KR102492580B1 - System for Providing Rehabilitaion Exercise Using Rehabilitaion Exercise Apparatus - Google Patents

Abstract

A rehabilitation exercise system using a rehabilitation exercise apparatus maximizes the effect of rehabilitation exercise, when a user performs rehabilitation exercise using a rehabilitation exercise apparatus after knee surgery, by performing rehabilitation exercise using an optimal knee motion angle within a range without knee pain. The present invention has an effect of increasing rehabilitation efficiency by obtaining a rehabilitation exercise effect without side effects by finding out an optimal knee motion angle in a range without knee pain by using surgery-related information, and performing rehabilitation exercise using the optimal knee motion angle.

Description

Rehabilitation exercise system using a rehabilitation exercise device {System for Providing Rehabilitaion Exercise Using Rehabilitaion Exercise Apparatus}

The present invention relates to a rehabilitation exercise system, and more particularly, when performing rehabilitation exercise using a rehabilitation exercise device after knee surgery, by performing rehabilitation exercise using an optimal knee motion angle within a range without knee pain. It relates to a rehabilitation exercise system using a rehabilitation exercise device capable of maximizing exercise effects.

Rehabilitation exercise is essential after artificial joint surgery or arthroscopy. This is because it is important to improve the range of motion of the leg joints and prevent stiffening of the leg joints.

Rehabilitation exercise uses a CPM (Continuous Passive Motion) device, which is a rehabilitation exercise treatment device that passively helps joint motion after knee surgery.

After artificial joint surgery, CPM can extend and bend the knee joint to the maximum to perform exercises to improve the range of motion of the knee, such as widening and bending the knee, and exercises to improve muscle strength around the joint.

CPM treatment serves to reduce pain and widen the range of joint motion.

The surgical patient removes the blood drainage bag 1 to 2 days after the surgery and, if possible, uses the CPM device as soon as possible to perform leg flexion and extension exercises.

If the caregiver or guardian bends excessively, the patient's pain can become severe, so it is good for the patient to do active exercises on their own.

However, with the CPM device, if you put your knee on the machine, the machine automatically moves back and forth. Since it is a short time after joint surgery, the knee is bent and stretched, so severe knee pain occurs or horizontal reciprocating motion is performed. There is a problem in that it is inconvenient to move continuously.

Therefore, patients may tend to be reluctant to actively perform CPM treatment while enduring pain due to knee pain.

Korea Patent Registration No. 10-1459696

In order to solve this problem, the present invention, when performing rehabilitation exercise using a rehabilitation exercise device after knee surgery, performs rehabilitation exercise using an optimal knee motion angle within a range without knee pain, thereby improving the rehabilitation exercise effect. Its purpose is to provide a rehabilitation exercise system using a rehabilitation exercise device that can be maximized.

Rehabilitation exercise system according to the features of the present invention for achieving the above object,

A device body having a slide groove of a certain depth along the center and having a controller at one end, a connecting member connected to one side of the device body, and a calf support coupled to the connecting member to support and fix the patient's calf A foldable member for leg support consisting of a thigh support connected to the calf support by a rotational connector to support and fix the patient's thigh, and a lower surface of the foldable member for leg support to be inserted into the slide groove of the main body of the device. An electric link member having a certain length is coupled in the vertical direction, the electric link member is connected to a driving means formed inside the device body, and when reciprocating back and forth by the driving force of the driving means, the calf support and the thigh support are a rehabilitation exercise device that bends and straightens the patient's leg while being rotated around the rotation connector and folded at a certain angle and then unfolded; and

A control button electrically connected to the controller to control knee motion angle setting, drive time setting, power on/off setting, and knee pain during rehabilitation exercise of bending and straightening the patient's leg, thereby resetting the knee motion angle And a remote control having an angle readjustment button for performing angle readjustment if desired,

When the power is turned on using the control button of the remote control, the controller controls the driving means to move the motorized link member back and forth to repeat the bending and stretching of the leg, and the angle needs to be readjusted at an angle where knee pain is felt. When receiving a selection signal of the angle readjustment button of the remote controller, the current readjusted knee motion angle is stored in a storage unit together with the angle storage date, and the readjusted electric link member is moved from 0 degrees by controlling the driving means. It further includes a control unit for controlling to perform a horizontal reciprocating motion while increasing by 1 degree or decreasing by 1 degree until the knee movement angle.

According to the configuration described above, the present invention can find out the optimal knee motion angle in the range without knee pain using surgery-related information, and use this to perform rehabilitation exercises to obtain a rehabilitation exercise effect without side effects and increase rehabilitation efficiency. There is an effect.

1 is a diagram showing the configuration of a rehabilitation exercise system using a rehabilitation exercise device according to an embodiment of the present invention.
2 is a perspective view showing the configuration of a rehabilitation exercise device according to an embodiment of the present invention.
3 is a block diagram briefly showing the internal configuration of a controller and a remote control according to an embodiment of the present invention.
4 is a diagram showing an example of a knee motion angle according to an embodiment of the present invention.
5 is a diagram showing a field configuration of surgery-related information according to an embodiment of the present invention.
6 is a diagram showing the configuration of a learning model and an artificial neural processing network of a rehabilitation exercise management server according to an embodiment of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. Like reference numerals have been used for like elements throughout the description of each figure.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. The term “and/or” includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when an element is referred to as “directly connected” or “directly connected” to another element, it should be understood that no other element exists in the middle.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

Hereinafter, with reference to the accompanying drawings, preferred embodiments of the present invention will be described in more detail. In order to facilitate overall understanding in the description of the present invention, the same reference numerals are used for the same components in the drawings, and redundant descriptions of the same components are omitted.

