CN115862809A - Intelligent rehabilitation nursing equipment based on big data - Google Patents
Intelligent rehabilitation nursing equipment based on big data Download PDFInfo
- Publication number
- CN115862809A CN115862809A CN202211636729.9A CN202211636729A CN115862809A CN 115862809 A CN115862809 A CN 115862809A CN 202211636729 A CN202211636729 A CN 202211636729A CN 115862809 A CN115862809 A CN 115862809A
- Authority
- CN
- China
- Prior art keywords
- training
- rehabilitation
- lower limb
- evaluation
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 230000000474 nursing effect Effects 0.000 title claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 215
- 238000011156 evaluation Methods 0.000 claims abstract description 209
- 210000003141 lower extremity Anatomy 0.000 claims abstract description 141
- 238000007418 data mining Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 15
- 230000005021 gait Effects 0.000 claims description 85
- 210000004197 pelvis Anatomy 0.000 claims description 54
- 210000003205 muscle Anatomy 0.000 claims description 33
- 238000011084 recovery Methods 0.000 claims description 26
- 210000003414 extremity Anatomy 0.000 claims description 22
- 230000002596 correlated effect Effects 0.000 claims description 16
- 230000004064 dysfunction Effects 0.000 claims description 11
- 230000000875 corresponding effect Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 210000002027 skeletal muscle Anatomy 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 206010061296 Motor dysfunction Diseases 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 description 8
- 210000002569 neuron Anatomy 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 208000012661 Dyskinesia Diseases 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 230000036982 action potential Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 210000003169 central nervous system Anatomy 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000004118 muscle contraction Effects 0.000 description 2
- 230000003387 muscular Effects 0.000 description 2
- 210000001640 nerve ending Anatomy 0.000 description 2
- 210000000225 synapse Anatomy 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Abstract
The invention discloses intelligent rehabilitation nursing equipment based on big data, which belongs to the technical field of rehabilitation nursing equipment and comprises a lower limb rehabilitation training module, a data acquisition unit, a data processing module, a lower limb rehabilitation evaluation module, a rehabilitation doctor service terminal, a lower limb rehabilitation cloud database, a data mining module and a recommendation unit. The lower limb rehabilitation exercise parameter evaluation method and device can evaluate the individual lower limb rehabilitation state according to the rehabilitation exercise parameters of the patient, provide a diagnosis data base for lower limb rehabilitation doctors conveniently, improve the diagnosis efficiency of the lower limb rehabilitation doctors, customize personalized lower limb rehabilitation and nursing schemes for the patient, utilize the Internet cloud platform to construct a lower limb rehabilitation database, automatically provide scientific lower limb rehabilitation exercise parameters for the patient, and the existing rehabilitation nursing equipment cannot evaluate the patient rehabilitation state through the exercise data of the patient and compare the patient rehabilitation state with the Internet big data, and cannot automatically select scientific lower limb rehabilitation exercise parameters for the patient according to the comparison result.
Description
Technical Field
The invention relates to intelligent rehabilitation nursing equipment, in particular to intelligent rehabilitation nursing equipment based on big data, and belongs to the technical field of rehabilitation nursing equipment.
Background
The rehabilitation robot can drive a patient to perform repetitive rehabilitation training according to the motion rule of a healthy human body, enhance the motion sense of the patient, and enable the patient to learn and remember a correct motion posture, wherein the lower limb rehabilitation robot is an important branch in the field of rehabilitation robots and can perform repeated and regular gait training on lower limbs to help the patient gradually recover the independent walking ability, assist the patient with lower limb motion dysfunction to perform bionic gait training, enable the patient with lower limb motion dysfunction to recover partial motion functions of the lower limbs, not only can the workload of lower limb rehabilitation nursing doctors be relieved, but also one-to-one training service can be realized, the rehabilitation training service is provided for the patient uninterruptedly, the recovery speed of the lower limbs of the patient is improved, the motion data of the user can be transmitted to the rehabilitation doctors to perform diagnosis, and then the patient can be helped to customize an individualized rehabilitation and nursing scheme, but the existing rehabilitation nursing equipment cannot compare the assessment of the recovery state of the patient with internet big data through the motion data of the patient, and the lower limb rehabilitation motion parameters which can not be selected for the patient automatically according to the comparison result scientifically. In order to overcome the defects, the invention provides the intelligent rehabilitation nursing equipment based on the big data, which can evaluate the recovery state of the lower limbs of a person according to the rehabilitation motion parameters of the patient, is convenient for providing a diagnostic data base for lower limb rehabilitation doctors, improves the diagnostic efficiency of the lower limb rehabilitation doctors, customizes an individualized lower limb rehabilitation and nursing scheme for the patient, constructs a lower limb rehabilitation database by using an internet cloud platform, digs out the rehabilitation motion parameters adaptive to the current recovery degree of the patient from the database, automatically provides scientific lower limb rehabilitation motion parameters for the patient, assists the patient to scientifically perform lower limb rehabilitation training, is convenient for improving the effect of the patient on performing lower limb motion training, and improves the lower limb rehabilitation speed of the patient.
Disclosure of Invention
The invention mainly aims to solve the problems that the conventional rehabilitation nursing equipment cannot evaluate the rehabilitation state of a patient through the movement data of the patient and compare the rehabilitation state with internet big data, and scientific lower limb rehabilitation movement parameters cannot be automatically selected for the patient according to a comparison result, and the intelligent rehabilitation nursing equipment based on the big data is provided.
