etc., which is determined by the actual application.

[0035] In this embodiment, a specific calculation formula for the matching value is given. The matching value between the i-th joint point in the image to be evaluated and the -th joint point in the reference image can be expressed as: Among them, represents the matching value between the i-th joint point in the image to be evaluated and the -th joint point in the reference image, represents the difference in the distance metric of the i-th joint point in the image to be evaluated and the -th joint point in the reference image, represents the difference in the depth metric of the i-th joint point in the image to be evaluated and the -th joint point in the reference image, represents the cosine value between the direction vector of the i-th joint point in the image to be evaluated and the -th joint point in the reference image.

[0036] In this embodiment, adding 0.01 to the denominator of the calculation formula for the matching value is to prevent the denominator from being 0. In specific applications, the implementer can set it according to specific circumstances. When the difference in the distance metric between the i-th joint point and the -th joint point is smaller, the difference in the depth metric between the i-th joint point and the -th joint point is smaller, and the cosine value between the direction vector of the i-th joint point in the image to be evaluated and the -th joint point in the reference image is larger, it indicates that the similarity of the features presented by the i-th joint point and the -th joint point is higher, that is, the matching value between the i-th joint point in the image to be evaluated and the -th joint point in the reference image is higher.

[0037] Using the above method, the matching value between the candidate joint and each joint point in the reference image can be calculated. The larger the matching value, the more the corresponding two joint points should be regarded as a matching joint point pair. Therefore, the joint point in the reference image with the largest matching value with the candidate joint point is determined as the matching joint point of the candidate joint point, and the candidate joint point and its matching key point form a matching joint point pair.

[0038] Using the above method, all joint points in the image to be evaluated are processed, and multiple matching joint point pairs are obtained. Each matching joint point pair is composed of a joint point in the image to be evaluated and a joint point in the reference image.

[0039] Next, taking the candidate joint point as an example for illustration, based on the difference in the relative occurrence time corresponding to the image to be evaluated where the candidate joint point is located and the reference image, and the matching values of all matching joint point pairs in the image to be evaluated where the candidate joint point is located and the reference image, the possibility value that the image to be evaluated and the reference image are of the same action is obtained; specifically, the ratio of the duration from the initial moment to the acquisition moment of the image where the joint point is located to the total duration of completing the current ADL ability training is denoted as the duration ratio of the corresponding image. Based on the difference in the duration ratios of the image to be evaluated where the candidate joint point is located and the reference image, and the average value of the matching values of all matching joint point pairs formed by the key points in the image to be evaluated where the candidate joint point is located and the reference image, the possibility value that the image to be evaluated and the reference image are of the same action is obtained. The average value of the matching values has a positive correlation with the possibility value, and the difference in the duration ratios has a negative correlation with the possibility value. The initial moment is the first moment of the ADL ability training.

[0040] In this embodiment, the calculation formula of the possibility value is given. The possibility value that the k-th pose image of the neurological disease patient and the -th reference image are of the same action can be expressed as: Among them, represents the possibility value that the k-th pose image of the neurological disease patient and the -th reference image are of the same action, represents the average value of the matching values of all matching joint point pairs formed by the joint points in the k-th pose image of the neurological disease patient and the -th reference image, represents the duration ratio of the k-th pose image of the neurological disease patient, represents the -th reference image's duration ratio, represents the absolute value symbol.

[0041] Denote the difference between the duration ratio of the k-th pose image of a neurological disease patient and the duration ratio of the -th reference image. The smaller the difference between the two, the smaller the absolute value, and the more similar the time sequences of the two images in the overall video. In this embodiment, adding 0.01 to the denominator of the formula for calculating the possibility value is to prevent the denominator from being 0. In specific applications, implementers can set it according to specific circumstances. The average value of the matching values of all matching joint point pairs formed by the joint points in the k-th pose image of the neurological disease patient and the -th reference image is used to reflect the overall matching degree of the joint points in the k-th pose image of the neurological disease patient and the -th reference image. When the difference in the duration ratio between the k-th pose image of the neurological disease patient and the -th reference image is smaller, and the average value of the matching values of all matching joint point pairs formed by the joint points in the k-th pose image of the neurological disease patient and the -th reference image is larger, it indicates that the similarity degree between the k-th pose image of the neurological disease patient and the -th reference image is higher, and these two images are more likely to be the pictures of the same action, that is, the possibility value that the k-th pose image of the neurological disease patient and the -th reference image are of the same action is higher.

