Working site safety analysis method based on personnel behavior analysis

Abstract

The invention relates to the technical field of operation safety management, and provides an operation site safety analysis method based on personnel behavior analysis, which comprises the following steps: receiving a behavior monitoring request and analyzing operator information, generating behavior characteristic information after acquiring behavior data, and displaying the characteristic information and a risk assessment control by analyzing a popup window, and performing risk assessment according to the configured risk level. And when an abnormal behavior request is detected, generating a verification rule based on a preset behavior library, sending the verification rule to the safety monitoring device, displaying the rule by an external display, and receiving to-be-verified behavior data. And performing noise filtering and feature extraction on to-be-verified data, generating a behavior feature vector, calculating similarity with a historical feature vector, screening target similarity meeting a threshold value to determine a matched feature vector, and triggering safety early warning if matching succeeds. The method comprises the whole processes of data acquisition, feature processing, risk matching and early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of operation safety management. More specifically, the present invention relates to a method for analyzing the safety of an operation site based on personnel behavior analysis. Background Art

[0002] In modern industrial production, the safety management of the operation site has always been an important link that has attracted much attention. With the continuous expansion of production scale and the increasing complexity of the operation environment, the behavior of operators has a more significant impact on the on-site safety. Traditional operation site safety management mainly relies on manual inspections and simple monitoring devices. Its technical principle is mainly to discover potential safety hazards through manual observation or video recording playback. However, this method is not only inefficient but also easily affected by human factors, making it difficult to identify the abnormal behavior of operators in real-time and accurately. In recent years, although some technologies based on sensors or video analysis have been introduced into safety management, most of these technologies can only achieve single-type behavior monitoring and have deficiencies in behavior feature extraction and risk assessment, unable to meet the high-precision and real-time requirements of safety analysis in complex operation sites.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: First, the traditional safety management method cannot achieve real-time monitoring and dynamic analysis of the behavior of operators, making it difficult to discover potential safety hazards in a timely manner; Second, when extracting behavior features in the prior art, the integrity and accuracy of behavior data are often ignored, resulting in unreliable analysis results; Third, for different types of behavior monitoring requests, the prior art lacks a flexible processing mechanism and cannot meet the diverse behavior analysis needs; Fourth, most of the prior art adopts fixed rules in risk assessment, lacking the ability to deeply mine behavior feature information and dynamically adjust, and it is difficult to adapt to the complex and changeable operation site environment. Summary of the Invention

[0004] The present invention provides a method, device, and medium for analyzing the safety of an operation site based on personnel behavior analysis.

[0005] In the first aspect of the present invention, a method for analyzing the safety of an operation site based on personnel behavior analysis is provided, including:

[0006] In response to receiving a behavior monitoring request through a target application associated with an operation site safety monitoring device, parsing the behavior monitoring request to obtain operator information corresponding to the behavior monitoring request, where the behavior monitoring request is a request to apply for behavior monitoring of the current operation site;

[0007] Obtaining the behavior data of the operator;

[0008] Generate behavioral feature information based on the said behavioral data;

[0009] Display an analysis pop-up window corresponding to the said behavioral feature information, wherein the analysis pop-up window displays the said behavioral feature information and a risk assessment configuration control;

[0010] Conduct a risk assessment on the said behavioral feature information according to the risk level information configured for the said risk assessment configuration control;

[0011] In response to detecting an abnormal behavior request through the said on-site operation safety monitoring device, generate a behavior verification rule according to a preset behavior library;

[0012] Send the said behavior verification rule to the said on-site operation safety monitoring device, so that the on-site operation safety monitoring device displays the said behavior verification rule through an external display;

[0013] Receive the behavior data to be verified corresponding to the said behavior verification rule sent by the said on-site operation safety monitoring device as the information of the person to be identified, wherein the behavior data to be verified is the behavior record of the operator during the monitoring period;

[0014] In response to obtaining the information of the person to be identified through the said on-site operation safety monitoring device, conduct a matching process on the information of the person to be identified according to each stored behavioral feature information to obtain a matching result, wherein conducting a matching process on the information of the person to be identified according to each stored behavioral feature information to obtain a matching result includes: filtering out noise and removing invalid data from the said behavior data to be verified to obtain processed behavior data;

[0015] Conduct feature extraction processing on the said processed behavior data to obtain a behavioral feature vector;

[0016] Generate the behavioral similarity between the said behavioral feature vector and each historical feature vector included in each of the said behavioral feature information to obtain a similarity set;

[0017] Determine the similarity that meets the first preset similarity condition in the said similarity set as the target similarity, wherein the first preset similarity condition is that the similarity is the maximum value in the similarity set;

[0018] In response to determining that the said target similarity meets the second preset similarity condition, determine the feature vector corresponding to the said target similarity as the matching feature vector, wherein the second preset similarity condition is that the target similarity is greater than a preset similarity threshold;

[0019] Generate a matching result according to the personnel information corresponding to the said matching feature vector;

[0020] In response to determining that the matching result indicates a successful match, control the warning component of the on-site safety monitoring device for the operation to perform a safety warning operation.

[0021] Further, the operator information includes an operator identifier and location information; and before obtaining the behavior data of the operator, the method further includes:

[0022] In response to detecting a selection operation on a start control acting on a behavior monitoring page, obtain the location information of the operator corresponding to the behavior monitoring request according to the operator identifier, where the behavior monitoring page corresponds to the behavior monitoring request, and the operator information including the operator name is displayed on the behavior monitoring page;

[0023] Determine whether the location information meets the preset range condition corresponding to the target operation area;

[0024] In response to determining that the location information meets the preset range condition, send a behavior data collection instruction corresponding to the behavior monitoring request to the on-site safety monitoring device for the operation; and obtaining the behavior data of the operator includes: in response to receiving feedback information indicating consent to collection corresponding to the behavior data collection instruction, obtaining the behavior data of the operator.

[0025] Further, generating behavior feature information according to the behavior data includes:

[0026] Perform integrity detection processing on the behavior data to obtain an integrity detection result;

[0027] In response to determining that the integrity detection result indicates the existence of valid behavior records, generate behavior feature information according to the behavior data.

[0028] Further, the behavior monitoring request is a video behavior monitoring request, and the behavior data is behavior video data; and performing integrity detection processing on the behavior data to obtain an integrity detection result includes: performing action recognition processing on the behavior data to obtain an action recognition result as the integrity detection result.

