CN113362925A - Automatic good limb position control method and device - Google Patents

Automatic good limb position control method and device Download PDF

Info

Publication number
CN113362925A
CN113362925A CN202110728780.1A CN202110728780A CN113362925A CN 113362925 A CN113362925 A CN 113362925A CN 202110728780 A CN202110728780 A CN 202110728780A CN 113362925 A CN113362925 A CN 113362925A
Authority
CN
China
Prior art keywords
user
limb position
good limb
good
position control
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.)
Granted
Application number
CN202110728780.1A
Other languages
Chinese (zh)
Other versions
CN113362925B (en
Inventor
陈霞
宋可鑫
刘霞
梁芳
崔全芹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Provincial Hospital Affiliated to Shandong First Medical University
Original Assignee
Shandong Provincial Hospital Affiliated to Shandong First Medical University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong Provincial Hospital Affiliated to Shandong First Medical University filed Critical Shandong Provincial Hospital Affiliated to Shandong First Medical University
Priority to CN202110728780.1A priority Critical patent/CN113362925B/en
Publication of CN113362925A publication Critical patent/CN113362925A/en
Application granted granted Critical
Publication of CN113362925B publication Critical patent/CN113362925B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Abstract

The embodiment of the specification discloses an automatic limb position control method and equipment, wherein the method comprises the following steps: the controller of the mattress sends a good limb position use request of a user to the medical care node, so that the medical care node can call case information of the user conveniently, and when the medical care node confirms the good limb position use request, the good limb position control platform determines a good limb position control scheme of the user according to the case information and the body characteristic information of the user; the good limb position control platform determines a region to be controlled of the mattress and a control instruction according to a good limb position control scheme, wherein the control instruction comprises inflation or deflation operation of the region to be controlled, inflation time or deflation time of the region to be controlled and inflation quantity of the region to be controlled; the good limb position control platform sends the good limb position control scheme to the controller of the mattress, so that the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, and a user is assisted to complete the good limb position control. And a customized good limb position control scheme is generated according to the actual conditions of different users, so that the automatic control of the good limb position is realized.

