A method and system for identifying risks in power grid metering on-site based on edge terminals

Abstract

The present invention discloses a method and system for identifying risks at a power grid metering site based on an edge terminal, and relates to the technical field of risk identification at a power grid metering site, wherein the method comprises the following steps: acquiring image information at a power grid metering site; when the image information contains personnel characteristic information, determining the wearing information of protective equipment of the personnel characteristic information, and determining the risk identification result according to the protective identification corresponding to the wearing information; when the risk identification result is an alarm result, reporting the personnel information associated with the personnel characteristic information to a management terminal. The present invention identifies the wearing information of personnel at a power grid metering site, and then determines the risk result of the current operation site, and reports the risk result to a remote management terminal, without the need for manual safety detection, thereby reducing the impact of subjective factors on the detection result and improving the accuracy of the detection.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid metering site risk identification, and in particular to an edge-end-based power grid metering site risk identification method and system. Background Art

[0002] At the power grid metering site, workers are required to perform equipment maintenance. During the maintenance process, workers usually need to detect the operating status of the equipment and record the test data of the equipment so as to analyze the results based on the test data. To ensure the safety and accuracy of the test results, workers need to wear appropriate protective equipment.

[0003] In order to ensure the safety of grid metering on-site construction, safety reminder signs are usually installed, and on-site supervisors observe the staff's clothing. However, this detection method is time-consuming and prone to missed detection and false detection, resulting in poor accuracy of staff safety detection. Some people also want to use intelligent methods to achieve safety detection, but the accuracy cannot be improved. Specifically:

[0004] For example, the invention patent with application number 2018114820150 discloses a system and method for collecting and identifying safety risks in the operation process of a power plant. It discloses the use of synchronous dual cameras to collect video data in the current operating environment, and then performs image processing to extract feature data for safety risk analysis, with high detection accuracy. When extracting feature data, contour detection is first performed using an image gradient algorithm to extract the region of interest, and then a deep neural network algorithm is used to extract features from the region of interest. This method can quickly identify operating methods or operating locations that pose safety risks, and promptly and effectively remind operators to pay attention to safety. This invention completely relies on the neural network algorithm for the accuracy of safety detection, but in actual work, there are many factors that affect on-site construction, and simply relying on the neural network is not reliable. In addition, this application does not disclose which specific factors are used to train the neural network. Therefore, it still cannot solve the problems of the prior art. Summary of the invention

[0005] Purpose of the invention: In order to overcome the shortcomings of the prior art, the present invention provides a method for identifying risks at a power grid metering site based on an edge terminal, which solves the problem of poor accuracy of safety detection at a power grid metering site in the prior art. The present invention also provides a system for identifying risks at a power grid metering site based on an edge terminal.

[0006] Technical solution: According to a first aspect of the present invention, a method for identifying risks in a power grid metering site based on an edge terminal is provided, the method comprising the following steps:

[0007] S1 acquires image information of multiple personnel at a power grid metering site in real time, wherein the image information includes image information of an edge end at the power grid metering site, wherein the edge end refers to a portion located between a power grid metering terminal device and a network access point;

[0008] S2 determines whether the collected image information includes personnel feature information. If the image information includes personnel feature information, determines the wearing information of the protective equipment of the personnel feature information, and determines the risk identification result according to the protective identification corresponding to the wearing information. Otherwise, excludes the image that does not include personnel feature information.

[0009] S3 makes corresponding processing according to the risk identification result. If the risk identification result is an alarm result, the personnel information associated with the personnel characteristic information is reported to the management end. The management end is used to obtain the work risk information of all personnel at the current power grid metering site and perform corresponding notification processing. Otherwise, if the risk identification result is a safety result, the target image information of the edge end of the power grid metering site is obtained, and the target image information is the work image information of the personnel in the pre-set work area.

[0010] Further, including:

[0011] In the step S2, determining the risk identification result according to the protection mark corresponding to the wearing information includes the following steps:

[0012] S21 uses a target detection algorithm to extract frame information of the image information, and when the frame information contains the personnel feature information, the wearing information is determined, wherein the frame information is identification information similar to the image information of the staff member read by the target detection algorithm,

[0013] S22 determines whether the detected identification information is the same as the preset identification information. If they are the same, the risk identification result is determined to be a safety result. Otherwise, the risk identification result is an alarm result. The specific alarm category is determined according to the determined alarm result.

[0014] Further, including:

[0015] In the step S22, determining a specific alarm category according to the alarm determination result specifically includes:

[0016] S221: when the risk identification result is an alarm result, determining an alarm type corresponding to the alarm result and an alarm interval corresponding to the alarm type, wherein the alarm type includes not wearing a safety helmet, not wearing insulating gloves, and not wearing work clothes;

[0017] S222 If the alarm interval corresponding to the current alarm type is greater than the preset interval, the personnel information is reported to the management end; otherwise, the number of detection events corresponding to the alarm result is determined, and the number of detection events is the number of detected persons not wearing safety helmets, not wearing insulating gloves, and not wearing protective clothing; if the number of detection events corresponding to the alarm type is different from the number of detection events of the previous alarm result, it means that the alarm result is not from the same person. At this time, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, if the number of detection events corresponding to the alarm type is the same as the number of detection events of the previous alarm result, there is no need to report the personnel information to the management end, and the image information of the power grid metering site is re-acquired.

[0018] Further, including:

[0019] In the step S3, reporting the personnel information associated with the personnel characteristic information to the management end includes:

[0020] S31 reports and processes the information in batches according to the emergency handling capability of the personnel information, wherein the emergency handling capability of the personnel information is determined according to the personnel information associated with the personnel characteristic information and the operation capability index corresponding to the personnel information, thereby determining the emergency handling level of different personnel;

[0021] S32 determines whether the emergency handling level of the current personnel is higher than the preset level. If the emergency handling level of the current personnel is lower than the preset level, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, the alarm result is sent to the corresponding personnel separately.

