Infusion bag water bath sterilization temperature control method and device, electronic equipment and medium

Abstract

The invention relates to an infusion bag water bath sterilization temperature control method and device, electronic equipment and a medium, and belongs to the technical field of medical sterilization equipment control. Analyzing according to each piece of image information to obtain infusion bag data on each layer of tray; generating a three-dimensional virtual model according to the infusion bag data on each layer of tray; the infusion bag density of each monitoring area is determined according to the three-dimensional virtual model, a primary sterilization scheme is determined according to the infusion bag density of each monitoring area, and the primary sterilization scheme is executed by the main spraying device and the auxiliary spraying devices of the monitoring areas; acquiring real-time temperature data based on a temperature sensor; after the preliminary sterilization scheme is executed for a preset time, the preliminary sterilization scheme is adjusted according to the real-time temperature data, so that the main spraying equipment and the auxiliary spraying equipment in each monitoring area execute the updated sterilization scheme until sterilization is completed. The sterilization device has the effect of improving the sterilization efficiency.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of medical sterilization equipment control, and in particular to an infusion bag water bath sterilization temperature control method and device, electronic equipment and a medium. BACKGROUND

[0002] Infusion bag water bath sterilization is a key process of terminal sterilization of large-volume injections, and the core requirement is to achieve complete killing of microorganisms through a high-temperature and high-pressure water environment. Temperature uniformity is the core guarantee of sterilization effect, and the temperature difference at each point in the sterilization cavity needs to be less than or equal to 1 DEG C.

[0003] In the existing infusion bag sterilization method, a whole temperature control scheme is mainly used, that is, the temperature data of the whole body is collected through the temperature sensor built in the sterilization cavity, and then the sterilization time is uniformly adjusted to realize temperature control. However, this method has the following defects: Firstly, in actual production, the loading density of the infusion bag is flexibly adjusted according to the production batch and the bag capacity. The temperature control parameters of the existing system are fixed set values, so when the loading density is increased, the gap between the bags is reduced, the heat water flowability is poor, and temperature dead angles are easily formed. When the loading density is reduced, the turbulent intensity of the hot water is insufficient, the local area is heated too quickly, and the temperature fluctuation is likely to exceed the standard, so manual parameter adjustment is required, which is complicated and low in efficiency.

[0004] Secondly, the existing system relies on a small number of centralized temperature sensors and cannot accurately capture the temperature distribution difference in the unit space of the sterilization cavity, and can only reflect the overall average temperature. Even if the overall temperature meets the standard, the local area may still not meet the standard due to poor water flow, thereby affecting the sterilization effect.

[0005] Therefore, it is urgent to provide a water bath sterilization temperature control method that can automatically adjust to the change of the loading density of the infusion bag and accurately balance the temperature field, to solve the problems of complicated parameter adaptation and low production efficiency. SUMMARY

[0006] In order to improve the sterilization efficiency, the application provides an infusion bag water bath sterilization temperature control method, device, electronic equipment and medium.

[0007] In the first aspect, the application provides an infusion bag water bath sterilization temperature control method, which adopts the following technical scheme: A method for controlling the temperature of infusion bags during water bath sterilization is applied to a pressure water bath sterilizer. The three-dimensional space of the water bath sterilization chamber of the pressure water bath sterilizer is divided into multiple monitoring zones, each monitoring zone is equipped with a corresponding temperature sensor, and a main spray device is also installed at the top of the water bath sterilization chamber. Each monitoring zone is equipped with a set of auxiliary spray devices. A support frame is provided inside the water bath sterilization chamber, and multiple trays are placed on the support frame. Multiple infusion bags are laid flat on each tray. At least one industrial camera is installed on at least one side of the water bath sterilization chamber sidewall corresponding to each tray for capturing images of the surface of each tray. The method is executed by electronic equipment and includes: Image information is acquired based on the industrial camera; Data on the infusion bags on each layer of the tray is obtained by analyzing the image information. A 3D virtual model is generated based on the data of the infusion bags on each layer of the tray; The density of infusion bags in each monitoring area is determined based on the three-dimensional virtual model. A preliminary sterilization plan is then determined based on the density of infusion bags in each monitoring area, and the main spray equipment and the auxiliary spray equipment in the monitoring area execute the preliminary sterilization plan. Real-time temperature data is acquired based on the temperature sensor. After the preset time for the preliminary sterilization scheme is executed, the preliminary sterilization scheme is adjusted according to the real-time temperature data, so that the main spray equipment and the auxiliary spray equipment in each of the monitoring areas execute the updated sterilization scheme until sterilization is completed.

[0008] By adopting the above technical solutions, through zoned monitoring, image recognition modeling, and dynamic spray adjustment, the distribution of infusion bags is accurately identified and a three-dimensional model is constructed. A preliminary sterilization plan is formulated based on density differences, and the main and auxiliary sprays work together to adapt to the needs of different areas. Parameters are dynamically optimized based on real-time temperature data to avoid incomplete or over-sterilization caused by uneven density, significantly improving the uniformity and control accuracy of sterilization temperature, ensuring the sterilization quality and drug efficacy stability of infusion bags, reducing manual intervention costs, adapting to various placement methods and specifications of infusion bags, significantly improving sterilization efficiency and equipment versatility, and providing reliable protection for medical infusion safety.

[0009] Further, the step of analyzing the image information to obtain the data of the infusion bags on each tray includes: If an industrial camera for capturing images of the surface of each tray is installed on the side wall of the water bath sterilization chamber corresponding to one side of the tray, the image information is input into the trained neural network infusion bag recognition model to obtain infusion bag data on each layer of tray; If one or more industrial cameras for capturing images of the surface of each tray are installed on the side wall of the water bath sterilization chamber corresponding to one or more sides of the tray, then: Determine the viewpoint type corresponding to the image information; The image information is segmented according to the template of the corresponding viewpoint type, and the first image after segmentation is retained. The edge parts of the first image with opposite or adjacent viewpoints overlap. The first image is transformed by perspective to obtain the second image; The second image is stitched together according to a preset position, and the overlapping areas of the second image are processed to obtain a third image in which there are no overlapping infusion bags. The third image is input into the trained neural network infusion bag recognition model to obtain infusion bag data on each layer of the tray.

[0010] By employing the above technical solutions, through direct recognition with a single camera or multi-camera segmentation, perspective transformation, and overlapping processing followed by stitching recognition, infusion bag data can be accurately acquired. This adapts to different tray widths, avoids visual blind spots and image distortion, and improves recognition accuracy.

[0011] Further, the processing of the second image of the overlapping area to obtain a third image without overlapping infusion bags includes: The overlapping region image is preprocessed, and the edge of the infusion bag in the overlapping region image is identified by the Canny edge detection algorithm. Morphological optimization operation is applied to identify the edge of the infusion bag in the overlapping region image, resulting in an overlapping region image with the edge of the infusion bag. Increase the transparency of the overlapping area image with the edge of the infusion bag to obtain a fourth image, and then overlap the two fourth images; Each infusion bag edge is sequentially identified as a target edge. For each target edge, it is determined whether there are identical or partially identical infusion bag edges within a preset range. If two identical infusion bag edges exist, the infusion bag image corresponding to the edge of either of the four images will be erased. If two infusion bag edges are identical, the infusion bag image corresponding to the incomplete infusion bag edge in the fourth image will be erased. The two processed fourth images are overlapped and their original transparency is restored. They are then stitched together with the non-overlapping areas of the second image in their original positions to form a third image in which there are no overlapping infusion bags.