The purpose of the invention can be achieved by adopting the following technical scheme:
the utility model provides an intelligence rehabilitation and nursing equipment based on big data, includes low limbs rehabilitation training module, data acquisition unit, data processing module, low limbs rehabilitation evaluation module, recovered doctor service terminal, low limbs rehabilitation cloud database, data mining module and recommendation unit, low limbs rehabilitation training module with the data acquisition unit links to each other, the data acquisition unit with the data processing module links to each other, the data processing module with the low limbs rehabilitation evaluation module links to each other, low limbs rehabilitation evaluation module with recovered doctor service terminal with the low limbs rehabilitation cloud database links to each other, low limbs rehabilitation cloud database with the data mining module links to each other, the data mining module with the recommendation unit links to each other, the recommendation unit with the low limbs rehabilitation training module links to each other, the low limbs rehabilitation evaluation module assesses the rehabilitation training effect of patient through comprehensive training evaluation index, and comprehensive training evaluation index is pelvis motion evaluation index, sole mechanics evaluation index and the weighted sum of gait phase place evaluation index, and the weight of sole motion evaluation index, mechanics evaluation index and low limbs evaluation index are 0.6, 0.2 and 0.2 respectively, and the evaluation index of comprehensive training formula is the gait phase place evaluation index:
P Z ＝0.6P pelvis +0.2P feet +0.2P tread ；
in the formula: p Z Evaluation of the indicators for comprehensive training, P pelvis Evaluation of the index for pelvic movement, P feet Evaluation of the index for plantar mechanics, P tread Evaluating an index for the lower limbs of the gait;
the lower limb rehabilitation evaluation module standardizes and regularizes comprehensive training evaluation indexes, and substitutes the processed data as independent variables into a function
And (5) evaluating the comprehensive training evaluation index by using the function value classification.
As a further aspect of the present invention, in the lower limb rehabilitation evaluation module, the pelvic motion evaluation index is positively correlated with the change amount of the pelvic tilt angle, the change amount of the pelvic pitch angle, and the change amount of the pelvic rotation angle, and the evaluation formula of the pelvic motion evaluation index is as follows:
in the formula: a is an amplitude adjustment coefficient, B is a numerical value adjustment parameter, and is obtained by experience, wherein delta alpha is a pelvis inclination angle variation, delta beta is a pelvis pitch angle variation, and delta gamma is recorded as a pelvis rotation angle variation;
the plantar mechanics evaluation index is positively correlated with the plantar area, negatively correlated with the plantar pressure distribution index, and the evaluation formula of the plantar mechanics evaluation index is as follows:
in the formula: f max The maximum force on the sole, S is the sole area, I fb Recording as the plantar pressure distribution index;
the plantar pressure distribution index is in negative correlation with the numerical range of plantar pressure and in positive correlation with the area occupied by the maximum plantar pressure, and the formula of the plantar pressure distribution index is as follows:
in the formula: f min Minimum pressure of the sole, S mf The area occupied by the maximum plantar pressure is shown;
the gait lower limb evaluation index is negatively correlated with the average duration of completing five groups of gait training periods, and positively correlated with the surface electromyographic signal amplitudes of tibialis anterior, gastrocnemius, lateral and biceps femoris in gait, and the evaluation formula of the gait lower limb evaluation index is as follows:
in the formula: i is the sequence number of gait training, T i The period duration, H, required to complete gait training for the ith pass tam Is the surface electromyographic signal amplitude, H, of the tibialis anterior muscle under gait gm Is the surface electromyographic signal amplitude of gastrocnemius, H lm Is the surface electromyographic signal amplitude of the lateral muscle, H bf Is the surface electromyographic signal amplitude of the biceps femoris muscle.
As a further scheme of the invention, the lower limb rehabilitation training module is used for assisting a patient with lower limb motor dysfunction to complete gait training, the gait training comprises support time phase training and swing time phase training, a micro-posture sensor for measuring a pelvis inclination angle variation, a pelvis pitch angle variation and a pelvis rotation angle variation is mounted on the lower limb rehabilitation training module, the lower limb rehabilitation training module is further provided with a pressure sensor for measuring sole pressure, sole area and area occupied by maximum sole force and a numerical analysis module connected with the pressure sensor, the lower limb rehabilitation training module is further provided with an electrode plate for measuring surface electromyographic signal amplitudes of tibialis anterior, gastrocnemius, lateral muscles and biceps femoris muscle under gait and a timer for timing, the electrode plate is connected with a signal preprocessing module, and the signal preprocessing module is connected with a feature extraction module.
As a further aspect of the present invention, the data acquisition unit is configured to acquire gait training parameters acquired by the lower limb rehabilitation training module, and the data processing module is configured to remove abnormal values and outliers in the data.
As a further scheme of the present invention, the data mining module performs maximum entropy clustering analysis on the data transmitted by the lower limb rehabilitation evaluation module, acquires gait training data of different lower limb rehabilitation degree evaluation results, and performs recommendation degree descending ranking on the pace and training duration of gait training to form a ranking list of recommended gait training, the recommending unit acquires recommended training parameter ranges corresponding to different lower limb evaluation results, the recommended parameter range takes a parameter corresponding to the tenth of recommended gait training as the minimum of recommended parameters, a parameter corresponding to the first of recommended gait training as the maximum of recommended parameters, and recommends the range of recommended training parameters to the lower limb rehabilitation training module.
