CN111951941B - Intelligent medical rehabilitation auxiliary management system - Google Patents
Intelligent medical rehabilitation auxiliary management system Download PDFInfo
- Publication number
- CN111951941B CN111951941B CN202010859972.1A CN202010859972A CN111951941B CN 111951941 B CN111951941 B CN 111951941B CN 202010859972 A CN202010859972 A CN 202010859972A CN 111951941 B CN111951941 B CN 111951941B
- Authority
- CN
- China
- Prior art keywords
- rehabilitation training
- rehabilitation
- action
- module
- training
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Physical Education & Sports Medicine (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Rehabilitation Tools (AREA)
Abstract
The invention relates to the field of intelligent medical treatment and discloses an intelligent medical treatment rehabilitation assistance management system which comprises a plurality of rehabilitation assistance devices and a rehabilitation management platform, wherein the rehabilitation management platform is in communication connection with each rehabilitation assistance device. The rehabilitation management platform comprises: the device comprises an image processing module, a core point acquisition module, a core point positioning module, an action track recognition module, a rehabilitation training action construction module, a rehabilitation training integration module, a rehabilitation training characteristic fusion module, a rehabilitation training instruction generation module and a database, wherein the modules are in communication connection. The rehabilitation assisting device collects rehabilitation training image data, rehabilitation training stress data and rehabilitation training time data and sends the data to the rehabilitation management platform. The rehabilitation management platform analyzes and processes the rehabilitation training instruction to obtain a rehabilitation training instruction, and the rehabilitation training instruction is mapped and matched with the basic information of the patient to obtain rehabilitation training data of the corresponding patient and store the rehabilitation training data in the database.
Description
Technical Field
The invention relates to the field of intelligent medical treatment and medical big data, in particular to an intelligent medical treatment rehabilitation auxiliary management system.
Background
The intelligent medical treatment is the medical treatment which is universal, personalized and intelligent and realizes the interaction between a patient and medical staff, medical institutions and medical equipment by creating a medical information platform in a health file area and utilizing the technologies of the Internet of things, big data, artificial intelligence and the like. Intelligent medical treatment provides an effective method for medical health services in developing countries, and under the condition of shortage of medical human resources, medical problems in developing countries can be solved through mobile medical treatment.
Along with social development, the constant change of dietary structure and external environment in recent years, the probability of car accidents and diseases is greatly increased, so that the situation of limb movement dysfunction of a patient is greatly increased, and reasonable rehabilitation training can help the patient to rebuild limb movement function to a certain extent.
The traditional rehabilitation training method generally adopts medical personnel to carry out rehabilitation training on patients manually, and the rehabilitation treatment means based on manual assistance has high cost and low efficiency and is difficult to meet the rehabilitation requirements.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent medical rehabilitation auxiliary management system, which comprises: the rehabilitation management platform is in communication connection with each rehabilitation auxiliary device.
The rehabilitation management platform comprises: the device comprises an image processing module, a core point acquisition module, a core point positioning module, an action track recognition module, a rehabilitation training action construction module, a rehabilitation training integration module, a rehabilitation training characteristic fusion module, a rehabilitation training instruction generation module and a database, wherein the modules are in communication connection.
The rehabilitation auxiliary equipment acquires rehabilitation training image data, rehabilitation training stress data and rehabilitation training time data and sends the data to the rehabilitation management platform;
the image processing module divides a rehabilitation training image in the rehabilitation training image data into a plurality of sub-regions, and screens out a plurality of independent sub-regions in the rehabilitation training image, wherein the independent sub-regions are discontinuous with other sub-regions;
the image processing module filters out independent sub-regions with areas larger than a noise threshold value according to the pixel distribution characteristics of the foreground image and the background image in the rehabilitation training image to obtain the rehabilitation training foreground image;
the core point acquisition module acquires limb core points of a patient during corresponding rehabilitation training actions from the rehabilitation training foreground images through mean value clustering;
the core point positioning module acquires the confidence coefficient of each limb core point and the first rehabilitation coordinate position of each limb core point in a first rehabilitation coordinate system, and then the first rehabilitation coordinate position of each limb core point is mapped to a second rehabilitation coordinate system through a coordinate mapping function to obtain a second rehabilitation coordinate position;
the motion track recognition module maps each limb core point to a corresponding motion track according to the second rehabilitation coordinate position of each limb core point so as to obtain a motion core sequence corresponding to the rehabilitation training motion;
the rehabilitation training action construction module constructs rehabilitation training actions according to the action core sequence and the rehabilitation training action construction function to obtain corresponding rehabilitation training actions;
the rehabilitation training integration module sorts the rehabilitation training actions corresponding to each rehabilitation training image in the rehabilitation training image data according to the time sequence to obtain a rehabilitation training action set;
the rehabilitation training characteristic fusion module extracts multidimensional action characteristics of a rehabilitation training action set, extracts multidimensional time characteristics of rehabilitation training time data and then extracts multidimensional stress characteristics of rehabilitation training stress data;
the rehabilitation training feature fusion module performs multi-dimensional feature fusion on the multi-dimensional action feature, the multi-dimensional time feature and the multi-dimensional stress feature in a multi-dimensional space to obtain a multi-dimensional fusion feature;
the rehabilitation training instruction generation module carries out angle and strength decomposition according to the multi-dimensional fusion characteristics to generate a rehabilitation training instruction, then carries out mapping matching on the rehabilitation training instruction and the basic information of the patient to obtain rehabilitation training data of the corresponding patient and stores the rehabilitation training data in the database.
