A method, device, storage medium, and terminal equipment for preventing cross-infection in patient wards.

Abstract

This invention discloses a method, device, storage medium, and terminal equipment for preventing cross-infection in hospital wards. The method includes: acquiring the ID information of visiting medical personnel, allowing them to enter the ward for visits based on their ID information, with different monitored areas within the ward; acquiring intrusion signals from the monitored areas, generating cleaning and disinfection tasks based on these areas, and establishing a visitor infection risk dataset; the monitored areas include: clean areas, generally contaminated areas, and heavily contaminated areas; acquiring video data and sensor data from the clean areas and inputting them into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection tasks are completed; the cleaning cleanliness scoring model is trained by a neural network; if the disinfection task is completed, unlocking the ward door lock and recording a cleaning completion marker on the visitor infection risk dataset. By scoring each cleaning and disinfection task using the cleaning cleanliness scoring model, the standardization and effectiveness of disinfection and cleaning are effectively improved, reducing the incidence of hospital-acquired infections.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a method, device, storage medium and terminal equipment for ward isolation to prevent cross-infection. Background Technology

[0002] Preventing cross-infection in hospital wards is a core, systemic healthcare safety task involving multiple aspects such as the environment, personnel, processes, and patients. All patients' blood, bodily fluids, secretions, excretions (excluding sweat), non-intact skin, and mucous membranes are considered potentially infectious and must be handled with standard precautions. Furthermore, personnel management and behavioral norms require strict control. For example, the hygiene precautions that healthcare workers must take when entering and leaving the ward (such as hand and facial hygiene) also need to be strictly controlled.

[0003] Past ward cross-infection prevention and control measures typically relied on methods such as the duration of time spent in sensitive areas, whether one reached clean areas, and whether one pressed a hand sanitizer dispenser or turned on a tap to determine whether cleaning had been performed. Logically, this method can only determine whether cleaning was done (it can only determine if it was done), but it cannot determine whether the cleaning was effective (it cannot determine how well it was done). For example, one might press a hand sanitizer dispenser in the area, but the sanitizer might not necessarily fall into their hand; or one might turn on a tap to rinse, but not necessarily rinse their hands, and the hand movements might not be effective.

[0004] However, during busy ward visits, medical staff are prone to neglecting hygiene and protective measures. This can easily lead to cross-infection during patient visits, seriously affecting the health and safety of both patients and medical staff.

[0005] Therefore, the aforementioned technical deficiencies urgently need to be addressed. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a method, device, storage medium, and terminal equipment for ward isolation to prevent cross-infection. It aims to automatically identify the category of wireless products and complete pairing, enabling pairing of multiple product categories, improving the effectiveness and security of pairing, and solving the technical problem of signal interference that easily occurs during traditional wireless pairing.

[0007] To address the aforementioned technical problems, the first aspect of this application provides a method for ward isolation to prevent cross-infection, the method comprising:

[0008] Obtain the ID information of visiting medical staff, and allow them to enter the ward for visits based on the ID information. Different monitoring areas are set up in the ward.

[0009] The system acquires intrusion signals from monitored areas, generates cleaning and disinfection tasks based on these areas, and establishes a dataset on the risk of infection during patient visits. Monitored areas include: clean areas, moderately contaminated areas, and heavily contaminated areas.

[0010] The system acquires video and sensor data from the clean area and inputs the video and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task has been completed. The cleaning cleanliness scoring model is formed by training a neural network.

[0011] If the disinfection task is completed, the ward door lock is unlocked, and a cleaning completion marker is entered into the visitor infection risk dataset.

[0012] The method for preventing cross-infection in wards includes the following steps: acquiring video and sensor data from the clean area, and inputting the video and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task has been completed.

[0013] Acquire video and sensor data of medical staff performing cleaning and disinfection operations in the clean area;

[0014] Video data and sensor data are input into the cleaning cleanliness scoring model;

[0015] Obtain the cleaning score data of the cleaning and disinfection task from the cleaning and disinfection score model;

[0016] Cleanliness score data is recorded in the visitation infection risk dataset;

[0017] Determine whether the cleaning score data is above the preset standard score threshold.

[0018] The method for preventing cross-infection in patient wards includes the following steps: acquiring video and sensor data from medical staff during cleaning and disinfection operations in the clean area.

[0019] Point cloud data and video data were acquired. The point cloud data was obtained by scanning the clean area with millimeter-wave radar. The video data included video data of hand rubbing and video data of tool brushing. Sensor data included data on cleaning fluid consumption, disinfectant consumption, and water flow.

[0020] The point cloud data and video data are fitted to obtain the fitted data;

[0021] The fitted data is input into a convolutional neural network model to obtain the relative spatial relationship data between the hand, tools, and consumables;

[0022] Based on a deep learning-based target detector and a convolutional neural network model, the system determines whether the medical staff's hands, tools, and consumables are aligned according to relative spatial relationship data. Consumables include water, cleaning agents, and disinfectants. If aligned, the relative spatial relationship data is input into the cleaning cleanliness scoring model. If not aligned, an alarm message is output to prompt the medical staff to repeat the cleaning and disinfection process.

