Control method, device and equipment of medical cleaning machine and readable storage medium

Abstract

The application provides a control method and device of a medical cleaning machine, and relates to the technical field of medical cleaning machines.In the application, the AGV scheduling system receives a medical cleaning machine scheduling application instruction so as to activate the scheduling system, and collects first image information and second image information so as to improve the effectiveness of data and reduce data redundancy.Then, the first image information and the second image are subjected to image recognition, the regulation and control route between the current task node and the next task node is determined, and regulation and control are performed according to the regulation and control route.The method can realize intelligent cleaning, closed-loop control and full-automatic control of the central supply room.The application greatly saves the labor cost by using the intelligent AGV scheduling system, the work mode of the assembly line saves the cleaning time, the equipment operation condition can be monitored in all directions, the work is reasonably distributed, the equipment is prevented from being idle, the problem that time is consumed and waiting is required when a single-cabin medical cleaning machine is used is solved, and the cleaning and disinfection and drying effects can be effectively guaranteed.

Description

Technical Field

[0001] This invention relates to the field of medical cleaning and disinfection technology, specifically to a medical cleaning machine, and more particularly to a control method, device, equipment, and readable storage medium for a medical cleaning machine. Background Technology

[0002] Medical cleaning machines are used for cleaning medical devices. The specific cleaning steps include: initial washing, enzyme washing, rinsing, disinfection, and drying. During the cleaning and disinfection steps, water of different temperatures is used to repeatedly spray the medical devices within the cleaning chamber to achieve the desired cleaning and disinfection. Existing single-chamber cleaning machines perform initial washing, enzyme washing, rinsing, disinfection, and drying within the same chamber. Each subsequent step must wait until the previous one is completed, and the entire process is only finished after the last step is completed.

[0003] To improve cleaning efficiency, existing technologies have proposed a multi-compartment combined medical cleaning machine that can simultaneously perform pre-washing, enzyme washing, rinsing, disinfection, and drying processes in multiple compartments to save cleaning time. However, in terms of cleaning coordination between the various cleaning compartments, due to the different durations of each process, some cleaning compartments often complete their cleaning tasks early and remain idle. If the already cleaned medical devices are continued to be cleaned during the idle waiting period, it may result in over-cleaning, which wastes resources and may reduce the service life of the medical devices.

[0004] In view of this, it is necessary to optimize and improve the control methods and intelligence of existing medical cleaning machines in order to reduce or avoid the idle waiting time of each cleaning chamber during operation. Summary of the Invention

[0005] The purpose of this invention is to provide a control method, apparatus, equipment, and readable storage medium for a medical cleaning machine to improve the aforementioned problems. It allows for the simultaneous operation of different modes, enabling initial washing, enzyme washing, rinsing, disinfection, and drying to be performed concurrently in multiple compartments, completing the cleaning tasks of the production line. Furthermore, the entire process requires no manual operation, automatically handling AGV scheduling, automatic instrument loading, automatic identification of cleaning modes, automatic program execution, and automatic unloading. To achieve the above objectives, the technical solution adopted by this invention is as follows:

[0006] In a first aspect, this application provides a control method for a medical cleaning machine, comprising:

[0007] The system acquires a medical cleaning machine scheduling request instruction, a preset cleaning task execution route, and a scheduling scenario model. The medical cleaning machine scheduling request instruction is a request command issued when there are objects to be cleaned in the cleaning line. The preset cleaning task execution route is a task execution route composed of multiple different task nodes connected sequentially. The scheduling scenario model is a set of regions established based on the spatial relationships of various areas of the cleaning line in the actual scene. Each region in the set is spatial information constructed based on the spatial geometric data of each region.

[0008] In response to the medical cleaning machine scheduling request instruction, first image information and second image information are acquired; the first image information is an image of the receiving area of ​​the object to be cleaned in the cleaning line, and the second image information is real-time image information collected in each of the areas;

[0009] Based on the first image information, image recognition is performed to obtain object recognition results, and the object recognition results are matched with the preset cleaning task execution route to determine the cleaning task sequence.

[0010] Based on the second image information, image recognition is performed to obtain the idle and non-idle scene status results. Based on the idle scene status results and the cleaning task timing, the control route is determined and the task execution control is performed.