As a further scheme of the invention, the method for carrying out classification evaluation on the comprehensive training evaluation indexes by the lower limb rehabilitation evaluation module comprises the following steps:
s1, obtaining a sample data training set: acquiring a training data sample set of comprehensive training evaluation indexes through a lower limb rehabilitation cloud database;
s2, standardizing comprehensive training evaluation indexes: calculating the mean value and the variance of the numerical value of the comprehensive training evaluation index, subtracting the mean value from each data, and dividing the obtained difference value by the variance to obtain a standardized comprehensive training evaluation index;
s3, regularizing the standardized comprehensive training evaluation indexes: forming a standard comprehensive training evaluation index regularization vector from the standardized comprehensive training evaluation indexes, solving the norm of the standard comprehensive training evaluation index regularization vector, and dividing the standard comprehensive training evaluation index regularization vector by the norm of the whole standard comprehensive training evaluation index regularization vector to obtain the regularized comprehensive training evaluation indexes and increase the data diversity of the comprehensive training evaluation indexes;
s4, carrying out classification evaluation on normalized comprehensive training evaluation indexes: substituting the normalized comprehensive training evaluation index as an independent variable into a function
Using f (P) Z,C ) The normalized comprehensive training evaluation index is classified by the numerical value of (A), wherein P Z,C For the normalized comprehensive training evaluation index, when f (P) is more than or equal to 0 Z,C )<When 0.5 hour, the recovery degree of patients with lower limb movement dysfunction is first grade, and is not less than 0.5 ≤f(P Z,C ) When the lower limb movement dysfunction is less than or equal to 1, the recovery degree of the patient with lower limb movement dysfunction is second grade.
As a further aspect of the present invention, the rehabilitation doctor service terminal is configured to transmit the pelvic motion evaluation index, the plantar mechanics evaluation index, the gait lower limb evaluation index, the comprehensive training evaluation index and the evaluation index evaluated by the lower limb rehabilitation evaluation module to a rehabilitation doctor in a classified manner.
The invention has the beneficial technical effects that: according to the intelligent rehabilitation nursing device based on big data, the training data of a patient can be measured while gait rehabilitation training is carried out on the patient with lower limb dyskinesia by arranging the lower limb rehabilitation training module, the data acquisition unit and the processing unit acquire data and preprocess the data, the lower limb rehabilitation evaluation module evaluates the lower limb recovery degree of the patient through the processed data, acquires the pelvis movement evaluation index, the sole mechanics evaluation index and the gait lower limb evaluation index through data analysis, jointly analyzes the pelvis movement evaluation index, the sole mechanics evaluation index and the gait lower limb evaluation index to acquire the comprehensive training evaluation index, carries out classification evaluation on the comprehensive training evaluation index, transmits the evaluated data and results to a rehabilitation doctor service terminal for online checking, conveniently provides direct evaluation data and a foundation for diagnosing the recovery state of the patient for the rehabilitation doctor, further facilitates the doctor to customize a personalized recovery scheme for the patient through the evaluation data, transmits the data to the cloud database for constructing the rehabilitation training database, conveniently digs out cloud data suitable for different comprehensive training indexes, further facilitates the scientific combination of the rehabilitation training and the gait training of the patient, and is beneficial to improving the diagnosis and treatment effect of the patient.
Drawings
Fig. 1 is an overall block diagram of a big data based intelligent rehabilitation and nursing device according to the present invention.
Detailed Description
In order to make the technical solutions of the present invention more clear and definite for those skilled in the art, the present invention is further described in detail below with reference to the examples and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
As shown in fig. 1, the big data based intelligent rehabilitation nursing device provided in this embodiment includes a lower limb rehabilitation training module, a data acquisition unit, a data processing module, a lower limb rehabilitation evaluation module, a rehabilitation doctor service terminal, a lower limb rehabilitation cloud database, a data mining module, and a recommendation unit, where the lower limb rehabilitation training module is connected to the data acquisition unit, the data acquisition unit is connected to the data processing module, the data processing module is connected to the lower limb rehabilitation evaluation module, the lower limb rehabilitation evaluation module is connected to the rehabilitation doctor service terminal and the lower limb rehabilitation cloud database, the lower limb rehabilitation cloud database is connected to the data mining module, the data mining module is connected to the recommendation unit, the recommendation unit is connected to the lower limb rehabilitation training module, the lower limb rehabilitation evaluation module evaluates the rehabilitation training effect of a patient through a comprehensive training evaluation index, the comprehensive training evaluation index is a weighted sum of a pelvic motion evaluation index, a plantar mechanics evaluation index, and a gait phase evaluation index, weights of the pelvic motion evaluation index, the plantar motion evaluation index and the lower limb mechanics evaluation index are 0.6, 0.2 and a gait phase evaluation formula, and weights of the comprehensive training evaluation index are respectively:
P Z ＝0.6P pelvis +0.2P feet +0.2P tread ；
in the formula: p Z Evaluation of the indicators for comprehensive training, P pelvis Evaluation of the index for pelvic movement, P feet Evaluation of the index for plantar mechanics, P tread Evaluating an index for a lower limb of gait;
the lower limb rehabilitation evaluation module standardizes and regularizes comprehensive training evaluation indexes, and substitutes the processed data as independent variables into a function
And evaluating comprehensive training evaluation indexes by using function value classification.
