Intelligent early warning method for on-site behaviors of infrastructure line operating personnel

Abstract

The invention relates to the technical field of intelligent early warning of behaviors, and particularly discloses an intelligent early warning method for on-site behaviors of an infrastructure line operator, and the method comprises the steps: judging whether a high-definition camera and a sensor arranged on an infrastructure line operation site are reliable or not, and combining the illumination intensity of the infrastructure line site, matching an intelligent early warning deviation factor of the behaviors of the infrastructure line, and carrying out the early warning of the behaviors of the infrastructure line; the method comprises the following steps: extracting an action analysis factor, a position analysis factor and a behavior abnormal degree factor of an operator site, determining an intelligent early-warning level of the field behavior of the infrastructure line operator, recording a response condition after intelligent early-warning of the field behavior of the infrastructure line operator, and evaluating an intelligent early-warning effect of the field behavior of the infrastructure line operator. The problems that traditional safety management mainly depends on manual supervision, and traditional intelligent early warning data processing capacity and dynamic response capacity of on-site behaviors of capital construction line workers are insufficient are solved, early warning is more scientific and accurate, and personalized early warning can be achieved easily.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent behavior early warning, and in particular to an intelligent on-site behavior early warning method for infrastructure line operators. Background Art

[0002] The infrastructure industry covers a wide range, including roads, bridges, power lines, communication lines and many other fields. Due to its complex working environment, such as high altitude, underground, and outdoors, workers face various dangers, such as falling, electric shock, mechanical injuries, etc. These accidents not only cause huge personal injuries to workers, but also cause project delays and economic losses. The advancement of sensor technology makes it possible to accurately obtain various data of workers. High-definition camera technology is also constantly developing. High-resolution and high-frame-rate cameras can clearly capture the behavior of workers and can work under complex lighting and environmental conditions. The development of artificial intelligence and machine learning algorithms provides powerful tools for behavior recognition, enabling intelligent early warning systems to operate efficiently and accurately.

[0003] Nowadays, there are still some shortcomings in the research on intelligent early warning of on-site behavior of infrastructure line operators. Specifically, traditional safety management mainly relies on manual supervision, and it is difficult for safety managers to monitor the behavior of each operator in real time and comprehensively. In addition, the traditional intelligent early warning data processing capabilities of on-site behavior of infrastructure line operators are insufficient, and the dynamic response capabilities are insufficient. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent early warning method for on-site behavior of infrastructure line operators, which can effectively solve the problems involved in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for intelligent early warning of on-site behavior of infrastructure line operators, comprising the following steps: analyzing the characteristics of high-definition cameras and sensors arranged at the infrastructure line operation site to determine whether the high-definition cameras and sensors are reliable: if the high-definition cameras and sensors are unreliable, a data acquisition defect warning is issued; if the high-definition cameras and sensors are reliable, the intelligent early warning deviation factor of the infrastructure line behavior is matched in combination with the light intensity at the infrastructure line site; analyzing the image data collected by the high-definition camera to extract the motion analysis factor and position analysis factor of the operator on site; analyzing the on-site behavior status of the operator to obtain the abnormal degree factor of the operator's behavior on site; determining the intelligent early warning level of the on-site behavior of the infrastructure line operator based on the motion analysis factor, position analysis factor and abnormal degree factor of the behavior, and in combination with the intelligent early warning deviation factor of the infrastructure line behavior; recording the response of the infrastructure line operator after the intelligent early warning of the on-site behavior, and evaluating the effect of the intelligent early warning of the on-site behavior of the infrastructure line operator.

[0006] As a further method, the characteristics of high-definition cameras and sensors arranged at the construction line operation site are analyzed to determine whether the high-definition cameras and sensors are reliable. The specific analysis process is: obtain the characteristic data of high-definition cameras and sensors at the operation site, which specifically include the image resolution of high-definition cameras, the frame rate of high-definition cameras, and the average response time of sensors; based on the obtained characteristic data of high-definition cameras and sensors at the operation site, a comprehensive analysis is performed to obtain the reliability characteristics of the equipment at the operation site, and the reliability characteristics of the equipment at the operation site are used as the analysis basis for determining whether the high-definition cameras and sensors are reliable; compare the reliability characteristics of the equipment at the operation site with the reliability threshold of the equipment at the operation site stored in the database; if the reliability characteristics of the equipment at the operation site are lower than the reliability threshold of the equipment at the operation site, the high-definition cameras and sensors corresponding to the reliability characteristics of the equipment at the operation site are unreliable, and a data collection defect warning is issued; if the reliability characteristics of the equipment at the operation site are not lower than the reliability threshold of the equipment at the operation site, the high-definition cameras and sensors corresponding to the reliability characteristics of the equipment at the operation site are reliable, and the intelligent warning deviation factor of the behavior of the infrastructure line is matched in combination with the light intensity at the construction line site.

