An infusion status monitoring method and system for an intelligent ward

Abstract

The present invention relates to the field of smart medical technology, particularly to a method and system for monitoring the infusion status of a smart ward, comprising: using a relative position regulator to fix the relative position between an infusion bag and a collection device, and connecting the relative position regulator to an infusion stand; in response to a start monitoring instruction, each collection device begins to acquire the corresponding infusion bag information according to pre-set detection rules; in response to a stop monitoring instruction, each collection device stops acquiring infusion bag information; all infusion bag information is input into a comprehensive judgment model for liquid solution remaining, and a comprehensive judgment is performed to obtain the infusion bag remaining status; and an early warning message is issued based on the displayed infusion bag remaining status. This method overcomes the common drawbacks of existing technologies, such as difficulty in balancing cost, accuracy, and environmental adaptability, and meets the comprehensive needs of medical institutions for economy, reliability, and universality.

Description

Technical Field

[0001] The present invention belongs to the field of smart medical technology, and in particular relates to a method and system for monitoring the infusion status of a smart ward. Background Art

[0002] Clinical infusion monitoring in existing technologies mainly relies on the following technical means: First, a weighing sensor is used to estimate the liquid remaining amount through weight changes, but factors such as the shaking of the infusion stand and the uneven liquid dripping rate will cause the weight data to fluctuate violently, especially when the patient moves or adjusts his position, the error is large; Second, the image recognition solution based on visible light camera can directly observe the liquid level position, but due to the material characteristics of the translucent infusion bag, the recognition accuracy is significantly reduced in backlight, strong light or night environment, and problems such as liquid surface reflection and bubble interference have not been effectively solved; Third, although high-precision three-dimensional sensing equipment such as depth camera can detect the liquid level, the equipment cost is too high and requires a high-performance processor to support point cloud data analysis, making it difficult to deploy on a large scale in ordinary wards.

[0003] Therefore, there is an urgent need for a method and system for monitoring the infusion status of smart wards. By rigidly fixing the relative position adjuster between the infusion bag and the acquisition device, the viewing angle deviation caused by patient movement is eliminated, significantly reducing the error rate of liquid level detection. By combining RGB image preprocessing and near-infrared structured light three-dimensional point cloud dynamic compensation technology, the interference of reflections, bubbles and complex lighting can be overcome, effectively improving the accuracy of liquid surface recognition and adopting a low-cost alternative solution. By integrating the FLSI model with multi-parameter weight analysis such as liquid level and deformation, a four-level dynamic graded warning of the remaining status is achieved, significantly reducing the false alarm rate. The modular design adapts to the hospital's existing system and supports low-cost large-scale deployment. Summary of the Invention

[0004] The object of the present invention is to provide a method for monitoring the infusion status of an intelligent ward, comprising the following steps:

[0005] A relative position regulator is used to fix the relative position between the infusion bag and the collection device, and the relative position regulator is connected to the infusion stand; in response to a start monitoring instruction, each collection device begins to obtain the infusion bag information corresponding to the collection device according to a preset detection rule; in response to a stop monitoring instruction, each collection device stops collecting the infusion bag information; all infusion bag information is input into a comprehensive judgment model for liquid solution remaining amount to perform a comprehensive judgment and obtain the infusion bag remaining amount status; and a warning message is issued according to the displayed infusion bag remaining amount status;

[0006] The acquiring of the infusion bag information corresponding to the acquisition device includes: using a front RGB image acquisition device to acquire an RGB image of the front of the infusion bag, and acquiring liquid level proportion information based on the RGB image of the front of the infusion bag; using a side profile information acquisition device to acquire an infusion bag width set on the side of the infusion bag, and acquiring average profile information based on the infusion bag width set;

[0007] The infusion bag information includes: liquid level ratio information and average profile information;

[0008] The relative position adjuster includes a compatible connection part, a collection device fixing part and an infusion bag fixing part which are connected in sequence; the compatible connection part is used to replace the infusion bag and connect to the existing infusion stand; the collection device fixing part includes a plurality of retractable fixing arms, on which the collection device is fixed; the infusion bag fixing part is fixedly connected to the infusion bag.

[0009] Furthermore, the obtaining of liquid level proportion information based on the RGB image of the front side of the infusion bag includes:

[0010] An RGB image acquisition device is fixed to the front of the infusion bag to obtain an RGB image of the front of the infusion bag in real time; the front RGB image is preprocessed to generate standardized image data; the liquid level line position information of the infusion bag is extracted from the standardized image data based on an image algorithm; and the percentage of the liquid level height to the total height of the infusion bag is calculated based on the liquid level line position information to obtain the liquid level proportion information.