[0022] Further, including:

[0023] The step S3 further comprises:

[0024] S33 The administrator of the management end responds to the management instruction fed back by the management end by broadcasting or personal email;

[0025] S34: if the management instruction includes a monitoring instruction, the risk identification information of the target area where the personnel are located is updated in real time to ensure that all personnel have worn corresponding protective equipment;

[0026] S35 If the management instruction includes an early warning instruction, the location information of the person is determined, and early warning prompt information is sent to the early warning device corresponding to the location information, so that the early warning device outputs safety prompt information to prompt the person holding the early warning device to wear protective equipment.

[0027] Further, including:

[0028] In the step S3, if the risk identification result is a safety result, the target image information of the edge end of the power grid metering site is obtained, and in addition, the following steps are also included:

[0029] S4: based on a preset time period, if no work sign is detected in the target image information, the risk identification result corresponding to the edge end is marked as an alarm result, and the personnel information associated with the edge end is reported to the management end; otherwise, go to step S5;

[0030] S5: Based on the preset time period, when the work sign is detected in the target image information, it means that the staff hangs the sign according to the regulations. At this time, the continuous operation time corresponding to the target image information is determined;

[0031] S6: Then, within the continuous operation time, if it is detected that the personnel characteristic information leaves the area corresponding to the target image information, the risk identification result corresponding to the edge end is marked as an alarm result, and the personnel information associated with the edge end is reported to the management end; otherwise, go to step S7;

[0032] S7: if the risk identification result is a safe result, target image information of the edge end of the power grid metering site is obtained.

[0033] On the other hand, the present invention also provides an edge-based grid metering field risk identification system, the system comprising:

[0034] A collection module, used to obtain image information of multiple personnel at a power grid metering site in real time, wherein the image information includes image information of an edge end at the power grid metering site, wherein the edge end refers to a portion located between a power grid metering terminal device and a network access point;

[0035] A risk identification and judgment module is used to determine whether the collected image information includes personnel feature information. If the image information includes personnel feature information, the wearing information of the protective equipment of the personnel feature information is determined, and the risk identification result is determined according to the protective identification corresponding to the wearing information. Otherwise, the image that does not include personnel feature information is excluded;

[0036] The processing module is used to perform corresponding processing according to the risk identification result, specifically including:

[0037] A judgment unit, used to judge whether the risk identification result is a warning result or a safety result;

[0038] An alarm processing unit, if the risk identification result is an alarm result, reports the personnel information associated with the personnel characteristic information to the management end, and the management end is used to obtain the work risk information of all personnel at the current power grid metering site and perform corresponding notification processing;

[0039] The safety processing unit obtains target image information of the edge end of the power grid metering site if the risk identification result is a safety result, wherein the target image information is work image information of personnel in a preset work area.

[0040] Further, including:

[0041] In the risk identification and judgment module, the risk identification result is determined according to the protection mark corresponding to the wearing information, including:

[0042] a detection unit, configured to extract frame information of the image information by using a target detection algorithm, and determine the wearing information when the frame information contains the personnel feature information, wherein the frame information is identification information similar to the image information of the staff member read by the target detection algorithm,

[0043] The risk identification unit determines whether the detected identification information is the same as the preset identification information. If they are the same, the risk identification result is determined to be a safe result. Otherwise, the risk identification result is an alarm result. The specific alarm category is determined according to the determined alarm result.

[0044] Further, including:

[0045] In the risk identification unit, determining a specific alarm category according to the alarm determination result specifically includes:

[0046] When the risk identification result is an alarm result, determining an alarm type corresponding to the alarm result and an alarm interval corresponding to the alarm type, wherein the alarm type includes not wearing a safety helmet, not wearing insulating gloves, and not wearing work clothes;

[0047] If the alarm interval corresponding to the current alarm type is greater than the preset interval, the personnel information is reported to the management end; otherwise, the number of detection events corresponding to the alarm result is determined, and the number of detection events is the number of detected persons not wearing safety helmets, not wearing insulating gloves, and not wearing protective clothing; if the number of detection events corresponding to the alarm type is different from the number of detections in the previous alarm result, it means that the alarm result is not from the same person. At this time, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, if the number of detection events corresponding to the alarm type is the same as the number of detections in the previous alarm result, there is no need to report the personnel information to the management end, and the image information of the power grid metering site is reacquired.

[0048] Further, including:

[0049] In the alarm processing unit, reporting the personnel information associated with the personnel characteristic information to the management end includes:

[0050] Reporting and processing information in batches according to the emergency handling capability of personnel information, the emergency handling capability of the personnel information is determined according to the personnel information associated with the personnel characteristic information and the operational capability index corresponding to the personnel information, thereby determining the emergency handling level of different personnel;

[0051] Determine the level of emergency response of the current personnel and the preset level. If the emergency response level of the current personnel is lower than the preset level, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, the alarm result is sent to the corresponding personnel separately.

[0052] Beneficial effects: Compared with the prior art, the present invention has the following advantages: the present invention first obtains image information of the power grid metering site, and when the image information contains personnel characteristic information, determines the wearing information of the protective equipment of the personnel characteristic information, and determines the risk identification result according to the protection mark corresponding to the wearing information; when the risk identification result is an alarm result, the personnel information associated with the personnel characteristic information is reported to the management end for processing; on the basis of the intelligent method, a variety of influencing factors are combined and connection relationships are established between the factors, and the risk results are obtained quickly and accurately according to the set logical method, so as to make accurate and rapid judgments on whether the construction personnel are constructing safely and whether the risks are high.