According to a preferred embodiment, the rehabilitation assisting device is used for assisting a nursing staff in rehabilitation training of a patient, and comprises: an upper limb rehabilitation robot, a lower limb rehabilitation robot, an auxiliary walking rehabilitation robot and an exoskeleton rehabilitation robot.
According to a preferred embodiment, the rehabilitation training image data comprises a plurality of rehabilitation training images for recording rehabilitation training movements, each rehabilitation training image corresponding to a rehabilitation training movement.
According to a preferred embodiment, the patient basic information comprises: name, gender, hospital bed number and type of rehabilitation.
According to a preferred embodiment, the first rehabilitation coordinate system is a coordinate system with a rehabilitation assistance device center point as a coordinate origin, and the second rehabilitation coordinate system is a coordinate system with a geodetic center point as a coordinate origin.
According to a preferred embodiment, the limb core points are key points for identifying a rehabilitation training action, and the confidence of the limb core points is used for indicating the probability that the corresponding limb core points are correctly identified.
According to a preferred embodiment, the rehabilitation training stress data comprises stress data for each rehabilitation training action performed by the patient while performing the rehabilitation training.
According to a preferred embodiment, the rehabilitation training comprises a number of rehabilitation training actions ordered in time.
According to a preferred embodiment, the rehabilitation training instruction generating module performing angle and force decomposition according to the multi-dimensional fusion features to generate the rehabilitation training instruction comprises:
the rehabilitation training instruction generation module acquires a rehabilitation gravitation vector generated by the nursing staff to the second rehabilitation coordinate system in each rehabilitation training action in the rehabilitation training according to the multi-dimensional fusion characteristics;
the rehabilitation training instruction generation module acquires a rehabilitation repulsion vector generated by the patient to the second rehabilitation coordinate system in each rehabilitation training action in the rehabilitation training according to the multi-dimensional stress characteristics in the multi-dimensional fusion characteristics;
the rehabilitation training instruction generation module carries out synthetic operation through the rehabilitation attraction force vector and the rehabilitation repulsion force vector to obtain a rehabilitation resultant force vector of each rehabilitation training action;
the rehabilitation training instruction generation module calculates a rehabilitation training action angle and a rehabilitation training action strength of each rehabilitation training action according to the rehabilitation resultant force vector of each rehabilitation training action, and generates a training parameter of each rehabilitation training action according to the rehabilitation training action angle and the rehabilitation training action strength;
the rehabilitation training instruction generation module generates rehabilitation training instructions according to the training parameters of each rehabilitation training action.
According to a preferred embodiment, the rehabilitation training action construction module for constructing the rehabilitation training action according to the action core sequence and the rehabilitation training action construction function to obtain the rehabilitation training action comprises:
the rehabilitation training action construction module extracts a second rehabilitation position coordinate of each limb core point in the action core sequence according to the action core sequence;
the rehabilitation training action construction module acquires a rehabilitation training action track vector according to the second rehabilitation position coordinate of each limb core point in the action core sequence;
the rehabilitation training action construction module calculates the variance of the rehabilitation training action track vector according to the rehabilitation training action track vector to obtain a rehabilitation training action variance vector;
the rehabilitation training action construction module compares each variance in the rehabilitation training action variance vector with a variance threshold value, and extracts a second rehabilitation coordinate position of the limb core point with the variance larger than the variance threshold value as a feature vector;
the rehabilitation training action construction module processes all feature vectors of the limb core points with the variance larger than the variance threshold value to obtain rehabilitation training action vectors;
and the rehabilitation training action construction module constructs rehabilitation training actions according to the rehabilitation training action vector and the rehabilitation training action construction function to obtain the rehabilitation training actions.