[0007] As a further method, the on-site light intensity of the infrastructure line is combined to match the intelligent early warning deviation factor of the infrastructure line behavior. The specific analysis process is: obtain the on-site light intensity of the infrastructure line; store the reliability characteristics of the equipment at the operation site and the on-site light intensity of the infrastructure line as designated tags, compare the designated tags with the set tags stored in the database, obtain the set tag corresponding to the designated tag, and obtain the intelligent early warning deviation factor of the infrastructure line behavior corresponding to the set tag stored in the database.

[0008] As a further method, the image data collected by the high-definition camera is analyzed to extract the action analysis factors and position analysis factors of the operators on site. The specific analysis process is: pre-processing the collected image data and using Gaussian filtering to remove image noise: ; in, represents the pixel value of the preprocessed image at the (x, y) coordinate, G(s, t) is the Gaussian kernel function, k is the kernel radius, and I(x+s, y+t) is the pixel value of the original image at the corresponding coordinate; Based on the preprocessed image data, the mean change in the distance between the operator's head and the ground is calculated: ; in, It represents the average change of the distance between the operator's head and the ground. and are the distance between the operator's head and the ground at the i-th data point and the i-1-th data point after preprocessing, respectively. i is the number of the data point of the distance between the operator's head and the ground, i=1, 2, 3…, N, N is the total number of data points of the distance between the operator's head and the ground; Calculate the frequency of illegal climbing by operators: ; in, Indicates the frequency of illegal climbing on the tower by workers. is the number of illegal climbing on the tower by operators, and T is the total duration of infrastructure line operations; Action analysis factor, the specific analysis process is: ; In the formula, is the action analysis factor, is the compensation factor for the mean change in the distance between the operator’s head and the ground, The compensation factor for the frequency of illegal climbing on the tower by the operators; Position analysis factor, the specific analysis process is: ; in, Indicates the relative distance between the operator and each dangerous area. is the operator's location coordinate, are the coordinates of the boundary points of each dangerous area, and u is the number of each dangerous area; Determine the minimum distance between operators and hazardous areas based on the relative distance between operators and each hazardous area , and determine the operator's stay time at the minimum distance position ; ; In the formula, is the position analysis factor, The compensation factor for the minimum distance between the operator and the dangerous area is set. is the compensation factor for the operator's stay time at the minimum distance position, and e is a natural constant.

[0009] As a further method, the on-site behavioral status of the operators is analyzed to obtain the on-site behavioral abnormality degree factor of the operators. The specific analysis process is: obtaining the on-site behavioral status data of the operators, the on-site behavioral status data of the operators specifically includes the normal wearing ratio of the safety equipment of the operators, the deviation rate of the moving speed of the operators, and the deviation rate of the body inclination angle of the operators; based on the obtained on-site behavioral status data of the operators, a comprehensive analysis is performed to obtain the on-site behavioral abnormality degree factor of the operators, and the behavioral abnormality degree factor is used as the analysis basis for determining the on-site behavior intelligent warning level of the infrastructure line operators.

[0010] As a further method, the behavior abnormality degree factor, the specific analysis process is: ; In the formula, is the factor of abnormal behavior, scd is the normal wearing ratio of safety equipment for operators, ydp is the deviation rate of operator movement speed, qxj is the deviation rate of operator body tilt angle, is the compensation factor of the set scd, is the compensation factor of the set ydp, is the compensation factor of the set qxj.

[0011] As a further method, based on the action analysis factor, the position analysis factor and the behavior abnormality degree factor, and combined with the intelligent warning deviation factor of the infrastructure line behavior, the intelligent warning level of the on-site behavior of the infrastructure line operators is determined. The specific analysis process is: based on the action analysis factor, the position analysis factor and the behavior abnormality degree factor, and combined with the intelligent warning deviation factor of the infrastructure line behavior, a comprehensive analysis is performed to obtain the on-site behavior warning signal of the infrastructure line operators. The on-site behavior warning signal of the infrastructure line operators is used as the analysis basis for determining the intelligent warning level of the on-site behavior of the infrastructure line operators; the on-site behavior warning signal of the infrastructure line operators is compared with the intermediate warning range of the on-site behavior of the infrastructure line operators stored in the database; if the on-site behavior warning signal of the infrastructure line operators belongs to the on-site intelligent warning range of the infrastructure line operators If the on-site behavior warning signal of the infrastructure line operator falls within the intermediate warning range of on-site behavior of the infrastructure line operator, then the intelligent warning level of on-site behavior of the infrastructure line operator corresponding to the on-site behavior warning signal of the infrastructure line operator is level two; if the on-site behavior warning signal of the infrastructure line operator does not fall within the intermediate warning range of on-site behavior of the infrastructure line operator, and is higher than the maximum value of the on-site behavior warning range of the infrastructure line operator, then the intelligent warning level of on-site behavior of the infrastructure line operator corresponding to the on-site behavior warning signal of the infrastructure line operator is level one; if the on-site behavior warning signal of the infrastructure line operator does not fall within the intermediate warning range of on-site behavior of the infrastructure line operator, and is lower than the minimum value of the on-site behavior warning range of the infrastructure line operator, then the intelligent warning level of on-site behavior of the infrastructure line operator corresponding to the on-site behavior warning signal of the infrastructure line operator is level three.