[0012] By adopting the above technical solution, through Canny edge detection, morphological optimization and transparency overlay processing, the edges of infusion bags that are the same or partially the same in overlapping areas are accurately identified, redundant images are efficiently removed, infusion bags are avoided from being counted repeatedly, and the integrity and accuracy of the third image after stitching are ensured.

[0013] Further, determining whether there are identical or partially identical infusion bag edges within a preset range for each target edge includes: For each edge of an infusion bag within the overlapping area, a search area of ​​a preset range is defined based on its contour feature points, and the edges of other infusion bags within the search area are determined as edges to be matched. Calculate the shape similarity and partial overlap rate between each of the edges to be matched and the target edge; If the shape similarity of the edge to be matched is less than or equal to the first threshold and the partial overlap rate is greater than or equal to the second threshold, then the edge to be matched is determined to be the same as or partially the same as the target edge.

[0014] By adopting the above technical solution, the search area is delineated by contour feature points. By calculating the shape similarity and partial overlap rate, and combining dual thresholds, the edges of the same or partially the same infusion bags in the overlapping area are accurately determined, avoiding edge misjudgment, improving the accuracy and efficiency of overlap processing, and ensuring that subsequent infusion bag data identification is without redundancy or omission.

[0015] Furthermore, the step of generating a three-dimensional virtual model based on the data of the infusion bags on each layer of the tray includes: Establish virtual support racks and virtual pallets; A third image is obtained after being recognized by the neural network infusion bag recognition model. A coordinate system is established based on the third image to determine the first coordinate of each infusion bag. The third image coordinate system is standardized and unified with the coordinates of the virtual tray. Based on the first coordinates, the second coordinates of the infusion bag on the virtual tray are obtained. A virtual infusion bag is generated on the second coordinate, thus generating a three-dimensional virtual model.

[0016] By adopting the above technical solution, constructing a virtual support and tray, unifying the coordinate system and transforming the position of the infusion bag, a three-dimensional virtual model is accurately generated, restoring the actual placement of the infusion bag, and intuitively presenting the density distribution of each monitoring area, providing visualized and precise data support for the formulation of the preliminary sterilization plan.

[0017] Further, the monitoring area is divided based on the vertical plane of the water bath sterilization chamber, and the auxiliary spray device is located on the side wall of the water bath sterilization chamber adjacent to the monitoring area. The sterilization scheme includes spraying time and spraying intensity. The step of determining the preliminary sterilization scheme based on the density of infusion bags in each monitoring area, and causing the main spray device and the auxiliary spray device in the monitoring area to execute the preliminary sterilization scheme, includes: The overall infusion bag density is determined based on the infusion bag density in each monitoring area; Based on the comparison between the overall infusion bag density and the preset table, the first water spraying time and the first water spraying intensity of the main spraying equipment corresponding to the level of the overall infusion bag density are determined. The sterilization coefficient for each monitoring area is determined based on the first water spraying time and the first water spraying intensity. If the sterilization coefficient of the monitored area does not reach the threshold, then the difference between the sterilization coefficient and the threshold is calculated; The start-up time, second water spraying time, and second water spraying intensity of the auxiliary spraying equipment are determined based on the difference and the density of the infusion bag.

[0018] By adopting the above technical solution, combining overall and zoned density, matching the main spray parameters through a preset table, judging the demand based on the sterilization coefficient threshold, and accurately setting the secondary spray parameters based on the difference and density, the main and secondary sprays work together to adapt to the sterilization needs of different areas, avoiding sterilization imbalance caused by uneven density, improving the uniformity and control accuracy of sterilization temperature, ensuring sterilization effect, and optimizing the allocation of spray resources.

[0019] Further, adjusting the preliminary sterilization plan based on the real-time temperature data, so that the main spray equipment and the auxiliary spray equipment in the monitoring area execute the updated sterilization plan, includes: Calculate the average temperature and temperature fluctuation value of each monitoring area within a preset time period, and then calculate the overall average temperature; For the temperature data of each monitoring area, adjust the preliminary sterilization protocol according to the following rules: If the average temperature equals the preset target temperature, and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then the main spray parameters and the auxiliary spray parameters remain unchanged. If the average temperature is less than the preset target temperature, and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then the watering time or watering intensity is increased, including: Main spray equipment: If the overall average temperature is less than the preset target temperature, the first water spraying time is extended by a first preset ratio, or the first water spraying intensity is increased by a second preset ratio. Secondary sprinkler equipment: The second water spraying time is extended by a third preset ratio, or the second water spraying intensity is increased by a fourth preset ratio; If the average temperature is greater than the preset target temperature and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then reduce the water spraying time or water spraying intensity. Main spray equipment: If the overall average temperature is greater than the preset target temperature, shorten the first water spraying time by a first preset ratio, or reduce the first water spraying intensity by a second preset ratio; Secondary spray equipment: The second spraying time is shortened by a third preset ratio, or the second spraying intensity is reduced by a fourth preset ratio; If the temperature fluctuation value is greater than the temperature fluctuation threshold, adjust the spray angle of the auxiliary spray device and fine-tune the second water spray intensity according to the fluctuation direction of the average temperature. By combining the adjustment strategies of the main spray equipment and the auxiliary spray equipment in each of the monitoring areas, an updated sterilization scheme is obtained, and the main spray equipment and the auxiliary spray equipment in each of the monitoring areas execute the updated sterilization scheme.

[0020] By adopting the above technical solution, the spray parameters are dynamically adjusted based on the average temperature and fluctuation value of the zones. If the temperature meets the target, the parameters are maintained. If the temperature is too high or too low, the spraying time or intensity is adjusted accordingly. If the fluctuation is too large, the spraying angle and intensity are optimized. The system adapts to the temperature changes in the sterilization chamber in real time, ensuring that the temperature of each area is stable and close to the target value, improving the uniformity and reliability of sterilization, and avoiding over- or incomplete sterilization.

[0021] Secondly, this application provides a water bath sterilization temperature control device for infusion bags, which adopts the following technical solution: The image information acquisition module is used to acquire image information based on the industrial camera; The infusion bag data analysis module is used to analyze the infusion bag data on each layer of the tray based on the image information. The 3D virtual model generation module is used to generate a 3D virtual model based on the data of the infusion bags on each layer of the tray. The preliminary sterilization scheme generation module is used to determine the density of infusion bags in each monitoring area based on the three-dimensional virtual model, determine the preliminary sterilization scheme based on the density of infusion bags in each monitoring area, and enable the main spray equipment and the auxiliary spray equipment in the monitoring area to execute the preliminary sterilization scheme. A real-time temperature data acquisition module is used to acquire real-time temperature data based on the temperature sensor. The sterilization scheme update module is used to adjust the preliminary sterilization scheme according to the real-time temperature data after the preset time of the preliminary sterilization scheme is executed, so that the main spray equipment and the auxiliary spray equipment in each of the monitoring areas execute the updated sterilization scheme until sterilization is completed.