Description

Automatic good limb position control method and device
Technical Field
The specification relates to the technical field of medical treatment, in particular to an automatic good limb position control method and device.
Background
Limb posture is one of the important measures to prevent spasm in early stages, and is to maintain the limb in a certain position or posture for good function. The limb position can stabilize the joint after hemiplegia, can effectively prevent the typical spasm pattern of upper limb flexor and lower limb extensor, and is one of the methods for preventing the pathological movement pattern from appearing later. In addition, spasm (upper limb flexor and lower limb extensor) can occur in the process of recovering functions of limbs of patients with nervous system diseases (mainly including cerebrovascular accidents, brain trauma and the like), and the abnormal posture generated by the spasm affects the life quality of the patients, so the placement, maintenance and regular replacement of the good limb positions of the patients with the diseases play an important role in recovering the diseases.
At present, the good limb position of a patient is mostly required to be adjusted by the assistance of families and nurses, and the good limb position is fixed by using bedclothes, pillows and the like in an auxiliary manner, so that extra workload and larger physical load are added to the families and nurses, and an automatic control method for the good limb position is lacked.
Disclosure of Invention
One or more embodiments of the present disclosure provide an automatic Limb position control method and apparatus, which are used to solve the following technical problems: in the prior art, articles such as a pillow are depended on for placement and fixation at a good known position, and a method for automatically controlling the good limb position is lacked.
One or more embodiments of the present disclosure adopt the following technical solutions:
one or more embodiments of the present disclosure provide a method for automatic orthobaric control, the method comprising: a controller of the mattress sends a request for using the good limb position of a user to a medical care node so that the medical care node can call case information of the user conveniently, wherein the request comprises user identification and body characteristic information; when the medical care node confirms the good limb position use request, the good limb position control platform determines a good limb position control scheme of the user according to the case information and the body characteristic information of the user, wherein the good limb position control scheme comprises the inflation quantity of an area to be controlled, a good limb position placing position and time corresponding to the good limb position placing position; the good limb position control platform determines a region to be controlled of the mattress and a control instruction according to the good limb position control scheme, wherein the control instruction comprises the inflation or deflation operation of the region to be controlled, the inflation time or deflation time of the region to be controlled and the inflation quantity of the region to be controlled; the good limb position control platform sends the good limb position control scheme to a controller of the mattress, so that the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, and the user is assisted to complete the good limb position control.
Further, prior to sending the orthostatic control scheme to the controller of the mattress, the method further comprises: setting a body placing area and a body adjacent area of the mattress to be controlled, so that a controller of the mattress controls the body adjacent area to execute the control instruction, and assisting the user to complete good limb position control; wherein the area to be controlled includes: a left shoulder region, a right shoulder region, a left upper limb region, a right upper limb region, a left lower limb region, and a right lower limb region, each region comprising one or more of the body placement regions and at least one of the body proximity regions.
Further, the determining a good limb position control scheme of the user according to the case information and the body characteristic information of the user specifically includes: constructing an initial neural network model, acquiring medical institution case information, body characteristic information and relevant data of a good limb position control scheme based on a web crawler technology, and training the initial neural network model according to the medical institution case information, the body characteristic information and the relevant data of the good limb position control scheme to obtain a good limb position control model meeting requirements; and inputting the case information and the physical characteristic information of the user into the satisfactory limb position control model meeting the requirements, and determining a satisfactory limb position control scheme of the user.
Further, according to the medical institution case information, the physical characteristic information and the relevant data of the good limb position control scheme, training the initial neural network model to obtain a satisfactory limb position control model meeting the requirements, specifically comprising: constructing a data set by using a plurality of groups of medical institution case information, body characteristic information and data of a good limb position control scheme, and dividing the data set into a training set and a verification set according to a preset proportion; constructing a network structure of a convolutional neural network model, wherein 0-95 layers of the convolutional neural network are deep convolutional layers and are composed of convolutional blocks and single-layer convolutional layers, and 96-126 layers of the convolutional neural network are characteristic interaction layers; presetting training parameters, wherein the training parameters comprise: inputting medical institution case information, body characteristic information and relevant data of a good limb position control scheme in a training set into the convolutional neural network model for cyclic iterative training, wherein the medical institution case information, the body characteristic information and the relevant data of the good limb position control scheme are input into the convolutional neural network model; inputting medical institution case information, body characteristic information and a good limb position control scheme concentrated in verification into a good limb position control model, recording a loss function value in the model training process, adjusting the connection weight among all neurons in a neural network model according to the loss function value, and obtaining the good limb position control model meeting the requirements when the loss function value reaches a preset loss function threshold or the training times reaches a preset maximum iteration times; wherein the loss function is a cross entropy loss function.
Further, the determining a good limb position control scheme of the user according to the case information and the body characteristic information of the user specifically includes: determining a first good limb position control scheme of the user according to the body characteristic information of the user, wherein the body characteristic information comprises: a height of the user and a weight of the user, the first ortholimb control scheme comprising: placing the initial position of the user and the inflation amount of the area to be controlled; the determining a first good limb position control scheme of the user according to the body feature information of the user specifically includes: presetting a relation between a body index and the inflation quantity, wherein the body index is a ratio of the weight of the user to the height square of the user; when the body index is smaller than a first preset threshold value, the inflation amount is a first inflation amount; when the body index is larger than the first preset threshold and smaller than a second preset threshold, the inflation amount is a second inflation amount; when the body index is larger than the second preset threshold value, the inflation intensity is a third inflation amount; the first inflation amount is greater than the second inflation amount, and the second inflation amount is greater than the third inflation amount.
Further, after the determining the first ortholimb control scheme of the user according to the physical characteristic information of the user, the method further includes: and determining a good limb position use type and a corresponding second good limb position control scheme according to the case information of the user, wherein the second good limb position control scheme comprises a good limb position placing position and time of the good limb position placing position, and the different good limb position use types correspond to different good limb position placing positions and time of the good limb position placing position.
Further, the determining the area to be controlled of the mattress and the control instruction according to the favorable limb position control scheme specifically includes: according to the good limb position placing position in the good limb position control scheme, determining the area to be controlled and the mattress inflation or deflation operation in the control instruction, wherein the good limb position placing position comprises the following steps: supine position, lateral position and lateral position; and determining the mattress inflation time according to the position change time in the favorable limb position control scheme.
Further, before the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, the method further comprises: the controller of the mattress constructs a coordinate system by taking the preset position of the mattress as an origin, and records a first position coordinate of a first preset part and a second position coordinate of a second preset part of the user; after the assisting the user in completing orthostatic control, the method further comprises: the controller of the mattress records a third position coordinate of the first preset part and a fourth position coordinate of the second preset part; judging whether the user correctly uses the good limb position according to the first position coordinate, the second position coordinate, the third position coordinate and the fourth position coordinate, and specifically comprising the following steps: determining the position condition of the user before completing the good limb position according to the difference value of the first position coordinate and the second position coordinate, wherein the position condition is used for reflecting the position of each part of the body before the user completes the good limb position; determining the position condition of the user after completing the good limb position according to the difference value of the third position coordinate and the fourth position coordinate, wherein the position condition is used for reflecting the position of each part of the body of the user after completing the good limb position; and judging whether the user moves according to the good limb position control scheme and whether the current good limb position of the user is in a correct position according to the position condition of the user before the user finishes the good limb position and the position condition of the user after the user finishes the good limb position.
Further, before the controller of the mattress controls the region to be controlled of the mattress according to the control instruction, the good limb position control platform obtains a first position of a bone key point at a first preset time according to a human body key point prediction network, and specifically includes: acquiring image data of a user before completing limb position control, inputting the image data into a human body key point prediction network, outputting prediction probability that each pixel point in the image is a skeleton key point, forming a thermodynamic diagram, converting the thermodynamic diagram into numerical coordinates of the skeleton key point by a soft-argmax function, and outputting the numerical coordinates, wherein the human body key point prediction network is obtained by introducing a CBAM (cubic cellular amplitude modulation) attention model based on a CPN (coherent population network) feature pyramid network, and the CPN feature pyramid network comprises a GlobalNet model and a RefineNet model; obtaining a predicted position of the bone key point according to a first position and an instantaneous speed at a first preset moment, and obtaining the first position and the predicted position through Q-AQ1+ BP + C gives the boneLocation trajectories of iliac keypoints; the system comprises a skeleton key point, a state transformation matrix and a processing unit, wherein Q is a feature vector and is used for representing state information of the skeleton key point at a second preset moment, the state information of the skeleton key point comprises speed information of the skeleton key point and coordinate information of the skeleton key point, A is the state transformation matrix and is used for associating the state information of the skeleton key point at the first preset moment to the state of the skeleton key point at the second preset moment, and the first preset moment is a previous moment of the second preset moment; and judging whether the user correctly uses the good limb position according to the position track of the bone key point.