[0029] Further, generating behavior feature information according to the behavior data includes:

[0030] Perform frame division processing on the behavior data to obtain a behavior data sequence;

[0031] For each behavior data unit in the behavior data sequence, perform the following steps: Determine whether there is a complete human contour area in the behavior data unit;

[0032] In response to determining that there is a complete human profile area in the behavior data unit, intercept the human profile area in the behavior data unit to obtain profile data;

[0033] Perform color simplification processing on the profile data to obtain simplified profile data;

[0034] Perform brightness detection on the simplified profile data to obtain profile data intensity information;

[0035] Perform contrast detection on the simplified profile data to obtain profile data contrast information;

[0036] Generate profile data parameters according to the simplified profile data quality information, the profile data intensity information, and the profile data contrast information;

[0037] According to the obtained profile data parameters, select the profile data that meets the preset data parameter conditions from the obtained profile data as the target profile data;

[0038] Perform data optimization processing on the target profile data according to the simplified profile data quality information, profile data intensity information, and profile data contrast information corresponding to the target profile data to obtain optimized profile data;

[0039] Perform feature extraction processing on the optimized profile data to obtain profile data feature information;

[0040] Generate behavior feature information according to the profile data feature information and the personnel information.

[0041] Further, the performing color simplification processing on the profile data to obtain simplified profile data includes:

[0042] Perform color simplification processing on the profile data to obtain simplified profile data;

[0043] Remove each data point in the simplified profile data that meets the preset edge condition to obtain the profile data after removal;

[0044] For each data point in the simplified profile data, perform the following steps: Determine the data point adjacent to the right of the data point in the simplified profile data as the right adjacent data point;

[0045] Determine the data point adjacent to the top of the data point in the simplified profile data as the top adjacent data point;

[0046] Generate a first value and a second value according to the value of the right adjacent data point and the value of the data point;

[0047] Generate a third value and a fourth value according to the value of the upper adjacent data point and the value of the data point;

[0048] Determine the sum of each obtained first value, each second value, each third value, and each fourth value as a fifth value;

[0049] Determine the number of each data point included in the simplified contour data as the total number of data points;

[0050] Determine the ratio of the fifth value to the total number of data points as the contour data quality information corresponding to the simplified contour data.

[0051] Further, the data optimization process for the target contour data according to the simplified contour data quality information, contour data intensity information, and contour data comparison information corresponding to the target contour data to obtain the optimized contour data includes:

[0052] In response to determining that the simplified contour data quality information corresponding to the target contour data meets the preset quality optimization condition, perform quality enhancement processing on the target contour data to update the target contour data;

[0053] In response to determining that the contour data intensity information corresponding to the target contour data meets the preset intensity optimization condition, perform intensity adjustment processing on the target contour data to update the target contour data;

[0054] In response to determining that the contour data comparison information corresponding to the target contour data meets the preset comparison optimization condition, perform comparison enhancement processing on the target contour data to update the target contour data;

[0055] Perform size normalization processing on the updated target contour data to update the target contour data;

[0056] Determine the updated target contour data as the optimized contour data.

[0057] Further, the behavior monitoring request is an action behavior monitoring request, and the behavior data is action sensor data; and the integrity detection process for the behavior data to obtain the integrity detection result includes: performing action feature extraction processing on the behavior data to obtain the action feature result as the integrity detection result; and generating behavior feature information according to the behavior data, including:

[0058] Perform noise filtering and invalid data elimination processing on the behavior data to obtain the processed data;

[0059] Perform feature extraction processing on the processed data to obtain the action feature vector;

[0060] For each feature dimension in the action feature vector, perform the following steps: Determine the eigenvalue corresponding to the feature dimension;

[0061] Determine the feature weight corresponding to the feature dimension;

[0062] Generate a comprehensive feature score based on the eigenvalue and the feature weight;

[0063] Select the comprehensive feature scores that meet the preset score conditions from the generated comprehensive feature scores as the target comprehensive feature scores;

[0064] Determine the target comprehensive feature score and the personnel information as the behavior feature information.

[0065] In a second aspect of the present invention, there is provided an electronic device, the electronic device includes: at least one processor, a memory, and an input / output unit; wherein, the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the method according to any one of the first aspect.

[0066] In a third aspect of the present invention, there is provided a computer-readable storage medium, which includes instructions, and when it runs on a computer, it causes the computer to execute the method according to any one of the first aspect.

[0067] According to the above embodiments of the present invention, it has at least the following beneficial effects: The operation site safety analysis method based on personnel behavior analysis can effectively improve the safety of the operation site. By real-time monitoring and analyzing the behavior data of the operators, combined with the generation of behavior feature information and the flexible application of risk assessment configuration controls, abnormal behaviors can be detected in time and accurate risk assessments can be carried out. When an abnormal behavior is detected, a behavior verification rule is generated based on a preset behavior library, and the behavior data of the operators is matched, so as to achieve accurate identification and early warning, effectively prevent potential safety accidents, and ensure the personal safety of the operators and the normal operation of the operation site. In addition, the method can also flexibly process behavior data according to different types of behavior monitoring requests, such as video behavior monitoring requests and action behavior monitoring requests, further improving the accuracy and reliability of behavior analysis, and providing strong support for the safety management of the operation site.

[0068] In addition, this method can also optimize the safety management efficiency at the job site. Before obtaining the behavior data of the operators, by verifying whether the location information of the operators meets the preset range conditions, it ensures the pertinence and effectiveness of the collection of behavior data, avoids the interference of irrelevant data, and improves the efficiency of data processing. When generating the behavior feature information, through processing such as integrity detection, noise filtering, elimination of invalid data, and feature extraction of the behavior data, it can ensure the quality and accuracy of the behavior feature information, providing a reliable basis for subsequent risk assessment and behavior matching. At the same time, this method also further improves the usability of the behavior feature information through data optimization processing, such as quality enhancement, intensity adjustment, and contrast enhancement, making the entire safety analysis process more efficient and accurate, helping to reduce the labor cost and time cost of safety management at the job site, and enhancing the intelligent level of safety management. Brief Description of the Drawings

[0069] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, wherein:

[0070] Figure 1 It is a schematic flowchart of a method for safety analysis of a job site based on personnel behavior analysis provided by an embodiment of the present invention. Detailed Embodiments

[0071] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and then implement the present invention, rather than limiting the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to be able to convey the scope of the present invention fully to those skilled in the art.