1 is a diagram showing the configuration of a rehabilitation exercise system using a rehabilitation exercise device according to an embodiment of the present invention.

The rehabilitation exercise system 100 according to an embodiment of the present invention includes a communication network 102 , a rehabilitation exercise device 110 , a rehabilitation exercise management server 140 and a user terminal 150 .

The rehabilitation exercise system 100 is linked with the user terminal 150 that executes the rehabilitation exercise service app 20 and the user terminal 150 through the communication network 102 to use the rehabilitation exercise service, and the rehabilitation exercise service app ( 20) Rehabilitation that provides services for rehabilitation exercise service program functions, manages statistical data on the history of using the app for remote control and knee motion angles, and provides optimized motion angles for users' painful knees. It includes an exercise management server 140 .

The rehabilitation exercise system 100 may be constructed to link with the rehabilitation exercise management server 140 through the communication network 102 in order to transmit and receive information related to a customized knee motion angle.

The rehabilitation exercise service app 20 is a management app installed in the user terminal 150 to receive a rehabilitation exercise recommendation program provided by the rehabilitation exercise management server 140 or provided as a web-based service.

The rehabilitation exercise recommendation program provided through the rehabilitation exercise service app 20 is a customized rehabilitation exercise recommendation program that collects user's surgery-related information and recommends a knee motion angle for the user's rehabilitation exercise. The rehabilitation exercise management server 140 may provide a program suitable for a user among subdivided programs by utilizing a recommendation algorithm based on the collected data.

In addition, the rehabilitation exercise service app 20 may be produced and provided in different versions according to the type of terminal, and may be provided separately as a mobile version or a PC version, for example.

The rehabilitation exercise management server 140 provides a user-customized rehabilitation exercise recommendation program through the rehabilitation exercise service app 20 running on the user terminal 150, based on personal data of the knee motion angle collected in relation to the user. Using a neural network learning and recommendation algorithm, a suitable rehabilitation exercise recommendation program can be provided to the user, and through the rehabilitation exercise service app 20, remote control, knee motion angle statistical data, and knee motion angle recommendation function can be performed. there is.

The rehabilitation exercise service app 20 uses the user terminal 150 from the outside to drive and control the rehabilitation exercise device 110 indoors, and the rehabilitation exercise based on the user's surgery-related information. and one or more functional modes of a knee motion angle recommendation mode 22 for recommending a knee motion angle to be used.

The user terminal 150 may select a remote control mode 21 and a knee motion angle recommendation mode 22 in the rehabilitation exercise service app 20 .

The user terminal 150 may execute the rehabilitation exercise service app 20 to provide a rehabilitation exercise service and input surgery-related information related to knee surgery. The user terminal 150 includes a smart phone, a mobile phone, a navigation device, a computer, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a tablet PC, and the like. For example, the user terminal 150 may communicate with the rehabilitation exercise management server 140 through the communication network 102 using a wireless or wired communication method.

The communication network 102 is not limited to a communication method, and may include, for example, a communication method using a mobile communication network, wired Internet, wireless Internet, or a broadcasting network, as well as short-distance wireless communication between devices. For example, communication networks include a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet. One or more of the networks may include any network. In addition, the communication network 102 may include any one or more of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network, and the like. Not limited.

The rehabilitation exercise device 110 is exercise equipment for assisting rehabilitation of a patient's knee or shoulder, and the rehabilitation of the present invention is limited to the knee for convenience of description, and will be described in detail with reference to FIG. 2 below.

The rehabilitation exercise management server 140 transmits and receives data with the rehabilitation exercise device 110 through short-distance or long-distance communication.

2 is a perspective view showing the configuration of a rehabilitation exercise device according to an embodiment of the present invention, FIG. 3 is a block diagram briefly showing the internal configuration of a controller and a remote controller according to an embodiment of the present invention, and FIG. It is a diagram showing an example of a knee motion angle according to an embodiment, and FIG. 5 is a diagram showing a field configuration of surgery-related information according to an embodiment of the present invention.

Rehabilitation exercise device 110 according to an embodiment of the present invention is coupled to the device body 111, the connecting member 112 connected to the end of the device body 111, and the connecting member 112, so that the patient's leg It includes a foldable member 113 for leg support, which is fixed and allows the leg to be bent and straightened during rehabilitation, and a support portion 114 for fixing the foot by inserting the sole of the foot into the end of the foldable member 113 for leg support.

The device body 111 is formed in a shape of a certain length, like a human leg, and a controller 120 formed at the end to control various components and a remote controller 130 connected to the controller 120 by wire or wirelessly includes

The foldable member 113 for leg support includes a connecting member 112, a thigh support 113a, a calf support 113b, and a pivoting connector 113c.

One side of the connection member 112 is coupled to one side of the device body 111 and the other side is coupled to one side of the lower surface of the calf support 113b to move to one side of the device body 111 according to the movement of the calf support 113b. The bonded area is rotated.

The foldable member 113 for supporting the leg is coupled to the connecting member 112 to support and fix the calf of the patient, and is coupled to the calf support 113b by the pivoting connector 113c to support the patient's calf. It includes a thigh support 113a that supports and fixes the thigh.