According to a preferred embodiment, after the rehabilitation management platform generates rehabilitation training data, the nursing staff inputs basic information of the patient in the rehabilitation auxiliary device to generate a rehabilitation training request;
the rehabilitation auxiliary equipment sends a rehabilitation training request to a rehabilitation management platform;
the rehabilitation management platform calls corresponding rehabilitation training data from the database according to the rehabilitation training request, acquires a rehabilitation training instruction in the rehabilitation training data and sends the rehabilitation training instruction to the rehabilitation auxiliary equipment;
the rehabilitation assistance device performs rehabilitation training on the patient in response to the received rehabilitation training instructions.
The invention has the following beneficial effects: the rehabilitation training image data of gathering the rehabilitation auxiliary device through the rehabilitation management platform, the rehabilitation training atress data and the rehabilitation training time data carry out analysis processes in order to obtain corresponding patient's rehabilitation training instruction, and map it and patient disease data and match in order to utilize the rehabilitation auxiliary device to assist nursing staff to carry out rehabilitation training to the patient when carrying out rehabilitation training to this patient next time, thereby the burden of nursing staff has been alleviateed, make nursing staff can accomplish the work that needs to be close to the patient and go on when rehabilitation robot assists the patient to carry out rehabilitation training, supervise the treatment process, the operating efficiency of rehabilitation training has been improved.
Drawings
Fig. 1 is a block diagram illustrating an intelligent medical rehabilitation assistance management system according to an exemplary embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various devices, elements, components or elements, these devices, elements, components or elements should not be limited by these terms. These terms are only used to distinguish one device, element, component or element from another device, element, component or element.
Referring to fig. 1, in one embodiment, the intelligent medical rehabilitation assistance management system may include: the rehabilitation management platform is in communication connection with each rehabilitation auxiliary device.
The rehabilitation assisting device is used for assisting a nursing person to carry out rehabilitation training on a patient, and comprises: an upper limb rehabilitation robot, a lower limb rehabilitation robot, an auxiliary walking rehabilitation robot and an exoskeleton rehabilitation robot.
The rehabilitation assisting device collects rehabilitation training image data, rehabilitation training stress data and rehabilitation training time data and sends the data to the rehabilitation management platform.
The rehabilitation management platform comprises: the device comprises an image processing module, a core point acquisition module, a core point positioning module, an action track recognition module, a rehabilitation training action construction module, a rehabilitation training integration module, a rehabilitation training characteristic fusion module, a rehabilitation training instruction generation module and a database, wherein the modules are in communication connection.
The image processing module divides the rehabilitation training image in the rehabilitation training image data into a plurality of sub-regions, and screens out a plurality of independent sub-regions in the rehabilitation training image, wherein the independent sub-regions are discontinuous with other sub-regions.
And the image processing module filters out independent sub-regions with areas larger than a noise threshold value according to the pixel distribution characteristics of the foreground image and the background image in the rehabilitation training image to obtain the rehabilitation training foreground image.
The core point acquisition module acquires limb core points of the patient during corresponding rehabilitation training actions from the rehabilitation training foreground images through mean value clustering.
The core point positioning module acquires the confidence coefficient of each limb core point and the first rehabilitation coordinate position of each limb core point in the first rehabilitation coordinate system, and then the first rehabilitation coordinate position of each limb core point is mapped to the second rehabilitation coordinate system through the coordinate mapping function to obtain the second rehabilitation coordinate position.
And the action track recognition module maps each limb core point to a corresponding action track according to the second rehabilitation coordinate position of each limb core point so as to acquire an action core sequence corresponding to the rehabilitation training action.
And the rehabilitation training action construction module constructs rehabilitation training actions according to the action core sequence and the rehabilitation training action construction function to obtain corresponding rehabilitation training actions.
The rehabilitation training integration module sorts the rehabilitation training actions corresponding to each rehabilitation training image in the rehabilitation training image data according to the time sequence to obtain a rehabilitation training action set.
The rehabilitation training characteristic fusion module extracts multidimensional action characteristics of a rehabilitation training action set, extracts multidimensional time characteristics of rehabilitation training time data and then extracts multidimensional stress characteristics of rehabilitation training stress data.
And the rehabilitation training characteristic fusion module performs multi-dimensional characteristic fusion on the multi-dimensional action characteristic, the multi-dimensional time characteristic and the multi-dimensional stress characteristic in a multi-dimensional space to obtain a multi-dimensional fusion characteristic.
The rehabilitation training instruction generation module carries out angle and strength decomposition according to the multi-dimensional fusion characteristics to generate a rehabilitation training instruction, then carries out mapping matching on the rehabilitation training instruction and the basic information of the patient to obtain rehabilitation training data of the corresponding patient and stores the rehabilitation training data in the database.