[0042] By using the above method, the possibility value that the k-th pose image of a neurological disease patient and each reference image are of the same action can be obtained. Since this embodiment has collected image data of multiple normal persons, and each normal person has multiple reference images, therefore, for any normal person: The reference image corresponding to the maximum possibility value among all the reference images of this normal person that are of the same action as the k-th pose image of the neurological disease patient is used as the control image of the k-th pose image of the neurological disease patient. It should be noted that: If there are multiple reference images among all the reference images of this normal person whose possibility values of being of the same action as the k-th pose image of the neurological disease patient are all the maximum, then according to the chronological order, the first reference image is used as the control image of the k-th pose image of the neurological disease patient.

[0043] By using the above method, calculate the possibility value that all the images to be evaluated of the neurological disease patient and each reference image are of the same action, and multiple reference images of each image to be evaluated can be screened out according to the calculated possibility value.

[0044] Step S3: Integrate the possibility value that the image to be evaluated and all reference images are of the same action and the acquisition time of the image to be evaluated to obtain the movement completion index of the neurological disease patient at each moment; according to the differences in the change characteristics of each type of index and other indexes of the neurological disease patient at each moment and each type of index, determine the coordination coefficient at each moment, where the indexes include the movement completion index and the scoring values of different types of scales.

[0045] If, when the neurological disease patient completes the specified action, the more images that match successfully with the posture images of normal persons and the higher the matching degree, it indicates that the higher the movement completion index of the current neurological disease patient's movement trajectory in this detection. Based on this feature, next, integrate the possibility value that the image to be evaluated and all reference images are of the same action and the acquisition time of the image to be evaluated to determine the movement completion index of the neurological disease patient at each moment.

[0046] For any image to be evaluated: Calculate the average value of the possibility values that the image to be evaluated and all its reference images are of the same action, and record this average value as the first average value; calculate the product of the first average value and the number of frames of the reference image of the image to be evaluated of the neurological disease patient; determine the ratio between this product and the detection duration corresponding to the posture image during the ADL ability training process of the neurological disease patient as the movement completion index of the neurological disease patient at the acquisition time of the image to be evaluated; the larger the ratio between this product and the detection duration corresponding to the posture image during the ADL ability training process of the neurological disease patient, it indicates that when the current neurological disease patient completes the specified action, the higher the similarity with normal persons, that is, the larger the movement completion index. By using this method, the movement completion index of the neurological disease patient at each moment can be obtained.

[0047] Take the movement completion index and the scoring values of different scales as different types of indexes, that is, multiple types of indexes are obtained.

[0048] Next, take a moment during the ADL ability training process of the neurological disease patient as an example for illustration, and the method provided in this embodiment can be used to process other moments.

[0049] Record any moment during the ADL ability training process of the neurological disease patient as the moment to be analyzed.

[0050] For any type of index: Take the difference between the value of this type of index of the neurological disease patient at the next moment of the moment to be analyzed and the value of this type of index at the moment to be analyzed as the change value of this type of index at the moment to be analyzed; if this change value is negative, then determine the moment to be analyzed as the abnormal fluctuation moment of this type of index.

[0051] Denote any one type of indicators as the first type of indicators, and denote any other type of indicators except the first type of indicators as the second type of indicators; Denote the number of moments when the first type of indicators and the second type of indicators are both in abnormal fluctuations at the moment to be analyzed and before it as the first quantity, and denote the number of moments when the first type of indicators are in abnormal fluctuations at the moment to be analyzed and before it as the second quantity; Determine the ratio of the first quantity to the second quantity as the abnormal consistency coefficient of the first type of indicators and the second type of indicators at the moment to be analyzed. By using the above method, the abnormal consistency coefficient of the first type of indicators and each other type of indicators at the moment to be analyzed can be obtained.

[0052] Further, based on the abnormal consistency coefficient of the first type of indicators and each other type of indicators at the moment to be analyzed, and the difference in the change values between the first type of indicators and the corresponding other indicators when the first type of indicators and each other type of indicators are both in abnormal fluctuations at the moment to be analyzed and before it, obtain the correlation coefficient of the first type of indicators and all other indicators at the moment to be analyzed.