[0022] By adopting the above technical solutions, through zoned monitoring, image recognition modeling, and dynamic spray adjustment, the distribution of infusion bags is accurately identified and a three-dimensional model is constructed. A preliminary sterilization plan is formulated based on density differences, and the main and auxiliary sprays work together to adapt to the needs of different areas. Parameters are dynamically optimized based on real-time temperature data to avoid incomplete or over-sterilization caused by uneven density, significantly improving the uniformity and control accuracy of sterilization temperature, ensuring the sterilization quality and drug efficacy stability of infusion bags, reducing manual intervention costs, adapting to various placement methods and specifications of infusion bags, significantly improving sterilization efficiency and equipment versatility, and providing reliable protection for medical infusion safety.

[0023] Thirdly, this application provides an electronic device that adopts the following technical solution: An electronic device, comprising: At least one processor; Memory; At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program being configured to: perform the method as described in any one of the first aspects.

[0024] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and execute the method as described in any one of the first aspects.

[0025] In summary, this application includes at least one of the following beneficial technical effects: 1. By using zoned monitoring, image recognition modeling, and dynamic spray adjustment, the distribution of infusion bags is accurately identified and a three-dimensional model is constructed. A preliminary sterilization plan is formulated based on density differences, and the main and auxiliary sprays work together to adapt to the needs of different areas. 2. By dynamically optimizing parameters based on real-time temperature data, it avoids incomplete or over-sterilization caused by uneven density, significantly improves the uniformity and control accuracy of sterilization temperature, reduces the cost of manual intervention, adapts to various placement methods and specifications of infusion bags, and significantly improves sterilization efficiency and equipment versatility. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the division of monitoring areas in an embodiment of this application.

[0027] Figure 2 This is a schematic flowchart of the water bath sterilization temperature control method for infusion bags in the embodiments of this application.

[0028] Figure 3 This is a schematic diagram of the camera capturing the upper surface of the tray in an embodiment of this application.

[0029] Figure 4 This is a schematic diagram of an image stitched together from images of the same tray captured in an embodiment of this application.

[0030] Figure 5 This is a structural block diagram of the water bath sterilization temperature control device for infusion bags in the embodiments of this application.

[0031] Figure 6 This is a structural block diagram of the electronic device in the embodiments of this application. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0034] This application discloses a pressure water bath sterilizer, which includes a water bath sterilization chamber. The three-dimensional space of the water bath sterilization chamber is divided into multiple non-overlapping monitoring zones along a vertical plane. For example, for a chamber 2m long, 2m wide, and 1.5m high, it can be divided into sections every 1m along both the length and width directions, forming a total of 2×2=4 vertical monitoring zones, ensuring that the density and temperature of the infusion bags in each zone can be independently monitored and controlled. Figure 1 The monitoring areas are divided into monitoring zones A through D according to the above method.

[0035] At least one high-precision temperature sensor is installed in the side wall of the water bath sterilization chamber near each monitoring zone to collect the water bath temperature data of the corresponding monitoring zone in real time. The temperature sensor is connected to the electronic equipment via wired communication.

[0036] A retractable support rack is installed inside the water bath sterilization chamber, with the rack designed in layers along the height direction. For example, each layer is spaced 0.2m apart, with a total of 5 layers, and one tray is placed on each layer. The tray has a hollow structure to facilitate water bath circulation and heat transfer. Multiple infusion bags can be laid flat on each layer of the tray, such as 80 infusion bags arranged in a 10×8 pattern.

[0037] The spray system sprays hot water onto the support frame, and a water recovery device is located at the bottom of the water bath sterilization chamber. A main spray system is installed on the inner wall of the top surface of the water bath sterilization chamber, with multiple spray heads evenly distributed along the length of the chamber, achieving full coverage of all areas within the chamber. A secondary spray system is installed on the side wall of the water bath sterilization chamber adjacent to each monitoring area. Each secondary spray system contains 2-3 spray heads with adjustable spray angles, providing precise water spraying only to the corresponding monitoring area. Both the main and secondary spray systems are equipped with flow control valves and pressure control valves, allowing electronic control of the spraying time and intensity.

[0038] At least one industrial camera is installed on the side wall of the water bath sterilization chamber on at least one side of each tray to capture images of the tray surface. If the tray width is small (≤0.5m), one camera is installed on one side, with a resolution of ≥5 megapixels, and the shooting angle covers the entire upper surface of the tray. If the tray width is large (>0.5m), multiple cameras are installed on two or more sides, one on each of the two sides, or one on each of the three sides, to ensure that all infusion bags on the tray can be completely captured without blind spots. Figure 2 The shooting range of camera m is range m, the shooting range of camera n is range n, and range m and range n cover the tray.

[0039] Industrial cameras connect to electronic devices via the internet.

[0040] To facilitate the use of industrial cameras, lighting is installed inside the water bath sterilization chamber. The lighting is turned on after the support is in place inside the water bath sterilization chamber and turned off after the sterilization process begins.

[0041] This application discloses a method for controlling the temperature during water bath sterilization of infusion bags. (Refer to...) Figure 3 This is performed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, desktop computer, etc., but is not limited to these. (Steps S101 to S106) Step S101: Acquire image information based on an industrial camera.

[0042] Specifically, the electronic device communicates with each industrial camera. The electronic device sends shooting instructions to the industrial cameras at a preset shooting frequency (e.g., once per minute). The industrial cameras respond to the instructions, capture images of the corresponding tray surface, and transmit the captured image information to the electronic device in real time.

[0043] After receiving image information, the electronic device performs preliminary verification on the image, such as checking the image clarity and integrity. If the image is blurry or obstructed, the camera is triggered to retake the picture. After the verification is passed, the image is stored in the local cache for subsequent analysis.

[0044] Step S102: Analyze the image information to obtain the data of the infusion bags on each tray layer. This data includes the number of infusion bags and the position coordinates of each bag. The analysis is performed in two cases based on the number of industrial cameras installed: If an industrial camera for capturing images of the surface of each tray is installed on the side wall of the water bath sterilization chamber corresponding to one side of the tray, then step S1021 is executed: input the image information into the trained neural network infusion bag recognition model to obtain the infusion bag data on each layer of the tray.

[0045] Specifically, if the tray width is small and a single-sided camera can completely cover the upper surface of the tray, the verified image information is directly input into the trained neural network infusion bag recognition model.

[0046] The neural network-based infusion bag recognition model is a target detection model based on CNN. During training, images of different types of infusion bags placed on a tray are collected, covering different arrangement methods and different occlusion situations. The images are then labeled, such as the bounding boxes of the infusion bags. The labeled images are divided into training and test sets in an 8:2 ratio and input into the CNN network for training. The network parameters are optimized until the model's recognition accuracy reaches a preset value, thus obtaining a trained model.