In one embodiment, a rehabilitation assistance method for smart medical treatment may include:
s1, the nursing staff sends the basic information of the patient to the rehabilitation management platform through the rehabilitation auxiliary device before the rehabilitation training of the patient; when a nursing person carries out rehabilitation training on a patient, the nursing person connects the rehabilitation auxiliary device with the rehabilitation part of the patient, and the rehabilitation auxiliary device collects rehabilitation training image data, rehabilitation training stress data and rehabilitation training time data and sends the data to the rehabilitation management platform.
The rehabilitation training image data comprises a plurality of rehabilitation training images, the rehabilitation training images are used for recording rehabilitation training actions, and each rehabilitation training image corresponds to one rehabilitation training action.
The basic information of the patient includes: name, gender, hospital bed number and type of rehabilitation.
The rehabilitation training stress data includes stress data for each rehabilitation training action performed by the patient while performing rehabilitation training.
The rehabilitation training time data are absolute time and relative time of each rehabilitation training action when the nursing staff carries out rehabilitation training, the absolute time is a time point when each rehabilitation training action is executed, and the relative time is a time period when each rehabilitation training action lasts.
The nursing staff is a medical staff for the rehabilitation training of the patient.
The rehabilitation part is a part for executing rehabilitation training and comprises: upper, lower and waist.
The rehabilitation assisting device is used for assisting a nursing person to carry out rehabilitation training on a patient, and comprises: an upper limb rehabilitation robot, a lower limb rehabilitation robot, an auxiliary walking rehabilitation robot and an exoskeleton rehabilitation robot.
The rehabilitation training comprises a plurality of rehabilitation training actions which are sequenced according to time.
S2, dividing a rehabilitation training image in the rehabilitation training image data into a plurality of sub-regions by an image processing module of the rehabilitation management platform, and screening out a plurality of independent sub-regions in the rehabilitation training image; and the image processing module filters out independent sub-regions with areas larger than a noise threshold value according to the pixel distribution characteristics of the foreground image and the background image in the rehabilitation training image to obtain the rehabilitation training foreground image.
In particular, an individual subregion is a subregion that is not contiguous with other subregions.
Optionally, the rehabilitation training foreground image is a rehabilitation training image with the background image removed, and the influence of the background of the rehabilitation training image is removed in the process of recognizing the rehabilitation training action, so that the accuracy of recognizing the rehabilitation training action is improved.
And S3, the core point acquisition module acquires the limb core points of the patient in the corresponding rehabilitation training action from the rehabilitation training foreground images through mean value clustering.
Optionally, the limb core points are key points for identifying the rehabilitation training action, and the confidence of the limb core points is used for indicating the probability that the corresponding limb core points are correctly identified.
S4, the core point positioning module obtains the confidence coefficient of each limb core point and the first rehabilitation coordinate position of each limb core point in the first rehabilitation coordinate system, and then the first rehabilitation coordinate position of each limb core point is mapped to the second rehabilitation coordinate system through the coordinate mapping function to obtain the second rehabilitation coordinate position.
Optionally, mapping the first rehabilitation coordinate position of each limb core point to a second rehabilitation coordinate system to obtain a second rehabilitation coordinate position comprises:
in particular, the amount of the solvent to be used,
a second rehabilitation coordinate position of the ith limb core point in a second rehabilitation coordinate system, plo (.) is a coordinate mapping function,
is the first rehabilitation coordinate position of the ith limb core point in the first rehabilitation coordinate system.
Optionally, the first rehabilitation coordinate system is a coordinate system with a rehabilitation assistance device center point as a coordinate origin, and the second rehabilitation coordinate system is a coordinate system with a geodetic center point as a coordinate origin.
The limb core points are key points for recognizing rehabilitation training actions, and the confidence degrees of the limb core points are used for indicating the probability that the corresponding limb core points are correctly recognized.
And S5, the action track recognition module maps each limb core point to a corresponding action track according to the second rehabilitation coordinate position of each limb core point so as to acquire an action core sequence corresponding to the rehabilitation training action.
Optionally, the second rehabilitation coordinate position of each limb core point is acquired and arranged according to the position sequence, so as to form an action core sequence of the action track.
And S6, the rehabilitation training action construction module constructs rehabilitation training actions according to the action core sequence and the rehabilitation training action construction function to obtain corresponding rehabilitation training actions.
Specifically, the rehabilitation training action construction module extracts a second rehabilitation position coordinate of each limb core point in the action core sequence according to the action core sequence.
And the rehabilitation training action construction module acquires a rehabilitation training action track vector according to the second rehabilitation position coordinate of each limb core point in the action core sequence.