In the foldable member 113 for supporting the leg, the thigh support 113a and the calf support 113b are rotated around the pivoting connector 113c to be folded at a certain angle and then unfolded.

The device main body 111 has a slide groove 111a of a certain depth dug along the center thereof.

The motorized link member 115 is formed with a certain length in the vertical direction to be inserted into the slide groove 111a of the device body 111 from the lower surface of the calf support 113b.

The motorized link member 115 is formed in a straight line from both sides of the calf support 113b in the downward direction, and a horizontal support coupled to meet in the horizontal direction at each end, and a center portion of the device body 111 on the lower surface of the horizontal support. It includes a vertical support coupled to the slide groove (111a) formed in.

The motorized link member 115 is connected to the driving means 122 formed inside the device main body 111 to the vertical support inserted into the slide groove 111a of the device main body 111, and the driving force of the driving means 122 move back and forth by

The motorized link member 115 is connected to a driving means 122 providing a driving force, and reciprocates back and forth by the driving means 122. At this time, in the foldable member 113 for supporting the leg, the thigh support 113a and the calf support 113b are folded at a certain angle and then unfolded around the pivoting connecting body 113c.

The device body 111 has various driving means 122 for driving the electric link member 115 in the internal space, and a controller housing 121 having a plurality of buttons 121a on the outer surface at one end portion To form a controller 120 consisting of.

Here, the drive means 122 corresponds to the prior art, and may be composed of a cylinder member, a gear member, a gear and a motor, a device connected to a chain member, etc., and is connected to the motorized link member 115 to ) can be moved back and forth in any manner.

The electric link member 115 is moved back and forth along the slide groove 111a of the device body 111 by the driving means 122 to perform horizontal reciprocating motion.

The user terminal 150 is mounted on the terminal cradle 30 erected vertically, and is installed on one side of the patient lying down in order to photograph the rehabilitation exercise of the patient.

The user terminal 150 uses a camera module to take a picture of performing a horizontal reciprocating motion to bend and straighten the leg, and transmits image information including the shooting date information to the rehabilitation exercise management server 140 through the communication network 102. do. The user frequently takes pictures of the rehabilitation exercise and transmits them to an external server (hospital server), and after analyzing the video information, the doctor in charge can comment or contact the patient.

The controller 120 according to an embodiment of the present invention includes a plurality of buttons 121a, a driving means 122, a control unit 123, a display unit 124, and a communication unit inside or outside a controller housing 121 having a predetermined shape. (125) and storage (126).

The plurality of buttons 121a set the motion angle of the patient's knee by the foldable member 113 for leg support, set the driving time of the rehabilitation exercise device 110, and turn on/off the power of the rehabilitation exercise device 110. It is a function button that selects the function to be performed.

The remote control 130 is connected to the controller 120 by wire or wirelessly, and various functions of the controller 120 can be selected and used while the patient is lying down.

The remote controller 130 according to an embodiment of the present invention includes a control button 131, an angle readjustment button 132, an angle initialization button 133, an input unit 134, and a display unit 135.

The remote controller 130 includes a control button 131, an angle readjustment button 132, an angle initialization button 133, an input unit 134, and a display unit 135.

The control button 131 includes a button for setting a knee motion angle, a button for setting a driving time, and a button for controlling power on/off setting.

The angle readjustment button 132 is a button that selects the knee motion angle up to a point desired by the patient as the maximum value when knee pain occurs during a rehabilitation exercise of bending and straightening the patient's leg and the knee motion angle is desired to be reset.

The angle initialization button 133 is a button that initializes the reset knee motion angle selected by the angle readjustment button 132 to zero.

The input unit 134 performs data input functions such as text keys, numeric keys, various function keys, touch screen detection, ID, type of surgery, weight, height, age, degree of injury (high, middle and low), date of surgery, and knee exercise. Surgery-related information 10 including the angle is input.

The display unit 135 outputs knee movement angle, driving time, power on/off state, surgery-related information display, reset knee movement angle, and the like.

The control unit 123 of the controller 120 receives surgery-related information 10 input through the input unit 134 of the remote controller 130 and stores it in the storage unit 126 .

The patient lies down and fixes the thigh and calf to the thigh support 113a and the calf support 113b, and fixes the foot by inserting it into the support 114 for fixing the foot. Subsequently, the patient sets the driving time and knee motion angle using the control button 131 of the remote controller 130, and turns on the power of the rehabilitation exercise device 110.

In general, after surgery, the knee motion angle starts at 60 degrees and gradually increases to 70 degrees, 80 degrees, and 140 degrees. However, depending on the person's weight, age, and type of surgery, the severity of knee pain may vary. 4 shows an example of a knee motion angle.

When the power is turned on using the control button 131 of the controller 120, the controller 123 of the controller 120 controls the driving means 122 to move the electric link member 115 back and forth to bend and straighten the leg. Repeat the action.

The patient presses the angle readjustment button 132 of the remote controller 130 when the angle needs to be readjusted at the angle at which knee pain is felt. For example, if the initial setting of the knee movement angle is set to 60 degrees, and severe knee pain is felt when the knee movement angle is about 50 degrees, the angle readjustment button 132 of the remote control is pressed.