[0053] In this embodiment, a specific calculation formula for the correlation coefficient is given. The correlation coefficient of the first type of indicators and all other indicators at the moment to be analyzed can be expressed as: Wherein, represents the correlation coefficient of the first type of indicators and all other indicators at the moment to be analyzed, represents the average value of the abnormal consistency coefficients of the first type of indicators and all other types of indicators at the moment to be analyzed, represents the number of types of indicators, represents the number of moments when the first type of indicators and the x-th type of indicators except the first type of indicators are both in abnormal fluctuations at the moment to be analyzed and before it, represents the first type of indicators at the T-th abnormal fluctuation moment when the first type of indicators and the x-th type of indicators except the first type of indicators are both in abnormal fluctuations at the moment to be analyzed and before it, represents the x-th type of indicators at the T-th abnormal fluctuation moment when the first type of indicators and the x-th type of indicators except the first type of indicators are both in abnormal fluctuations at the moment to be analyzed and before it, represents the absolute value symbol, represents a normalization function, used to make the value of be within the range of (0, 1).

[0054] is used to reflect the cumulative sum of the differences in the abnormal degrees when the first type of indicators and the remaining indicators are both in abnormal fluctuations. The smaller its value, the larger the average value of the abnormal consistency coefficients of the first type of indicators and all other types of indicators at the moment to be analyzed, indicating that the correlation between the first type of indicators and all other indicators at the moment to be analyzed is stronger, and at this time the correlation coefficient is larger.

[0055] By using the above method, the correlation coefficients between each type of index at the moment to be analyzed and all other indexes can be obtained.

[0056] The product between each type of index at the moment to be analyzed and the correlation coefficients between each type of index and all other indexes is denoted as the first eigenvalue of each type of index at the moment to be analyzed; there is a first eigenvalue for each type of index at the moment to be analyzed; the sum of the first eigenvalues of all indexes at the moment to be analyzed is determined as the coordination coefficient at the moment to be analyzed.

[0057] By using the above method, the coordination coefficient at each moment during the ADL ability training process of neurological disease patients can be obtained.

[0058] Step S4: Determine the effective evaluation value of the training according to the change situation of the coordination coefficient during the ADL ability training process of neurological disease patients.

[0059] During the recovery process of the ADL ability of neurological disease patients, there is a situation where the recovery of the patient's daily living ability is unstable due to factors such as disease progression or symptom recurrence. For example, after a stroke, the recovery of the patient's cognitive function may have certain fluctuations, which may also lead to certain fluctuations in the recovery of the patient's daily living ability. Therefore, the effective evaluation value of the training is evaluated based on the change situation of the coordination coefficient during the ADL ability training process of neurological disease patients.

[0060] If, as of the current moment, during the ADL ability training process of the patient, the better the recovery of the limb coordination ability, that is, the more times the limb coordination coefficient increases and the greater the increase amplitude, then as of the current moment, the recovery situation of the patient's daily living ability is more stable and the recovery degree is better.

[0061] In this embodiment, the moment to be analyzed is still taken as an example for illustration. The ratio between the coordination coefficient at the moment to be analyzed and the coordination coefficient at the previous moment of the moment to be analyzed is determined as the coordination ability growth index at the moment to be analyzed; if the coordination ability growth index is greater than 1, then the moment to be analyzed is taken as a growth moment; if the coordination ability growth index is less than or equal to 1, then the moment to be analyzed is taken as a decreasing moment. By using this method, all other moments except the first moment during the ADL ability training process of neurological disease patients are judged, and these moments are divided into two categories, namely growth moments and decreasing moments. Consecutive growth moments form a growth period, and consecutive decreasing moments form a decreasing period.

[0062] If the proportion of the growth period in the total training duration up to the current moment is larger, and the change amplitude of the limb coordination ability is larger compared to the decreasing period, and the time interval between the rising periods is shorter, then the recovery situation of the daily living ability in the current state is more stable.

[0063] Based on this feature, according to the time distribution of the growth periods, the relative magnitude relationship between the range of the growth indices of the growth periods and the range of the growth indices of the decline periods, the recovery index is obtained. Specifically, calculate the first ratio between the average value of the ranges of the growth indices of all growth periods and the average value of the ranges of the growth indices of all decline periods, and the second ratio between the total duration of all growth periods and the total duration of the detection process of the neurological disease patients; determine the recovery index according to the maximum time interval between adjacent growth periods, the first ratio, and the second ratio. Both the first ratio and the second ratio are positively correlated with the recovery index, and the maximum time interval is negatively correlated with the recovery index.