[0072] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, equipment, method, or computer program product. Therefore, the present invention can be specifically implemented in the following forms: completely hardware, completely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0073] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0074] Refer to the following Figure 1 , Figure 1 It is a schematic flowchart of a method for safety analysis of a job site based on personnel behavior analysis provided by an embodiment of the present invention. As Figure 1As shown in the figure, a method for safety analysis of an operation site based on personnel behavior analysis includes:

[0075] S1 In response to receiving a behavior monitoring request through a target application associated with the operation site safety monitoring device, parse the behavior monitoring request to obtain the operator information corresponding to the behavior monitoring request, where the behavior monitoring request is a request to apply for behavior monitoring of the current operation site;

[0076] S2 Obtain the behavior data of the operator;

[0077] S3 Generate behavior feature information according to the behavior data;

[0078] S4 Display an analysis pop-up window corresponding to the behavior feature information, where the analysis pop-up window displays the behavior feature information and a risk assessment configuration control;

[0079] S5 Perform a risk assessment on the behavior feature information according to the risk level information configured for the risk assessment configuration control;

[0080] S6 In response to detecting an abnormal behavior request through the operation site safety monitoring device, generate a behavior verification rule according to a preset behavior library;

[0081] S7 Send the behavior verification rule to the operation site safety monitoring device, so that the operation site safety monitoring device displays the behavior verification rule through an external display;

[0082] S8 Receive the behavior data to be verified corresponding to the behavior verification rule sent by the operation site safety monitoring device as the information of the person to be identified, where the behavior data to be verified is the behavior record of the operator during the monitoring period;

[0083] S9 In response to obtaining the information of the person to be identified through the operation site safety monitoring device, perform a matching process on the information of the person to be identified according to the stored behavior feature information to obtain a matching result, where performing a matching process on the information of the person to be identified according to the stored behavior feature information to obtain a matching result includes: performing noise filtering and invalid data elimination processing on the behavior data to be verified to obtain processed behavior data;

[0084] S10 Perform feature extraction processing on the processed behavior data to obtain a behavior feature vector;

[0085] S11 Generate the behavior similarity between the behavior feature vector and each historical feature vector included in the behavior feature information to obtain a similarity set;

[0086] S12 determines the similarity that meets the first preset similarity condition in the similarity set as the target similarity, where the first preset similarity condition is that the similarity is the maximum value in the similarity set;

[0087] S13 in response to determining that the target similarity meets the second preset similarity condition, determines the feature vector corresponding to the target similarity as the matching feature vector, where the second preset similarity condition is that the target similarity is greater than the preset similarity threshold;

[0088] S14 generates a matching result according to the personnel information corresponding to the matching feature vector;

[0089] S15 in response to determining that the matching result indicates successful matching, controls the warning component of the on-site safety monitoring device of the operation to perform a safety warning operation.

[0090] It should be noted that the present invention proposes a method for on-site safety analysis based on personnel behavior analysis. Among them, the behavior monitoring request refers to a request initiated through a target application associated with the on-site safety monitoring device of the operation for applying to perform behavior monitoring on the current operation site. This request contains personnel information of the operation personnel, such as the identifier, location, etc. of the operation personnel, and is used to determine the object and scope to be monitored. The behavior data refers to the behavior records of the operation personnel at the operation site, which may include video data, motion sensor data, etc. These data are the basis for subsequent analysis. By parsing the behavior monitoring request to obtain the personnel information of the operation personnel and further obtaining the behavior data, it can provide a basis for subsequent generation of behavior feature information and risk assessment. The core of this method lies in timely discovering potential safety hazards and giving warnings through real-time monitoring and analysis of the behavior of the operation personnel.

[0091] Specifically, the behavior monitoring request mentioned in the present invention is a key concept. It is initiated by the safety monitoring system at the job site to start the behavior monitoring process for specific workers. The worker information includes the worker's identification and location information. The identification can be the work number, name, or other unique identifiers used to distinguish different workers. The location information can be the specific location coordinates of the worker at the job site obtained through positioning technology, which is used to determine whether the worker is in the area that needs to be monitored. The behavior data refers to various behavior records of the worker during the operation, such as the behavior video data collected by video monitoring devices or the motion sensor data collected by motion sensors. After collection, these data will undergo a series of processes, such as integrity detection, noise filtering, etc., to ensure the quality and usability of the data. In addition, the risk assessment configuration control is a user interface component used to set and adjust the parameters and rules of risk assessment, such as the classification criteria of risk levels. Through these configurations, the system can flexibly conduct risk assessment according to different job site requirements and safety standards.

[0092] Preferably, the processing process of the behavior data can be further refined. Taking the behavior video data as an example, first, the video data is frame-divided, that is, the video is decomposed into a series of frame images to form a behavior data sequence. For each frame image, the system will detect whether there is a complete human contour area. If so, the area is intercepted to obtain the contour data. Next, color simplification processing is performed on the contour data. For example, complex color information is simplified to grayscale images or other limited color ranges to reduce the data volume and highlight key features. At the same time, brightness detection and contrast detection are also performed on the simplified contour data to obtain the contour data intensity information and contrast information respectively. These information will be used to generate contour data parameters, and then the contour data that meets the preset data parameter conditions is selected as the target contour data. For the target contour data, data optimization processing is also performed, such as quality enhancement, intensity adjustment, and contrast enhancement, etc., to further improve the quality and usability of the data. Finally, contour data feature information is obtained through feature extraction processing and combined with the personnel information to generate behavior feature information. These behavior feature information will be used as an important basis for subsequent risk assessment, so as to achieve accurate analysis and risk warning of the worker's behavior.

[0093] In some embodiments, the worker information includes the worker identification and location information; and before obtaining the behavior data of the worker, the method further includes:

[0094] In response to detecting a selection operation on the start control of the behavior monitoring page, obtain the location information of the operator corresponding to the behavior monitoring request according to the operator identification, wherein the behavior monitoring page corresponds to the behavior monitoring request, and the operator information including the operator name is displayed on the behavior monitoring page;

[0095] Determine whether the location information meets the preset range conditions corresponding to the target operation area;

[0096] In response to determining that the location information meets the preset range conditions, send the behavior data collection instruction corresponding to the behavior monitoring request to the on-site safety monitoring device for the operation; and obtaining the behavior data of the operator includes: in response to receiving the feedback information indicating consent to collection corresponding to the behavior data collection instruction, obtaining the behavior data of the operator.