According to the intelligent rehabilitation nursing device based on the big data, the lower limb rehabilitation training module is arranged, training data of a patient can be measured while gait rehabilitation training is carried out on the patient with lower limb dyskinesia, the data acquisition unit and the processing unit acquire data and preprocess the data, the lower limb rehabilitation evaluation module evaluates the lower limb recovery degree of the patient through the processed data, a pelvis movement evaluation index, a sole mechanics evaluation index and a gait lower limb evaluation index are obtained through data analysis, the pelvis movement evaluation index, the sole mechanics evaluation index and the gait lower limb evaluation index are jointly analyzed to obtain a comprehensive training evaluation index, classification evaluation is carried out on the comprehensive training evaluation index, the evaluated data and results are transmitted to a rehabilitation doctor service terminal for online checking, direct evaluation data and a basic basis are conveniently provided for a rehabilitation doctor to diagnose the recovery state of the patient, the doctor conveniently customizes an individualized recovery scheme for the patient through the evaluation data, the data are transmitted to a cloud database to construct a rehabilitation training database, the cloud database is convenient for digging out to obtain different comprehensive training parameters suitable for the rehabilitation training of the patient, and the rehabilitation training range is convenient for the doctor to select the rehabilitation training range to improve the diagnosis and the gait speed of the patient.
In the lower limb rehabilitation evaluation module, the pelvis movement evaluation index is positively correlated with the pelvis inclination angle change quantity, the pelvis pitch angle change quantity and the pelvis rotation angle change quantity, and the evaluation formula of the pelvis movement evaluation index is as follows:
in the formula: a is an amplitude adjustment coefficient, B is a numerical value adjustment parameter, and is obtained by experience, wherein delta alpha is a pelvis inclination angle variation, delta beta is a pelvis pitch angle variation, and delta gamma is recorded as a pelvis rotation angle variation;
the plantar mechanics evaluation index is positively correlated with the plantar area, negatively correlated with the plantar pressure distribution index, and the evaluation formula of the plantar mechanics evaluation index is as follows:
in the formula: f max Maximum force on the sole, S is the plantar area, I fb Recording as plantar pressure distribution index;
the plantar pressure distribution index is in negative correlation with the numerical range of plantar pressure and in positive correlation with the area occupied by the maximum plantar pressure, and the formula of the plantar pressure distribution index is as follows:
in the formula: f min Minimum pressure of the sole, S mf The area occupied by the maximum plantar pressure is shown;
the gait lower limb evaluation index is negatively correlated with the average duration of completing five groups of gait training periods, and positively correlated with the surface electromyographic signal amplitudes of tibialis anterior, gastrocnemius, lateral and biceps femoris in gait, and the evaluation formula of the gait lower limb evaluation index is as follows:
in the formula: i is the sequence number of gait training, T i The cycle duration, H, required to complete gait training for the ith time tam Is the surface electromyographic signal amplitude, H, of the tibialis anterior muscle under gait gm Is the surface electromyographic signal amplitude of gastrocnemius, H lm Is the surface electromyographic signal amplitude of the lateral muscle, H bf Is the surface electromyographic signal amplitude of the biceps femoris muscle.
By monitoring the pelvis inclination angle change quantity, the pelvis pitch angle change quantity and the pelvis rotation angle change quantity of the patient during lower limb gait rehabilitation training, the movement condition of the pelvis of the patient during gait training can be conveniently monitored, the evaluation on the pelvis stability degree of the patient during lower limb gait rehabilitation training can be conveniently carried out through the movement condition of the pelvis, and further the evaluation on the lower limb rehabilitation state can be conveniently realized through the evaluation on the pelvis stability degree; by monitoring the maximum force of the soles, the negative correlation of the areas of the soles and the distribution index of the pressure of the soles, the evaluation on the landing capability of a patient can be conveniently realized through the data, so that the pressure of the patient on the ground and the capability of keeping the feet stably pressing the ground can be conveniently evaluated, and the recovery degree of the lower limbs of the patient and the stability of the gait are further reflected; the monitoring of the surface electromyographic signal amplitudes of the tibialis anterior, gastrocnemius, lateral and biceps femoris muscles under gait can reflect the recovery condition of the muscle strength of the lower limbs of the patient, the muscle strength of the muscle groups of the lower limbs of the patient is reflected by measuring the electric potential generated by the action, and then the recovery degree of the muscle strength of the lower limbs of the patient is evaluated by monitoring the muscle strength.
Lower limbs rehabilitation training module is used for assisting the patient who accomplishes lower limbs movement dysfunction to accomplish gait training, and gait training is including supporting time phase training and swing time phase training, install the little attitude sensor who is used for measuring pelvis inclination angle change, pelvis pitch angle change and pelvis rotation angle change on the lower limbs rehabilitation training module, lower limbs rehabilitation training module still is equipped with the pressure sensor who is used for measuring sole pressure, sole area, the shared area of sole maximum force and with the numerical value analysis module that pressure sensor links to each other, lower limbs rehabilitation training module still is equipped with the electrode slice that is used for measuring the surface electromyographic signal amplitude of tibialis anterior muscle, gastrocnemius muscle, lateral muscle and biceps femoris muscle under the gait and is used for the time-recorder of timing, electrode slice connection has signal preprocessing module, signal preprocessing module is connected with the characteristic and draws the module.