[0064] In this embodiment, a specific calculation formula for the recovery index is given, and the recovery index can be expressed as: Wherein, represents the recovery index, represents the total duration of all growth periods in the detection process of the neurological disease patients, represents the total duration of the detection process of the neurological disease patients, represents the maximum time interval between all adjacent growth periods in the detection process of the neurological disease patients, represents the average value of the ranges of the growth indices of all growth periods in the detection process of the neurological disease patients, represents the average value of the ranges of the growth indices of all decline periods in the detection process of the neurological disease patients.

[0065] represents the first ratio. The larger this ratio is, the greater the change amplitude of the limb coordination ability in the growth periods compared to the decline periods; represents the second ratio, and this ratio represents the proportion of the growth periods in the total duration of the detection process of the neurological disease patients. When the first ratio is larger, the second ratio is larger, and the maximum time interval between all adjacent growth periods in the detection process of the neurological disease patients is smaller, the recovery index is larger.

[0066] After determining the recovery index, in combination with the relative magnitude relationship between the coordination coefficient at the initial moment of the ADL ability training and the coordination coefficient at the current moment and the recovery index, evaluate the effective evaluation value of the training.

[0067] Specifically, calculate the ratio between the coordination coefficient at the initial moment of the ADL ability training and the coordination coefficient at the current moment, and denote this ratio as the third ratio. The larger the third ratio is, the better the coordination degree of the patient's limbs in the current state compared to the initial training; determine the product of the third ratio and the recovery index as the effective evaluation value of the training. When the third ratio is larger and the recovery index is also larger, the effective evaluation value of the training is larger.

[0068] The effective evaluation value of the training can provide a reference basis for medical staff. Subsequently, medical staff can judge whether it is necessary to adjust the training method according to the effective evaluation value of the training and experience.

[0069] In this embodiment, first, based on the differences in the position distribution, depth differences, and corresponding relative occurrence times of the joint points in the pose images during the ADL ability training process of neurological disease patients and those in the pose images of normal persons, the possibility value that the image to be evaluated and the reference image are of the same action is evaluated. That is, the possibility that the joint points in the pose images during the ADL ability training process of neurological disease patients and the pose images of normal persons belong to the images of the same action is judged by integrating the temporal sequence features and the features presented by the joint points in the images. The control images that belong to the same action as the pose images during the ADL ability training process of neurological disease patients are screened using the possibility value. Furthermore, the movement completion situation of neurological disease patients is evaluated, and the movement completion index at each moment is obtained. The movement completion index and the scoring values of different types of scales are used as different indicators. According to the differences in the change characteristics of each type of indicator of neurological disease patients at each moment compared with other indicators and the numerical distribution of each type of indicator, the effective evaluation value of the training of neurological disease patients is determined, realizing the comprehensive evaluation of the ADL ability training data of neurological disease patients, improving the accuracy of the evaluation of the ADL ability training data of patients, and providing a reference for medical staff.

[0070] In other embodiments, a management device for ADL ability training data of neurological disease patients is also provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the method performed by the above-mentioned management system for ADL ability training data of neurological disease patients. The device can specifically be a chip, component, or module. The chip may include a processor and a memory connected thereto; wherein, the memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the method performed by the management system for ADL ability training data of neurological disease patients provided in the above embodiment.

[0071] In other embodiments, a computer program product is also provided. When the computer program product runs on a computer, the computer is enabled to execute the above-related steps to implement the management method for ADL ability training data of neurological disease patients provided in the above embodiment.

[0072] In other embodiments, a computer-readable storage medium is further provided. The computer-readable storage medium stores computer program code. When the computer program code runs on a computer, the computer is caused to execute the above-related method steps to implement the method performed by the ADL ability training data management system for neurological disease patients provided in the above embodiments.

[0073] Among them, the provided device, computer program product, and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved by them can refer to the beneficial effects in the corresponding methods provided above, and will not be elaborated here.