[0097] It should be noted that before obtaining the behavior data of the operator, the present invention detects the selection operation on the start control of the behavior monitoring page, obtains the location information according to the operator identification, and determines whether the location information meets the preset range conditions of the target operation area. This process is to ensure the pertinence and effectiveness of behavior data collection, and avoid unnecessary data collection for operators in non-target areas. Only when the location of the operator meets the preset range conditions, the behavior data collection instruction will be sent to the on-site safety monitoring device for the operation, thereby starting the behavior data collection process. This method can improve the efficiency of data collection, reduce the interference of invalid data, and provide more accurate basic data for subsequent behavior analysis.

[0098] Specifically, the behavior monitoring page is a user interface associated with the behavior monitoring request, used to display operator information, such as the operator name, etc. The start control is an operation button on this page. When the user (such as a safety manager or a system operator) clicks this control, the system will trigger the subsequent operator information acquisition process. The operator identification is an identifier used to uniquely identify the operator, which can be a work number, an ID card number, or other unique codes. The location information is the specific location coordinates of the operator at the operation site obtained through positioning technologies (such as GPS, Wi-Fi positioning, or RFID, etc.). The preset range conditions refer to the boundary conditions of a specific area in the operation site where behavior monitoring is required, such as the coordinate range of a specific operation area. When the location information of the operator falls within this range, the system considers that the operator is in the target operation area, thereby triggering the sending of the behavior data collection instruction. This instruction is a signal generated by the system, used to notify the on-site safety monitoring device to start collecting behavior data. The feedback information is the signal returned by the monitoring device after receiving the collection instruction, indicating that it is ready and agrees to start collecting behavior data.

[0099] Preferably, the acquisition of location information and the setting of preset range conditions can be further refined. For example, the location information can be obtained in real time through positioning tags (such as RFID tags or smart safety helmets, etc.) installed on the operator, and these tags will regularly send their location coordinates to the system. The preset range condition can be a polygonal area enclosed by multiple coordinate points, or a circular area within a certain radius centered on a certain fixed point. The system will judge whether the operator's location meets the conditions according to these coordinate ranges. When sending the behavior data collection instruction, parameters such as the priority and timeout time of the instruction can be set to ensure that the instruction can be received and responded to by the monitoring device in a timely and effective manner. For example, if the monitoring device does not return feedback information within the specified time, the system can automatically resend the instruction or trigger an alarm to ensure the smooth progress of behavior data collection.

[0100] In some embodiments, generating behavior feature information according to the behavior data includes:

[0101] Performing integrity detection processing on the behavior data to obtain an integrity detection result;

[0102] In response to determining that the integrity detection result indicates the existence of valid behavior records, generating behavior feature information according to the behavior data.

[0103] It should be noted that before generating behavior feature information, the present invention will perform integrity detection processing on the behavior data to ensure the validity and usability of the collected data. The integrity detection result will determine whether to continue generating behavior feature information. This process is crucial for ensuring the accuracy of subsequent analysis, because only complete and valid behavior data can generate accurate behavior feature information, thereby providing a reliable basis for risk assessment. In this way, the present invention can effectively filter out invalid or incomplete data and avoid interfering with subsequent security analysis.

[0104] Specifically, behavior data refers to the behavior records of workers obtained from on-site safety monitoring devices of operations. These records can be video data, motion sensor data, or other forms of monitoring data. Integrity detection processing is a data verification process used to check whether the behavior data contains valid behavior records. For example, for video behavior data, integrity detection may involve checking whether the video is continuous, whether there are obvious occlusions or blurs, etc.; for motion sensor data, it may check whether the sensor signals are complete and whether there is data loss. The integrity detection result is a judgment flag indicating whether the data meets the conditions for further processing. If the integrity detection result indicates the existence of valid behavior records, the system will generate behavior feature information based on this data. Behavior feature information is obtained by analyzing and processing behavior data and can reflect the key features of workers' behavior patterns, such as action frequency, behavior trajectory, or posture features, etc.

[0105] Preferably, the integrity detection processing can be further refined into multiple specific operations. Taking video behavior data as an example, integrity detection can include action recognition processing, that is, identifying the actions of personnel in the video through computer vision technology to determine whether there is a complete action sequence. For example, a deep learning model (such as a convolutional neural network) can be used to analyze video frames to identify specific actions of workers, such as raising hands, bending down, or walking. If the model can identify a series of coherent actions, the video data is considered to have integrity. For motion sensor data, integrity detection can include time series analysis of sensor signals to check for data loss or abnormal fluctuations. For example, a threshold can be set. If the sensor data does not change or the change amplitude exceeds the normal range within a certain period of time, the data is considered incomplete. Through these specific integrity detection steps, the system can more accurately screen out valid behavior data, thereby improving the accuracy and reliability of behavior feature information generation.

[0106] In some embodiments, the behavior monitoring request is a video behavior monitoring request, and the behavior data is behavior video data; and the integrity detection processing of the behavior data to obtain an integrity detection result includes: performing action recognition processing on the behavior data to obtain an action recognition result as the integrity detection result.

[0107] It should be noted that the behavior monitoring request mentioned in the present invention is a video behavior monitoring request, and the behavior data is behavior video data. In this case, the integrity detection process is achieved by performing action recognition processing on the behavior video data. The purpose of the action recognition processing is to extract the action features of the operators from the video data, so as to determine whether the video data contains complete and valid action records. This processing method can effectively identify the behavior patterns of the operators in the video, providing a basis for the subsequent generation of behavior feature information. The action recognition result obtained through the action recognition processing is used as the integrity detection result, which can ensure the quality and usability of the video data, and further improve the accuracy and reliability of the entire behavior analysis system.