[0011] Secondly, this application also provides a control device for a medical cleaning machine, including a first acquisition module, a second acquisition module, an identification module, and a control module, wherein:

[0012] The first acquisition module is used to acquire medical cleaning machine scheduling request instructions, preset cleaning task execution routes, and scheduling scenario models. The medical cleaning machine scheduling request instruction is a request command issued when there are objects to be cleaned in the cleaning line. The preset cleaning task execution route is a task execution route formed by sequentially connecting multiple different task nodes. The scheduling scenario model is a set of regions established based on the spatial relationships of various areas of the cleaning line in the actual scene. Each region in the set is spatial information constructed based on the spatial geometric data of each region.

[0013] The second acquisition module is used to acquire first image information and second image information in response to the medical cleaning machine scheduling request instruction; the first image information is an image of the receiving area of ​​the object to be cleaned in the cleaning line, and the second image information is image information collected in real time in each area;

[0014] Recognition module: used to perform image recognition based on the first image information to obtain object recognition results, and to match the object recognition results with the preset cleaning task execution route to determine the cleaning task sequence;

[0015] Control module: used to perform image recognition based on the second image information to obtain idle and non-idle scene status results, and to determine the control route and perform task execution control based on the idle scene status results and the cleaning task timing.

[0016] Thirdly, this application also provides a control device for a medical cleaning machine, comprising:

[0017] Memory, used to store computer programs;

[0018] A processor is configured to implement the steps of the control method for the medical cleaning machine when executing the computer program;

[0019] One or more of multimedia components, I / O interfaces, and communication components, including a display and an audio component, wherein the display is used to monitor the operating status of the device, and the audio component is used to output and / or input audio signals.

[0020] Fourthly, this application also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the control method based on a medical cleaning machine described above.

[0021] The beneficial effects of this invention are as follows:

[0022] In this application, when an object to be cleaned is detected at the receiving station in the contaminated area, the AGV scheduling system receives a medical cleaning machine scheduling request instruction to activate the system, allowing it to hibernate during idle periods, thus saving power and reducing hardware wear and tear. Furthermore, the collection of first and second image information only begins after receiving the medical cleaning machine scheduling request instruction, improving data validity, reducing data redundancy, and filtering out invalid image information from storage. Then, image recognition is performed on the first image information to determine the object type of the object to be cleaned, and the corresponding preset cleaning task execution route is found, clearly defining the sequence of each task node, i.e., the cleaning task sequence, eliminating the need for manual consideration of which cleaning task should be executed first. Moreover, this avoids damage to the object to be cleaned for those unfamiliar with the cleaning process, improving the level of intelligence and convenience. Then, image recognition is performed based on the second image information to determine which task nodes are currently idle and which are not. Based on the sequence of cleaning tasks, the task space corresponding to the currently idle scene state is found. This allows for the determination of the control route from the current task node to the next task node, and the next task is executed according to this route until completion. This method not only realizes platform-based, intelligent, and closed-loop control of the supply room cleaning system, but also achieves fully automated control, freeing up manpower and saving costs. In this application, the use of an intelligent AGV scheduling system significantly reduces labor costs, and the assembly line operation mode saves cleaning time, eliminating the waiting time required when using single-compartment medical cleaning machines, effectively ensuring cleaning and drying effects.

[0023] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the control method for the medical cleaning machine described in an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of the control device structure of the medical cleaning machine described in an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of the control device structure of the medical cleaning machine described in an embodiment of the present invention.

[0028] In the diagram: 710 - First acquisition module; 711 - Triggering unit; 712 - Modeling unit; 713 - Classification unit; 714 - Setting unit; 720 - Second acquisition module; 730 - Identification module; 731 - Acquisition unit; 732 - First extraction unit; 733 - Second extraction unit; 734 - Pairing unit; 735 - Reconstruction unit; 736 - Matching unit; 740 - Control module; 800 - Tag receiving device; 801 - Processor; 802 - Memory; 803 - Multimedia component; 804 - I / O interface; 805 - Communication component. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0030] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0031] Example 1:

[0032] This embodiment provides a control method for a medical cleaning machine.