One or more embodiments of the present disclosure provide an automatic posture control apparatus, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to: a controller of the mattress sends a request for using the good limb position of a user to a medical care node so that the medical care node can call case information of the user conveniently, wherein the request comprises user identification and body characteristic information; when the medical care node confirms the good limb position use request, the good limb position control platform determines a good limb position control scheme of the user according to the case information and the body characteristic information of the user, wherein the good limb position control scheme comprises the air inflation amount of an area to be controlled, good limb position placing position information and time corresponding to the good limb position placing position; the good limb position control platform determines a region to be controlled of the mattress and a control instruction according to the good limb position control scheme, wherein the control instruction comprises the inflation or deflation operation of the region to be controlled, the inflation time or deflation time of the region to be controlled and the inflation quantity of the region to be controlled; the good limb position control platform sends the good limb position control scheme to a controller of the mattress, so that the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, and the user is assisted to complete the good limb position control.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects: the corresponding good limb position control scheme is determined according to the case information and the body characteristic information of the user, the exclusive good limb position customization scheme of the user is generated according to the actual situation of the user, the region to be controlled of the mattress and the control instruction are determined according to the good limb position control scheme, and the inflation or deflation operation of the region to be controlled is achieved through the mattress controller so as to achieve the technical effect of helping the user to achieve the automatic good limb position control.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort. In the drawings:
fig. 1 is a diagram illustrating an application scenario of an automatic orthotopic control method according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of an automatic orthotopic control method provided in an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of a region to be controlled of a mattress provided by an embodiment of the present disclosure;
FIG. 4 is a schematic view of a left lower limb area provided by an embodiment of the present disclosure;
FIG. 5 is a diagram of the position relationship between a patient and a mattress provided in an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an automatic limb position control device according to an embodiment of the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present specification without any creative effort shall fall within the protection scope of the present specification.
Limb posture is a temporary posture designed for the needs of treatment, care and rehabilitation, and is one of the important measures for preventing spasm in early stage. The limb position can stabilize the joint after hemiplegia, can effectively prevent the typical spasm pattern of upper limb flexor and lower limb extensor, and is one of the methods for preventing the pathological movement pattern from appearing later. Clinically, the requirement for good limb position is different according to the different disease conditions of patients. For example, before the patients are recovered from anesthesia, the patients need to adopt lateral clinostatism in different directions according to different surgical sites, so that the secretion and vomit in the oral cavity can easily flow out, and the vomit backflow caused by the anesthetic can be prevented from causing asphyxia; for example, a cardiopulmonary resuscitation patient should be kept in a flat lying state, and the head position should be kept in a backward leaning state to ensure that the respiratory tract of the patient is smooth; for example, also stroke patients, the best position is sitting on a chair if the patient is a conscious stroke patient, and the best position is lying down if the patient is a comatose stroke patient; for another example, stroke patients usually suffer from sensory disorders, limb disorders and cognitive disorders of different degrees, which affect the self-care ability and the living ability of the patients, and for stroke patients, scientific limb position arrangement is required for rehabilitation nursing. For patients with hemiplegia due to cerebral infarction, the limb position can improve limb dysfunction of different degrees left by the patients after cerebral infarction, and can reduce heavy burden of individuals, families and society.
An embodiment of the present specification provides an automatic Limb position control method, and fig. 1 is an application scenario diagram of the Limb position control method provided in the embodiment of the present specification. As shown in fig. 1, the limb position control system comprises a limb position control platform 1, a medical care node 2 and a controller 3 of a mattress, wherein the limb position control platform comprises a server 11. The patient triggers the operation of using good limb position on mattress controller 3, controller 3 of mattress generates good limb position application request, and send good limb position application request to medical care node 2 department, medical care node 2 confirms good limb position application request of patient, and call patient's case information according to application request, send case information and confirmed good limb position application request to good limb position control platform 1, server 11 generates good limb position control scheme, and confirm the mattress and wait to control regional and control command according to good limb position control scheme, send good limb position control scheme to controller 3 of mattress, the controller of mattress waits to control the region according to control command control mattress, assist the patient to accomplish the limb position control.
Fig. 2 is a schematic flow chart of an automatic Limb position control method according to an embodiment of the present disclosure, and as shown in fig. 2, the automatic Limb position control method mainly includes:
step S201, the mattress controller sends a request for using the good limb position of the user to the medical care node, so that the medical care node can call the case information of the user, where the request includes the user identification and the physical characteristic information. It should be noted that the user identification refers to an identification of a patient to use a good limb position, and may be an identification number or other unique identification, which is not specifically limited in this specification. In addition, the body characteristic information is acquired by an information acquisition module of the mattress, and the body characteristic information comprises the height, the weight, the trunk length, the limb length, the shoulder width and other information of the patient. It should be noted that, the physical characteristic information of different patients is different, and after the physical characteristic information is collected, a good limb position use scheme can be customized according to the physical characteristics of the patients, so that better use experience is brought to the patients, and a better treatment effect can be further obtained.
In one embodiment of the present specification, the user triggering the operation using the good limb position may be a family member of the patient, or a caregiver of the patient, or the patient himself or herself may trigger the operation using the good limb position when the patient is awake. In addition, the triggering operation of the user can be in a mode of clicking a button of the mattress controller or clicking a touch screen of the mattress controller, and can be in a voice recognition mode, so that the use of the user is facilitated.
In an embodiment of the present specification, after the mattress controller sends the request for good limb position use to the medical care node, the medical care node calls the case information of the user according to the user identity in the request for good limb position use, where it needs to be described that the case information of the user includes the past medical history, the treatment process record, and the like. Through the past patient history in the user case information, the good limb position using scheme can be adjusted according to the actual situation of the patient. For example, patient a is a surgical patient and needs to lie on the left side and the right side, but the past medical history of patient a shows that the left lower limb has been operated half year ago and stress is to be avoided, so for patient a, the right side lying is adopted as the good limb position using method to prevent asphyxia caused by vomit after aspiration.
Step S202, when the medical care node confirms the good limb position use request, the good limb position control platform determines a good limb position control scheme of the user according to the case information and the body characteristic information of the user, wherein the good limb position control scheme comprises the air inflation amount of the area to be controlled, good limb position placing position information and time corresponding to the good limb position placing position.
In an embodiment of the present specification, after receiving a good limb position use request of a user, a medical care node confirms the good limb position use request of the user, and the good limb position control platform determines a good limb position control scheme of the user according to case information and body characteristic information of the user based on the confirmation of the medical care node on the user use request. It should be noted that the medical care node may determine whether the user is suitable for using the good limb position at the present stage according to the actual situation of the user, and if it is determined that the user is suitable for using the good limb position, the medical care node may confirm the request for using the good limb position of the user.
In an embodiment of the present specification, the good limb position control platform may determine a good limb position control scheme for use according to the case information and the physical characteristic information of the user, where the control scheme includes a good limb position placing position, it should be noted that the good limb position placing position includes a supine position and a lateral position, and the lateral position further includes a healthy lateral position and an affected lateral position, where the affected lateral position may be one side of the user that is unconscious, or one side of the post-operative surgical site. Next, taking a patient with hemiplegia due to cerebral infarction as an example, the standard of the placement position of the limbs will be described, and the standard placement of the supine position will be described first. The head of the patient is padded with a thin pillow, the shoulder blade and the upper limb of the patient are padded with a long pillow, the upper arm is rotated backwards and abducted by 20-40 degrees, the elbow and the wrist are stretched, the fingers are stretched, the palm is upward, the pillows are placed under the hip, the hip and the outer side of the thigh, the knee is padded up slightly, and the toe is upward. Secondly, the standard laying position of the affected side lying position is to keep the affected side down and the healthy side up, the pillow for head and the pillow for back and back are to keep the affected side lying, the affected arm stretches forwards and rotates backwards after abduction, the affected shoulder extends forwards, the forearm rotates backwards, the upper limb and the trunk are 90 degrees, the elbow and the wrist are both straightened, the palm center is upward, the affected lower limb slightly bends and is placed on the bed, the healthy leg bends hip and bends knee forwards and is placed on the long pillow, the healthy upper limb relaxes and is placed on the pillow or the trunk in front of the chest. And finally, the standard placing position of the lying position of the healthy side is adopted, the placing mode of the healthy side below and the affected side above is kept, the head bolster is used, the upper limb of the affected side is stretched and placed on the pillow, the scapula of the affected side extends forwards by 90-100 degrees, the forearm rotates forwards, the fingers stretch, the palm is downward, the lower limb of the affected side is slightly bent and placed on the long pillow, and the ankle joint of the affected side cannot be turned inwards and suspended at the edge of the pillow, so that the foot is prevented from turning inwards and dropping.