[0108] Specifically, the video behavior monitoring request refers to a request initiated through a target application, which requires video monitoring of the operation site and analysis of the operators' behaviors. The behavior video data refers to the behavior records of the operators obtained from video monitoring devices, usually existing in the form of video streams. The action recognition processing in the integrity detection process is a computer vision-based technology used to extract action features from video data. This process usually involves the analysis of video frames to identify the action patterns of the people in the video. For example, deep learning algorithms such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs) can be used to implement action recognition. These algorithms can identify action sequences in the video, such as waving, jumping, running, etc., and determine whether the actions are complete. The integrity detection result is the output of the action recognition processing, indicating whether the video data contains valid action records. If the video data contains a complete action sequence, the data is considered valid and can be used for further generation of behavior feature information.

[0109] Preferably, the action recognition processing can be implemented using a deep learning model. For example, a model based on convolutional neural networks (CNNs) can be constructed, which identifies action features by analyzing the pixel information in video frames. The input parameters of the model can include the resolution, frame rate, and duration of the video frames. In the model training stage, a large number of labeled video data can be used as the training set, which contains various common actions of the operators. Through training, the model can learn the feature representations of different actions. In practical applications, the collected behavior video data is input into the trained model, and the model will output the action recognition result, indicating whether there is a complete action sequence in the video. If a complete action sequence is recognized, the result is used as the integrity detection result for further generation of behavior feature information. In addition, some parameters can be set to optimize the accuracy of action recognition. For example, a confidence threshold for action recognition can be set, and only when the model's recognition confidence in the action is higher than this threshold, the action is considered valid. In this way, the accuracy and reliability of the integrity detection can be further improved.

[0110] In some embodiments, generating behavior feature information based on the behavior data includes:

[0111] Performing frame processing on the behavior data to obtain a behavior data sequence;

[0112] For each behavior data unit in the behavior data sequence, perform the following steps: Determine whether there is a complete human contour area in the behavior data unit;

[0113] In response to determining that there is a complete human contour area in the behavior data unit, perform cropping processing on the human contour area in the behavior data unit to obtain contour data;

[0114] Performing color simplification processing on the contour data to obtain simplified contour data;

[0115] Performing brightness detection on the simplified contour data to obtain contour data intensity information;

[0116] Performing contrast detection on the simplified contour data to obtain contour data contrast information;

[0117] Generating contour data parameters based on the simplified contour data quality information, the contour data intensity information, and the contour data contrast information;

[0118] Selecting, from the obtained contour data, the contour data that meets the preset data parameter conditions as the target contour data according to the obtained respective contour data parameters;

[0119] Performing data optimization processing on the target contour data according to the simplified contour data quality information, contour data intensity information, and contour data contrast information corresponding to the target contour data to obtain optimized contour data;

[0120] Performing feature extraction processing on the optimized contour data to obtain contour data feature information;

[0121] Generating behavior feature information based on the contour data feature information and the personnel information.

[0122] It should be noted that the process of processing behavioral data in the present invention involves a series of complex analysis and optimization operations on behavioral video data to generate behavioral feature information. This process includes frame-by-frame processing of behavioral data, detection and extraction of the personnel contour area, color simplification processing, brightness and contrast detection, as well as data optimization and feature extraction based on these detection results. Through these steps, key feature information that can accurately reflect the behavior patterns of operators can be extracted from the original video data, providing high-quality data support for subsequent behavior analysis and risk assessment. This method can effectively improve the accuracy and reliability of behavior analysis while reducing the interference of invalid data on the analysis results.

[0123] Specifically, the behavioral data sequence refers to decomposing the behavioral video data into a series of individual frame images, and each frame image contains the behavioral information of the operator at a certain moment. When processing each frame image, it is first necessary to determine whether there is a complete personnel contour area, that is, whether the body contour of the operator is complete and clearly visible. If there is a complete personnel contour area, the area is intercepted to obtain contour data. Color simplification processing refers to simplifying the color information in the contour data into a more easily processed form, such as converting a color image into a grayscale image or other limited color ranges to reduce the data volume and highlight key features. Brightness detection and contrast detection are image quality assessment operations performed on the simplified contour data. Brightness detection is used to evaluate the brightness of the image, and contrast detection is used to evaluate the brightness difference between different regions in the image. These detection results will be used to generate contour data parameters, and then target contour data that meets the preset conditions is selected and data optimization processing is performed on it. Finally, contour data feature information is extracted. These feature information are combined with personnel information to generate behavioral feature information for subsequent behavior analysis.

[0124] Preferably, the detection and extraction of the human contour area can be achieved by computer vision technology. For example, the background subtraction method or a deep learning model (such as an object detection model based on a convolutional neural network) can be used to detect the human contour area in each frame of the image. If the detected human contour area is complete and clear, the area is extracted to ensure the accuracy of subsequent processing. The color simplification process can be achieved by converting the image into a grayscale image, which can effectively reduce the complexity of color information while retaining the basic structural features of the image. The brightness detection can be achieved by calculating the average brightness value of the pixels in the image, and the contrast detection can be achieved by calculating the standard deviation of the pixel brightness in the image. These detection results will be used to generate contour data parameters. For example, the quality of the contour data can be evaluated by calculating the weighted sum of the brightness value and the contrast value. In the data optimization process, quality enhancement, intensity adjustment, and contrast enhancement operations can be performed on the target contour data according to the quality information, intensity information, and contrast information of the contour data. For example, if the brightness of the contour data is low, the visibility of the image can be enhanced by adjusting the brightness value of the image; if the contrast is low, the contour area can be highlighted by adjusting the contrast of the image. Finally, feature extraction processing is performed on the optimized contour data. A deep learning model (such as a convolutional neural network) can be used to extract the feature vectors of the contour data, and these feature vectors will serve as the basis for behavioral feature information for subsequent behavioral analysis and risk assessment.

[0125] In some embodiments, the color simplification process of the contour data to obtain the simplified contour data includes:

[0126] Performing a color simplification process on the contour data to obtain the simplified contour data;

[0127] Removing each data point in the simplified contour data that satisfies the preset edge condition to obtain the contour data after removal;

[0128] For each data point in the simplified contour data, perform the following steps: determining the data point adjacent to the right of the data point in the simplified contour data as the right adjacent data point;

[0129] Determining the data point adjacent to the top of the data point in the simplified contour data as the top adjacent data point;

[0130] Generating a first value and a second value according to the value of the right adjacent data point and the value of the data point;

[0131] Generating a third value and a fourth value according to the value of the top adjacent data point and the value of the data point;

[0132] Determine the sum of each obtained first value, each second value, each third value, and each fourth value as the fifth value;

[0133] Determine the number of each data point included in the simplified contour data as the total number of data points;

[0134] Determine the ratio of the fifth value to the total number of data points as the contour data quality information corresponding to the simplified contour data.