[0053] Therefore, by identifying the wearing information of protective equipment of each staff member at the power grid metering site, the risk status of the on-site workers is judged, and the risk results are reported to the remote management end. There is no need for manual safety inspections, which reduces the impact of subjective factors on the test results and improves the accuracy of the detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow chart of a first embodiment of a method for identifying risks on-site in power grid metering based on an edge terminal of the present invention;

[0055] Figure 2 It is a flow chart of a second embodiment of the method for identifying risks on-site of power grid metering based on edge terminals of the present invention;

[0056] Figure 3 It is a flow chart of a third embodiment of the method for identifying risks on-site of power grid metering based on edge terminals of the present invention;

[0057] Figure 4 It is a flow chart of a fourth embodiment of the method for identifying risks in a power grid metering site based on an edge terminal of the present invention;

[0058] Figure 5 It is a schematic diagram of the terminal hardware structure of each embodiment of the edge-based grid metering on-site risk identification method of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0061] In order to ensure the safety of grid metering construction, safety reminder signs are usually installed, and on-site supervisors observe the workers' clothing. However, this detection method is time-consuming and prone to missed detection and false detection, resulting in poor accuracy of worker safety detection.

[0062] To solve the above-mentioned defects, the present invention judges the risk status of on-site workers by identifying the wearing information of protective equipment of each staff member at the power grid metering site, and reports the risk results to the remote management end. There is no need for manual safety inspections, which reduces the impact of subjective factors on the test results and improves the accuracy of the detection.

[0063] In order to better understand the above technical solution, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0064] Please refer to Figure 1 The steps of the risk identification method based on the edge-end power grid metering site of the present invention include:

[0065] S1 acquires image information of multiple personnel at a power grid metering site in real time, wherein the image information includes image information of an edge end at the power grid metering site, wherein the edge end refers to a portion located between a power grid metering terminal device and a network access point;

[0066] S2 determines whether the collected image information includes personnel feature information. If the image information includes personnel feature information, determines the wearing information of the protective equipment of the personnel feature information, and determines the risk identification result according to the protective identification corresponding to the wearing information. Otherwise, excludes the image that does not include personnel feature information.

[0067] In this embodiment, a target detection algorithm can be used to extract the border information of the image information, and when the border information contains the personnel feature information, the wearing information is determined. The border information is identification information similar to the image information of the staff member read by the target detection algorithm. Then, it is determined whether the detected identification information is the same as the preset identification information. If they are the same, the risk identification result is determined to be a safety result. Otherwise, the risk identification result is an alarm result, and the specific alarm category is determined according to the determined alarm result.

[0068] Specifically, in the process of determining the alarm category, when the risk identification result is an alarm result, the alarm type corresponding to the alarm result and the alarm interval corresponding to the alarm type are determined, the alarm types include not wearing a safety helmet, not wearing insulating gloves, and not wearing work clothes. If the alarm interval corresponding to the current alarm type is greater than the preset interval, the current personnel information is reported to the management end; otherwise, the number of detection events corresponding to the alarm result is determined, and the number of detection events is the number of detected not wearing a safety helmet, not wearing insulating gloves, and not wearing protective clothing; if the number of detection events corresponding to the alarm type is different from the number of detections of the previous alarm result, it means that the alarm result is not from the same person, and the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, if the number of detection events corresponding to the alarm type is the same as the number of detections of the previous alarm result, it is not necessary to report the personnel information to the management end, and the image information of the power grid metering site is re-acquired.

[0069] S3 makes corresponding processing according to the risk identification result. If the risk identification result is an alarm result, the personnel information associated with the personnel characteristic information is reported to the management end. The management end is used to obtain the work risk information of all personnel at the current power grid metering site and perform corresponding notification processing. Otherwise, if the risk identification result is a safety result, the target image information of the edge end of the power grid metering site is obtained, and the target image information is the work image information of the personnel in the pre-set work area.

[0070] In this embodiment, when uploading data, the information can be reported in batches according to the emergency handling capability of the personnel information. The emergency handling capability of the personnel information is determined according to the personnel information associated with the personnel characteristic information and the operational capability index corresponding to the personnel information, thereby determining the emergency handling level of different personnel. Specifically, the emergency handling level of the current personnel is judged to be higher than the preset level. If the emergency handling level of the current personnel is lower than the preset level, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, the alarm result is sent to the corresponding personnel separately.

[0071] Optionally, in addition to this, the administrator of the management end can also respond to the management instructions fed back by the management end by broadcasting or personal email. If the management instructions include monitoring instructions, the risk identification information of the target area where the personnel is located is updated in real time to ensure that all personnel have worn corresponding protective equipment. If the management instructions include early warning instructions, the location information of the personnel is determined, and early warning prompt information is sent to the early warning device corresponding to the location information, so that the early warning device outputs safety prompt information to prompt the personnel holding the early warning device to wear protective equipment.

[0072] Optionally, within a preset time period, if no work sign is detected in the target image information, the risk identification result corresponding to the edge end is marked as an alarm result, and the personnel information associated with the edge end is reported to the management end, otherwise, go to step S5;

[0073] S5: Based on the preset time period, when the work sign is detected in the target image information, it means that the staff hangs the sign according to the regulations. At this time, the continuous operation time corresponding to the target image information is determined;

[0074] S6: Then, within the continuous operation time, if it is detected that the personnel characteristic information leaves the area corresponding to the target image information, the risk identification result corresponding to the edge end is marked as an alarm result, and the personnel information associated with the edge end is reported to the management end; otherwise, go to step S7;

[0075] S7: if the risk identification result is a safe result, target image information of the edge end of the power grid metering site is obtained.

[0076] In the technical solution disclosed in this embodiment, the risk status of on-site workers is judged by identifying the wearing information of protective equipment of each staff member at the power grid metering site, and the risk results are reported to the remote management end. There is no need for manual safety inspections, which reduces the impact of subjective factors on the test results and improves the accuracy of the detection.

[0077] In another alternative implementation, see Figure 2 The method for identifying risks of power grid metering on-site based on the edge terminal of the present invention also includes:

[0078] Step S10: acquiring image information of the power grid metering site;

[0079] In this embodiment, the power grid metering site is the actual operation site for electric energy metering in the power system. When the staff performs corresponding work at the power grid metering site, if they do not wear corresponding protective equipment as specified, the risk of performing the work task is high. Based on this, in order to be able to efficiently obtain the wearing information of the staff, it is necessary to shoot the working scene at the edge of the power grid metering site, that is, the operation risk identification system needs to obtain the image information of the edge of the power grid metering site. Among them, the edge refers to the part located between the power grid metering terminal equipment (such as a metering device, a collection device) and the network access point, and the staff usually perform work tasks at the edge.

