Nursing interaction processing method and system based on digital twin model

Abstract

The invention provides a nursing interaction processing method and system based on a digital twinborn model, and belongs to the data processing technology, and the method specifically comprises the steps: binding a patient and a doctor-seeing position identifier in the twinborn model, recording the flow velocity of a medicine and the initial position of a flow regulator, and calculating the infusion time in combination with the capacity of the medicine; the hand action type of the patient is judged, the flow velocity change trend is determined according to the hand action type, and the hand action type comprises a flow increasing input type and a flow reducing input type; updating the medicine flow rate according to the flow rate change trend, and recalculating the infusion time according to the updated medicine flow rate and the current medicine capacity; when the hand action type of the patient is not recognized, the current position of the flow regulator is obtained according to the mobile device, infusion time is recalculated according to the medicine flow rate corresponding to the current position, and when the infusion time is smaller than a threshold value, reminding information is sent to the nursing terminal. The infusion condition of a patient can be monitored in real time, and nursing efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to digital processing technology, and in particular to a nursing interaction processing method and system based on a digital twin model. Background Art

[0002] In the modern medical system, the infusion room and ward of the hospital are very common treatment places. A large number of patients receive infusion treatment here every day. Especially when the number of patients is large, the management of the infusion process becomes extremely complicated. Different patients have different conditions and medication conditions, which requires nursing staff to be able to perform drug replacement and other operations in a timely manner according to the patient's specific infusion process.

[0003] Existing technical means mainly rely on regular inspections by nursing staff. Nursing staff need to regularly go to each infusion station to check in and out and perform corresponding nursing operations. However, when there are a large number of patients, the frequency of manual inspections is limited, making it difficult to achieve real-time monitoring, which reduces the efficiency of the nursing process.

[0004] Therefore, how to monitor the patient's infusion process in real time and improve nursing efficiency has become an urgent problem that needs to be solved today. Summary of the invention

[0005] The present invention provides a nursing interaction processing method and system based on a digital twin model, which can monitor the patient's infusion process in real time and improve nursing efficiency.

[0006] A first aspect of the present invention provides a nursing interaction processing method based on a digital twin model, comprising: Bind the patient and the treatment location in the twin model, record the drug flow rate and the initial position of the flow regulator, and calculate the infusion time based on the drug volume; Determine the patient's hand movement type, and determine the flow rate change trend according to the hand movement type, wherein the hand movement type includes a flow increase input type and a flow decrease input type; Update the drug flow rate according to the flow rate change trend, and recalculate the infusion time according to the updated drug flow rate and the current drug volume; When the patient's hand movement type is not recognized, the current position of the flow regulator is obtained according to the mobile device, and the infusion time is recalculated according to the drug flow rate corresponding to the current position. When the infusion time is less than the threshold, a reminder message is sent to the nursing terminal.

[0007] Optionally, in a possible implementation of the first aspect, the hand motion type of the patient is determined, and the flow rate change trend is determined according to the hand motion type, wherein the hand motion type includes a flow increase input type and a flow decrease input type, including: Acquire a real-time image of the area corresponding to the diagnosis position mark, and determine the region of interest corresponding to the flow regulator in the real-time image; When the hand contour of the patient is identified in the region of interest, the moving trajectory of the key points in the hand contour is obtained. When the coordinates of the moving trajectory in the vertical direction are increasing, it is determined to be an increasing flow input type. When the coordinates of the moving trajectory in the vertical direction are decreasing, it is determined to be a decreasing flow input type. Determine that the flow increase input type corresponds to the increasing trend, determine that the flow reduction input type corresponds to the decelerating trend, and the flow velocity change trend includes the increasing trend and the decelerating trend.

[0008] Optionally, in a possible implementation manner of the first aspect, acquiring a real-time image of an area corresponding to the examination position identifier, and determining a region of interest corresponding to the flow regulator in the real-time image includes: Extract the infusion device in the real-time image and identify the infusion tube area in the infusion device; Traversing the infusion tube area in sequence from top to bottom, determining a pixel point in the infusion tube area whose pixel value is outside a preset pixel interval corresponding to the infusion tube area as a target pixel point; The regulator contour is generated based on adjacent target pixel points, and the region corresponding to the regulator contour is determined as the region of interest after the regulator contour is magnified according to a preset magnification.

[0009] Optionally, in a possible implementation of the first aspect, when a hand contour of the patient is identified in the region of interest, a moving trajectory of key points in the hand contour is obtained, and when the coordinates of the moving trajectory in the vertical direction are increasing, it is determined to be an increasing flow input type, and when the coordinates of the moving trajectory in the vertical direction are decreasing, it is determined to be a decreasing flow input type, including: The fingertip contour points in the hand contour are obtained as key points, the position coordinates of the key points in consecutive frames are recorded according to the time sequence, and the position coordinates are connected in sequence to obtain the movement trajectory; Select adjacent key points in the moving trajectory in chronological order and calculate their vertical coordinate differences; If the coordinate differences within the preset time period are all greater than the reference constant, it is determined that the coordinates on the moving trajectory are increasing, and it is determined to be an increasing flow input type; If the coordinate differences within the preset time period are all smaller than the reference constant, it is determined that the coordinates on the moving trajectory are decreasing and it is determined to be a flow reduction input type.

[0010] Optionally, in a possible implementation manner of the first aspect, before obtaining the movement trajectory of the key points in the hand contour, the method further includes: Obtain the palm contour points and fingertip contour points in the hand contour as judgment points, and calculate the point distance between the judgment points; The point distance difference of the corresponding judgment points in adjacent frames is calculated. When the point distance difference corresponding to the preset frame is less than the reference constant, the trajectory recording information is responded to and the moving trajectory is started to be obtained.

