AI wearable device synchronous management method and system for security risk identification

Abstract

The invention provides an AI wearable device synchronous management method and system for safety risk identification, and belongs to the technical field of device management, and the method specifically comprises the steps: carrying out the synchronous processing of an identification result of a safety risk point in a monitoring image of a person with a wearable device in a synchronous processing region, the method comprises the following steps: determining a moment when a security risk point exists in a monitoring image of a person wearing the equipment, determining a real-time synchronization processing area according to the consistency degree of the security risk point of the monitoring image at the moment when the security risk point exists, and determining the security risk point of the person wearing the equipment according to the data of the person with the wearing equipment in the real-time synchronization processing area. And determining the synchronization processing time of the wearable device in the remaining synchronization processing area. The reliability degree of monitoring processing of the security risk point is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of device management, and particularly relates to an AI wearable device synchronous management method and system for safety risk identification. BACKGROUND

[0002] In order to improve the reliability of safety risk identification processing, more and more enterprises use wearable devices with monitoring devices to identify safety risks, thereby greatly improving the reliability of safety risk identification processing. Specifically, a similar technical solution is given in the invention patent application CN115034588A "Electric power equipment intelligent identification system based on AI image".

[0003] In the occasion with many risk factors such as construction, the number of personnel with AI wearable devices for safety risk identification is large, so that the number of monitoring images is large when the remote processing platform identifies safety risks, and thus the reliability of analysis and processing cannot meet the requirements. Therefore, how to synchronously manage the monitoring images of the wearable devices of different personnel to improve the reliability of safety risk point monitoring management has become a technical problem to be solved.

[0004] To solve the above technical problems, the application provides an AI wearable device synchronous management method and system for safety risk identification. SUMMARY

[0005] To achieve the purpose of the application, the application adopts the following technical solutions: Specifically, the application provides an AI wearable device synchronous management method for safety risk identification, which specifically includes: S1 determines personnel with wearable devices, determines an area that needs to be synchronously processed according to the matching degree of the personnel with wearable devices in the area and safety risk point data, and takes the area as a synchronous processing area; S2 determines safety risk points in the monitoring images of the personnel with wearable devices according to the identification results of the monitoring images of the personnel with wearable devices when the synchronous processing area does not belong to the area of real-time synchronous processing according to the aggregation degree of the positions of the safety risk points in the synchronous processing area; S3 determines the time when the safety risk points exist in the monitoring images of the personnel with wearable devices according to the identification results of the safety risk points in the monitoring images of the personnel with wearable devices in the synchronous processing area, and determines the area of real-time synchronous processing according to the consistency degree of the safety risk points in the monitoring images at the time when the safety risk points exist; S4 determines the synchronous processing time of the wearable devices of the remaining synchronous processing area according to the personnel data with wearable devices in the area of real-time synchronous processing.

[0006] The beneficial effects of the present application are: In the present application, the consistency of the safety risk points in the monitored images at the time when the safety risk points exist is determined to determine the real-time synchronization processing area, which realizes the consistency of the safety risk points in the monitored images of the wearing device, the synchronization processing area of the selection of the distribution of the safety risk points which is too concentrated and the work area of the personnel with the wearing device which is relatively concentrated, ensures that the risk points can be synchronized and fused from the monitored images of different personnel with the wearing device, and improves the reliability of the safety risk point monitoring management.

[0007] In the present application, the synchronization processing time of the wearing device in the remaining synchronization processing area is determined according to the personnel data with the wearing device in the real-time synchronization processing area, which not only considers the number of personnel with the wearing device for real-time synchronization processing, but also considers the influence of the reliability of the synchronization processing in the whole area, and further realizes the determination of the synchronization processing demand and the synchronization processing time of the wearing device in the other remaining synchronization processing area at different times from the difference in reliability, which not only ensures the reliability of the fusion processing, but also reduces the difficulty of the fusion processing of the remote platform.