[0012] As a further method, the on-site behavior warning signals of infrastructure line operators are analyzed in the following specific process: ; In the formula, Provides early warning signals for on-site behavior of infrastructure line operators. It is the intelligent early warning deviation factor of infrastructure line behavior. is the action analysis factor, is the position analysis factor, is the factor of abnormal behavior degree, and e is a natural constant.

[0013] As a further method, the response of the infrastructure line operators after the intelligent warning of the on-site behavior is recorded, and the effect of the intelligent warning of the on-site behavior of the infrastructure line operators is evaluated. The specific analysis process is as follows: Based on the recorded on-site behavior of infrastructure line operators, the response to the intelligent warning is calculated to calculate the warning efficiency: ; In the formula, To ensure effective early warning, is the total number of corrected behaviors, is the total number of warnings; Calculate the average response time: ; In the formula, is the average response time, is the response time of the cth correct corrective action, c is the number of each correct corrective action, c=1, 2, 3…, ; Calculate the false positive rate: ; In the formula, is the false alarm rate, is the number of false positives; Based on a comprehensive analysis of the warning efficiency, average response time and false alarm rate, an intelligent warning response analysis factor is obtained, and the intelligent warning response analysis factor is used as an analysis basis for evaluating the intelligent warning effect of the on-site behavior of infrastructure line operators; the intelligent warning response analysis factor is compared with the intelligent warning response analysis threshold stored in the database; if the intelligent warning response analysis factor is not lower than the intelligent warning response analysis threshold, the intelligent warning effect of the on-site behavior of the infrastructure line operators corresponding to the intelligent warning response analysis factor is excellent; if the intelligent warning response analysis factor is lower than the intelligent warning response analysis threshold, the intelligent warning effect of the on-site behavior of the infrastructure line operators corresponding to the intelligent warning response analysis factor is poor.

[0014] As a further method, intelligent early warning response analysis factors, the specific analysis process is: ; In the formula, It is the intelligent early warning response analysis factor.

[0015] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention provides an intelligent early warning method for the on-site behavior of infrastructure line operators, analyzes the characteristics of high-definition cameras and sensors, can control quality, help to promptly discover equipment with problems, avoid data errors or missing due to equipment failures, and dynamically adjust the analysis strategy according to the lighting conditions to reduce misjudgments caused by lighting problems. By extracting motion analysis factors and position analysis factors from image data and analyzing the degree of abnormal behavior factors, the on-site behavior of operators can be fully and carefully understood.

[0016] (2) The present invention determines the warning level based on multiple factors and combines the warning deviation factor, making the warning more scientific and accurate. Recording the response after the warning and evaluating the warning effect helps to discover the advantages and disadvantages of the warning system. By statistically analyzing indicators such as the response time of the operators to the warning and the correctness of the corrective behavior, the effectiveness of the warning system in actual application can be understood and the performance of the warning system can be improved.

[0017] (3) The present invention ensures data quality by judging whether high-definition cameras and sensors are reliable, combining the on-site light intensity of the infrastructure line, and matching the intelligent early warning deviation factor of the infrastructure line behavior. Unreliable equipment will produce erroneous data, such as blurred camera images, sensor data drift or loss, etc. Checking the reliability of the equipment in advance can timely discover and solve these potential data quality risks.

[0018] (4) The deviation factor of intelligent early warning of infrastructure line behavior can compensate for the behavior judgment deviation caused by environmental factors and equipment characteristics. Ensuring equipment reliability and considering lighting factors can reduce the interference of external factors on the early warning system and help achieve personalized early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0020] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0021] Figure 2 A flow chart of the steps to determine whether the HD camera and sensor are reliable. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] Reference Figure 1As shown, the present invention provides an intelligent early warning method for on-site behavior of infrastructure line operators, including: analyzing the characteristics of high-definition cameras and sensors arranged at the infrastructure line operation site to determine whether the high-definition cameras and sensors are reliable: if the high-definition cameras and sensors are unreliable, a data collection defect warning is issued; if the high-definition cameras and sensors are reliable, the infrastructure line behavior intelligent early warning deviation factor is matched in combination with the on-site light intensity of the infrastructure line.

[0024] like Figure 2 As shown, the specific analysis process is: obtain the characteristic data of the high-definition camera and sensor at the operation site, which specifically includes the image resolution of the high-definition camera, the frame rate of the high-definition camera, and the average response time of the sensor; based on the obtained characteristic data of the high-definition camera and sensor at the operation site, comprehensively analyze and obtain the reliability characteristics of the equipment at the operation site, and use the reliability characteristics of the equipment at the operation site as the analysis basis for judging whether the high-definition camera and sensor are reliable; compare the reliability characteristics of the equipment at the operation site with the reliability threshold of the equipment at the operation site stored in the database; If the reliability characteristics of the equipment on the job site are lower than the reliability threshold of the equipment on the job site, the high-definition cameras and sensors corresponding to the reliability characteristics of the equipment on the job site are unreliable, and a data collection defect warning is issued and they need to be replaced; if the reliability characteristics of the equipment on the job site are not lower than the reliability threshold of the equipment on the job site, the high-definition cameras and sensors corresponding to the reliability characteristics of the equipment on the job site are reliable, and the infrastructure line behavior intelligent warning deviation factor is matched based on the on-site light intensity of the infrastructure line.