[0080] Step S20: when the image information contains personal characteristic information, determine the wearing information of the protective equipment of the personal characteristic information, and determine the risk identification result according to the protective identification corresponding to the wearing information;

[0081] In this embodiment, before determining the wearing information, it is necessary to identify and process the acquired image information through a detection algorithm. That is, it is necessary to extract the border information of the image information based on the target detection algorithm, and determine the wearing information when the border information contains the personnel feature information. Among them, the target detection algorithm can be the YOLOv5 (YouOnly Look Once) algorithm, which is based on the YOLO series and is improved and optimized on the basis of YOLOv4. The algorithm can adaptively expand training data and unaligned multi-scale training. When it is applied to image detection, it can improve the accuracy and robustness of detection. Border information refers to the identification information similar to the image information of the staff member read by the algorithm, and the personnel feature information refers to the pixel information corresponding to the staff member in the image information. Optionally, the target detection algorithm can also be an image recognition algorithm generated by an AI (Artificial Intelligence) algorithm detection model.

[0082] Specifically, when the image information contains personnel feature information, that is, pixel information of the staff, the wearing information of the personnel feature information can be extracted based on the target detection algorithm, and the wearing information corresponding to the wearing information can be determined. For example, the protective identification can include the identification of a safety helmet, the identification of an insulating suit, and the identification of insulating gloves, etc., that is, when it is detected that the personnel feature information includes a safety helmet, it means that the state of the protective identification corresponding to the safety helmet is not empty. Based on this, the target detection algorithm can determine the protective identification corresponding to the wearing information based on whether the detected personnel feature information wears a safety helmet, insulating suit, and insulating gloves.

[0083] When the protection mark is different from the preset protection mark, for example, the preset protection mark includes a safety helmet and insulating gloves, but the protection mark of a worker in the image information only includes insulating gloves, which means that the worker did not wear protective equipment according to the regulations, and the corresponding risk identification result is an alarm result. When the protection mark is the same as the preset protection mark, the risk identification result is determined to be a safe result. Determining the risk identification result of the worker by the protection mark corresponding to the wearing information can improve the accuracy of the risk identification result.

[0084] Optionally, when the protection mark is different from the preset protection mark, the risk identification result is determined to be an alarm result, and the alarm category corresponding to the alarm result. Since there are multiple protection marks, the alarm result can usually include specific alarm categories, for example, the alarm categories include not wearing a safety helmet, not wearing protective clothing, not wearing insulating gloves and / or not wearing a safety belt, etc. By setting different alarm categories for the alarm results, the accuracy of detection can be improved so that the management end can perform targeted prompt processing.

[0085] It should be noted that the corresponding personnel feature information in the image information can be one or more, and the target detection algorithm can extract information from multiple personnel feature information at the same time. Therefore, in the image information obtained based on the power grid metering site, when there are multiple personnel feature information, the risk identification results obtained are also multiple.

[0086] Step S30: When the risk identification result is an alarm result, the personnel information associated with the personnel characteristic information is reported to the management end.

[0087] In this embodiment, the management end may be a remotely connected management device, which is used to obtain the work risk information of all staff members at the current power grid metering site. When the risk identification result is an alarm result, it means that at the current metering site, there are staff members whose wearing information does not meet the work specifications, and the risk level of the staff member at work is high. Therefore, the personnel information corresponding to the identified personnel feature information can be reported to the management end, and the management personnel at the management end will perform corresponding notification processing to improve processing efficiency. Among them, the personnel information reported to the management end is the personnel information corresponding to the alarm result, not the information of all staff members in the image information.

[0088] Optionally, when the risk identification result is an alarm result, the information can also be reported in batches according to the emergency handling capability of the personnel information. That is, when the risk identification result is an alarm result, the personnel information associated with the personnel characteristic information and the operational capability index corresponding to the personnel information are determined. Among them, the evaluation criteria of the operational capability index can be scored by the basic information of the staff member, such as years of employment, job grade, and professional skill certificate grade.

[0089] After determining the staff's operating ability index, when there are multiple pieces of personnel information, determine the emergency handling levels corresponding to the multiple operating ability indicators, and report the target personnel information whose emergency handling level is lower than the preset level to the management end, and send the alarm information to the devices corresponding to other target personnel information whose emergency handling level is higher than or equal to the preset level.

[0090] It is understandable that the higher the staff's operating ability index, the higher the corresponding emergency handling level, that is, the stronger the emergency handling ability. Therefore, only the target personnel information whose emergency handling level is lower than the preset level needs to be reported to the management end, and the other target personnel information can be notified by sending a separate prompt message. Then, the management end can give priority to safety awareness training for staff with lower operating ability indicators, thereby reducing the risk of subsequent measurement sites.

[0091] Optionally, the direct superior information corresponding to the target personnel information can also be determined, and then the target personnel information can be reported to the management device corresponding to the direct superior information, and other personnel information except the target personnel information can be reported to the corresponding personal terminal device, so that the staff whose risk identification result is an alarm result can receive the alarm information in time and put on the protective equipment again.

[0092] Optionally, after reporting the personnel information to the management end, the management personnel inform the staff to wear protective equipment in time through the management end by broadcasting or personal email. That is, it is possible to respond to the management instructions fed back by the management end. When the management instructions include monitoring instructions, it is necessary to update the risk identification information of the target area where the personnel information is located in real time to ensure that all staff have worn corresponding protective equipment. When the management instructions include early warning instructions, it is necessary to determine the location information of the personnel information and send early warning prompt information to the early warning device corresponding to the location information, so that the early warning device outputs safety prompt information based on the early warning prompt information to prompt the staff to wear protective equipment and improve the safety of on-site operations.