[0011] Furthermore, the preprocessing of the front RGB image to generate standardized image data includes:

[0012] Image denoising: Use Gaussian filtering or median filtering to remove image noise;

[0013] Image enhancement: adjust image brightness and contrast, and highlight the liquid level line and the edge of the infusion bag;

[0014] Image cropping: cropping the region of interest based on the position of the infusion bag in the image;

[0015] The step of extracting the liquid level position information of the infusion bag from the standardized image data based on an image algorithm includes:

[0016] Use the Canny edge detection algorithm to extract the liquid level line of the infusion bag;

[0017] The straight line feature of the liquid level line is detected by Hough transform to determine the position of the liquid level line in the image;

[0018] Calculate the pixel distance between the liquid level line and the bottom of the infusion bag as the liquid level line position information;

[0019] The obtaining of the liquid level proportion information includes:

[0020] Liquid level ratio information = liquid level line position information / infusion bag height.

[0021] Furthermore, the collecting of the infusion bag width set of the side of the infusion bag using the side profile information collecting device includes:

[0022] Acquire a depth image of the infusion bag using a side profile information acquisition device; the side profile information acquisition device includes: a near-infrared structured light projection device and a bandpass filter CMOS camera;

[0023] Use sub-pixel interpolation algorithm to convert depth image into 3D point cloud;

[0024] Performing motion compensation processing on the three-dimensional point cloud to obtain optimized point cloud data; the motion compensation processing includes: Kalman filtering and quaternion attitude solution based on inertial sensors;

[0025] The contour information of the side of the infusion bag is obtained based on the optimized point cloud data. Based on the contour information, a set of infusion bag widths of the side of the infusion bag is obtained using a number of equally spaced parallel lines.

[0026] Furthermore, obtaining average profile information based on the infusion bag width set includes:

[0027] The infusion bag width set is traversed from the top of the infusion bag to the bottom of the infusion bag in sequence. If the total width from the top of the infusion bag to the middle of the infusion bag is greater than a preset first threshold, the average value of all the infusion bag width data from the top of the infusion bag to the bottom of the infusion bag is used to calculate the average value to obtain the average contour information; otherwise, the average value of all the infusion bag width data from the middle of the infusion bag to the bottom of the infusion bag is used to calculate the average contour information.

[0028] Furthermore, the step of inputting all the infusion bag information into the comprehensive judgment model for the remaining amount of the liquid medicine for comprehensive judgment includes:

[0029] The comprehensive judgment model of the residual amount of liquid medicine is:

[0030] FLSI = (W_avg × α) + (H_per × β) + (T_inv × γ) + (ΔW_rate × δ)

[0031] The weight coefficient must be satisfied: α + β + γ + δ = 1

[0032] Where FLSI is the liquid level status index, W_avg is the average width of the infusion bag, H_per is the percentage of the liquid level height, T_inv is the inverse of the detection time, and ΔW_rate is the width change rate;

[0033] The process of obtaining the remaining status of the infusion bag includes:

[0034] If FLSI ≥ 80%, the remaining state of the infusion bag is judged as: high remaining state;

[0035] If 60%≤FLST≤80%, the remaining state of the infusion bag is judged as: normal remaining state;

[0036] If 10%≤FLST≤60%, the remaining state of the infusion bag is judged as: low remaining;

[0037] If FLSI ≤ 10%, the remaining status of the infusion bag is judged as: replacement is required.

[0038] Another object of the present invention is to provide an infusion status monitoring device for the infusion status monitoring method of the smart ward according to the present invention, comprising:

[0039] Relative position regulator, acquisition device, calculation module, power supply module, alarm module and user control module;

[0040] The relative position regulator is used to fix the relative position between the infusion bag and the collection device, and the relative position regulator is connected to the infusion stand;

[0041] The acquisition device includes: a front RGB image acquisition device and a side profile information acquisition device;

[0042] The calculation module, power supply module, alarm module and user control module are installed inside the relative position regulator;

[0043] The calculation module is used to execute the comprehensive judgment model of the remaining amount of the liquid medicine to make a comprehensive judgment, input the infusion bag information, and output the remaining amount status of the infusion bag; and issue a warning message according to the displayed remaining amount status of the infusion bag;

[0044] The power supply module is powered by a detachable battery;

[0045] The alarm module includes a buzzer and a color display device;

[0046] The user control module includes: a start detection button, a pause detection button and a reset button.

[0047] Furthermore, the front RGB image acquisition device is fixedly connected to the relative position adjuster via a retractable fixed arm; the line connecting the front RGB image acquisition device and the center of the infusion bag is perpendicular to the plane on which the front of the infusion bag is located; the side profile information acquisition device is fixedly connected to the relative position adjuster via a retractable fixed arm; the line connecting the side profile information acquisition device and the center of the infusion bag is parallel to the plane on which the front of the infusion bag is located;

[0048] The acquisition device comprises: two front RGB image acquisition devices respectively located on both sides of the front of the infusion bag and two side profile information acquisition devices respectively located on both sides of the measuring surface of the infusion bag;

[0049] or

[0050] The acquisition device comprises: a front RGB image acquisition device and a side profile information acquisition device;

[0051] or

[0052] The acquisition device is: a front RGB image acquisition device;

[0053] or

[0054] The collecting device is: a side profile information collecting device.