[0025] The reliability characteristics of equipment at the operation site, the specific analysis process is as follows: ; In the formula, is the reliability characteristic of the equipment at the work site, tfb is the image resolution of the HD camera, tzl is the frame rate of the HD camera, xys is the average response time of the sensor, is the compensation factor of the set tfb, is the compensation factor of the set tzl, is the compensation factor of the set xys.

[0026] Normalize tfb, tzl, xys and all the following parameters.

[0027] It should be explained that the compensation factors of TFB, TZL, and XYS set above are obtained from the database. According to the historical data, a mapping set of the historically measured HD camera image resolution, HD camera frame rate, average sensor response time and the compensation factors of TFB, TZL, and XYS is established to obtain the compensation factors of TFB, TZL, and XYS corresponding to the current TFB, TZL, and XYS.

[0028] It should be noted that the following , , , , , , They are also obtained through a mapping set of historical data and compensation factors established in a database, that is, the corresponding compensation factors are obtained according to the current data.

[0029] By acquiring key feature data such as the image resolution, frame rate, and average sensor response time of high-definition cameras, we can fully understand the performance of the equipment. Image resolution and frame rate directly affect the camera's ability to capture the details of the operator's behavior. The higher the resolution and the faster the frame rate, the more accurate the recording of the operator's actions and positions. The average sensor response time reflects the timeliness of the sensor's acquisition of data. The shorter the response time, the more time-effective the data. This comprehensive consideration of multiple equipment characteristics avoids the one-sidedness caused by judging the reliability of the equipment based on only a single factor.

[0030] Comparing the reliability characteristics of the equipment at the work site with the reliability threshold of the equipment at the work site stored in the database provides a clear judgment standard. This precise judgment of the equipment status can avoid using data collected by unreliable equipment. At the construction line operation site, these invalid data are prevented from entering the subsequent analysis process, improving the accuracy of the entire early warning system. When the equipment is reliable, the intelligent early warning deviation factor of the infrastructure line behavior is matched with the light intensity at the construction line site, which can further optimize the performance of the early warning system and adapt to problems such as image overexposure or shadow interference caused by light, thereby improving the accuracy of the on-site behavior analysis of the operators and providing guarantees for accurate early warning.

[0031] Obtain the on-site light intensity of the infrastructure line; store the reliability characteristics of the equipment at the work site and the on-site light intensity of the infrastructure line as a specified tag, compare the specified tag with each set tag stored in the database, obtain the set tag corresponding to the specified tag, and obtain the infrastructure line behavior intelligent early warning deviation factor corresponding to the set tag stored in the database.

[0032] By comparing the specified tag with each set tag stored in the database, the matching set tag can be found quickly. The uniqueness and relevance of the tag are utilized, and the comparison operation can be completed in a short time through an efficient algorithm. The intelligent early warning deviation factor of the infrastructure line behavior corresponding to the set tag stored in the database is obtained, so that the early warning system can provide personalized early warning strategies according to the actual situation of the operation site (equipment reliability and light intensity). Accurate deviation factor matching can effectively improve the accuracy of the intelligent early warning of infrastructure line behavior.

[0033] The image data collected by the high-definition camera is analyzed to extract the motion analysis factors and position analysis factors of the operators on site.

[0034] The specific analysis process is: pre-process the collected image data and use Gaussian filtering to remove image noise: ; in, represents the pixel value of the preprocessed image at the (x, y) coordinate, G(s, t) is the Gaussian kernel function, k is the kernel radius, and I(x+s, y+t) is the pixel value of the original image at the corresponding coordinate; Based on the preprocessed image data, the mean change in the distance between the operator's head and the ground is calculated: ; in, It represents the average change of the distance between the operator's head and the ground. and are the distance between the operator's head and the ground at the i-th data point and the i-1-th data point after preprocessing, respectively. i is the number of the data point of the distance between the operator's head and the ground, i=1, 2, 3…, N, N is the total number of data points of the distance between the operator's head and the ground; Calculate the frequency of illegal climbing by operators: ; in, Indicates the frequency of illegal climbing on the tower by workers. is the number of illegal climbing on the tower by operators, and T is the total duration of infrastructure line operations; Action analysis factor, the specific analysis process is: ; In the formula, is the action analysis factor, is the compensation factor for the mean change in the distance between the operator’s head and the ground, The compensation factor for the frequency of illegal climbing on the tower by the operators; Position analysis factor, the specific analysis process is: ; in, Indicates the relative distance between the operator and each dangerous area. is the operator's location coordinate, are the coordinates of the boundary points of each dangerous area, and u is the number of each dangerous area.

[0035] Determine the minimum distance between operators and hazardous areas based on the relative distance between operators and each hazardous area , and determine the operator's stay time at the minimum distance position ; ; In the formula, is the position analysis factor, The compensation factor for the minimum distance between the operator and the dangerous area is set. is the compensation factor for the operator's stay time at the minimum distance position, and e is a natural constant.