The rehabilitation training action construction module calculates the variance of the rehabilitation training action track vector according to the rehabilitation training action track vector to obtain a rehabilitation training action variance vector.
And the rehabilitation training action construction module compares each variance in the rehabilitation training action variance vector with a variance threshold value, and extracts a second rehabilitation coordinate position of the limb core point with the variance larger than the variance threshold value as a feature vector.
And the rehabilitation training action construction module processes all the feature vectors of the limb core points with the variance larger than the variance threshold value to obtain the rehabilitation training action vector.
And the rehabilitation training action construction module constructs rehabilitation training actions according to the rehabilitation training action vector and the rehabilitation training action construction function to obtain the rehabilitation training actions.
Specifically, the rehabilitation training action construction module carries out rehabilitation training action construction according to the rehabilitation training action vector and the rehabilitation training action construction function to obtain the rehabilitation training action, and comprises the following steps:
wherein r isiFor the i-th feature vector, v, of the rehabilitation training motion vectoriConfidence degree, alpha, of limb core point corresponding to ith feature vector of rehabilitation training motion vectoriThe number of the characteristic vectors in the rehabilitation training motion vector is n, and the index of the characteristic vector is i.
S7, the rehabilitation training integration module sorts the rehabilitation training actions corresponding to each rehabilitation training image in the rehabilitation training image data according to the time sequence to obtain a rehabilitation training action set.
Acquiring the acquisition time of each rehabilitation training image when acquiring the rehabilitation training images, and sequencing the rehabilitation training images according to the acquisition time of the rehabilitation training images to obtain rehabilitation training image data.
The rehabilitation training integration module acquires the rehabilitation training action corresponding to each rehabilitation training image, and sequences each rehabilitation training action according to the sequence of the acquisition time of the corresponding rehabilitation training image to obtain a rehabilitation training action set.
S8, extracting multi-dimensional action features of a rehabilitation training action set by the rehabilitation training feature fusion module, extracting multi-dimensional time features of rehabilitation training time data, and extracting multi-dimensional stress features of rehabilitation training stress data; and the rehabilitation training characteristic fusion module performs multi-dimensional characteristic fusion on the multi-dimensional action characteristic, the multi-dimensional time characteristic and the multi-dimensional stress characteristic in a multi-dimensional space to obtain a multi-dimensional fusion characteristic.
And S9, the rehabilitation training instruction generation module carries out angle and force decomposition according to the multi-dimensional fusion characteristics to generate a rehabilitation training instruction, and then the rehabilitation training instruction is mapped and matched with the basic information of the patient to obtain rehabilitation training data of the corresponding patient and stored in the database.
The rehabilitation training instruction generation module carries out angle and strength decomposition according to the multidimensional fusion characteristics to generate rehabilitation training instructions and comprises the following steps:
and the rehabilitation training instruction generation module acquires a rehabilitation gravitation vector generated by the nursing staff to the second rehabilitation coordinate system in each rehabilitation training action in the rehabilitation training according to the multi-dimensional fusion characteristics.
And the rehabilitation training instruction generation module acquires a rehabilitation repulsion vector generated by the patient to the second rehabilitation coordinate system in each rehabilitation training action in the rehabilitation training according to the multi-dimensional stress characteristic in the multi-dimensional fusion characteristic.
The rehabilitation training instruction generation module carries out synthesis operation through the rehabilitation attraction force vector and the rehabilitation repulsion force vector to obtain a rehabilitation resultant force vector of each rehabilitation training action.
The rehabilitation training instruction generation module calculates a rehabilitation training action angle and a rehabilitation training action strength of each rehabilitation training action according to the rehabilitation resultant force vector of each rehabilitation training action, and generates a training parameter of each rehabilitation training action according to the rehabilitation training action angle and the rehabilitation training action strength.
The rehabilitation training instruction generation module generates rehabilitation training instructions according to the training parameters of each rehabilitation training action.
After the rehabilitation management platform generates the rehabilitation training data, in one embodiment, the caregiver enters the patient basic information in the rehabilitation assistance device to generate the rehabilitation training request.
The rehabilitation assisting device sends the rehabilitation training request to the rehabilitation management platform.
And the rehabilitation management platform calls corresponding rehabilitation training data from the database according to the rehabilitation training request, acquires a rehabilitation training instruction in the rehabilitation training data and sends the rehabilitation training instruction to the rehabilitation auxiliary equipment.
The rehabilitation assistance device performs rehabilitation training on the patient in response to the received rehabilitation training instructions.