When receiving the ON operation signal of the remote control 130, the controller 123 controls the driving means 122 to adjust the knee movement angle by 1 degree as the electric link member 115 connected to the driving means 122 moves horizontally. The process of horizontally moving forward from 0 degrees to the initially set knee motion angle while increasing is repeated to perform horizontal reciprocating motion.

As another embodiment, the controller 123 checks the set driving time and the set knee motion angle when receiving the on operation signal of the remote controller 130 .

The control unit 123 controls the driving means 122 to perform horizontal reciprocating motion while increasing or decreasing the motorized link member 115 by 1 degree or by 1 degree from 0 degree to an angle obtained by subtracting 10 degrees from the initially set knee motion angle. . At this time, the driving time is the time obtained by subtracting 10 minutes (which can be changed) from the set driving time.

Subsequently, the control unit 123 increases the motorized link member 115 from 0 degrees to the initially set knee motion angle by 1 degree or decreases it by 1 degree for the remaining 10 minutes of driving time to perform horizontal reciprocating motion (122 ) to control.

For example, if the driving time is 25 minutes and the initially set knee motion angle is set to 60 degrees, the controller 123 performs horizontal reciprocating motion while increasing or decreasing by 1 degree from 0 degrees to 50 degrees for 15 minutes, Perform horizontal reciprocating motions from 0 to 60 degrees in 1 minute increments of 1 degree or decrease of 1 degree.

Another embodiment performs a painless rehabilitation exercise to an originally set angular range when the rehabilitation exercise is performed to a painless range and becomes soft.

During the movement of the motorized link member 115, when the control unit 123 receives a selection signal of the angle readjustment button 132 of the remote controller 130, the current knee motion angle is stored together with the angle storage date. ), and by turning off the power of the driving means 122, the motorized link member 115 is controlled not to move horizontally beyond the stored readjusted knee motion angle.

Subsequently, the control unit 123 sets the maximum value of the knee motion angle to the readjusted knee motion angle, and turns on the power of the driving means 122 to horizontally move the motorized link member 115 by 1 degree from the readjusted knee motion angle. The horizontal reciprocating motion is performed by repeating the process of horizontally moving backward to 0 degrees while decreasing and horizontally moving forward from 0 degrees to the readjusted knee motion angle while increasing the knee motion angle by 1 degree.

For example, if the initial setting of the knee motion angle is set to 60 degrees, and knee pain is felt and the angle readjustment button 132 is pressed at 50 degrees, the knee motion angle is then adjusted from 0 degrees to 50 degrees. It makes a horizontal reciprocating motion to bend and straighten.

When receiving the selection signal of the angle initialization button 133, the control unit 123 initializes the knee movement angle stored in the storage unit 126 to 0 degrees.

As shown in FIG. 5 , when the controller 123 stores the readjusted knee motion angle and the date of storing the angle in the storage unit 126, the controller 123 adds and stores the field of surgery-related information 10 that matches the user's ID. do.

The controller 123 calculates the date after surgery by subtracting the date of storing the angle from the date of surgery, adds the calculated date after surgery to the field of the surgery-related information 10 and stores it in the storage unit 126 .

A field of the surgery-related information 10 may be deleted or an additional field may be added.

The surgery-related information 10 stored in the storage unit 126 includes the user's ID, type of surgery, weight, height, age, degree of injury (upper to lower), date of surgery, knee motion angle, date of storage of the angle, date after surgery, and surgery. Contains relevant information (10). Here, the knee motion angle may be an initially set knee motion angle or a knee motion angle readjusted by the angle readjustment button 132 .

5 shows an example of the field configuration of the surgery-related information 10.

The control unit 123 transmits the surgery-related information 10 stored in the storage unit 126 to the rehabilitation exercise management server 140 through the communication unit 125 via the communication network 102 .

When the user terminal 150 receives a selection signal of the remote control mode 21 from the rehabilitation exercise service app 20, the rehabilitation exercise device 110 generates a remote control signal using the ID of the rehabilitation exercise device 110. ) is sent to

When receiving a remote control signal including ID information from the user terminal 150 through the communication unit 125, the control unit 123 of the rehabilitation exercise device 110 extracts the ID information included in the received remote control signal, It is determined whether it is the same as the ID, and if it is the same, the communication channel is connected.

In the remote control mode 21, the same buttons as the button for setting the knee motion angle, the button for setting the driving time, and the button for controlling the power on/off setting provided in the control button 131 of the rehabilitation exercise device 110 Include input means.

The user terminal 150 sets the patient's knee motion angle using various button input means of the remote control mode 21 of the rehabilitation exercise service app 20 while the communication channel with the rehabilitation exercise device 110 is connected. , A driving time of the rehabilitation exercise device 110 is set, and a function of turning on or off the power of the rehabilitation exercise device 110 is selected.

According to these function settings, the user terminal 150 remotely controls the rehabilitation exercise device 110 to control the driving means 122 to reciprocate the electric link member 115 back and forth by the driving force of the driving means 122.

When a patient indoors is elderly or has a disability, a patient guardian holding the user terminal 150 may remotely control the rehabilitation exercise device 110 from the outside to perform rehabilitation exercise.

When receiving a selection signal for the knee motion angle recommendation mode 22 from the rehabilitation exercise service app 20, the user terminal 150 receives and displays the recommended knee motion angle from the rehabilitation exercise management server 140. It will be described in detail with reference to FIG. 6 below.