[0074] It should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data management system for ADL ability training of patients with neurological diseases, comprising a memory and a processor, characterized in that: The processor executes the computer program stored in the memory to implement the following steps: Obtain posture images and different types of scales during ADL ability training of normal people and patients with neurological diseases; According to the difference between the position distribution of the joint points in the image to be evaluated and the joint points in the reference image, the difference in depth and the difference in the corresponding relative occurrence time, the possibility value that the image to be evaluated and the reference image are the same action is evaluated, wherein the image to be evaluated is a posture image of a patient with a neurological disease, and the reference image is a posture image of a normal person; Using the likelihood value to screen a reference image of the image to be evaluated; The possibility value of the image to be evaluated and all the control images being the same action and the acquisition time of the image to be evaluated are combined to obtain the movement completion index of the neurological disease patient at each moment; according to the difference in the change characteristics of each type of index and other indicators of the neurological disease patient at each moment and each type of index, the coordination coefficient at each moment is determined, wherein the indicators include the movement completion index and the score values ​​of different types of scales; According to the changes of coordination coefficient during ADL ability training of patients with neurological diseases, the effective evaluation value of the training was determined.

2. The ADL ability training data management system based on neurological disease patients according to claim 1 is characterized in that: The method of evaluating the possibility value of the image to be evaluated and the reference image being the same action according to the difference between the position distribution of the joint points in the image to be evaluated and the joint points in the reference image, the depth difference and the corresponding relative occurrence time difference comprises: For any joint point: the ratio of the Euclidean distance between any joint point and the coordinate center point of the human body region where the joint point is located to the Euclidean distance between the two joint points with the farthest distance in the human body region is determined as the distance index of the any joint point; the direction vector from the any joint point to its adjacent joint point is used as the direction vector of the any joint point; the ratio between the depth value of the any joint point and the depth mean of all relevant nodes in the image where the any joint point is located is determined as the depth index of the any joint point; According to the cosine value between the direction vector of the candidate joint point and the direction vector of each joint point in the reference image, the difference in the distance index between the candidate joint point and each joint point in the reference image, and the difference in the depth index, the matching value of the candidate joint point and each joint point in the reference image is obtained, wherein the cosine value is positively correlated with the matching value, and the difference in the distance index and the difference in the depth index are both negatively correlated with the matching value; the joint point in the reference image with the largest matching value with the candidate joint point is determined as the matching joint point of the candidate joint point; the candidate joint point is any joint point in the image to be evaluated; According to the difference in relative occurrence time between the image to be evaluated and the reference image where the candidate joint point is located, and the matching value of all matching joint point pairs in the image to be evaluated and the reference image where the candidate joint point is located, the possibility value that the image to be evaluated and the reference image are the same action is obtained; wherein the matching joint point pairs are composed of joint points in the image to be evaluated and joint points in the reference image that match the joint points in the image to be evaluated.

3. The ADL ability training data management system based on neurological disease patients according to claim 2 is characterized in that: The method of obtaining the possibility value of the image to be evaluated and the reference image being the same action according to the difference in relative occurrence time between the image to be evaluated where the candidate joint point is located and the reference image, and the matching value of all matching joint point pairs in the image to be evaluated where the candidate joint point is located and the reference image, comprises: The ratio of the time from the initial moment to the acquisition moment of the image where the joint point is located to the total time to complete the current ADL ability training is recorded as the duration ratio of the corresponding image; According to the difference in the duration ratio between the image to be evaluated and the reference image where the candidate joint point is located, and the average of the matching values ​​of all matching joint point pairs formed by the joint points in the image to be evaluated and the reference image where the candidate joint point is located, the possibility value that the image to be evaluated and the reference image are the same action is obtained, the average of the matching values ​​is positively correlated with the possibility value, and the difference in the duration ratio is negatively correlated with the possibility value.

4. The ADL ability training data management system based on neurological disease patients according to claim 1, characterized in that: The method of screening the reference image of the image to be evaluated by using the possibility value includes: For any normal person: the reference image corresponding to the maximum likelihood value is determined as the control image of the image to be evaluated.

5. The ADL ability training data management system based on neurological disease patients according to claim 4 is characterized in that: The possibility value of the image to be evaluated and all the control images being the same action and the acquisition time of the image to be evaluated are combined to obtain the movement completion index of the neurological disease patient at each moment, including: For any image to be evaluated: Calculate a first average value of the likelihood values ​​of any image to be evaluated and all its reference images being the same action; Calculate the product of the first average value and the number of frames of the control image of any image to be evaluated of the neurological disease patient; determine the ratio between the product and the detection time corresponding to the posture image of the ADL ability training process of the neurological disease patient as the movement completion index of the neurological disease patient at the time of acquisition of any image to be evaluated.