[0036] Images collected at the construction line operation site are subject to interference from various factors, such as changes in ambient light and electronic noise from the equipment itself. By processing the image with the Gaussian filter formula, these noises can be effectively reduced, making the image clearer. Clear images are essential for the subsequent accurate extraction of various features of the operator. The preprocessed image provides a more reliable data basis for the subsequent calculation of features such as the mean amplitude of the distance change between the operator's head and the ground. The presence of noise can lead to deviations in feature extraction such as distance measurement. After filtering, this deviation will be reduced, thereby improving the accuracy of feature extraction.

[0037] The calculation of the motion analysis factor comprehensively considers two important motion-related factors: the mean change in the distance between the operator's head and the ground and the frequency of illegal climbing. Combining these two factors can more comprehensively evaluate the operator's motion behavior. The mean change in the distance between the operator's head and the ground reflects the stability of the operator's motion in the vertical direction. For example, when working at height, a large change in the distance means that the operator loses balance or performs dangerous actions. The frequency of illegal climbing directly reflects whether the operator complies with safety regulations during climbing operations.

[0038] The calculation of the location analysis factor accurately calculates the relative distance between the operator and each dangerous area through a formula. There are various dangerous areas at the construction line operation site, such as high-voltage equipment areas, deep pit edges, etc. Accurately determining the distance between the operator and these dangerous areas is the key to ensuring the safety of the operation. Real-time monitoring of whether the operator is approaching the dangerous area provides important data support for timely warning. In addition to the distance factor, the location analysis factor also takes into account the operator's stay time at the minimum distance position. If the operator only approaches the dangerous area briefly, the risk level is relatively low, but if he stays near the dangerous area for a long time, the risk will increase greatly.

[0039] The on-site behavioral status of the operators is analyzed to obtain the on-site behavioral abnormality factor of the operators.

[0040] Specifically, the on-site behavioral status of the operating personnel is analyzed to obtain the on-site behavioral abnormality degree factor of the operating personnel. The specific analysis process is: obtaining the on-site behavioral status data of the operating personnel, the on-site behavioral status data of the operating personnel specifically includes the normal wearing ratio of the operating personnel's safety equipment, the operating personnel's moving speed deviation rate, and the operating personnel's body inclination angle deviation rate; based on the obtained on-site behavioral status data of the operating personnel, a comprehensive analysis is performed to obtain the on-site behavioral abnormality degree factor of the operating personnel, and the behavioral abnormality degree factor is used as the analysis basis for determining the on-site behavior intelligent warning level of the infrastructure line operating personnel.

[0041] The specific analysis process of the behavioral abnormality factor is as follows: ; In the formula, is the factor of abnormal behavior, scd is the normal wearing ratio of safety equipment for operators, ydp is the deviation rate of operator movement speed, qxj is the deviation rate of operator body tilt angle, is the compensation factor of the set scd, is the compensation factor of the set ydp, is the compensation factor of the set qxj.

[0042] By obtaining multi-dimensional on-site behavior status data such as the normal wearing ratio of safety equipment for operators, the deviation rate of operator movement speed, and the deviation rate of operator body inclination angle, the behavior of operators can be fully understood. The wearing of safety equipment is the basis for ensuring the life safety of operators. The deviation of movement speed indicates whether the operator is in an abnormal state, and the deviation of body inclination angle is closely related to the balance state and operational norms of the operator. This multi-dimensional data collection method avoids the limitations of single factor evaluation and can more accurately grasp the overall behavior status of operators. The behavioral abnormality factor, as an analytical basis for determining the intelligent early warning level of on-site behavior of infrastructure line operators, can provide more scientific and reasonable decision support for the early warning system. The deviation rate is the ratio of the absolute value of the difference between the actual value and the reference value to the reference value.

[0043] Based on the motion analysis factor, position analysis factor and behavior abnormality degree factor, and combined with the infrastructure line behavior intelligent early warning deviation factor, the on-site behavior intelligent early warning level of infrastructure line operators is determined.

[0044] The specific analysis process is as follows: based on the action analysis factor, the position analysis factor and the behavior abnormality degree factor, combined with the infrastructure line behavior intelligent early warning deviation factor, a comprehensive analysis is performed to obtain the on-site behavior early warning signal of the infrastructure line operator, and the on-site behavior early warning signal of the infrastructure line operator is used as the analysis basis for determining the on-site behavior intelligent early warning level of the infrastructure line operator; the on-site behavior early warning signal of the infrastructure line operator is compared with the on-site behavior intermediate early warning range of the infrastructure line operator stored in the database; If the infrastructure line operator on-site behavior warning signal belongs to the infrastructure line operator on-site behavior intermediate warning range, the infrastructure line operator on-site behavior intelligent warning level corresponding to the infrastructure line operator on-site behavior warning signal is level 2; If the infrastructure line operator on-site behavior warning signal does not belong to the infrastructure line operator on-site behavior intermediate warning range, and is higher than the maximum value of the infrastructure line operator on-site behavior intermediate warning range, then the infrastructure line operator on-site behavior intelligent warning level corresponding to the infrastructure line operator on-site behavior warning signal is level one; If the on-site behavior warning signal of infrastructure line operators does not fall within the intermediate warning range of on-site behavior of infrastructure line operators, and is lower than the minimum value of the intermediate warning range of on-site behavior of infrastructure line operators, then the on-site behavior intelligent warning level of infrastructure line operators corresponding to the on-site behavior warning signal of infrastructure line operators is level three, and the intermediate warning range of on-site behavior of infrastructure line operators is the left closed and right closed interval.

[0045] The on-site behavior warning signals of infrastructure line operators, the specific analysis process is as follows: ; In the formula, Provides early warning signals for on-site behavior of infrastructure line operators. It is the intelligent early warning deviation factor of infrastructure line behavior.

[0046] By combining the action analysis factor, position analysis factor, behavior abnormality degree factor and infrastructure line behavior intelligent warning deviation factor to calculate the on-site behavior warning signal of infrastructure line operators, multiple key aspects of operator behavior can be comprehensively considered. The action analysis factor can reflect whether the operator's operating action is standardized, whether there is a frequency of dangerous actions, etc.; the position analysis factor can reflect the distance and stay of the operator from the dangerous area; the behavior abnormality degree factor covers comprehensive behavioral states such as the wearing of safety equipment, moving speed and body tilt angle. This fusion method avoids the one-sidedness caused by relying on a single factor for warning, so that the warning signal can more comprehensively reflect the actual situation on site.

[0047] The generated warning signals of the on-site behavior of the construction line operators are compared with the intermediate warning range stored in the database to divide the warning level. This method provides a clear and objective grading standard. By determining whether the warning signal belongs to the intermediate warning range, and the degree above or below the range, the warning level is divided into one, two, and three levels, making the division of the warning level more accurate and reasonable. When the value of the warning signal is within the intermediate warning range, it is judged as a second-level warning, which indicates that the behavior of the operator has a certain degree of risk and needs attention; when it is higher than the maximum value of the intermediate warning range, it is judged as a first-level warning, which means that the risk is relatively low, but it still needs to be continuously monitored; and when it is lower than the minimum value of the intermediate warning range, it is judged as a third-level warning, indicating that the situation is more critical and immediate measures need to be taken.

[0048] Accurate warning level classification helps to reasonably allocate safety management resources and optimize emergency response. For level 3 warning, more safety resources can be deployed immediately, such as emergency rescue personnel and equipment, and operators are required to stop current dangerous behaviors immediately; for level 2 warning, on-site supervision and guidance can be strengthened; for level 1 warning, regular monitoring methods can be used to monitor it. Targeted measures can be taken according to the level of risk to improve the efficiency and effectiveness of safety management.

[0049] Record the response of infrastructure line operators after intelligent early warning of on-site behavior, and evaluate the effectiveness of intelligent early warning of on-site behavior of infrastructure line operators.

[0050] Based on the recorded on-site behavior of infrastructure line operators, the response to the intelligent warning is calculated to calculate the warning efficiency: ; In the formula, To ensure effective early warning, is the total number of corrected behaviors, is the total number of warnings; Calculate the average response time: ; In the formula, is the average response time, is the response time of the cth correct corrective action, c is the number of each correct corrective action, c=1, 2, 3…, ; Calculate the false positive rate: ; In the formula, is the false alarm rate, is the number of false positives; Based on a comprehensive analysis of the warning efficiency, average response time and false alarm rate, an intelligent warning response analysis factor is obtained, and the intelligent warning response analysis factor is used as an analysis basis for evaluating the intelligent warning effect of the on-site behavior of infrastructure line operators; the intelligent warning response analysis factor is compared with the intelligent warning response analysis threshold stored in the database; if the intelligent warning response analysis factor is not lower than the intelligent warning response analysis threshold, the intelligent warning effect of the on-site behavior of the infrastructure line operators corresponding to the intelligent warning response analysis factor is excellent; if the intelligent warning response analysis factor is lower than the intelligent warning response analysis threshold, the intelligent warning effect of the on-site behavior of the infrastructure line operators corresponding to the intelligent warning response analysis factor is poor.

[0051] Intelligent early warning response analysis factors, the specific analysis process is: ; In the formula, It is the intelligent early warning response analysis factor.

[0052] The calculation of early warning efficiency, average response time and false alarm rate to comprehensively analyze the intelligent early warning response analysis factors can comprehensively evaluate the effect of the intelligent early warning system for on-site behavior of infrastructure line operators. Early warning efficiency reflects the proportion of early warning systems that successfully prompt operators to correctly correct dangerous behaviors, and is a key indicator for measuring the effectiveness of early warning systems; the average response time reflects the speed of operators' response to early warning information. The shorter the response time, the more timely the early warning system can avoid danger; the false alarm rate indicates the situation where the early warning system mistakenly issues an alarm. A high false alarm rate will reduce the credibility of the system. This multi-indicator comprehensive consideration method avoids the one-sidedness of relying on only a single indicator to evaluate the early warning effect. This clear effect judgment can provide targeted directions for the improvement of the early warning system.

[0053] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. An intelligent early warning method for on-site behavior of infrastructure line operators, characterized in that: The following steps are involved: Analyze the characteristics of high-definition cameras and sensors deployed at the infrastructure line operation site to determine whether the high-definition cameras and sensors are reliable: If the high-definition camera and sensor are unreliable, an early warning of data collection defects will be issued; If the high-definition camera and sensor are reliable, the intelligent early warning deviation factor of the infrastructure line behavior will be matched in combination with the on-site light intensity of the infrastructure line; Analyze the image data collected by the high-definition camera to extract the action analysis factors and position analysis factors of the operators on site; Analyze the on-site behavior status of the operators to obtain the abnormal degree factor of the on-site behavior of the operators; Based on the action analysis factor, location analysis factor and behavior abnormality factor, combined with the infrastructure line behavior intelligent early warning deviation factor, the on-site behavior intelligent early warning level of infrastructure line operators is determined; Record the response of infrastructure line operators after intelligent early warning of on-site behavior, and evaluate the effectiveness of intelligent early warning of on-site behavior of infrastructure line operators.

2. According to claim 1, a method for intelligent early warning of on-site behavior of infrastructure line operators is characterized by: The characteristics of the high-definition cameras and sensors arranged at the infrastructure line operation site are analyzed to determine whether the high-definition cameras and sensors are reliable. The specific analysis process is as follows: Obtain feature data of high-definition cameras and sensors at the work site, including image resolution of high-definition cameras, frame rate of high-definition cameras, and average response time of sensors; Based on the acquired feature data of the high-definition cameras and sensors at the work site, the reliability characteristics of the equipment at the work site are obtained through comprehensive analysis. The reliability characteristics of the equipment at the work site are used as the analysis basis for judging whether the high-definition cameras and sensors are reliable. comparing the job site equipment reliability characteristics with job site equipment reliability thresholds stored in a database; If the reliability characteristic of the equipment on the job site is lower than the reliability threshold of the equipment on the job site, the high-definition camera and sensor corresponding to the reliability characteristic of the equipment on the job site are unreliable, and a data collection defect warning is issued; If the reliability characteristics of the equipment at the work site are not lower than the reliability threshold of the equipment at the work site, the high-definition camera and sensor corresponding to the reliability characteristics of the equipment at the work site are reliable. Combined with the on-site light intensity of the infrastructure line, the intelligent early warning deviation factor of the infrastructure line behavior is matched.

3. According to claim 2, a method for intelligent early warning of on-site behavior of infrastructure line operators is characterized by: The above method combines the on-site illumination intensity of the infrastructure line to match the intelligent warning deviation factor of the infrastructure line behavior. The specific analysis process is as follows: Obtain the light intensity of infrastructure line sites; The reliability characteristics of the equipment at the work site and the light intensity at the infrastructure line site are stored as designated tags, and the designated tags are compared with the set tags stored in the database to obtain the set tag corresponding to the designated tag, and the intelligent early warning deviation factor of the infrastructure line behavior corresponding to the set tag stored in the database is obtained.

4. According to claim 1, a method for intelligent early warning of on-site behavior of infrastructure line operators is characterized by: The image data collected by the high-definition camera is analyzed to extract the action analysis factors and position analysis factors of the operators on site. The specific analysis process is as follows: Preprocess the collected image data and use Gaussian filtering to remove image noise: ； in, represents the pixel value of the preprocessed image at the (x, y) coordinate, G(s, t) is the Gaussian kernel function, k is the kernel radius, and I(x+s, y+t) is the pixel value of the original image at the corresponding coordinate; Based on the preprocessed image data, the mean change in the distance between the operator's head and the ground is calculated: ； in, It represents the average change of the distance between the operator's head and the ground. and are the distance between the operator's head and the ground at the i-th data point and the i-1-th data point after preprocessing, respectively. i is the number of the data point of the distance between the operator's head and the ground, i=1, 2, 3…, N, N is the total number of data points of the distance between the operator's head and the ground; Calculate the frequency of illegal climbing by operators: ； in, Indicates the frequency of illegal climbing on the tower by workers. is the number of illegal climbing on the tower by operators, and T is the total duration of infrastructure line operations; Action analysis factor, the specific analysis process is: ； In the formula, is the action analysis factor, is the compensation factor for the mean change in the distance between the operator’s head and the ground, The compensation factor for the frequency of illegal climbing on the tower by the operators; Position analysis factor, the specific analysis process is: ； in, Indicates the relative distance between the operator and each dangerous area. is the operator's location coordinate, are the coordinates of the boundary points of each dangerous area, and u is the number of each dangerous area; Determine the minimum distance between operators and hazardous areas based on the relative distance between operators and each hazardous area , and determine the operator's stay time at the minimum distance position ; ； In the formula, is the position analysis factor, The compensation factor for the minimum distance between the operator and the dangerous area is set. is the compensation factor for the operator's stay time at the minimum distance position, and e is a natural constant.

5. According to claim 1, a method for intelligent early warning of on-site behavior of infrastructure line operators is characterized by: The on-site behavior status of the operator is analyzed to obtain the on-site behavior abnormality factor of the operator. The specific analysis process is as follows: Obtaining the on-site behavior status data of the operators, which specifically includes the normal wearing rate of safety equipment of the operators, the deviation rate of the movement speed of the operators, and the deviation rate of the body inclination angle of the operators; Based on the acquired on-site behavior status data of the operators, a comprehensive analysis is conducted to obtain the on-site behavior abnormality degree factor of the operators. The behavior abnormality degree factor is used as the analysis basis for determining the on-site behavior intelligent early warning level of the infrastructure line operators.

6. The intelligent early warning method for on-site behavior of infrastructure line operators according to claim 5 is characterized by: The specific analysis process of the abnormal behavior degree factor is as follows: ； In the formula, is the factor of abnormal behavior, scd is the normal wearing ratio of safety equipment for operators, ydp is the deviation rate of operator movement speed, qxj is the deviation rate of operator body tilt angle, is the compensation factor of the set scd, is the compensation factor of the set ydp, is the compensation factor of the set qxj.

7. The intelligent early warning method for on-site behavior of infrastructure line operators according to claim 1 is characterized by: Based on the action analysis factor, the position analysis factor and the behavior abnormality degree factor, and combined with the infrastructure line behavior intelligent early warning deviation factor, the on-site behavior intelligent early warning level of the infrastructure line operator is determined. The specific analysis process is as follows: Based on the action analysis factor, position analysis factor and behavior abnormality degree factor, combined with the infrastructure line behavior intelligent early warning deviation factor, a comprehensive analysis is performed to obtain the on-site behavior early warning signal of the infrastructure line operator. The on-site behavior early warning signal of the infrastructure line operator is used as the analysis basis for determining the on-site behavior intelligent early warning level of the infrastructure line operator. Compare the on-site behavior warning signal of the infrastructure line operator with the intermediate warning range of the on-site behavior of the infrastructure line operator stored in the database; If the infrastructure line operator on-site behavior warning signal belongs to the infrastructure line operator on-site behavior intermediate warning range, the infrastructure line operator on-site behavior intelligent warning level corresponding to the infrastructure line operator on-site behavior warning signal is level 2; If the infrastructure line operator on-site behavior warning signal does not belong to the infrastructure line operator on-site behavior intermediate warning range, and is higher than the maximum value of the infrastructure line operator on-site behavior intermediate warning range, then the infrastructure line operator on-site behavior intelligent warning level corresponding to the infrastructure line operator on-site behavior warning signal is level one; If the on-site behavior warning signal of infrastructure line operators does not fall within the intermediate warning range of on-site behavior of infrastructure line operators, and is lower than the minimum value of the intermediate warning range of on-site behavior of infrastructure line operators, then the on-site behavior intelligent warning level of infrastructure line operators corresponding to the on-site behavior warning signal of infrastructure line operators is level three.

8. The intelligent early warning method for on-site behavior of infrastructure line operators according to claim 7 is characterized by: The specific analysis process of the on-site behavior warning signal of the infrastructure line operator is as follows: ； In the formula, Provides early warning signals for on-site behavior of infrastructure line operators. It is the intelligent early warning deviation factor of infrastructure line behavior. is the action analysis factor, is the position analysis factor, is the factor of abnormal behavior degree, and e is a natural constant.

9. The intelligent early warning method for on-site behavior of infrastructure line operators according to claim 1 is characterized by: The response to the intelligent warning of the on-site behavior of the infrastructure line operators is recorded, and the effect of the intelligent warning of the on-site behavior of the infrastructure line operators is evaluated. The specific analysis process is as follows: Based on the recorded on-site behavior of infrastructure line operators, the response after intelligent warning is calculated to calculate the warning efficiency: ； In the formula, To ensure effective early warning, is the total number of corrected behaviors, is the total number of warnings; Calculate the average response time: ； In the formula, is the average response time, is the response time of the cth correct corrective action, c is the number of each correct corrective action, c=1, 2, 3…, ; Calculate the false positive rate: ； In the formula, is the false alarm rate, is the number of false positives; Based on the comprehensive analysis of early warning efficiency, average response time and false alarm rate, the intelligent early warning response analysis factor is obtained. The intelligent early warning response analysis factor is used as the analysis basis for evaluating the intelligent early warning effect of on-site behavior of infrastructure line operators. comparing the intelligent early warning response analysis factor with the intelligent early warning response analysis threshold stored in the database; If the intelligent early warning response analysis factor is not lower than the intelligent early warning response analysis threshold, the intelligent early warning effect of the on-site behavior of the infrastructure line operator corresponding to the intelligent early warning response analysis factor is excellent; If the intelligent early warning response analysis factor is lower than the intelligent early warning response analysis threshold, the intelligent early warning effect of the on-site behavior of the infrastructure line operators corresponding to the intelligent early warning response analysis factor is poor.

10. The intelligent early warning method for on-site behavior of infrastructure line operators according to claim 9, characterized in that: The specific analysis process of the intelligent early warning response analysis factor is as follows: ； In the formula, It is the intelligent early warning response analysis factor.

Images