6 is a diagram showing the configuration of a learning model and an artificial neural processing network of a rehabilitation exercise management server according to an embodiment of the present invention.

The rehabilitation exercise management server 140 according to an embodiment of the present invention includes a wireless communication unit 141, an app manager 142, a server control unit 143, a big data processing unit 144, a learning model unit 160, and artificial neural processing. net 170.

The wireless communication unit 141 communicates with the user terminal 150 through the communication network 102 to collect user data through the rehabilitation exercise service app 20 or transmit and receive data to provide programs and health management auxiliary function services. It performs, and for this purpose, a communication protocol compatible with the communication network 102 is included.

Here, the communication network 102 refers to a connection structure capable of exchanging information between nodes such as terminals and servers, and includes a local area network, a wide area network, and the Internet (World Wide Area Network). Web), wired and wireless data communication networks, telephone networks, and wired and wireless television communication networks.

Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi, Bluetooth communication, infrared communication, ultrasonic communication, visible light communication (VLC: Visible Light Communication), LiFi, and the like, but are not limited thereto.

In addition, the wireless communication unit 141 may further include an API (Application Programming Interface) for functional interworking between the rehabilitation exercise service app 20 and compatible server management programs.

The app management unit 142 creates and manages rehabilitation exercise service apps 20 that are executed in the user terminal 150 and provides the rehabilitation exercise service apps 20 to various devices (user terminals, etc.).

The app management unit 142 provides a user-customized rehabilitation exercise recommendation program to the user terminal 150 through the rehabilitation exercise service app 20 running on the user terminal 150, and performs specific detailed functions such as providing statistical data. It is possible to provide recommended knee motion angle information for rehabilitation exercise service.

The server control unit 143 receives surgery-related information 10 from the rehabilitation exercise device 110 through the wireless communication unit 141 and stores it in the big data processing unit 144 .

The big data processing unit 144 stores personal information such as a name, address, and phone number corresponding to a person's ID.

The big data processing unit 144 stores surgery-related information 10 and personal information by matching the user's ID.

The rehabilitation exercise management server 140 receives a plurality of surgery-related information 10 from the rehabilitation exercise device 110, stores them in the big data processing unit 144, and matches knee motion angles corresponding to the surgery-related information 10. Sort and save.

The rehabilitation exercise management server 140 inputs a plurality of surgery-related information 10 to the artificial neural processing network 170 and, in response to the artificial neural processing network 170, recommends a knee exercise corresponding to the surgery-related information 10. output the angle

The surgery-related information 10 may include a plurality of pieces of information among type of surgery, weight, height, age, degree of injury (high, middle, and low), and days after surgery.

The recommended knee motion angle indicates a knee motion angle matched with the surgery-related information 10 or a readjusted knee motion angle.

The rehabilitation exercise management server 140 stores knee motion angles in the big data processing unit 144 according to the type of surgery, weight, height, age, degree of injury, and elapsed days after surgery.

The rehabilitation exercise management server 140 inputs a plurality of surgery-related information 10 to the artificial neural processing network, and outputs a recommended knee motion angle corresponding to the surgery-related information 10 as a response of the artificial neural processing network 170. and stored in the big data processing unit 144.

The recommended knee motion angle has the effect of controlling pain and maximizing the effect of rehabilitation exercise due to the optimal motion angle.

The rehabilitation exercise management server 140 databases the recommended knee motion angles corresponding to the surgery-related information 10 through the learning model unit 160 and the artificial neural processing network 170 and stores them in the big data processing unit 144. .

The rehabilitation exercise management server 140 uses the learning model unit 160 and the artificial neural processing network 170 to derive the optimal knee motion angle according to the type of surgery, weight, height, age, degree of injury, and postoperative days. pay

The rehabilitation exercise management server 140 calculates different optimized knee motion angles for each postoperative day (60 degrees on the first day, 70 degrees on the second day, etc.) according to the type of surgery, weight, height, age, and degree of injury. can

The rehabilitation exercise management server 140 databases the surgery-related information 10 of the type of surgery, weight, height, age, degree of injury, elapsed days after surgery, and the readjusted knee motion angle from the rehabilitation exercise device 110 to a big data processing unit. Save to (144).

The rehabilitation motion management server 140 derives the optimal knee motion angle for the next day by analyzing the readjusted knee motion angle where knee pain occurred the previous day in the database of surgery-related information 10 of the big data processing unit 144. can do.

The rehabilitation exercise management server 140 uses the learning model unit 160 and the artificial neural processing network 170 to optimize the optimal motion according to the type of surgery, weight, height, age, degree of injury, postoperative day, and readjusted knee motion angle. derives the knee motion angle of

The rehabilitation exercise management server 140 uses the learning model unit 160 and the artificial neural processing network 170 to derive an optimal knee motion angle for the next day according to the postoperative day and the readjusted knee motion angle of the previous day.

The rehabilitation exercise management server 140 uses the big data processing unit 144, the learning model unit 160, and the artificial neural processing network 170 to adjust the type of surgery, weight, height, age, degree of injury, postoperative day and readjusted data. The pain level scale is analyzed using the knee motion angle, and the optimal knee motion angle is calculated according to the type of surgery, weight, height, age, degree of injury, and postoperative days.

The server controller 143 provides the optimal knee motion angle to the user terminal 150 through the wireless communication unit 141 .