[0033] See Figure 1 The figure shows that the method includes steps S1, S2, S3 and S4.

[0034] Step S1: Obtain the medical cleaning machine scheduling request instruction, the preset cleaning task execution route, and the scheduling scenario model. The medical cleaning machine scheduling request instruction is a request command issued when there are objects to be cleaned in the cleaning line. The preset cleaning task execution route is a task execution route formed by sequentially connecting multiple different task nodes. The scheduling scenario model is a set of regions established based on the spatial relationship of each area of ​​the cleaning line in the actual scene. Each region in the set is spatial information constructed based on the spatiotemporal data of each region.

[0035] It is understandable that in this step, different objects are organized according to their unique cleaning rules and processes to form a preset cleaning task execution route. For example, in this embodiment, the preset cleaning task execution route is initial washing—enzyme washing—rinsing—ultrasonic cleaning—rinsing—disinfection—drying—cooling—end. In other embodiments, it may be other task processes, and there are no specific limitations. At the same time, spatial simulation is performed based on the spatiotemporal (temporal sequence and spatial geometric relationship) relationship corresponding to each cleaning task in the cleaning line set in the actual scenario to obtain a scheduling scenario model. When an object to be cleaned is detected at the receiving station in the contaminated area, the cleaning rack identification system sends a medical cleaning machine scheduling request instruction to the AGV scheduling system, giving a clear AGV scheduling system activation instruction so that it can be put into hibernation during idle periods, which not only saves power but also reduces hardware wear and tear. At the same time, the preset cleaning task execution route and scheduling scenario model stored in the memory are retrieved from the AGV scheduling system.

[0036] In detail, the triggering conditions for the medical cleaning machine scheduling request instruction include: the weight of the object to be cleaned is greater than a preset weight or the volume of the object to be cleaned is greater than a preset volume, wherein the preset weight is the minimum weight of the object to be cleaned when the cleaning task is activated; and the preset volume is the minimum volume of the object to be cleaned when the cleaning task is activated.

[0037] It is understandable that in this step, when the weight of the objects to be cleaned piled up at the receiving station in the contaminated area exceeds the preset weight, or the volume of the objects to be cleaned piled up exceeds the preset volume, it indicates that there are objects to be cleaned at the receiving station in the contaminated area.

[0038] The method for obtaining the scheduling scenario model described above includes steps S11, S12 and S13.

[0039] Step S11: Construct a spatial set based on the geometric data of each area of ​​the cleaning line in the actual scene. The spatial set includes an obstacle space set and a task space set. The obstacle space set represents all impassable obstacle spaces in the spatial set. The task space set represents the task space in the spatial set where all the task nodes are set.

[0040] Understandably, in this step, geometric spatial scene data of the cleaning line is collected on-site using various sensor devices such as cameras and infrared rangefinders. Then, based on this collected data, software such as 3DS Max, Maya, Rhin, Zbrush, and Google SketchUp is used to fit a virtual space according to a preset scale, and a meta-space set is constructed within the virtual space using a cellular automata model. Next, based on the location parameters of obstacles in the actual scene data, all spaces in the spatial set corresponding to those parameters are identified and defined as obstacle spaces. Obstacles can be walls, fences, or other structures. Spaces with cleaning tasks (task nodes) are defined as task spaces.

[0041] Step S12: Classify the task space set based on the task type of the task node to obtain a field set, where each field in the field set corresponds to the task space corresponding to the same type of task node.

[0042] Understandably, in this step, the task space set is categorized according to the type of task node to obtain the field set. For example, all enzyme washing is classified into the primary cleaning field, all rinsing into the secondary cleaning field, all ultrasonic cleaning into the tertiary cleaning field, and so on. All fields constitute the field set.

[0043] Step S13: Set different field labels for each field to obtain the scheduling scenario model.

[0044] Understandably, in this step, different field labels are set for each field, such as labeling the first-level cleaning field as A, the second-level cleaning field as B, and so on. The goal is simply to distinguish the different cleaning tasks corresponding to each field; no specific restrictions are imposed. By traversing all task spaces and setting corresponding field labels using the method described above, a scheduling scenario model is obtained. This scheduling scenario model clarifies the spatial relationship of each task node in the actual scene, facilitating the later location of the corresponding task nodes.

[0045] Step S2: In response to the medical cleaning machine scheduling request instruction, acquire first image information and second image information; the first image information is an image of the receiving area of ​​the object to be cleaned in the cleaning line, and the second image information is real-time image information collected in each area.

[0046] Understandably, in this step, when the AGV scheduling system receives the medical cleaning machine scheduling request instruction issued by the cleaning rack identification system, it collects the first image information and the second image information respectively. This not only improves the effectiveness of the data, but also reduces data redundancy and filters out the storage of invalid image information.

[0047] Step S3: Based on the first image information, perform image recognition to obtain object recognition results, and match the object recognition results with the preset cleaning task execution route to determine the cleaning task sequence.

[0048] Understandably, in this step, the AGV scheduling system uses algorithms such as DSnet, SIFT, or deep learning-based edge contour extraction to perform image recognition on the first image information, obtaining the object identification result to determine which type of object the item to be cleaned belongs to. Alternatively, each object could have a QR code containing all its attribute information; scanning this code yields the corresponding object identification result. Then, based on the object identification result, a search is performed to find the corresponding preset cleaning task execution route. By determining the order of each task node in the preset cleaning task execution route, the cleaning task sequence can be quickly determined, eliminating the need for manual consideration of which task should be executed first. Furthermore, this avoids damage to the object to be cleaned for those unfamiliar with the cleaning process, improving the level of intelligence and convenience.

[0049] In detail, the recognition method for the above object recognition results includes steps S31, S32, S33, S34, S35 and S36.

[0050] Step S31: Obtain object feature images, where the object feature images are the most representative regions among the various components of each different object.

[0051] Step S32: After normalizing the first image information, color features are extracted based on the HIS color model to obtain the target region.

[0052] Understandably, in this step, the image recognition system first normalizes the first image information to minimize changes to the original image features, unifying the image format and size without altering pixel values ​​to facilitate data processing. Then, the normalized image is converted from the RGB color space to the HIS color space, and the H, I, and S component values ​​of each pixel are extracted. These H, I, and S component values ​​are then used to distinguish between rusted and non-rusted points, thus separating the target area from the background area. This allows limited attention to be focused on the target area, saving resources, quickly obtaining the most effective information, and improving the accuracy of the recognition results.

[0053] Step S33: Based on the depth image corresponding to the target region, an edge detection algorithm is used to extract the contour to obtain a contour image.

[0054] It is understandable that in this step, the AGV scheduling system extracts the contour lines of the depth image through the quantization information of the pixel neighborhood to retain more boundary information. The Canny algorithm used in this embodiment detects the edges of the depth image and extracts the contour lines to obtain the contour line image. This algorithm is existing technology and the corresponding image processing steps can be found by searching, so it will not be described in detail here. In other embodiments, the Sobel operator, Roberts operator, or LOG transform, etc., can be used to calculate the grayscale approximation of the image brightness function for edge detection. This algorithm is also existing technology and will not be described in detail here. For example, the edge detection classification result of the Canny algorithm is shown in formula (1), and the convolution operator of the Sobel operator is shown in formula (2):

[0055] R=F(g,d1,d2) (1)

[0056]

[0057] Where: R represents the edge detection result; F is the original image; g is the edge detection function; d1 is the first threshold of the Canny algorithm; d2 is the second threshold of the Canny algorithm; △ x For the horizontal Sobel operator template; △ y This is the template for the Sobel operator in the vertical direction.

[0058] Step S34: Based on the color information of the target region, the contour image is corrected and paired to obtain a paired image.

[0059] Understandably, in this step, the target area is aligned with the contour image based on the same color information, and then some edges are corrected and smoothed to remove contours that change little within the depth image, and then paired with it to obtain a paired image.

[0060] Step S35: Using the paired image as a guide, the target region is sampled using a joint bilateral filter to obtain a high-resolution image.

[0061] Understandably, in this step, guided by the contour lines in the paired image, the target area is sampled to obtain a high-resolution image, avoiding interference from ghosting and noise in the image, improving image quality, and thus improving the accuracy of identifying the type of the object to be cleaned in the later stages.

[0062] Step S36: Based on the high-resolution image and the object feature image, perform recognition to obtain the object recognition result.

[0063] Understandably, in this step, the image recognition system calculates the cosine similarity between the high-resolution image and the object feature image, and determines the corresponding object type based on the maximum cosine similarity to obtain the object recognition result, which is then sent to the AGV scheduling system.

[0064] Step S4: Based on the second image information, perform image recognition to obtain idle and non-idle scene state results, and based on the idle scene state results and the cleaning task timing, determine the control route and perform task execution control.

[0065] Understandably, in this step, the image recognition system performs image recognition based on the second image information (images within the area of ​​each cleaning task node) to determine which task nodes are currently idle and which are not. Then, based on the sequence of cleaning tasks, it finds the task space corresponding to the currently idle scene state, thus determining the control route from the current task node to the next task node, and sends it to the AGV scheduling system. The AGV scheduling system controls the cleaning rack to execute the next task according to the control route until completion. This method not only realizes the platformization, intelligence, and closed-loop control of the supply room cleaning system, but also achieves fully automated control, freeing up manpower and saving costs. In this application, the use of an intelligent AGV scheduling system greatly saves manpower costs, and the assembly line working mode saves cleaning time, solving the waiting time required when using a single-compartment medical cleaning machine, and effectively ensuring cleaning and drying effects.

[0066] Example 2:

[0067] like Figure 2 As shown, this embodiment provides a control device for a medical cleaning machine. See [link / reference]. Figure 2 The device includes a first acquisition module 710, a second acquisition module 720, an identification module 730, and a control module 740, wherein:

[0068] The first acquisition module 710 is used to acquire medical cleaning machine scheduling request instructions, preset cleaning task execution routes, and scheduling scenario models. The medical cleaning machine scheduling request instructions are request commands issued when there are objects to be cleaned in the cleaning line. The preset cleaning task execution routes are task execution routes formed by sequentially connecting multiple different task nodes. The scheduling scenario model is a set of regions established based on the spatial relationships of various areas of the cleaning line in the actual scene. Each region in the set is spatial information constructed based on the spatial geometric data of each region.

[0069] Preferably, the first acquisition module 710 includes a triggering unit 711, and the triggering conditions of the triggering unit 711 include: the weight of the object to be cleaned is greater than a preset weight or the volume of the object to be cleaned is greater than a preset volume, wherein the preset weight is the minimum weight of the object to be cleaned when the cleaning task is activated; and the preset volume is the minimum volume of the object to be cleaned when the cleaning task is activated.

[0070] In detail, the first acquisition module 710 further includes a modeling unit 712, a classification unit 713, and a setting unit 714:

[0071] Modeling unit 712: is used to construct a spatial set based on the geometric data of each area of ​​the cleaning line in the actual scene. The spatial set includes an obstacle space set and a task space set. The obstacle space set represents all impassable obstacle spaces in the spatial set. The task space set represents the task space in the spatial set where all the task nodes are set.

[0072] Classification unit 713: is used to classify the task space set based on the task type of the task node to obtain a field set, wherein each field in the field set corresponds to the task space corresponding to the same type of task node;

[0073] Setting unit 714: used to set different field labels based on each of the fields to obtain a scheduling scenario model.

[0074] The second acquisition module 720 is used to acquire first image information and second image information in response to the medical cleaning machine scheduling request instruction; the first image information is an image of the receiving area of ​​the object to be cleaned in the cleaning line, and the second image information is image information collected in real time in each area;

[0075] Recognition module 730: used to perform image recognition based on the first image information to obtain object recognition results, and to match the object recognition results with the preset cleaning task execution route to determine the cleaning task sequence;

[0076] Specifically, the aforementioned identification module 730 includes an acquisition unit 731, a first extraction unit 732, a second extraction unit 733, a pairing unit 734, a reconstruction unit 735, and a matching unit 736, wherein:

[0077] Acquisition unit 731: used to acquire object feature images, wherein the object feature images are the most representative regions among the various components of each different object;

[0078] First extraction unit 732: used to normalize the first image information and then extract color features based on the HIS color model to obtain the target region;

[0079] The second extraction unit 733 is used to extract contours based on the depth image corresponding to the target region using an edge detection algorithm to obtain a contour image.

[0080] Pairing unit 734: used to correct the contour image based on the color information of the target area and complete the pairing to obtain a paired image;

[0081] Reconstruction unit 735: used to sample the target region using a joint bilateral filter, guided by the paired image, to obtain a high-resolution image;

[0082] Matching unit 736: used to perform recognition based on the high-resolution image and the object feature image to obtain object recognition results.

[0083] Control module 740: is used to perform image recognition based on the second image information to obtain idle and non-idle scene state results, and to determine the control route and perform task execution control based on the idle scene state results and the cleaning task timing.

[0084] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.

[0085] Example 3:

[0086] Corresponding to the above method embodiments, this embodiment also provides a control device for a medical cleaning machine. The control device for a medical cleaning machine described below and the control method for a medical cleaning machine described above can be referred to in correspondence.

[0087] Figure 3 This is a block diagram illustrating a control device 800 for a medical cleaning machine according to an exemplary embodiment. (See diagram below.) Figure 3 As shown, the control device 800 of the medical cleaning machine includes a processor 801 and a memory 802. The control device 800 of the medical cleaning machine also includes one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0088] The processor 801 controls the overall operation of the control device 800 of the medical cleaning machine to complete all or part of the steps in the control method of the medical cleaning machine described above. The memory 802 stores various types of data to support the operation of the control device 800 of the medical cleaning machine. This data may include, for example, instructions for any application or method operating on the control device 800 of the medical cleaning machine, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 includes a display and an audio component. The display may be, for example, a touchscreen, primarily used to monitor the device's operating status. The audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, or buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the control device 800 of the medical cleaning machine and other devices. Wireless communication includes, for example, Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0089] In an exemplary embodiment, the control device 800 of the medical cleaning machine may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the control method of the medical cleaning machine described above.

[0090] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the control method for the medical cleaning machine described above. For example, the computer-readable storage medium may be the memory 802 including the program instructions described above, which may be executed by the processor 801 of the control device 800 of the medical cleaning machine to complete the control method for the medical cleaning machine described above.

[0091] Example 4:

[0092] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the control method of a medical cleaning machine described above.

[0093] A computer program is stored on a readable storage medium, and when executed by a processor, the computer program implements the steps of the control method for the medical cleaning machine described in the above method embodiments.

[0094] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0095] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0096] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A control method for a medical cleaning machine, characterized in that, include: The system acquires a medical cleaning machine scheduling request instruction, a preset cleaning task execution route, and a scheduling scenario model. The medical cleaning machine scheduling request instruction is a request command issued when there are objects to be cleaned in the cleaning line. The preset cleaning task execution route is a task execution route composed of multiple different task nodes connected sequentially. The scheduling scenario model is a set of regions established based on the spatial relationships of various areas of the cleaning line in the actual scenario. Each region in the set is spatial information constructed based on the spatial geometric data of each region. In response to the medical cleaning machine scheduling request instruction, first image information and second image information are acquired; the first image information is an image of the receiving area of ​​the object to be cleaned in the cleaning line, and the second image information is real-time image information collected in each of the areas; Based on the first image information, image recognition is performed to obtain object recognition results, and the object recognition results are matched with the preset cleaning task execution route to determine the cleaning task sequence. Based on the second image information, image recognition is performed to obtain the idle and non-idle scene status results. Based on the idle scene status results and the cleaning task sequence, the control route is determined and the task execution control is performed. The object recognition result obtained by image recognition based on the first image information includes: Obtain object feature images, which are the most representative regions among the various components of each different object; After normalizing the first image information, color features are extracted based on the HIS color model to obtain the target region; Based on the depth image corresponding to the target region, an edge detection algorithm is used to extract the contour to obtain a contour image. The contour image is corrected and paired based on the color information of the target region to obtain a paired image; Using the paired image as a guide, the target region is sampled using a joint bilateral filter to obtain a high-resolution image; Based on the high-resolution image and the object feature image, an object recognition result is obtained.