[0047] After the image is input into the model, the model extracts image features through operations such as convolution and pooling, identifies the bounding box and position of each infusion bag in the image, counts the number of infusion bags, and calculates the center coordinates of each infusion bag, so that the electronic device obtains the data of the infusion bags on the tray.

[0048] On the other hand, if the tray is wide enough that a single industrial camera cannot cover the upper surface of the tray, that is, if one or more industrial cameras for capturing the upper surface of each tray are installed on the side wall of the water bath sterilization chamber above one side of the tray, then steps S1022 to S1026 are executed: Step S1022: Determine the viewpoint type corresponding to the image information.

[0049] Specifically, the electronic device stores parameters such as the installation location and shooting angle of each camera. Based on the mapping relationship between the camera number and the installation location, it determines the viewpoint type corresponding to each image, such as left-side view, right-side view, front-side view, etc.

[0050] Step S1023: Segment the image information according to the template of the corresponding viewpoint type, retain the first image after segmentation, and the edge parts of the first image with opposite or adjacent viewpoints overlap.

[0051] Specifically, for each viewpoint type, the electronic device stores a corresponding image segmentation template. Each image is cropped according to the segmentation template corresponding to its viewpoint type, removing invalid areas outside the tray in the image, and retaining only the image containing the upper surface of the tray, i.e., the first image. Among them, the first images captured by cameras with opposite or adjacent viewpoints must maintain a preset overlap rate (such as 10%-20%) at their edges to ensure that no areas are missed during subsequent stitching.

[0052] For example, the right edge of the first image captured by the left camera overlaps with the left edge of the first image captured by the right camera by 15%, covering the middle area of ​​the tray, thus avoiding the middle area being missed due to differences in perspective.

[0053] Step S1024: Perform perspective transformation on the first image to obtain the second image.

[0054] Specifically, such as Figure 2 Because the industrial camera shoots at an angle to the top surface of the tray, the first image obtained has perspective distortion, such as the tray and infusion bag appearing as trapezoids instead of rectangles, which requires perspective transformation correction.

[0055] In the first image, the four corner points of the tray are selected as feature points for perspective transformation. Based on the preset actual size of the tray, a mapping relationship between the pixel coordinate system and the actual physical coordinate system is established. The first image is corrected by the perspective transformation matrix to obtain a second image that is consistent with the actual plane ratio of the tray and has no distortion. In the second image, the infusion bag presents its true shape and positional relationship.

[0056] Step S1025: The second image is stitched together according to the preset position, and the overlapping area of ​​the second image is processed to obtain a third image without overlapping infusion bags.

[0057] Specifically, all second images corresponding to the same tray are stitched together according to preset positions, based on the stitching order determined by the camera's installation position, such as the left image being on the left and the right image on the right. Figure 3 The image on the left was taken by camera m, and the image on the right was taken by camera n. Due to errors caused by the camera shooting angle and errors in the perspective correction process, the infusion bags will inevitably overlap in the overlapping area after the second image of the tray is stitched together. Therefore, the second image of the overlapping area needs to be processed to avoid affecting the recognition accuracy of the model.

[0058] When processing the second image of the overlapping area to stitch together a third image that does not have overlapping infusion bags, steps Sa to Sf are included: Step Sa: Preprocess the overlapping region image, apply the Canny edge detection algorithm to identify the edges of the infusion bags in the overlapping region image, and apply morphological optimization operations to identify the overlapping region image with the edges of the infusion bags, thus obtaining the overlapping region image with the edges of the infusion bags.

[0059] Specifically, the electronic device performs grayscale and noise reduction processing on the overlapping area image, applies the Canny edge detection algorithm to identify the edges of the infusion bags in the overlapping area image, and performs morphological optimization operations on the overlapping area image after edge identification, first dilating and then eroding, with the structuring element being a 5×5 rectangle, to fill the edge gaps and obtain an overlapping area image with clear infusion bag edges.

[0060] Step Sb: Increase the transparency of the overlapping area image with the edge of the infusion bag to obtain the fourth image, and then overlap the two fourth images.

[0061] Step Sc: Sequentially determine the edge of each infusion bag as the target edge, and for each target edge, determine whether there are identical or partially identical infusion bag edges within a preset range.

[0062] Specifically, the electronic device sequentially identifies the edge of each infusion bag as the target edge. Based on the contour feature points of the target edge, such as the inflection points and endpoints of the edge, 10-20 feature points are extracted for each edge. A search area with a preset range is defined, such as a circular area with a radius of 5 pixels centered on the feature points. The edges of other infusion bags within the search area are identified as edges to be matched.

[0063] Calculate the shape similarity and partial overlap rate between the edge to be matched and the target edge: The shape similarity is obtained by calculating the cosine similarity of the contour feature vectors of the two edges, with a value range of [0,1]. The closer to 1, the more similar the shapes are.

[0064] Partial overlap rate: The ratio of the number of pixels in the intersection of two edges to the total number of pixels on the smaller edge. For example, if edge A is half of the bag and edge B is the complete bag, and the number of pixels in the intersection / the total number of pixels on edge A is greater than or equal to the second threshold, then it is considered a partial match.

[0065] Preset first threshold (e.g., 0.95) and second threshold (e.g., 0.8): If there is an edge to be matched with a shape similarity ≥ the first threshold and a partial overlap rate ≥ the second threshold, then it is determined to be two completely identical infusion bag edges.

[0066] Step Sd: If there are two identical infusion bag edges, erase the infusion bag image corresponding to the edge of either of the fourth images.

[0067] Specifically, the electronic device obtains a precise edge mask of the infusion bag through edge detection, and then uses OpenCV's inpaint function to automatically synthesize pixels based on the surrounding background texture to replace the bag area, thereby achieving erasure.

[0068] Step Se: If there are two identical infusion bag edges, erase the incomplete infusion bag edges in the fourth image.

[0069] Specifically, a third threshold (0.8) is preset. If there is an edge to be matched with a shape similarity greater than or equal to the third threshold and less than the first threshold, and a partial overlap rate greater than or equal to the second threshold, then it is determined to be two infusion bag edges with the same part, and the infusion bag image containing incomplete parts in the fourth image is erased.

[0070] Step Sf: Overlay the two processed fourth images and restore their original transparency, then stitch them together with the non-overlapping areas of the second image in their original positions to obtain a third image with no overlapping infusion bags.

[0071] Step S1026: Input the third image into the trained neural network infusion bag recognition model to obtain the infusion bag data on each layer of the tray.

[0072] Step S103: Generate a three-dimensional virtual model based on the data of the infusion bags on each tray. This includes steps S1031 to S1034.

[0073] Step S1031: Create a virtual support frame and a virtual pallet.

[0074] Specifically, the electronic device creates a virtual support frame in 3D modeling software based on parameters such as the size, number of layers, and layer spacing of the actual support frame; and creates a virtual pallet at the corresponding layer of the virtual support frame according to parameters such as the size and hollow structure of the actual pallet, ensuring that the structure and size of the virtual support frame and the virtual pallet are consistent with the actual ones.