[0055] Another object of the present invention is to provide a computer device comprising: a memory for storing instructions; a processor for executing the instructions, so that the device implements the infusion status monitoring method of the smart ward as described in the present invention.

[0056] Another object of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the infusion status monitoring method of the smart ward as described in the present invention.

[0057] The beneficial effects of the present invention are:

[0058] 1. Stable monitoring viewing angle: By designing a relative position adjuster (compatible connection part, acquisition device fixing part, infusion bag fixing part), the infusion bag and the acquisition device are rigidly fixed, eliminating the viewing angle deviation caused by patient movement or body position adjustment, and effectively reducing the error rate of liquid level detection.

[0059] 2. Multimodal, high-precision liquid level recognition: Based on front-facing RGB image preprocessing (denoising, enhancement, and cropping), Canny edge detection, and Hough transform algorithms, combined with side-facing near-infrared structured light 3D point cloud compensation (sub-pixel interpolation and motion compensation), this technology effectively overcomes the effects of translucent material reflections, bubble interference, and complex lighting, significantly improving liquid level recognition accuracy.

[0060] 3. Low-cost dynamic contour modeling: Low-cost near-infrared structured light is used to replace the depth camera, and the real-time monitoring of the infusion bag deformation state is achieved through dynamic contour width collection and adaptive mean calculation.

[0061] 4. Intelligent comprehensive margin judgment: The designed liquid level status index (FLSI) model integrates multiple parameters such as liquid level height, contour width, detection time, and deformation rate (weight coefficients α, β, γ, δ) to accurately classify high / normal / low margin and replacement status, effectively reducing false alarm rates.

[0062] 5. Scalable deployment architecture: Modular devices (retractable fixed arms, multi-collection device layout) adapt to various infusion stands and ward scenarios. Lightweight computing modules and edge storage solutions support low-cost large-scale deployment and are compatible with existing hospital information systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a flow chart of a method for monitoring the infusion status of an intelligent ward according to the present invention;

[0064] Figure 2 This is a structural diagram of an infusion status monitoring device for an intelligent ward according to an embodiment of the present invention;

[0065] Figure 3 Schematic diagrams of four arrangements of the collection device according to an embodiment of the present invention;

[0066] Among them, (a) is a front RGB image acquisition device, (b) is a side profile information acquisition device, (c) is a front RGB image acquisition device and a side profile information acquisition device, and (d) is two front RGB image acquisition devices and two side profile information acquisition devices;

[0067] In the figure, 100: infusion bag, 210: compatible connection part, 220: acquisition device fixing part, 230: infusion bag fixing part, 240: fixing arm, 310: front RGB image acquisition device, 320: side profile information acquisition device. DETAILED DESCRIPTION

[0068] The present invention provides a method and system for monitoring the infusion status of an intelligent ward, which will be further described in detail below with reference to the accompanying drawings.

[0069] like Figure 1 The embodiment of the present invention shown discloses a method for monitoring the infusion status of a smart ward, comprising the following steps:

[0070] A relative position regulator is used to fix the relative position between the infusion bag and the collection device, and the relative position regulator is connected to the infusion stand; in response to a start monitoring instruction, each collection device begins to obtain the infusion bag information corresponding to the collection device according to a preset detection rule; in response to a stop monitoring instruction, each collection device stops collecting the infusion bag information; all infusion bag information is input into a comprehensive judgment model for liquid solution remaining amount to perform a comprehensive judgment and obtain the infusion bag remaining amount status; and a warning message is issued according to the displayed infusion bag remaining amount status;

[0071] The acquisition of the infusion bag information corresponding to the acquisition device includes: using the front RGB image acquisition device 310 to acquire an RGB image of the front of the infusion bag, and acquiring liquid level proportion information based on the RGB image of the front of the infusion bag; using the side profile information acquisition device 320 to acquire an infusion bag width set on the side of the infusion bag, and acquiring average profile information based on the infusion bag width set;

[0072] The infusion bag information includes: liquid level ratio information and average profile information;

[0073] The relative position adjuster includes a compatible connection part 210, a collection device fixing part 220 and an infusion bag fixing part 230 connected in sequence; the compatible connection part 210 is used to replace the infusion bag and connect to the existing infusion stand; the collection device fixing part 220 includes a plurality of retractable fixing arms 240, on which the collection device is fixed; the infusion bag fixing part 230 is fixedly connected to the infusion bag.