The gait training of the patient is conveniently completed by the arrangement of the lower limb rehabilitation training module, and meanwhile, the individualized rehabilitation motion parameter recommendation can be provided for the patient by combining the data mining of the rehabilitation data, so that the individualized lower limb rehabilitation data customization of the patient is conveniently realized; the micro-attitude sensor can capture and describe the motion state of the pelvis by measuring a three-dimensional angle, so that the evaluation of the stability of the pelvis is conveniently realized by the motion state of the pelvis, and the recovery degree of the lower limbs of a patient is reflected; the pressure sensor and the numerical analysis module are arranged to conveniently measure the pressure of the sole and the distribution condition of the pressure, so that the actual pressure situation of the sole can be conveniently captured and analyzed through the measurement of the pressure of the sole and the distribution of the pressure, and a calculation basis and a basis are conveniently provided for the mechanical evaluation index of the sole; the brain cortex generated by the patient during the muscular movement is excited to stimulate the neuron of the central nervous system to generate an electric pulse, the electric pulse is transmitted to the skeletal muscle of the nerve ending along the synapse of the neuron to be limited to generate an action potential, the electrode plate can capture the generated action point position for evaluating the muscle force generated by the patient during the muscle contraction, and the muscle force is evaluated to be used as an evaluation parameter of the lower limb rehabilitation degree of the patient.
The data acquisition unit is used for acquiring gait training parameters acquired by the lower limb rehabilitation training module, and the data processing module is used for removing abnormal values and outliers in the data.
Through the setting of data acquisition unit, conveniently carry out preliminary screening to the outlier and the outlier in the data, reduce the data anomaly that arouses because equipment failure, avoid the input of abnormal data to arouse the reduction of assessment result accuracy.
The data mining module carries out maximum entropy clustering analysis on the data transmitted by the lower limb rehabilitation evaluation module to obtain gait training data of different lower limb rehabilitation degree evaluation results, carries out recommendation degree descending ranking on the pace and the training duration of gait training to form a ranking list for recommending gait training, the recommending unit obtains recommended training parameter ranges corresponding to different lower limb evaluation results, the recommended parameter ranges take the parameter corresponding to the tenth recommended gait training as the minimum value of the recommended parameter, the parameter corresponding to the first recommended gait training as the maximum value of the recommended parameter, and the range of the recommended training parameter is recommended to the lower limb rehabilitation training module.
Through the arrangement of the data mining module, data mining can be conveniently carried out on the evaluation result of the patient and the diagnosis and treatment scheme of a rehabilitation doctor, gait training parameters adaptive to the comprehensive training evaluation indexes are mined, the recommended parameter range is recommended to the lower limb rehabilitation training module used by the patient, and the patient can conveniently carry out personalized gait rehabilitation training.
The method for carrying out classification evaluation on the comprehensive training evaluation indexes by the lower limb rehabilitation evaluation module comprises the following steps:
s1, obtaining a sample data training set: acquiring a training data sample set of comprehensive training evaluation indexes through a lower limb rehabilitation cloud database;
s2, standardizing comprehensive training evaluation indexes: calculating the mean value and the variance of the numerical value of the comprehensive training evaluation index, subtracting the mean value from each data, and dividing the obtained difference value by the variance to obtain a standardized comprehensive training evaluation index;
s3, regularizing the standardized comprehensive training evaluation indexes: forming a standard comprehensive training evaluation index regularization vector from the standardized comprehensive training evaluation indexes, solving the norm of the standard comprehensive training evaluation index regularization vector, dividing the standard comprehensive training evaluation index regularization vector by the norm of the whole standard comprehensive training evaluation index regularization vector to obtain the regularized comprehensive training evaluation indexes, and increasing the data diversity of the comprehensive training evaluation indexes;
s4, carrying out classification evaluation on normalized comprehensive training evaluation indexes: substituting the normalized comprehensive training evaluation index as an independent variable into a function
Using f (P) Z,C ) The normalized comprehensive training evaluation index is classified by the numerical value of (A), wherein P Z,C For the normalized comprehensive training evaluation index, when f (P) is more than or equal to 0 Z,C )<At 0.5, the recovery degree of patients with lower limb motor dysfunction is first grade, f (P) is more than or equal to 0.5 Z,C ) When the lower limb movement dysfunction is less than or equal to 1, the recovery degree of the patient with lower limb movement dysfunction is second grade.
The comprehensive training assessment indexes are standardized, the comprehensive training assessment indexes are convenient to accumulate, the standardized comprehensive training assessment indexes are regularized, the standardized comprehensive training assessment indexes are convenient to convert to unit norm, the diversity of the comprehensive training assessment indexes can be increased, the difficulty of judgment and classification caused by accumulation and stacking of the comprehensive training assessment indexes is avoided, the standardized and regularized comprehensive training assessment indexes are classified, visual classification results are convenient to form, the efficiency of diagnosing the recovery condition of a patient by a rehabilitation doctor is improved, the working efficiency of the rehabilitation doctor is improved, the workload of the rehabilitation doctor is reduced, and the personalized rehabilitation nursing scheme can be customized for the patient efficiently.
The rehabilitation doctor service terminal is used for transmitting the pelvic motion evaluation index, the plantar mechanics evaluation index, the gait lower limb evaluation index, the comprehensive training evaluation index and the evaluation index evaluated by the lower limb rehabilitation evaluation module to a rehabilitation doctor in a classified manner.