[0075] Step S1032: Obtain the third image after recognition by the neural network infusion bag recognition model, establish a coordinate system based on the third image, and determine the first coordinate of each infusion bag.

[0076] Specifically, the electronic device acquires a third image after it has been identified by the neural network infusion bag recognition model. A pixel coordinate system is established in the third image. For example, the upper left corner of the image is the origin, the horizontal direction to the right is the x-axis, and the vertical direction downward is the y-axis. Then, based on the bounding box of each infusion bag identified by the model, the center pixel coordinates of each infusion bag are calculated. These coordinates are the first coordinates of the infusion bag in the third image.

[0077] Step S1033: Standardize and unify the coordinates of the third image coordinate system with the coordinates of the virtual tray, and transform according to the first coordinate to obtain the second coordinate of the infusion bag on the virtual tray.

[0078] Specifically, measure the physical dimensions of the actual pallet, such as length L=1m and width W=0.8m, and the pixel dimensions of the third image, such as length... =1000 pixels, width =800 pixels, establish the conversion relationship between pixel coordinates and physical coordinates: physical coordinate x=( / )×L, physical coordinates y=( / )×W.

[0079] The electronic device determines the first coordinate of each infusion bag based on the conversion relationship. , The infusion bag is converted into its physical coordinates (x, y) on the virtual tray, which is the second coordinate; at the same time, the z-axis coordinate of the infusion bag in the virtual space is determined according to the actual height of the infusion bag.

[0080] Step S1034: Generate a virtual infusion bag on the second coordinate and generate a three-dimensional virtual model.

[0081] Specifically, the electronic device generates a virtual infusion bag at the second coordinate (x,y,z) position of the virtual tray, which is consistent with the size and shape of the actual infusion bag; the generation of virtual infusion bags on all levels of trays is completed in sequence, and finally a three-dimensional virtual model containing virtual support, virtual tray and virtual infusion bag is obtained. This model is completely consistent with the placement of infusion bags in the actual water bath sterilization chamber.

[0082] Step S104: Determine the density of infusion bags in each monitoring area based on the three-dimensional virtual model, and determine the preliminary sterilization plan based on the density of infusion bags in each monitoring area, so that the main spray equipment and the auxiliary spray equipment in the monitoring area can perform the preliminary sterilization plan. Steps S1041 to S1045.

[0083] Step S1041: Determine the overall infusion bag density based on the infusion bag density of each monitoring area.

[0084] Specifically, the electronic device, based on a three-dimensional virtual model, divides the monitoring areas of the virtual water bath sterilization chamber to match the actual area, counts the number of virtual infusion bags corresponding to each monitoring area, and calculates the infusion bag density of each monitoring area based on the actual volume of the monitoring area. =Number of IV bags in the monitoring area / Volume of the monitoring area; Calculate the overall IV bag density based on the IV bag density of all monitoring areas. =Total number of infusion bags in all monitoring areas / Total volume of water bath sterilization chamber.

[0085] Step S1042: Based on the comparison between the overall infusion bag density and the preset table, determine the first water spraying time and the first water spraying intensity of the main spraying equipment corresponding to the overall infusion bag density level.

[0086] The electronic device pre-stores a preset table that records the main spray equipment's water spraying parameters corresponding to different overall infusion bag density levels, for example: The overall infusion bag density grade, overall infusion bag density range (bags / m²), and first water spray intensity (MPa) are as follows: Low density - <50-0.3 Medium to low density -50≤ <80-0.4 Medium density -80≤ <120-0.5 Medium to high density -120≤ <150-0.6 High density - ≥150-0.7 The values ​​shown are for illustrative purposes only; the actual values ​​should be set according to the specific needs of the situation.

[0087] The electronic device will calculate the overall density of the infusion bag. By comparing the density range with the preset table, the corresponding density level is determined, and then the first water spraying time t1 and the first water spraying intensity p1 corresponding to the level are obtained, which are the preliminary water spraying parameters of the main sprinkler equipment.

[0088] Step S1043: Determine the sterilization coefficient for each monitoring area based on the first water spraying time and the first water spraying intensity.

[0089] Specifically, the sterilization coefficient K is used to evaluate the sterilization capability of the main spray equipment for the monitored area, and it is calculated as follows: ,in: p1 is the first water spray intensity (MPa), t1 is the first water spray time (min), and their product reflects the total sterilization input of the main spray equipment; To measure the density of infusion bags in the monitoring area (bags / m²), α× This reflects the degree to which density hinders sterilization; the higher the density, the larger this value. β is a correction factor (β=0.1), to avoid When the expression equals 0, the denominator of the formula is 0, ensuring the validity of the calculation; Assume p1 = 0.5 MPa, t1 = 25 min, α = 0.01 m² / unit, β = 0.1: Low-density monitoring area ( =50 pieces / m²): K=(0.5×25)×(1 / (0.01×50+0.1))=12.5×(1 / 0.6)≈20.83; High-density monitoring area ( =100 pieces / m²): K=(0.5×25)×(1 / (0.01×100+0.1))=12.5×(1 / 1.1)≈11.36; It is evident that the lower the density, the greater the sterilization coefficient K.

[0090] The electronic equipment has a preset sterilization coefficient threshold K0 for each monitoring area: If K≥K0: This means that the water spraying parameters of the main spray equipment can meet the sterilization requirements of the monitoring area, and the auxiliary spray equipment is not turned on. If K < K0, it means that the water spray parameters of the main spray equipment are insufficient to cover the sterilization requirements of the monitoring area, and the auxiliary spray equipment needs to be started to supplement it.

[0091] Step S1044: If the sterilization coefficient of the monitoring area does not reach the threshold, calculate the difference between the sterilization coefficient and the threshold.

[0092] Step S1045: Determine the start time of the auxiliary spraying equipment, the second spraying time, and the second spraying intensity based on the difference and the density of the infusion bag.

[0093] Specifically, the electronic device calculates the difference ∆K between K and K0. The larger ∆K is, the better. The higher the value, the longer the second watering time t2.

[0094]

[0095] in, The average concentration of infusion bags in all monitoring areas. This reflects the percentage of the main sprinkler capacity shortfall and has a value of [0,1]. It reflects the multiple of the density of the monitoring area relative to the average level.

[0096] For example, k0=20, t1=25min, =60 units / m², high-density monitoring area ∆K=8.64, =100 pieces / m², then t2 = 25 × (8.64 / 20) × (100 / 60) = 18 (min).

[0097] Furthermore, the larger ∆K is, The higher the value, the higher the second water spray intensity p2.

[0098]

[0099] in, The strength of p2's replenishment is determined by considering both the k-value gap and density.

[0100] For example, k0=20, p1=0.5MPa, =60 units / m², high-density monitoring area ∆K=8.64, =100 pieces / m², then p2=0.5×(8.64×100) / (20×60)=0.36(Mpa).

