Method and apparatus for controlling medical device

Abstract

This invention discloses a control method and apparatus for medical devices, relating to the field of medical technology development. It primarily addresses the problem of low control accuracy in moxibustion robots. The method mainly includes: acquiring image information of acupoint reference objects through an image sensor located on the corresponding robotic arm of the medical device; identifying the planar and vertical coordinates of the acupoints after determining that the image information contains all the image features of the acupoint reference objects; determining the running time and path of at least one target acupoint after identifying it for moxibustion, and controlling the robotic arm to move according to the running time and path; monitoring the positional deviation of the acupoint reference objects in real time during moxibustion according to the running time and path; and controlling the robotic arm to move based on the positional deviation when the positional deviation exceeds the maximum deviation value for moxibustion. This method is mainly used to control moxibustion robots.

Description

Technical Field

[0001] This invention relates to the field of medical technology development technology, and in particular to a control method and device for medical equipment. Background Technology

[0002] As people's understanding of Traditional Chinese Medicine (TCM) deepens, moxibustion has gradually become one of the mainstream methods of modern health preservation, enjoying widespread social acceptance. With the development of modern science and technology, automated and intelligent moxibustion equipment is beginning to replace manual labor, and various moxibustion robots are gradually being promoted and applied to people's daily health maintenance.

[0003] Currently, existing moxibustion robots typically move along pre-programmed acupoint paths to apply moxibustion at designated locations. However, since patients are usually not completely still during the treatment, simply controlling the robot's movement along pre-set paths can lead to misalignment or even incorrect acupoint application. Repeatedly calibrating the acupoint and path positions involves numerous tedious operations, compromising the accuracy of moxibustion and significantly impacting the robot's control accuracy and the effectiveness of the therapy. Summary of the Invention

[0004] In view of this, the present invention provides a control method and apparatus for medical devices, the main purpose of which is to solve the problem of low control accuracy of existing moxibustion robots.

[0005] According to one aspect of the present invention, a method for controlling a medical device is provided, comprising:

[0006] Image information of acupoint reference objects is acquired by an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers that are pre-placed on multiple human acupoints.

[0007] Once it is determined that the image information contains all the image features of the acupoint reference object, the planar coordinates and vertical coordinates of the human acupoint are identified.

[0008] Once at least one target acupoint for moxibustion is determined, the running time and running path of the target acupoint are determined, and the robotic arm is controlled to move according to the running time and the running path.

[0009] During the moxibustion process according to the specified running time and running path, the positional deviation of the acupoint reference object is monitored in real time.

[0010] When the positional deviation is greater than the maximum deviation value for moxibustion, the robotic arm is controlled to move based on the positional deviation.

[0011] Furthermore, acquiring image information of the acupoint reference object through an image sensor located on the corresponding robotic arm of the medical device includes:

[0012] With the image sensor activated, the robotic arm is driven to move within a pre-defined acupuncture area, and image information containing the acupoint reference object is extracted from the image video stream data. The pre-defined acupuncture area includes the movement area corresponding to different human body shapes and the image scanning path.

[0013] The acupoint reference object is a patch with a circular outer outline and a square hole in the middle. The patch color is different for different acupoints on different human bodies.

[0014] Furthermore, the identification of the planar coordinates and vertical coordinates of the acupoints includes:

[0015] Extract the first coordinate position of the square image feature and the second coordinate position of the circular image feature from the image features;

[0016] Construct planar coordinates relative to the center point of the human acupoint based on the first coordinate position and the second coordinate position; and determine the vertical coordinates based on the difference between the first coordinate position, the second coordinate position and the distance to the preset vertical plane.

[0017] Furthermore, the method also includes:

[0018] Feature extraction is performed on the image information, and the image information containing all extracted features is filtered according to the integrity status information of the square image features and the circular image features to obtain all image features containing the acupoint reference object.

[0019] Furthermore, determining the running time and running path of the target acupoint, and controlling the robotic arm to move according to the running time and the running path includes:

[0020] The running time and running path of the target acupoints are determined according to the number of acupoints to be moxibusted and the initial posture of the moxibustion. The running time includes the total running time and the individual running time, and the running path includes the planar running path and the vertical running path.

[0021] During the process of controlling the robotic arm to move according to the running time and the running path, the posture information of the moxibustion head is detected;

[0022] If the offset of the posture information is greater than a preset offset, the movement position of the robotic arm is adjusted based on the offset.

[0023] Furthermore, the real-time monitoring of the positional deviation of the acupoint reference object includes:

[0024] The third coordinate position of the square image feature and the fourth coordinate position of the circular image feature of the acupoint reference object are collected in real time.

[0025] The position difference between the third coordinate position and the first coordinate position is calculated and determined as the horizontal position deviation, and the position difference between the fourth coordinate position and the second coordinate position is calculated and determined as the vertical position deviation.

[0026] Furthermore, the method also includes:

[0027] Obtain the initial location network of the constructed target acupoints;

[0028] During the movement of the robotic arm, the real-time position of the robotic arm that is performing moxibustion is obtained;

[0029] If the real-time location is within the initial location network, then the medical device is confirmed to be operating correctly.

[0030] If the real-time location is not in the initial location network, the human moxibustion strategy library is retrieved, and if the real-time location does not match an acupoint in the human moxibustion strategy library, an alarm message for abnormal control of the medical device is sent.

[0031] According to another aspect of the present invention, a control device for a medical device is provided, comprising:

[0032] The acquisition module is used to acquire image information of acupoint reference objects through an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers pre-placed on multiple human acupoints.

[0033] The recognition module is used to recognize the planar coordinates and vertical coordinates of the human acupoint after determining that the image information contains all the image features of the acupoint reference object.

[0034] The first control module is used to determine the running time and running path of the target acupoint after determining at least one target acupoint to be treated with moxibustion, and to control the robotic arm to move according to the running time and the running path.

[0035] The monitoring module is used to monitor the positional deviation of the acupoint reference object in real time during the moxibustion process according to the running time and the running path;

[0036] The second control module is used to control the robotic arm to move based on the position deviation when the position deviation is greater than the maximum deviation value for moxibustion.

[0037] Furthermore, the acquisition module includes:

[0038] The first extraction unit is used to drive the robotic arm to move within a pre-set moxibustion area when the image sensor is turned on, and to extract image information containing the acupoint reference object from the image video stream data. The pre-set moxibustion area includes the movement area corresponding to different human body shapes and the image scanning path.

[0039] The acupoint reference object is a patch with a circular outer outline and a square hole in the middle. The patch color is different for different acupoints on different human bodies.

[0040] Furthermore, the identification module includes:

[0041] The second extraction unit is used to extract the first coordinate position of the square image feature and the second coordinate position of the circular image feature from the image features.

[0042] Construct planar coordinates relative to the center point of the human acupoint based on the first coordinate position and the second coordinate position; and determine the vertical coordinates based on the difference between the first coordinate position, the second coordinate position and the distance to the preset vertical plane.

[0043] Furthermore, the device also includes:

[0044] The extraction module is used to extract features from the image information and filter the image information containing all extracted features according to the integrity status information of the square image features and the circular image features, so as to obtain all image features containing the acupoint reference object.

[0045] Furthermore, the first control module includes:

[0046] The determining unit is used to determine the running time and running path of the target acupoints according to the number of moxibustion applications and the initial posture of the moxibustion application. The running time includes the total running time and the individual running time, and the running path includes the planar running path and the vertical running path.

[0047] The detection unit is used to detect the posture information of the moxibustion head during the process of controlling the robotic arm to move according to the running time and the running path;

[0048] An adjustment unit is used to adjust the movement position of the robotic arm based on the offset if the offset of the posture information is greater than a preset offset.

[0049] Furthermore, the monitoring module includes:

[0050] The acquisition unit is used to acquire in real time the third coordinate position of the square image features and the fourth coordinate position of the circular image features of the acupoint reference object;

[0051] The calculation unit is used to calculate the position difference between the third coordinate position and the first coordinate position, determine it as the horizontal position deviation, and calculate the position difference between the fourth coordinate position and the second coordinate position, determine it as the vertical position deviation.

[0052] Furthermore, the device also includes:

[0053] The acquisition module is also used to acquire the initial position network of the constructed target human acupoints;

[0054] The acquisition module is also used to acquire the real-time position of the robotic arm that is performing moxibustion during the movement of the robotic arm;

[0055] The confirmation module is used to confirm that the medical device is operating correctly if the real-time location is within the initial location network.

[0056] The sending module is used to retrieve the human moxibustion strategy library if the real-time location is not in the initial location network, and send the medical device control abnormality alarm information when the real-time location does not match the acupoints in the human moxibustion strategy library.

[0057] According to another aspect of the present invention, a storage medium is provided, wherein at least one executable instruction is stored therein, the executable instruction causing a processor to perform an operation corresponding to the control method of the medical device described above.

[0058] According to another aspect of the present invention, a terminal is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0059] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the control method of the above-mentioned medical device.

[0060] By employing the above-described technical solutions, the technical solutions provided by the embodiments of the present invention have at least the following advantages:

[0061] This invention provides a control method and apparatus for a medical device. Compared with the prior art, the embodiments of this invention acquire image information of acupoint reference objects through an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers pre-placed on multiple human acupoints. After determining that the image information contains all the image features of the acupoint reference objects, the planar coordinates and vertical coordinates of the human acupoints are identified. After determining at least one target human acupoint to be treated with moxibustion, the running time and running path of the target human acupoint are determined, and the robotic arm is controlled to move according to the running time and running path. During the moxibustion process according to the running time and running path, the positional deviation of the acupoint reference objects is monitored in real time. When the positional deviation is greater than the maximum deviation value for moxibustion, the robotic arm is controlled to move based on the positional deviation. Through the configuration of the acupoint reference objects, accurate positioning of the acupoints to be treated with moxibustion is achieved. When the acupoint position deviates, the deviation can be automatically corrected in time, avoiding the intervention of manual calibration, greatly reducing the cumbersomeness of equipment operation, and thus effectively improving the control accuracy and effectiveness of the moxibustion equipment.

[0062] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above features and advantages of the present invention more obvious and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0063] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0064] Figure 1 A flowchart of a control method for a medical device provided by an embodiment of the present invention is shown;

[0065] Figure 2 A schematic diagram of an acupoint marking patch provided in an embodiment of the present invention is shown;

[0066] Figure 3 A flowchart of another control method for a medical device provided by an embodiment of the present invention is shown;

[0067] Figure 4 This diagram illustrates a block diagram of a control device for a medical device according to an embodiment of the present invention.

[0068] Figure 5 A schematic diagram of the structure of a terminal provided in an embodiment of the present invention is shown. Detailed Implementation

[0069] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0070] This invention provides a control method for a medical device, such as... Figure 1 As shown, the method includes:

[0071] 101. Obtain image information of the acupoint reference object through the image sensor located on the corresponding robotic arm of the medical device.

[0072] In this embodiment of the invention, the medical device is a moxibustion device, specifically a moxibustion robot. This moxibustion robot includes a movable robotic arm equipped with a fixing device for gripping and moving the moxa stick, and an image sensor for acquiring image information. Moxibustion is applied to acupoints by moving the robotic arm that grips the moxa stick. To ensure the robotic arm can accurately move to the acupoints to be treated, the image sensor acquires an image of a reference object for the acupoints. This reference object is a marker pre-placed on multiple acupoints. For example, if ten acupoints need to be marked, the moxibustion practitioner affixes markers of different colors to the corresponding acupoints. The marker, used to mark the acupoints to be treated, is an adhesive material containing an open area and capable of being fixed to the body; preferably, it is a medicated patch that promotes the therapeutic effect of moxibustion. The shape of the opening area can be square, circular, rhomboid, etc., and the outline of the adhesive can also be square, circular, rhomboid, etc. The non-opening area can be decorated with markings, which can be concentric circles, squares, ovals, etc., or other text or patterns. This embodiment of the invention does not specifically limit the overall dimensions of the adhesive or the size of the opening geometry. The number of acupoints corresponding to the markings and the names of the acupoints can be customized according to specific application needs; this embodiment of the invention does not specifically limit these. The clamping component of the moxa stick is also equipped with a gravity sensor to ensure that the moxa stick does not fall off or is used up.

[0073] 102. After determining that the image information contains all the image features of the acupoint reference object, identify the planar coordinates and vertical coordinates of the human acupoint.

[0074] In this embodiment of the invention, all image features refer to all pattern features of the marker corresponding to any acupoint, for example, Figure 2This is an acupoint marker sticker. The square opening, circular pattern, text, and certain specific colors in the sticker constitute all the image features of the marker. Since image information is acquired during the movement of the robotic arm, the image sensor's viewing angle may be limited, resulting in incomplete image acquisition of the acupoint reference object. For example, the image sensor may only capture half or one-third of the marker's pattern. In such cases, using an incomplete marker pattern to locate the acupoint can easily lead to significant positioning errors. Therefore, it is necessary to determine the marker's features. Only when the acquired image information contains all the marker's image features can the planar and vertical coordinates of the corresponding acupoint be further identified. The planar and vertical coordinates are the marker's coordinates in the machine coordinate system.

[0075] 103. After determining at least one target acupoint to be treated with moxibustion, determine the running time and running path of the target acupoint, and control the robotic arm to move according to the running time and the running path.

[0076] In this embodiment of the invention, after identifying at least one marker containing all image features from the image information, it can be further determined whether the acupoint corresponding to the marker is at least one target acupoint requiring moxibustion, and the running time and running path of the target acupoint are determined so that the robotic arm performs moxibustion according to the running time and running path. The running time may include the moxibustion time corresponding to each target acupoint, and may also include the movement time of the robotic arm between various target acupoints, and the total time required to complete the moxibustion of all target acupoints; this embodiment of the invention does not impose specific limitations. The running path is the robotic arm movement path calculated based on the coordinate information corresponding to the target acupoint.

[0077] It should be noted that by pre-setting markers on acupoints on the human body and acquiring image information of the markers through image sensors on the robotic arm, the accuracy of identifying and locating the target acupoints for moxibustion can be greatly improved. Combined with the running time and running path of different target acupoints, the robotic arm can perform moxibustion on different acupoints in a more targeted manner, thereby improving the control accuracy of the moxibustion robot.

[0078] 104. During the moxibustion process according to the running time and the running path, the positional deviation of the acupoint reference object is monitored in real time.

[0079] 105. When the position deviation is greater than the maximum deviation value for moxibustion, the robotic arm is controlled to move based on the position deviation.

[0080] In this embodiment of the invention, the positional deviation of the acupoint reference object is monitored in real time during moxibustion. The positional deviation can be calculated based on the current coordinates and initial coordinates of the acupoint reference object, or it can be calculated based on the positional change deviation of the marker image; this embodiment of the invention does not impose a specific limitation. The maximum deviation value is used to characterize the maximum allowable deviation value that does not affect the moxibustion effect. If the positional deviation is less than or equal to the maximum deviation value, it indicates that the positional deviation does not affect the normal progress of moxibustion at the current acupoint, and no adjustment is required. If the positional deviation is greater than the maximum deviation value, it indicates that the positional deviation poses a risk of affecting the moxibustion effect at the current acupoint, and the robotic arm is moved according to the positional deviation to correct the positional deviation.

[0081] It should be noted that since the object of moxibustion is the human body, movement of the human body during the moxibustion process is inevitable. Accordingly, the acupoint reference object pre-placed on the human body will shift in position as the human body moves. Real-time monitoring of the positional deviation of the acupoint reference object and timely correction of positional deviations that affect the moxibustion effect can avoid the human body's movements from affecting the accuracy of the moxibustion robot's moxibustion position, thereby further improving the accuracy of the moxibustion robot's moxibustion.

[0082] In one embodiment of the present invention, for further explanation and limitation, such as Figure 3 As shown, the step of acquiring image information of the acupoint reference object through an image sensor located on the corresponding robotic arm of the medical device includes:

[0083] 201. With the image sensor activated, drive the robotic arm to move within the pre-set acupuncture area.

[0084] 202. Extract image information containing the acupoint reference object from the image video stream data.

[0085] In this embodiment of the invention, the image sensor is a sensor of a binocular camera module, which is mounted on the moxibustion head at the end of the robotic arm. Before using the camera, the camera_calibration package in ROS (Robot Operating System software package) needs to be used to calibrate the camera using a checkerboard calibration board to obtain the intrinsic parameters K1 and distortion coefficients D of the binocular camera. Based on the hand-eye calibration method commonly used in computer vision, calibration is performed using the "eye on hand" method to obtain the change matrix of the left eye camera relative to the moxibustion head. The moxibustion head is then moved to its initial position to activate the image sensor. The pre-set moxibustion area includes movement regions and image scanning paths corresponding to different human body types. To obtain image information of the acupoint reference object, comprehensive image information of the human body or localized body parts to be treated needs to be acquired using the image sensor. Before driving the robotic arm, movement regions and image scanning paths with a higher degree of adaptation to the current human body type can be matched from the pre-set moxibustion area, allowing the robotic arm to perform image scanning according to movement regions and image scanning paths that better suit the current human body type. Due to significant differences in individual body types, for example, the back area of ​​a person weighing 90 catties may differ by nearly double from that of a person weighing 200 catties. Matching the corresponding movement regions and image scanning paths according to different human body types for image acquisition can avoid incomplete image acquisition or excessive invalid image information, thereby effectively improving the accuracy of image acquisition.

[0086] After image scanning is completed, image information containing only acupoint reference objects is extracted from the acquired image and video data stream to filter the image information, reduce the amount of image information to be identified, and extract only the effective image information to facilitate subsequent identification of acupoint reference objects.

[0087] It should be noted that the acupoint reference object is a patch with a circular outer outline and a square hole in the center. The patch color varies depending on the acupoint. As shown in Figure 2, which is a schematic diagram of the shape of the acupoint reference object, the area indicated by 1 is the color-coded area. Different colored non-woven fabrics are used in this area to distinguish different acupoints, allowing for identification of the corresponding acupoints based on color. The material of areas 2 and 3 is non-woven fabric. The area between the square and the ring indicated by 2 is a medicinal cake that can be filled with different medicinal powders and pressed into shape. The medicinal cake is pasted onto the non-woven fabric. During moxibustion, the medicinal power of the medicinal cake penetrates the body through the acupoint with the help of the heat of the moxa, thereby enhancing the therapeutic effect of moxibustion. The area indicated by 3 is the hollow area with an opening, used to align with the center of the acupoint to define the accurate area of ​​the acupoint.

[0088] In one embodiment of the present invention, for further explanation and limitation, the method further includes:

[0089] Feature extraction is performed on the image information, and the image information containing all extracted features is filtered according to the integrity status information of the square image features and the circular image features to obtain all image features containing the acupoint reference object.

[0090] In this embodiment of the invention, after obtaining the image information, Gaussian blurring and noise removal are performed on the image information. OTSU (Otsu's method) is used to automatically perform global binarization on the processed image, and a closing operation is performed on the image to eliminate isolated points, obtaining the human body region contour. The human body region contour image and the original image in the image information are used for mask calculation to obtain the human body image within the moxibustion area. A color mask is added to the human body image within the moxibustion area to extract images under different color channels. Edges are detected for each color channel image. Based on parameters such as the shape, area, and perimeter of the acupoint reference object, acupoint reference objects that do not contain complete image features are filtered out, and unreasonable acupoints are eliminated, obtaining all image features of the acupoint reference object.

[0091] In one embodiment of the present invention, for further explanation and limitation, identifying the planar coordinates and vertical coordinates of the acupoints includes:

[0092] Extract the first coordinate position of the square image feature and the second coordinate position of the circular image feature from the image features;

[0093] Construct planar coordinates relative to the center point of the human acupoint based on the first coordinate position and the second coordinate position; and determine the vertical coordinates based on the difference between the first coordinate position, the second coordinate position and the distance to the preset vertical plane.

[0094] In this embodiment of the invention, the first coordinate position of the opening area marked by the target marker and the second coordinate position of the maximum circumference of the annulus are extracted from the image information, and the acupoint coordinates are calculated based on the first coordinate position and the second coordinate position, respectively. The calculation process of the acupoint coordinates is explained below using the first coordinate position as an example, setting the pixel coordinates of the first coordinate position in the image as (u, v). Based on the transformation matrix between the image sensor position and the moxibustion head, the first coordinate position, and the robot arm's base coordinate system, the pixel coordinates of the acupoint in the image are converted into world coordinates in the robot (robotic arm) coordinate system. These world coordinates include planar coordinates (X...). w ,Y w and vertical coordinate Z w Specifically, the coordinates of any acupoint in the robot's base coordinate system are set as (X... w ,Y w Z w The calculation formula is:

[0095]

[0096] Among them, K I R represents the intrinsic parameter matrix of the camera; 3*3 Let T represent a 3x3 rotation matrix. 3*1 This represents a 3x1 translation matrix.

[0097] in,

[0098]

[0099] ;in, This represents the transformation matrix from the camera to the robot's coordinate system. This represents the transformation matrix from the robot's base coordinate system to the camera. This represents the transformation matrix from the moxibustion working head at the end of the robotic arm to the robot's base coordinate system. This matrix changes with the change of the moxibustion working head. This represents the transformation matrix from the camera to the moxibustion application head; z c This represents the vertical coordinate in the camera coordinate system. c The calculation process is as follows:

[0100]

[0101]

[0102]

[0103] Z w =z c T w1 (2,0)-T w2 (2,0) (8);

[0104] z c =(Z w +T w2 (2,0) / T w1 (2,0) (9);

[0105] Among them, Z w T represents the height of acupoints in the real world. * (2,0) represents the element in the 3rd row and 1st column of the matrix, where T w1 T is the vertical coordinate of the first coordinate position. w2 This is the preset vertical plane distance.

[0106] In one embodiment of the present invention, for further explanation and limitation, determining the running time and running path of the target acupoint, and controlling the robotic arm to move according to the running time and the running path includes:

[0107] The running time and running path of the target acupoints are determined according to the number of acupoints to be treated and the initial posture of the treatment.

[0108] During the movement of the robotic arm according to the running time and the running path, the posture information of the moxibustion working head is detected;

[0109] If the offset of the posture information is greater than a preset offset, the movement position of the robotic arm is adjusted based on the offset.

[0110] In this embodiment of the invention, the running time includes the total running time and the individual running time, and the running path includes a planar running path and a vertical running path. The individual running time refers to the moxibustion time corresponding to different acupoints. Specifically, during image extraction, different colored acupoint reference objects can be numbered, for example, red, green, blue, and white can be numbered 1, 2, 3, 4, etc., respectively. A mapping relationship between different numbers and different individual running times and moxibustion distances can be established, so that the moxibustion time and distance of the current acupoint can be matched according to the color of the acupoint reference object. Simultaneously, this number can also serve as the moxibustion order, which determines the planar running path. The total running time can be calculated based on the individual running time, the number of acupoints treated, and the running path. By assigning different individual running times to different colors, flexible configuration of the moxibustion time for different acupoints can be achieved to meet the precise control requirements of different acupoints and improve control flexibility.

[0111] In this embodiment of the invention, the vertical running path is calculated based on a preset moxibustion distance and initial moxibustion posture. The component holding the moxibustion head can adjust the posture of the moxibustion head, ensuring it is in its initial posture position before moxibustion begins. The posture information of the moxibustion head can be collected and calculated based on a six-axis gyroscope posture sensor installed at the end of the robotic arm, or it can be collected and calculated using other posture sensors; this embodiment of the invention does not impose specific limitations. During the movement of the robotic arm according to the stated running time and running path, an acupoint is obtained from the target acupoints, and its coordinates are set as (X...). w ,Y w Z), and the original normal N corresponding to the initial attitude position. ori During the movement of the robotic arm, it is determined whether the current running time is greater than the total running time. If it is greater than or equal to the total running time, the process exits directly. If it is less than the total running time, it is determined whether the moxibustion time for the current acupoint meets the corresponding individual running time. If not, an acupoint is selected from the remaining target acupoints, and the above judgment is repeated. If the time meets the requirements, the moxibustion head is moved directly above the current acupoint and its posture is adjusted to (rx, ry, rz) for moxibustion. During this process, 3D point cloud data is acquired using the software development kit provided by the binocular camera manufacturer, and the coordinates (X, y, rz) are obtained from the point cloud data. w ,Y wBased on the average depth D corresponding to the moxibustion head, and the distance d between the moxibustion head and the body provided by the moxibustion therapist, and the current height coordinate Z of the moxibustion head, the new moxibustion head Z is calculated. new value:

[0112] Z new =Z-(Dd) (10);

[0113] Obtain the new world coordinates (X) of the moxibustion application head. w ,Y w Z new ); and with R as the radius, and (X) w ,Y w Z new Centered on a point cloud set, the normal N of the surface within the current moxibustion head region is obtained by calling the function for calculating normals in the camera point cloud processing library; the normal N is then calculated and compared with the original normal N. ori The rotation between these axes yields the angles (rx0, ry0, rz0) that the moxibustion head needs to rotate around the x, y, and z axes. The new moxibustion head posture (rx0, ry0, rz0) is then calculated. new ,ry new ,rz new The formula is:

[0114] (rx new ,ry new ,rz new )=(rx,ry,rz)+(rx0,ry0,rz0) (11);

[0115] Based on the newly calculated position and orientation, the robotic arm is controlled to move the moxibustion head to position (X). w ,Y w Z new Adjust the attitude to (rx) new ,ry new ,rz new Moxibustion is then performed. To ensure that the moxibustion head does not shift during the application, its posture is continuously monitored. If the posture deviates from the set posture and the deviation is greater than a preset deviation, the posture is recalculated according to the above steps. If the deviation is less than or equal to the preset deviation, the posture information is not updated. The preset deviation can be customized according to specific application requirements; this embodiment of the invention does not impose specific limitations. By continuously monitoring the posture of the moxibustion head in real time during the application, adjustments can be made promptly when the moxibustion head shifts, thereby improving the accuracy of the moxibustion.

[0116] In one embodiment of the present invention, for further explanation and limitation, the step of real-time monitoring of the positional deviation of the acupoint reference object includes:

[0117] The third coordinate position of the square image feature and the fourth coordinate position of the circular image feature of the acupoint reference object are collected in real time.

[0118] The position difference between the third coordinate position and the first coordinate position is calculated and determined as the horizontal position deviation, and the position difference between the fourth coordinate position and the second coordinate position is calculated and determined as the vertical position deviation.

[0119] In this embodiment of the invention, the square image feature defines a smaller area, resulting in more accurate horizontal positioning. Calculating the horizontal position deviation using the coordinates corresponding to this image feature yields a more accurate result. The circular image feature covers a larger area, allowing the vertical position deviation to be determined by interpolation or averaging of the vertical coordinates of each point within the feature. This avoids misjudgments caused by single-point protrusions or depressions, effectively improving the accuracy of the vertical position deviation. Horizontal and vertical position deviations can be configured with corresponding deviation thresholds. When the position deviation exceeds the corresponding threshold, a manual intervention warning is generated, or adaptive adjustments are made based on the position deviation. This embodiment of the invention does not impose specific limitations. The deviation threshold can be customized according to specific application requirements, such as 10mm or 5mm. This embodiment of the invention does not impose specific limitations.

[0120] In one embodiment of the present invention, for further explanation and limitation, the method further includes:

[0121] Obtain the initial location network of the constructed target acupoints;

[0122] During the movement of the robotic arm, the real-time position of the end of the robotic arm that is being used for moxibustion is obtained;

[0123] If the real-time location is within the initial location network, then the correct operation and control of the medical device is confirmed.

[0124] If the real-time location is not in the initial location network, the human moxibustion strategy library is retrieved, and if the real-time location does not match an acupoint in the human moxibustion strategy library, an alarm message for abnormal control of the medical device is sent.

[0125] In this invention, multiple moxibustion devices can simultaneously apply moxibustion to a single human body, with each device corresponding to its own target acupoints. Based on the coverage area of ​​each target acupoint on the human body, each acupoint is treated as a node in a grid, and the grid is processed to obtain an initial position network. Generally, throughout the entire moxibustion process, the real-time position of the robotic arm should remain within its corresponding initial position network range. If the real-time position exceeds the initial position network, it is necessary to use a human moxibustion strategy library to determine if the current moxibustion process is abnormal. This human moxibustion strategy library includes the location information of different acupoints and the correspondence between different acupoints and different moxibustion practitioners. Each moxibustion device's current login account is uniquely associated with a moxibustion practitioner; that is, each moxibustion practitioner has restrictions on the acupoints they can apply moxibustion to. For example, moxibustion practitioner A only has permission to apply moxibustion to back acupoints, while moxibustion practitioner B only has permission to apply moxibustion to joint acupoints. Based on the currently logged-in account, the system can match the corresponding acupoint set of the current moxibustion therapist from the human body moxibustion strategy library. If the acupoint corresponding to the real-time location is not in the current moxibustion therapist's acupoint set, it indicates that the current moxibustion process by the robotic arm is exceeding the authorized permissions. In this case, an equipment control anomaly alarm message needs to be generated so that the moxibustion therapist can adjust the control of the moxibustion equipment. The human body moxibustion strategy library can control the moxibustion therapist's moxibustion permissions to meet the need for a fine division of the moxibustion therapist's job functions.

[0126] This invention provides a control method for a medical device. Compared with the prior art, the embodiments of this invention acquire image information of acupoint reference objects through an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers pre-placed on multiple human acupoints. After determining that the image information contains all the image features of the acupoint reference objects, the planar coordinates and vertical coordinates of the human acupoints are identified. After determining at least one target human acupoint to be treated with moxibustion, the running time and running path of the target human acupoint are determined, and the robotic arm is controlled to move according to the running time and running path. During the moxibustion process according to the running time and running path, the positional deviation of the acupoint reference objects is monitored in real time. When the positional deviation is greater than the maximum deviation value for moxibustion, the robotic arm is controlled to move based on the positional deviation. Through the configuration of acupoint reference objects, accurate positioning of the acupoints to be treated with moxibustion is achieved. When the position of the acupoint deviates, the deviation can be automatically corrected in time, avoiding the intervention of manual calibration, greatly reducing the cumbersomeness of device operation, and thus effectively improving the control accuracy and effectiveness of the moxibustion device.

[0127] Furthermore, as a response to the above Figure 1 The implementation of the method shown in this invention provides a control device for a medical device, such as... Figure 4 As shown, the device includes:

[0128] The acquisition module 31 is used to acquire image information of acupoint reference objects through an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers pre-placed on multiple human acupoints.

[0129] The recognition module 32 is used to recognize the planar coordinates and vertical coordinates of the human acupoint after determining that the image information contains all the image features of the acupoint reference object;

[0130] The first control module 33 is used to determine the running time and running path of the target acupoint after determining at least one target acupoint to be treated with moxibustion, and to control the robotic arm to move according to the running time and the running path.

[0131] Monitoring module 34 is used to monitor the positional deviation of the acupoint reference object in real time during the moxibustion process according to the running time and the running path;

[0132] The second control module 35 is used to control the robotic arm to move based on the position deviation when the position deviation is greater than the maximum deviation value for moxibustion.

[0133] Furthermore, the acquisition module 31 includes:

[0134] The first extraction unit is used to drive the robotic arm to move within a pre-set moxibustion area when the image sensor is turned on, and to extract image information containing the acupoint reference object from the image video stream data. The pre-set moxibustion area includes the movement area corresponding to different human body shapes and the image scanning path.

[0135] The acupoint reference object is a patch with a circular outer outline and a square hole in the middle. The patch color is different for different acupoints on different human bodies.

[0136] Furthermore, the identification module 32 includes:

[0137] The second extraction unit is used to extract the first coordinate position of the square image feature and the second coordinate position of the circular image feature from the image features.

[0138] Construct planar coordinates relative to the center point of the human acupoint based on the first coordinate position and the second coordinate position; and determine the vertical coordinates based on the difference between the first coordinate position, the second coordinate position and the distance to the preset vertical plane.

[0139] Furthermore, the device also includes:

[0140] The extraction module is used to extract features from the image information and filter the image information containing all extracted features according to the integrity status information of the square image features and the circular image features, so as to obtain all image features containing the acupoint reference object.

[0141] Furthermore, the first control module 33 includes:

[0142] The determining unit is used to determine the running time and running path of the target acupoints according to the number of moxibustion applications and the initial posture of the moxibustion application. The running time includes the total running time and the individual running time, and the running path includes the planar running path and the vertical running path.

[0143] The detection unit is used to detect the posture information of the moxibustion head during the process of controlling the robotic arm to move according to the running time and the running path;

[0144] An adjustment unit is used to adjust the movement position of the robotic arm based on the offset if the offset of the posture information is greater than a preset offset.

[0145] Furthermore, the monitoring module 34 includes:

[0146] The acquisition unit is used to acquire in real time the third coordinate position of the square image features and the fourth coordinate position of the circular image features of the acupoint reference object;

[0147] The calculation unit is used to calculate the position difference between the third coordinate position and the first coordinate position, determine it as the horizontal position deviation, and calculate the position difference between the fourth coordinate position and the second coordinate position, determine it as the vertical position deviation.

[0148] Furthermore, the device also includes:

[0149] The acquisition module is also used to acquire the initial position network of the constructed target human acupoints;

[0150] The acquisition module is also used to acquire the real-time position of the robotic arm that is performing moxibustion during the movement of the robotic arm;

[0151] The confirmation module is used to confirm that the medical device is operating correctly if the real-time location is within the initial location network.

[0152] The sending module retrieves the human moxibustion strategy library if the real-time location is not in the initial location network, and sends the medical device control abnormality alarm information when the real-time location does not match the acupoints in the human moxibustion strategy library.

[0153] This invention provides a control method and apparatus for a medical device. Compared with the prior art, the embodiments of this invention acquire image information of acupoint reference objects through an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers pre-placed on multiple human acupoints. After determining that the image information contains all the image features of the acupoint reference objects, the planar coordinates and vertical coordinates of the human acupoints are identified. After determining at least one target human acupoint to be treated with moxibustion, the running time and running path of the target human acupoint are determined, and the robotic arm is controlled to move according to the running time and running path. During the moxibustion process according to the running time and running path, the positional deviation of the acupoint reference objects is monitored in real time. When the positional deviation is greater than the maximum deviation value for moxibustion, the robotic arm is controlled to move based on the positional deviation. Through the configuration of the acupoint reference objects, accurate positioning of the acupoints to be treated with moxibustion is achieved. When the acupoint position deviates, the deviation can be automatically corrected in time, avoiding the intervention of manual calibration, greatly reducing the cumbersomeness of device operation, and thus effectively improving the control accuracy and effectiveness of the moxibustion device.

[0154] According to one embodiment of the present invention, a storage medium is provided, the storage medium storing at least one executable instruction, the computer-executable instruction being capable of executing the control method of the medical device in any of the above method embodiments.

[0155] Figure 5 The diagram shows a structural schematic of a terminal according to an embodiment of the present invention. The specific implementation of the terminal is not limited by the specific embodiment of the present invention.

[0156] like Figure 5 As shown, the terminal may include: a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0157] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408.

[0158] Communication interface 404 is used to communicate with other network elements such as clients or other servers.

[0159] The processor 402 is used to execute program 410, specifically to execute the relevant steps in the above-described embodiment of the control method for the medical device.

[0160] Specifically, program 410 may include program code that includes computer operation instructions.

[0161] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The terminal may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0162] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0163] Specifically, program 410 can be used to cause processor 402 to perform the following operations:

[0164] Image information of acupoint reference objects is acquired by an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers that are pre-placed on multiple human acupoints.

[0165] Once it is determined that the image information contains all the image features of the acupoint reference object, the planar coordinates and vertical coordinates of the human acupoint are identified.

[0166] Once at least one target acupoint for moxibustion is determined, the running time and running path of the target acupoint are determined, and the robotic arm is controlled to move according to the running time and the running path.

[0167] During the moxibustion process according to the specified running time and running path, the positional deviation of the acupoint reference object is monitored in real time.

[0168] When the positional deviation is greater than the maximum deviation value for moxibustion, the robotic arm is controlled to move based on the positional deviation.

[0169] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0170] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for controlling a medical device, characterized in that, include: Image information of acupoint reference objects is acquired by an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers pre-placed on multiple human acupoints. The acupoint reference objects are patches with a circular outer outline and a square hole in the middle. The patches placed on different human acupoints are of different colors. Once it is determined that the image information contains all the image features of the acupoint reference object, the planar coordinates and vertical coordinates of the human acupoint are identified; the identification of the planar coordinates and vertical coordinates of the human acupoint includes, Extract the first coordinate position of the square image feature and the second coordinate position of the circular image feature from the image features; Construct planar coordinates relative to the center point of the human acupoint based on the first and second coordinate positions; and determine the vertical coordinates based on the difference between the first and second coordinate positions and the distance to the preset vertical plane. Once at least one target acupoint for moxibustion is determined, the running time and running path of the target acupoint are determined, and the robotic arm is controlled to move according to the running time and the running path. During the process of controlling the robotic arm to move according to the said running time and running path, the positional deviation of the acupoint reference object is monitored in real time; the real-time monitoring of the positional deviation of the acupoint reference object includes... The third coordinate position of the square image feature and the fourth coordinate position of the circular image feature of the acupoint reference object are collected in real time. Calculate the position difference between the third coordinate position and the first coordinate position to determine the horizontal position deviation, and calculate the position difference between the fourth coordinate position and the second coordinate position to determine the vertical position deviation; When the positional deviation is greater than the maximum deviation value for moxibustion, the robotic arm is controlled to move based on the positional deviation.

2. The method according to claim 1, characterized in that, The step of acquiring image information of the acupoint reference object through an image sensor located on the corresponding robotic arm of the medical device includes: With the image sensor activated, the robotic arm is driven to move within the pre-set moxibustion area, and image information containing the acupoint reference object is extracted from the image video stream data. The pre-set moxibustion area includes the movement area corresponding to different human body shapes and the image scanning path.

3. The method according to claim 2, characterized in that, The method further includes: Feature extraction is performed on the image information, and the image information containing all extracted features is filtered according to the integrity status information of the square image features and the circular image features to obtain all image features containing the acupoint reference object.

4. The method according to claim 3, characterized in that, The step of determining the running time and running path of the target acupoint, and controlling the robotic arm to move according to the running time and the running path includes: The running time and running path of the target acupoints are determined according to the number of acupoints to be moxibusted and the initial posture of the moxibustion. The running time includes the total running time and the individual running time, and the running path includes the planar running path and the vertical running path. During the movement of the robotic arm according to the running time and the running path, the posture information of the moxibustion head is detected; If the offset of the posture information is greater than a preset offset, the movement position of the robotic arm is adjusted based on the offset.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Obtain the initial location network of the constructed target acupoints; During the movement of the robotic arm, the real-time position of the robotic arm is acquired; If the real-time location is within the initial location network, then the medical device is confirmed to be operating correctly. If the real-time location is not in the initial location network, the human moxibustion strategy library is retrieved, and if the real-time location does not match an acupoint in the human moxibustion strategy library, an alarm message for abnormal control of the medical device is sent.

6. A control device for a medical device, characterized in that, The control method for executing the medical device according to any one of claims 1-5 further includes: The acquisition module is used to acquire image information of acupoint reference objects through an image sensor located on the corresponding robotic arm of the medical device. The acupoint reference objects are markers pre-placed on multiple human acupoints. The acupoint reference objects are patches with a circular outer contour and a square hole in the middle. The patches placed on different human acupoints are of different colors. The recognition module is used to recognize the planar coordinates and vertical coordinates of the acupoint after determining that the image information contains all the image features of the acupoint reference object; the recognition of the planar coordinates and vertical coordinates of the acupoint includes, Extract the first coordinate position of the square image feature and the second coordinate position of the circular image feature from the image features; Construct planar coordinates relative to the center point of the human acupoint based on the first and second coordinate positions; and determine the vertical coordinates based on the difference between the first and second coordinate positions and the distance to the preset vertical plane. The first control module is used to determine the running time and running path of the target acupoint after determining at least one target acupoint to be treated with moxibustion, and to control the robotic arm to move according to the running time and the running path. The monitoring module is used to monitor the positional deviation of the acupoint reference object in real time during the process of controlling the robotic arm to move according to the running time and the running path; the real-time monitoring of the positional deviation of the acupoint reference object includes... The third coordinate position of the square image feature and the fourth coordinate position of the circular image feature of the acupoint reference object are collected in real time. Calculate the position difference between the third coordinate position and the first coordinate position to determine the horizontal position deviation, and calculate the position difference between the fourth coordinate position and the second coordinate position to determine the vertical position deviation; The second control module is used to control the robotic arm to move based on the position deviation when the position deviation is greater than the maximum deviation value for moxibustion.

7. A storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the control method of the medical device as described in any one of claims 1-5.

8. A terminal, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform an operation corresponding to the control method of the medical device as described in any one of claims 1-5.

Images