2. The control method for the medical cleaning machine according to claim 1, characterized in that, The triggering conditions for the medical cleaning machine scheduling request instruction include: the weight of the object to be cleaned is greater than a preset weight or the volume of the object to be cleaned is greater than a preset volume. The preset weight is the minimum weight of the object to be cleaned when the cleaning task is activated; the preset volume is the minimum volume of the object to be cleaned when the cleaning task is activated.

3. The control method for a medical cleaning machine according to claim 1, characterized in that, The method for obtaining the scheduling scenario model includes: Based on the geometric data of each area of ​​the cleaning line in the actual scene, a spatial set is constructed. The spatial set includes an obstacle space set and a task space set. The obstacle space set represents all impassable obstacle spaces in the spatial set. The task space set represents the task space in the spatial set where all the task nodes are set. Based on the task type of the task node, the task space set is classified to obtain a field set, and each field in the field set corresponds to the task space corresponding to the same type of task node. Based on setting different field labels for each field, a scheduling scenario model is obtained.

4. A control device for a medical cleaning machine, characterized in that, include: The first acquisition module is used to acquire medical cleaning machine scheduling request instructions, preset cleaning task execution routes, and scheduling scenario models. The medical cleaning machine scheduling request instructions are request commands issued when there are objects to be cleaned in the cleaning line. The preset cleaning task execution routes are task execution routes formed by sequentially connecting multiple different task nodes. The scheduling scenario model is a set of regions established based on the spatial relationships of various areas of the cleaning line in the actual scenario. Each region in the set is spatial information constructed based on the spatial geometric data of each region. The second acquisition module is used to acquire first image information and second image information in response to the medical cleaning machine scheduling request instruction; the first image information is an image of the receiving area of ​​the object to be cleaned in the cleaning line, and the second image information is image information collected in real time in each area; Recognition module: used to perform image recognition based on the first image information to obtain object recognition results, and to match the object recognition results with the preset cleaning task execution route to determine the cleaning task sequence; Control module: used to perform image recognition based on the second image information to obtain idle and non-idle scene state results, and to determine the control route and perform task execution control based on the idle scene state results and the cleaning task timing; The identification module includes: Acquisition unit: used to acquire object feature images, wherein the object feature images are the most representative regions among the various components of each different object; First extraction unit: used to normalize the first image information and then extract color features based on the HIS color model to obtain the target region; The second extraction unit is used to extract contours based on the depth image corresponding to the target region using an edge detection algorithm to obtain a contour line image. Pairing unit: used to correct the contour image based on the color information of the target area and complete the pairing to obtain a paired image; Reconstruction unit: used to sample the target region using a joint bilateral filter, guided by the paired image, to obtain a high-resolution image; Matching unit: used to perform recognition based on the high-resolution image and the object feature image to obtain object recognition results.

5. The control device for the medical cleaning machine according to claim 4, characterized in that, The first acquisition module includes a triggering unit, and the triggering conditions of the triggering unit include: the weight of the object to be cleaned is greater than a preset weight or the volume of the object to be cleaned is greater than a preset volume. The preset weight is the minimum weight of the object to be cleaned when the cleaning task is activated; the preset volume is the minimum volume of the object to be cleaned when the cleaning task is activated.

6. The control device for the medical cleaning machine according to claim 4, characterized in that, The first acquisition module further includes: Modeling unit: used to construct a spatial set based on the geometric data of each area of ​​the cleaning line in the actual scene. The spatial set includes an obstacle space set and a task space set. The obstacle space set represents all impassable obstacle spaces in the spatial set. The task space set represents the task space in the spatial set where all the task nodes are set. Classification unit: used to classify the task space set based on the task type of the task node to obtain a field set, wherein each field in the field set corresponds to the task space corresponding to the same type of task node; Setting unit: used to set different field labels for each field to obtain a scheduling scenario model.

7. A control device for a medical cleaning machine, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the control method for the medical cleaning machine as described in any one of claims 1 to 3; One or more of multimedia components, I / O interfaces, and communication components, including a display and an audio component, wherein the display is used to monitor the operating status of the device, and the audio component is used to output and / or input audio signals.

8. A readable storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the control method for the medical cleaning machine as described in any one of claims 1 to 3.

Images