[0074] In this embodiment, the infusion bag is fixedly connected to the relative position regulator via the infusion bag fixing portion 230; the collection device is fixedly connected to the relative position regulator via the collection device fixing portion 220; the relative position between the infusion bag and the collection device is fixed by the relative position regulator, so that the infusion bag information can be collected by the subsequent collection device.

[0075] The compatible connection part 210 is connected to the existing infusion stand, so that it is compatible with various existing infusion stands without any modification. The retractable fixed arm 240 adjusts the relative position of the collection device to achieve compatibility with collection devices with different performance parameters.

[0076] The specific implementation process of each step is explained below.

[0077] The method of obtaining liquid level ratio information based on the RGB image of the front side of the infusion bag includes:

[0078] An RGB image acquisition device is fixed to the front of the infusion bag to obtain an RGB image of the front of the infusion bag in real time; the front RGB image is preprocessed to generate standardized image data; the liquid level line position information of the infusion bag is extracted from the standardized image data based on an image algorithm; and the percentage of the liquid level height to the total height of the infusion bag is calculated based on the liquid level line position information to obtain the liquid level proportion information.

[0079] Preprocessing the front RGB image to generate standardized image data includes:

[0080] Image denoising: Use Gaussian filtering or median filtering to remove image noise;

[0081] Image enhancement: adjust image brightness and contrast, and highlight the liquid level line and the edge of the infusion bag;

[0082] Image cropping: cropping the region of interest based on the position of the infusion bag in the image;

[0083] The step of extracting the liquid level position information of the infusion bag from the standardized image data based on an image algorithm includes:

[0084] Use the Canny edge detection algorithm to extract the liquid level line of the infusion bag;

[0085] The straight line feature of the liquid level line is detected by Hough transform to determine the position of the liquid level line in the image;

[0086] Calculate the pixel distance between the liquid level line and the bottom of the infusion bag as the liquid level line position information;

[0087] The obtaining of the liquid level proportion information includes:

[0088] Liquid level ratio information = liquid level line position information / infusion bag height.

[0089] In this embodiment, the front RGB image acquisition device 310 obtains liquid level height information and determines the remaining status of the infusion bag. The liquid level height is analyzed by the image processing algorithm, and combined with the comprehensive judgment model of the remaining amount of the infusion bag, accurate monitoring and early warning of the remaining status of the infusion bag are achieved.

[0090] The specific implementation process is as follows:

[0091] Step 1: Installation and Initialization

[0092] The front RGB image acquisition device 310 is fixed in front of the infusion bag through the acquisition device fixing part of the relative position adjuster to ensure that the acquisition device maintains a preset distance and angle with the infusion bag.

[0093] Initialize the front RGB image acquisition device 310 and set parameters such as image acquisition resolution and frame rate to ensure that the image clarity meets the liquid level detection requirements.

[0094] Step 2: Image acquisition and preprocessing

[0095] The front RGB image acquisition device 310 continuously acquires the RGB image of the front of the infusion bag.

[0096] Preprocess the collected images, including:

[0097] Image denoising: Use Gaussian filtering or median filtering to remove image noise.

[0098] Image enhancement: adjust image brightness and contrast to highlight the liquid level line and the edge of the infusion bag.

[0099] Image cropping: Based on the position of the infusion bag in the image, the region of interest (ROI) is cropped to reduce the amount of calculation.

[0100] Step 3: Liquid level detection

[0101] Use an edge detection algorithm (such as Canny edge detection) to extract the liquid level line of the infusion bag.

[0102] The straight line features of the liquid level line are detected by Hough Transform to determine the position of the liquid level line in the image.

[0103] Calculate the pixel distance between the liquid level line and the bottom of the infusion bag as a preliminary measurement of the liquid level height.

[0104] In an optional embodiment, the method further includes:

[0105] Step 4: Liquid level calibration;

[0106] Based on the known dimensions of the infusion bag (e.g., height and width) and the pixel ratio in the image, the pixel values of the liquid level are converted to the actual physical height. The calibration process takes into account the tilt angle of the infusion bag and the viewing angle deviation of the acquisition device, and uses geometric transformation to correct measurement errors.

[0107] Step 5: Calculate the pixel distance between the liquid level line and the bottom of the infusion bag as the liquid level line position information;

[0108] The obtaining of the liquid level proportion information includes:

[0109] Liquid level ratio information = liquid level line position information / infusion bag height.

[0110] In an optional embodiment, when the remaining amount falls below a preset threshold, the system issues an early warning message, including an audible prompt, flashing lights, or remote notification; the early warning message is displayed in real time via the smart ward monitoring platform, alerting medical staff to take timely action. This is not specifically limited in this embodiment.

[0111] In a preferred embodiment, the alarm module includes a buzzer and a color display device; omitting modules such as the Internet of Things and wireless data transmission is more conducive to reducing power consumption and better meeting the actual application scenario requirements of smart wards. It has the following advantages:

[0112] High precision: Image processing algorithms and geometric calibration ensure the accuracy of liquid level measurement.