In summary, in this embodiment, according to the intelligent rehabilitation and nursing device based on big data of this embodiment, by monitoring the change amount of the tilt angle of the pelvis, the change amount of the pitch angle of the pelvis, and the change amount of the rotation angle of the pelvis when the patient performs gait rehabilitation training, the movement condition of the pelvis of the patient during gait training can be conveniently monitored, the evaluation of the pelvic stability degree of the patient during lower limb gait rehabilitation training can be conveniently performed through the movement condition of the pelvis, and then the evaluation of the lower limb rehabilitation state can be conveniently realized through the evaluation of the pelvic stability degree; by monitoring the maximum force of the soles, the negative correlation of the areas of the soles and the distribution index of the pressure of the soles, the evaluation on the landing capability of a patient can be conveniently realized through the data, so that the pressure of the patient on the ground and the capability of keeping the feet stably pressing the ground can be conveniently evaluated, and the recovery degree of the lower limbs of the patient and the stability of the gait are further reflected; the monitoring of the surface electromyographic signal amplitudes of the tibialis anterior, gastrocnemius, lateral and biceps femoris muscles under gait can reflect the recovery condition of the muscle strength of the lower limbs of the patient, the muscle strength of the muscle groups of the lower limbs of the patient is reflected by measuring the electric potential generated by the action, and then the recovery degree of the muscle strength of the lower limbs of the patient is evaluated by monitoring the muscle strength. The gait training of the patient is conveniently completed by the arrangement of the lower limb rehabilitation training module, and meanwhile, the individualized rehabilitation motion parameter recommendation can be provided for the patient by combining the data mining of the rehabilitation data, so that the individualized lower limb rehabilitation data customization of the patient is conveniently realized; the micro-attitude sensor can capture and describe the motion state of the pelvis by measuring a three-dimensional angle, so that the evaluation of the stability of the pelvis is conveniently realized by the motion state of the pelvis, and the recovery degree of the lower limbs of a patient is reflected; the pressure sensor and the numerical analysis module are arranged to facilitate the measurement of the pressure of the sole and the distribution of the pressure, so that the actual pressure situation of the sole can be conveniently captured and analyzed through the measurement of the pressure of the sole and the distribution of the pressure, and a calculation basis and a basis can be conveniently provided for the mechanical evaluation index of the sole; the brain cortex generated by the patient during the muscular movement is excited to stimulate the neuron of the central nervous system to generate an electric pulse, the electric pulse is transmitted to the skeletal muscle of the nerve ending along the synapse of the neuron to be limited to generate an action potential, the electrode plate can capture the generated action point position for evaluating the muscle force generated by the patient during the muscle contraction, and the muscle force is evaluated to be used as an evaluation parameter of the lower limb rehabilitation degree of the patient. Through the setting of data acquisition unit, conveniently carry out preliminary shining to the outlier in the data and select, reduce because the data that equipment trouble arouses are unusual, avoid the input of unusual data to arouse the reduction of assessment result accuracy. Through the arrangement of the data mining module, data mining can be conveniently carried out on the evaluation result of the patient and the diagnosis and treatment scheme of a rehabilitation doctor, gait training parameters adaptive to the comprehensive training evaluation indexes are mined, the recommended parameter range is recommended to the lower limb rehabilitation training module used by the patient, and the patient can conveniently carry out personalized gait rehabilitation training. The comprehensive training assessment indexes are standardized, the comprehensive training assessment indexes are convenient to accumulate, the standardized comprehensive training assessment indexes are regularized, the standardized comprehensive training assessment indexes are convenient to convert to unit norm, the diversity of the comprehensive training assessment indexes can be increased, the difficulty of judgment and classification caused by accumulation and stacking of the comprehensive training assessment indexes is avoided, the standardized and regularized comprehensive training assessment indexes are classified, visual classification results are convenient to form, the efficiency of diagnosing the recovery condition of a patient by a rehabilitation doctor is improved, the working efficiency of the rehabilitation doctor is improved, the workload of the rehabilitation doctor is reduced, and the personalized rehabilitation nursing scheme can be customized for the patient efficiently.
The above description is only for the purpose of illustrating the present invention and is not intended to limit the scope of the present invention, and any person skilled in the art can substitute or change the technical solution of the present invention and its conception within the scope of the present invention.
Claims (7)
1. The utility model provides an intelligence rehabilitation nursing equipment based on big data which characterized in that, includes low limbs rehabilitation training module, data acquisition unit, data processing module, low limbs rehabilitation aassessment module, recovered doctor service terminal, low limbs rehabilitation cloud database, data mining module and recommendation unit, low limbs rehabilitation training module with the data acquisition unit links to each other, data acquisition unit with data processing module links to each other, data processing module with low limbs rehabilitation aassessment module links to each other, low limbs rehabilitation aassessment module with recovered doctor service terminal with low limbs rehabilitation cloud database links to each other, low limbs rehabilitation cloud database with data mining module links to each other, data mining module with the recommendation unit links to each other, the recommendation unit with the low limbs rehabilitation training module links to each other, low limbs rehabilitation aassessment module assesses the patient's rehabilitation training effect through the comprehensive training aassessment index, the comprehensive training aassessment index is pelvis motion aassessment index, sole mechanics aassessment index and the weighted sum of gait phase place aassessment index, the weight of pelvis motion aassessment index, sole mechanics aassessment index and low limbs aassessment index are 0.6, 0.2 and 0.2 respectively, and the evaluation formula of comprehensive training is that the evaluation index is that the evaluation formula is 0.2:
P Z ＝0.6P pelvis +0.2P feet +0.2P tread ；
in the formula: p Z Evaluation of the indicators for comprehensive training, P pelvis Assessment of indicators for pelvic movements，P feet Evaluation of the index for plantar mechanics, P tread Evaluating an index for a lower limb of gait;
the lower limb rehabilitation evaluation module standardizes and regularizes comprehensive training evaluation indexes, and substitutes the processed data as independent variables into a function
And evaluating comprehensive training evaluation indexes by using function value classification.