[0023] The method for preventing cross-infection in patient wards includes the following steps: acquiring video and sensor data from medical staff during cleaning and disinfection operations in the clean area.

[0024] Acquire pressure sensor data from the output end of the consumable container. The pressure sensor data includes the pressure value and duration.

[0025] Determine whether the pressure value and duration are within the preset pressure threshold and preset time threshold; if yes, input the consumable consumption data into the cleaning cleanliness scoring model; if no, issue an alarm message indicating insufficient consumable usage to the display device.

[0026] The aforementioned method for preventing cross-infection in wards includes obtaining the ID information of visiting medical staff and allowing them to enter the ward for visits based on that ID information. The method also includes the following steps: [Further details about the steps involved in setting up different monitored areas within the ward are needed.]

[0027] The ID information of visiting medical staff can be obtained through biometric devices or ID card scanning devices.

[0028] Retrieve visitation tasks within the current time period based on ID information;

[0029] Grant work permissions to the corresponding ID based on the visitation task.

[0030] The method for preventing cross-infection in patient wards, wherein the step of obtaining the ID information of medical staff through biometric devices includes:

[0031] The facial recognition camera obtains the facial recognition information of medical staff, and the ID information of the visiting medical staff is obtained based on the facial recognition information.

[0032] The method for preventing cross-infection in ward isolation includes a monitoring area intrusion signal that is at least one of image recognition signal, infrared signal, and pressure sensing signal.

[0033] A second aspect of this application provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps in the ward isolation method for preventing cross-infection as described above.

[0034] A third aspect of this application provides a ward isolation device for preventing cross-infection, comprising:

[0035] The first acquisition module is used to acquire the ID information of visiting medical staff and allow them to enter the ward for visits based on the ID information. Different monitoring areas are set up in the ward.

[0036] The second acquisition module is used to acquire intrusion signals in the monitored area, generate cleaning and disinfection tasks based on the monitored area, and establish a dataset of infection risk from intrusions; the monitored area includes: clean area, generally contaminated area, and heavily contaminated area;

[0037] The scoring module is used to acquire video data and sensor data from the clean area, and input the video data and sensor data into the cleaning cleanliness scoring model to determine whether the cleaning and disinfection task has been completed. The cleaning cleanliness scoring model is formed by training a neural network.

[0038] The judgment module is used to unlock the ward door lock and record a cleaning completion mark on the visitor infection risk dataset if the disinfection task is completed.

[0039] A fourth aspect of this application provides a terminal device, which includes: a processor, a memory, and a communication bus; the memory stores a computer-readable program that can be executed by the processor;

[0040] The communication bus enables communication between the processor and the memory;

[0041] When the processor executes the computer-readable program, it implements the steps in the ward isolation method for preventing cross-infection as described above.

[0042] Beneficial Effects: Compared with existing technologies, this invention provides a method, device, storage medium, and terminal equipment for preventing cross-infection in patient wards. The method includes: acquiring the ID information of visiting medical personnel, allowing them to enter the ward for visits based on the ID information, wherein different monitoring areas are set up within the ward; acquiring intrusion signals from the monitoring areas, generating cleaning and disinfection tasks based on the monitoring areas, and establishing a visitor infection risk dataset; the monitoring areas include: clean areas, generally contaminated areas, and heavily contaminated areas; acquiring video data and sensor data from the clean areas, inputting the video data and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection tasks are completed, wherein the cleaning cleanliness scoring model is trained by a neural network; if the disinfection task is completed, unlocking the ward door lock and recording a cleaning completion mark on the visitor infection risk dataset. By scoring each cleaning and disinfection task using the cleaning cleanliness scoring model, the standardization and effectiveness of hand hygiene and equipment disinfection for medical personnel are effectively improved, reducing the incidence of hospital infections and ensuring the safety of patients and medical personnel. Attached Figure Description

[0043] Figure 1 A flowchart of a ward isolation method for preventing cross-infection provided by the present invention;

[0044] Figure 2 for Figure 1 A flowchart illustrating step S30;

[0045] Figure 3 for Figure 2 A flowchart illustrating step S301;

[0046] Figure 4 for Figure 2 Another flowchart of step S301;

[0047] Figure 5 for Figure 1 A flowchart illustrating step S10;

[0048] Figure 6 A schematic diagram of the ward isolation device for preventing cross-infection provided by the present invention;

[0049] Figure 7 The structural schematic diagram of the terminal device provided by the present invention. Detailed Implementation

[0050] This invention provides a method, apparatus, storage medium, and terminal device for preventing cross-infection in hospital wards. To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention.

[0051] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0052] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0053] The invention will be further explained below with reference to the accompanying drawings and the description of the embodiments.