[0113] Real-time: The front RGB image acquisition device continuously monitors and updates the remaining status in real time.

[0114] Adaptability: Compatible with infusion bags of different specifications and adaptable to various scenarios through calibration and model adjustment.

[0115] Intelligence: Combined with the comprehensive judgment model of liquid medicine remaining, it realizes automatic early warning and reduces manual intervention.

[0116] The collecting of the infusion bag width set on the side of the infusion bag by using the side profile information collecting device 320 includes:

[0117] A side profile information acquisition device 320 is used to acquire a depth image of the infusion bag; the side profile information acquisition device 320 includes: a near-infrared structured light projection device and a bandpass filter CMOS camera;

[0118] Use sub-pixel interpolation algorithm to convert depth image into 3D point cloud;

[0119] Performing motion compensation processing on the three-dimensional point cloud to obtain optimized point cloud data; the motion compensation processing includes: Kalman filtering and quaternion attitude solution based on inertial sensors;

[0120] The contour information of the side of the infusion bag is obtained based on the optimized point cloud data. Based on the contour information, a set of infusion bag widths of the side of the infusion bag is obtained using a number of equally spaced parallel lines.

[0121] In this embodiment, the specific steps of obtaining the depth image of the infusion bag include:

[0122] a) Perform a laser safety self-test, set the power density to ≤5mW / cm², and adjust the camera focus using the voice coil motor to achieve the following image clarity function:

[0123]

[0124] Where Gx and Gy are the Sobel gradient operators in the horizontal and vertical directions respectively; the Sobel operator is used to detect edges and measure image clarity;

[0125] b) The near-infrared laser is driven by a 120Hz square wave to project a speckle pattern with a speckle size of σ = 1.22λ / NA.

[0126]

[0127] Where, λ=850nm, numerical aperture NA=0.05;

[0128] c) Synchronously capture two frames of images and calculate the effective image:

[0129]

[0130] Where, I on is the frame when the structured light is activated, I off For frames with only ambient light, ε=0.01;

[0131] d) Perform Census transform in a 9×9 window to generate a bit string C(u,v), and obtain the sub-pixel disparity d by Hamming distance matching sub :

[0132]

[0133] Where d is the parallax;

[0134] e) Fusion of inertial sensor data to compensate for pixel displacement:

[0135]

[0136] Where f is the focal length of the camera, Z is the depth of the scene, and V x is the velocity obtained by integrating the gyroscope data, a x is the acceleration provided by the accelerometer, Δt is the time interval;

[0137] f) Generate depth matrix , calculate the confidence Q:

[0138]

[0139] Where N valid is the number of valid disparity measurements, N total is the total number of measurements, is the variance of disparity;

[0140] g) When Q < 0.85, the resampling mechanism is triggered, otherwise the depth image of the infusion bag is generated.

[0141] The sub-pixel interpolation algorithm specifically includes:

[0142] Bicubic interpolation is used to improve spatial resolution during the disparity calculation stage;

[0143] Introduce parallax compensation:

[0144]

[0145] Where a is the instantaneous acceleration of the infusion bag and t is the sampling interval.

[0146] The specific steps of the motion compensation are:

[0147] Create the state vector:

[0148]

[0149] Where x, y, z are the coordinates of the object in three-dimensional space, θx, θy, θz are the Euler angles of the object around the x, y, z axes;

[0150] The Mahony complementary filter is used to fuse the gyroscope angular velocity ω and the accelerometer data a;

[0151] Correct point cloud coordinates in real time through coordinate transformation matrix:

[0152]

[0153] Where R is the rotation matrix and T is the translation vector.

[0154] The acquiring of average profile information based on the infusion bag width set includes:

[0155] The infusion bag width set is traversed from the top of the infusion bag to the bottom of the infusion bag in sequence. If the total width from the top of the infusion bag to the middle of the infusion bag is greater than a preset first threshold, the average value of all the infusion bag width data from the top of the infusion bag to the bottom of the infusion bag is used to calculate the average value to obtain the average contour information; otherwise, the average value of all the infusion bag width data from the middle of the infusion bag to the bottom of the infusion bag is used to calculate the average contour information.

[0156] In this embodiment, the side of the infusion bag exhibits a spindle shape, narrow at the top and wide at the bottom, due to gravity. In the later stages of infusion, changes in the bag's side width are primarily concentrated at the bag's bottom. Therefore, when the total width from the top to the middle of the bag exceeds a preset first threshold, the average value of all bag width data from the top to the bottom is calculated to obtain average profile information. Otherwise, the average value of all bag width data from the middle to the bottom is calculated to obtain average profile information. In this embodiment, based on the actual variation characteristics of the infusion bag, processing is performed only on the bottom of the bag during the more important later stages of infusion. Obtaining average profile information based on the bag width set is more accurate and secure.