[0101] Furthermore, the electronic equipment is set to start at the same time as the main spraying equipment, and commands are sent to the secondary spraying equipment to start synchronously with the main spraying equipment, with a second spraying time of 18 minutes and a second spraying intensity of 0.36 MPa.

[0102] Step S105: Acquire real-time temperature data based on the temperature sensor.

[0103] Specifically, the electronic device receives real-time temperature data collected by temperature sensors in each monitoring area and records the temperature values ​​of each monitoring area at different time points, forming temperature time-series data. The electronic device performs anomaly detection on the received temperature data. For example, it sets a preset temperature range. If the detected temperature exceeds the preset temperature range, it is determined to be abnormal data, the sensor performs a self-check or re-collects data, and then generates an alarm message.

[0104] Step S106: After the preset time of the preliminary sterilization plan is executed, the preliminary sterilization plan is adjusted according to the real-time temperature data so that the main spray equipment and the auxiliary spray equipment in the monitoring area execute the updated sterilization plan.

[0105] Specifically, the electronic device presets a target sterilization temperature and a temperature fluctuation threshold. After the preliminary sterilization process has been completed for a preset time, the following steps are executed (steps S11 to S13): Step S11: Calculate the average temperature and temperature fluctuation value of each monitoring area within a preset time, and then calculate the overall average temperature.

[0106] Step S12: For the temperature data of each monitoring area, adjust the preliminary sterilization plan according to the following rules: If the average temperature equals the preset target temperature and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then the main spray parameters and the auxiliary spray parameters remain unchanged.

[0107] If the average temperature is less than the preset target temperature, and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then increase the water spraying time or water spraying intensity, including: Main spray equipment: If the overall average temperature is less than the preset target temperature, the first spraying time will be extended by a first preset ratio, or the first spraying intensity will be increased by a second preset ratio. Secondary spray equipment: The second spraying time is extended by a third preset ratio, or the second spraying intensity is increased by a fourth preset ratio.

[0108] Specifically, the temperature in the monitoring area is low at this time, so it is necessary to increase the water spraying time or intensity. The overall average temperature is the average value of the average temperature of all monitoring areas, and the first, second, third, and fourth preset ratios can be set according to actual needs.

[0109] If the average temperature is greater than the preset target temperature and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then reduce the water spraying time or water spraying intensity. Main spray equipment: If the overall average temperature is greater than the preset target temperature, shorten the first spraying time by a first preset ratio, or reduce the first spraying intensity by a second preset ratio. Secondary spray equipment: shorten the second spraying time by a third preset ratio, or reduce the second spraying intensity by a fourth preset ratio.

[0110] Specifically, the temperature in the monitoring area is relatively high at this time, so the water spraying time or intensity can be reduced.

[0111] If the temperature fluctuation value exceeds the temperature fluctuation threshold, adjust the spray angle of the auxiliary spray equipment and fine-tune the second water spray intensity of the monitoring area according to the direction of the average temperature fluctuation.

[0112] Specifically, if the temperature fluctuation in the monitoring area is too large, the rotation angle of the secondary spray head is controlled by electronic equipment to make the water spray more even. If the temperature fluctuation is too high, the intensity of the second water spray is reduced; if the temperature fluctuation is too low, the intensity of the second water spray is increased. The unit of adjustment is the fifth preset value.

[0113] Step S13: Integrate the adjustment strategies of the main spray equipment and the auxiliary spray equipment in each monitoring area to obtain an updated sterilization plan, and make the main spray equipment and the auxiliary spray equipment in each monitoring area execute the updated sterilization plan.

[0114] The electronic device sends the updated sterilization plan to the main spray equipment and the auxiliary spray equipment. The equipment responds to the instruction and executes the sterilization plan according to the new parameters. During the subsequent sterilization process, the electronic device repeats steps S11 and S12 at preset time intervals and continuously adjusts the sterilization plan according to real-time temperature data until the sterilization process is completed, such as when the total sterilization time reaches the maximum sterilization time, such as 30 minutes.

[0115] To better implement the above method, this application also provides a water bath sterilization temperature control device for infusion bags, referring to... Figure 5 The infusion bag water bath sterilization temperature control device 200 includes: Image information acquisition module 201 is used to acquire image information based on an industrial camera; The infusion bag data analysis module 202 is used to analyze and obtain the infusion bag data on each layer of the tray based on the image information. The 3D virtual model generation module 203 is used to generate a 3D virtual model based on the data of the infusion bags on each layer of the tray. The preliminary sterilization scheme generation module 204 is used to determine the density of infusion bags in each monitoring area based on the three-dimensional virtual model, and to determine the preliminary sterilization scheme based on the density of infusion bags in each monitoring area, so that the main spray equipment and the auxiliary spray equipment in the monitoring area can execute the preliminary sterilization scheme. Real-time temperature data acquisition module 205 is used to acquire real-time temperature data based on a temperature sensor; The sterilization scheme update module 206 is used to adjust the preliminary sterilization scheme according to real-time temperature data after the preset time of the preliminary sterilization scheme is executed, so that the main spray equipment and the auxiliary spray equipment in each monitoring area execute the updated sterilization scheme until sterilization is completed.

[0116] Furthermore, the infusion bag data analysis module 202 is specifically used for: If an industrial camera is installed on the side wall of the water bath sterilization chamber corresponding to one side of the tray to capture the surface of each tray, the image information is input into the trained neural network infusion bag recognition model to obtain the infusion bag data on each layer of the tray. If one or more industrial cameras are installed on the side wall of the water bath sterilization chamber above one side of the tray to capture images of the surface of each tray, then: Determine the viewpoint type corresponding to the image information; The image information is segmented according to the template of the corresponding viewpoint type, and the first image after segmentation is retained. The edges of the first images with opposite or adjacent viewpoints overlap. The first image is transformed by perspective to obtain the second image; The second images are stitched together according to preset positions, and the overlapping areas of the second images are processed to obtain a third image in which there are no overlapping infusion bags. The third image is input into the trained neural network infusion bag recognition model to obtain the infusion bag data on each layer of the tray.

[0117] Further, the second image of the overlapping area is processed and stitched together to obtain a third image in which the infusion bags do not overlap, including: The overlapping region image is preprocessed, and the Canny edge detection algorithm is applied to identify the edges of the infusion bags in the overlapping region image. Morphological optimization operation is applied to identify the overlapping region image with the edges of the infusion bags, resulting in an overlapping region image with the edges of the infusion bags. Increase the transparency of the overlapping area image with the edge of the infusion bag to obtain the fourth image, and then overlap the two fourth images. Each infusion bag edge is sequentially identified as a target edge. For each target edge, it is determined whether there are identical or partially identical infusion bag edges within a preset range. If two identical infusion bag edges exist, the infusion bag image corresponding to the edge of either of the four images will be erased. If two infusion bag edges are identical, the infusion bag image corresponding to the incomplete infusion bag edge in the fourth image will be erased. The two processed fourth images are overlapped and their original transparency is restored. They are then stitched together with the non-overlapping areas of the second image in their original positions to form a third image in which there are no overlapping infusion bags.