According to the invention, the rehabilitation training image data, the rehabilitation training stress data and the rehabilitation training time data collected by the rehabilitation auxiliary equipment are analyzed and processed through the rehabilitation management platform to obtain the rehabilitation training instruction of the corresponding patient, and are mapped and matched with the patient disease data so as to be convenient for assisting a nursing staff to perform rehabilitation training on the patient by using the rehabilitation auxiliary equipment when the patient is subjected to rehabilitation training next time, so that the burden of the nursing staff is reduced, the nursing staff can complete the work needing to be performed close to the patient while the rehabilitation robot assists the patient to perform rehabilitation training, and the operation efficiency of the rehabilitation training is improved.
Various techniques may be described herein in the general context of software hardware elements or program modules. Generally, these modules include routines, programs, objects, elements, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The terms "module," "functionality," and "component" as used herein generally represent software, firmware, hardware, or a combination thereof. The features of the techniques described herein are platform-independent, meaning that the techniques may be implemented on a variety of computing platforms having a variety of processors.
An implementation of the described modules and techniques may be stored on or transmitted across some form of computer readable media. Computer readable media can include a variety of media that can be accessed by a computing device. By way of example, and not limitation, computer-readable media may comprise "computer-readable storage media" and "computer-readable signal media".
It will be appreciated that embodiments of the invention have been described with reference to different functional blocks for clarity. However, the functionality of each functional module may be implemented in a single module, in multiple modules, or as part of other functional modules, without departing from the invention. For example, functionality illustrated to be performed by a single module may be performed by multiple different modules. Thus, references to specific functional blocks are only to be seen as references to suitable blocks for providing the described functionality rather than indicative of a strict logical or physical structure or organization. Thus, the invention may be implemented in a single module or may be physically and functionally distributed between different modules and circuits.
Although the present invention has been described in connection with some embodiments, it is not intended to be limited to the specific form set forth herein. Rather, the scope of the invention is limited only by the appended claims. The order of features in the claims does not imply any specific order in which the features must be worked. Furthermore, in the claims, the word "comprising" does not exclude other elements, and the indefinite article "a" or "an" does not exclude a plurality.
Claims (8)
1. The utility model provides an intelligent medical treatment rehabilitation assists management system which characterized in that, it includes: the rehabilitation management platform is in communication connection with each rehabilitation auxiliary device;
the rehabilitation management platform comprises: the device comprises an image processing module, a core point acquisition module, a core point positioning module, an action track recognition module, a rehabilitation training action construction module, a rehabilitation training integration module, a rehabilitation training characteristic fusion module, a rehabilitation training instruction generation module and a database, wherein the modules are in communication connection;
the rehabilitation auxiliary equipment acquires rehabilitation training image data, rehabilitation training stress data and rehabilitation training time data and sends the data to the rehabilitation management platform;
the image processing module divides a rehabilitation training image in the rehabilitation training image data into a plurality of sub-regions, and screens out a plurality of independent sub-regions in the rehabilitation training image, wherein the independent sub-regions are discontinuous with other sub-regions;
the image processing module filters out independent sub-regions with areas larger than a noise threshold value according to the pixel distribution characteristics of the foreground image and the background image in the rehabilitation training image to obtain the rehabilitation training foreground image;
the core point acquisition module acquires limb core points of a patient during corresponding rehabilitation training actions from the rehabilitation training foreground images through mean value clustering;
the core point positioning module acquires the confidence coefficient of each limb core point and the first rehabilitation coordinate position of each limb core point in a first rehabilitation coordinate system, and then the first rehabilitation coordinate position of each limb core point is mapped to a second rehabilitation coordinate system through a coordinate mapping function to obtain a second rehabilitation coordinate position;
the motion track recognition module maps each limb core point to a corresponding motion track according to the second rehabilitation coordinate position of each limb core point so as to obtain a motion core sequence corresponding to the rehabilitation training motion;
the rehabilitation training action construction module constructs rehabilitation training actions according to the action core sequence and the rehabilitation training action construction function to obtain corresponding rehabilitation training actions;
the rehabilitation training integration module sorts the rehabilitation training actions corresponding to each rehabilitation training image in the rehabilitation training image data according to the time sequence to obtain a rehabilitation training action set;
the rehabilitation training characteristic fusion module extracts multidimensional action characteristics of a rehabilitation training action set, extracts multidimensional time characteristics of rehabilitation training time data and then extracts multidimensional stress characteristics of rehabilitation training stress data;
the rehabilitation training feature fusion module performs multi-dimensional feature fusion on the multi-dimensional action feature, the multi-dimensional time feature and the multi-dimensional stress feature in a multi-dimensional space to obtain a multi-dimensional fusion feature;
the rehabilitation training instruction generation module carries out angle and force decomposition according to the multi-dimensional fusion characteristics to generate a rehabilitation training instruction, and then carries out mapping matching on the rehabilitation training instruction and the basic information of the patient to obtain rehabilitation training data of the corresponding patient.