[0093] In the technical solution disclosed in this embodiment, the risk identification system can obtain image information at the edge of the power grid metering site, and then extract key risk information of the work site through the target detection algorithm, that is, detect whether the staff at the power grid metering site wear safety helmets, insulating gloves, or work clothes, etc., and then judge the risk identification results of the on-site staff during construction based on the wearing information, and when the risk identification result is an alarm result, report the personnel information corresponding to the alarm result to the remote management end. Based on this, the risk identification system identifies the wearing information of the protective equipment of each staff member at the power grid metering site, and judges the risk status of the on-site workers, avoiding the management personnel from directly conducting inspections by observation, reducing the impact of subjective factors, and improving the accuracy of the inspection.

[0094] In another embodiment, please refer to Figure 3 , after step S20, further comprising:

[0095] Step S40: when the risk identification result is a safety result, obtaining target image information of the edge end of the power grid metering site;

[0096] In this embodiment, when the risk identification result is a safety result, it means that the staff at the current work site are all wearing protective equipment such as safety helmets and work clothes. At this time, the risk identification system believes that the work has started and needs to obtain the target image information of the edge end of the power grid metering site in real time, so that the risk identification system can ensure whether the staff are on duty or whether the on-duty time is reasonable, thereby reducing the risk of the power grid metering site. Among them, the target image information is the image information of the staff's work area, which can be pre-set in the risk identification system by the management personnel.

[0097] In step S50, based on a preset time period, when no work sign is detected in the target image information, the risk identification result corresponding to the edge end is marked as the alarm result, and the personnel information associated with the edge end is reported to the management end.

[0098] In this embodiment, before the staff starts working, they usually place work signs in the work area and then perform their work tasks. Since the work signs are used to standardize task operations and reduce safety hazards, if no work signs are detected within the preset period, it means that the staff did not hang the signs according to regulations. At this time, in order to avoid unnecessary safety hazards, the risk identification system will mark the risk identification result corresponding to the edge end as an alarm result, and then report the related personnel information to the management end.

[0099] Optionally, based on the preset time period, when the work sign is detected in the target image information, it indicates that the staff has hung the sign in accordance with regulations. At this time, in order to further ensure the safety of the site, it is necessary to determine the personnel information during the continuous working time to avoid safety hazards caused by the temporary departure of the staff during working hours. Therefore, it is necessary to first determine the continuous working time corresponding to the target image information, and then during the continuous working time, if the personnel characteristic information is detected to have left the area corresponding to the target image information, the risk identification result corresponding to the edge end is marked as the alarm result, and the personnel information associated with the edge end is reported to the management end.

[0100] For example, at the power grid metering site, all workers wear helmets, work clothes and insulating gloves, and a work sign is detected in the work area at the edge. At this time, workers wearing helmets, insulating gloves and work clothes in the work area are working on site. The on-site working time is 2 hours. At the same time, within the specified time, there is a situation where workers leave the work area, that is, the risk identification system detects that the number of workers is less than the preset number, and the risk identification system reports the personnel information in the current work area to the cloud management library.

[0101] It should be noted that the above data are only used for explanation and description, and are not intended to limit the present invention.

[0102] In the technical solution disclosed in this embodiment, the risk identification system can detect the working area of ​​the staff, and when no work sign is detected in the target image information at the edge, or when the work sign is detected and the staff temporarily leaves the site during the continuous working time, the current risk identification result will be marked as an alarm result, and the corresponding personnel information will be reported to the management end, thereby avoiding unnecessary safety hazards at the working site and improving the safety of on-site operations at the power grid metering site.

[0103] In another embodiment, please refer to Figure 4 , step S30 specifically includes:

[0104] Step S31, when the risk identification result is an alarm result, determining an alarm type corresponding to the alarm result and an alarm interval corresponding to the alarm type;

[0105] Step S32, when the alarm type has not changed and the alarm interval is greater than a preset interval, a step of reporting the personnel information associated with the personnel characteristic information to a management terminal is performed.

[0106] That is, if the alarm interval time corresponding to the current alarm type is greater than the preset interval time, the current personnel information is reported to the management end; otherwise, the number of detection events corresponding to the alarm result is determined, and the number of detection events is the number of detected persons not wearing safety helmets, not wearing insulating gloves, and not wearing protective clothing; if the number of detection events corresponding to the alarm type is different from the number of detection events of the previous alarm result, it means that the alarm result is not from the same person. At this time, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, if the number of detection events corresponding to the alarm type is the same as the number of detection events of the previous alarm result, there is no need to report the personnel information to the management end, and the image information of the power grid metering site is re-acquired.

[0107] In this embodiment, when the risk identification result is an alarm result, the alarm result has different alarm categories such as not wearing a safety helmet, not wearing insulating gloves and / or not wearing work clothes. Similarly, the risk identification detection is carried out in real time. When a person who does not wear protective equipment correctly appears at the measurement site, the detection system can obtain the current detection result in real time. In order to avoid continuously reporting the information of the same person to the management end in a short period of time, resulting in a large amount of data processing on the management end, by setting the data reporting time interval, that is, the preset time interval, during this period, if no new risk identification results appear, that is, the alarm type has not changed, then the current personnel information will be updated to the management end.

[0108] Optionally, when the alarm type changes within the preset interval, it means that a new person who is not wearing safety work clothes is detected in the current measurement site, and the information of the person who has been alarmed is reported to the management end. Based on this, when the risk identification result is an alarm result, the accuracy of the risk identification result is improved by analyzing and comparing the data corresponding to the alarm result.

[0109] In an optional implementation scenario, the preset time interval is 10 seconds. When worker A who is not wearing a helmet is detected for the first time, the personnel information of worker A is reported to the management end. Then, within the next 10 seconds, if worker B who is not wearing a helmet or worker C who is not wearing insulating gloves appears, the personnel information of workers A, B and C is directly reported to the management end. After 10 seconds, the person corresponding to the alarm information is still worker A, and the personnel information of worker A is updated to the management end.