[0157] The step of inputting all the infusion bag information into the comprehensive judgment model for the remaining amount of the liquid medicine for comprehensive judgment includes:

[0158] The Fluid Level Status Index (FLSI) was calculated using the comprehensive judgment model for residual liquid amount.

[0159] The comprehensive judgment model of the residual amount of liquid medicine is:

[0160] FLSI = (W_avg × α) + (H_per × β) + (T_inv × γ) + (ΔW_rate × δ)

[0161] The weight coefficient must be satisfied: α + β + γ + δ = 1

[0162] Where FLSI is the liquid level status index, W_avg is the average width of the infusion bag, H_per is the percentage of liquid level height, T_inv is the inverse of the detection time, and ΔW_rate is the width change rate;

[0163] The process of obtaining the remaining status of the infusion bag includes:

[0164] If FLSI ≥ 80%, the remaining state of the infusion bag is judged as: high remaining state;

[0165] If 60%≤FLST≤80%, the remaining state of the infusion bag is judged as: normal remaining state;

[0166] If 10%≤FLST≤60%, the remaining state of the infusion bag is judged as: low remaining;

[0167] If FLSI ≤ 10%, the remaining status of the infusion bag is judged as: replacement is required.

[0168] In this embodiment, the specific values of the parameters of the comprehensive judgment model for the residual amount of liquid medicine are as follows:

[0169] 1. Average width of infusion bag (W_avg)

[0170] Calculation method: arithmetic average of the width data collected within a single detection cycle

[0171] Weight recommendation: α = 0.2

[0172] Basis: reflects the overall expansion / contraction state of the infusion bag, but with hysteresis

[0173] 2. Liquid level height percentage (H_per)

[0174] Calculation method: H_per = (current liquid level / total container height) × 100%

[0175] Weight recommendation: β = 0.5

[0176] Basis: Directly reflects the liquid balance and is the core monitoring indicator

[0177] 3. Inverse detection time (T_inv)

[0178] Calculation method: T_inv = 1 / detection duration (unit: seconds⁻¹)

[0179] Weight suggestion: γ = 0.1

[0180] Basis: The shorter the detection interval, the higher the real-time data. Refer to the detection timeliness requirements.

[0181] 4. Width change rate (ΔW_rate)

[0182] Calculation: ΔW_rate = (W_now - W_prev) / Δt × 100%

[0183] Weight recommendation: δ = 0.2

[0184] Basis: reflects abnormal liquid flow rate and can warn of blockage / leakage

[0185] In this embodiment, the comprehensive model for determining remaining drug level combines the percentage of liquid level height after processing the RGB image of the front of the infusion bag and the average width of the infusion bag obtained from the side of the bag using a near-infrared structured light projection device and a bandpass filtered CMOS camera. This model combines the advantages of image processing and 3D reconstruction technologies. A relative position adjuster is also used to maintain the relative position between the infusion bag and the acquisition device, ensuring high recognition efficiency and compatibility.

[0186] like Figure 2 As shown, another embodiment of the present invention discloses an infusion status monitoring device according to the infusion status monitoring method of the smart ward of the present invention, comprising:

[0187] Relative position regulator, acquisition device, calculation module, power supply module, alarm module and user control module;

[0188] The relative position regulator is used to fix the relative position between the infusion bag and the collection device, and the relative position regulator is connected to the infusion stand;

[0189] The acquisition device includes: a front RGB image acquisition device 310 and a side profile information acquisition device 320;

[0190] The calculation module, power supply module, alarm module and user control module are installed inside the relative position regulator;

[0191] The calculation module is used to execute the comprehensive judgment model of the remaining amount of the liquid medicine to make a comprehensive judgment, input the infusion bag information, and output the remaining amount status of the infusion bag; and issue a warning message according to the displayed remaining amount status of the infusion bag;

[0192] The power supply module is powered by a detachable battery;

[0193] The alarm module includes a buzzer and a color display device;

[0194] The user control module includes: a start detection button, a pause detection button and a reset button.

[0195] In this embodiment, the actual situation of the smart ward is fully taken into consideration, and the compatible connection part 210 is fully compatible with the existing infusion stand without the need for physical modification; the relative position regulator is used to fix the relative position between the infusion bag and the acquisition device, so that the acquired RGB picture and depth image maintain a relatively fixed perspective and are as close to the front view perspective as possible, effectively reducing the complexity of the algorithm, without relying on a complex dynamic compensation process, effectively improving the detection efficiency and reducing the power consumption of the equipment operation; the recognition results of the RGB image and the depth image are integrated through the comprehensive judgment model of the remaining amount of liquid medicine, which can adapt to the complex light environment in the ward and improve the robustness of the system.