[0118] Furthermore, for each target edge, it is determined whether there are identical or partially identical infusion bag edges within a preset range, including: For each edge of an infusion bag within the overlapping area, a search area of ​​a preset range is defined based on its contour feature points, and the edges of other infusion bags within the search area are determined as edges to be matched. Calculate the shape similarity and partial overlap rate between each edge to be matched and the target edge; If there exists an edge to be matched whose shape similarity is less than or equal to the first threshold and whose partial overlap rate is greater than or equal to the second threshold, then the edge to be matched is determined to be the same as or partially the same as the target edge.

[0119] The 3D virtual model generation module 203 is specifically used for: Establish virtual support racks and virtual pallets; The third image after recognition by the neural network infusion bag recognition model is obtained, and a coordinate system is established based on the third image to determine the first coordinate of each infusion bag; The coordinates of the third image system and the coordinates of the virtual tray are standardized and unified. The first coordinates are transformed to obtain the second coordinates of the infusion bag on the virtual tray. A virtual infusion bag is generated on the second coordinate system, thus creating a three-dimensional virtual model.

[0120] Furthermore, the preliminary sterilization protocol generation module 204 is specifically used for: The overall infusion bag density is determined based on the infusion bag density in each monitoring area; Based on the comparison between the overall infusion bag density and the preset table, determine the first water spraying time and the first water spraying intensity of the main sprinkler equipment corresponding to the overall infusion bag density level; The sterilization coefficient for each monitoring area is determined based on the first water spraying time and the first water spraying intensity. If the sterilization coefficient of the monitored area does not reach the threshold, the difference between the sterilization coefficient and the threshold is calculated. The start-up time, second water spraying time, and second water spraying intensity of the auxiliary spraying equipment are determined based on the difference and the density of the infusion bags.

[0121] Furthermore, the sterilization protocol update module 206 is specifically used for: Calculate the average temperature and temperature fluctuation value of each monitoring area within a preset time period, and then calculate the overall average temperature; For the temperature data of each monitoring area, adjust the preliminary sterilization protocol according to the following rules: If the average temperature equals the preset target temperature, and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then the main spray parameters and the auxiliary spray parameters remain unchanged. If the average temperature is less than the preset target temperature, and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then increase the water spraying time or water spraying intensity, including: Main spray equipment: If the overall average temperature is less than the preset target temperature, the first spraying time will be extended by a first preset ratio, or the first spraying intensity will be increased by a second preset ratio. Secondary sprinkler equipment: The second water spraying time is extended by a third preset ratio, or the second water spraying intensity is increased by a fourth preset ratio; If the average temperature is greater than the preset target temperature and the temperature fluctuation value is less than or equal to the temperature fluctuation threshold, then reduce the water spraying time or water spraying intensity. Main spray equipment: If the overall average temperature is greater than the preset target temperature, shorten the first spraying time by a first preset ratio, or reduce the first spraying intensity by a second preset ratio. Secondary sprinkler equipment: shorten the second water spraying time by a third preset ratio, or reduce the second water spraying intensity by a fourth preset ratio; If the temperature fluctuation value is greater than the temperature fluctuation threshold, adjust the spray angle of the auxiliary spray equipment and fine-tune the second spray intensity according to the direction of the average temperature fluctuation. By integrating the adjustment strategies of the main spray equipment and the auxiliary spray equipment in each monitoring area, an updated sterilization scheme is obtained, enabling the main spray equipment and the auxiliary spray equipment in each monitoring area to execute the updated sterilization scheme.

[0122] The various variations and specific examples of the methods in the foregoing embodiments are also applicable to the infusion bag water bath sterilization temperature control device of this embodiment. Through the foregoing detailed description of the infusion bag water bath sterilization temperature control method, those skilled in the art can clearly understand the implementation method of the infusion bag water bath sterilization temperature control device of this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0123] To better implement the above methods, embodiments of this application provide an electronic device, referring to... Figure 6The electronic device 300 includes a processor 301, a memory 303, and a display screen 305. The memory 303 and the display screen 305 are both connected to the processor 301, such as via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0124] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0125] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 may be divided into address bus, data bus, control bus, etc.

[0126] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0127] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0128] Figure 6 The electronic device 300 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0129] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, the program implements the water bath sterilization temperature control method for infusion bags provided in the above embodiments. Through zoned monitoring, image recognition modeling, and dynamic spray adjustment, it accurately identifies the distribution of infusion bags and constructs a three-dimensional model. It formulates a preliminary sterilization plan based on density differences, and the main and auxiliary sprays work together to adapt to the needs of different areas. Relying on real-time temperature data, it dynamically optimizes parameters to avoid incomplete or over-sterilization caused by uneven density, significantly improves the uniformity and control accuracy of sterilization temperature, ensures the sterilization quality and drug efficacy stability of infusion bags, reduces the cost of manual intervention, adapts to various placement methods and specifications of infusion bags, significantly improves sterilization efficiency and equipment versatility, and provides reliable protection for medical infusion safety.

[0130] In this embodiment, the computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0131] The computer program in this embodiment includes program code for performing all the aforementioned methods. The program code may include instructions corresponding to the method steps provided in the above embodiments. The computer program can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The computer program can be executed entirely on the user's computer as a standalone software package.

[0132] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

[0133] Additionally, it should be understood that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

Claims

1. A method for temperature control of water bath sterilization of an infusion bag, characterized by, The application is applied to a pressure water bath sterilizer, the three-dimensional space of the water bath sterilization cavity of the pressure water bath sterilizer is divided into multiple monitoring areas, a corresponding temperature sensor is arranged in each monitoring area, a main spraying device is further arranged on the inner top of the water bath sterilization cavity, a group of auxiliary spraying devices is correspondingly arranged in each monitoring area, a supporting frame is arranged in the water bath sterilization cavity, multiple layers of trays are placed on the supporting frame, multiple infusion bags are laid on each tray, at least one industrial camera for shooting the upper surface of each tray is arranged on the side wall of the water bath sterilization cavity corresponding to at least one side of each tray, and the method is executed by an electronic device and includes the following steps: obtaining image information based on the industrial camera; obtaining infusion bag data on each tray according to each image information; generating a three-dimensional virtual model according to the infusion bag data on each tray; determining the infusion bag density of each monitoring area according to the three-dimensional virtual model, determining a preliminary sterilization scheme according to the infusion bag density of each monitoring area, and making the main spraying device and the auxiliary spraying device of each monitoring area execute the preliminary sterilization scheme; obtaining real-time temperature data based on the temperature sensor; adjusting the preliminary sterilization scheme according to the real-time temperature data after a preset time of executing the preliminary sterilization scheme, making the main spraying device and the auxiliary spraying device of each monitoring area execute an updated sterilization scheme until sterilization is completed.