In one embodiment of the present description, the acral control scheme further comprises the amount of inflation of the area to be controlled and the time corresponding to the location of the acral. Different inflation quantities are determined according to the physical conditions of patients, so that the comfort of users in good limb positions is enhanced, and secondary damage caused by the fact that the limbs of the patients are squeezed due to overlarge inflation quantity is avoided. In addition, still including the time of putting that corresponds good limb position among the control scheme, because the patient that most use good limb position is hemiplegia patient or the inconvenient patient of activity, unable normal activity, set up every kind of good limb position according to patient's actual conditions and put the time and can avoid the patient to keep a posture for a long time and produce the emergence of complications such as bedsore and deep vein thrombosis.
Specifically, step S202 specifically includes: determining a good limb position control scheme of a user according to case information and body characteristic information of the user, which specifically comprises the following steps: constructing an initial neural network model, acquiring medical institution case information, body characteristic information and relevant data of a good limb position control scheme based on a web crawler technology, and training the initial neural network model according to the medical institution case information, the body characteristic information and the relevant data of the good limb position control scheme to obtain a good limb position control model meeting requirements; and inputting the case information and the physical characteristic information of the user into a good limb position control model meeting the requirements, and determining a good limb position control scheme of the user. According to medical institution case information, body characteristic information and the relevant data of the good limb position control scheme, training an initial neural network model, obtaining a satisfactory limb position control model meeting requirements, and specifically comprising: constructing a data set by using a plurality of groups of medical institution case information, body characteristic information and data of a good limb position control scheme, and dividing the data set into a training set and a verification set according to a preset proportion; constructing a network structure of a convolutional neural network model, wherein 0-95 layers of the convolutional neural network are deep convolutional layers and are composed of convolutional blocks and single-layer convolutional layers, and 96-126 layers of the convolutional neural network are characteristic interaction layers; presetting training parameters, wherein the training parameters comprise: inputting medical institution case information, body characteristic information and relevant data of a good limb position control scheme in a training set into a convolutional neural network model for cyclic iterative training, wherein the medical institution case information, the body characteristic information and the relevant data of the good limb position control scheme are input into the convolutional neural network model; inputting medical institution case information, body characteristic information and a good limb position control scheme concentrated in verification into a good limb position control model, recording a loss function value in the model training process, adjusting the connection weight among all neurons in the neural network model according to the loss function value, and obtaining the good limb position control model meeting the requirements when the loss function value reaches a preset loss function threshold or the training times reach a preset maximum iteration times; wherein the loss function is a cross entropy loss function.
In one embodiment of the present description, a Limb position control scheme for a user is derived via a Limb position control model. Firstly, an initial neural network model is constructed, wherein the initial neural network model can be a convolutional neural network structure, 0-95 layers of the convolutional neural network are deep convolutional layers and are composed of convolutional blocks and single convolutional layers, and 96-126 layers are characteristic interaction layers. Then, medical institution case information, user physical characteristic information and data related to the Limb position control scheme are collected based on a web crawler technology, it should be noted that the web crawler technology is a program or script for automatically capturing world Wide Web information according to a certain rule, and is widely used in Internet search engines or other similar websites, and can automatically collect all page contents that can be accessed by the web crawler technology so as to acquire or update the contents and retrieval modes of the websites. And carrying out data processing on the collected multiple groups of medical institution case information, multiple groups of body characteristic information and data of the good limb position control scheme, constructing a data set from the processed data, and dividing the data set into a training set and a verification set according to a ratio of 7: 3. Here, the ratio is a preset random ratio.
In one embodiment of the present description, the initial neural network model may be trained as follows: presetting training parameters, wherein the training parameters comprise: the method comprises the steps of obtaining initial learning rate, weight attenuation rate and maximum iteration times, inputting medical institution case information, body characteristic information and data related to a good limb position control scheme in a training set into a convolutional neural network model for cyclic iteration training, inputting medical institution case information, body characteristic information and a good limb position control scheme in a verification set into a good limb position control model, and recording a loss function value in the model training process, wherein the loss function is a cross entropy loss function. And adjusting the connection weight among the neurons in the neural network model according to the loss function value, and obtaining a qualified orthopodal position control model when the loss function value reaches a preset loss function threshold or the training times reaches a preset maximum iteration time.
In one embodiment of the present description, the initial neural network model may also be trained by: inputting medical institution case information, physical characteristic information and good limb position control scheme related data in a training set into a pre-constructed convolutional neural network model to obtain a plurality of good limb position control models, inputting medical institution case information and physical characteristic information in a verification set into the good limb position control models to calculate good limb position control scheme data corresponding to each good limb position control model, comparing the difference between the good limb position control scheme obtained by each good limb position control model and the good limb position control scheme in the verification set, and setting different weight values for the inflation volume of a region to be controlled in the good limb position control scheme, the good limb position information and the time corresponding to the good limb position according to priority in the process of comparing the good limb position control scheme difference, wherein the weight occupied by the good limb position is the maximum, and the weight occupied by the good limb position is the maximum, The time weight of the good limb position is the minimum, and the comparison of the invention is not limited specifically. And selecting the good limb position control model with the minimum difference as the good limb position control model meeting the requirement according to the comparison result. It should be noted that the present specification does not specifically limit the model training method.
In an embodiment of the present specification, after obtaining a satisfactory limb position control model meeting requirements, case information and body characteristic information of a user to use a satisfactory limb position are input into the satisfactory limb position control model meeting requirements, so as to obtain a satisfactory limb position control scheme corresponding to the user. Compared with manual generation, the good limb position control scheme generated by the model effectively saves the time of medical workers, and avoids the problem that the secondary injury of a patient is caused by mistakenly using the good limb position by a user.
Specifically, step S202 further includes: according to the body characteristic information of the user, a first good limb position control scheme of the user is determined, wherein the body characteristic information comprises: a height of a user and a weight of the user, the first ortholimb control scheme comprising: placing the initial position of a user and the inflation amount of an area to be controlled; according to the body characteristic information of the user, a first good limb position control scheme of the user is determined, and the method specifically comprises the following steps: presetting a relationship of a body index inflation quantity, wherein the body index is a ratio of the weight of a user to the height square of the user; when the body index is smaller than a first preset threshold value, the inflation amount is a first inflation amount; when the body index is larger than the first preset threshold and smaller than the second preset threshold, the inflation amount is a second inflation amount; when the body index is larger than a second preset threshold value, the inflation intensity is a third inflation amount; the first inflation amount is greater than the second inflation amount, and the second inflation amount is greater than the third inflation amount.
In one embodiment of the present description, the posture control scheme of the user further includes a first posture control scheme and a second posture control scheme, wherein the first posture control scheme includes an initial position for placing the user and an inflation amount of the area to be controlled, and the second posture control scheme includes a posture position and a time of the posture position.
In one embodiment of the present description, the first posture control scheme is determined based on physical characteristic information of the user. First, the relationship between the body index, which is the ratio of the user's weight to the user's height squared, and the amount of inflation is preset. The relationship between body index and inflation is as follows: when the body index is smaller than a first preset threshold value, the inflation amount is a first inflation amount; when the body index is larger than the first preset threshold and smaller than the second preset threshold, the inflation amount is a second inflation amount; and when the body index is larger than a second preset threshold value, the inflation intensity is a third inflation amount, the first inflation amount is larger than the second inflation amount, and the second inflation amount is larger than the third inflation amount. . It should be noted that the first preset threshold may be 18.5, and the second preset threshold may be 24. For example, if the height of the A user is 1.65m and the weight is 80KG, the body index of the A user is 80/(1.65 m)2) I.e., the physical index of the a user is 29, which is greater than 24, and therefore the amount of inflation is a low intensity inflation (third inflation) when the a user is using good limb positions. It is clear to those skilled in the art that, when the region to be controlled is inflated, the body part of the user is fixed in a certain region, when the body index of the user is larger, the area occupied by the body of the user is larger, and the body of the user can be fixed only by inflating the surrounding region with a low inflation amount, and conversely, if the body index of the user is larger, the body of the user can be fixedWhen the body index is small, the occupied area is small, so that the surrounding area needs to be filled with high-intensity inflation quantity to prevent the body of the user from being pulled away. And a good limb position control scheme is generated according to the body characteristic information of the user, so that the use comfort of the user is improved.