[0054] First, it's important to clarify that past ward cross-infection prevention and control measures typically relied on methods like measuring time spent in sensitive areas, whether one reached clean areas, or whether hand sanitizer was dispensed or water was turned on to determine if cleaning had been performed. Logically, this method only determines whether cleaning was done (it can only tell if it was done), but it cannot determine whether the cleaning was effective (it cannot tell how well it was done). For example, someone might press a hand sanitizer dispenser, but the sanitizer might not actually get into their hand; or they might turn on the water, but they might not be directly rinsing their hands, and their hand movements might not be effective. During busy ward visits, medical staff are prone to neglecting hygiene precautions. This can easily lead to cross-infection during patient visits, seriously affecting the health and safety of both patients and medical staff.

[0055] This embodiment provides a method for preventing cross-infection in patient wards. The executing entity of this method can be a receiver used for wireless connection. It is understood that the executing entity in this embodiment can be a control host. For example, the control host obtains the ID information of visiting medical personnel and allows them to enter the ward for visits based on the ID information. Different monitoring areas are set up within the ward. The control host obtains intrusion signals from the monitored areas, generates cleaning and disinfection tasks based on the monitored areas, and establishes a visitor infection risk dataset. The monitored areas include: clean areas, generally contaminated areas, and heavily contaminated areas. The control host obtains video data and sensor data from the clean areas and inputs the video data and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task is completed. The cleaning cleanliness scoring model is formed by training a neural network. If the disinfection task is completed, the ward door lock is unlocked, and a cleaning completion marker is entered into the visitor infection risk dataset.

[0056] The cleaning cleanliness scoring model assesses whether disinfectant fell into the hands of healthcare workers, whether they rinsed their hands thoroughly, whether their handwashing actions were proper, and whether their handwashing was sufficient (combining time and speed). The final score determines whether the cleaning and disinfection work was completed.

[0057] It should be noted that the above application scenarios are shown only for the purpose of understanding the present invention, and the embodiments of the present invention are not limited in any way. On the contrary, the embodiments of the present invention can be applied to any applicable scenario.

[0058] Furthermore, such as Figure 1 As shown in the accompanying drawings, in order to further illustrate the invention, the embodiments will be described in detail below with reference to the accompanying drawings.

[0059] The ward isolation method for preventing cross-infection provided in this embodiment is as follows: Figure 1 As shown, the method specifically includes:

[0060] Step S10: Obtain the ID information of visiting medical personnel. Based on this ID information, allow medical personnel to enter the ward for visits. Different monitoring areas are set up within the ward. Verify the medical personnel's work permissions based on their ID information. If their work permissions allow entry, the ward door opens, and the medical personnel can enter smoothly. This step is to verify the identity of medical personnel and prevent medical personnel without current medical visitation duties or other unrelated personnel from entering high-risk wards, thus reducing the risk of cross-infection.

[0061] In this step, facial recognition devices can be used to authenticate medical staff, or ID recognition devices can be used to identify the name tags of medical staff to obtain their ID information.

[0062] Step S20: Obtain intrusion signals from monitored areas, generate cleaning and disinfection tasks based on the monitored areas, and establish a dataset of infection risk from patient visits. Monitored areas include: clean areas, generally contaminated areas, and heavily contaminated areas. Intrusion signals from monitored areas are collected by various sensors installed in different monitored areas. Examples include pressure sensors on workbenches, infrared sensors, and cameras installed in the monitored area. Different monitored areas have different virus concentrations, and corresponding infection risks also differ. Therefore, monitored areas can be divided into clean areas, generally contaminated areas, and heavily contaminated areas.

[0063] It should also be noted that the infection risk varies across different regulatory areas, and the cleaning and disinfection measures required by medical personnel differ accordingly. Therefore, this embodiment requires implementing corresponding cleaning and disinfection measures based on the activity trajectory of medical personnel (the regulatory areas involved), and aggregating these measures to generate a cleaning and disinfection task. This allows medical personnel to perform cleaning and disinfection work based on the task.

[0064] In some embodiments, the intrusion signal in the monitored area can also be a signal that is specific to the contact between the hands or parts of the body of medical staff and high-risk infection areas: for example, by using sensors such as visual sensors and millimeter-wave radar to monitor and capture the contact points between high-risk infection areas and the bodies (and medical tools) of medical staff in real time, and record the contact points in the cleaning and disinfection task so that medical staff can perform cleaning and disinfection operations one by one in the future.

[0065] Step S30: Acquire video and sensor data from the clean area. Input the video and sensor data into the cleaning cleanliness scoring model to determine whether the cleaning and disinfection task is completed. The cleaning cleanliness scoring model is trained by a neural network. It should be noted that the clean area is a dedicated area for cleaning and disinfection. After visiting patients, medical staff must perform standard cleaning and disinfection of their hands and tools in the clean area before leaving the ward. The clean area is equipped with at least one camera, at least one millimeter-wave radar, and various sensors. The camera captures real-time images of medical staff during the cleaning and disinfection process. The millimeter-wave radar collects point cloud data of medical staff and the environment. The various sensors collect data on the usage of various consumables, such as water flow, disinfectant usage, and cleaning agent usage, thereby improving the effectiveness of cleaning and disinfection.

[0066] Ultimately, the standard cleaning and disinfection procedures were determined by collecting data on the hand movements of medical staff and the amount of consumables used.

[0067] Step S40: If the disinfection task is completed, unlock the ward door and enter a cleaning completion marker in the visitor infection risk dataset. Only after verifying the successful completion of all cleaning tasks in the above steps will the system allow medical staff to enter. Furthermore, all verification data from the cleaning and disinfection process performed by medical staff will be saved in the visitor infection risk dataset for subsequent data review.

[0068] Furthermore, such as Figure 2 As shown, the steps for acquiring video and sensor data from the clean area and inputting this data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task has been completed include:

[0069] Step S301: Acquire video data and sensor data of medical staff during cleaning and disinfection operations in the clean area;

[0070] Step S302: Input the video data and sensor data into the cleaning cleanliness scoring model;

[0071] Step S303: Obtain the cleaning score data of the cleaning and disinfection task from the cleaning and disinfection score model;

[0072] Step S304: Record the cleaning score data in the visitor infection risk dataset;

[0073] Step S305: Determine whether the cleaning score data is above the preset standard score threshold.

[0074] For example, during the disinfectant rubbing detection process, sensors are installed on the disinfectant bottle or container to monitor whether healthcare workers' fingers are rubbing with disinfectant. When the sensor detects that the disinfectant bottle has been opened and fingers are rubbing, the action is recorded. Similarly, during the detergent rinsing detection process, sensors are installed on the sink or detergent bottle to monitor whether healthcare workers' fingers are washing with detergent. When the sensor detects that the detergent bottle has been opened and fingers are washing, the action is recorded. Data analysis: The data recorded by the sensors is analyzed, combined with information on area intrusion, disinfectant rubbing, and detergent rinsing, to determine whether the fingers were cleaned according to the correct steps. This method enables the monitoring and evaluation of the hand cleaning process, helping to ensure the effectiveness and thoroughness of hand cleaning. This intelligent hand cleaning monitoring system helps improve the standardization and hygiene of cleaning procedures, reducing the risk of germ transmission.

[0075] Furthermore, such as Figure 3 The steps for acquiring video and sensor data from healthcare workers during cleaning and disinfection operations in the clean area, as shown, include:

[0076] Step S3011: Acquire point cloud data and video data. The point cloud data is obtained by scanning the clean area with millimeter-wave radar. The video data includes video data of hand rubbing and video data of tool brushing. The sensor data includes cleaning solution consumption data, disinfectant consumption data and water flow data.

[0077] Step S3012: Fit the point cloud data and video data to obtain the fitted data;

[0078] Step S3013: Input the fitted data into the convolutional neural network model to obtain the relative spatial relationship data between the hand, tools and consumables;

[0079] Step S3014: Based on a deep learning-based target detector and convolutional neural network model, determine whether the medical staff's hands, tools, and consumables are aligned according to the relative spatial relationship data. Consumables include water, cleaning agents, and disinfectants. If so, input the relative spatial relationship data into the cleaning cleanliness scoring model. If not, output an alarm message to prompt the medical staff to repeat the cleaning and disinfection.

[0080] Understandably, during cleaning and disinfection processes, details such as whether healthcare workers aim their hands directly at the water and whether they use sufficient cleaning agents and disinfectants are crucial. This is also where traditional methods fall short. Traditional assessment methods can only determine whether cleaning has been done (only whether it has been done), but cannot determine whether the cleaning was effective (cannot determine how well it was done). For example, when entering an area, someone might press a disinfectant pump, but the disinfectant may not necessarily fall into their hand; or when rinsing with water, they may not aim it directly at their hands, and their hand movements may not be effective. Healthcare workers are prone to neglecting hygiene and protective measures during busy ward visits. This can easily lead to cross-infection during patient visits, seriously affecting the health and safety of both patients and healthcare workers.

[0081] To determine in real time whether water is aimed at the hand, this solution preferably uses computer vision technology combined with radar millimeter wave or infrared sensing detection. Through deep learning and image processing, it can accurately collect the positional relationship between the medical staff's hands and the consumables.

[0082] In this approach, a deep learning model (convolutional neural network model) is used for the analysis and computation of image and point cloud data. Before using the model, image samples containing hands and water are first collected, including cases where the water is aligned with and not aligned with the hand. Then, a deep learning model, such as a convolutional neural network (CNN), is trained using these image samples to learn the spatial relationship between the water and the hand.

[0083] Secondly, real-time images are captured by a camera, and the positions of the hands and water are detected in each frame. Object detection algorithms, such as deep learning-based object detectors like YOLO and Faster R-CNN, can be used to detect the positions of the hands and water.

[0084] Deep learning models are used to predict the positions of the hand and water, and to analyze their relative spatial relationship. Algorithms can be used to calculate information such as the distance, position, and angle between the water and the hand to determine whether the water is aligned with the hand.

[0085] Furthermore, an innovative method involves detecting whether fingers have come into contact with contaminated areas through regional intrusion detection, combined with steps such as rubbing with disinfectant and rinsing with detergent to determine whether hand cleaning has been performed. This method can be achieved through the following steps:

[0086] Furthermore, such as Figure 4 The steps for acquiring video and sensor data from healthcare workers during cleaning and disinfection operations in the clean area, as shown, include:

[0087] Step S3015: Obtain pressure sensor data at the output end of the consumable container. The pressure sensor data includes pressure value and duration.

[0088] Step S3016: Determine whether the pressure value and duration are within the preset pressure threshold and preset time threshold; if yes, input the consumable consumption data into the cleaning cleanliness scoring model; if no, issue an alarm message of insufficient consumable usage to the display device.

[0089] For example, a pressure sensor can be installed on the squeeze nozzle of a disinfectant or cleaning agent to monitor the squeezing force and time. By analyzing the sensor data, it can be determined whether the amount of disinfectant or cleaning agent dispensed is sufficient.

[0090] In some embodiments, a liquid level sensor may be installed inside the container of the disinfectant or cleaning agent to monitor changes in the liquid level. The sensor will send a signal when the amount of liquid dispensed reaches a certain threshold.

[0091] In some other embodiments, a weight sensor can be installed below the container of the disinfectant or cleaning agent to monitor changes in the weight of the disinfectant or cleaning agent. By comparing the weight difference before and after squeezing, it can be determined whether enough cleaning agent has been used.

[0092] By applying these sensor technologies, it is possible to monitor the amount of disinfectant or cleaning agent used, ensuring that sufficient cleaning agent is used during hand cleaning, thereby improving cleaning effectiveness and hygiene. This intelligent cleaning agent usage monitoring system helps standardize cleaning procedures and reduce the risk of germ transmission.

[0093] In the method steps for detecting water flow, this solution's first embodiment uses a pressure sensor installed on a sink or faucet to detect the strength of the water flow, thereby determining whether fingers are in contact with the water flow during handwashing. The second embodiment utilizes computer vision technology: using a camera and computer vision technology, the detection of handwashing actions can be achieved. By recognizing the position, movement trajectory, and gestures of the fingers, it can be determined whether the fingers are performing a handwashing action. Furthermore, machine learning algorithms can be used: combining sensor data and computer vision technology, machine learning algorithms can be used to train a model to recognize and detect handwashing actions. Through model learning and training, accurate detection of handwashing actions can be achieved.

[0094] Furthermore, in some embodiments, local encryption processing can be applied to images of patients' private areas.

[0095] It should be noted that video equipment in hospital wards sometimes captures video clips of patients, some of which may expose patients' private parts. To prevent this video data from being leaked or unintentionally displayed, this solution can also apply mosaic (or other blurring methods) to the video data containing patients' private parts. The specific processing steps are as follows:

[0096] Furthermore, prior to the steps of acquiring video and sensor data from the clean area, the process also includes:

[0097] Based on a clothing feature recognition model, video frames in the video data are scanned, video frames containing patient features are marked, and patient video segments are obtained.

[0098] Based on the human feature recognition model, the patient video clips are identified and the patient's private body parts in the video clips are marked;

[0099] By blurring the body features in patient video clips, privacy-preserving video clips can be obtained.

[0100] Privacy-preserving video clips are encrypted using a blockchain encryption engine and then stored in the cloud.

[0101] First, private areas in medical images or videos are blurred using mosaic technology to ensure effective concealment of sensitive information. Then, the data is encrypted using blockchain: the blurred medical image or video data is uploaded to a blockchain network, where blockchain technology is used to encrypt and store the data. A data chain is established: a data chain is created on the blockchain network to store and manage the blurred medical image or video data, ensuring data security and immutability. Access control is implemented: through technologies such as smart contracts, access control for medical image or video data is implemented, allowing only authorized users to access and view the data, protecting privacy from misuse. A comprehensive privacy protection strategy is established, including data access control, data encryption, and identity verification measures, to ensure the effective protection of the privacy of medical staff and patients. By combining mosaic processing of private areas with blockchain encryption, the privacy of medical staff and patients can be effectively protected, ensuring the security and privacy of medical data. This method not only improves data security but also enhances data transparency and traceability, contributing to the establishment of a secure and reliable medical information management system.

[0102] Furthermore, such as Figure 5 As shown, the process involves obtaining the ID information of visiting medical staff and granting them access to the ward based on that ID information. This includes steps involving different monitored areas within the ward:

[0103] Step S101: Obtain the ID information of visiting medical staff through a biometric device or through an ID card scanning device;

[0104] Step S102: Retrieve the visitation tasks within the current time period based on the ID information;

[0105] Step S103: Grant work permissions to the corresponding ID based on the visitation task.

[0106] Furthermore, the steps for obtaining healthcare workers' ID information through biometric devices include:

[0107] The facial recognition camera obtains the facial recognition information of medical staff, and the ID information of the visiting medical staff is obtained based on the facial recognition information.

[0108] Furthermore, the intrusion signal in the monitored area is at least one of image recognition signals, infrared signals, and pressure sensing signals.

[0109] In summary, this embodiment provides a method, device, storage medium, and terminal equipment for preventing cross-infection in patient wards. The method includes: acquiring the ID information of visiting medical personnel, allowing them to enter the ward for visits based on the ID information, wherein different monitoring areas are set up within the ward; acquiring intrusion signals from the monitoring areas, generating cleaning and disinfection tasks based on the monitoring areas, and establishing a visitor infection risk dataset; the monitoring areas include: clean areas, generally contaminated areas, and heavily contaminated areas; acquiring video data and sensor data from the clean areas, inputting the video data and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection tasks are completed, wherein the cleaning cleanliness scoring model is trained by a neural network; if the disinfection task is completed, unlocking the ward door lock, and recording a cleaning completion mark on the visitor infection risk dataset. By scoring each cleaning and disinfection task using the cleaning cleanliness scoring model, the standardization and effectiveness of hand hygiene and equipment disinfection for medical personnel are effectively improved, reducing the incidence of hospital-acquired infections and ensuring the safety of patients and medical personnel.

[0110] To better implement the above methods, this application embodiment also provides a ward isolation device 100 for preventing cross-infection. This device can be integrated into an electronic device, such as a terminal, server, or personal computer. For example, in this embodiment, the device may include: a first acquisition module 101, a second acquisition module 102, a scoring module 103, and a judgment module 104, as detailed below (e.g.) Figure 6 ):

[0111] The first acquisition module 101 is used to acquire the ID information of visiting medical staff and allow them to enter the ward for visits based on the ID information, wherein different monitoring areas are set up in the ward.

[0112] The second acquisition module 102 is used to acquire intrusion signals in the monitored area, generate cleaning and disinfection tasks based on the monitored area, and establish a dataset of infection risk from the visitation; the monitored area includes: a clean area, a generally contaminated area, and a heavily contaminated area;

[0113] The scoring module 103 is used to acquire video data and sensor data of the clean area, and input the video data and sensor data into the cleaning cleanliness scoring model to determine whether the cleaning and disinfection task has been completed. The cleaning cleanliness scoring model is formed by training a neural network.

[0114] The judgment module 104 is used to unlock the ward door lock if the disinfection task is completed, and to enter a cleaning completion mark on the visitor infection risk dataset.

[0115] In some embodiments, a ward isolation device 100 for preventing cross-infection includes a first acquisition module 101, a second acquisition module 102, a scoring module 103, and a judgment module 104. The first acquisition module 101 is used to acquire the ID information of visiting medical personnel and allow them to enter the ward for visits based on the ID information. Different monitoring areas are set up in the ward. The second acquisition module 102 acquires intrusion signals in the monitoring areas, generates cleaning and disinfection tasks based on the monitoring areas, and establishes a visitor infection risk dataset. The monitoring areas include: clean areas, generally contaminated areas, and heavily contaminated areas. The scoring module 103 acquires video data and sensor data of the clean area and inputs the video data and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task is completed. The cleaning cleanliness scoring model is formed by training a neural network. The judgment module 104, if the disinfection task is completed, unlocks the ward door lock and records a cleaning completion mark on the visitor infection risk dataset.

[0116] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0117] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0118] Based on the above-described method for preventing cross-infection in wards, this embodiment provides a computer-readable storage medium storing one or more programs. These programs can be executed by one or more processors to implement the steps in the method for preventing cross-infection in wards as described in the above embodiment. For example, executing the above-described... Figure 1 Method steps S10 to S40 in the text Figure 2 Method steps S301 to S305 in the text Figure 3 Method steps S3011 to S3014 in the text Figure 4 Method steps S3015 to S3016 in the text Figure 5 The method steps S101 to S103 are as follows:

[0119] Obtain the ID information of visiting medical staff, and allow them to enter the ward for visits based on the ID information. Different monitoring areas are set up in the ward.

[0120] The system acquires intrusion signals from monitored areas, generates cleaning and disinfection tasks based on these areas, and establishes a dataset on the risk of infection during patient visits. Monitored areas include: clean areas, moderately contaminated areas, and heavily contaminated areas.

[0121] The system acquires video and sensor data from the clean area and inputs the video and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task has been completed. The cleaning cleanliness scoring model is formed by training a neural network.

[0122] If the disinfection task is completed, unlock the ward door and mark the cleaning as complete on the visitor infection risk dataset.

[0123] The method for preventing cross-infection in wards includes the following steps: acquiring video and sensor data from the clean area, and inputting the video and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task has been completed.

[0124] Acquire video and sensor data of medical staff performing cleaning and disinfection operations in the clean area;

[0125] Video data and sensor data are input into the cleaning cleanliness scoring model;

[0126] Obtain the cleaning score data of the cleaning and disinfection task from the cleaning and disinfection score model;

[0127] Cleanliness score data is recorded in the visitation infection risk dataset;

[0128] Determine whether the cleaning score data is above the preset standard score threshold.

[0129] In some embodiments, the step of acquiring video data and sensor data of healthcare workers performing cleaning and disinfection operations in a clean area includes:

[0130] Point cloud data and video data were acquired. The point cloud data was obtained by scanning the clean area with millimeter-wave radar. The video data included video data of hand rubbing and video data of tool brushing. Sensor data included data on cleaning fluid consumption, disinfectant consumption, and water flow.

[0131] The point cloud data and video data are fitted to obtain the fitted data;

[0132] The fitted data is input into a convolutional neural network model to obtain the relative spatial relationship data between the hand, tools, and consumables;

[0133] Based on a deep learning-based target detector and a convolutional neural network model, the system determines whether the medical staff's hands, tools, and consumables are aligned according to relative spatial relationship data. Consumables include water, cleaning agents, and disinfectants. If aligned, the relative spatial relationship data is input into the cleaning cleanliness scoring model. If not aligned, an alarm message is output to prompt the medical staff to repeat the cleaning and disinfection process.

[0134] In some embodiments, the step of acquiring video data and sensor data of healthcare workers performing cleaning and disinfection operations in a clean area includes:

[0135] Acquire pressure sensor data from the output end of the consumable container. The pressure sensor data includes the pressure value and duration.

[0136] Determine whether the pressure value and duration are within the preset pressure threshold and preset time threshold; if yes, input the consumable consumption data into the cleaning cleanliness scoring model; if no, issue an alarm message indicating insufficient consumable usage to the display device.

[0137] In some embodiments, obtaining the ID information of visiting medical personnel and allowing them to enter the ward for visits based on the ID information, wherein different monitoring areas are set up within the ward, includes the following steps:

[0138] The ID information of visiting medical staff can be obtained through biometric devices or ID card scanning devices.

[0139] Retrieve visitation tasks within the current time period based on ID information;

[0140] Grant work permissions to the corresponding ID based on the visitation task.

[0141] Based on the above-mentioned ward isolation method for preventing cross-infection, the present invention also provides a terminal device, such as... Figure 7As shown, it includes at least one processor 20; a display screen 21; and a memory 22, and may also include a communications interface 23 and a bus 24. The processor 20, display screen 21, memory 22, and communications interface 23 can communicate with each other via the bus 24. The display screen 21 is configured to display a preset user guide interface in the initial setup mode. The communications interface 23 can transmit information. The processor 20 can invoke logical instructions in the memory 22 to execute the methods described in the above embodiments.

[0142] Furthermore, the logical instructions in the aforementioned memory 22 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0143] The memory 22, as a computer-readable storage medium, can be configured to store software programs, computer-executable programs, such as program instructions or modules corresponding to the methods in the embodiments of this disclosure. The processor 20 executes functional applications and data processing by running the software programs, instructions, or modules stored in the memory 22, thereby implementing the methods in the above embodiments.

[0144] The memory 22 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 22 may include high-speed random access memory (RAM) and non-volatile memory. Examples include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, as well as transient storage media.

[0145] Furthermore, the specific process of loading and executing multiple instructions in the aforementioned storage medium and mobile terminal has been described in detail in the above method, and will not be repeated here.

[0146] In summary, compared with existing technologies, the present invention has the following beneficial effects: a method, device, storage medium, and terminal equipment for preventing cross-infection in patient wards, wherein the method includes: acquiring the ID information of visiting medical personnel, allowing them to enter the ward for visits based on the ID information, wherein different monitoring areas are set up within the ward; acquiring intrusion signals from the monitoring areas, generating cleaning and disinfection tasks based on the monitoring areas, and establishing a visitor infection risk dataset; the monitoring areas include: clean areas, generally contaminated areas, and heavily contaminated areas; acquiring video data and sensor data from the clean areas, inputting the video data and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection tasks are completed, wherein the cleaning cleanliness scoring model is formed by training a neural network; if the disinfection task is completed, unlocking the ward door lock and recording a cleaning completion mark on the visitor infection risk dataset. By scoring each cleaning and disinfection task using the cleaning cleanliness scoring model, the standardization and effectiveness of hand hygiene and equipment disinfection for medical personnel are effectively improved, reducing the incidence of hospital infections and ensuring the safety of patients and medical personnel.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for ward isolation to prevent cross-infection, characterized in that, The method includes: Obtain the ID information of visiting medical staff, and allow them to enter the ward for visits based on the ID information, wherein different monitoring areas are set up in the ward; The system acquires intrusion signals from monitored areas, generates cleaning and disinfection tasks based on these areas, and establishes a dataset of infection risks associated with patient visits. The monitored areas include: clean areas, moderately contaminated areas, and heavily contaminated areas. The system acquires video data and sensor data from the clean area, and inputs the video data and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task has been completed. The cleaning cleanliness scoring model is formed by training a neural network. If the disinfection task is completed, the ward door lock is unlocked, and a cleaning completion marker is entered into the visitor infection risk dataset. The step of acquiring video data and sensor data of the clean area and inputting the video data and sensor data into the cleaning cleanliness scoring model to determine whether the cleaning and disinfection task is completed includes: Acquire the video and sensor data of medical staff during cleaning and disinfection operations in the clean area; The video data and the sensor data are input into the cleaning cleanliness scoring model; Obtain the cleaning score data of the cleaning and disinfection task based on the cleaning and disinfection score model. The cleanliness score data is recorded in the visitation infection risk dataset; The step of determining whether the cleaning score data is above a preset standard scoring threshold, and acquiring the video data and sensor data of medical personnel performing cleaning and disinfection operations in the clean area, includes: The system acquires point cloud data and video data. The point cloud data is obtained by scanning the cleaning area with millimeter-wave radar. The video data includes video data of hand rubbing and video data of tool brushing. The sensor data includes cleaning solution consumption data, disinfectant consumption data, and water flow data. The point cloud data and the video data are fitted together to obtain fitted data; The fitted data is input into a convolutional neural network model to obtain the relative spatial relationship data between the hand, tools, and consumables; Based on a deep learning-based target detector and a convolutional neural network model, the system determines whether the medical staff's hands, tools, and consumables are aligned according to the relative spatial relationship data. The consumables include water, cleaning agents, and disinfectants. If aligned, the relative spatial relationship data is input into the cleaning cleanliness scoring model. If not aligned, an alarm message is output to prompt the medical staff to repeat the cleaning and disinfection process.