[0011] Optionally, in a possible implementation of the first aspect, updating the drug flow rate according to the flow rate change trend, and recalculating the infusion time according to the updated drug flow rate and the current drug volume, includes: The patient's adjustment time is obtained, and the predicted distance is obtained according to the product of the adjustment time and the reference speed; When the flow velocity change trend is an increasing trend, a position at a predicted distance from the initial position in a preset increasing direction is determined as a predicted increasing position, and the flow velocity corresponding to the predicted increasing position is updated as the drug flow velocity; When the flow velocity change trend is a deceleration trend, a position at a predicted distance from the initial position in the preset deceleration direction is determined as a predicted deceleration position, and the flow velocity corresponding to the predicted deceleration position is updated as the drug flow velocity; The infusion time is recalculated based on the ratio of the current drug volume and the updated drug flow rate.

[0012] Optionally, in a possible implementation manner of the first aspect, calculating the flow velocity corresponding to the predicted speed-up position or the predicted speed-down position by the following steps includes: Retrieving a preset model corresponding to the flow regulator, determining a plurality of preset positions corresponding to the preset model, each preset position being configured with a corresponding preset flow rate; Obtaining a preset position interval where the predicted speed-up position or the predicted speed-down position is located, and determining the interval length of the preset position interval; Calculate the predicted length from the predicted speed-up position or the predicted speed-down position to the left end point of the preset position, and obtain the interval proportion according to the ratio of the predicted length to the interval length; The flow velocity difference corresponding to the preset position interval is obtained, and the product of the interval proportion and the flow velocity difference is added to the preset flow velocity corresponding to the left endpoint of the preset position interval to obtain the flow velocity corresponding to the predicted acceleration position or the predicted deceleration position.

[0013] Optionally, in a possible implementation of the first aspect, when the hand motion type of the patient is not identified, obtaining the current position of the flow regulator according to the mobile device, and recalculating the infusion time according to the drug flow rate corresponding to the current position, includes: When the hand motion type of the patient is not identified, the first moment is recorded, and the mobile device is controlled to go to the position corresponding to the diagnosis position mark to collect image data, and the second moment of the collection is recorded; Retrieving a preset model corresponding to the flow regulator, the preset model includes a scale line, and the scale line has a plurality of preset positions; Obtaining the span line of the flow regulator in the flow direction of the infusion tube in the collected image, and determining the position point of the regulating element on the span line, and determining the target point position of the position point on the scale line according to the proportional relationship between the scale line and the span line; The remaining amount of medicine at the first moment is calculated according to the historical drug flow rate, the drug consumption from the first moment to the second moment is calculated according to the drug flow rate at the target point, and the infusion time is recalculated by dividing the value obtained by subtracting the drug consumption from the remaining amount of medicine by the drug flow rate corresponding to the target point.

[0014] Optionally, in a possible implementation of the first aspect, obtaining a span line of the flow regulator in the flow direction of the infusion tube in the acquired image, determining a position point of the regulating element on the span line, and determining a target point position of the position point on the scale line according to a proportional relationship between the scale line and the span line, includes: Extract the current contour corresponding to the flow regulator in the acquired image, obtain two endpoints of the current contour in the flow direction of the infusion tube, and connect the two endpoints to obtain a span line; Obtaining the center point of multiple contour intersections of the regulating element and the span line as the finally selected position point, and determining a first distance between the position point and the left end point of the span line; Determine the length ratio of the scale line and the span line according to the proportional relationship between the scale line and the span line, and multiply the first distance and the length ratio to obtain the second distance; Determine the position point at the second distance from the left end point of the scale line as the target point.

[0015] A second aspect of the present invention provides a nursing interaction processing system based on a digital twin model, comprising: The initial module is used to bind the patient and the treatment location identification in the twin model, record the drug flow rate and the initial position of the flow regulator, and calculate the infusion time based on the drug volume; A judgment module, used to judge the hand movement type of the patient, and determine the flow rate change trend according to the hand movement type, wherein the hand movement type includes a flow increase input type and a flow decrease input type; A calculation module, used to update the drug flow rate according to the flow rate change trend, and recalculate the infusion time according to the updated drug flow rate and the current drug volume; The warning module is used to obtain the current position of the flow regulator according to the mobile device when the patient's hand movement type is not recognized, recalculate the infusion time according to the drug flow rate corresponding to the current position, and send a reminder message to the nursing terminal when the infusion time is less than the threshold.

[0016] The beneficial effects of the present invention are as follows: The present invention can utilize a camera to continuously collect images of the patient's treatment area at a certain frequency, and use image recognition technology to accurately identify the patient's hand movement type and determine whether it is a flow increase input type or a flow reduction input type. By tracking the moving trajectory of key points in the hand contour, the action type is determined according to the change of vertical coordinates, which greatly improves the accuracy of the judgment. At the same time, when the patient's hand movement type is not identified, the mobile device monitoring mechanism is started, and the mobile device goes to the patient's treatment position to collect flow regulator image data. By processing and analyzing the image, the current position of the flow regulator is accurately obtained, and the drug flow rate corresponding to the current position is determined in combination with the preset model. For example, when determining the target point of the flow regulator, the flow regulator contour in the image is extracted, the span line is obtained, the position point of the regulating element is determined, and then the target point is accurately determined according to the proportional relationship between the scale line and the span line, so as to accurately calculate the infusion time. Thereby, real-time and accurate monitoring of the infusion process is realized, the accuracy of the infusion parameters is ensured, and the efficiency of the nursing process is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of a nursing interaction processing method based on a digital twin model provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a twin model corresponding to a nursing hall provided in an embodiment of the present invention; Figure 3 This is a schematic diagram showing a reminder message provided by an embodiment of the present invention; Figure 4 This is a structural diagram of a nursing interaction processing system based on a digital twin model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 , is a flow chart of a nursing interaction processing method based on a digital twin model provided by an embodiment of the present invention, Figure 1The execution subject of the method shown may be a software and / or hardware device. The execution subject of the present application may include but is not limited to at least one of the following: user equipment, network equipment, etc. Among them, user equipment may include but is not limited to computers, smart phones, personal digital assistants (PDA) and the electronic devices mentioned above. Network equipment may include but is not limited to a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers, wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. It includes steps S101 to S104, as follows: S101, bind the patient and the treatment location identification in the twin model, record the drug flow rate and the initial position of the flow regulator, and calculate the infusion time based on the drug volume.