[0135] It should be noted that the step of performing color simplification processing on the contour data in the present invention further refines the data processing flow. This step not only simplifies the contour data but also further optimizes the data quality by removing data points that meet the preset edge conditions. In addition, by calculating the numerical relationship between the data points adjacent to each data point, contour data quality information is generated. This process can effectively reduce the interference of noise data and, at the same time, evaluate the quality of the contour data in a quantitative manner, providing a more accurate basis for subsequent data optimization and feature extraction. In this way, the present invention can more accurately process the behavior video data, thereby improving the accuracy and reliability of generating behavior feature information.

[0136] Specifically, the contour data refers to the image data containing the operator's contour intercepted from the behavior video data. Color simplification processing is to simplify complex color information into a more easily processable form, such as converting a color image into a grayscale image or other limited color ranges. The preset edge conditions refer to certain boundary features defined in the contour data, such as the brightness or color change threshold of edge pixels. The data points that meet these conditions are considered edge data points and may interfere with subsequent processing, so they need to be removed. For each data point, its right adjacent data point and upper adjacent data point refer to the pixel points adjacent to the current data point horizontally to the right and vertically upward in the image matrix. By calculating the relationship between the numerical values of these adjacent data points and the numerical value of the current data point, a series of numerical values can be generated, and these numerical values reflect the mutual relationship between the data points. Finally, by calculating the ratio of the sum of these numerical values to the total number of data points, the contour data quality information is obtained, and this information is used to evaluate the overall quality of the contour data.

[0137] Preferably, the color simplification process can be achieved by converting a color image into a grayscale image. This method can effectively reduce the complexity of color information while retaining the basic structural features of the image. The preset edge condition can be set such that the brightness change of an edge pixel exceeds a certain threshold. For example, when the brightness change exceeds a certain set value, the pixel is considered to belong to the edge data points and is excluded. When calculating the numerical relationship adjacent to the data point, specific calculation rules can be defined. For example, the first numerical value can be the difference between the brightness value of the right adjacent data point and the brightness value of the current data point, the second numerical value can be the ratio of the brightness value of the right adjacent data point to the brightness value of the current data point, and the third and fourth numerical values respectively correspond to similar calculations for the upper adjacent data point. By adding these numerical values to obtain a fifth numerical value and then dividing by the total number of data points, the contour data quality information is obtained. This information can be used for subsequent data optimization processing, such as selecting whether to perform further enhancement processing on the contour data according to the level of the quality information. In this way, the data processing flow can be controlled more precisely to ensure that the generated behavioral feature information has high quality and high reliability.

[0138] In some embodiments, the performing data optimization processing on the target contour data according to the simplified contour data quality information, contour data intensity information, and contour data contrast information corresponding to the target contour data to obtain optimized contour data includes:

[0139] In response to determining that the simplified contour data quality information corresponding to the target contour data satisfies a preset quality optimization condition, performing quality enhancement processing on the target contour data to update the target contour data;

[0140] In response to determining that the contour data intensity information corresponding to the target contour data satisfies a preset intensity optimization condition, performing intensity adjustment processing on the target contour data to update the target contour data;

[0141] In response to determining that the contour data contrast information corresponding to the target contour data satisfies a preset contrast optimization condition, performing contrast enhancement processing on the target contour data to update the target contour data;

[0142] Performing size normalization processing on the updated target contour data to update the target contour data;

[0143] Determining the updated target contour data as the optimized contour data.

[0144] It should be noted that the steps of optimizing the target contour data in the present invention are aimed at further improving the quality and accuracy of the behavioral feature information. By performing targeted optimization processing according to the quality, intensity, and contrast information of the contour data, such as quality enhancement, intensity adjustment, and contrast enhancement, it can be ensured that the optimized contour data can more clearly and accurately reflect the behavioral characteristics of the operator. In addition, performing size normalization processing on the updated target contour data can unify the data format and make it more suitable for subsequent feature extraction and analysis processes. This series of optimization operations provides a strong guarantee for generating high-quality behavioral feature information, thereby improving the reliability and effectiveness of the entire behavioral analysis system.

[0145] Specifically, the target contour data refers to the contour data that meets the preset data parameter conditions after preliminary processing (such as color simplification, noise removal, etc.). The contour data quality information reflects the overall quality of the contour data, such as the clarity, integrity, and noise level of the image. The contour data intensity information usually refers to the average level of the brightness or gray value of the image, reflecting the overall light and dark degree of the image. The contour data contrast information represents the degree of light and dark difference between different regions in the image, and a higher contrast helps to highlight the contour features. The preset quality optimization conditions, preset intensity optimization conditions, and preset contrast optimization conditions refer to the thresholds or standards set according to actual application requirements, which are used to judge whether it is necessary to perform corresponding optimization processing on the target contour data. For example, if the quality information of the target contour data is lower than a certain set threshold, quality enhancement processing is triggered; if the intensity information is not within a reasonable range, intensity adjustment processing is performed; if the contrast information is insufficient, contrast enhancement processing is performed. The size normalization processing refers to adjusting the size of the target contour data to a unified standard size for subsequent processing and analysis.

[0146] Preferably, the specific steps of data optimization processing can be further refined. For example, in quality enhancement processing, image filtering techniques such as median filtering or Gaussian filtering can be used to reduce noise and improve image quality. Specific parameter settings include the size and shape of the filter. For example, the window size of the median filter can be adjusted according to the resolution and noise level of the contour data. In intensity adjustment processing, histogram equalization technology can be used to adjust the brightness distribution of the image, making the intensity information of the image more uniform. Contrast enhancement processing can be achieved by adjusting the contrast range of the image, such as enhancing the contrast of the image through linear stretching or non-linear transformation (such as gamma correction). Specific parameter settings include the range of contrast adjustment and the parameters of the transformation function. In size normalization processing, the width and height of the target contour data can be adjusted to a preset standard size. For example, all contour data can be uniformly adjusted to an image of 128×128 pixels. This process can be achieved through an image interpolation algorithm, and the specific parameters include the interpolation method (such as nearest neighbor interpolation, bilinear interpolation, etc.) and the target size. Through these specific optimization processing steps, the quality and consistency of the target contour data can be ensured, thus providing high-quality data support for subsequent behavior feature extraction and analysis.