[0196] The front RGB image acquisition device 310 is fixedly connected to the relative position adjuster via a retractable fixed arm 240; the line connecting the front RGB image acquisition device 310 and the center of the infusion bag is perpendicular to the plane on which the front of the infusion bag is located; the side profile information acquisition device 320 is fixedly connected to the relative position adjuster via a retractable fixed arm 240; the line connecting the side profile information acquisition device 320 and the center of the infusion bag is parallel to the plane on which the front of the infusion bag is located;

[0197] In this embodiment, the four arrangements of the collection device of the embodiment of the present invention are as follows: Figure 3 As shown;

[0198] Among them, (a) is a front RGB image acquisition device, (b) is a side profile information acquisition device, (c) is a front RGB image acquisition device and a side profile information acquisition device, and (d) is two front RGB image acquisition devices and two side profile information acquisition devices;

[0199] The acquisition devices are: two front RGB image acquisition devices 310 located on both sides of the front of the infusion bag and two side profile information acquisition devices 320 located on both sides of the measuring surface of the infusion bag 100;

[0200] or

[0201] The acquisition device comprises: a front RGB image acquisition device 310 and a side profile information acquisition device 320;

[0202] or

[0203] The acquisition device is: a front RGB image acquisition device 310;

[0204] or

[0205] The collection device is: a side profile information collection device 320.

[0206] In this embodiment, the user can switch between the four modes according to the specific application scenario, and can perform special processing according to special circumstances such as light protection requirements and hard infusion bottles.

[0207] In this embodiment, the relevant implementation environment information is as follows:

[0208] Hardware configuration:

[0209] Front RGB image acquisition device 310: high-definition camera (resolution ≥ 1080p, frame rate ≥ 30fps).

[0210] Relative position adjuster: The retractable fixed arm 240 ensures that the distance between the camera and the infusion bag 100 is 20-30 cm.

[0211] Software Configuration:

[0212] Image processing algorithm: edge detection, Hough transform, etc. are implemented based on the OpenCV library.

[0213] Comprehensive judgment model for liquid medicine residue: residue calculation module developed based on Python or MATLAB.

[0214] Early warning system:

[0215] Local warning mode: LED light and buzzer.

[0216] Another embodiment of the present invention discloses a computer device, comprising: a memory for storing instructions; and a processor for executing the instructions, so that the device implements the infusion status monitoring method for the smart ward as described in the present invention.

[0217] Another embodiment of the present invention discloses a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the method for monitoring the infusion status of the smart ward according to the present invention is implemented.

Claims

1. A method for monitoring the infusion status of an intelligent ward, characterized in that: The following steps are involved: A relative position regulator is used to fix the relative position between the infusion bag and the collection device, and the relative position regulator is connected to the infusion stand; in response to the start monitoring instruction, each collection device starts to obtain the infusion bag information corresponding to the collection device according to the preset detection rules; In response to the stop monitoring instruction, each collection device stops collecting the infusion bag information; all the infusion bag information is input into the liquid balance comprehensive judgment model for comprehensive judgment to obtain the infusion bag balance status; Issue warning information according to the remaining status of the infusion bag; The acquisition of the infusion bag information corresponding to the acquisition device includes: using the front RGB image acquisition device (310) to acquire the RGB image of the front of the infusion bag, and acquiring the liquid level ratio information based on the RGB image of the front of the infusion bag; using the side profile information acquisition device (320) to acquire the infusion bag width set of the side of the infusion bag, and acquiring the average profile information based on the infusion bag width set; The infusion bag information includes: liquid level ratio information and average profile information; The relative position regulator comprises a compatible connection portion (210), a collection device fixing portion (220), and an infusion bag fixing portion (230) connected in sequence; the compatible connection portion (210) is used to replace the infusion bag and connect to the existing infusion stand; the collection device fixing portion (220) comprises a plurality of retractable fixing arms (240), on which the collection device is fixed; and the infusion bag fixing portion (230) is fixedly connected to the infusion bag. The method of obtaining liquid level ratio information based on the RGB image of the front side of the infusion bag includes: By using an RGB image acquisition device fixed to the front of the infusion bag, an RGB image of the front of the infusion bag is acquired in real time; the front RGB image is preprocessed to generate standardized image data; the liquid level position information of the infusion bag is extracted from the standardized image data based on an image algorithm; and the percentage of the liquid level height to the total height of the infusion bag is calculated based on the liquid level position information to obtain the liquid level percentage information; Preprocessing the front RGB image to generate standardized image data includes: Image denoising: Use Gaussian filtering or median filtering to remove image noise; Image enhancement: adjust image brightness and contrast, and highlight the liquid level line and the edge of the infusion bag; Image cropping: cropping the region of interest based on the position of the infusion bag in the image; The step of extracting the liquid level position information of the infusion bag from the standardized image data based on an image algorithm includes: Use the Canny edge detection algorithm to extract the liquid level line of the infusion bag; The straight line feature of the liquid level line is detected by Hough transform to determine the position of the liquid level line in the image; Calculate the pixel distance between the liquid level line and the bottom of the infusion bag as the liquid level line position information; The obtaining of the liquid level proportion information includes: Liquid level ratio information = liquid level line position information / infusion bag height; The step of inputting all the infusion bag information into the comprehensive judgment model for the remaining amount of the liquid medicine for comprehensive judgment includes: The comprehensive judgment model of the residual amount of liquid medicine is: FLSI = (W_avg × α) + (H_per × β) + (T_inv × γ) + (ΔW_rate × δ) The weight coefficient must be satisfied: α + β + γ + δ = 1 Where FLSI is the liquid level status index, W_avg is the average width of the infusion bag, H_per is the percentage of liquid level height, T_inv is the inverse of the detection time, and ΔW_rate is the width change rate; The process of obtaining the remaining status of the infusion bag includes: If FLSI ≥ 80%, the remaining state of the infusion bag is judged as: high remaining state; If 60%≤FLST≤80%, the remaining state of the infusion bag is judged as: normal remaining state; If 10%≤FLST≤60%, the remaining state of the infusion bag is judged as: low remaining; If FLSI ≤ 10%, the remaining status of the infusion bag is judged as: replacement is required.