6. The ADL ability training data management system for neurological disease patients according to claim 1, characterized in that: Determining the coordination coefficient at each moment according to the difference in the change characteristics of each type of indicator and other indicators of the neurological disease patient at each moment and each type of indicator includes: For any type of indicator: the difference between the indicator of the patient with a neurological disease at the next moment after the moment to be analyzed and the indicator of the patient at the moment to be analyzed is taken as the change value of the indicator of the patient at the moment to be analyzed; if the change value is a negative number, the moment to be analyzed is determined as the abnormal fluctuation moment of the indicator of the patient; Any one type of index is marked as a first type of index, and any other type of index except the first type of index is marked as a second type of index; the number of moments when the first type of index and the second type of index are both in abnormal fluctuation moments before and before the time to be analyzed is recorded as a first number, and the number of moments when the first type of index is in abnormal fluctuation moments before and before the time to be analyzed is recorded as a second number; the ratio of the first number to the second number is determined as the abnormal consistency coefficient of the first type of index and the second type of index at the time to be analyzed; According to the abnormal consistency coefficient between the first category indicator and each other category indicator at the time to be analyzed, and the difference in the change value between the first category indicator and each other category indicator at the time to be analyzed and before the time to be analyzed when they are at the moment of abnormal fluctuation and the corresponding other indicators, the correlation coefficient between the first category indicator and all other indicators at the time to be analyzed is obtained; According to the correlation coefficient between each type of indicator at the time to be analyzed and all other indicators, and each type of indicator at the time to be analyzed, the coordination coefficient at the time to be analyzed is obtained; The time to be analyzed is any time during the ADL ability training process of the neurological disease patient.

7. The ADL ability training data management system for neurological disease patients according to claim 6, characterized in that: The coordination coefficient of the time to be analyzed is obtained according to the correlation coefficient of each type of indicator at the time to be analyzed and all other indicators, and each type of indicator at the time to be analyzed, including: The product of each type of indicator at the time to be analyzed and the correlation coefficient between each type of indicator and all other indicators is recorded as the first eigenvalue of each type of indicator at the time to be analyzed; The cumulative sum of the first characteristic values ​​of all indicators at the time to be analyzed is determined as the coordination coefficient at the time to be analyzed.

8. The ADL ability training data management system for neurological disease patients according to claim 6, characterized in that: The effective evaluation value of the training is determined according to the change of the coordination coefficient during the ADL ability training of the neurological disease patient, including: The ratio between the coordination coefficient at the time to be analyzed and the coordination coefficient at the moment before the time to be analyzed is determined as the coordination ability growth index at the time to be analyzed; if the coordination ability growth index is greater than 1, the time to be analyzed is regarded as the growth moment; if the coordination ability growth index is less than or equal to 1, the time to be analyzed is regarded as the reduction moment; A recovery index is obtained according to the time distribution of the growth period, the relative size relationship between the range of the growth index of the growth period and the range of the growth index of the reduction period; the growth period is composed of continuous growth moments; the reduction period is composed of continuous reduction moments; The effective evaluation value of the training is evaluated by combining the relative magnitude relationship between the coordination coefficient at the initial moment of the ADL ability training and the coordination coefficient at the current moment and the recovery index.

9. The ADL ability training data management system for neurological disease patients according to claim 8, characterized in that: The recovery index is obtained according to the time distribution of the growth period, the relative size relationship between the range of the growth index of the growth period and the range of the growth index of the reduction period, including: Calculating a first ratio between an average value of the range of the growth index of all growth periods and an average value of the range of the growth index of all reduction periods, and a second ratio between a total duration of all growth periods and a total duration of the neurological disease patient detection process; The recovery index is determined according to the maximum time interval between adjacent growth periods, the first ratio and the second ratio, the first ratio and the second ratio are both positively correlated with the recovery index, and the maximum time interval is negatively correlated with the recovery index.

10. The ADL ability training data management system for neurological disease patients according to claim 8, characterized in that: The effective evaluation value of the training is evaluated by combining the relative magnitude relationship between the coordination coefficient at the initial moment of the ADL ability training and the coordination coefficient at the current moment and the recovery index, including: calculating a third ratio between the coordination coefficient at the initial moment of the ADL ability training and the coordination coefficient at the current moment; The product of the third ratio and the recovery index is determined as the effective evaluation value of the training.

Images