[0110] It should be noted that the values ​​of the above-mentioned preset time intervals are only used for explanation and description. The preset time intervals can be dynamically set according to the actual work site and are not specific limitations on the preset intervals.

[0111] In the technical solution disclosed in this embodiment, when the risk identification result is an alarm result, the alarm interval time, alarm type and corresponding number of detection events corresponding to the alarm result can be analyzed and judged for a second time, thereby ensuring whether the alarm result is accurate and avoiding repeated reporting of the same personnel information in a short period of time. By analyzing and comparing the data corresponding to the alarm result, the accuracy of the risk identification result is improved.

[0112] On the other hand, the present invention also provides an edge-based grid metering field risk identification system, the system comprising:

[0113] A collection module, used to obtain image information of multiple personnel at a power grid metering site in real time, wherein the image information includes image information of an edge end at the power grid metering site, wherein the edge end refers to a portion located between a power grid metering terminal device and a network access point;

[0114] A risk identification and judgment module is used to determine whether the collected image information includes personnel feature information. If the image information includes personnel feature information, the wearing information of the protective equipment of the personnel feature information is determined, and the risk identification result is determined according to the protective identification corresponding to the wearing information. Otherwise, the image that does not include personnel feature information is excluded;

[0115] The processing module is used to perform corresponding processing according to the risk identification result, specifically including:

[0116] A judgment unit, used to judge whether the risk identification result is a warning result or a safety result;

[0117] An alarm processing unit, if the risk identification result is an alarm result, reports the personnel information associated with the personnel characteristic information to the management end, and the management end is used to obtain the work risk information of all personnel at the current power grid metering site and perform corresponding notification processing;

[0118] The safety processing unit obtains target image information of the edge end of the power grid metering site if the risk identification result is a safety result, wherein the target image information is work image information of personnel in a preset work area.

[0119] Further, including:

[0120] In the risk identification and judgment module, the risk identification result is determined according to the protection mark corresponding to the wearing information, including:

[0121] a detection unit, configured to extract frame information of the image information by using a target detection algorithm, and determine the wearing information when the frame information contains the personnel feature information, wherein the frame information is identification information similar to the image information of the staff member read by the target detection algorithm,

[0122] The risk identification unit determines whether the detected identification information is the same as the preset identification information. If they are the same, the risk identification result is determined to be a safe result. Otherwise, the risk identification result is an alarm result. The specific alarm category is determined according to the determined alarm result.

[0123] Further, including:

[0124] In the risk identification unit, determining a specific alarm category according to the alarm determination result specifically includes:

[0125] When the risk identification result is an alarm result, determining an alarm type corresponding to the alarm result and an alarm interval corresponding to the alarm type, wherein the alarm type includes not wearing a safety helmet, not wearing insulating gloves, and not wearing work clothes;

[0126] If the alarm interval corresponding to the current alarm type is greater than the preset interval, the personnel information is reported to the management end; otherwise, the number of detection events corresponding to the alarm result is determined, and the number of detection events is the number of detected persons not wearing safety helmets, not wearing insulating gloves, and not wearing protective clothing; if the number of detection events corresponding to the alarm type is different from the number of detections in the previous alarm result, it means that the alarm result is not from the same person. At this time, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, if the number of detection events corresponding to the alarm type is the same as the number of detections in the previous alarm result, there is no need to report the personnel information to the management end, and the image information of the power grid metering site is reacquired.

[0127] Further, including:

[0128] In the alarm processing unit, reporting the personnel information associated with the personnel characteristic information to the management end includes:

[0129] Reporting and processing information in batches according to the emergency handling capability of personnel information, the emergency handling capability of the personnel information is determined according to the personnel information associated with the personnel characteristic information and the operational capability index corresponding to the personnel information, thereby determining the emergency handling level of different personnel;

[0130] Determine the level of emergency response of the current personnel and the preset level. If the emergency response level of the current personnel is lower than the preset level, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, the alarm result is sent to the corresponding personnel separately.

[0131] Other technical features corresponding to the edge-based power grid metering on-site risk identification system described in the present invention are similar to the edge-based power grid metering on-site risk identification method, and will not be repeated here.

[0132] Reference Figure 5 , which is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment of the present invention.

[0133] like Figure 5 As shown, the terminal may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a network interface 1003, and a memory 1004. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The network interface 1003 may optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1004 may be a high-speed RAM memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1004 may optionally be a storage device independent of the aforementioned processor 1001.

[0134] Those skilled in the art will understand that Figure 5 The terminal structure shown in the figure does not constitute a limitation on the terminal, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0135] like Figure 5 As shown, the memory 1004 as a computer storage medium may include an operating system, a data storage module, a network communication module, and an operation risk identification program.

[0136] exist Figure 5 In the terminal shown, the network interface 1003 is mainly used to connect to the backend server and perform data communication with the backend server; the processor 1001 can call the operation risk identification program stored in the memory 1004 and perform the following operations:

[0137] Obtain image information of power grid metering site;

[0138] When the image information contains personal characteristic information, determining the wearing information of protective equipment of the personal characteristic information, and determining the risk identification result according to the protective identification corresponding to the wearing information;

[0139] When the risk identification result is an alarm result, the personnel information associated with the personnel characteristic information is reported to the management end.

[0140] Furthermore, the processor 1001 may call the operation risk identification program stored in the memory 1004, and further perform the following operations:

[0141] When the risk identification result is a safe result, obtaining target image information of the edge end of the power grid metering site;

[0142] Based on a preset time period, when no work sign is detected in the target image information, the risk identification result corresponding to the edge end is marked as the alarm result, and the personnel information associated with the edge end is reported to the management end.