In one embodiment of the present description, the relationship of torso length, limb length, and shoulder width to the initial placement position of the user is preset: when trunk length, four limbs length and shoulder width were when predetermineeing the within range, it is normal scope to explain trunk length, four limbs length and shoulder width this moment, can set up user's initial placement position according to general placement scheme this moment, and wherein general placement scheme is for setting up according to human body proportion, need not artifical supplementary adjustment. When the trunk length, the limb length and the shoulder width are not within the preset range, it is indicated that the trunk length, the limb length and the shoulder width of the user are different from the normal body proportion, and manual auxiliary adjustment is needed on the basis of a general placement scheme.
In one embodiment of the present specification, the good limb position usage type is determined according to the case information of the user, for example, when the case information of the a user shows that the user is a postoperative patient and the operation site is an abdominal operation, in order to avoid that the user mistakenly sucks vomitus by lying on his back after the operation, the good limb position placement positions in the good limb position usage type corresponding to the user are left-side lying and right-side lying, and the placement time of each position is 30 minutes. For example, the case information of the user B shows that the patient is a hemiplegic patient, the hemiplegic part is the left side, the suggested placing positions of the good limb positions are a healthy lateral lying position, a supine position and an affected lateral lying position, and in order to prevent the occurrence of the situations such as bedsore on the affected side of the patient, the placing time of each position can be set to be 20 minutes; it should be noted that the lateral position of the patient is the lateral position on the nonparallelism side (healthy side), the lateral position of the patient is the lateral position on the paraplegia side, and for the left-side hemiplegia patient, the lateral position of the patient is the right lateral position, and the lateral position of the patient is the left lateral position. That is, according to the determined usage type of the good limb position of the case information, different usage types of the good limb position correspond to different good limb position and good limb position time, and further, a second good limb position control scheme is determined, wherein the second control scheme comprises the good limb position and the good limb position time.
The good limb position control scheme is automatically generated according to the actual condition of the user, so that the time of medical care workers is saved, the scientificity of using the good limb position by the user is further improved, and the good limb position control can better help the user to perform rehabilitation training and the like.
And S203, the favorable limb position control platform determines a region to be controlled of the mattress and a control instruction according to the favorable limb position control scheme, wherein the control instruction comprises the inflation or deflation operation of the region to be controlled, the inflation time or deflation time of the region to be controlled and the inflation quantity of the region to be controlled.
Specifically, step S203 specifically includes: determining a region to be controlled and a mattress inflation or deflation operation in a control instruction according to a favorable limb position placing position in a favorable limb position control scheme, wherein the favorable limb position placing position comprises: supine position, lateral position and lateral position; and determining the mattress inflation time according to the position change time in the favorable limb position control scheme.
Prior to step S204, the method further comprises: setting a body placing area and a body adjacent area of a mattress to be controlled, so that a controller of the mattress controls the body adjacent area to execute a control instruction, and assisting a user to complete limb position control; wherein the area to be controlled includes: a left shoulder region, a right shoulder region, a left upper limb region, a right upper limb region, a left lower limb region, and a right lower limb region, each region comprising one or more body placement regions and at least one body proximity region.
In an embodiment of the present specification, fig. 3 is a partition of a region to be controlled of a mattress provided in an embodiment of the present specification, as shown in fig. 3, the region to be controlled of the mattress includes a head region 31, a left shoulder region 32, a right shoulder region 33, a left upper limb region 34, a right upper limb region 35, a left lower limb region 36, and a right lower limb region 37, it should be noted that, here, left and right refer to left and right sides corresponding to standing facing the mattress, and each region includes a body placement region and a body adjacent region as shown in fig. 4, the left lower limb region 36 is taken as an example for explanation, the region 362 and the region 364 are body placement regions, and the region 361, the region 363, and the region 365 are body adjacent regions. Taking the region 362 as an example, the region 362 is a body placement region, the surrounding regions (the region 361 and the region 363) are inflated, the region 362 can be inflated with a small amount of gas, so that the region 362 has a swelling effect, but the swelling degree of the region 362 is smaller than that of the region 361 and the region 363, so that the effects of two sides being high and the middle being low can be achieved, the affected limb of the user can be lifted, and the limb can be fixed by using the height difference of the two sides.
In one embodiment of the present specification, the area to be controlled and the control command are determined according to the posture position of the good limb in the good limb position control scheme, for example, as shown in fig. 5, the posture positions of the good limb in the good limb position control scheme of the C user (right hemiplegia means that the right part of the patient is damaged) are a supine position, a healthy lateral recumbent position (left lateral recumbent position) and a sick lateral recumbent position (right lateral recumbent position), the conversion time is 20 minutes, and the inflation amount is a medium-intensity inflation amount. As will be described below in conjunction with fig. 3 and 5, when determining the supine position, the patient lies flat on the mattress, with the right side of the patient actually corresponding to the left side of the mattress, and the corresponding control regions of the mattress in the supine position are the left shoulder region 32, the left upper limb region 34, and the left lower limb region 36. The right shoulder, the right upper limb and the right lower limb of the patient are respectively placed in the body placing areas of the left shoulder area 32, the left upper limb area 34 and the left lower limb area 36, and the inflation operation is performed on the body adjacent areas (corresponding to the dark shading in the mattress of fig. 5) in the left shoulder area 32, the left upper limb area 34 and the left lower limb area 36, the inflation duration is 20 minutes, the inflation amount is a medium-strength inflation amount, in order to enable the mattress to lift and fix the right shoulder, the right upper limb and the right lower limb of the patient, and the body placing areas of the left shoulder area 32, the left upper limb area 34 and the left lower limb area 36 can be inflated with small strength. In this way, the body placement area exhibits a micro-doming effect; and, the cooperation of the different gas loadings of area and the health near-by region is placed to the health can play the effect of better fixed user right side shoulder, right side upper limbs and right side low limbs to guarantee that elbow, wrist all straighten, the finger extends, and the palm is upwards in order to realize the standard position of supine position. When the supine position is changed to the healthy lateral position (left lateral position), the left shoulder area 32, the left upper limb area 34 and the left lower limb area 36 are deflated, the control areas are determined as the right shoulder area 33, the right upper limb area 35 and the right lower limb area 37, the body adjacent areas (corresponding to the dark shading in the mattress of fig. 5) of the areas are inflated for 20 minutes, the inflation amount is the middle-intensity inflation amount, and the body placing areas of the areas are inflated with a small amount of gas, so that the limbs of the patient can be lifted slightly, and the affected side limbs can be fixed by the height difference. When the patient is changed from the healthy lateral recumbent position (left lateral recumbent position) to the affected lateral recumbent position (right lateral recumbent position), the right shoulder region 33, the right upper limb region 35, and the right lower limb region 37 are deflated, the control regions are determined as the left shoulder region 32, the right shoulder region 33, the left upper limb region 34, the right upper limb region 35, and the right lower limb region 37, the body-adjacent regions (corresponding to the dark hatching in the mattress of fig. 5) of the above regions are inflated for 20 minutes, and the inflation amount is a medium-intensity inflation amount. The mattress is divided into different areas according to the physiological structure of the human body, so that the universality of the mattress is improved, and the mattress can be suitable for most users; in addition, in the good limb position control process, the area to be controlled is determined firstly, and then the area to be controlled is operated, so that the operating pressure of the good limb position control platform is further reduced.
And step S204, the good limb position control platform sends the good limb position control scheme to a controller of the mattress, so that the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, and a user is assisted to complete good limb position control.
In one embodiment of the present specification, the orthobaric position control scheme is sent to a controller of the mattress, and the controller assists the patient to complete orthobaric position control by controlling the corresponding region to be controlled of the mattress to perform inflation or deflation operation, the inflation time or deflation time of the region to be controlled, and the inflation amount of the region to be controlled.
Specifically, before the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, the method further comprises the following steps: a controller of the mattress constructs a coordinate system by taking a preset position of the mattress as an original point, and records a first position coordinate of a first preset part of a user and a second position coordinate of a second preset part of the user; after assisting the user in completing orthostatic control, the method further comprises: the controller of the mattress records the third position coordinate of the first preset part and the fourth position coordinate of the second preset part; judging whether the user correctly uses the good limb position according to the first position coordinate, the second position coordinate, the third position coordinate and the fourth position coordinate, and specifically comprising the following steps: determining the position condition of the user before completing the good limb position according to the difference value of the first position coordinate and the second position coordinate; determining the position condition of the user after completing the good limb position according to the difference value of the third position coordinate and the fourth position coordinate; and judging whether the user moves according to the good limb position control scheme and whether the current good limb position of the user is in the correct position according to the position condition before the user completes the good limb position and the position condition after the user completes the good limb position.