2. The intelligent rehabilitation nursing device based on big data as claimed in claim 1, wherein in the lower limb rehabilitation evaluation module, the pelvic motion evaluation index is positively correlated with the change of the pelvic tilt angle, the change of the pelvic pitch angle and the change of the pelvic rotation angle, and the evaluation formula of the pelvic motion evaluation index is as follows:
in the formula: a is an amplitude adjustment coefficient, B is a numerical value adjustment parameter, and is obtained by experience, wherein delta alpha is a pelvis inclination angle change quantity, delta beta is a pelvis pitch angle change quantity, and delta gamma is recorded as a pelvis rotation angle change quantity;
the plantar mechanics evaluation index is positively correlated with the plantar maximal force, negatively correlated with the plantar area and negatively correlated with the plantar pressure distribution index, and the evaluation formula of the plantar mechanics evaluation index is as follows:
in the formula: f max Maximum force on the sole, S is the plantar area, I fb Recording as the plantar pressure distribution index;
the plantar pressure distribution index is in negative correlation with the numerical range of the plantar pressure and in positive correlation with the area occupied by the maximum plantar pressure, and the formula of the plantar pressure distribution index is as follows:
in the formula: f min Minimum pressure of the sole, S mf The area occupied by the maximum plantar pressure is shown;
the gait lower limb evaluation index is negatively correlated with the average duration of completing five groups of gait training periods, and positively correlated with the surface electromyographic signal amplitudes of tibialis anterior, gastrocnemius, lateral and biceps femoris in gait, and the evaluation formula of the gait lower limb evaluation index is as follows:
in the formula: i is the sequence number of gait training, T i The cycle duration, H, required to complete gait training for the ith time tam Is the surface electromyographic signal amplitude, H, of the tibialis anterior muscle under gait gm Is the surface electromyographic signal amplitude of the gastrocnemius muscle, H lm Is the surface electromyographic signal amplitude of the lateral muscle, H bf Is the surface electromyographic signal amplitude of the biceps femoris muscle.
3. The intelligent rehabilitation and nursing device based on big data of claim 1, wherein the lower limb rehabilitation training module is used for assisting a patient who completes lower limb movement dysfunction to complete gait training, the gait training includes support time phase training and swing time phase training, a micro-posture sensor used for measuring pelvis inclination angle variation, pelvis pitch angle variation and pelvis rotation angle variation is installed on the lower limb rehabilitation training module, the lower limb rehabilitation training module is further provided with a pressure sensor used for measuring sole pressure, sole area and occupied area of maximum sole force and a numerical value analysis module connected with the pressure sensor, the lower limb rehabilitation training module is further provided with an electrode plate used for measuring surface electromyographic signal amplitude of tibialis anterior muscle, gastrocnemius muscle, lateral muscle and biceps femoris muscle under gait and a timer used for timing, the electrode plate is connected with a signal preprocessing module, and the signal preprocessing module is connected with a feature extraction module.
4. The intelligent big data-based rehabilitation and nursing device according to claim 1, wherein said data acquisition unit is used for acquiring gait training parameters acquired by said lower limb rehabilitation training module, and said data processing module is used for eliminating abnormal values and outliers in the data.
5. The intelligent big-data-based rehabilitation nursing device according to claim 1, wherein the data mining module performs maximum entropy clustering analysis on the data transmitted by the lower limb rehabilitation evaluation module to obtain gait training data of different lower limb rehabilitation degree evaluation results, and performs recommendation degree descending ranking on pace speed and training duration of gait training to form a ranking list for recommending gait training, the recommending unit obtains recommended training parameter ranges corresponding to different lower limb evaluation results, the recommended parameter range takes a parameter corresponding to the tenth recommended gait training as the minimum value of recommended parameters, the parameter corresponding to the first recommended gait training as the maximum value of recommended parameters, and the range of recommended training parameters is recommended to the lower limb rehabilitation training module.