[0147] In some embodiments, the behavior monitoring request is an action behavior monitoring request, and the behavior data is action sensor data; and the integrity detection process of the behavior data to obtain an integrity detection result includes: performing action feature extraction processing on the behavior data to obtain an action feature result as the integrity detection result; and generating behavior feature information according to the behavior data, including:

[0148] Performing noise filtering and invalid data removal processing on the behavior data to obtain processed data;

[0149] Performing feature extraction processing on the processed data to obtain an action feature vector;

[0150] For each feature dimension in the action feature vector, perform the following steps: determining the eigenvalue corresponding to the feature dimension;

[0151] Determining the feature weight corresponding to the feature dimension;

[0152] Generating a comprehensive feature score according to the eigenvalue and the feature weight;

[0153] Selecting the comprehensive feature scores that meet the preset score conditions from the generated comprehensive feature scores as the target comprehensive feature scores;

[0154] Determining the target comprehensive feature score and the personnel information as behavior feature information.

[0155] It should be noted that, in the present invention, a method for integrity detection of action sensor data and generation of behavior feature information is provided for the processing manner of behavior data in response to an action behavior monitoring request. Action sensor data usually contains action information of the operator, such as acceleration, angular velocity, etc. By performing noise filtering, invalid data elimination, and feature extraction on these data, behavior feature information reflecting the behavior pattern of the operator can be generated. This method is particularly applicable to scenarios where behavior data cannot be obtained through video monitoring, such as in low-light environments or work sites where privacy protection is required. By means of comprehensive feature scoring, the behavior characteristics of the operator can be evaluated more accurately, providing a reliable basis for subsequent risk assessment.

[0156] Specifically, an action behavior monitoring request refers to a request initiated through a target application to monitor the actions of operators at a work site. Action sensor data refers to the action information of the operator collected by action sensors (such as accelerometers, gyroscopes, etc.), and these data usually record information such as the amplitude, frequency, and direction of the operator's actions in the form of a time series. Integrity detection processing refers to analyzing the action sensor data to determine whether it contains complete and valid action features. Noise filtering and invalid data elimination processing are to remove interference signals and unreasonable data points in the data, thereby improving the data quality. Feature extraction processing is the process of converting the processed action data into feature vectors, and each feature dimension in the feature vector corresponds to a specific feature of the action data. Feature weight refers to the proportion of importance of each feature dimension in the behavior feature information, which can be set according to the actual application scenario. Comprehensive feature scoring is calculated by combining the feature values with the feature weights, and it is a quantitative index used to evaluate the behavior characteristics of the operator. The preset scoring condition refers to the standard set according to actual needs for screening behavior feature information. For example, a scoring threshold is set, and only the comprehensive feature scoring that meets this threshold will be selected as the target comprehensive feature scoring.

[0157] Preferably, the processing process of the motion sensor data can be further refined. For example, in the noise filtering and invalid data elimination processing stage, digital filtering techniques can be adopted, such as using a low-pass filter to remove high-frequency noise, or by setting a threshold to eliminate data points outside the normal range. In the feature extraction processing stage, machine learning algorithms, such as principal component analysis (PCA) or support vector machine (SVM), can be used to extract the key features of the motion data. Specific parameter settings include the cut-off frequency of the filter and the number of principal components of PCA, etc. For the setting of feature weights, it can be adjusted according to the physical meaning of the motion data and the actual application scenario. For example, the weight of acceleration data may be higher than that of angular velocity data. The calculation of the comprehensive feature score can be obtained by multiplying the feature value of each feature dimension by its corresponding feature weight and then summing them up. The selection of the target comprehensive feature score can be achieved by setting a score threshold. For example, select the features with a score higher than a certain fixed value as the target comprehensive feature score. Through these specific processing steps, the behavioral feature information can be generated more accurately, thereby improving the accuracy and reliability of behavioral analysis.

[0158] The above various embodiments of the present invention have the following beneficial effects: The present invention can collect and intelligently analyze the behavioral data of the operators in real time. By dynamically generating behavioral feature information and a risk assessment mechanism, the accuracy of safety monitoring at the operation site is significantly improved. When an abnormal behavior is detected, a verification rule can be automatically generated and matched with historical data to quickly identify potential risks, thereby triggering the warning mechanism in a timely manner and effectively reducing the possibility of safety accidents.

[0159] In addition, the present invention can perform adaptive processing for different monitoring requirements (such as video behavior or sensor motion data). Through steps such as data optimization, feature extraction, and similarity matching, the reliability of behavioral analysis is ensured. At the same time, by combining the personnel location information with the operation area range conditions, precise monitoring can be achieved, and the data validity can be improved through technical means such as quality enhancement and intensity adjustment, further enhancing the timeliness and accuracy of safety warnings.

[0160] The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0161] An electronic device may include a processing device (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, the ROM, and the RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0162] Generally, the following devices may be connected to the I / O interface: input devices including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices including, for example, a magnetic tape, a hard disk, etc.; and a communication device. The communication device may allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data.

[0163] Furthermore, the storage medium of the embodiments of the present application stores program instructions capable of implementing all the above methods. Among them, the program instructions may be stored in the above storage medium in the form of a software product, including several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in the various embodiments of the present application. And the foregoing storage medium includes: various media that can store program codes such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, or a terminal device such as a computer, a server, a mobile phone, or a tablet.

[0164] The above description is only some preferred embodiments of the present invention and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, a technical solution formed by mutually replacing the above features with technical features having similar functions (but not limited to) disclosed in the embodiments of the present invention.