In one embodiment of the present description, it may be monitored whether the user is using the orthopodal position correctly by: the controller of the mattress takes a mattress preset position as an origin to construct a coordinate system, wherein the mattress preset position can be a mattress central point, a mattress upper left end point, a mattress lower left end point, a mattress upper right end point, a mattress lower right end point, or a position of any position of the mattress. In addition, the coordinate system can be a three-dimensional coordinate system, and the direction of the coordinate system can be set according to the placement condition of the mattress. Before a controller of the mattress controls a region to be controlled of the mattress according to a control instruction, recording a first position coordinate of a first preset part and a second position coordinate of a second preset part of a user, wherein the first preset part and the second preset part are adjacent joints on the same side of the body of the user, such as a left shoulder joint and a left elbow joint on the left side of the body of the user, and a left knee joint and a left hip joint on the left side of the body of the user. And after the auxiliary user finishes controlling the good limb position, recording and recording a third position coordinate of the first preset part and a fourth position coordinate of the second preset part. That is to say, the first position coordinate and the second position coordinate are positions of the first preset part and the second preset part before the user completes the good limb position, and the position condition of the user before the user completes the good limb position is determined according to the difference value of the first position coordinate and the second position coordinate. Similarly, the third position coordinate and the fourth position coordinate are positions of the first preset part and the second preset part after the user completes the good limb position, and the position condition of the user after the user completes the good limb position can be determined according to the difference value of the third position coordinate and the fourth position coordinate. And judging whether the user moves according to the good limb position control scheme according to the two position conditions, and judging whether the current good limb position of the user is in a correct position.
In one embodiment of the present description, it may also be monitored whether the user is using the orthopodal position correctly by: after assisting the patient to accomplish good limb position control, can also confirm standard good limb position state parameter according to good limb position control scheme to obtain the real-time status parameter of patient after using good limb position, count real-time status parameter and standard good limb position state parameter and compare, judge whether the difference between the two surpasss and predetermine the threshold value, if judge that the difference exceeds and predetermine the threshold value, then adjust the mattress area of waiting to control and control command according to the difference, so that accomplish good limb position control. The method for acquiring the real-time state parameters of the patient after using the orthopodal position comprises the following steps: firstly, the camera and the steering device are used for collecting the state image of the patient, the steering device can realize all-around collection, and the condition that the state parameters are not accurate due to incomplete picture collection is avoided. Secondly, a good limb position monitoring model is constructed and trained so as to obtain a good limb position monitoring model meeting the requirements. And inputting the acquired state image of the patient into a satisfactory limb position monitoring model meeting the requirements, and determining the current satisfactory limb position state parameter of the patient.
Specifically, the method further comprises: before a controller of a mattress controls a region to be controlled of the mattress according to a control instruction, a good limb position control platform obtains a first position of a bone key point at a first moment according to a human body key point prediction network, and the method specifically comprises the following steps: collecting image data before user completes limb control, inputting the image data into human body key point prediction network, outputting prediction probability that each pixel point in the image is skeleton key point, and forming heating powerConverting the thermodynamic diagram into numerical coordinates of skeletal keys by a soft-argmax function and outputting the numerical coordinates, wherein the human body key point prediction network is obtained by introducing a CBAM (cubic cellular am) attention model based on a CPN (compact personal computer) feature pyramid network, and the CPN feature pyramid network comprises a GlobalNet model and a RefineNet model; obtaining the predicted position of the key point of the skeleton according to the first position and the instantaneous speed at the first preset moment, and obtaining the first position and the predicted position through Q-AQ1+ BP + C to obtain the position track of the key points of the skeleton; the system comprises a skeleton key point, a state transformation matrix and a first processing unit, wherein Q is a feature vector and is used for representing state information of the skeleton key point at a second preset moment, the state information of the skeleton key point comprises speed information of the skeleton key point and coordinate information of the skeleton key point, A is the state transformation matrix and is used for associating the state information of the skeleton key point at the first preset moment with the state of the skeleton key point at the second preset moment, and the first preset moment is the last moment of the second preset moment; and judging whether the user correctly uses the good limb position according to the position track of the key points of the skeleton.
In one embodiment of the present description, it may also be monitored whether the user is using the orthopodic position correctly by: before the controller of mattress according to control command control mattress treat the control area, gather the image data that the user was located at first preset moment through image acquisition device, image data can be picture, photo etc. and image acquisition device can be the rotatable camera that sets up in the mattress top, is convenient for gather user's panorama image. After image data are collected, the image data are input into a human body key point prediction network, prediction probabilities that all pixel points corresponding to an output image are skeleton key points form a thermodynamic diagram, for example, the probability that a certain pixel point is a skeleton key point is 99%, the probability that an adjacent pixel point is a skeleton key point is 50%, the thermodynamic diagram is converted into a numerical coordinate of the skeleton key point through a soft-argmax function, and the position coordinate is output, wherein the soft-argmax function is
Figure BDA0003138545900000181
It should be noted that the human body key point prediction network introduces CBAM on the basis of CPN characteristic pyramid networkThe method comprises the steps that an attention model is obtained, wherein the CPN characteristic pyramid network comprises a GlobalNet model for integrally detecting skeletal key points and a fine-tuning network RefineNet model, the fusion of the CPN characteristic pyramid network to a deep layer and a shallow layer is better played through the combination of the models, the advantage of the attention model for distributing weight to learn useful information is greatly played, the accuracy of positioning the skeletal key points of a human body is further improved, the position coordinates of the skeletal key points of the human body can be determined, and the method is more accurate compared with the position coordinates obtained through manual positioning.
After a first position coordinate of a first preset moment is obtained, a predicted position corresponding to a bone key point is obtained according to the first position of the first preset moment and the instantaneous speed of a certain bone key point, and the first position and the predicted position are calculated according to a formula Q-AQ1+ BP + C to obtain the position track of the key points of the skeleton; and A is a state transformation matrix which is used for correlating the state information of the bone key point at the first preset moment to the state of the bone key point at the second preset moment, and judging whether the user correctly uses the good limb position according to the position track of the bone key point. For example, the user starts to perform position transformation at time T1, time T2 is a transformation process, time T3 is a successful time of position transformation, at this time, the first preset time may be time T1, the second preset time may be time T2, the position of time T2 may be obtained according to the position coordinate of a certain bone key point at time T1 and the instantaneous speed of the bone key point, and similarly, when the first preset time is time T2 and the second preset time is time T3, the position of the bone key point at time T3 may be obtained, the motion trajectory of the bone key point may be further determined, and the motion trajectories of a plurality of bone key points are combined to determine whether the user correctly uses the good limb position. For another example, taking the user changing from the supine position to the left lateral position as an example, the first preset time may be the last time of the supine position, the second preset time may be the first time of the left lateral position, and the first preset time and the second preset time are based on the first preset time and the second preset timeAnd determining the position track of the bone key point, and judging whether the motion track is the motion track of the bone key point changed from the supine position to the left lateral position. It should be noted that, in the embodiments of the present description, the capturing of the image data of the user before completing the acral control may refer to the image data of the user at the first position during the process of changing from the first position to the second position.
The good limb position of the user is detected in the above mode, the accuracy of the detection mode is improved, the condition that the good limb position is used in an irregular mode is found in time, the user is adjusted according to the condition that the user uses the good limb position, and the user is helped to achieve the best using effect.
The illustrated embodiment also provides an automatic orthobaric control device, as shown in fig. 6, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to: the controller of the mattress sends a good limb position use request of a user to the medical care node so that the medical care node can call case information of the user conveniently, wherein the request comprises user identity identification and body characteristic information; when the medical care node confirms the good limb position use request, the good limb position control platform determines a good limb position control scheme of the user according to case information and body characteristic information of the user, wherein the good limb position control scheme comprises the air inflation amount of an area to be controlled, good limb position placing position information and time corresponding to the good limb position placing position; the good limb position control platform determines a region to be controlled of the mattress and a control instruction according to a good limb position control scheme, wherein the control instruction comprises inflation or deflation operation of the region to be controlled, inflation time or deflation time of the region to be controlled and inflation quantity of the region to be controlled; the good limb position control platform sends the good limb position control scheme to the controller of mattress is treated the control region according to control command control mattress, so that supplementary user accomplishes good limb position control.
In one or more embodiments of the present description, a Limb position control scheme is determined according to user case information and body characteristic information, so that the use of Limb position is more unique, and the customized Limb position control scheme further improves the use experience of the user, and the control scheme is obtained according to the case information, so that the obtained scheme is more scientific, and the Limb position is helpful for helping the patient to perform rehabilitation treatment; in addition, after the good limb position control scheme is obtained, the good limb position is automatically controlled in a control instruction mode, and the burden of family members and nursing workers of the patient is relieved.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and for the relevant points, reference may be made to the partial description of the embodiments of the method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is merely one or more embodiments of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments of the present description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of the claims of the present specification.