[0143] Furthermore, the processor 1001 may call the operation risk identification program stored in the memory 1004, and further perform the following operations:

[0144] Based on the preset time period, when the work sign is detected in the target image information, determining the continuous operation time corresponding to the target image information;

[0145] During the continuous operation time, if it is detected that the personnel characteristic information leaves the area corresponding to the target image information, the risk identification result corresponding to the edge end is marked as the alarm result, and the personnel information associated with the edge end is reported to the management end.

[0146] Furthermore, the processor 1001 may call the operation risk identification program stored in the memory 1004, and further perform the following operations:

[0147] When the risk identification result is an alarm result, determining an alarm type corresponding to the alarm result and an alarm interval corresponding to the alarm type;

[0148] When the alarm interval under the same alarm type is greater than the preset interval, the step of reporting the personnel information associated with the personnel characteristic information to the management end is performed.

[0149] Furthermore, the processor 1001 may call the operation risk identification program stored in the memory 1004, and further perform the following operations:

[0150] When the alarm interval under the same alarm type is less than or equal to the preset interval, determining the number of detection events corresponding to the alarm result;

[0151] When the number of detection events is different from the target detection number of the previous alarm result corresponding to the alarm type, performing the step of reporting the personnel information associated with the personnel feature information to the management end; or

[0152] When the number of alarm events is the same as the target number of alarms corresponding to the previous alarm result, the process jumps to the step of acquiring the image information of the power grid metering site.

[0153] Furthermore, the processor 1001 may call the operation risk identification program stored in the memory 1004, and further perform the following operations:

[0154] Extracting the frame information of the image information based on the target detection algorithm, and when the frame information contains the personnel feature information, performing the steps of determining the wearing information of the protective equipment of the personnel feature information, and determining the risk identification result according to the protection mark corresponding to the wearing information;

[0155] The step of determining the wearing information of the protective equipment of the personnel characteristic information and determining the risk identification result according to the protective identification corresponding to the wearing information includes:

[0156] Extracting the wearing information of the personnel characteristic information based on the target detection algorithm, and determining the protection mark corresponding to the wearing information;

[0157] When the protection identifier is different from the preset protection identifier, determining the risk identification result as the warning result; or

[0158] When the protection identifier is the same as the preset protection identifier, the risk identification result is determined to be a safe result.

[0159] Furthermore, the processor 1001 may call the operation risk identification program stored in the memory 1004, and further perform the following operations:

[0160] When the risk identification result is an alarm result, determining the personnel information associated with the personnel characteristic information, and the operation capability index corresponding to the personnel information;

[0161] When there are multiple pieces of information on the personnel, determine the emergency handling levels corresponding to the multiple operating capability indicators, and report the target personnel information whose emergency handling level is lower than the preset level to the management end, and send the alarm information to the devices corresponding to other target personnel information whose emergency handling level is higher than or equal to the preset level; or

[0162] Determine the direct superior information corresponding to the target personnel information, report the target personnel information to the management device corresponding to the direct superior information, and report other personnel information other than the target personnel information to the personal terminal device corresponding to the other personnel information.

[0163] Furthermore, the processor 1001 may call the operation risk identification program stored in the memory 1004, and further perform the following operations:

[0164] In response to the management instruction fed back by the management end, when the management instruction includes a monitoring instruction, updating the risk identification information of the target area where the personnel information is located in real time;

[0165] When the management instruction includes an early warning instruction, the location information of the personnel information is determined, and early warning prompt information is sent to the early warning device corresponding to the location information, so that the early warning device outputs safety prompt information based on the early warning prompt information.

[0166] In addition, it can be understood by a person skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the control terminal to implement the process steps of the embodiment of the above method.

[0167] Therefore, the present invention also provides a computer-readable storage medium, which stores a job risk identification program. When the job risk identification program is executed by a processor, the various steps of the job risk identification method described in the above embodiment are implemented.

[0168] It should be noted that since the storage medium provided in the embodiment of the present application is the storage medium used to implement the method of the embodiment of the present application, based on the method introduced in the embodiment of the present application, the person skilled in the art can understand the specific structure and deformation of the storage medium, so it is not repeated here. All storage media used in the method of the embodiment of the present application belong to the scope of protection of this application.

[0169] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0170] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0171] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0173] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0174] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0175] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0176] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for identifying risks in power grid metering on-site based on edge terminals, characterized in that: The method comprises the following steps: S1 acquires image information of multiple personnel at a power grid metering site in real time, wherein the image information includes image information of an edge end at the power grid metering site, wherein the edge end refers to a portion located between a power grid metering terminal device and a network access point; S2 determines whether the collected image information includes personnel feature information. If the image information includes personnel feature information, determines the wearing information of the protective equipment of the personnel feature information, and determines the risk identification result according to the protective identification corresponding to the wearing information. Otherwise, excludes the image that does not include personnel feature information. S3 performs corresponding processing according to the risk identification result. If the risk identification result is an alarm result, the personnel information associated with the personnel characteristic information is reported to the management end, and the management end is used to obtain the work risk information of all personnel at the current power grid metering site and perform corresponding notification processing. Otherwise, if the risk identification result is a safety result, the target image information of the edge end of the power grid metering site is obtained, and the target image information is the work image information of the personnel in the preset work area; In the step S2, determining the risk identification result according to the protection mark corresponding to the wearing information includes the following steps: S21 uses a target detection algorithm to extract frame information of the image information, and when the frame information contains the personnel feature information, the wearing information is determined, wherein the frame information is identification information similar to the image information of the staff member read by the target detection algorithm, S22 determines whether the detected identification information is the same as the preset identification information. If they are the same, the risk identification result is determined to be a safety result. Otherwise, the risk identification result is an alarm result. The specific alarm category is determined according to the alarm result. In the step S22, determining a specific alarm category according to the alarm determination result specifically includes: S221: when the risk identification result is an alarm result, determining an alarm type corresponding to the alarm result and an alarm interval corresponding to the alarm type, wherein the alarm type includes not wearing a safety helmet, not wearing insulating gloves, and not wearing work clothes; S222 If the alarm interval time corresponding to the current alarm type is greater than the preset interval time, the current personnel information is reported to the management end; otherwise, the number of detection events corresponding to the alarm result is determined, and the number of detection events is the number of detected persons not wearing safety helmets, not wearing insulating gloves, and not wearing protective clothing; if the number of detection events corresponding to the alarm type is different from the number of detection events of the previous alarm result, it means that the alarm result is not from the same person. At this time, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, if the number of detection events corresponding to the alarm type is the same as the number of detection events of the previous alarm result, there is no need to report the personnel information to the management end, and the image information of the power grid metering site is re-acquired.