6. The intelligent big-data-based rehabilitation and nursing device according to claim 1, wherein the method for performing classification evaluation on the comprehensive training evaluation index by the lower limb rehabilitation evaluation module comprises the following steps:
s1, acquiring a sample data training set: acquiring a training data sample set of comprehensive training evaluation indexes through a lower limb rehabilitation cloud database;
s2, standardizing comprehensive training evaluation indexes: calculating the mean value and the variance of the numerical value of the comprehensive training evaluation index, subtracting the mean value from each datum, and dividing the obtained difference value by the variance to obtain a standardized comprehensive training evaluation index;
s3, regularizing the standardized comprehensive training evaluation indexes: forming a standard comprehensive training evaluation index regularization vector from the standardized comprehensive training evaluation indexes, solving the norm of the standard comprehensive training evaluation index regularization vector, and dividing the standard comprehensive training evaluation index regularization vector by the norm of the whole standard comprehensive training evaluation index regularization vector to obtain the regularized comprehensive training evaluation indexes and increase the data diversity of the comprehensive training evaluation indexes;
s4, carrying out classification evaluation on normalized comprehensive training evaluation indexes: substituting the normalized comprehensive training evaluation index as an independent variable into a function
Using f (P) Z,C ) The normalized comprehensive training evaluation index is classified by the numerical value of (A), wherein P Z,C For the normalized comprehensive training evaluation index, when f (P) is more than or equal to 0 Z,C )<At 0.5, the recovery degree of patients with lower limb motor dysfunction is first grade, f (P) is more than or equal to 0.5 Z,C ) When the lower limb movement dysfunction is less than or equal to 1, the recovery degree of the patient with lower limb movement dysfunction is second grade.
7. The intelligent big data-based rehabilitation and nursing device according to claim 1, wherein the rehabilitation doctor service terminal is used for transmitting the pelvic motion evaluation index, the plantar mechanics evaluation index, the gait lower limb evaluation index, the comprehensive training evaluation index and the evaluation index evaluated by the lower limb rehabilitation evaluation module to a rehabilitation doctor in a classified manner.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211636729.9A CN115862809A (en) | 2022-12-16 | 2022-12-16 | Intelligent rehabilitation nursing equipment based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211636729.9A CN115862809A (en) | 2022-12-16 | 2022-12-16 | Intelligent rehabilitation nursing equipment based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115862809A true CN115862809A (en) | 2023-03-28 |
Family
ID=85674307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211636729.9A Withdrawn CN115862809A (en) | 2022-12-16 | 2022-12-16 | Intelligent rehabilitation nursing equipment based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115862809A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116206774A (en) * | 2023-04-27 | 2023-06-02 | 深圳市浩然盈科通讯科技有限公司 | Method and system for automatically matching nursing treatment scheme by combining big data |
| CN117352165A (en) * | 2023-12-06 | 2024-01-05 | 深圳市健怡康医疗器械科技有限公司 | Postoperative rehabilitation nursing method and system for old people |
-
2022
- 2022-12-16 CN CN202211636729.9A patent/CN115862809A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116206774A (en) * | 2023-04-27 | 2023-06-02 | 深圳市浩然盈科通讯科技有限公司 | Method and system for automatically matching nursing treatment scheme by combining big data |
| CN117352165A (en) * | 2023-12-06 | 2024-01-05 | 深圳市健怡康医疗器械科技有限公司 | Postoperative rehabilitation nursing method and system for old people |
| CN117352165B (en) * | 2023-12-06 | 2024-02-20 | 深圳市健怡康医疗器械科技有限公司 | Postoperative rehabilitation nursing method and system for old people |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115862809A (en) | Intelligent rehabilitation nursing equipment based on big data | |
| US10004455B2 (en) | Realtime biofeedback mechanism and data presentation for knee injury rehabilitation monitoring and a soft real time intelligent system thereof | |
| Ghasemzadeh et al. | A body sensor network with electromyogram and inertial sensors: Multimodal interpretation of muscular activities | |
| CN110916679B (en) | Human body lower limb pose gait detection device and method | |
| CN100418476C (en) | Physical movement analyzer and physical movement analyzing method | |
| US20100312152A1 (en) | Smart gait rehabilitation system for automated diagnosis and therapy of neurologic impairment | |
| JP4825456B2 (en) | Muscle activity estimation system | |
| CN106725509B (en) | Feature extraction method of biomechanical information | |
| CN113101134B (en) | Child lower limb movement auxiliary rehabilitation system based on power exoskeleton | |
| US20140100494A1 (en) | Smart gait rehabilitation system for automated diagnosis and therapy of neurologic impairment | |
| WO2018140429A1 (en) | Method, system, and device for analyzing ankle joint kinematics | |
| CN112691292B (en) | Parkinson closed-loop deep brain stimulation system based on wearable intelligent equipment | |
| US11752325B2 (en) | Functional electrical stimulation system offering coordinated and natural movements | |
| CN112494054A (en) | Apoplexy lower limb movement rehabilitation assessment method based on multi-myoelectric and electroencephalogram coherence | |
| CN110931104A (en) | Upper limb rehabilitation robot intelligent training system and method based on machine learning | |
| CN114366559A (en) | Multi-mode sensing system for lower limb rehabilitation robot | |
| Jiang et al. | Exploration of gait parameters affecting the accuracy of force myography-based gait phase detection | |
| CN117298452B (en) | Lower limb rehabilitation system under virtual reality assistance stimulated by transcranial alternating current | |
| Li et al. | An automatic recognition system for patients with movement disorders based on wearable sensors | |
| Badura | Accelerometric signals in automatic balance assessment | |
| US10966652B1 (en) | Method and system for quantifying movement disorder systems | |
| CN116746913A (en) | Equipment for monitoring gait and physical health based on pressure sensor | |
| US11363982B1 (en) | Method and system for quantifying movement disorder symptoms | |
| CN114748079A (en) | Wearable myoelectric method for online evaluation of muscle movement fatigue degree | |
| CN117275723B (en) | Early parkinsonism prediction method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230328 |
|
| WW01 | Invention patent application withdrawn after publication |