2. The system of claim 1, wherein the rehabilitation assistance device is used to assist a caregiver in rehabilitating a patient, comprising: an upper limb rehabilitation robot, a lower limb rehabilitation robot, an auxiliary walking rehabilitation robot and an exoskeleton rehabilitation robot.
3. The system of claim 1 or 2, wherein the rehabilitation regimen comprises a plurality of rehabilitation regimen actions ordered by time.
4. The system of claim 2, wherein the rehabilitation training image data includes a plurality of rehabilitation training images, the rehabilitation training images for recording rehabilitation training movements, one for each rehabilitation training image.
5. The system of claim 4, wherein the rehabilitation training stress data comprises stress data for each rehabilitation training action performed by the patient while performing rehabilitation training.
6. The system of claim 5, wherein the rehabilitation training instruction generating module performing angle and force decomposition according to the multi-dimensional fusion features to generate the rehabilitation training instructions comprises:
the rehabilitation training instruction generation module acquires a rehabilitation gravitation vector generated by the nursing staff to the second rehabilitation coordinate system in each rehabilitation training action in the rehabilitation training according to the multi-dimensional fusion characteristics;
the rehabilitation training instruction generation module acquires a rehabilitation repulsion vector generated by the patient to the second rehabilitation coordinate system in each rehabilitation training action in the rehabilitation training according to the multi-dimensional stress characteristics in the multi-dimensional fusion characteristics;
the rehabilitation training instruction generation module carries out synthetic operation through the rehabilitation attraction force vector and the rehabilitation repulsion force vector to obtain a rehabilitation resultant force vector of each rehabilitation training action;
the rehabilitation training instruction generation module calculates a rehabilitation training action angle and a rehabilitation training action strength of each rehabilitation training action according to the rehabilitation resultant force vector of each rehabilitation training action, and generates a training parameter of each rehabilitation training action according to the rehabilitation training action angle and the rehabilitation training action strength;
the rehabilitation training instruction generation module generates rehabilitation training instructions according to the training parameters of each rehabilitation training action.
7. The system of claim 6, wherein the rehabilitation training action construction module performs rehabilitation training action construction according to the action core sequence and the rehabilitation training action construction function to obtain the rehabilitation training action comprises:
the rehabilitation training action construction module extracts a second rehabilitation position coordinate of each limb core point in the action core sequence according to the action core sequence;
the rehabilitation training action construction module acquires a rehabilitation training action track vector according to the second rehabilitation position coordinate of each limb core point in the action core sequence;
the rehabilitation training action construction module calculates the variance of the rehabilitation training action track vector according to the rehabilitation training action track vector to obtain a rehabilitation training action variance vector;
the rehabilitation training action construction module compares each variance in the rehabilitation training action variance vector with a variance threshold value, and extracts a second rehabilitation coordinate position of the limb core point with the variance larger than the variance threshold value as a feature vector;
the rehabilitation training action construction module processes all feature vectors of the limb core points with the variance larger than the variance threshold value to obtain rehabilitation training action vectors;
and the rehabilitation training action construction module constructs rehabilitation training actions according to the rehabilitation training action vector and the rehabilitation training action construction function to obtain the rehabilitation training actions.