When the user terminal 150 receives a selection signal for the knee motion angle recommendation mode 22 from the rehabilitation exercise service app 20, the type of surgery, weight, height, age, degree of injury, postoperative day, and readjusted knee exercise An input means for inputting surgery-related information 10 for inputting one or more information among angles is output.

When the user terminal 150 receives the surgery-related information 10 , it generates a request signal for a knee motion angle including the surgery-related information 10 and transmits it to the rehabilitation exercise management server 140 .

When receiving a request signal for the knee movement angle from the user terminal 150, the rehabilitation exercise management server 140 extracts surgery-related information 10 included in the request signal, and converts the extracted surgery-related information 10 into a learning model. By substituting into the unit 160, a recommended knee motion angle is generated.

The rehabilitation exercise management server 140 transmits the generated recommended knee motion angle to the user terminal 150 through the wireless communication unit 141 .

The data set stored in the big data processor 144 is further divided into a training set and a test set. The training set is fed to a machine learning or deep learning model.

The learning model unit 160 includes a data processing unit 161, a learning unit 162, and a classification unit 163.

The artificial neural processing network 170 includes an input layer 171, a convolution layer unit 173, a pooling layer unit 174 and a hidden layer 172 composed of a fully connected layer unit 175, and an output layer 176 do.

The data processing unit 161 receives a training set consisting of a plurality of vectorized surgery-related information 10 from the big data processing unit 144 and transmits it to the artificial neural processing network 170 . A training set represents training data.

The data processing unit 161 receives a training set consisting of a plurality of surgery-related information 10 vectorized in the data set from the data collection unit 140 and transmits it to the artificial neural processing network 170 .

The data processing unit 161 receives a test set consisting of a plurality of surgery-related information 10 vectorized in the data set from the data collection unit 140 and transmits it to the classification unit 163 .

The data processing unit 161 may be formed as a database unit capable of distributed parallel processing.

The artificial neural processing network 170 inputs and applies a training set consisting of a plurality of vectorized surgery-related information 10 to the artificial neural processing network 170 to correct errors, and uses the corrected errors to apply the training set. Whether or not the prediction result of the recommended knee motion angle is output.

The artificial neural processing network 170 inputs and applies a training set consisting of a plurality of vectorized surgery-related information 10 to the artificial neural processing network 170 to correct errors, and uses the corrected errors to apply the training set. A recommended knee motion angle result corresponding to the surgery-related information 10 is output.

In this case, the artificial neural processing network 170 may use deep convolutional neural networks (CNNs) and include an input layer 171, a hidden layer 172, and an output layer 176.

The artificial neural processing network 170 uses a neural network-based model for predictive analysis.

The artificial neural processing network 170 includes an input layer 171 x, an output layer 176 y, and an arbitrary amount of hidden layers 172 containing four neurons.

Each layer, except for the output layer 176, consists of a set of biases and weights denoted by band W. The sigmoid function is used as the activation function of each hidden layer. Bias and weight fine-tuning of the input data is performed to improve the model's prediction score. In the training process, each iteration includes the following steps:

A training process of the neural network model consisting of two steps, feed-forward including calculation of the predicted output layer 176 y and back-propagation updating weights and biases, is performed.

The artificial neural processing network 170 performs back propagation to measure the error of prediction loss, and measures the prediction error (loss).

The derivative of the loss function with respect to biases and weights is used to adjust the weights and biases.

The input layer 171 acquires the learning data stored in the data processing unit 161 and stores the acquired learning data as a layer having a feature map. Here, the feature map has a structure in which a plurality of nodes are arranged in two dimensions, so that connection with the hidden layer 172 described later can be facilitated.

The hidden layer 172 obtains a feature map of a layer located in an upper layer, and gradually extracts higher level features from the obtained feature map. One or more hidden layers 172 may be formed and include a convolution layer part 173 , a pooling layer part 174 and a pulley connected layer part 175 .

The convolution layer unit 173 is a component that performs a convolution operation on learning data, and includes a feature map connected to a plurality of input feature maps.

The pooling layer unit 174 is a component that receives the output of the convolution layer unit 173 as an input and performs a convolution operation, that is, a subsampling operation, and the convolution layer unit 173 located in the lower layer of the hidden layer 172 includes the same number of feature maps as the number of input feature maps, and each feature map is connected to the input feature map one-to-one.

The fully connected layer unit 175 receives the output of the convolution layer unit 173 as an input and learns according to the output of each category output from the output layer 130, and integrates the learned local information, that is, features. to learn abstract content.

At this time, when the hidden layer 172 includes the pooling layer unit 172, the polling connected layer unit 175 is connected to the polling layer unit 174, and features are synthesized from the output of the polling layer unit 174. Learn abstract content.

The output layer 176 maps an output for each category desired to be classified into a probability value using a function such as soft-max. In this case, the result output from the output layer 176 may be transmitted to the learning unit 162 or the classification unit 163 to perform error backpropagation or may be output as response data.

The learning unit 162 performs supervised learning, which infers a function by applying a machine learning algorithm to learning data, and finds an answer through the inferred function.

The learning unit 162 may generate a linear model representing the learning data through supervised learning and predict future events through the linear model.

The learning unit 162 determines how new data is classified into previously learned data based on previously learned data.

The learning unit 162 performs learning of the artificial neural processing network 170 on a training set consisting of a plurality of surgery-related information 10 vectorized in a data set from the data processing unit 161, and deep learning for each type. A recommended knee motion angle corresponding to the surgery-related information 10 is learned using the feature value.