Claims (10)

1. An automatic orthotopic control method, the method comprising:
a controller of the mattress sends a request for using the good limb position of a user to a medical care node so that the medical care node can call case information of the user conveniently, wherein the request comprises user identification and body characteristic information;
when the medical care node confirms the good limb position use request, the good limb position control platform determines a good limb position control scheme of the user according to the case information and the body characteristic information of the user, wherein the good limb position control scheme comprises the air inflation amount of an area to be controlled, good limb position placing position information and time corresponding to the good limb position placing position;
the good limb position control platform determines a region to be controlled of the mattress and a control instruction according to the good limb position control scheme, wherein the control instruction comprises the inflation or deflation operation of the region to be controlled, the inflation time or deflation time of the region to be controlled and the inflation quantity of the region to be controlled;
the good limb position control platform sends the good limb position control scheme to a controller of the mattress, so that the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, and the user is assisted to complete the good limb position control.
2. The method of claim 1, wherein prior to sending the Limb position control plan to the controller of the mattress, the method further comprises:
setting a body placing area and a body adjacent area of the mattress to be controlled, so that a controller of the mattress controls the body adjacent area to execute the control instruction, and assisting the user to complete good limb position control; wherein the area to be controlled includes:
a left shoulder region, a right shoulder region, a left upper limb region, a right upper limb region, a left lower limb region, and a right lower limb region, each region comprising one or more of the body placement regions and at least one of the body proximity regions.
3. The method of claim 1, wherein the determining the Limb control plan of the user according to the case information and the body characteristic information of the user specifically comprises:
constructing an initial neural network model, acquiring medical institution case information, body characteristic information and relevant data of a good limb position control scheme based on a web crawler technology, and training the initial neural network model according to the medical institution case information, the body characteristic information and the relevant data of the good limb position control scheme to obtain a good limb position control model meeting requirements;
and inputting the case information and the physical characteristic information of the user into the satisfactory limb position control model meeting the requirements, and determining a satisfactory limb position control scheme of the user.
4. The method of claim 3, wherein the training of the initial neural network model according to the medical institution case information, the physical characteristic information and the data related to the Limb position control scheme to obtain a satisfactory Limb position control model comprises:
constructing a data set by using a plurality of groups of medical institution case information, body characteristic information and data of a good limb position control scheme, and dividing the data set into a training set and a verification set according to a preset proportion;
constructing a network structure of a convolutional neural network model, wherein 0-95 layers of the convolutional neural network are deep convolutional layers and are composed of convolutional blocks and single-layer convolutional layers, and 96-126 layers of the convolutional neural network are characteristic interaction layers;
presetting training parameters, wherein the training parameters comprise: inputting medical institution case information, body characteristic information and relevant data of a good limb position control scheme in a training set into the convolutional neural network model for cyclic iterative training, wherein the medical institution case information, the body characteristic information and the relevant data of the good limb position control scheme are input into the convolutional neural network model;
inputting medical institution case information, body characteristic information and a good limb position control scheme concentrated in verification into a good limb position control model, recording a loss function value in the model training process, adjusting the connection weight among all neurons in a neural network model according to the loss function value, and obtaining the good limb position control model meeting the requirements when the loss function value reaches a preset loss function threshold or the training times reaches a preset maximum iteration times; wherein the loss function is a cross entropy loss function.
5. The method of claim 1, wherein the determining the Limb control plan of the user according to the case information and the body characteristic information of the user specifically comprises:
determining a first good limb position control scheme of the user according to the body characteristic information of the user, wherein the body characteristic information comprises: a height of the user and a weight of the user, the first ortholimb control scheme comprising: placing the initial position of the user and the inflation amount of the area to be controlled;
the determining a first good limb position control scheme of the user according to the body feature information of the user specifically includes:
presetting a relation between a body index and the inflation quantity, wherein the body index is a ratio of the weight of the user to the height square of the user;
when the body index is smaller than a first preset threshold value, the inflation amount is a first inflation amount;
when the body index is larger than the first preset threshold and smaller than a second preset threshold, the inflation amount is a second inflation amount;
when the body index is larger than the second preset threshold value, the inflation intensity is a third inflation amount;
the first inflation amount is greater than the second inflation amount, and the second inflation amount is greater than the third inflation amount.
6. The method of claim 5, wherein after determining the first Limb control scheme for the user based on the physical characteristic information of the user, the method further comprises:
and determining a good limb position use type and a corresponding second good limb position control scheme according to the case information of the user, wherein the second good limb position control scheme comprises a good limb position placing position and time of the good limb position placing position, and the different good limb position use types correspond to different good limb position placing positions and time of the good limb position placing position.
7. The method of claim 1, wherein the determining the area to be controlled and the control command of the mattress according to the Limb position control scheme specifically comprises:
according to the good limb position placing position in the good limb position control scheme, determining the area to be controlled and the mattress inflation or deflation operation in the control instruction, wherein the good limb position placing position comprises the following steps: supine position, lateral position and lateral position; and determining the mattress inflation time according to the position change time in the favorable limb position control scheme.
8. The method of claim 1, wherein before the controller of the mattress controls the area of the mattress to be controlled according to the control command, the method further comprises: the controller of the mattress constructs a coordinate system by taking the preset position of the mattress as an origin, and records a first position coordinate of a first preset part and a second position coordinate of a second preset part of the user;
after the assisting the user in completing orthostatic control, the method further comprises:
the controller of the mattress records a third position coordinate of the first preset part and a fourth position coordinate of the second preset part;
judging whether the user correctly uses the good limb position according to the first position coordinate, the second position coordinate, the third position coordinate and the fourth position coordinate, and specifically comprising the following steps:
determining the position condition of the user before completing the good limb position according to the difference value of the first position coordinate and the second position coordinate, wherein the position condition is used for reflecting the position of each part of the body before the user completes the good limb position;
determining the position condition of the user after completing the good limb position according to the difference value of the third position coordinate and the fourth position coordinate, wherein the position condition is used for reflecting the position of each part of the body of the user after completing the good limb position;
and judging whether the user moves according to the good limb position control scheme and whether the current good limb position of the user is in a correct position according to the position condition of the user before the user finishes the good limb position and the position condition of the user after the user finishes the good limb position.
9. The method of claim 1, wherein the method further comprises:
before the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, the good limb position control platform obtains a first position of a bone key point at a first preset moment according to a human body key point prediction network, and the method specifically comprises the following steps:
acquiring image data of a user before completing limb position control, inputting the image data into a human body key point prediction network, outputting prediction probability that each pixel point in the image is a skeleton key point, forming a thermodynamic diagram, converting the thermodynamic diagram into numerical coordinates of the skeleton key point by a soft-argmax function, and outputting the numerical coordinates, wherein the human body key point prediction network is obtained by introducing a CBAM (cubic cellular amplitude modulation) attention model based on a CPN (coherent population network) feature pyramid network, and the CPN feature pyramid network comprises a GlobalNet model and a RefineNet model;
obtaining a predicted position of the bone key point according to a first position and an instantaneous speed at a first preset moment, and obtaining the first position and the predicted position through Q-AQ1+ BP + C gives the skeleton-bone-jointA locus of positions of the key points; the system comprises a skeleton key point, a state transformation matrix and a processing unit, wherein Q is a feature vector and is used for representing state information of the skeleton key point at a second preset moment, the state information of the skeleton key point comprises speed information of the skeleton key point and coordinate information of the skeleton key point, A is the state transformation matrix and is used for associating the state information of the skeleton key point at the first preset moment to the state of the skeleton key point at the second preset moment, and the first preset moment is a previous moment of the second preset moment;
and judging whether the user correctly uses the good limb position according to the position track of the bone key point.
10. An automatic Limb position control device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to: a controller of the mattress sends a request for using the good limb position of a user to a medical care node so that the medical care node can call case information of the user conveniently, wherein the request comprises user identification and body characteristic information;
when the medical care node confirms the good limb position use request, the good limb position control platform determines a good limb position control scheme of the user according to the case information and the body characteristic information of the user, wherein the good limb position control scheme comprises the air inflation amount of an area to be controlled, good limb position placing position information and time corresponding to the good limb position placing position;
the good limb position control platform determines a region to be controlled of the mattress and a control instruction according to the good limb position control scheme, wherein the control instruction comprises the inflation or deflation operation of the region to be controlled, the inflation time or deflation time of the region to be controlled and the inflation quantity of the region to be controlled;
the good limb position control platform sends the good limb position control scheme to a controller of the mattress, so that the controller of the mattress controls the area to be controlled of the mattress according to the control instruction, and the user is assisted to complete the good limb position control.
CN202110728780.1A 2021-06-29 2021-06-29 Automatic good limb position control method and device Active CN113362925B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110728780.1A CN113362925B (en) 2021-06-29 2021-06-29 Automatic good limb position control method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110728780.1A CN113362925B (en) 2021-06-29 2021-06-29 Automatic good limb position control method and device

