Hand hygiene compliance monitoring management system and method

Abstract

The embodiment of the invention relates to the technical field of medical health supervision, and discloses a hand hygiene compliance monitoring management system and management method.The method comprises the steps that firstly, images of different objects in the hand hygiene processing process are captured, and the complexity of the images (namely the computing power needed for processing) is evaluated; the images with high complexity are uploaded to a cloud server for deep hand hygiene compliance analysis; and for images with relatively low complexity or moderate complexity, the edge server is selected for processing, so that the efficiency is improved and the cloud burden is reduced. Besides, when the edge server or the cloud server sends out an early warning signal, remote control spot check is carried out on a specific target object, and the collected image is directly uploaded to the cloud server for detailed analysis. Therefore, by intelligently allocating the image analysis task to the cloud or the edge server, the processing efficiency and the resource utilization are effectively balanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical and health supervision, and particularly relates to a hand hygiene compliance monitoring management system and method. BACKGROUND

[0002] In a medical environment, hand hygiene is a key link in preventing and controlling hospital infections and ensuring the safety of patients and medical staff. Hand hygiene compliance monitoring refers to the monitoring and evaluation process of medical staff and other relevant personnel performing hand hygiene regulations. However, traditional hand hygiene compliance monitoring faces many challenges. In the past, it has relied on manual observation and recording. This method not only consumes a lot of manpower, but also has strong subjectivity and is prone to omissions, which makes it difficult to ensure the accuracy and integrity of the monitoring data.

[0003] With the development of technology, some hand hygiene monitoring systems based on image recognition technology have emerged. However, these systems often do not fully consider the complexity of the actual application scenario, and therefore cannot balance the monitoring efficiency and monitoring accuracy. SUMMARY

[0004] The main purpose of the present application is to provide a hand hygiene compliance monitoring management system and method, which aims to solve the technical problem that the prior art cannot simultaneously balance the monitoring efficiency and monitoring accuracy.

[0005] To achieve the above-mentioned purpose, in a first aspect, the present application provides a hand hygiene compliance monitoring management system, comprising:

[0006] a terminal acquisition device, comprising an image acquisition sensor and an image preliminary identification module, the image acquisition sensor is configured to acquire images in the hand hygiene process of medical staff in a hospital to obtain target images, and the image preliminary identification module is used to identify the complexity of the target images;

[0007] an edge server, comprising a first hand hygiene analysis algorithm model and a first early warning module, the first hand hygiene analysis algorithm model is configured to perform local analysis on the target images to obtain hand hygiene compliance data when the complexity is less than or equal to a preset value;

[0008] a cloud server, comprising a second hand hygiene analysis algorithm model and a second early warning module, the second hand hygiene analysis algorithm model is configured to perform cloud analysis on the target images to obtain hand hygiene compliance data when the complexity is greater than the preset value;

[0009] an inspection and feeling control terminal, comprising an inspection and feeling remote controller, which is used to remotely check target departments or target personnel so that the target images collected are directly uploaded to the cloud server for analysis and processing;

[0010] The user terminal is connected to the edge server and the cloud server, and is used for users to view hand hygiene compliance data in real time on the terminal APP or mini program.

[0011] In one possible implementation, the lower end of the terminal acquisition device is also provided with a control platform for pitch movement and yaw movement. The control platform is configured to adjust the pitch and / or yaw angles when the complexity of the target image is greater than a preset value so that the complexity of the target image is less than or equal to the preset value.

[0012] In a second aspect, an embodiment of the present application further provides a hand hygiene compliance monitoring and management method, which is applied to the hand hygiene compliance monitoring and management system as described in the first aspect, and the method includes:

[0013] Acquire images of different objects during hand hygiene treatment to obtain target images;

[0014] Performing preliminary recognition analysis on the target image to obtain a complexity level of the target image, where the complexity level is used to represent the amount of computing power required when processing the target image;

[0015] If the complexity of the target image is greater than a preset value, the target image is transmitted to a cloud server for hand hygiene compliance analysis to obtain hand hygiene compliance data;

[0016] If the complexity of the target image is less than or equal to a preset value, transmitting the target image to an edge server for hand hygiene compliance analysis to obtain hand hygiene compliance data;

[0017] In response to the early warning signal triggered by the edge server or cloud server, a remote spot check is performed on the target object so that the collected target image is directly uploaded to the cloud server for analysis and processing to obtain hand hygiene compliance data, wherein the early warning signal carries the target object information.

[0018] In a possible implementation, the lower end of the terminal acquisition device is further provided with a control platform for pitch and yaw motions. After performing preliminary recognition and analysis on the target image to obtain the complexity of the target image, the method further includes:

[0019] When the complexity of the target image is greater than a preset value, automatically adjusting the pitch and / or yaw angles so that the complexity of the target image is less than or equal to the preset value;

[0020] After automatically adjusting the pitch and / or yaw angle for a preset time period, if the complexity of the target image is still greater than a preset value, the angle of the terminal acquisition device is adjusted to a position with the least complexity.