2. The ward isolation method for preventing cross-infection according to claim 1, characterized in that, The step of acquiring the video data and sensor data of medical staff during cleaning and disinfection operations in the clean area further includes: Acquire pressure sensor data at the output end of the consumable container, the pressure sensor data including pressure value and duration; Determine whether the pressure value and the duration are within the preset pressure threshold and preset time threshold; if yes, input the consumable consumption data into the cleaning cleanliness scoring model; if no, issue an alarm message indicating insufficient consumable usage to the display device.

3. The ward isolation method for preventing cross-infection according to claim 1, characterized in that, The steps of obtaining the ID information of visiting medical staff and allowing them to enter the ward for visits based on the ID information, wherein different monitoring areas are set up within the ward, include: The ID information of visiting medical staff can be obtained through biometric devices or ID card scanning devices. Retrieve visitation tasks within the current time period based on the ID information; Grant work permissions to the corresponding ID based on the aforementioned exploration task.

4. The ward isolation method for preventing cross-infection according to claim 3, characterized in that, The steps for obtaining the ID information of medical personnel through biometric devices include: The facial recognition information of medical staff is obtained through a facial recognition camera, and the ID information of the visiting medical staff is obtained based on the facial recognition information.

5. The ward isolation method for preventing cross-infection according to claim 1, characterized in that, The intrusion signal in the monitored area is at least one of image recognition signal, infrared signal, and pressure sensing signal.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps in the ward isolation method for preventing cross-infection as described in any one of claims 1 to 5.

7. A ward isolation device for preventing cross-infection, characterized in that, include: The first acquisition module is used to acquire the ID information of visiting medical staff and allow them to enter the ward for visits based on the ID information, wherein different monitoring areas are set up in the ward. The second acquisition module is used to acquire intrusion signals in the monitored area, generate cleaning and disinfection tasks based on the monitored area, and establish a dataset of infection risk from visits. The monitored areas include: clean areas, moderately polluted areas, and heavily polluted areas; The scoring module is used to acquire video data and sensor data from the clean area, and input the video data and sensor data into a cleaning cleanliness scoring model to determine whether the cleaning and disinfection task is completed. The cleaning cleanliness scoring model is formed by training a neural network. The step of acquiring video data and sensor data from the clean area and inputting the video data and sensor data into the cleaning cleanliness scoring model to determine whether the cleaning and disinfection task is completed includes: Acquire the video and sensor data of medical staff during cleaning and disinfection operations in the clean area; The video data and the sensor data are input into the cleaning cleanliness scoring model; Obtain the cleaning score data of the cleaning and disinfection task based on the cleaning and disinfection score model. The cleanliness score data is recorded in the visitation infection risk dataset; The step of determining whether the cleaning score data is above a preset standard scoring threshold, and acquiring the video data and sensor data of medical personnel performing cleaning and disinfection operations in the clean area, includes: The system acquires point cloud data and video data. The point cloud data is obtained by scanning the cleaning area with millimeter-wave radar. The video data includes video data of hand rubbing and video data of tool brushing. The sensor data includes cleaning solution consumption data, disinfectant consumption data, and water flow data. The point cloud data and the video data are fitted together to obtain fitted data; The fitted data is input into a convolutional neural network model to obtain the relative spatial relationship data between the hand, tools, and consumables; Based on a deep learning-based target detector and a convolutional neural network model, the system determines whether the medical staff's hands, tools, and consumables are aligned according to the relative spatial relationship data. The consumables include water, cleaning agents, and disinfectants. If aligned, the relative spatial relationship data is input into the cleaning cleanliness scoring model. If not aligned, an alarm message is output to prompt the medical staff to repeat the cleaning and disinfection process. The judgment module is used to unlock the ward door lock and record a cleaning completion mark on the visitor infection risk dataset if the disinfection task is completed.

8. A terminal device, characterized in that, include: Processor, memory, and communication bus; the memory stores a computer-readable program that can be executed by the processor; The communication bus enables communication between the processor and the memory; When the processor executes the computer-readable program, it implements the steps of the ward isolation method for preventing cross-infection as described in any one of claims 1-5.

Images