The learning unit 162 learns a recommended knee motion angle corresponding to the surgery-related information 10 from the artificial neural processing network 170 using deep learning feature values for each type.

In one embodiment of the present invention, learning of the artificial neural processing network 170 is performed by supervised-learning.

Supervised learning is a method of inputting training data and output data corresponding thereto to the artificial neural processing network 170 and updating weights of connected edges so that output data corresponding to the training data is output. For example, the artificial neural processing network 170 of the present invention may update connection weights between artificial neurons using the delta rule and error backpropagation learning.

Error-back-propagation learning estimates errors by feed-forward for given training data, and then estimates in the reverse direction, starting from the output layer and toward the hidden layer 172 and the input layer 171 An error is propagated, and connection weights between artificial neurons are updated in the direction of reducing the error.

The artificial neural processing network 170 calculates an error from the result obtained through the input layer 171 - hidden layer 172 - polling connected layer unit 175 - output layer 176, and corrects the calculated error. Again, the connection weight may be updated by propagating errors in the order of the output layer 176 - the polling connected layer unit 175 - the hidden layer 172 - the input layer 171.

The learning unit 162 becomes an input vector with a training set consisting of the surgery-related information 10 and the recommended knee motion angle, and passes through the input layer 171, the hidden layer 172, and the output layer 176, It is learned through supervised learning to generate a recommended knee motion angle corresponding to the surgery-related information 10 as an output vector.

The learning unit 162 uses the artificial neural processing network 170, and the feature values of the plurality of surgery-related information 10 that are input become input vectors, and the input layer 171, the hidden layer 172, and the output layer 176 If it passes, it is learned through supervised learning to generate a recommended knee motion angle corresponding to the plurality of surgery-related information 10 as an output vector.

The learning unit 162 uses the recommended knee movement angle corresponding to the plurality of surgery-related information 10 as learning data and learns with artificial intelligence in conjunction with the artificial neural processing network 170 .

The learning unit 162 may use a knee motion angle prediction model that predicts a recommended knee motion angle in response to the plurality of surgery-related information 10 as a training data set for machine learning.

The learning unit 162 loads a knee motion angle prediction model into a memory unit (not shown) and performs machine learning to predict a recommended knee motion angle using feature vectors of a plurality of surgery-related information 10 as input data.

When an input value (a plurality of surgery-related information 10) is input, the artificial neural processing network 170 knows in advance whether an output value (a recommended knee motion angle corresponding to the plurality of surgery-related information 10) should come out.

The classification unit 163 may output output data of the artificial neural processing network 170 having connection weights updated through error backpropagation in the learning unit 162 as response data.

The classification unit 163, when learning data, test data, or new data not used for learning is input to the artificial neural processing network 170 having updated connection weights, input layer 171 - hidden layer 172 - polling connection The result output through the tid layer unit 175-output layer 176 may be obtained and output as response data.

The artificial neural processing network 170 generates a deep learning-based classifier model through optimization based on recommended knee motion angles corresponding to the input plurality of surgery-related information 10 .

The learning unit 162 may differently apply individual element weights related to the layers in the artificial neural processing network and the connection strength between the layers according to the plurality of surgery-related information 10 .

The learning unit 162 learns through supervised learning to generate the recommended knee motion angle result as an output vector, calculates the direction from the input layer 171 to the output layer 176, and conversely from the output layer 176 to the input layer 171 ) direction, the error is minimized by correcting the weight while repeating the calculation operation.

The classification unit 163 outputs the input plurality of surgery-related information 10, which is test data, as result values of response data (recommended knee motion angle results) by using the deep learning-based classifier model of the artificial neural processing network 170. do.

The classification unit 163 outputs a recommended knee motion angle result in response to the vectorized plurality of surgery-related information 10 .

The classification unit 163 outputs a recommended knee motion angle by using the deep learning-based classifier model of the artificial neural processing network 170 for the input plurality of surgery-related information 10 as test data.

The output unit 164 displays the recommended knee motion angle received from the classification unit 163 on the screen.

Operations according to the embodiments of the present specification can be implemented as computer-readable programs or codes on a computer-readable recording medium. A computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored. In addition, computer-readable recording media may be distributed to computer systems connected through a network to store and execute computer-readable programs or codes in a distributed manner.

When the embodiment is implemented as software, the above-described technique may be implemented as a module (process, function, etc.) that performs the above-described functions. A module can be stored in memory and executed by a processor. The memory may be internal or external to the processor, and may be coupled with the processor in a variety of well-known means.

In addition, the computer-readable recording medium may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, and flash memory. The program command may include high-level language codes that can be executed by a computer using an interpreter or the like as well as machine code generated by a compiler.

Although some aspects of the present invention have been described in the context of an apparatus, it may also represent a description according to a corresponding method, where a block or apparatus corresponds to a method step or feature of a method step. Similarly, aspects described in the context of a method may also be represented by a corresponding block or item or a corresponding feature of a device. Some or all of the method steps may be performed by (or using) a hardware device such as, for example, a microprocessor, programmable computer or electronic circuitry. In some embodiments, one or more of the most important method steps may be performed by such an apparatus.