[0021] In a possible implementation, the preliminary identification analysis on the target image obtains the complexity of the target image, including:

[0022] The preliminary analysis on the target image obtains the hand position deviation degree, the image definition, and the image brightness deviation degree of the target image.

[0023] The hand position deviation degree, the image definition, and the image brightness deviation degree of the target image are input into a preliminary identification model to obtain the complexity of the target image.

[0024] In a possible implementation, the preliminary analysis on the target image obtains the hand position deviation degree, including:

[0025] An image positioning algorithm is used to determine the center position of the hand position in the target image.

[0026] The pixel offset of the center of the hand position and the center of the image in the horizontal and vertical directions is calculated to obtain the horizontal and vertical offset, with the geometric center of the target image as the reference point.

[0027] According to the horizontal and vertical offset, a quantitative value of the hand position deviation degree is calculated through a preset mathematical formula.

[0028] In a possible implementation, the preliminary analysis on the target image obtains the image definition, including:

[0029] A Laplacian operator is used to perform convolution operation on the target image to obtain the Laplacian response value of the image.

[0030] The variance of the Laplacian response value is calculated, and the variance value is taken as a quantitative index of the image definition, and the variance value is positively correlated with the image definition.

[0031] In a possible implementation, the preliminary analysis on the target image obtains the image brightness deviation degree of the target image, including:

[0032] The brightness values of all pixel points in the target image are counted, and the average brightness value of the image is calculated.

[0033] A standard brightness value is set, the absolute value of the difference between the average brightness value and the standard brightness value is calculated, and the ratio of the absolute value to the standard brightness value is taken as a quantitative value of the image brightness deviation degree.

[0034] In a possible implementation, the preliminary identification model satisfies the following expression:

[0035]

[0036] Wherein, D is the hand part deviation degree in the target image, D max is the maximum value of the hand part deviation degree obtained by statistical analysis on a large number of sample images; C is the image definition, C max is the maximum value of the image definition obtained by statistical analysis on a large number of sample images; B is the image brightness deviation degree, B max is the maximum value of the image brightness deviation degree obtained by statistical analysis on a large number of sample images; W D , W C , W B are weight coefficients corresponding to the hand part deviation degree, the image definition and the image brightness deviation degree respectively.

[0037] In a possible implementation, the hand hygiene compliance data at least includes hand hygiene operation abnormality data, and the target object is remotely checked in response to the early warning signal triggered by the edge server or the cloud server, so that the target image collected is directly uploaded to the cloud server for analysis and processing to obtain the hand hygiene compliance data, including:

[0038] In the case that the hand hygiene operation abnormality data meets the set condition, a self-check instruction is obtained, and the self-check instruction carries a self-check time period;

[0039] According to the self-check instruction, the target image collected from the target object is directly uploaded to the cloud server for analysis and processing to obtain the hand hygiene compliance data in the self-check time period; or,

[0040] In the case that the hand hygiene operation abnormality data meets the set condition, a temporary check instruction triggered by a person is obtained;

[0041] According to the temporary check instruction, the target image collected from the target object is directly uploaded to the cloud server for analysis and processing to obtain the hand hygiene compliance data.

[0042] Differing from the prior art, the hand hygiene compliance monitoring and management method provided by the embodiments of the present application first captures images in the hand hygiene process of different objects, and evaluates the complexity (i.e. the size of the required computing power) of the images. For images with high complexity, the images are uploaded to a cloud server for in-depth hand hygiene compliance analysis; and for images with low or moderate complexity, the images are processed by an edge server to improve efficiency and reduce the burden on the cloud. In addition, when the edge server or the cloud server issues a warning signal, remote spot checks will be conducted on specific target objects, and the collected images will be directly uploaded to the cloud server for detailed analysis. In this way, by intelligently assigning image analysis tasks to the cloud or the edge server, the processing efficiency and resource utilization are effectively balanced. The cloud processing of complex images ensures the accuracy of the analysis, while the edge processing of simple images speeds up the overall response speed. At the same time, the remote spot checks under the warning mechanism enhance the flexibility and pertinence of supervision, which helps to timely discover and correct problems in hand hygiene compliance, thereby improving the overall health management level. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor based on the drawings shown.

[0044] Figure 1 The structural schematic diagram of the hand hygiene compliance monitoring and management system in some embodiments of the present application;

[0045] Figure 2 The flowchart of the hand hygiene compliance monitoring and management method in some embodiments of the present application;

[0046] Figure 3 The flowchart of the hand hygiene compliance monitoring and management method in some embodiments of the present application;

[0047] Figure 4 The hardware structural schematic diagram of the hand hygiene compliance monitoring and management system in some embodiments of the present application.