Publications (2)

Publication Number Publication Date
CN113362925A true CN113362925A (en) 2021-09-07
CN113362925B CN113362925B (en) 2022-04-08

Family

ID=77537094

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110728780.1A Active CN113362925B (en) 2021-06-29 2021-06-29 Automatic good limb position control method and device

Country Status (1)

Country Link
CN (1) CN113362925B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050193492A1 (en) * 2003-02-10 2005-09-08 Yoshino Industry Co., Ltd. Appliance for adjusting points of upper body in good limb
US20060026767A1 (en) * 2004-08-04 2006-02-09 Chambers Kenith W Mattress system for a hospital bed
US20150290059A1 (en) * 2014-04-15 2015-10-15 Select Comfort Corporation Adjustable bed system
CN106687119A (en) * 2014-07-17 2017-05-17 杰罗米.申塔格 Activation of the endogenous ileal brake hormone pathway for organ regeneration and related compositions, methods of treatment, diagnostics, and regulatory systems
CN207118978U (en) * 2017-03-15 2018-03-20 喻海燕 A kind of anti-spasm body position pillow
CN111387990A (en) * 2020-03-24 2020-07-10 首都医科大学宣武医院 Cerebral apoplexy hemiplegia patient is with early warning system that leaves bed
CN211460954U (en) * 2019-12-12 2020-09-11 黄艳 Air cushion for keeping good limb position
CN212699446U (en) * 2020-04-27 2021-03-16 昆明市中医医院 Combined pad for placing upper and lower limbs in multifunctional good limb position

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050193492A1 (en) * 2003-02-10 2005-09-08 Yoshino Industry Co., Ltd. Appliance for adjusting points of upper body in good limb
US20060026767A1 (en) * 2004-08-04 2006-02-09 Chambers Kenith W Mattress system for a hospital bed
US20150290059A1 (en) * 2014-04-15 2015-10-15 Select Comfort Corporation Adjustable bed system
CN106687119A (en) * 2014-07-17 2017-05-17 杰罗米.申塔格 Activation of the endogenous ileal brake hormone pathway for organ regeneration and related compositions, methods of treatment, diagnostics, and regulatory systems
CN207118978U (en) * 2017-03-15 2018-03-20 喻海燕 A kind of anti-spasm body position pillow
CN211460954U (en) * 2019-12-12 2020-09-11 黄艳 Air cushion for keeping good limb position
CN111387990A (en) * 2020-03-24 2020-07-10 首都医科大学宣武医院 Cerebral apoplexy hemiplegia patient is with early warning system that leaves bed
CN212699446U (en) * 2020-04-27 2021-03-16 昆明市中医医院 Combined pad for placing upper and lower limbs in multifunctional good limb position

Also Published As

Publication number Publication date
CN113362925B (en) 2022-04-08

Similar Documents

Publication Publication Date Title
CN103519966B (en) Portable hemiplegy rehabilitation training robot for hemiplegic upper limb
Timoszyk et al. The rat lumbosacral spinal cord adapts to robotic loading applied during stance
CN105852874A (en) Autonomous rehabilitation training system and method
CN111700618B (en) Counting rehabilitation training system and device
CN109011174A (en) Cloud intelligent rehabilitation physical therapeutic system, passive bionic movement rehabilitation physical therapy machine people
Nair et al. Stroke rehabilitation: traditional and modern approaches
CN113362925B (en) Automatic good limb position control method and device
RU2539164C1 (en) Method for rehabilitation treatment of patients suffering vertebral-spinal injury
US20080146415A1 (en) Method for managing exercise for function recovery and muscle strengthening
CN201342026Y (en) Body position holding mat
CN111053635A (en) Robot device capable of sleeping healthily
CN205163559U (en) Chair is tempered to intelligence muscles along regular meridians
Lay-Ekuakille et al. Preventing, Monitoring and Treating Foot Conditions in Medical Robotic Rehabilitation
KR200222638Y1 (en) Exercise bed for patient of firmity with age
Ogonowska et al. Physiotherapy in patients after ischemic stroke
Lee et al. Development of a direction-oriented motion and short-sitting and lying Tai Chi (DOM-SSLTC) model for function recovery in stroke patients
RU2715549C1 (en) Method of upper limb support function formation in patients with pathology of spine and spinal cord at cervical level
CN216258950U (en) Hospital rehabilitation exercise device
CN116327530A (en) Passive loosening device, control method, storage medium and computer equipment thereof
Wilson-Meredith et al. 24-hour approach to physical management
Kim et al. PRINCIPLES OF REHABILITATION FOR YOUNG PEOPLE AFTER ISCHEMIC STROKE (literature review)
Siegel Postural compensation in the motor-handicapped blind
Robayo-Torres et al. Design of a Standing Device for Children with Spinal Dysraphysm
Zhao et al. Corollary Equipment of Rehabilitation Training of Neurological Training
CN114129152A (en) Self-adaptive motion control device based on lower limb rehabilitation robot

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
GR01 Patent grant
GR01 Patent grant