2. The method for monitoring the infusion status of an intelligent ward according to claim 1, characterized in that: The method of using the side profile information collection device (320) to collect the infusion bag width set of the side of the infusion bag comprises: A side profile information acquisition device (320) is used to acquire a depth image of the infusion bag; the side profile information acquisition device (320) comprises: a near-infrared structured light projection device and a bandpass filtering CMOS camera; Use sub-pixel interpolation algorithm to convert depth image into 3D point cloud; Performing motion compensation processing on the three-dimensional point cloud to obtain optimized point cloud data; the motion compensation processing includes: Kalman filtering and quaternion attitude solution based on inertial sensors; The contour information of the side of the infusion bag is obtained based on the optimized point cloud data, and based on the contour information, a set of infusion bag widths of the side of the infusion bag is obtained using a number of equally spaced parallel lines.

3. The method for monitoring the infusion status of an intelligent ward according to claim 1, characterized in that: The acquiring of average profile information based on the infusion bag width set includes: The infusion bag width set is traversed from the top of the infusion bag to the bottom of the infusion bag in sequence. If the total width from the top of the infusion bag to the middle of the infusion bag is greater than a preset first threshold, the average value of all the infusion bag width data from the top of the infusion bag to the bottom of the infusion bag is used to calculate the average value to obtain the average contour information; otherwise, the average value of all the infusion bag width data from the middle of the infusion bag to the bottom of the infusion bag is used to calculate the average contour information.

4. An infusion status monitoring device according to the infusion status monitoring method of the smart ward according to any one of claims 1 to 3, characterized in that: include: Relative position regulator, acquisition device, calculation module, power supply module, alarm module and user control module; The relative position regulator is used to fix the relative position between the infusion bag and the collection device, and the relative position regulator is connected to the infusion stand; The acquisition device comprises: a front RGB image acquisition device (310) and a side profile information acquisition device (320); The calculation module, power supply module, alarm module and user control module are installed inside the relative position regulator; The calculation module is used to execute the comprehensive judgment model of the remaining amount of the liquid medicine to make a comprehensive judgment, input the infusion bag information, and output the remaining amount status of the infusion bag; and issue a warning message according to the displayed remaining amount status of the infusion bag; The power supply module is powered by a detachable battery; The alarm module includes a buzzer and a color display device; The user control module includes: a start detection button, a pause detection button and a reset button.

5. The infusion status monitoring device according to claim 4, characterized in that: The front RGB image acquisition device (310) is fixedly connected to the relative position regulator via a retractable fixed arm (240); a line connecting the front RGB image acquisition device (310) and the center of the infusion bag is perpendicular to the plane where the front of the infusion bag is located; the side profile information acquisition device (320) is fixedly connected to the relative position regulator via a retractable fixed arm (240); a line connecting the side profile information acquisition device (320) and the center of the infusion bag is parallel to the plane where the front of the infusion bag is located; The acquisition devices include: two front RGB image acquisition devices (310) located on both sides of the front of the infusion bag, and two side profile information acquisition devices (320) located on both sides of the measuring surface of the infusion bag. or The acquisition device comprises: a front RGB image acquisition device (310) and a side profile information acquisition device (320); or The acquisition device comprises: a front RGB image acquisition device (310); or The collection device is: a side profile information collection device (320).

6. A computer device, characterized in that: include: a memory for storing instructions; The processor is used to execute the instructions so that the device implements the infusion status monitoring method of the smart ward as described in any one of claims 1-3.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the infusion status monitoring method of the intelligent ward as described in any one of claims 1 to 3 is implemented.

Images