[0020] This embodiment is suitable for use in hospital infusion rooms, wards and other scenarios where the infusion process needs to be monitored, and is particularly suitable for use in situations where there are a large number of patients and nursing resources are relatively tight. This embodiment can achieve real-time monitoring of the patient's infusion status, accurately adapt to the medication needs of different patients and optimize the allocation of medical resources.

[0021] Since the medication conditions of each patient are different, in order to enable medical staff to change medicines in time according to the infusion progress of each patient and improve the safety and efficiency of the nursing process, this embodiment will calculate the patient's infusion time, so that the medical staff can be reminded when the infusion time is less than the threshold. When reminding, this embodiment will show the medical staff the specific location of the patient through the twin model of the corresponding area, so that the medical staff can quickly find the patient and perform nursing operations.

[0022] See also Figure 2 , which is a schematic diagram of a twin model corresponding to a nursing hall provided in an embodiment of the present invention. The twin model corresponds to a nursing hall, such as an infusion hall. The infusion area includes multiple consultation positions corresponding to the infusion. The consultation position identifier is a virtual position identifier corresponding to the patient position in the twin model. Medical staff can enter patient information in the system and establish a binding relationship with the consultation position identifier in the digital twin model. Medical staff can enter the parameters of the infusion pump, including the initial drug flow rate, the position of the regulator, and the drug capacity, and then calculate the initial infusion time based on the ratio of the drug capacity to the initial flow rate. The flow regulator is an infusion speed regulating roller, which controls the infusion speed by changing the position of the roller on the track.

[0023] S102, determining the patient's hand movement type, and determining the flow rate change trend according to the hand movement type, wherein the hand movement type includes a flow increase input type and a flow decrease input type.

[0024] During the infusion process, the patient may adjust the infusion flow rate, causing the infusion time to change. Therefore, in order to more accurately monitor the patient's infusion process, this embodiment will also recalculate the infusion time when the patient adjusts the infusion flow rate. Specifically, the flow rate change information will be quickly obtained through the patient's hand movements.

[0025] Understandably, in a large infusion room, the camera needs to cover a large area, and it is difficult for the camera to clearly capture the specific position of the roller after it is turned. However, the hand movement amplitude is relatively large, which is easier to be captured by the camera. By analyzing the direction of the hand movement, the direction of the roller can be indirectly inferred, and then the flow rate change can be determined.

[0026] The specific camera can collect images of the patient's treatment area at a certain frequency, and identify the patient's hand movements, determine whether the patient's hand movements are moving upward (i.e., the hand movements corresponding to the flow increase input type) or downward (i.e., the hand movements corresponding to the flow reduction input type), and determine the increase in flow input type corresponding to the increase in speed trend. In this case, the roller will slide toward the wide end of the track, the pressure on the catheter will be reduced, and the flow rate will increase. Determine the decrease in flow input type corresponding to the deceleration trend. In this case, the roller will slide toward the narrow end of the track, squeezing the catheter more significantly, causing the liquid flow rate to slow down. The flow rate change trend includes the increase in speed trend and the deceleration trend.

[0027] In some embodiments, based on the above embodiments, the specific implementation of step S102 may be: A real-time image of the area corresponding to the diagnosis position mark is collected, and a region of interest corresponding to the flow regulator in the real-time image is determined.

[0028] The region of interest is the region where the patient's hand movement detection is performed. When determining the region of interest, the region including the infusion roller and the surrounding area that may be operated by the hand can be determined as the region of interest.

[0029] In some embodiments, a fixed area may be pre-calibrated in the image as a region of interest, which may cover various possible motion ranges of the patient's hand operating the roller to ensure that no operating motion is missed.

[0030] In some other embodiments, the region of interest may be determined by: Extract the infusion device in the real-time image and identify the infusion tube area in the infusion device.

[0031] In practical applications, the contour of the infusion device can be extracted according to the shape and color features of the infusion device using algorithms such as threshold segmentation and edge detection. The flow regulator is generally installed on the infusion tube and is a component of the infusion tube. Therefore, after extracting the corresponding contour of the infusion device, the area corresponding to the infusion tube in the infusion device can be identified.

[0032] The infusion tube region is traversed in sequence from top to bottom, and a pixel point in the infusion tube region whose pixel value is outside a preset pixel interval corresponding to the infusion tube region is determined as a target pixel point.

[0033] Normally, after the flow regulator is imaged, its corresponding pixel set is within the pixel set of the corresponding area of ​​the infusion tube. Because the flow regulator exists in dependence on the infusion tube, the area occupied by the flow regulator in the image is part of the overall area of ​​the infusion tube. For example, in the image, the infusion tube appears as a long and thin strip, and the flow regulator is a specific part of this strip. The pixel points corresponding to the roller are completely contained in the area formed by the pixel points representing the infusion tube, and the pixel values ​​corresponding to the flow regulator and the infusion tube are generally different. Therefore, the pixel points located in the infusion tube area and whose pixel values ​​are not in the preset pixel interval can be selected to determine the area corresponding to the flow regulator.