[0048] The implementation of the object of the present application, functional features and advantages will be further described with reference to the embodiments and the drawings. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0051] In addition, the descriptions of "first", "second", etc. in the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, "and / or" in the full text includes three solutions. Taking A and / or B as an example, it includes technical solution A, technical solution B, and technical solution that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0052] In healthcare settings, hand hygiene is a critical component in preventing and controlling nosocomial infections and ensuring the safety of patients and healthcare workers. However, traditional hand hygiene compliance monitoring faces numerous challenges. Previously, it relied on manual observation and record-keeping, a labor-intensive approach that is subject to subjectivity and omissions, making it difficult to ensure the accuracy and completeness of monitoring data.

[0053] With the development of technology, some hand hygiene monitoring systems based on image recognition technology have begun to emerge, but these systems often fail to fully consider the complexity of actual application scenarios, and thus cannot take into account both regulatory efficiency and accuracy.

[0054] like Figure 1 As shown, Figure 1 This is a schematic diagram of the structure of the hand hygiene compliance monitoring and management system in some embodiments of the present application. In the embodiments of the present application, the hand hygiene compliance monitoring and management system includes:

[0055] A terminal acquisition device 100, comprising an image acquisition sensor 110 configured to acquire images in a hand hygiene process of medical staff in a hospital to obtain target images, and an image preliminary identification module 120 configured to identify a complexity of the target images;

[0056] An edge server 200, comprising a first hand hygiene analysis algorithm model 210 and a first early warning module 220, wherein the first hand hygiene analysis algorithm model 210 is configured to analyze the target images locally to obtain hand hygiene compliance data when the complexity is less than or equal to a preset value.

[0057] A cloud server 300, comprising a second hand hygiene analysis algorithm model 310 and a second early warning module 320, wherein the second hand hygiene analysis algorithm model 310 is configured to analyze the target images in the cloud to obtain hand hygiene compliance data when the complexity is greater than the preset value.

[0058] A sensory control terminal 400, comprising a sensory remote controller 410, configured to remotely check a target department or a target staff to make the target images acquired to be directly uploaded to the cloud server 300 for analysis and processing.

[0059] A user terminal 500, connected to the edge server 200 and the cloud server 300, configured to allow a user to view hand hygiene compliance data in real time on a terminal APP or a mini program.

[0060] Specifically, the image acquisition sensor 110 can be a high-definition camera, etc., configured to acquire multi-angle and high-resolution images in a hand hygiene process of medical staff in a hospital in real time. The image preliminary identification module 120 can perform preliminary noise reduction, format conversion and image complexity identification processing on the images acquired, and then send the images to the cloud server 300 or the edge server 200 through a wireless communication module in an encrypted transmission mode.

[0061] The cloud server 300 is provided with a high-performance image analysis processor and a hand hygiene analysis algorithm model (i.e., the first hand hygiene analysis algorithm model 210) based on deep learning, which is trained by a large number of hand hygiene standard action and irregular action samples, can accurately identify hand hygiene operation steps, action specification degree and duration in the images, analyze and calculate hand hygiene compliance data, store the data in an associated database, and support early warning of hand hygiene compliance abnormal conditions according to preset rules.

[0062] The edge server 200 is provided with an image analysis processing unit with certain computing power and a lightweight hand hygiene analysis algorithm model (i.e., the second hand hygiene analysis algorithm model 310). This lightweight algorithm model is also based on deep learning technology, but is obtained through model compression, pruning and other optimization methods on the basis of the large-scale training model of the cloud server 300, to adapt to the relatively limited computing resources of the edge server. This algorithm model is trained with a large number of representative hand hygiene standard actions and rule-breaking action samples. Although its size and complexity are reduced compared to the model of the cloud server, it can still identify the hand hygiene operation steps, action specification degree and approximate duration in the image within a reasonable range of accuracy. When the complexity of the target image is less than or equal to the preset value, the edge server 200 uses the algorithm model to analyze the target image locally and quickly calculates the hand hygiene compliance data. The edge server 200 is also equipped with a local storage module for temporarily storing the hand hygiene compliance data obtained by analysis. At the same time, it will regularly synchronize these data to the database associated with the cloud server 300 to ensure the integrity and consistency of the data. In addition, the edge server 200 also has a warning function. It supports preliminary warning of hand hygiene compliance abnormalities according to preset basic rules. When an abnormal situation is detected, it will send a warning message to the cloud server 300 in time for the cloud server to further confirm and handle, and at the same time, the warning message can also be directly fed back to the relevant user terminal 500, realizing rapid response and processing.

[0063] The sensory control terminal 400 is a key component in the entire hand hygiene compliance monitoring management system for implementing targeted spot check function, and the core part is the sensory remote controller 410. The sensory control terminal 400 has a special wireless communication module, which can establish a stable and reliable connection with the terminal collection device 100 to realize remote control operation on the target department or target personnel. And the sensory remote controller 410 is designed with an intuitive operation interface, and the operator (such as the sensory person) can conveniently select the target department or target personnel that needs to be spot checked through the interface. After selecting the target, the sensory remote controller 410 will send a specific control instruction, which is transmitted to the terminal collection device 100 through the wireless communication module. After receiving the instruction, the terminal collection device 100 will immediately start the image collection function and collect the hand hygiene process of the specified target department or target personnel to obtain the corresponding target image. These collected target images will bypass the regular processing flow of the edge server 200 and be directly uploaded to the cloud server 300 through the high-speed network channel. After receiving the target image, the cloud server 300 will use its high-performance image analysis processor and hand hygiene analysis algorithm model based on deep learning to analyze the image in depth to obtain accurate hand hygiene compliance data. Such design enables the sensory control terminal 400 to perform timely and accurate spot check on specific targets when needed, enhancing the flexibility and targeting of the system and helping to more effectively supervise the hand hygiene situation in the hospital. In addition, the sensory control terminal 400 can also automatically lock the spot check target to complete self-service spot check after receiving the warning signal.

[0064] The user terminal 500 is an important terminal device for users to access hand hygiene compliance data conveniently. It maintains real-time communication with the edge server 200 and the cloud server 300 through stable network connections such as Wi-Fi, 4G / 5G, etc. The user terminal 500 supports multiple device forms, including but not limited to smartphones, tablets, laptops, etc., to meet the usage needs of different users in different scenarios. On the user terminal 500, users can choose to access the system through the terminal APP or applet. Both the terminal APP and applet can view hand hygiene compliance data in real time. These data can be presented in a visual form, such as column chart, line chart, pie chart, etc., clearly showing the hand hygiene compliance statistics of different time periods, different departments, and different medical staff. Users can also flexibly filter data according to their own needs, such as filtering by date range, department name, personnel name, etc., to more specifically view the data of interest. In addition, the user terminal 500 also has the function of receiving warning information. When the edge server 200 or the cloud server 300 detects hand hygiene compliance anomalies and sends a warning signal, the user terminal 500 will receive the notification in time, reminding the user to pay attention to the relevant issues. At the same time, users can also comment, feedback, etc. on the data viewed on the terminal APP or applet. These feedback information will be transmitted to the system background in time, providing a reference basis for further optimizing hand hygiene management.

[0065] In an embodiment, the lower end of the terminal acquisition device is further provided with a control gimbal for pitch movement and yaw movement, and the control gimbal is configured to adjust the pitch and / or yaw angle to make the complexity of the target image less than or equal to the preset value when the complexity of the target image is greater than the preset value.

[0066] Specifically, the control platform installed at the bottom of the terminal acquisition device enables pitch and yaw movement. Simply put, pitch allows the terminal acquisition device to rotate up and down, similar to a person nodding their head, thereby changing the vertical angle of the image. Yaw, similar to a person shaking their head, allows the device to rotate left and right, changing the horizontal angle of the image. When the system's preliminary image recognition module determines that the target image's complexity exceeds a preset value, it indicates that the image being acquired may be difficult to analyze due to factors such as angle and range. This may require more computing power than the edge server can handle, potentially affecting the accuracy of the analysis. This is when the control platform comes into play. The control platform adjusts its pitch and yaw angles based on a preset algorithm. For example, if the image complexity is due to the high shooting angle, making the details of the hand movements unclear, the control platform will adjust the pitch angle downward to bring the shooting angle closer to the hand movements, thereby obtaining a clearer and easier-to-analyze image. If the image complexity is due to the large shooting range, which includes too much irrelevant background information, the control platform may adjust the yaw angle to focus more closely on the hand movements and remove unnecessary interference. By adjusting the pitch and / or yaw angles in this way, the complexity of the recaptured target image is reduced to or equal to a preset value. This makes the adjusted image more suitable for local analysis by the edge server, improving analysis efficiency while fully utilizing the edge server's computing resources, reducing the pressure on the cloud server and ensuring the efficient and stable operation of the entire hand hygiene compliance monitoring and management system.

[0067] like Figures 1-3 As shown, the following takes the hand hygiene compliance monitoring and management system to perform the hand hygiene compliance monitoring and management method as an example for explanation. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order than here. Figure 3 The method includes the following steps S100 to S600:

[0068] S100, acquiring images of different objects during hand hygiene treatment to obtain target images;

[0069] Specifically, terminal data collection devices (such as cameras installed in key areas such as hospital wards, operating rooms, and nurse stations) capture images of different medical staff (i.e., different subjects) performing hand hygiene procedures (such as handwashing and disinfection). The captured images are referred to as target images and serve as the basis for subsequent analysis to determine the medical staff's compliance with hand hygiene.

[0070] S200, performing preliminary recognition analysis on the target image to obtain a complexity level of the target image, where the complexity level is used to represent the amount of computing power required for processing the target image;

[0071] Specifically, the target image is first subjected to preliminary analysis in multiple aspects, such as image sharpness analysis, brightness analysis, image validity analysis, etc. The greater the complexity of the image, the greater the computing power required for accurate and rapid analysis of the image.

[0072] In an embodiment, the preliminary identification analysis of the target image to obtain the complexity of the target image comprises: S210, performing preliminary analysis on the target image to obtain the hand position deviation degree, image sharpness, and image brightness deviation degree of the target image; S220, inputting the hand position deviation degree, image sharpness, and image brightness deviation degree of the target image into a preliminary identification model to obtain the complexity of the target image.

[0073] Specifically, when analyzing the hand position deviation degree, the center position of the hand position in the target image can be first determined by using an image positioning algorithm (such as an algorithm based on feature point detection, template matching, etc.). Then, taking the geometric center of the target image as a reference point, the pixel offset of the center of the hand position and the center of the image in the horizontal and vertical directions is calculated, and then a quantitative value of the hand position deviation degree is calculated according to a preset mathematical formula. The greater the hand position deviation degree, the more the position of the hand in the image is not centered, increasing the difficulty of subsequent analysis.

[0074] When analyzing the image sharpness, the target image can be subjected to convolution operation by using a Laplace operator to obtain the Laplace response value of the image. The Laplace operator can highlight the edge and detail information in the image. Then, the variance of the Laplace response value is calculated, and the variance value is taken as a quantitative index of the image sharpness. The greater the variance value, the sharper the image, which is more conducive to subsequent analysis; on the contrary, the smaller the variance value, the more blurred the image, increasing the processing difficulty.

[0075] When analyzing the image brightness deviation degree, the brightness values of all pixel points in the target image are counted, and the average brightness value of the image is calculated. A standard brightness value (which can be determined according to the actual application scenario and experience value) is set, the absolute value of the difference between the average brightness value and the standard brightness value is calculated, and the ratio of the absolute value to the standard brightness value is taken as a quantitative value of the image brightness deviation degree. The image brightness deviation degree reflects whether the brightness of the image conforms to the normal range. A too large deviation may affect the analyzability of the image.

[0076] After obtaining the hand position deviation degree, image sharpness, and image brightness deviation degree of the target image, the quantitative values of the hand position deviation degree, image sharpness, and image brightness deviation degree obtained above can be input into a preliminary identification model to obtain the complexity of the target image. The higher the complexity, the greater the computing power required for processing the image.

[0077] In an embodiment, the preliminary identification model satisfies the following expression:

[0078] wherein D is the hand part deviation degree in the target image, D max is the maximum value of the hand part deviation degree obtained by statistical analysis on a large number of sample images; C is the image definition, C max is the maximum value of the image definition obtained by statistical analysis on a large number of sample images; B is the image brightness deviation degree, B max is the maximum value of the image brightness deviation degree obtained by statistical analysis on a large number of sample images; W D , W C , and W B are weight coefficients corresponding to the hand part deviation degree, the image definition, and the image brightness deviation degree, respectively.

[0079] In this way, the embodiment of the present application accurately quantifies the complexity of the image by comprehensively considering factors such as the hand part deviation degree, the image definition, and the image brightness deviation degree. Moreover, the maximum values of the factors obtained by statistical analysis on a large number of sample images are used for normalization, and the weight coefficients are set, so that the influence of different factors on the complexity of the image can be more accurately reflected. The system based on the more accurate complexity evaluation analyzes the hand hygiene operation, thereby improving the accuracy of the hand hygiene compliance data.

[0080] During the monitoring process, if it is found that the hand part deviation degree has a greater influence on the complexity, the position or angle of the terminal acquisition device can be adjusted to reduce the hand part deviation, improve the image quality, and reduce the processing difficulty.

[0081] S300, in the case where the complexity of the target image is greater than a preset value, the target image is transmitted to a cloud server for hand hygiene compliance analysis to obtain hand hygiene compliance data;

[0082] When the complexity of the target image calculated in step S200 is greater than a preset threshold (preset value), it indicates that the processing difficulty of the image is greater, and the edge server may not be able to accurately and efficiently analyze it. At this time, the system transmits the target image to the cloud server through the network. The cloud server is equipped with a high-performance image analysis processor and a hand hygiene analysis algorithm model based on deep learning (trained on a large number of hand hygiene standard action and illegal action samples), which can perform in-depth analysis on complex target images, identify the hand hygiene operation steps, action specification degree, and duration information in the image, and then calculate the hand hygiene compliance data. These data can reflect whether the medical staff conforms to the standard requirements in this hand hygiene operation.

[0083] S400, in the case where the complexity of the target image is less than or equal to a preset value, transmitting the target image to an edge server for hand hygiene compliance analysis to obtain hand hygiene compliance data;

[0084] Unlike step S300, if the complexity of the target image determined in step S200 is less than or equal to a preset value, it indicates that the image is relatively simple, and the edge server has the ability to process the image. At this time, the system transmits the target image to the edge server. The edge server uses its own first hand hygiene analysis algorithm model (also based on deep learning and trained by relevant samples) to perform localized analysis on the target image, calculates the hand hygiene compliance data by recognizing the hand hygiene operation information in the image. This can reduce the burden of the cloud server and improve the overall processing efficiency of the system.

[0085] S500, in response to a warning signal triggered by the edge server or the cloud server, performing remote spot checks on the target object to make the collected target images directly uploaded to the cloud server for analysis and processing to obtain hand hygiene compliance data, wherein the warning signal carries target object information.

[0086] Specifically, during the process of analyzing and calculating hand hygiene compliance data by the edge server or the cloud server on the target image, if it is found that the hand hygiene operation abnormal data meets the set conditions (for example, the hand hygiene operation steps are missing, the operation time is too short, etc. to a certain extent), the server will issue a warning signal, and the warning signal carries the relevant information of the target object (such as specific medical staff or department).

[0087] At this time, the system will respond to the warning signal and perform remote spot check operation. There are two ways:

[0088] In the case where the hand hygiene operation abnormal data meets the set conditions, the pre-set self-check instruction (which carries the self-check time period) is obtained. The system will control the terminal collection device to collect images of the target object again within the specified self-check time period according to the self-check instruction. The collected target images are directly uploaded to the cloud server for analysis and processing to obtain more accurate hand hygiene compliance data and further confirm the hand hygiene situation.

[0089] In the case where the hand hygiene operation abnormal data meets the set conditions, the temporarily triggered spot check instruction is obtained. When a management personnel or a relevant personnel manually triggers the temporary spot check instruction, the system will control the terminal collection device to collect images of the target object according to the instruction, and directly upload the collected target images to the cloud server for analysis and processing to obtain hand hygiene compliance data, so as to timely discover and correct the non-standard hand hygiene behavior.

[0090] In an embodiment, the lower end of the terminal acquisition device is further provided with a control holder capable of pitch movement and yaw movement, and after the preliminary identification analysis of the target image to obtain the complexity of the target image, the method further comprises: automatically adjusting the pitch and / or yaw angle to make the complexity of the target image less than or equal to the preset value if the complexity of the target image is greater than the preset value; and adjusting the angle of the terminal acquisition device to the position with the minimum complexity after the preset time length of automatic adjustment of the pitch and / or yaw angle.

[0091] Specifically, when the terminal acquisition device acquires the target image and the preliminary identification analysis shows that the complexity of the target image is greater than the preset value, it indicates that the current image has a large processing difficulty due to the angle, range, etc., which is not conducive to subsequent hand hygiene compliance analysis. At this time, the control holder is automatically started. The control holder has the functions of pitch movement (up and down rotation) and yaw movement (left and right rotation). It automatically adjusts the pitch angle and / or yaw angle according to a certain algorithm. For example, if the image complexity is caused by too high shooting angle, which makes the details of the hand unclear, the control holder will adjust the pitch angle downward; if the shooting range is too wide and contains too many irrelevant backgrounds, the control holder may adjust the yaw angle to focus more on the hand movement. Through these angle adjustments, it is expected that the complexity of the re-acquired target image can be reduced to the preset value or below, so that the edge server can perform local analysis, reduce the dependence on the cloud server, improve the analysis efficiency, and reduce the system cost.

[0092] If the control holder automatically adjusts the pitch and / or yaw angle for a preset time length (which is pre-set according to the actual situation), and the complexity analysis of the target image again shows that the complexity is still greater than the preset value, it indicates that the current adjustment strategy does not achieve the ideal effect. At this time, the system will take further measures to adjust the angle of the terminal acquisition device to the position with the minimum complexity. The image acquired at this position may still have a certain complexity, but it is the relatively easiest to process under the current conditions, and then the image is transmitted to the cloud server for analysis to obtain the hand hygiene compliance data. In this way, through the automatic adjustment and optimization strategy of the control holder, the complexity of the target image is reduced as much as possible locally, the resources of the edge server and the cloud server are reasonably utilized, and the overall performance of the hand hygiene compliance monitoring and management system is improved.

[0093] Based on this, the method for monitoring and managing hand hygiene compliance provided by the embodiments of the present application first captures images in the hand hygiene process of different objects, and evaluates the complexity of the images (i.e. the size of the required computing power). For images with high complexity, they are uploaded to the cloud server for in-depth hand hygiene compliance analysis; and for images with low or moderate complexity, edge servers are selected for processing to improve efficiency and reduce the burden on the cloud. In addition, when the edge server or the cloud server issues a warning signal, remote spot checks will be carried out for specific target objects, and the collected images will be directly uploaded to the cloud server for detailed analysis. In this way, by intelligently assigning image analysis tasks to the cloud or edge servers, the processing efficiency and resource utilization are effectively balanced. The use of cloud processing for complex images ensures the accuracy of the analysis, while the edge processing of simple images speeds up the overall response speed. At the same time, remote spot checks under the warning mechanism enhance the flexibility and pertinence of supervision, helping to timely discover and correct problems in hand hygiene compliance, thereby improving the overall level of health management.

[0094] As shown in Figure 4 , Figure 4 is a schematic diagram of the hardware structure of the hand hygiene compliance monitoring and management system in some embodiments of the present application. The hand hygiene compliance monitoring and management system provided by the embodiments of the present application further includes a memory 1000 and a processor 2000, wherein the memory 1000 is used to store computer readable instructions, and the processor 2000 is used to call the computer readable instructions to execute the hand hygiene compliance monitoring and management method as described above.

[0095] The processor 2000 is configured to provide computing and control capabilities to control the hand hygiene compliance monitoring and management system to perform corresponding tasks, for example, to control the hand hygiene compliance monitoring and management system to perform the hand hygiene compliance monitoring and management method in any of the method embodiments described above. The method includes: obtaining target images in the hand hygiene process of different objects; performing preliminary identification analysis on the target images to obtain the complexity of the target images, the complexity being used to represent the size of the required computing power when the target images are processed; in the case where the complexity of the target images is greater than a preset value, transmitting the target images to a cloud server for hand hygiene compliance analysis to obtain hand hygiene compliance data; in the case where the complexity of the target images is less than or equal to the preset value, transmitting the target images to an edge server for hand hygiene compliance analysis to obtain hand hygiene compliance data; in response to a warning signal triggered by the edge server or the cloud server, performing remote spot checks on target objects so that the collected target images are directly uploaded to the cloud server for analysis and processing to obtain hand hygiene compliance data, wherein the warning signal carries target object information.

[0096] The processor 2000 can be a general processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; and can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0097] The memory 1000, as a non-transitory computer readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the hand hygiene compliance monitoring management method in the embodiments of the present application. The processor 2000 can realize the hand hygiene compliance monitoring management method in any of the method embodiments by running the non-transitory software programs, instructions and modules stored in the memory 1000.

[0098] Specifically, the memory 1000 can include a volatile memory (VM), such as a random access memory (RAM); the memory 1000 can also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), or other non-transitory solid-state storage devices; and the memory 1000 can also include a combination of the above types of memories.

[0099] In summary, the hand hygiene compliance monitoring management system of the present application adopts the technical solutions of any one of the hand hygiene compliance monitoring management method embodiments described above, and therefore at least has the beneficial effects brought by the technical solutions of the above embodiments, which will not be repeated here.

[0100] The embodiments of the present application further provide a computer readable storage medium, for example, a memory including program codes, which can be executed by a processor to complete the hand hygiene compliance monitoring management method in the above embodiments. For example, the computer readable storage medium can be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CDROM), a magnetic tape, a floppy disk and an optical data storage device, etc.

[0101] The embodiments of the present application further provide a computer program product including one or more program codes stored in a computer readable storage medium. The processor of the hand hygiene compliance monitoring management system reads the program codes from the computer readable storage medium, and the processor executes the program codes to complete the steps of the hand hygiene compliance monitoring management method provided in the above embodiments.

[0102] Those skilled in the art can understand that all or part of the steps of the above embodiments can be completed by hardware, or by program codes related hardware, and the program can be stored in a computer readable storage medium. The storage medium mentioned above can be a Read-Only Memory, a magnetic disk or an optical disk, etc.

[0103] It should be noted that the above described device embodiments are only schematic, and the units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0104] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a general hardware platform, and of course, can also be implemented by hardware. Those skilled in the art can understand that all or part of the processes in the above embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above embodiments. The storage medium can be a magnetic disk, an optical disk, a Read-Only Memory (ROM) or a Random Access Memory (RAM), etc.

[0105] The above merely describes the preferred embodiments of the present application, and is not intended to limit the patent scope of the present application. Any equivalent structural changes made according to the content of the present application specification and drawings, or direct / indirect application in other related technical fields, are included in the patent protection scope of the present application.

Claims

1. A hand hygiene compliance monitoring and management system, characterized in that: include: The terminal acquisition device includes an image acquisition sensor and an image preliminary recognition module. The image acquisition sensor is configured to acquire images of medical staff during hand hygiene treatment in the hospital to obtain a target image. The image preliminary recognition module is used to identify the complexity of the target image. an edge server, comprising a first hand hygiene analysis algorithm model and a first early warning module, wherein the first hand hygiene analysis algorithm model is configured to perform a localized analysis on the target image to obtain hand hygiene compliance data when the complexity level is less than or equal to a preset value; a cloud server comprising a second hand hygiene analysis algorithm model and a second early warning module, wherein the second hand hygiene analysis algorithm model is configured to perform cloud analysis on the target image to obtain hand hygiene compliance data when the complexity level exceeds a preset value; The sensor control terminal includes a sensor remote control for remotely spot-checking target departments or target personnel so that the captured target images are directly uploaded to the cloud server for analysis and processing; The user terminal is connected to the edge server and the cloud server, and is used for users to view hand hygiene compliance data in real time on the terminal APP or mini program.

2. The hand hygiene compliance monitoring and management system according to claim 1, wherein: The lower end of the terminal acquisition device is also provided with a control platform for pitch and yaw movement. The control platform is configured to adjust the pitch and / or yaw angles when the complexity of the target image is greater than a preset value so that the complexity of the target image is less than or equal to the preset value.