2. The method of claim 1, wherein, The method of obtaining infusion bag data on each tray according to each image information includes the following steps: if one industrial camera for shooting the upper surface of each tray is arranged on the side wall of the water bath sterilization cavity corresponding to one side of each tray, the image information is input into a trained neural network infusion bag recognition model to obtain the infusion bag data on each tray; if more than one industrial camera for shooting the upper surface of each tray is arranged on the side wall of the water bath sterilization cavity corresponding to more than one side of each tray, the following steps are performed: determining the perspective type corresponding to the image information; segmenting the image information according to the template of the corresponding perspective type, retaining the first image after segmentation, and overlapping the edge parts of the first images with relative or adjacent perspectives; performing perspective transformation on the first image to obtain a second image; splicing the second images according to the preset position, processing the second images in the overlapping area, and splicing to obtain a third image without overlapping infusion bags; inputting the third image into the trained neural network infusion bag recognition model to obtain the infusion bag data on each tray.

3. The method of claim 2, wherein, The method of processing the second images in the overlapping area and splicing to obtain a third image without overlapping infusion bags includes the following steps: preprocessing the overlapping area image, identifying the infusion bag edge in the overlapping area image by applying the Canny edge detection algorithm, and obtaining the overlapping area image with the infusion bag edge by applying the morphological optimization operation to the overlapping area image with the identified infusion bag edge; increasing the transparency of the overlapping area image with the infusion bag edge to obtain a fourth image, and overlapping two fourth images. sequentially determine each infusion bag edge as a target edge, for each target edge, judge whether there is an identical or partially identical infusion bag edge within a preset range thereof; if there are two completely identical infusion bag edges, erase the infusion bag image corresponding to the infusion bag edge in any one of the fourth images; if there are two partially identical infusion bag edges, erase the infusion bag image corresponding to the incomplete infusion bag edge in the fourth image; overlap the two fourth images after processing and restore the original transparency, and splice according to the original position with the non-overlapping area in the second image to obtain a third image without overlapping infusion bags.

4. The method of claim 3, wherein, The judgment of whether there is an identical or partially identical infusion bag edge within a preset range of each target edge includes: For each infusion bag edge in the overlapping area, the contour feature point is taken as the reference to demarcate the search area of the preset range, and other infusion bag edges in the search area are determined as matching edges; Calculate the shape similarity and partial overlap rate of each matching edge and the target edge; If the shape similarity of the matching edge is less than or equal to the first threshold value and the partial overlap rate is greater than or equal to the second threshold value, it is determined that the matching edge is identical or partially identical to the target edge.

5. The method of claim 2, wherein, The three-dimensional virtual model is generated according to the infusion bag data on each layer of the tray, including: establishing a virtual support frame and a virtual tray; obtaining the third image after the neural network infusion bag recognition model is recognized, establishing a coordinate system based on the third image, and determining the first coordinates of each infusion bag; standardize the third image coordinate system and the virtual tray coordinate system, convert the first coordinates to obtain the second coordinates of the infusion bag on the virtual tray; generate a virtual infusion bag on the second coordinates to generate a three-dimensional virtual model.

6. The method of claim 2, wherein, The monitoring area is divided based on the vertical plane of the water bath sterilization cavity, the auxiliary spraying device is located on the side wall of the water bath sterilization cavity close to the monitoring area, the sterilization scheme includes water spraying time and water spraying intensity, and the preliminary sterilization scheme is determined according to the infusion bag density of each monitoring area, so that the main spraying device and the auxiliary spraying device of the monitoring area execute the preliminary sterilization scheme, including: determine the overall infusion bag density according to the infusion bag density of each monitoring area; determine the first water spraying time and the first water spraying intensity of the main spraying device corresponding to the grade of the overall infusion bag density according to the comparison between the overall infusion bag density and a preset table; determine the sterilization coefficient of each monitoring area according to the first water spraying time and the first water spraying intensity, respectively; if the sterilization coefficient of the monitoring area does not reach a threshold value, calculate the difference between the sterilization coefficient and the threshold value; determine the opening time, the second water spraying time and the second water spraying intensity of the auxiliary spraying device based on the difference and the infusion bag density.

7. The method of claim 6, wherein, The preliminary sterilization scheme is adjusted according to the real-time temperature data, and the main spraying device and the auxiliary spraying device of the monitoring area execute the updated sterilization scheme, including: calculating an average temperature and a temperature fluctuation value of each monitoring area in a preset time, and then calculating an overall average temperature; adjusting the preliminary sterilization scheme according to the temperature data of each monitoring area according to the following rules: if the average temperature = preset target temperature, and the temperature fluctuation value ≤ temperature fluctuation threshold, the main spraying parameter and the auxiliary spraying parameter remain unchanged; if the average temperature < preset target temperature, and the temperature fluctuation value ≤ temperature fluctuation threshold, the water spraying time or the water spraying intensity is increased, including: the main spraying device: if the overall average temperature < preset target temperature, the first water spraying time is extended by a first preset proportion, or the first water spraying intensity is adjusted upward by a second preset proportion; the auxiliary spraying device: the second water spraying time is extended by a third preset proportion, or the second water spraying intensity is adjusted upward by a fourth preset proportion; if the average temperature > preset target temperature and the temperature fluctuation value ≤ temperature fluctuation threshold, the water spraying time or the water spraying intensity is reduced: the main spraying device: if the overall average temperature > preset target temperature, the first water spraying time is shortened by a first preset proportion, or the first water spraying intensity is adjusted downward by a second preset proportion; the auxiliary spraying device: the second water spraying time is shortened by a third preset proportion, or the second water spraying intensity is adjusted downward by a fourth preset proportion; if the temperature fluctuation value > temperature fluctuation threshold, the spraying angle of the auxiliary spraying device is adjusted, and the second water spraying intensity is fine-tuned according to the fluctuation direction of the average temperature; comprehensive adjustment strategies of the main spraying device and the auxiliary spraying device of each monitoring area are obtained to obtain an updated sterilization scheme, so that the main spraying device and the auxiliary spraying device of each monitoring area execute the updated sterilization scheme.

8. An infusion bag water bath sterilization temperature control device, characterized by, It includes: an image information acquisition module configured to acquire image information based on the industrial camera; an infusion bag data analysis module configured to analyze the image information to obtain infusion bag data on each tray; a three-dimensional virtual model generation module configured to generate a three-dimensional virtual model based on the infusion bag data on each tray; a preliminary sterilization scheme generation module configured to determine the infusion bag density of each monitoring area based on the three-dimensional virtual model, and determine a preliminary sterilization scheme based on the infusion bag density of each monitoring area, so that the main spraying device and the auxiliary spraying device of the monitoring area execute the preliminary sterilization scheme; a real-time temperature data acquisition module configured to acquire real-time temperature data based on the temperature sensor; a sterilization scheme updating module configured to adjust the preliminary sterilization scheme based on the real-time temperature data after a preset time of executing the preliminary sterilization scheme, so that the main spraying device and the auxiliary spraying device of each monitoring area execute an updated sterilization scheme until sterilization is completed.

9. An electronic device, comprising: It includes: at least one processor; a memory; at least one computer program, wherein the at least one computer program is stored in the memory and is configured to be executed by the at least one processor, and the at least one computer program is configured to execute the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored and can be loaded and executed by the processor to execute the method of any one of claims 1 to 7.

Images