In embodiments, a programmable logic device (eg, a field programmable gate array) may be used to perform some or all of the functions of the methods described herein. In embodiments, a field programmable gate array may operate in conjunction with a microprocessor to perform one of the methods described herein. Generally, methods are preferably performed by some hardware device.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will variously modify and change the present invention within the scope not departing from the spirit and scope of the present invention described in the claims below. You will understand that it can be done.

100: rehabilitation exercise system 102: communication network
110: rehabilitation exercise device 111: device body
111a: slide groove 112: connecting member
113: foldable member for leg support 113a: thigh support
113b: calf support 113c: pivot link
114: support for fixing feet 115: motorized link member
120: controller 121: controller housing
121a: button 122: driving means
123: control unit 124: display unit
125: communication unit 126: storage unit
130: remote control 131: control button
132: angle readjustment button 133: angle initialization button
134: input unit 135: display unit
140: rehabilitation exercise management server 150: user terminal

Claims (5)

A device body having a slide groove of a certain depth along the center and having a controller at one end, a connecting member connected to one side of the device body, and a calf support coupled to the connecting member to support and fix the patient's calf A foldable member for leg support consisting of a thigh support connected to the calf support by a rotational connector to support and fix the patient's thigh, and a lower surface of the foldable member for leg support to be inserted into the slide groove of the main body of the device. An electric link member having a certain length is coupled in the vertical direction, the electric link member is connected to a driving means formed inside the device body, and when reciprocating back and forth by the driving force of the driving means, the calf support and the thigh support are a rehabilitation exercise device that bends and straightens the patient's leg while being rotated around the rotation connector and folded at a certain angle and then unfolded; and
A control button electrically connected to the controller to control knee motion angle setting, drive time setting, power on/off setting, and knee pain during rehabilitation exercise of bending and straightening the patient's leg, thereby resetting the knee motion angle And a remote control having an angle readjustment button for performing angle readjustment if desired,
When the power is turned on using the control button of the remote control, the controller controls the driving means to move the motorized link member back and forth to repeat the bending and stretching of the leg, and the angle needs to be readjusted at an angle where knee pain is felt. When receiving a selection signal of the angle readjustment button of the remote controller, the current readjusted knee motion angle is stored in a storage unit together with the angle storage date, and the readjusted electric link member is moved from 0 degrees by controlling the driving means. Further comprising a control unit for controlling to perform horizontal reciprocating motion while increasing or decreasing by 1 degree until the knee movement angle,
The control unit drives the motorized link member to horizontally reciprocate while increasing or decreasing by 1 degree from 0 degree to an angle obtained by subtracting 10 degrees from the initially set knee motion angle for a time period obtained by subtracting 10 minutes from the set driving time. control means, and control the drive means to horizontally reciprocate while increasing or decreasing the motorized link member by 1 degree or by 1 degree until the initially set knee motion angle for the remaining 10 minutes,
A user with a built-in rehabilitation exercise service app in a remote control mode that drives and controls the rehabilitation exercise device indoors from the outside and a knee motion angle recommendation mode that recommends a knee motion angle to be used during rehabilitation based on the user's surgery-related information Including more terminals,
When receiving a remote control mode selection signal from the rehabilitation exercise service app, the user terminal generates a remote control signal using the ID of the rehabilitation exercise device and transmits the remote control signal to the rehabilitation exercise device, and communicates with the rehabilitation exercise device. In a state in which the communication channel is connected, the function of setting the knee motion angle of the patient using the button input means of the remote control mode, setting the driving time of the rehabilitation exercise device, and turning on and off the power of the rehabilitation exercise device and performs rehabilitation by controlling the rehabilitation exercise device remotely from the outside, and when the patient in the room is elderly or has a disability, the user terminal remotely controls the rehabilitation exercise device from the outside to perform rehabilitation exercise. rehabilitation exercise system. The method of claim 1,
The remote control further includes an input unit for receiving surgery-related information including ID, type of surgery, weight, height, age, degree of injury (high, medium and low), surgery date, knee motion angle, angle storage date, and date after surgery. exercise system. The method of claim 2,
When the readjusted knee motion angle is stored in the storage unit together with the angle storage date, the control unit adds and stores the surgery-related information field, and subtracts the angle storage date from the surgery date. Rehabilitation exercise system for calculating, adding the calculated number of days elapsed after surgery to a field of surgery-related information and storing it in the storage unit. The method of claim 3,
The type of surgery, weight, height, age, degree of injury, days after surgery, and surgery-related information of the knee motion angle matching the readjusted knee motion angle from the rehabilitation exercise device are databased and stored in the big data processing unit, and the big data In the database of surgery-related information of the processing unit, a rehabilitation exercise management server that analyzes the readjusted knee motion angle where knee pain occurred the previous day to derive an optimal knee motion angle for the next day,
The control unit transmits the surgery-related information to an external rehabilitation exercise management server through a communication unit, and the rehabilitation exercise management server inputs a plurality of surgery-related information to an artificial neural processing network, and receives a response from the artificial neural processing network. outputs a recommended knee motion angle corresponding to the related information;
The recommended knee motion angle is a knee motion angle matched to the surgery-related information or the readjusted knee motion angle,
The user terminal receives and displays the recommended knee motion angle from the rehabilitation exercise management server when receiving a selection signal for a knee motion angle recommendation mode from the rehabilitation exercise service app. The method of claim 4,
The rehabilitation exercise management server calculates different optimized knee motion angles for each postoperative day according to the type of surgery, weight, height, age, and degree of injury.

Images