Medical waste supervision method and device based on AI video engine technology

Abstract

The present invention discloses a medical waste supervision method and device based on AI video engine technology, which relates to the technical field of medical waste supervision. The method comprises obtaining appropriate opening areas corresponding to graph nodes in each grid space of an interactive area space. When temporarily storing medical waste, a real-time opening schematic line of the waste container is drawn according to the real-time coordinates of the moving point, and the real-time opening schematic line is compared with the appropriate opening area corresponding to the key node of the human hand as the graph node in the corresponding grid space to determine the triggering of an alarm mechanism. By constructing an interactive area space between the human body and the waste container, and using a lightweight real-time model to mark the key node of the human hand and the moving point of the waste container to determine the appropriate opening area corresponding to each grid space, the waste container opening schematic line and the appropriate opening area are compared in real time to determine the triggering of the alarm mechanism, thereby realizing real-time and accurate monitoring of the opening status of the waste container and reducing the risk of medical waste spillage and pathogen transmission.

Description

Technical Field

[0001] The present invention belongs to the field of medical waste supervision technology, specifically a medical waste supervision method and device based on AI video engine technology. Background Art

[0002] Properly managed medical waste disposal is crucial in healthcare facilities. Medical waste contains numerous bacteria, viruses, and other hazardous substances, which, if improperly handled, can pose a serious threat to the environment and human health. Medical waste management typically involves setting up temporary storage points or areas within healthcare facilities, where medical staff regularly collect and dispose of medical waste.

[0003] However, the supervision of medical waste storage areas mainly relies on manual inspections and video surveillance playback, and waste containers generally use infrared sensing or pressure sensing automatic opening designs. However, although such sensing containers can reduce the risk of operator contact contamination, they cannot determine the matching of the opening state and hand movements in real time. As a result, when the waste container is opened by sensing, the sensing-opened container may not be fully opened in actual use. The existing supervision method mainly relies on manual inspections and video surveillance playback, which makes it difficult to detect this problem in real time. For example, the risk of waste spillage and the spread of pathogens cannot be curbed in time. In addition, simple video surveillance can only record the picture and lacks the ability to intelligently analyze the video content. The abnormal opening of the sensing container is not included in the monitoring scope, which further amplifies the safety risks. Based on this, a medical waste supervision method and device based on AI video engine technology are proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a medical waste supervision method and device based on AI video engine technology, which solves the technical problem that simple video surveillance can only record the picture but lacks the ability to intelligently analyze the video content.

[0005] The medical waste supervision method and device based on AI video engine technology include the following steps:

[0006] Step 1: Collect video data of interactive events in the medical waste temporary storage area;

[0007] Step 2: Generate the interaction area space between the human body and the waste container;

[0008] Step 3: Mark the key nodes of the human hand and the moving points of the waste container in the medical waste temporary storage area, and then obtain graph nodes and additional nodes;

[0009] Step 4: Evenly divide the interaction area into multiple identical grid spaces. Analyze the coordinates of the moving points of the waste container when the graph nodes in the interaction event video data are in different grid spaces. Obtain the appropriate opening area corresponding to each grid space in the interaction area:

[0010] Step 5: During the temporary storage of medical waste, when the key node of the human hand enters the interactive area space, the real-time coordinates of the grid space where the key node of the human hand is located and the moving point of the waste container are obtained in real time. The real-time opening schematic line of the waste container is drawn according to the real-time coordinates of the moving point, and it is compared with the appropriate opening area corresponding to the key node of the human hand as a graph node in the corresponding grid space to determine whether to trigger the alarm mechanism.

[0011] As a further solution of the present invention, the specific method of generating the interaction area space between the human body and the waste container is:

[0012] Taking the edge of the waste container as the benchmark, the horizontal range is expanded outward by 0.5 meters, and the vertical range is expanded up and down by 0.3 meters according to the height of the container, thereby generating an interactive area space between the human body and the waste container.

[0013] As a further solution of the present invention: the specific method of obtaining the graph nodes and additional nodes is:

[0014] The center point of the waste container top cover is used as the moving point of the waste container; the wrist node in the key node of the human hand graph node is used as the graph node, and the moving point of the waste container is used as the additional node.

[0015] As a further solution of the present invention, a specific method for obtaining the appropriate opening areas corresponding to the graph nodes in each grid space of the interactive area space is as follows:

[0016] S1: Select one grid space from each grid space in the interaction area space as a calibration grid without replacement; mark the coordinates of the moving point of the waste container in the calibration grid of the graph node in the multiple interaction event video data as Ya (Yxa, Yya, Yza), and the grid positioning point is the center point in each grid space, where a is the coordinates of the moving point of the waste container in the multiple interaction event video data when the graph node is in the calibration grid;

[0017] S2: Analyze the horizontal coordinate, vertical coordinate and vertical coordinate in the position coordinates of each moving point to obtain the reference horizontal coordinate value Hx, reference vertical coordinate Hy and reference vertical coordinate Hz corresponding to the moving point when the graph node is in the calibration grid, obtain the standard deviations Ux, Uy and Uz of the horizontal coordinate Yxa, vertical coordinate Yya and vertical coordinate Yza, use EA (Hx + Ux, Hy + Uy, Hz + Uz) as the upper limit point EA corresponding to the moving point when the graph node is in the calibration grid, use EB (|Hx - Ux|, |Hy - Uy|, |Hz - Uz|) as the lower limit point EB corresponding to the moving point when the graph node is in the calibration grid, and combine the moving point of the waste container to obtain the appropriate opening area corresponding to the graph node in the calibration grid;

[0018] S3: Repeat steps S1-S2 to obtain the appropriate opening areas corresponding to the graph nodes in each grid space of the interaction area space.

[0019] As a further solution of the present invention, a specific method for obtaining the reference abscissa value, reference ordinate value, and reference vertical coordinate value corresponding to the moving point of the graph node in the calibration grid is as follows:

[0020] Obtain the number v of values in the horizontal coordinate Yxa of each moving point position coordinate that satisfy |Yxa-Yxp|≥Y2. When the number v is greater than the preset threshold Y1, define the mean value Yxp of Yxa as the reference horizontal coordinate value Hx corresponding to the moving point when the graph node is in the calibration grid. When the number v is less than the preset threshold Y1, define the mean of the maximum and minimum values in Yxa as the reference horizontal coordinate value Hx corresponding to the moving point when the graph node is in the calibration grid.

[0021] The same analysis method is used to analyze the ordinate Yya and vertical coordinate Yza of the position coordinates of each moving point, and then the reference ordinate Hy and reference vertical coordinate Hz corresponding to the moving point when the graph node is in the calibration grid are obtained.

[0022] As a further solution of the present invention, the appropriate opening area corresponding to the graph node in the calibration grid is obtained by combining the moving points of the waste container:

[0023] Draw a perpendicular line from the moving point of the waste container to the rotation axis of the container top cover, and take the intersection of the perpendicular line and the rotation axis as the rotation axis point Z. Connect the upper limit point EA and the lower limit point EB corresponding to the moving point of the graph node in the calibration grid to the rotation axis point Z respectively, and connect the upper limit point EA and the lower limit point EB at the same time to obtain the appropriate opening area corresponding to the graph node in the calibration grid.

[0024] As a further solution of the present invention: the specific method of determining the triggering of the alarm mechanism is:

[0025] Determine whether the real-time opening schematic line is in the corresponding moderate opening area. If so, do not do anything. If not, obtain the key nodes of the human hand as the corresponding real-time opening schematic lines of the graph nodes in the interactive area space for e consecutive times, and obtain the number g of the real-time opening schematic lines in the corresponding moderate opening area. When g is greater than the preset value Y3, do not do anything. When g is less than or equal to the preset value Y3, trigger the alarm mechanism, and the value of e is 4.

[0026] Medical waste monitoring devices based on AI video engine technology include:

[0027] The data collection end collects video data of interactive events in the medical waste temporary storage area;

[0028] An interactive area space generating end generates an interactive area space between the human body and the waste container;

[0029] At the graph node and additional node marking end, key nodes of the human hand and the moving points of the waste container in the medical waste temporary storage area are marked to obtain graph nodes and additional nodes;

[0030] The moderate opening area acquisition end evenly divides the interaction area space into multiple identical grid spaces, and obtains the moderate opening area corresponding to each graph node in each grid space of the interaction area space:

[0031] At the alarm mechanism triggering judgment end, when medical waste is temporarily stored, when the key node of the human hand enters the interactive area space, the real-time coordinates of the grid space where the key node of the human hand is located and the moving point of the waste container are obtained in real time to draw the real-time opening schematic line of the waste container, and compare it with the appropriate opening area corresponding to the key node of the human hand as a graph node in the corresponding grid space to determine the triggering of the alarm mechanism.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] (1) The present invention, through the collection of video data of interactive events in the medical waste temporary storage area and the precise marking of key nodes of human hands and movement points of waste containers, combined with the grid division and data analysis of the interactive area space, can accurately determine the appropriate opening area of the waste container at different positions, and realize the precise monitoring and judgment of the opening status of the waste container. Compared with the traditional supervision method, the accuracy and reliability of supervision are greatly improved;

[0034] (2) The present invention can effectively reduce false alarms by determining whether to trigger an alarm through multiple consecutive judgments and statistics when the real-time opening schematic line of the waste container is not in the corresponding appropriate opening area;

[0035] (3) The present invention constructs the interaction area space between the human body and the waste container, and uses a lightweight real-time model to mark the key nodes of the human hand and the moving points of the waste container to determine the appropriate opening area corresponding to each grid space. When the human hand enters the interaction area, the waste container opening schematic line and the appropriate opening area are compared in real time to determine whether to trigger the alarm mechanism. This effectively overcomes the lag of existing supervision methods and realizes real-time and accurate monitoring of the opening status of the waste container. It can timely warn of abnormal situations, reduce the risk of medical waste spillage and pathogen transmission, and improve supervision efficiency, providing a strong guarantee for the standardized and intelligent supervision of medical waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 Schematic diagram of the system framework structure of the present invention;

[0037] Figure 2 Schematic diagram of the device structure of the present invention;

[0038] Figure 3 Schematic diagram of the structure of the moderate opening area D1 of the present invention. DETAILED DESCRIPTION

[0039] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] Example 1: Please refer to Figure 1 and Figure 3 , this application provides a medical waste supervision method based on AI video engine technology, including the following steps:

[0041] Step 1: Deploy multi-angle cameras in the medical waste temporary storage area to fully cover the area and collect video data of interactive events in the area. Video data of interactive events refers to video data of medical staff placing medical waste;

[0042] Rationally deploy multi-angle cameras in the medical waste storage area to achieve full coverage of the area, focusing on collecting video data of interactions such as medical staff placing medical waste, providing basic information for subsequent analysis;

[0043] Step 2: Obtain the interaction area between the human body and the waste container. The specific method is:

[0044] Taking the edge of the waste container as the benchmark, the horizontal range is expanded outward by 0.5 meters, and the vertical range is expanded up and down by 0.3 meters according to the height of the container, thus forming a three-dimensional interactive area space, thereby generating an interactive area space between the human body and the waste container.

[0045] Step 3: Use a lightweight real-time model, such as the MediaPipe Pose or HRNet model, to mark key hand nodes and movement points of waste containers in the medical waste storage area. This will yield graph nodes and additional nodes. The specific method is as follows:

[0046] The center point of the waste container top cover is used as the moving point of the waste container; the wrist node in the key node of the human hand is used as the graph node, and the position point and moving point of the waste container are used as additional nodes;

[0047] Step 4: Evenly divide the interaction area into multiple identical grid spaces. Analyze the coordinates of the moving points of the waste container when the graph nodes in the interaction event video data are in different grid spaces. Obtain the appropriate opening area corresponding to each grid space in the interaction area. The specific method is as follows:

[0048] S1: Select one grid space from each grid space in the interaction area space as a calibration grid without replacement; mark the coordinates of the moving point of the waste container in the calibration grid of the graph node in the multiple interaction event video data as Ya (Yxa, Yya, Yza), and the grid positioning point is the center point in each grid space, where a is the coordinates of the moving point of the waste container in the multiple interaction event video data when the graph node is in the calibration grid;

[0049] S2: Obtain the numerical value Yxv that meets the preset filtering condition AI in the horizontal coordinate Yxa of the position coordinate of each moving point, where v is the number of numerical values in Yxa that meet the preset filtering condition AI, and compare the number v with the preset threshold value Y1. When the number v is greater than the preset threshold value Y1, it means that the number of numerical values in the horizontal coordinate Yxa that meet the preset filtering condition AI is large, and the mean value of Yxa is representative. Then, the mean value Yxp of Yxa is defined as the reference horizontal coordinate numerical value Hx corresponding to the moving point when the graph node is in the calibration grid. When the number v is less than the preset threshold value Y1, it means that the number of numerical values in Yxa that meet the preset filtering condition AI is small, and the mean value of Yxa is not representative. Then, the mean of the maximum and minimum values in Yxa is defined as the reference horizontal coordinate numerical value Hx corresponding to the moving point when the graph node is in the calibration grid;

[0050] Here, the preset condition AI is specifically: |Yxa-Yxp|≥Y2, where Y2 is the preset value, and the specific values of Y1 and Y2 are formulated by relevant personnel based on actual needs;

[0051] The same analysis method is used to analyze the ordinate Yya and vertical coordinate Yza of the position coordinates of each moving point, and then the reference ordinate Hy and reference vertical coordinate Hz corresponding to the moving point when the graph node is in the calibration grid are obtained;

[0052] Obtain the standard deviations Ux, Uy, and Uz of the horizontal coordinate Yxa, the vertical coordinate Yya, and the vertical coordinate Yza, and use EA (Hx+Ux, Hy+Uy, Hz+Uz) as the upper limit EA corresponding to the moving point of the graph node in the calibration grid, and use EB (|Hx-Ux|, |Hy-Uy|, |Hz-Uz|) as the lower limit EB corresponding to the moving point of the graph node in the calibration grid;

[0053] Draw a perpendicular line from the moving point of the waste container to the rotation axis of the container top cover, and use the intersection of the perpendicular line and the rotation axis as the rotation axis point Z. Connect the upper limit point EA and the lower limit point EB corresponding to the moving point of the graph node in the calibration grid to the rotation axis point Z respectively. At the same time, connect the upper limit point EA and the lower limit point EB to obtain the appropriate opening area D1 corresponding to the graph node in the calibration grid;

[0054] S3: Repeat steps S1-S2 to obtain the appropriate opening area Dr corresponding to each grid space of the graph node in the interaction area space, where r refers to different grid spaces in the interaction area space;

[0055] By collecting video data of interactive events in the medical waste storage area and accurately marking the key nodes of human hands and the movement points of waste containers, combined with the grid division and data analysis of the interactive area space, it is possible to accurately determine the appropriate opening areas of waste containers in different positions, and achieve accurate monitoring and judgment of the opening status of waste containers. Compared with traditional supervision methods, this greatly improves the accuracy and reliability of supervision.

[0056] Step 5: When medical waste is temporarily stored, when the key node of the human hand enters the interactive area space, the grid space where the key node of the human hand is located is obtained in real time, and then the corresponding grid space where the graph node is located is obtained, and the real-time coordinates of the moving point of the waste container are obtained in real time. The real-time opening schematic line of the waste container is drawn according to the real-time coordinates of the moving point, and the real-time opening schematic line of the waste container is compared with the appropriate opening area corresponding to the key node of the human hand as the graph node in the corresponding grid space to determine whether the real-time opening schematic line is in the corresponding appropriate opening area. If it is, no processing is performed. If not, the number g of the real-time opening schematic lines in the corresponding appropriate opening area is obtained according to the real-time opening schematic lines corresponding to the key node of the human hand as the graph node in the interactive area space for e consecutive times. When g is greater than the preset value Y3, no processing is performed. When g is less than or equal to the preset value Y3, an alarm mechanism is triggered to remind the waste container personnel that there is an abnormality in the opening of the waste container, and an abnormality information is sent to the supervisor at the same time. The specific value of the preset value Y3 is formulated by relevant personnel according to actual needs, and the value of e is 4;

[0057] An alarm mechanism based on real-time coordinate comparison and statistical analysis has been established. When the real-time opening schematic line of the waste container is not in the corresponding appropriate opening area, multiple consecutive judgments and statistics are used to decide whether to trigger the alarm. This can effectively reduce false alarms and promptly remind the disposal personnel and supervisors.

[0058] When an abnormal opening state of a waste container is detected, the alarm can be triggered in time according to the set alarm mechanism to remind the disposal personnel and supervisors so that timely measures can be taken to deal with it, effectively avoiding the risks of medical waste spillage, pathogen transmission, etc. caused by improper opening of the waste container. While ensuring the safety and standardization of the medical waste disposal process, it also realizes the precise supervision of the container opening state during the medical waste disposal process.

[0059] Example 2: Please refer to Figure 2 As a second embodiment of the present invention, a medical waste monitoring device based on AI video engine technology is provided. The device is used to apply the aforementioned solid-state hard disk control method, specifically including:

[0060] On the data collection side, multi-angle cameras are deployed in the medical waste temporary storage area to fully cover the area and collect video data of interactive events in the area. Video data of interactive events refers to video data of medical staff placing medical waste.

[0061] The interaction area space generation end is based on the edge of the waste container, expanding outward by 0.5 meters as the horizontal range, and vertically expanding up and down by 0.3 meters according to the height of the container, thereby forming a three-dimensional interaction area space, thereby generating the interaction area space between the human body and the waste container;

[0062] The graph node and the additional node mark end, the center point of the waste container top cover is used as the moving point of the waste container; the wrist node in the graph node human hand key node is used as the graph node, and the position point and moving point of the waste container are used as additional nodes;

[0063] The moderate opening area acquisition end evenly divides the interaction area space into multiple identical grid spaces, and obtains the moderate opening area corresponding to each graph node in each grid space of the interaction area space:

[0064] The alarm mechanism triggering judgment end, when the key node of the human hand enters the interactive area space during the temporary storage of medical waste, obtains the real-time coordinates of the grid space where the key node of the human hand is located and the moving point of the waste container in real time, draws the real-time opening schematic line of the waste container, compares it with the appropriate opening area corresponding to the key node of the human hand as a graph node in the corresponding grid space, and determines to trigger the alarm mechanism;

[0065] When medical waste is temporarily stored, the grid space where the key node of the human hand is located is obtained in real time, and then the corresponding grid space where the graph node is located is obtained, the real-time coordinates of the moving point of the waste container are obtained in real time, and the real-time opening schematic line of the waste container is drawn according to the real-time coordinates of the moving point. The real-time opening schematic line of the waste container is compared with the appropriate opening area corresponding to the key node of the human hand as the graph node in the corresponding grid space to determine whether the real-time opening schematic line is in the corresponding appropriate opening area. If it is, no processing is performed. If not, the number g of the real-time opening schematic lines in the corresponding appropriate opening area is obtained for each real-time opening schematic line according to the key node of the human hand as the graph node in the interactive area space. When g is greater than a preset value Y3, no processing is performed. When g is less than or equal to the preset value Y3, an alarm mechanism is triggered to remind the disposal personnel that there is an abnormality in the opening of the waste container, and at the same time, an abnormality information is sent to the supervisor. The specific value of the preset value Y3 is formulated by relevant personnel according to actual needs, and the value of e is 4.

[0066] Multi-angle cameras are used to collect video data of medical waste disposal behaviors within temporary storage areas, constructing a spatial structure for the interaction between the human body and waste containers. A lightweight real-time model is then used to mark key hand nodes and waste container movement points. Through grid division and data screening and analysis, the appropriate opening areas corresponding to each grid space are determined. When a human hand enters the interaction area, the waste container opening schematic line is compared with the appropriate opening area in real time, triggering an alarm mechanism through multiple determinations. This solution effectively overcomes the lag and inaccuracy of existing regulatory measures, enabling real-time and accurate monitoring of the opening status of waste containers. It can provide timely warnings of abnormal situations, reduce the risk of medical waste spillage and pathogen transmission, and simultaneously reduce manual intervention, improve regulatory efficiency, and form traceable data records, providing a strong guarantee for the standardized and intelligent regulation of medical waste.

[0067] Example 3: As Example 3 of the present invention, when this application is specifically implemented, compared with Example 1 and Example 2, the technical solution of this example is to combine the solutions of the above-mentioned Example 1 and Example 2 for implementation.

[0068] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0069] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A medical waste supervision method based on AI video engine technology, characterized in that: The following steps are involved: Step 1: Collect video data of interactive events in the medical waste temporary storage area; Step 2: Generate the interaction area space between the human body and the waste container; Step 3: Mark the key nodes of the human hand and the moving points of the waste container in the medical waste temporary storage area, and then obtain graph nodes and additional nodes; Step 4: Evenly divide the interaction area into multiple identical grid spaces. Analyze the coordinates of the waste container's moving points when the graph nodes are in different grid spaces in the interaction event video data. Obtain the appropriate opening area corresponding to each grid space in the interaction area: Step 5: During the temporary storage of medical waste, when the key node of the human hand enters the interactive area space, the real-time coordinates of the grid space where the key node of the human hand is located and the moving point of the waste container are obtained in real time. The real-time opening schematic line of the waste container is drawn according to the real-time coordinates of the moving point, and it is compared with the appropriate opening area corresponding to the key node of the human hand as a graph node in the corresponding grid space to determine whether to trigger the alarm mechanism.

2. The medical waste supervision method based on AI video engine technology according to claim 1 is characterized in that: The specific method of generating the interaction area space between the human body and the waste container is: Taking the edge of the waste container as the benchmark, the horizontal range is expanded outward by 0.5 meters, and the vertical range is expanded up and down by 0.3 meters according to the height of the container, thereby generating an interactive area space between the human body and the waste container.

3. The medical waste supervision method based on AI video engine technology according to claim 1 is characterized in that: The specific methods for obtaining graph nodes and additional nodes are: The center point of the waste container top cover is used as the moving point of the waste container; the wrist node among the key nodes of the human hand is used as the graph node, and the moving point of the waste container is used as the additional node.

4. The medical waste supervision method based on AI video engine technology according to claim 3 is characterized in that: The specific method of obtaining the appropriate opening areas corresponding to the graph nodes in each grid space of the interaction area space is as follows: S1: Select one grid space from each grid space in the interaction area space as a calibration grid without replacement; mark the position coordinates of the moving point of the waste container in the calibration grid of the graph node in the multiple interaction event video data as Ya (Yxa, Yya, Yza), and the grid positioning point is the center point in each grid space, where a is the position coordinates of the moving point of the waste container in the multiple interaction event video data when the graph node is in the calibration grid; S2: Analyze the horizontal coordinate, vertical coordinate, and vertical coordinate of each moving point position coordinate, and then obtain the reference horizontal coordinate value Hx, reference vertical coordinate Hy, and reference vertical coordinate Hz corresponding to the moving point when the graph node is in the calibration grid, obtain the standard deviations Ux, Uy, and Uz of the horizontal coordinate Yxa, vertical coordinate Yya, and vertical coordinate Yza, and use EA (Hx+Ux, Hy+Uy, Hz+Uz) as the upper limit point EA corresponding to the moving point when the graph node is in the calibration grid, and use EB (|Hx-Ux|, |Hy-Uy|, |Hz-Uz|) as the lower limit point EB corresponding to the moving point when the graph node is in the calibration grid. Combined with the moving point of the waste container, obtain the appropriate opening area corresponding to the graph node in the calibration grid; S3: Repeat steps S1-S2 to obtain the appropriate opening areas corresponding to the graph nodes in each grid space of the interaction area space.

5. The medical waste supervision method based on AI video engine technology according to claim 4 is characterized in that: The specific method to obtain the reference abscissa value, reference ordinate value, and reference vertical coordinate value corresponding to the moving point of the graph node in the calibration grid is: Obtain the number v of values in the horizontal coordinate Yxa of each moving point position coordinate that satisfy |Yxa-Yxp|≥Y2. When the number v is greater than the preset threshold Y1, define the mean value Yxp of Yxa as the reference horizontal coordinate value Hx corresponding to the moving point when the graph node is in the calibration grid. When the number v is less than the preset threshold Y1, define the mean of the maximum and minimum values in Yxa as the reference horizontal coordinate value Hx corresponding to the moving point when the graph node is in the calibration grid. The same analysis method is used to analyze the ordinate Yya and vertical coordinate Yza of the position coordinates of each moving point, and then the reference ordinate Hy and reference vertical coordinate Hz corresponding to the moving point when the graph node is in the calibration grid are obtained.

6. The medical waste supervision method based on AI video engine technology according to claim 4 is characterized in that: Combined with the moving points of the waste container, we can obtain the appropriate opening area corresponding to the graph node in the calibration grid: Draw a perpendicular line from the moving point of the waste container to the rotation axis of the container top cover, and use the intersection of the perpendicular line and the rotation axis as the rotation axis point Z. Connect the upper limit point EA and the lower limit point EB corresponding to the moving point of the graph node in the calibration grid to the rotation axis point Z respectively, and connect the upper limit point EA and the lower limit point EB at the same time to obtain the appropriate opening area corresponding to the graph node in the calibration grid.

7. The medical waste supervision method based on AI video engine technology according to claim 6 is characterized in that: The specific method for determining whether to trigger the alarm mechanism is as follows: Determine whether the real-time opening schematic line is in the corresponding moderate opening area. If so, do not do anything. If not, obtain the key nodes of the human hand as the corresponding real-time opening schematic lines of the graph nodes in the interactive area space for e consecutive times, and obtain the number g of the real-time opening schematic lines in the corresponding moderate opening area. When g is greater than the preset value Y3, do not do anything. When g is less than or equal to the preset value Y3, trigger the alarm mechanism, and the value of e is 4.

8. The medical waste monitoring device based on AI video engine technology is characterized by: The device applies the medical waste supervision method based on AI video engine technology described in any one of claims 1 to 7, including: The data collection end collects video data of interactive events in the medical waste temporary storage area; An interactive area space generating end generates an interactive area space between the human body and the waste container; At the graph node and additional node marking end, key nodes of the human hand and the moving points of the waste container in the medical waste temporary storage area are marked to obtain graph nodes and additional nodes; The moderate opening area acquisition end evenly divides the interaction area space into multiple identical grid spaces, and obtains the moderate opening area corresponding to each graph node in each grid space of the interaction area space: At the alarm mechanism triggering judgment end, when medical waste is temporarily stored, when the key node of the human hand enters the interactive area space, the real-time coordinates of the grid space where the key node of the human hand is located and the moving point of the waste container are obtained in real time to draw the real-time opening schematic line of the waste container, and compare it with the appropriate opening area corresponding to the key node of the human hand as a graph node in the corresponding grid space to determine the triggering of the alarm mechanism.

Images