[0008] Further, the wearing device is a helmet with AI image analysis capability. It can be understood that the helmet has a camera that can acquire images and use an image analysis module in the wearing device to perform analysis processing on the monitored images using an AI-based image analysis model.

[0009] It can be understood that the AI model is constructed using one or more of a CNN image recognition model, an RNN neural network model, and other image recognition models.

[0010] Further, the matching degree of the personnel with the wearing device and the safety risk point data is determined according to the matching of the number of personnel with the wearing device and the number of safety risk points. It should be noted that when the number of personnel is small and the number of safety risk points is small, on the one hand, different personnel are distributed relatively dispersedly, and in addition, the number of safety risks is also small, so on this basis, the monitored images of different personnel in the area do not need to be synchronized.

[0011] Further, the method for determining the synchronization processing area is: determining the number of personnel with the wearing device and the number of safety risk points in the area according to the matching degree of the personnel with the wearing device and the safety risk point data in the area; According to the number of personnel with the wearable device in the region and the number of safety risk points, it is determined whether the region is a synchronous processing region.

[0012] Further, the safety risk points in the monitoring image of the personnel with the wearable device are determined according to the image analysis module of the wearable device.

[0013] Further, the method for determining the real-time synchronous processing region is: The monitoring images with the same safety risk point are determined according to the consistency degree of the safety risk points in the monitoring images at the time when the safety risk point exists, and are taken as the same image; According to the distribution of the same image at different times, it is determined whether the synchronous processing region is a real-time synchronous processing region.

[0014] In a second aspect, the present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the above-mentioned AI wearable device synchronous management method for safety risk identification.

[0015] Other features and advantages will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the application. The objects and other advantages of the application will be realized and attained by the structure particularly pointed out in the description and the drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0017] The above-mentioned and other features and advantages of the present application will become more apparent by describing in detail example embodiments thereof with reference to the attached drawings.

[0018] Figure 1 is a flowchart of an AI wearable device synchronous management method for safety risk identification; Figure 2 is a flowchart of a method for determining a synchronous processing region; Figure 3 is a flowchart of a method for determining a real-time synchronous processing region; Figure 4 is a flowchart of a method for determining a synchronous processing time of a wearable device in a synchronous processing region. DETAILED DESCRIPTION

[0019] Example implementations are now described with reference to the drawings. Example implementations can, however, be implemented in many different forms and should not be construed as limited to the implementations set forth herein; rather, these example implementations are provided so that this disclosure will be thorough and complete, and will fully convey the inventive aspects to those skilled in the art. Like reference numerals refer to like elements throughout the specification. Detailed descriptions of structures, functions, and methods that are well known in the art are omitted herein to avoid obscuring the subject matter of the present disclosure.

[0020] The terms "a", "an", "the", "said", and "s" are used to denote one or more elements / components / etc.; the terms "include" and "have" are used to indicate open inclusion, and that additional elements / components / etc. can be present in addition to the listed elements / components / etc.

[0021] Embodiment 1 To solve the above problems, according to one aspect of the present application, as shown in the accompanying drawings, an AI wearable device synchronization management method for security risk identification is provided, specifically comprising: Figure 1 S1, determining personnel with a wearable device, determining the area that needs to be processed synchronously according to the matching degree of personnel with a wearable device in the area and security risk point data, and taking it as a synchronous processing area; S1, determining personnel with a wearable device, determining the area that needs to be processed synchronously according to the matching degree of personnel with a wearable device in the area and security risk point data, and taking it as a synchronous processing area; Further, the wearable device is a helmet with AI image analysis capability. It can be understood that the helmet has a camera that can acquire images, and an image analysis module in the wearable device is used to analyze the monitoring images based on an AI image analysis model.

[0022] It can be understood that the AI model is constructed by using one or more of a CNN image recognition model, an RNN neural network model, etc.

[0023] Further, the matching degree of personnel with a wearable device and security risk point data is determined according to the matching of the number of personnel with a wearable device and the number of security risk points. It should be noted that when the number of personnel is small and the number of security risk points is small, on the one hand, different personnel are distributed relatively dispersedly, and in addition, the number of security risks is also small, so that the monitoring images of different personnel in the area do not need to be processed synchronously.

[0024] It should be noted that the area is obtained by equal-area division according to the area of the target factory or mine.

[0025] Specifically, as shown in the accompanying drawings, the method for determining the synchronous processing area is: Figure 2 ​determining the number of personnel with the wearable device and the number of safety risk points in the region according to the matching degree of the personnel with the wearable device and the safety risk point data in the region; determining whether the region is a synchronous processing region according to the number of personnel with the wearable device and the number of safety risk points in the region.

[0026] It can be understood that when there is no safety risk point in the region, it is determined that the region does not belong to the synchronous processing region, and when there is a safety risk point in the region, a matching value is determined according to the ratio of the number of personnel with the wearable device and the number of safety risk points, wherein when the matching value and the number of safety risk points meet the requirements, it is determined that the region is a synchronous processing region.

[0027] In a possible embodiment, when the matching value is not less than 2 and the number of safety risk points is more than 3, it is determined that the region is a synchronous processing region.

[0028] Optionally, the method for determining the synchronous processing region is: determining the number of personnel with the wearable device and the number of safety risk points in the region according to the matching degree of the personnel with the wearable device and the safety risk point data in the region; determining a number difference according to the number of personnel with the wearable device and the number of safety risk points in the region, and determining whether the region is a synchronous processing region based on the number difference.

[0029] In a possible embodiment, when the number of personnel with the wearable device and the number of safety risk points in the region both meet the requirements and the number difference is greater than the number of safety risk points, it is determined that the region is a synchronous processing region.

[0030] S2, according to the aggregation degree of the positions of the safety risk points in the synchronous processing region, when the synchronous processing region does not belong to the region of real-time synchronous processing, determining the safety risk points in the monitoring image of the personnel with the wearable device according to the identification result of the monitoring image of the personnel with the wearable device. Further, determining that the synchronous processing region does not belong to the region of real-time synchronous processing specifically includes: determining the number of safety risk points in the synchronous processing region according to the aggregation degree of the positions of the safety risk points in the synchronous processing region; determining whether the synchronous processing region belongs to the region of real-time synchronous processing according to the number of safety risk points and the area of the synchronous processing region.

[0031] It can be understood that when the number of safety risk points in the synchronous processing area meets the requirement, and the ratio of the number of safety risk points to the area of the synchronous processing area, that is, the distribution density, is greater than the threshold value, it means that the number of safety risk points in the synchronous processing area is relatively large and the distribution is relatively concentrated, and therefore the synchronous processing area is determined as a real-time synchronous processing area.

[0032] It should be noted that in a possible embodiment, the chemical plant is divided into three areas, a reaction device area, a safety risk point including a reaction kettle, a distillation kettle and other high temperature and high pressure equipment, a storage and transportation system area, a safety risk point including a storage tank area, a loading and unloading area, a dangerous chemical warehouse, an open-air chemical storage area, and a pipeline: a safety risk point including a corrosion pipeline position and a pipeline leakage position.

[0033] In a possible embodiment, for the storage and transportation system area, when the number of safety risk points is more than 4 and the ratio of the number of safety risk points to the area of the synchronous processing area is greater than 0.02, the synchronous processing area is determined as a real-time synchronous processing area.

[0034] Optionally, determining that the synchronous processing area does not belong to a real-time synchronous processing area, specifically comprising: determining the number of safety risk points in the synchronous processing area according to the aggregation degree of the positions of the safety risk points in the synchronous processing area; determining the interval distance between different positions of safety risk points according to the positions of the safety risk points; determining whether the synchronous processing area belongs to a real-time synchronous processing area based on the number of safety risk points and the interval distance.

[0035] It should be noted that when the interval distance between different positions of safety risk points is far, it means that the distribution of different positions of safety risk points is too discrete, and therefore on this basis, it is determined that the synchronous processing area does not belong to a real-time synchronous processing area, wherein when the number of safety risk points meets the requirement and the interval distance between different positions of safety risk points is less than a preset distance threshold, it is determined that the synchronous processing area belongs to a real-time synchronous processing area.

[0036] Further, the safety risk points in the monitoring image of the personnel with the wearable device are determined according to the image analysis module of the wearable device.

[0037] S3 determines the time when the safety risk points exist in the monitoring image of the personnel with the wearable device in the synchronous processing area according to the identification result of the safety risk points in the monitoring image of the personnel with the wearable device in the synchronous processing area, and determines a real-time synchronous processing area according to the consistency degree of the safety risk points in the monitoring image at the time when the safety risk points exist. Specifically, asFigure 3 As shown, the method for determining the region for real-time synchronization processing is as follows: Based on the consistency of security risk points in surveillance images at the time when security risk points exist, surveillance images that share the same security risk point are identified and treated as identical images. Based on the distribution of the same images at different times, determine whether the synchronous processing area is a real-time synchronous processing area.

[0038] It is understandable that when the same image exists at different times, the synchronous processing area is determined to be the area for real-time synchronous processing.

[0039] It should be noted that when the synchronization processing area is a real-time synchronization processing area, the remote monitoring platform performs real-time analysis and processing on the monitoring images of different personnel's wearable devices in the real-time synchronization processing area, filters the monitoring images with the same security risk points, and performs fusion processing on the remote monitoring platform on the monitoring images with the same security risk points.

[0040] S4 determines the synchronization time for wearable devices in the remaining synchronization processing areas based on the data of people with wearable devices in the real-time synchronization processing area.

[0041] Specifically, such as Figure 4 As shown, the method for determining the synchronization time of the wearable device in the synchronization processing area is as follows: The number of people with wearable devices in the area is determined by using the data of people with wearable devices in the area that is being processed in real time. Based on the security risk point data in different real-time synchronized processing areas, determine the number of security risks in different real-time synchronized processing areas; Based on the number of people with wearable devices in different real-time synchronous processing areas and the number of security risk points, determine the synchronization processing time for wearable devices in the remaining synchronous processing areas.

[0042] It is understandable that the synchronization matching value is determined by the ratio of the number of people with wearable devices in different real-time synchronization processing areas to the total number of people with wearable devices, and the risk point matching value is determined by the ratio of the number of security risk points in different real-time synchronization processing areas to the total number of security risk points. It should be noted that when the synchronization matching value and the risk point matching value both meet the requirements, that is, the synchronization matching value and the risk point matching value are both greater than 0.6 or more, then at this time, the wearable devices in the remaining synchronization processing area do not need to be synchronized, the monitoring processing reliability of the safety risk points at this time and the synchronization processing reliability of the personnel with the wearable devices are higher, and therefore, on this basis, the wearable devices in the remaining synchronization processing area do not need to be synchronized.

[0043] In addition, it can be understood that when either the synchronization matching value or the risk point matching value does not meet the requirements, then at this time, the determination of the area in the remaining synchronization processing area for synchronization processing is determined according to the number of safety risk points, and when the same number of wearable devices in the area synchronized at the time meets the requirements, the time is taken as the synchronization processing time of the wearable devices in the area, and in a possible embodiment, the remaining synchronization processing area in the top 70% of the number of safety risk points in the remaining synchronization processing area is taken as the synchronization processing area, that is, the remaining synchronization processing area in the top 70% of the number of safety risk points is taken as the synchronization processing area, and when the same image of the wearable devices exists in the area synchronized at the time, the time is determined as the synchronization processing time of the wearable devices in the area, that is, the monitoring images of the wearable devices of different personnel in the synchronization processing area of the synchronization processing time are analyzed in real time by the remote monitoring platform, the monitoring images of the wearable devices of the same safety risk points in the remaining synchronization processing area are screened, and the monitoring images of the same safety risk points are fused in the remote monitoring platform.

[0044] In addition, it should be noted that when neither the synchronization matching value nor the risk point matching value meets the requirements, then when the same image of the wearable devices in the remaining synchronization processing area meets the requirements at the time, in a possible embodiment, when the safety risk points in the same image of the wearable devices in the synchronization processing area are not synchronized or the number of safety risk points in the same image of the wearable devices in the synchronization processing area meets the requirements, the time is taken as the synchronization processing time of the wearable devices in the remaining synchronization processing area.

[0045] In a possible embodiment, when the number of safety risk points in the same image of the wearable devices in the remaining synchronization processing area is 2 or more, it is determined that the number of safety risk points in the same image of the wearable devices in the synchronization processing area meets the requirements.

[0046] Optionally, the method for determining the synchronization processing time of the wearable devices in the synchronization processing area is: The personnel data of the personnel wearing the device in the real-time synchronous processing area is determined, the number of the personnel wearing the device in the real-time synchronous processing area is determined, the number of the safety risk points in different real-time synchronous processing areas is determined according to the safety risk point data in different real-time synchronous processing areas; The number of the safety risk points of the remaining synchronous processing area and the number of the safety risk points in the same image of the device in the remaining synchronous processing area at different time points are determined. The synchronous processing time point of the device in the remaining synchronous processing area is determined according to the number of the safety risk points in different real-time synchronous processing areas and the number of the personnel wearing the device, the number of the safety risk points of the remaining synchronous processing area and the number of the safety risk points in the same image of the device in the remaining synchronous processing area at different time points.

[0047] It should be noted that when it belongs to the synchronous processing time point, the monitoring images of the devices of different personnel in the synchronous processing area of the synchronous processing time point are analyzed in real time on the remote monitoring platform, the monitoring images of the devices of the remaining synchronous processing area which have the same safety risk points are screened, and the monitoring images of the devices of the remaining synchronous processing area which have the same safety risk points are fused on the remote monitoring platform.

[0048] Optionally, when the number of the personnel wearing the device in the real-time synchronous processing area and the number of the safety risk points both meet the requirements, that is, when the synchronous matching value and the risk point matching value both meet the requirements, the reliability of the synchronous processing at this time is higher, and therefore it is not necessary to perform synchronous processing on the devices in the remaining synchronous processing area.

[0049] When either the synchronous matching value or the risk point matching value does not meet the requirements, if the average value of the synchronous matching value and the risk point matching value is less than 0.3, then the same image of the device in the remaining synchronous processing area at the time point meets the requirements, and in a possible embodiment, when the safety risk points in the same image of the device in the synchronous processing area are not synchronously processed or the number of the safety risk points in the same image of the device in the synchronous processing area meets the requirements, the time point is taken as the synchronous processing time point of the device in the remaining synchronous processing area.

[0050] In addition, it should be noted that when the average value of the synchronous matching value and the risk point matching value is not less than 0.3, the synchronous processing area in the remaining synchronous processing area is determined according to the number of the safety risk points of the remaining synchronous processing area and the number of the personnel wearing the device, and when the same image of the device in the synchronous processing area at the time point, the time point is taken as the synchronous processing time point of the device in the synchronous processing area.

[0051] In a possible embodiment, the area of the synchronization processing in the remaining synchronization processing area is the top 70% of the remaining synchronization processing area with the largest ratio of the number of personnel wearing the device to the number of safety risk points.

[0052] Embodiment 2 In a second aspect, the present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the AI device synchronization management method for safety risk identification described above.

[0053] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0054] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the order described in the embodiments and still achieve the desired results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or necessary.

[0055] The above only describes one or more embodiments of the present application and does not limit the present application. One or more embodiments of the present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of one or more embodiments of the present application should be included in the scope of the claims of the present application.

Claims

1. An AI wearable device synchronization management method for security risk identification, characterized by, Specifically comprising: Determine the personnel with the wearable device, determine the area that needs to be processed synchronously according to the matching degree of the personnel with the wearable device and the safety risk point data in the area, and take it as the synchronous processing area; According to the aggregation degree of the position of the safety risk point in the synchronous processing area, when the synchronous processing area does not belong to the area of real-time synchronous processing, determine the safety risk point in the monitoring image of the personnel with the wearable device with the recognition result of the monitoring image of the personnel with the wearable device; According to the aggregation degree of the position of the safety risk point in the synchronous processing area, when the synchronous processing area does not belong to the area of real-time synchronous processing, determine the safety risk point in the monitoring image of the personnel with the wearable device with the recognition result of the monitoring image of the personnel with the wearable device; According to the aggregation degree of the position of the safety risk point in the synchronous processing area, when the synchronous processing area does not belong to the area of real-time synchronous processing, determine the safety risk point in the monitoring image of the personnel with the wearable device with the recognition result of the monitoring image of the personnel with the wearable device; 2.The AI wear device synchronization management method for security risk identification of claim 1, wherein, According to the aggregation degree of the position of the safety risk point in the synchronous processing area, when the synchronous processing area does not belong to the area of real-time synchronous processing, determine the safety risk point in the monitoring image of the personnel with the wearable device with the recognition result of the monitoring image of the personnel with the wearable device; 3.The AI wear device synchronization management method for security risk identification of claim 1, wherein, The wearable device is a helmet with AI image analysis capability. 4.The AI wear device synchronization management method for security risk identification of claim 1, wherein, The matching degree of the personnel with the wearable device and the safety risk point data is determined according to the matching of the number of personnel with the wearable device and the number of safety risk points. The method for determining the synchronous processing area is: Determine the number of personnel with the wearable device and the number of safety risk points in the area according to the matching degree of the personnel with the wearable device and the safety risk point data in the area; 5.The AI wear device synchronization management method for security risk identification of claim 4, wherein, Determine whether the area is a synchronous processing area according to the number of personnel with the wearable device and the number of safety risk points in the area. 6.The AI wear device synchronization management method for security risk identification of claim 1, wherein, When there is no safety risk point in the area, it is determined that the area does not belong to the synchronous processing area. Determine that the synchronous processing area does not belong to the area of real-time synchronous processing, specifically including: Determine the number of safety risk points in the synchronous processing area according to the aggregation degree of the position of the safety risk point in the synchronous processing area; 7.The AI wear device synchronization management method for security risk identification of claim 1, wherein, According to the number of safety risk points and the area of the synchronous processing area, determine whether the synchronous processing area belongs to the area of real-time synchronous processing. 8.The AI wear device synchronization management method for security risk identification of claim 1, wherein, The safety risk point in the monitoring image of the personnel with the wearable device is determined according to the image analysis module of the wearable device. The method for determining the synchronous processing time of the wearable device in the synchronous processing area is: Determine the number of personnel with the wearable device in the area of real-time synchronous processing according to the data of personnel with the wearable device in the area of real-time synchronous processing; According to the safety risk point data in different real-time synchronous processing areas, determine the number of safety risks in different real-time synchronous processing areas; According to the number of personnel with the wearable device and the number of safety risk points in different real-time synchronous processing areas, determine the synchronous processing time of the wearable device in the remaining synchronous processing area.

9. It can be understood that the synchronization matching value is determined by the ratio of the number of personnel with wearable devices in different real-time synchronization processing areas to the number of all personnel with wearable devices, and the risk point matching value is determined by the ratio of the number of safety risk points in different real-time synchronization processing areas to the number of all safety risk points; The AI wear device synchronization management method for security risk identification of claim 8, wherein, When the synchronization matching value and the risk point matching value both meet the requirements, then at this time there is no need to synchronize the wearable devices in the remaining synchronization processing areas.

10. A computer system comprising: The memory and the processor connected in communication, and the computer program stored on the memory and capable of running on the processor, characterized in that the processor executes the computer program to perform the AI wearable device synchronization management method for safety risk identification of any one of claims 1-9.

Images