3. A hand hygiene compliance monitoring and management method, characterized in that: Applied to the hand hygiene compliance monitoring and management system according to claim 1, the method comprises: Acquire images of different objects during hand hygiene treatment to obtain target images; Performing preliminary recognition analysis on the target image to obtain a complexity level of the target image, where the complexity level is used to represent the amount of computing power required when processing the target image; If the complexity of the target image is greater than a preset value, the target image is transmitted to a cloud server for hand hygiene compliance analysis to obtain hand hygiene compliance data; If the complexity of the target image is less than or equal to a preset value, transmitting the target image to an edge server for hand hygiene compliance analysis to obtain hand hygiene compliance data; In response to the early warning signal triggered by the edge server or cloud server, a remote spot check is performed on the target object so that the collected target image is directly uploaded to the cloud server for analysis and processing to obtain hand hygiene compliance data, wherein the early warning signal carries the target object information.

4. The hand hygiene compliance monitoring and management method according to claim 3, wherein: The lower end of the terminal acquisition device is also provided with a control platform for pitch and yaw movement. After performing preliminary recognition and analysis on the target image to obtain the complexity of the target image, the following steps are further included: When the complexity of the target image is greater than a preset value, automatically adjusting the pitch and / or yaw angles so that the complexity of the target image is less than or equal to the preset value; After automatically adjusting the pitch and / or yaw angle for a preset time period, if the complexity of the target image is still greater than a preset value, the angle of the terminal acquisition device is adjusted to a position with the least complexity.

5. The hand hygiene compliance monitoring and management method according to claim 3, wherein: The performing preliminary recognition analysis on the target image to obtain the complexity of the target image includes: Performing a preliminary analysis on the target image to obtain a hand position deviation degree, image clarity, and image brightness deviation degree of the target image; The hand position deviation degree, image clarity and image brightness deviation degree of the target image are input into a preliminary recognition model to obtain the complexity degree of the target image.

6. The hand hygiene compliance monitoring and management method according to claim 5, wherein: The preliminary analysis of the target image to obtain the degree of hand deviation of the target image includes: Use image localization algorithm to determine the center position of the hand in the target image; Taking the geometric center of the target image as the reference point, the pixel offsets between the center of the hand and the center of the image in the horizontal and vertical directions are calculated to obtain the horizontal and vertical offsets; According to the horizontal and vertical offsets, a quantitative value of the degree of deviation of the hand position is calculated using a preset mathematical formula.

7. The hand hygiene compliance monitoring and management method according to claim 6, wherein: The performing preliminary analysis on the target image to obtain image clarity includes: The Laplace operator is used to perform convolution operation on the target image to obtain the Laplace response value of the image. The variance of the Laplace response value is calculated and used as a quantitative indicator of image clarity. The variance value is positively correlated with the clarity of the image.

8. The hand hygiene compliance monitoring and management method according to claim 7, wherein: The performing preliminary analysis on the target image to obtain the image brightness deviation degree of the target image includes: Count the brightness values ​​of all pixels in the target image and calculate the average brightness value of the image; A standard brightness value is set, the absolute value of the difference between the average brightness value and the standard brightness value is calculated, and the ratio of the absolute value to the standard brightness value is used as a quantitative value of the image brightness deviation degree.

9. The hand hygiene compliance monitoring and management method according to claim 8, wherein: The preliminary recognition model satisfies the following expression: Where D is the deviation degree of the hand position in the target image, D max is the maximum value of hand position deviation obtained by statistical analysis of a large number of sample images; C is the image clarity, C max is the maximum value of image clarity obtained by statistical analysis of a large number of sample images; B is the degree of image brightness deviation, B max is the maximum value of the image brightness deviation obtained by statistical analysis of a large number of sample images; W D 、W C 、W B are the weight coefficients corresponding to the degree of deviation of hand position, image clarity, and image brightness respectively.

10. The hand hygiene compliance monitoring and management method according to claim 3, wherein: The hand hygiene compliance data includes at least hand hygiene operation abnormality data. The remote spot check of the target object is performed in response to the early warning signal of the edge server or the cloud server so that the collected target image is directly uploaded to the cloud server for analysis and processing to obtain the hand hygiene compliance data, including: When the hand hygiene operation abnormality data meets the set conditions, a pre-set self-service spot check instruction is obtained, and the self-service spot check instruction carries a self-service spot check time period; According to the self-service spot check instruction, the target image collected from the target object is directly uploaded to the cloud server within the self-service spot check time period for analysis and processing to obtain hand hygiene compliance data; or, When the abnormal data of hand hygiene operation meets the set conditions, obtain the temporary spot check instruction triggered manually; According to the temporary spot check instruction, the target image collected from the target object is directly uploaded to the cloud server for analysis and processing to obtain hand hygiene compliance data.

Images