[0034] The regulator contour is generated based on adjacent target pixel points, and the region corresponding to the regulator contour is determined as the region of interest after the regulator contour is magnified according to a preset magnification.

[0035] Among them, the preset magnification factor can be set in advance to cover a certain area around the flow regulator. After the regulator contour is magnified, the center point of the enlarged contour can be aligned with the center point of the contour before magnification, and the corresponding area can be used as the area of ​​interest.

[0036] When the patient's hand contour is identified in the area of ​​interest, the moving trajectory of the key points in the hand contour is obtained. When the coordinates of the moving trajectory in the vertical direction are increasing, it is determined to be an increasing flow input type. When the coordinates of the moving trajectory in the vertical direction are decreasing, it is determined to be a decreasing flow input type.

[0037] After the area of ​​interest is determined, the area can be continuously monitored. When the patient's hand outline is identified in the area, the subsequent analysis steps will be triggered. Specifically, the movement trajectory of the key points in the hand outline will be combined to determine whether it is moving up or down.

[0038] Among them, the key point refers to the reference point for determining the hand movement trajectory, which can be the contour point of the hand part such as the fingertip. The movement trajectory is generated by the key points of continuous frames.

[0039] When the scroll wheel is turned upward, the fingertip usually moves upward first, driving the scroll wheel to rotate. Therefore, the coordinates of the moving track corresponding to the key points may increase in the vertical direction, that is, the Y-axis coordinate values ​​on the moving track increase successively; the opposite is true when the scroll wheel is turned downward. Therefore, tracking the movement track of the key points corresponding to the fingertip is helpful to determine the adjustment direction of the scroll wheel, where the origin of the coordinates can be the center point of the image.

[0040] Specifically, in some embodiments, the hand motion type may be determined by the following steps: The fingertip contour points in the hand contour are obtained as key points, the position coordinates of the key points in consecutive frames are recorded according to the time sequence, and the position coordinates are connected in sequence to obtain the movement trajectory.

[0041] From the perspective of finger positions, the tip of the index finger is an important reference point. The index finger is often at the forefront of the action when turning the scroll wheel, and its motion trajectory can intuitively reflect the direction and amplitude of the turning. Therefore, the fingertip contour point can be the contour point of the index fingertip. In some embodiments, it can also be other fingertip contour points. The movement trajectory can intuitively present the movement path and direction of the key points of the hand in space.

[0042] Adjacent key points in the moving trajectory are selected in chronological order, and their vertical coordinate differences are calculated.

[0043] Calculate the coordinate difference in the vertical direction, that is, calculate the Y-axis coordinate value difference of adjacent key points. You can subtract the Y-axis coordinate value at the previous moment from the Y-axis coordinate value at the next moment.

[0044] If the coordinate differences within the preset time period are all greater than the reference constant, it is determined that the coordinates on the moving trajectory are increasing and are determined to be an increasing flow input type.

[0045] In practical applications, the reference constant can be 0. If the coordinate differences within the preset time period are all greater than 0, it means that the Y-axis coordinate differences in consecutive corresponding frames are all greater than 0, and the Y-axis coordinate value is continuously increasing. Therefore, it can be determined that its coordinates are increasing and it is determined to be an upward flow-increasing input type.

[0046] If the coordinate differences within the preset time period are all smaller than the reference constant, it is determined that the coordinates on the moving trajectory are decreasing and it is determined to be a flow reduction input type.

[0047] If the coordinate differences within the preset time period are all less than 0, it means that the Y-axis coordinate differences in the consecutive corresponding frames are all less than 0, and the Y-axis coordinate values ​​are continuously decreasing. Therefore, it can be determined that the coordinates are decreasing and it is determined to be a downward flow reduction input type.

[0048] Determine that the flow increase input type corresponds to the increasing trend, determine that the flow reduction input type corresponds to the decelerating trend, and the flow velocity change trend includes the increasing trend and the decelerating trend.

[0049] In addition, when the patient has no intention to operate, the hand may have various unintentional movements, tremors, or natural posture adjustments. If you try to determine the direction of the dial in these situations, it is easy to make a misjudgment. For example, the patient may just accidentally put his hand near the infusion device, and the slight movement of the hand is not to adjust the roller. Therefore, before determining the movement trajectory, it is also possible to determine whether the patient has the intention to operate the dial. When it is determined that the patient has this intention, determining the direction of the dial can greatly improve the accuracy of the judgment and reduce the probability of misjudgment.

[0050] Therefore, in some embodiments, before obtaining the moving trajectory of the key points in the hand contour, the following scheme is also included: The palm contour points and fingertip contour points in the hand contour are obtained as judgment points, and the point distances between the judgment points are calculated.

[0051] In order to filter out hand movements with operational intentions, the system will perform difference calculations on the point distances of corresponding judgment points in adjacent frames. Judgment points refer to reference points used to determine changes in hand movements. Calculating the difference in the point distances between the palm and fingertip contour points in adjacent frames can highlight changes in hand movements in a very short period of time.

[0052] The point distance difference of the corresponding judgment points in adjacent frames is calculated. When the point distance difference corresponding to the preset frame is less than the reference constant, the trajectory recording information is responded to and the moving trajectory is started to be obtained.

[0053] When the point distance differences corresponding to the preset frames are all less than the reference constant (0), it means that the distance between the palm contour point and the fingertip contour point is gradually decreasing. The gradual decrease in distance may mean that the hand is closing, which is most likely in preparation for grasping the infusion roller or performing a dialing operation. By closely monitoring this distance change trend, combined with the analysis of the point distance differences between adjacent frames and the judgment rules of the preset frames and reference constants, the patient's operating intention can be more accurately determined, and sufficient preparations can be made in advance to obtain accurate movement trajectories, further improving the timeliness and accuracy of the judgment of infusion adjustment actions, and providing more solid and powerful support for ensuring the smooth and safe infusion process. Among them, the trajectory recording information is the response information used to start recording the movement trajectory.