8. The system according to claim 7, wherein the limb core points are key points for identifying a rehabilitation training action, the confidence of the limb core points being indicative of the probability that the respective limb core points are correctly identified.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110093979.1A CN112768034A (en) | 2020-08-24 | 2020-08-24 | Rehabilitation management platform based on medical big data |
| CN202010859972.1A CN111951941B (en) | 2020-08-24 | 2020-08-24 | Intelligent medical rehabilitation auxiliary management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010859972.1A CN111951941B (en) | 2020-08-24 | 2020-08-24 | Intelligent medical rehabilitation auxiliary management system |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110093979.1A Division CN112768034A (en) | 2020-08-24 | 2020-08-24 | Rehabilitation management platform based on medical big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111951941A CN111951941A (en) | 2020-11-17 |
| CN111951941B true CN111951941B (en) | 2021-05-11 |
Family
ID=73360447
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010859972.1A Active CN111951941B (en) | 2020-08-24 | 2020-08-24 | Intelligent medical rehabilitation auxiliary management system |
| CN202110093979.1A Pending CN112768034A (en) | 2020-08-24 | 2020-08-24 | Rehabilitation management platform based on medical big data |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110093979.1A Pending CN112768034A (en) | 2020-08-24 | 2020-08-24 | Rehabilitation management platform based on medical big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111951941B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201611803A (en) * | 2014-07-03 | 2016-04-01 | Teijin Pharma Ltd | Rehabilitation assistance device and program for controlling rehabilitation assistance device |
| US10244990B2 (en) * | 2015-09-30 | 2019-04-02 | The Board Of Trustees Of The University Of Alabama | Systems and methods for rehabilitation of limb motion |
| CN108814894A (en) * | 2018-04-12 | 2018-11-16 | 山东大学 | The upper limb rehabilitation robot system and application method of view-based access control model human body pose detection |
| CN109102857B (en) * | 2018-05-31 | 2021-08-27 | 杭州同绘科技有限公司 | Intelligent limb rehabilitation training system and method |
| CN108986884A (en) * | 2018-05-31 | 2018-12-11 | 杭州同绘科技有限公司 | The training system and method that a kind of balanced rehabilitation and cognitive rehabilitation blend |
| CN109243572B (en) * | 2018-11-08 | 2021-09-21 | 中科数字健康科学研究院（南京）有限公司 | Accurate motion evaluation and rehabilitation training system |
| CN111345823B (en) * | 2018-12-24 | 2023-05-09 | 中国移动通信有限公司研究院 | Remote exercise rehabilitation method, device and computer readable storage medium |
| CN110215676A (en) * | 2019-06-17 | 2019-09-10 | 上海大学 | A kind of upper limb both arms rehabilitation training man-machine interaction method and system |
| CN111145865A (en) * | 2019-12-26 | 2020-05-12 | 中国科学院合肥物质科学研究院 | Vision-based hand fine motion training guidance system and method |
-
2020
- 2020-08-24 CN CN202010859972.1A patent/CN111951941B/en active Active
- 2020-08-24 CN CN202110093979.1A patent/CN112768034A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN112768034A (en) | 2021-05-07 |
| CN111951941A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334573B (en) | Human motion state discrimination method based on dense connection convolutional neural network | |
| CN112861624A (en) | Human body posture detection method, system, storage medium, equipment and terminal | |
| CN110490109B (en) | Monocular vision-based online human body rehabilitation action recognition method | |
| CN107330249A (en) | A kind of Parkinsonian symptoms area of computer aided method of discrimination based on KINECT skeleton datas | |
| CN113723312B (en) | Rice disease identification method based on visual transducer | |
| CN111951940A (en) | Intelligent medical rehabilitation assisting method | |
| CN113435236A (en) | Home old man posture detection method, system, storage medium, equipment and application | |
| CN115462783A (en) | Infant crawling posture analysis system based on skeleton key point detection | |
| CN114099234A (en) | Intelligent rehabilitation robot data processing method and system for assisting rehabilitation training | |
| CN110321827A (en) | A kind of pain level appraisal procedure based on face pain expression video | |
| CN113229807A (en) | Human body rehabilitation evaluation device, method, electronic device and storage medium | |
| CN114049683A (en) | Post-healing rehabilitation auxiliary detection system, method and medium based on three-dimensional human skeleton model | |
| CN111639533A (en) | Gait feature-based posture detection method, device, equipment and storage medium | |
| Ong et al. | Investigation of feature extraction for unsupervised learning in human activity detection | |
| CN111951941B (en) | Intelligent medical rehabilitation auxiliary management system | |
| CN109634419A (en) | The recognition methods of healing robot motion intention and its computer readable storage medium | |
| CN111951950B (en) | Three-dimensional data medical classification system based on deep learning | |
| CN117237351A (en) | Ultrasonic image analysis method and related device | |
| CN117392746A (en) | Rehabilitation training evaluation assisting method, device, computer equipment and storage medium | |
| Hai et al. | PCA-SVM algorithm for classification of skeletal data-based eigen postures | |
| CN116543455A (en) | Method, equipment and medium for establishing parkinsonism gait damage assessment model and using same | |
| CN113487579B (en) | Multi-mode migration method for automatically sketching model | |
| CN113768471A (en) | Parkinson disease auxiliary diagnosis system based on gait analysis | |
| Katiyar et al. | Clinical gait data analysis based on spatio-temporal features | |
| CN112861699A (en) | Method for estimating height of human body in any posture based on single depth image and multi-stage neural network |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Jianguo Inventor after: Zhao Jiajing Inventor after: Liu Yingsen Inventor before: Liu Yingsen |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210413 Address after: 200333 no.1291 Jiangning Road, Putuo District, Shanghai Applicant after: SHANGHAI PUTUO DISTRICT PEOPLE'S Hospital Address before: No.338, Qiaoge Road, Xuefeng, Lizhou District, Guangyuan, Sichuan 610000 Applicant before: GUANGYUAN LIANGZHIHUI TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |