Illegal behavior warning method for construction operation area and related equipment

Abstract

The invention discloses an illegal behavior warning method for a construction operation area and related equipment, and relates to the technical field of computers, the illegal behavior warning method for the construction operation area comprises the following steps: receiving an initial monitoring signal sent by safety management equipment, and collecting picture information of the construction operation area and safety equipment sensor data; based on a preset artificial intelligence model, performing security equipment violation behavior analysis on the security equipment sensor data and the picture information to obtain a violation behavior analysis result; and executing a corresponding alarm scheme according to the illegal behavior recognition result. According to the method and the device, the security equipment violation behavior analysis is performed on the security equipment sensor data and the picture information to obtain the violation behavior analysis result, and when the violation behavior occurs in the construction operation area, the violation behavior identification is realized through the artificial intelligence model, and the corresponding alarm scheme is executed, so that the security management of the violation behavior is realized. And thus, the efficiency of illegal behavior warning is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and related equipment for warning of illegal behavior in a construction operation area. Background Art

[0002] With the rapid development of industrialization and urbanization, the safety issues in special operation areas have received more and more attention. Due to their special working environment and potential high risks, these areas have clear regulations on the behavior of operators, but often due to lax supervision, operators perform illegal behaviors, causing serious losses. Therefore, how to identify illegal behaviors in construction operation areas has become a problem of concern.

[0003] At present, the violation warning in the construction area mainly relies on manual inspection and video monitoring system. However, manual inspection has problems such as low efficiency, limited coverage, and susceptibility to human factors. Although the video monitoring system can provide real-time images, it is limited by the monitoring range and angle, and requires a large amount of manpower for real-time monitoring, making it difficult to achieve comprehensive and efficient violation warning, resulting in reduced efficiency of violation warning.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a method and related equipment for warning of violations in a construction area, aiming to solve the technical problem of low efficiency of warning of violations.

[0006] To achieve the above purpose, the present application proposes a method for warning of illegal behavior in a construction area, the method comprising:

[0007] Receive the start monitoring signal sent by the safety management equipment, collect the image information of the construction area and the sensor data of the safety equipment;

[0008] Based on a preset artificial intelligence model, the safety equipment sensor data and the image information are analyzed for safety equipment violations to obtain violation analysis results;

[0009] According to the violation identification results, the corresponding alarm plan is executed.

[0010] In one embodiment, the step of performing safety device violation analysis on the safety device sensor data and the image information based on a preset artificial intelligence model to obtain the violation analysis result includes:

[0011] Preprocessing the safety device sensor data to obtain safety device sensor information;

[0012] Extracting safety behaviors from the image information through a preset behavior extraction model to obtain safety behavior information;

[0013] fusing the safety device sensor information with the safety behavior information to obtain a comprehensive feature data set;

[0014] The artificial intelligence model is used to analyze the safety equipment violation behavior of the comprehensive feature data set to obtain the violation behavior analysis result.

[0015] In one embodiment, the step of extracting safety behaviors from the picture information by using a preset behavior extraction model to obtain safety behavior information includes:

[0016] Obtain screen information samples and safety behavior information labels;

[0017] Sending the picture information sample to a preset model to be trained;

[0018] Based on the model to be trained, extracting safety behaviors from the image information sample to obtain safety behavior information extraction results;

[0019] Analyze the difference between the safety behavior information extraction result and the safety behavior information label to obtain an extraction loss value;

[0020] If the extracted loss value does not meet the preset loss standard, return to the step of extracting safe behaviors from the picture information sample based on the model to be trained to obtain safe behavior information extraction results, and stop training until the extracted loss value meets the loss standard to obtain a behavior extraction model that meets the loss standard.

[0021] In one embodiment, the step of fusing the safety device sensor information with the safety behavior information to obtain a comprehensive feature data set includes:

[0022] Based on a feature matching algorithm, aligning the time series features of the safety device sensor information and the safety behavior information;

[0023] Based on a data fusion algorithm, the feature vectors of the safety device sensor information and the safety behavior information are merged to form a comprehensive feature data set.

[0024] In one embodiment, the step of combining the feature vectors of the safety device sensor information and the safety behavior information based on a data fusion algorithm to form a comprehensive feature data set includes:

[0025] Through feature selection and feature extraction technology, the comprehensive feature data set is enhanced to obtain a comprehensive feature data set after feature enhancement.

[0026] In one embodiment, the step of executing a corresponding warning scheme according to the violation identification result includes:

[0027] Determine the warning level according to the severity of the violation identification result and the type of violation;

[0028] If the alarm level is a low-level alarm, the preset security management device is notified via a pop-up window on the interface or an email;

[0029] If the alarm level is a medium-level alarm, the preset security management device is notified via an interface pop-up window or email, and a message is pushed to the preset emergency contact device via SMS or mobile application;

[0030] If the alarm level is a high-level alarm, the preset emergency response procedure is initiated to trigger the emergency broadcast system.

[0031] In addition, to achieve the above purpose, the present application also proposes a violation warning device for a construction work area, the violation warning device for the construction work area comprising:

[0032] The acquisition module is used to receive the start monitoring signal sent by the safety management equipment and collect the image information of the construction area and the sensor data of the safety equipment;

[0033] An analysis module, used to analyze the safety equipment sensor data and the image information for safety equipment violations based on a preset artificial intelligence model to obtain a violation analysis result;

[0034] The alarm module is used to execute corresponding alarm plans based on the violation identification results.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a construction area violation alarm device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the construction area violation alarm method as described above.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the violation warning method in the construction work area as described above are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the violation warning method in the construction work area as described above.

[0038] One or more technical solutions proposed in this application have at least the following technical effects:

[0039] Compared with the related technologies, it mainly relies on manual inspection and video monitoring system. However, manual inspection has problems such as low efficiency, limited coverage, and susceptibility to human factors. Although the video monitoring system can provide real-time images, it is limited by the monitoring range and angle, and requires a large amount of manpower for real-time monitoring, making it difficult to achieve comprehensive and efficient violation warnings, resulting in reduced efficiency of violation warnings. In comparison, this application receives the starting monitoring signal sent by the safety management device, collects the picture information and safety equipment sensor data of the construction area; based on the preset artificial intelligence model, the safety equipment sensor data and the picture information are analyzed for safety equipment violations, and the violation analysis results are obtained; according to the violation identification results, the corresponding alarm scheme is executed. It can be understood that this application adopts an artificial intelligence model to analyze the safety equipment violation behavior of the safety equipment sensor data and the picture information, and obtain the violation analysis results. When violations occur in the construction area, the violation identification is realized through the artificial intelligence model, and the corresponding alarm scheme is executed, so as to achieve safety management of violations, thereby improving the efficiency of violation alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0042] Figure 1 A flowchart diagram of the first embodiment of the method for warning of illegal behavior in the construction work area of ​​this application;

[0043] Figure 2 This is a schematic diagram of the module structure of the violation warning device in the construction work area of ​​the embodiment of the present application;

[0044] Figure 3 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the method for warning of violations in a construction work area in an embodiment of the present application.

[0045] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0047] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0048] The main solutions of the embodiments of this application are:

[0049] Receive the start monitoring signal sent by the safety management equipment, collect the image information of the construction area and the sensor data of the safety equipment;

[0050] Based on a preset artificial intelligence model, the safety equipment sensor data and the image information are analyzed for safety equipment violations to obtain violation analysis results;

[0051] According to the violation identification results, the corresponding alarm plan is executed.

[0052] In this embodiment, the application uses the violation warning device in the construction area as the execution subject. For the convenience of expression, it is specifically described below as "device".

[0053] Existing technologies mainly rely on manual inspections and video surveillance systems. However, manual inspections are inefficient, have limited coverage, and are susceptible to human factors. Although video surveillance systems can provide real-time images, they are limited in monitoring range and angle, and require a large amount of manpower for real-time monitoring. It is difficult to achieve comprehensive and efficient violation alerts, resulting in reduced efficiency in violation alerts.

[0054] The present application provides a solution, which collects the image information and safety equipment sensor data of the construction operation area by receiving the starting monitoring signal sent by the safety management device; based on the preset artificial intelligence model, the safety equipment sensor data and the image information are analyzed for safety equipment violations to obtain the violation analysis results; according to the violation identification results, the corresponding alarm scheme is executed. It can be understood that the present application adopts an artificial intelligence model to analyze the safety equipment violation behavior of the safety equipment sensor data and the image information to obtain the violation analysis results. When violations occur in the construction operation area, the violation identification is realized through the artificial intelligence model, and the corresponding alarm scheme is executed, so as to realize the safety management of violations and improve the efficiency of violation alarms.

[0055] Based on this, the embodiment of the present application provides a method for warning of illegal behavior in a construction operation area, referring to Figure 1 , Figure 1This is a flow chart of the first embodiment of the method for warning of illegal behavior in the construction work area of ​​this application.

[0056] In this embodiment, the violation warning method in the construction area includes steps S10 to S40:

[0057] Step S10, receiving the start monitoring signal sent by the safety management device, collecting the image information of the construction work area and the safety equipment sensor data;

[0058] It should be noted that the safety management device is a preset device of the safety management center, which is used to connect, monitor and manage the safety status of the construction site. The starting monitoring signal is a signal sent by the safety management device, which is used to instruct the monitoring device to start collecting and analyzing the image information and safety equipment sensor data of the construction area.

[0059] In addition, it should be noted that the construction work area refers to a specific area in the construction site where workers need to wear personal protective equipment such as safety helmets and safety belts when working in this area. The picture information refers to the real-time video stream or image frame of the construction work area captured by the video surveillance camera, which is used to analyze the behavior of the workers and the use of safety equipment. The safety equipment sensor data refers to the data collected from the built-in sensors in personal protective equipment such as safety helmets and safety belts, such as wearing status, impact force, usage time, etc.

[0060] For example, at a construction site, the device receives a start monitoring signal from a safety management device, which instructs the device to start monitoring the safety status of the workers. The device then starts the collection process, collecting real-time image information through the AI ​​camera deployed in the construction area, and at the same time, the sensors in the safety helmets and safety belts worn by the workers also start transmitting data. The image information captured by the AI ​​camera includes the worker's movements, positions, and visible status of the safety equipment, while the safety equipment sensor data provides more detailed usage information, such as whether the safety helmet is worn correctly and whether the safety belt is fastened. These data are transmitted to the central processing unit, where the AI ​​algorithm analyzes the image information, identifies whether the worker is operating in accordance with safety regulations, and checks the usage status of the safety equipment. If the AI ​​algorithm detects that the worker is not wearing a safety helmet or safety belt correctly, the device will automatically trigger an alarm and notify the on-site safety manager. In this way, through real-time monitoring and automatic analysis, the safety management efficiency of the construction site is greatly improved, and safety accidents caused by illegal operations are reduced.

[0061] Step S20, based on a preset artificial intelligence model, analyzing the safety device sensor data and the image information for safety device violation behaviors to obtain a violation behavior analysis result;

[0062] It should be noted that the artificial intelligence model refers to a pre-trained algorithm or software that can identify and analyze safety equipment sensor data and image information to determine the compliance of safety equipment use. The safety equipment sensor data refers to the data collected from the sensors built into personal protective equipment such as safety helmets and seat belts. These data may include wearing status, impact force, usage time, etc., which are used to evaluate whether the use of personal protective equipment complies with safety regulations. The image information refers to the real-time video stream or image frame of the construction work area captured by the video surveillance camera, which is used to analyze the behavior of the workers and the use of safety equipment. The violation analysis result refers to the result obtained after the artificial intelligence model analysis, including whether the workers have violated safety regulations, such as not wearing safety equipment or wearing it improperly. The safety equipment violation analysis is a process in which the artificial intelligence model analyzes safety equipment sensor data and image information to determine whether the workers use safety equipment such as safety helmets and seat belts correctly.

[0063] For example, at an industrial construction site, in order to ensure the safety of workers, a set of AI-based monitoring devices is used. The core of the device is a preset AI model, which is specially designed to analyze safety equipment sensor data and image information to monitor whether workers use safety equipment in compliance with regulations. During implementation, the device first receives sensor data from the safety helmets and seat belts worn by workers. These data include information such as the wearing status, impact strength and usage time of the safety equipment. At the same time, the device also collects image information through AI cameras installed at the construction site, which includes the movements of workers and the visible status of safety equipment. The AI ​​model uses these sensor data and image information as input for in-depth analysis. The model uses deep learning algorithms, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), to identify whether workers wear safety helmets and seat belts correctly. For example, the model can identify whether the safety helmet is placed correctly on the head and whether the seat belt is buckled correctly. After analysis, the AI ​​model outputs the analysis results of violations. If the model detects that the operator is not wearing safety equipment correctly, such as not wearing a safety helmet or not fastening the seat belt, the device will record these violations and trigger the corresponding alarm mechanism, such as sending an alarm message to the on-site safety manager so that timely measures can be taken to correct the violations. Through this analysis based on the artificial intelligence model, the construction site can achieve real-time monitoring of the use of safety equipment by operators, effectively improve the safety management level of the construction site, and reduce safety accidents caused by illegal operations.

[0064] Step S30: Execute a corresponding warning plan based on the violation identification result.

[0065] It should be noted that the violation identification result is a conclusion on whether the operator complies with safety regulations after analyzing the image information captured by the camera and the sensor data of the safety equipment. The alarm scheme refers to a series of response measures preset by the device based on the violation identification result, including but not limited to notification, warning, emergency response, etc., which is intended to promptly remind the operator or manager to take action to ensure the safety of the operation.

[0066] For example, in a construction project, in order to improve the safety management efficiency and response speed of the construction site, the project manager deployed a set of artificial intelligence-based monitoring devices, which can automatically monitor and analyze the wearing of safety equipment by workers. The core of the device is a preset artificial intelligence model that can process image information from AI cameras and safety equipment sensor data. When workers enter the construction area, the AI ​​camera begins to capture their images, and at the same time, the sensors in the safety helmets and seat belts begin to transmit data. The artificial intelligence model analyzes these inputs to identify whether the workers are wearing safety helmets and seat belts correctly. Once the artificial intelligence model completes the analysis, it will output the violation identification results. If the identification results show that the workers are not wearing safety equipment as required, the device will execute the corresponding alarm plan based on these results. For example:

[0067] Low-level warning: If the violation is minor (such as a safety helmet not fastened), the device may only display a warning message on the monitoring screen and send a notification to the on-site safety supervisor, asking them to remind the operator to correct the behavior.

[0068] Medium-level alert: For more serious violations (such as not wearing a safety helmet), the device may trigger an on-site audible and visual alarm and send a text message or app push notification to safety managers, requiring them to take immediate action.

[0069] High-level alarm: In the most serious cases (such as multiple workers not wearing safety belts), the device may automatically notify the project safety manager and initiate emergency response procedures, including suspending operations and evacuating personnel.

[0070] The implementation of these warning schemes ensures that violations can be discovered and dealt with in a timely manner, thereby reducing safety risks at the construction site. Through this automated monitoring and response mechanism, construction projects can more effectively protect the safety of workers and improve the overall safety management level.

[0071] This embodiment provides a method for warning of violations in a construction area, which adopts an artificial intelligence model to analyze the safety equipment violations on the safety equipment sensor data and the image information to obtain violation analysis results. When violations occur in the construction area, the artificial intelligence model is used to identify the violations and execute the corresponding alarm plan, thereby achieving safe management of the violations and improving the efficiency of violation alarms.

[0072] In a feasible implementation, step S20 may include:

[0073] Preprocessing the safety device sensor data to obtain safety device sensor information;

[0074] Extracting safety behaviors from the image information through a preset behavior extraction model to obtain safety behavior information;

[0075] fusing the safety device sensor information with the safety behavior information to obtain a comprehensive feature data set;

[0076] The artificial intelligence model is used to analyze the safety equipment violation behavior of the comprehensive feature data set to obtain the violation behavior analysis result.

[0077] It should be noted that the safety equipment sensor data is the raw data collected from the sensors built into the safety protection equipment, including but not limited to wearing status, impact force, usage time, etc. The behavior extraction model is a preset model used to automatically identify and extract safety-related human behavior features from video images, such as whether safety equipment is worn. The image information refers to the real-time video stream or image frame of the construction work area captured by the video surveillance camera. The safety behavior information is data related to safety behavior extracted from the image information by the behavior extraction model, such as whether the operator wears the safety equipment correctly. The comprehensive feature data set is a data set formed by combining the safety equipment sensor information and the safety behavior information. This data set contains all relevant information collected from different sources for comprehensive safety analysis. The artificial intelligence model is a preset, well-trained model that can analyze the comprehensive feature data set to identify the compliance use of safety equipment.

[0078] For example, at a construction site, in order to ensure the safety of workers, the project manager deployed a set of artificial intelligence-based monitoring devices, which can automatically monitor and analyze the wearing of safety equipment by workers.

[0079] First, the device preprocesses the sensor data from the safety helmet and safety belt, including filtering, denoising and normalization, to obtain the safety equipment sensor information. This information includes the wearing status, impact force and usage time of the safety equipment. Then, the device analyzes the image information captured by the AI ​​camera through the preset behavior extraction model, automatically identifies whether the operator wears the safety equipment correctly, and obtains the safety behavior information. Then, the device fuses the safety equipment sensor information with the safety behavior information to form a comprehensive feature data set. This data set contains all relevant information extracted from the sensor and video images, providing comprehensive data support for the subsequent safety equipment violation analysis. Finally, the device analyzes the comprehensive feature data set through the artificial intelligence model to identify whether the operator uses the safety equipment in compliance with the regulations. The analysis result is the violation analysis result. If the device detects that the operator does not wear the safety equipment correctly, it will trigger the corresponding alarm and response measures. Through this series of steps, the construction project can monitor the use of safety equipment by the operators in real time, detect and correct violations in a timely manner, and thus improve the safety management level of the construction site.

[0080] In a feasible implementation manner, the step of extracting safety behaviors from the picture information by using a preset behavior extraction model to obtain safety behavior information includes:

[0081] Obtain screen information samples and safety behavior information labels;

[0082] Sending the picture information sample to a preset model to be trained;

[0083] Based on the model to be trained, extracting safety behaviors from the image information sample to obtain safety behavior information extraction results;

[0084] Analyze the difference between the safety behavior information extraction result and the safety behavior information label to obtain an extraction loss value;

[0085] If the extracted loss value does not meet the preset loss standard, return to the step of extracting safe behaviors from the picture information sample based on the model to be trained to obtain safe behavior information extraction results, and stop training until the extracted loss value meets the loss standard to obtain a behavior extraction model that meets the loss standard.

[0086] It should be noted that the picture information samples are specific images or video frames captured from the video surveillance device, and these samples are used to train and test the artificial intelligence model to identify whether the operator wears safety equipment correctly. The safety behavior information label is a label corresponding to the picture information sample, indicating whether the safety behavior of the operator in the sample is compliant, for example, whether the safety helmet and safety belt are worn correctly. These labels are used to train the model so that it can correctly identify safety behaviors. The model to be trained is an artificial intelligence model that has not yet completed training, and it is necessary to improve its recognition ability by learning a large number of picture information samples and corresponding safety behavior information labels. The safety behavior extraction is to use the artificial intelligence model to automatically identify and extract features related to safety behaviors from the picture information samples, such as whether the operator wears safety equipment. The safety behavior information extraction result is the result obtained by the model after analyzing the picture information sample, including the recognition result of the safety behavior of the operator. The extraction loss value is an indicator to measure the difference between the model prediction result and the actual label, which is used to evaluate the performance of the model. During the training process, the reduction of the loss value indicates the improvement of the model performance. The loss standard is a preset performance standard used to determine when the model training stops. When the extraction loss value drops below this criterion, the model is considered to be trained to a sufficient degree.

[0087] For example, in an industrial manufacturing plant, in order to improve the safety management level of the work site, the factory manager decided to deploy a set of artificial intelligence-based monitoring devices to automatically detect whether the workers are wearing safety helmets and safety belts correctly. First, the factory's safety management personnel collected a large number of picture information samples, which include images or video frames of workers at work. At the same time, safety behavior information labels are provided for these samples, clearly indicating whether the safety equipment wearing of the workers in each sample is compliant. Next, these picture information samples and the corresponding safety behavior information labels are sent to a preset model to be trained. This model is a deep learning network specially designed to extract features related to safety behaviors from images. The model extracts safety behaviors from the picture information samples and obtains safety behavior information extraction results. Then, these results are compared with the safety behavior information labels, the differences between the two are analyzed, and the extraction loss value is calculated. If the extraction loss value does not meet the preset loss standard, it indicates that the recognition ability of the model needs to be improved, so the training process will continue. The model will repeat the safety behavior extraction process based on new training data until the extraction loss value meets the preset loss standard. Once the extraction loss value meets the loss standard, the model training stops, and the model obtained at this time is considered to be a behavior extraction model that meets the loss standard. This model can accurately extract safety behavior information from screen information samples, providing factories with an effective tool to automate and improve the efficiency of safety management at the work site.

[0088] In a feasible implementation manner, the step of fusing the safety device sensor information with the safety behavior information to obtain a comprehensive feature data set includes:

[0089] Based on a feature matching algorithm, aligning the time series features of the safety device sensor information and the safety behavior information;

[0090] Based on a data fusion algorithm, the feature vectors of the safety device sensor information and the safety behavior information are merged to form a comprehensive feature data set.

[0091] It should be noted that the feature matching algorithm refers to a technology used to match data from different sources (such as sensor data and video picture information) at the feature level to ensure that the data is consistent in time series. The safety equipment sensor information refers to data collected from sensors built into personal protective equipment such as safety helmets and safety belts. These data may include wearing status, impact force, usage time, etc. The safety behavior information refers to information extracted from images or video frames captured by video surveillance devices, which describes the safety behavior of operators, such as whether safety equipment is worn correctly. The time series feature alignment is a process through which features from different data sources are adjusted and matched to ensure that they are synchronized in time, which is crucial for subsequent data analysis and pattern recognition. The data fusion algorithm is an algorithm for merging feature vectors of data from different sources into a comprehensive data set for more comprehensive analysis. The feature vector is a numerical representation of data, which contains numerical values ​​used to describe the characteristics of the data. The comprehensive feature data set is a data set that contains features from multiple data sources, which merges the feature vectors of safety equipment sensor information and safety behavior information through a data fusion algorithm.

[0092] For example, at a construction site, in order to improve the efficiency of safety supervision of workers, the project manager deployed a set of artificial intelligence-based monitoring devices. The device uses AI cameras and safety equipment sensors to monitor whether workers wear safety helmets and safety belts correctly. First, the device collects safety equipment sensor information through safety equipment sensors, which includes the use status and wearing conditions of safety helmets and safety belts. At the same time, the AI ​​camera captures the image information of the working area and extracts safety behavior information from it, which describes whether the workers wear personal protective equipment in accordance with safety regulations. Next, the device uses a feature matching algorithm to align the time series features of the safety equipment sensor information with the safety behavior information. This step ensures that the features extracted from the sensor and video images are consistent in time, even if they come from different data sources and sensors. Then, the device merges the feature vectors of the safety equipment sensor information and the safety behavior information based on the data fusion algorithm to form a comprehensive feature data set. This comprehensive feature data set contains all relevant safety information and provides comprehensive data support for the subsequent analysis of safety equipment violations. In this way, the device can more accurately analyze the safety behavior of workers, detect violations in a timely manner, and take corresponding safety measures, thereby improving the safety management level of the construction site.

[0093] In a feasible implementation manner, the step of merging the feature vectors of the safety device sensor information and the safety behavior information based on a data fusion algorithm to form a comprehensive feature data set includes:

[0094] Through feature selection and feature extraction technology, the comprehensive feature data set is enhanced to obtain a comprehensive feature data set after feature enhancement.

[0095] It should be noted that the feature selection technology refers to a method of identifying and selecting a subset of features that best represent the characteristics of the problem and are most helpful for model prediction from a large number of data features. The feature extraction technology is a method of extracting information from raw data that helps describe and identify data patterns, which may include converting raw data into higher-level abstractions and feature representations. The comprehensive feature dataset is a dataset that contains features from different data sources (such as AI cameras and security equipment sensors) and is used for comprehensive security equipment compliance analysis. The feature enhancement refers to improving the expressiveness of features in the dataset through feature selection and feature extraction techniques, so that the model can more easily learn and identify the compliant use of security equipment. The feature-enhanced comprehensive feature dataset is a comprehensive feature dataset that has been processed through feature enhancement, and contains more refined and useful features that can be more effectively used to train and optimize artificial intelligence models.

[0096] In a feasible implementation manner, the step of executing a corresponding alarm scheme according to the violation identification result includes:

[0097] Determine the warning level according to the severity of the violation identification result and the type of violation;

[0098] If the alarm level is a low-level alarm, the preset security management device is notified via a pop-up window on the interface or an email;

[0099] If the alarm level is a medium-level alarm, the preset security management device is notified via an interface pop-up window or email, and a message is pushed to the preset emergency contact device via SMS or mobile application;

[0100] If the alarm level is a high-level alarm, the preset emergency response procedure is started and the emergency broadcast device is triggered.

[0101] For example, at a large construction site, in order to improve the safety management efficiency of the work site, the project manager deployed a set of artificial intelligence-based monitoring devices, which can automatically monitor and analyze the wearing of safety equipment by workers. The device collects data through AI cameras and safety equipment sensors, and analyzes whether the workers wear safety helmets and safety belts correctly. After the analysis is completed, the device determines the alarm level according to the severity of the violation identification results and the type of violation. If the alarm level is a low-level alarm, for example, the worker does not wear a safety helmet correctly but is not in a high-risk area, the device will notify the preset safety management device through an interface pop-up window or email to remind the safety manager to pay attention and take corresponding measures. If the alarm level is a medium-level alarm, for example, the worker does not wear a safety belt when working at high altitude, the device will notify the preset safety management device through an interface pop-up window or email, and push messages to the preset emergency contact device, such as the on-site safety supervisor, through SMS or mobile applications, for rapid response. If the alarm level is a high-level alarm, such as detecting that multiple people are not wearing safety equipment or there is a risk of a major safety accident, the device will start the preset emergency response procedure, including triggering the emergency broadcast device to broadcast emergency evacuation instructions or safety warnings to all personnel on site. Through this hierarchical alarm and response mechanism, construction sites can promptly identify and respond to various safety violations, effectively reduce the risk of safety accidents, and protect the lives of workers.

[0102] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the violation warning method in the construction area of ​​the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0103] This application also provides a violation warning device for the construction work area, please refer to Figure 2The violation warning device in the construction work area includes:

[0104] The acquisition module 10 is used to receive the start monitoring signal sent by the safety management device and collect the image information of the construction work area and the sensor data of the safety equipment;

[0105] The analysis module 20 is used to analyze the safety device violation behavior on the safety device sensor data and the image information based on a preset artificial intelligence model to obtain a violation behavior analysis result;

[0106] The alarm module 30 is used to execute a corresponding alarm plan according to the violation identification result.

[0107] And / or, the analysis module 20 includes:

[0108] A first preprocessing module, used for preprocessing the safety device sensor data to obtain safety device sensor information;

[0109] A first extraction module is used to extract safety behaviors from the image information through a preset behavior extraction model to obtain safety behavior information;

[0110] A first fusion module, used to fuse the safety device sensor information with the safety behavior information to obtain a comprehensive feature data set;

[0111] The first analysis module is used to perform a security device violation analysis on the comprehensive feature data set through the artificial intelligence model to obtain a violation analysis result.

[0112] And / or, the violation warning device in the construction work area includes:

[0113] The first acquisition module is used to acquire the image information sample and the safety behavior information label;

[0114] A first sending module, used for sending the picture information sample to a preset model to be trained;

[0115] A first extraction module, configured to extract safety behaviors from the image information sample based on the model to be trained, and obtain safety behavior information extraction results;

[0116] A second analysis module is used to analyze the difference between the safety behavior information extraction result and the safety behavior information label to obtain an extraction loss value;

[0117] The first loop module is used to return to the step of performing safe behavior extraction on the picture information sample based on the model to be trained to obtain a safe behavior information extraction result if the extracted loss value does not meet the preset loss standard, and stop training after the extracted loss value meets the loss standard to obtain a behavior extraction model that meets the loss standard.

[0118] And / or, the first fusion module includes:

[0119] A first alignment module, configured to perform time series feature alignment between the safety device sensor information and the safety behavior information based on a feature matching algorithm;

[0120] The first merging module is used to merge the feature vectors of the safety device sensor information and the safety behavior information based on a data fusion algorithm to form a comprehensive feature data set.

[0121] And / or, the violation warning device in the construction work area includes:

[0122] The first enhancement module is used to perform feature enhancement on the comprehensive feature data set through feature selection and feature extraction technology to obtain the comprehensive feature data set after feature enhancement.

[0123] And / or, the alarm module 30 includes:

[0124] A first determination module is used to determine an alarm level according to the severity of the violation identification result and the type of violation;

[0125] A first alarm module is used to notify a preset security management device through an interface pop-up window or email if the alarm level is a low-level alarm;

[0126] The second alarm module is used to notify the preset security management device through an interface pop-up window or email if the alarm level is a medium-level alarm, and push a message to the preset emergency contact device through SMS or mobile application;

[0127] The third alarm module is used to start a preset emergency response program and trigger the emergency broadcast system if the alarm level is a high-level alarm.

[0128] The violation warning device for the construction area provided by the present application adopts the violation warning method for the construction area in the above embodiment, which can solve the technical problem of low efficiency of violation warning. Compared with the prior art, the beneficial effects of the violation warning device for the construction area provided by the present application are the same as the beneficial effects of the violation warning method for the construction area provided by the above embodiment, and the other technical features of the violation warning device for the construction area are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0129] The present application provides a violation warning device for a construction work area, and the violation warning device for the construction work area includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the violation warning method for the construction work area in the above-mentioned embodiment one.

[0130] Reference below Figure 3 , which shows a schematic diagram of the structure of a violation warning device for a construction operation area suitable for implementing the embodiment of the present application. The violation warning device for the construction operation area in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, tablet computers, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The violation warning device shown in the construction work area is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0131] like Figure 3As shown, the violation warning device for the construction operation area may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the violation warning device for the construction operation area are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the violation warning device in the construction work area to communicate with other devices wirelessly or by wire to exchange data. Although the violation warning device in the construction work area with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0132] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0133] The violation warning device for the construction area provided by the present application adopts the violation warning method for the construction area in the above embodiment, which can solve the technical problem of low efficiency of violation warning. Compared with the prior art, the beneficial effects of the violation warning device for the construction area provided by the present application are the same as the beneficial effects of the violation warning method for the construction area provided by the above embodiment, and other technical features of the violation warning device for the construction area are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0134] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0135] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0136] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for warning against violations in the construction work area in the above-mentioned embodiment.

[0137] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0138] The computer-readable storage medium may be included in the violation warning device in the construction work area; or it may exist independently without being installed in the violation warning device in the construction work area.

[0139] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the violation warning device in the construction area, the violation warning device in the construction area: receives the starting monitoring signal sent by the safety management device, and collects the image information of the construction area and the sensor data of the safety device;

[0140] Based on a preset artificial intelligence model, the safety equipment sensor data and the image information are analyzed for safety equipment violations to obtain violation analysis results;

[0141] According to the violation identification results, the corresponding alarm plan is executed.

[0142] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0144] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0145] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for warning the violation of the construction work area, and can solve the technical problem of low efficiency of the violation warning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the method for warning the violation of the construction work area provided by the above-mentioned embodiment, and will not be repeated here.

[0146] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for warning of violations in a construction operation area.

[0147] The computer program product provided by the present application can solve the technical problem of low efficiency of illegal behavior alarm. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the illegal behavior alarm method in the construction operation area provided by the above embodiment, which will not be repeated here.

[0148] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for warning of illegal behavior in a construction area, characterized in that: The method includes: Receive the start monitoring signal sent by the safety management equipment, collect the image information of the construction area and the sensor data of the safety equipment; Based on a preset artificial intelligence model, the safety equipment sensor data and the image information are analyzed for safety equipment violations to obtain violation analysis results; According to the violation identification results, the corresponding alarm plan is executed.

2. The method according to claim 1, characterized in that The step of performing safety equipment violation analysis on the safety equipment sensor data and the image information based on a preset artificial intelligence model to obtain the violation analysis result includes: Preprocessing the safety device sensor data to obtain safety device sensor information; Extracting safety behaviors from the image information through a preset behavior extraction model to obtain safety behavior information; fusing the safety device sensor information with the safety behavior information to obtain a comprehensive feature data set; The artificial intelligence model is used to analyze the safety equipment violation behavior of the comprehensive feature data set to obtain the violation behavior analysis result.

3. The method according to claim 2, characterized in that The step of extracting safety behaviors from the picture information by using a preset behavior extraction model to obtain safety behavior information includes: Obtain screen information samples and safety behavior information labels; Sending the picture information sample to a preset model to be trained; Based on the model to be trained, extracting safety behaviors from the image information sample to obtain safety behavior information extraction results; Analyze the difference between the safety behavior information extraction result and the safety behavior information label to obtain an extraction loss value; If the extracted loss value does not meet the preset loss standard, return to the step of extracting safe behaviors from the picture information sample based on the model to be trained to obtain safe behavior information extraction results, and stop training until the extracted loss value meets the loss standard to obtain a behavior extraction model that meets the loss standard.

4. The method according to claim 2, characterized in that The step of fusing the safety device sensor information with the safety behavior information to obtain a comprehensive feature data set includes: Based on a feature matching algorithm, aligning the time series features of the safety device sensor information and the safety behavior information; Based on a data fusion algorithm, the feature vectors of the safety device sensor information and the safety behavior information are merged to form a comprehensive feature data set.

5. The method according to claim 4, characterized in that The step of combining the feature vectors of the safety device sensor information and the safety behavior information based on a data fusion algorithm to form a comprehensive feature data set includes: Through feature selection and feature extraction technology, the comprehensive feature data set is enhanced to obtain a comprehensive feature data set after feature enhancement.

6. The method according to claim 1, characterized in that The step of executing a corresponding alarm scheme according to the violation identification result includes: Determine the warning level according to the severity of the violation identification result and the type of violation; If the alarm level is a low-level alarm, the preset security management device is notified via a pop-up window on the interface or an email; If the alarm level is a medium-level alarm, the preset security management device is notified via an interface pop-up window or email, and a message is pushed to the preset emergency contact device via SMS or mobile application; If the alarm level is a high-level alarm, the preset emergency response procedure is initiated to trigger the emergency broadcast system.

7. A violation warning device for a construction area, characterized in that: The device comprises: The acquisition module is used to receive the start monitoring signal sent by the safety management equipment and collect the image information of the construction area and the sensor data of the safety equipment; An analysis module, used to analyze the safety equipment sensor data and the image information for safety equipment violations based on a preset artificial intelligence model to obtain a violation analysis result; The alarm module is used to execute corresponding alarm plans based on the violation identification results.

8. A violation warning device for a construction area, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for warning of violations in a construction work area as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for warning of violations in the construction work area as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method for warning of illegal behavior in a construction work area according to any one of claims 1 to 6 are implemented.

Images