[0054] S103, updating the drug flow rate according to the flow rate change trend, and recalculating the infusion time according to the updated drug flow rate and the current drug volume.

[0055] After determining the flow rate change trend, this embodiment will update the drug flow rate in combination with the trend, and then recalculate the infusion time in combination with the updated flow rate. If it is an increasing trend, the drug flow rate is increased; if it is a decelerating trend, the drug flow rate is reduced. When increasing or reducing the flow rate, the position of the flow regulator adjusted under the corresponding trend can be determined in combination with the correspondence between the pre-set position and the flow rate, and the drug flow rate is updated in combination with the flow rate corresponding to the position. After updating the drug flow rate, the system will combine the current remaining drug capacity and recalculate the infusion time using the calculation method of dividing the current drug capacity by the updated drug flow rate. This recalculation process can ensure that the infusion time always remains consistent with the actual infusion situation, providing accurate infusion progress information to medical staff.

[0056] Based on the above embodiment, the specific implementation of step S103 may be: The patient's adjustment time is obtained, and the predicted distance is obtained according to the product of the adjustment time and the reference speed.

[0057] It is understandable that in order to predict the roller position after the patient's adjustment and then determine the flow rate after the patient's adjustment based on the correspondence between the roller position and the flow rate, the roller position can be predicted based on the duration of the patient's adjustment.

[0058] The patient's adjustment time can be determined in combination with the movement trajectory corresponding to the patient's hand contour. The adjustment time can be determined by determining the movement time of the movement trajectory. When determining the movement trajectory, if the change value of the corresponding coordinate point position within the preset time is less than the preset change threshold, it means that the operation may have stopped, and it can be used as the end point of the movement trajectory, and then the adjustment time is determined by the time from the starting point to the end point of the movement trajectory.

[0059] The reference speed may be a pre-set speed, and the displacement data of the patient's adjustment, that is, the predicted distance, may be predicted based on the reference speed and the adjustment duration.

[0060] When the flow velocity change trend is an increasing trend, a position at a predicted distance from an initial position in a preset increasing direction is determined as a predicted increasing position, and the flow velocity corresponding to the predicted increasing position is updated to the drug flow velocity.

[0061] In actual application, the roller of the infusion device controls the flow rate of the liquid by squeezing the infusion tube. When the roller is adjusted upward, the degree of squeezing of the infusion tube by the roller is reduced, the lumen of the infusion tube becomes relatively larger, the resistance to liquid flow is reduced, and more liquid can pass through the infusion tube per unit time, thereby speeding up the infusion speed. On the contrary, when the roller is adjusted downward, the roller will further squeeze the infusion tube, the lumen becomes narrower, the resistance to liquid flow increases, and the infusion speed will slow down. Therefore, the preset speed-up direction can be from bottom to top, and the predicted speed-up position is the roller position predicted in combination with the distance of the upward dial. Different positions have corresponding flow rates, so after determining the position, the corresponding drug flow rate can be known.

[0062] When the flow velocity variation trend is a deceleration trend, a position at a predicted distance from an initial position in a preset deceleration direction is determined as a predicted deceleration position, and the flow velocity corresponding to the predicted deceleration position is updated to the drug flow velocity.

[0063] The preset deceleration direction may be from top to bottom, and the predicted deceleration position is the predicted roller position in combination with the downward movement distance.

[0064] In some embodiments, the flow velocity corresponding to the predicted speed-up position or the predicted speed-down position may be calculated by the following steps: The preset model corresponding to the flow regulator is retrieved, and a plurality of preset positions corresponding to the preset model are determined, each preset position being configured with a corresponding preset flow rate.

[0065] In practical applications, a flow regulator can be pre-configured with a corresponding model, which includes multiple preset positions, and each preset position is configured with a corresponding preset flow rate. These preset positions and flow rates are pre-set and calibrated, providing basic data for subsequent calculations. For example, the preset model may include flow rate values ​​corresponding to different scale positions of the roller.

[0066] The preset position interval where the predicted speed-up position or the predicted speed-down position is located is obtained, and the interval length of the preset position interval is determined.

[0067] The preset position interval is the scale interval where the predicted acceleration position or the predicted deceleration position is located. For example, assuming that the predicted acceleration position is between two scale positions in the preset model, these two scale positions constitute a preset position interval, and the difference between them is the interval length.

[0068] Calculate the predicted length from the predicted speed-up position or the predicted speed-down position to the left end point of the preset position, and obtain the interval proportion based on the ratio of the predicted length to the interval length.

[0069] The left end point of the preset position interval can be a critical point with a small value, and the predicted length is the distance from the predicted acceleration position or the predicted deceleration position to the critical point. The interval ratio can reflect the relative position of the predicted position in the preset position interval. For example, if the predicted length is half of the interval length, the interval ratio is 0.5.

[0070] The flow velocity difference corresponding to the preset position interval is obtained, and the product of the interval proportion and the flow velocity difference is added to the preset flow velocity corresponding to the left endpoint of the preset position interval to obtain the flow velocity corresponding to the predicted acceleration position or the predicted deceleration position.

[0071] Get the flow rate difference corresponding to the preset position interval, that is, the difference between the preset flow rate corresponding to the right endpoint of the interval and the preset flow rate corresponding to the left endpoint. Then multiply the interval proportion by the flow rate difference, and add the preset flow rate corresponding to the left endpoint of the preset position interval to get the flow rate corresponding to the predicted speed-up position or the predicted speed-down position. Through this calculation method, the corresponding drug flow rate can be determined more accurately according to the predicted position, thereby achieving precise control and adjustment of the infusion flow rate.

[0072] For example, the flow rate at the left endpoint of the preset position interval is 50 ml / h, the flow rate at the right endpoint is 70 ml / h, the flow rate difference is 20 ml / h, and the interval proportion is 0.5, then the flow rate corresponding to the predicted position is 50 + 0.5×20 = 60 ml / h.

[0073] The infusion time is recalculated based on the ratio of the current drug volume and the updated drug flow rate.

[0074] Through the above method, when the patient adjusts the infusion flow rate, the new flow rate can be accurately determined, thereby improving the accuracy of monitoring.

[0075] S104, when the patient's hand movement type is not identified, the current position of the flow regulator is obtained according to the mobile device, and the infusion time is recalculated according to the drug flow rate corresponding to the current position. When the infusion time is less than the threshold, a reminder message is sent to the nursing terminal.

[0076] In order to improve the accuracy of monitoring, when the patient's hand movement type is not identified within a period of time, another set of monitoring mechanisms will be activated. Specifically, the mobile device can be controlled to go to the patient's corresponding treatment position identification position. The image acquisition device equipped on the mobile device will collect image data of the flow regulator. The collected image is processed and analyzed to obtain the current position of the flow regulator, and the drug flow rate corresponding to the current position is determined based on the pre-set position and flow rate correspondence. Based on this, the infusion time can be recalculated again based on the current remaining drug capacity and the flow rate.

[0077] When the infusion time is less than the preset threshold, it means that the infusion is about to end or an abnormal situation may occur. At this time, a reminder message can be immediately sent to the nursing terminal (such as a computer or other electronic device). After receiving the reminder on the nursing terminal, the nursing staff can know the patient's infusion status in time and make corresponding preparations in advance, such as preparing to replace the medicine, handling the follow-up matters after the infusion is completed, etc., to ensure the smooth progress of the infusion process. Figure 3 , is a schematic diagram of displaying a reminder information provided by an embodiment of the present invention. When the infusion time of a patient is less than a threshold, the corresponding position of the patient in the twin model can be quickly determined in combination with the position information bound to the patient, and then the corresponding position is displayed using different pixel values, for example Figure 3 The gray pixel value shown in the figure distinguishes it from the positions corresponding to the remaining white pixel values, so that medical staff can quickly locate the patient's position and perform corresponding nursing operations.

[0078] Based on the above embodiment, the specific implementation of step S104 may be: When the patient's hand movement type is not identified, the first moment is recorded, and the mobile device is controlled to go to the position corresponding to the examination position mark to collect image data, and the second moment of the collection is recorded.

[0079] When the type of hand movement of the patient is not identified, the first moment is first recorded, and then a mobile device such as a mobile robot is controlled to go to the preset position corresponding to the patient's treatment position mark. The image acquisition device (such as a camera) equipped on the mobile device will collect image data of the flow regulator and record the second moment of the acquisition. This step ensures that the status information of the flow regulator at a specific moment can be obtained. The reason for recording the first moment and the second moment is to be able to determine the time period when the mobile device goes to the corresponding position of the patient, so that when recalculating the infusion time, the consumed capacity during this period can be combined with the adjusted flow rate for calculation, thereby improving the accuracy of the flow rate calculation.

[0080] The preset model corresponding to the flow regulator is retrieved, wherein the preset model includes a scale line, and the scale line has a plurality of preset positions.

[0081] The preset model contains scale lines with multiple preset positions, each of which corresponds to a specific flow rate. The preset model is an important reference for position and flow rate judgment, through which the actual position of the flow regulator can be converted into corresponding flow rate information.

[0082] The span line of the flow regulator in the flow direction of the infusion tube in the collected image is obtained, and the position point of the regulating element on the span line is determined. According to the proportional relationship between the scale line and the span line, the target point position of the position point on the scale line is determined.

[0083] The span line is the movable range line of the regulating element. The regulating element is the roller in the flow regulator. The flow direction of the infusion tube can correspond to the direction of the infusion tube. The position point of the regulating element on the span line can be used to indicate the specific position of its adjustment.

[0084] According to the proportional relationship between the scale line and the span line, the target point of the position point on the scale line is calculated. For example, if the span line is 10 cm long, the adjustment element is 3 cm away from one end of the span line, and the total length of the scale line is 50 scale units, through proportional calculation (50 / 10 = x / 3), it can be determined that the target point corresponding to the position point on the scale line is the 15th scale unit.

[0085] Specifically, in some embodiments, the target point can be determined by the following steps: The current contour corresponding to the flow regulator in the acquired image is extracted, two endpoints of the current contour in the flow direction of the infusion tube are obtained, and the two endpoints are connected to obtain a span line.

[0086] In the image of the infusion scene, the flow regulator has a unique shape and features. Its outline can be separated from the complex background through image recognition technology (such as edge detection, contour extraction algorithm, etc.). Next, the two endpoints of the current outline in the flow direction of the infusion tube are obtained. The regulating element generally moves in the direction corresponding to the flow direction of the infusion tube, and the position change of the regulating element in this direction directly affects the infusion flow rate.

[0087] The center point of multiple contour intersections of the regulating element and the span line is obtained as the finally selected position point, and a first distance between the position point and the left end point of the span line is determined.

[0088] Since the regulating element and the span line may have multiple intersections, these intersections reflect the relative position of the regulating element on the span line. The center point of these intersections is calculated and used as the final selected position point. The center point is selected as the position point to more accurately represent the position of the regulating element on the span line and avoid inaccurate position judgment due to deviation of a single intersection point.

[0089] The first distance represents the positional relationship of the position point relative to the left endpoint of the span line. By measuring this distance, the specific position of the adjustment element on the span line can be quantified. For example, if the span line length is 100 pixels, the first distance between the position point and the left endpoint is 30 pixels, indicating that the adjustment element is located at 30% of the span line from the left endpoint.

[0090] The length ratio of the scale line and the span line is determined according to the proportional relationship between the scale line and the span line, and the second distance is obtained by multiplying the first distance and the length ratio.

[0091] The scale line is an important part of the preset model of the flow regulator. The scale on it corresponds to different flow rates. The span line is the actual range line determined from the acquired image. By comparing the lengths of the two, the proportional relationship between them is obtained. The second distance is obtained by multiplying the first distance and the length ratio. This second distance is the key step in converting the image-based span line position information to the scale line position information. Through this calculation, the distance of the position point on the span line is converted to the equivalent distance on the scale line.

[0092] Determine the position point at the second distance from the left end point of the scale line as the target point.

[0093] Through the previous calculation, a distance value (second distance) on the scale line is obtained. Starting from the left end point of the scale line, along the scale line direction, find the position point that is the second distance from the left end point. This position point is the target point. After the target point is determined, the infusion time can be accurately recalculated based on the flow rate corresponding to the target point in the preset model, combined with other relevant information (such as the remaining amount of medicine, etc.), thereby providing accurate infusion status information to nursing staff and ensuring the smooth progress of the infusion process.

[0094] The remaining amount of medicine at the first moment is calculated according to the historical drug flow rate, the drug consumption from the first moment to the second moment is calculated according to the drug flow rate at the target point, and the infusion time is recalculated by dividing the value obtained by subtracting the drug consumption from the remaining amount of medicine by the drug flow rate corresponding to the target point.

[0095] The remaining amount of medicine at the first moment is calculated based on the historical drug flow rate (i.e. the previously recorded drug flow rate information). For example, if the previous flow rate is 50ml / h, 2 hours have passed from the start of infusion to the first moment, and the initial drug capacity is 300ml, then the remaining amount of medicine at the first moment is 300 - 50×2 = 200ml. Next, the drug consumption from the first moment to the second moment is calculated based on the drug flow rate of the target point. Assuming that the flow rate corresponding to the target point is 60ml / h, and 0.5 hours have passed from the first moment to the second moment, the drug consumption is 60×0.5 = 30ml. Finally, the value obtained by subtracting the drug consumption from the remaining amount of medicine (200 - 30 = 170ml) is divided by the drug flow rate corresponding to the target point (60ml / h), and the infusion time is recalculated as 170÷60 ≈ 2.83 hours.

[0096] Through the above methods, the efficiency and accuracy of drug management in the nursing process can be improved.

[0097] See also Figure 4, is a structural diagram of a nursing interaction processing system based on a digital twin model provided by an embodiment of the present invention, and the nursing interaction processing system based on a digital twin model includes: The initial module is used to bind the patient and the treatment location identification in the twin model, record the drug flow rate and the initial position of the flow regulator, and calculate the infusion time based on the drug volume; A judgment module, used to judge the hand movement type of the patient, and determine the flow rate change trend according to the hand movement type, wherein the hand movement type includes a flow increase input type and a flow decrease input type; A calculation module, used to update the drug flow rate according to the flow rate change trend, and recalculate the infusion time according to the updated drug flow rate and the current drug volume; The warning module is used to obtain the current position of the flow regulator according to the mobile device when the patient's hand movement type is not recognized, recalculate the infusion time according to the drug flow rate corresponding to the current position, and send a reminder message to the nursing terminal when the infusion time is less than the threshold.

[0098] Figure 4 The apparatus of the embodiment shown can be used to perform Figure 1 The implementation principles and technical effects of the steps in the method embodiment shown are similar and will not be repeated here.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A nursing interaction processing method based on a digital twin model, characterized in that: include: Bind the patient and the treatment location in the twin model, record the drug flow rate and the initial position of the flow regulator, and calculate the infusion time based on the drug volume; Determine the patient's hand movement type, and determine the flow rate change trend according to the hand movement type, wherein the hand movement type includes a flow increase input type and a flow decrease input type; Update the drug flow rate according to the flow rate change trend, and recalculate the infusion time according to the updated drug flow rate and the current drug volume; When the patient's hand movement type is not recognized, the current position of the flow regulator is obtained according to the mobile device, and the infusion time is recalculated according to the drug flow rate corresponding to the current position. When the infusion time is less than the threshold, a reminder message is sent to the nursing terminal.

2. The method according to claim 1, characterized in that Determine the patient's hand movement type, and determine the flow rate change trend according to the hand movement type, wherein the hand movement type includes a flow increase input type and a flow decrease input type, including: Acquire a real-time image of the area corresponding to the diagnosis position mark, and determine the region of interest corresponding to the flow regulator in the real-time image; When the hand contour of the patient is identified in the region of interest, the moving trajectory of the key points in the hand contour is obtained. When the coordinates of the moving trajectory in the vertical direction are increasing, it is determined to be an increasing flow input type. When the coordinates of the moving trajectory in the vertical direction are decreasing, it is determined to be a decreasing flow input type. Determine that the flow increase input type corresponds to the increasing trend, determine that the flow reduction input type corresponds to the decelerating trend, and the flow velocity change trend includes the increasing trend and the decelerating trend.

3. The method according to claim 2, characterized in that Collect a real-time image of the area corresponding to the patient position identification, and determine the area of ​​interest corresponding to the flow regulator in the real-time image, including: Extract the infusion device in the real-time image and identify the infusion tube area in the infusion device; Traversing the infusion tube area in sequence from top to bottom, determining a pixel point in the infusion tube area whose pixel value is outside a preset pixel interval corresponding to the infusion tube area as a target pixel point; The regulator contour is generated based on adjacent target pixel points, and the region corresponding to the regulator contour is determined as the region of interest after the regulator contour is magnified according to a preset magnification.

4. The method according to claim 2, characterized in that: When the hand contour of the patient is identified in the region of interest, the moving trajectory of the key points in the hand contour is obtained. When the coordinates of the moving trajectory in the vertical direction are increasing, it is determined to be an increasing flow input type. When the coordinates of the moving trajectory in the vertical direction are decreasing, it is determined to be a decreasing flow input type, including: The fingertip contour points in the hand contour are obtained as key points, the position coordinates of the key points in consecutive frames are recorded according to the time sequence, and the position coordinates are connected in sequence to obtain the movement trajectory; Select adjacent key points in the moving trajectory in chronological order and calculate their vertical coordinate differences; If the coordinate differences within the preset time period are all greater than the reference constant, it is determined that the coordinates on the moving trajectory are increasing, and it is determined to be an increasing flow input type; If the coordinate differences within the preset time period are all smaller than the reference constant, it is determined that the coordinates on the moving trajectory are decreasing and it is determined to be a flow reduction input type.

5. The method according to claim 2, characterized in that: Before obtaining the moving trajectory of the key points in the hand contour, it also includes: Obtain the palm contour points and fingertip contour points in the hand contour as judgment points, and calculate the point distance between the judgment points; The point distance difference of the corresponding judgment points in adjacent frames is calculated. When the point distance difference corresponding to the preset frame is less than the reference constant, the trajectory recording information is responded to and the moving trajectory is started to be obtained.

6. The method according to claim 1, characterized in that Update the drug flow rate according to the flow rate change trend, and recalculate the infusion time based on the updated drug flow rate and the current drug volume, including: The patient's adjustment time is obtained, and the predicted distance is obtained according to the product of the adjustment time and the reference speed; When the flow velocity change trend is an increasing trend, a position at a predicted distance from the initial position in a preset increasing direction is determined as a predicted increasing position, and the flow velocity corresponding to the predicted increasing position is updated as the drug flow velocity; When the flow velocity change trend is a deceleration trend, a position at a predicted distance from the initial position in the preset deceleration direction is determined as a predicted deceleration position, and the flow velocity corresponding to the predicted deceleration position is updated as the drug flow velocity; The infusion time is recalculated based on the ratio of the current drug volume and the updated drug flow rate.

7. The method according to claim 6, characterized in that The flow velocity corresponding to the predicted speed-up position or the predicted speed-down position is calculated by the following steps, including: Retrieving a preset model corresponding to the flow regulator, determining a plurality of preset positions corresponding to the preset model, each preset position being configured with a corresponding preset flow rate; Obtaining a preset position interval where the predicted speed-up position or the predicted speed-down position is located, and determining the interval length of the preset position interval; Calculate the predicted length from the predicted speed-up position or the predicted speed-down position to the left end point of the preset position, and obtain the interval proportion according to the ratio of the predicted length to the interval length; The flow velocity difference corresponding to the preset position interval is obtained, and the product of the interval proportion and the flow velocity difference is added to the preset flow velocity corresponding to the left endpoint of the preset position interval to obtain the flow velocity corresponding to the predicted acceleration position or the predicted deceleration position.

8. The method according to claim 1, characterized in that When the patient's hand motion type is not identified, the current position of the flow regulator is obtained according to the mobile device, and the infusion time is recalculated according to the drug flow rate corresponding to the current position, including: When the hand motion type of the patient is not identified, the first moment is recorded, and the mobile device is controlled to go to the position corresponding to the diagnosis position mark to collect image data, and the second moment of the collection is recorded; Retrieving a preset model corresponding to the flow regulator, the preset model includes a scale line, and the scale line has a plurality of preset positions; Obtaining the span line of the flow regulator in the flow direction of the infusion tube in the collected image, and determining the position point of the regulating element on the span line, and determining the target point position of the position point on the scale line according to the proportional relationship between the scale line and the span line; The remaining amount of medicine at the first moment is calculated according to the historical drug flow rate, the drug consumption from the first moment to the second moment is calculated according to the drug flow rate at the target point, and the infusion time is recalculated by dividing the value obtained by subtracting the drug consumption from the remaining amount of medicine by the drug flow rate corresponding to the target point.

9. The method according to claim 8, characterized in that Obtain the span line of the flow regulator in the flow direction of the infusion tube in the captured image, determine the position point of the regulating element on the span line, and determine the target point position of the position point on the scale line according to the proportional relationship between the scale line and the span line, including: Extract the current contour corresponding to the flow regulator in the acquired image, obtain two endpoints of the current contour in the flow direction of the infusion tube, and connect the two endpoints to obtain a span line; Obtaining the center point of multiple contour intersections of the regulating element and the span line as the finally selected position point, and determining a first distance between the position point and the left end point of the span line; Determine the length ratio of the scale line and the span line according to the proportional relationship between the scale line and the span line, and multiply the first distance and the length ratio to obtain the second distance; Determine the position point at the second distance from the left end point of the scale line as the target point.

10. A nursing interaction processing system based on a digital twin model, characterized in that: include: The initial module is used to bind the patient and the treatment location identification in the twin model, record the drug flow rate and the initial position of the flow regulator, and calculate the infusion time based on the drug volume; A judgment module, used to judge the hand movement type of the patient, and determine the flow rate change trend according to the hand movement type, wherein the hand movement type includes a flow increase input type and a flow decrease input type; A calculation module, used to update the drug flow rate according to the flow rate change trend, and recalculate the infusion time according to the updated drug flow rate and the current drug volume; The warning module is used to obtain the current position of the flow regulator according to the mobile device when the patient's hand movement type is not recognized, recalculate the infusion time according to the drug flow rate corresponding to the current position, and send a reminder message to the nursing terminal when the infusion time is less than the threshold.

Images