2. The method for identifying risks in power grid metering on-site based on edge terminals according to claim 1 is characterized in that: In the step S3, reporting the personnel information associated with the personnel characteristic information to the management end includes: S31 reports and processes the information in batches according to the emergency handling capability of the personnel information, wherein the emergency handling capability of the personnel information is determined according to the personnel information associated with the personnel characteristic information and the operation capability index corresponding to the personnel information, thereby determining the emergency handling level of different personnel; S32 determines whether the emergency handling level of the current personnel is higher than the preset level. If the emergency handling level of the current personnel is lower than the preset level, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, the alarm result is sent to the corresponding personnel separately.

3. The method for identifying risks in edge-based power grid metering sites according to claim 2 is characterized in that: The step S3 further comprises: S33 The administrator of the management end responds to the management instruction fed back by the management end by broadcasting or personal email; S34: if the management instruction includes a monitoring instruction, the risk identification information of the target area where the personnel are located is updated in real time to ensure that all personnel have worn corresponding protective equipment; S35 If the management instruction includes an early warning instruction, the location information of the person is determined, and early warning prompt information is sent to the early warning device corresponding to the location information, so that the early warning device outputs safety prompt information to prompt the person holding the early warning device to wear protective equipment.

4. The method for identifying risks in the field of power grid metering based on the edge terminal according to claim 3 is characterized in that: In the step S3, if the risk identification result is a safety result, the target image information of the edge end of the power grid metering site is obtained, and in addition, the following steps are also included: S4: based on a preset time period, if no work sign is detected in the target image information, the risk identification result corresponding to the edge end is marked as an alarm result, and the personnel information associated with the edge end is reported to the management end; otherwise, go to step S5; S5: based on the preset time period, when the work sign is detected in the target image information, it means that the staff hangs the sign according to the regulations, and at this time, the continuous operation time corresponding to the target image information is determined; S6: Then, within the continuous operation time, if it is detected that the personnel characteristic information leaves the area corresponding to the target image information, the risk identification result corresponding to the edge end is marked as an alarm result, and the personnel information associated with the edge end is reported to the management end; otherwise, go to step S7; S7: if the risk identification result is a safe result, target image information of the edge end of the power grid metering site is obtained.

5. A grid metering site risk identification system based on edge terminals, characterized in that: The system includes: A collection module, used to obtain image information of multiple personnel at a power grid metering site in real time, wherein the image information includes image information of an edge end at the power grid metering site, wherein the edge end refers to a portion located between a power grid metering terminal device and a network access point; A risk identification and judgment module is used to determine whether the collected image information includes personnel feature information. If the image information includes personnel feature information, the wearing information of the protective equipment of the personnel feature information is determined, and the risk identification result is determined according to the protective identification corresponding to the wearing information. Otherwise, the image that does not include personnel feature information is excluded; The processing module is used to perform corresponding processing according to the risk identification result, specifically including: A judgment unit, used to judge whether the risk identification result is a warning result or a safety result; An alarm processing unit, if the risk identification result is an alarm result, reports the personnel information associated with the personnel characteristic information to the management end, and the management end is used to obtain the work risk information of all personnel at the current power grid metering site and perform corresponding notification processing; A safety processing unit, if the risk identification result is a safety result, obtains target image information of the edge end of the power grid metering site, wherein the target image information is work image information of personnel in a preset work area; In the risk identification and judgment module, the risk identification result is determined according to the protection mark corresponding to the wearing information, including: a detection unit, configured to extract frame information of the image information by using a target detection algorithm, and determine the wearing information when the frame information contains the personnel feature information, wherein the frame information is identification information similar to the image information of the staff member read by the target detection algorithm, A risk identification unit determines whether the detected identification information is the same as the preset identification information. If they are the same, the risk identification result is determined to be a safe result. Otherwise, the risk identification result is an alarm result. A specific alarm category is determined according to the alarm result. In the risk identification unit, determining a specific alarm category according to the alarm determination result specifically includes: When the risk identification result is an alarm result, determining an alarm type corresponding to the alarm result and an alarm interval corresponding to the alarm type, wherein the alarm type includes not wearing a safety helmet, not wearing insulating gloves, and not wearing work clothes; If the alarm interval corresponding to the current alarm type is greater than the preset interval, the personnel information is reported to the management end; otherwise, the number of detection events corresponding to the alarm result is determined, and the number of detection events is the number of detected persons not wearing safety helmets, not wearing insulating gloves, and not wearing protective clothing; if the number of detection events corresponding to the alarm type is different from the number of detections in the previous alarm result, it means that the alarm result is not from the same person. At this time, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, if the number of detection events corresponding to the alarm type is the same as the number of detections in the previous alarm result, there is no need to report the personnel information to the management end, and the image information of the power grid metering site is reacquired.

6. The edge-based grid metering on-site risk identification system according to claim 5 is characterized in that: In the alarm processing unit, reporting the personnel information associated with the personnel characteristic information to the management end includes: Reporting and processing information in batches according to the emergency handling capability of personnel information, the emergency handling capability of the personnel information is determined according to the personnel information associated with the personnel characteristic information and the operational capability index corresponding to the personnel information, thereby determining the emergency handling level of different personnel; Determine the level of emergency response of the current personnel and the preset level. If the emergency response level of the current personnel is lower than the preset level, the personnel information associated with the personnel characteristic information is reported to the management end; otherwise, the alarm result is sent to the corresponding personnel separately.

Images