Claims

1. A safety analysis method for a job site based on personnel behavior analysis, characterized in that Including: In response to receiving a behavior monitoring request through a target application associated with a job site safety monitoring device, parsing the behavior monitoring request to obtain the operator information corresponding to the behavior monitoring request, where the behavior monitoring request is a request to apply for behavior monitoring of the current job site; Obtaining the behavior data of the operator; Generating behavior feature information according to the behavior data; Displaying an analysis pop-up window corresponding to the behavior feature information, where the analysis pop-up window displays the behavior feature information and a risk assessment configuration control; Performing a risk assessment on the behavior feature information according to the risk level information configured for the risk assessment configuration control; In response to detecting an abnormal behavior request through the job site safety monitoring device, generating a behavior verification rule according to a preset behavior library; Sending the behavior verification rule to the job site safety monitoring device, so that the job site safety monitoring device displays the behavior verification rule through an external display; Receiving the behavior data to be verified corresponding to the behavior verification rule sent by the job site safety monitoring device as the information of the person to be identified, where the behavior data to be verified is the behavior record of the operator during the monitoring period; In response to obtaining the information of the person to be identified through the job site safety monitoring device, performing a matching process on the information of the person to be identified according to each stored behavior feature information to obtain a matching result, where performing a matching process on the information of the person to be identified according to each stored behavior feature information to obtain a matching result includes: performing noise filtering and invalid data elimination processing on the behavior data to be verified to obtain processed behavior data; Performing feature extraction processing on the processed behavior data to obtain a behavior feature vector; Generating the behavior similarity between the behavior feature vector and each historical feature vector included in each behavior feature information to obtain a similarity set; Determining the similarity that meets the first preset similarity condition in the similarity set as the target similarity, where the first preset similarity condition is that the similarity is the maximum value in the similarity set; In response to determining that the target similarity meets the second preset similarity condition, determining the feature vector corresponding to the target similarity as the matching feature vector, where the second preset similarity condition is that the target similarity is greater than a preset similarity threshold; Generating a matching result according to the personnel information corresponding to the matching feature vector; In response to determining that the matching result indicates successful matching, controlling the warning component of the job site safety monitoring device to perform a safety warning operation.

2. The method according to claim 1, wherein The operator information includes an operator identifier and location information; and before obtaining the behavior data of the operator, the method further includes: In response to detecting a selection operation on a start control acting on a behavior monitoring page, obtaining the location information of the operator corresponding to the behavior monitoring request according to the operator identifier, where the behavior monitoring page corresponds to the behavior monitoring request, and the person name included in the operator information is displayed on the behavior monitoring page; Determine whether the location information meets the preset range conditions corresponding to the target operation area; In response to determining that the location information meets the preset range conditions, send a behavior data collection instruction corresponding to the behavior monitoring request to the on-site safety monitoring device for the operation; and obtaining the behavior data of the operator includes: in response to receiving feedback information indicating consent to collection corresponding to the behavior data collection instruction, obtaining the behavior data of the operator.

3. The method according to claim 2, wherein Generating behavior feature information based on the behavior data includes: Performing integrity detection processing on the behavior data to obtain an integrity detection result; In response to determining that the integrity detection result indicates the existence of valid behavior records, generating behavior feature information based on the behavior data.

4. The method according to claim 3, wherein The behavior monitoring request is a video behavior monitoring request, and the behavior data is behavior video data; And performing integrity detection processing on the behavior data to obtain an integrity detection result includes: performing action recognition processing on the behavior data to obtain an action recognition result as the integrity detection result.

5. The method according to claim 4, characterized in that Generating behavior feature information based on the behavior data includes: Performing frame division processing on the behavior data to obtain a behavior data sequence; For each behavior data unit in the behavior data sequence, perform the following steps: determine whether there is a complete human contour area in the behavior data unit; In response to determining that there is a complete human contour area in the behavior data unit, perform intercepting processing on the human contour area in the behavior data unit to obtain contour data; Performing color simplification processing on the contour data to obtain simplified contour data; Performing brightness detection on the simplified contour data to obtain contour data intensity information; Performing contrast detection on the simplified contour data to obtain contour data contrast information; Generating contour data parameters based on the simplified contour data quality information, the contour data intensity information, and the contour data contrast information; Selecting, from the obtained contour data, the contour data that meets the preset data parameter conditions as target contour data according to the obtained contour data parameters; Performing data optimization processing on the target contour data according to the simplified contour data quality information, contour data intensity information, and contour data contrast information corresponding to the target contour data to obtain optimized contour data; Performing feature extraction processing on the optimized contour data to obtain contour data feature information; Generating behavior feature information based on the contour data feature information and the personnel information.

6. The method according to claim 5, characterized in that, Performing color simplification processing on the contour data to obtain simplified contour data includes: Performing color simplification processing on the contour data to obtain simplified contour data; Removing each data point in the simplified contour data that meets the preset edge conditions to obtain post-removal contour data; For each data point in the simplified contour data, perform the following steps: determining the data point adjacent to the right of the data point in the simplified contour data as the right adjacent data point; Determine the data points adjacent to the data point in the simplified contour data as the upper adjacent data points; Generate a first value and a second value based on the value of the right adjacent data point and the value of the data point; Generate a third value and a fourth value based on the value of the upper adjacent data point and the value of the data point; Determine the sum of all the obtained first values, second values, third values, and fourth values as the fifth value; Determine the number of all data points included in the simplified contour data as the total number of data points; Determine the ratio of the fifth value to the total number of data points as the contour data quality information corresponding to the simplified contour data.

7. The method according to claim 5, characterized in that, The data optimization process for the target contour data according to the simplified contour data quality information, contour data intensity information, and contour data comparison information corresponding to the target contour data to obtain the optimized contour data includes: In response to determining that the simplified contour data quality information corresponding to the target contour data meets the preset quality optimization condition, perform quality enhancement processing on the target contour data to update the target contour data; In response to determining that the contour data intensity information corresponding to the target contour data meets the preset intensity optimization condition, perform intensity adjustment processing on the target contour data to update the target contour data; In response to determining that the contour data comparison information corresponding to the target contour data meets the preset comparison optimization condition, perform comparison enhancement processing on the target contour data to update the target contour data; Perform size normalization processing on the updated target contour data to update the target contour data; Determine the updated target contour data as the optimized contour data.

8. The method according to claim 3, wherein The behavior monitoring request is an action behavior monitoring request, and the behavior data is action sensor data; And the integrity detection process for the behavior data to obtain an integrity detection result includes: performing action feature extraction processing on the behavior data to obtain an action feature result as the integrity detection result; and generating behavior feature information according to the behavior data, including: Perform noise filtering and invalid data removal processing on the behavior data to obtain processed data; Perform feature extraction processing on the processed data to obtain an action feature vector; For each feature dimension in the action feature vector, perform the following steps: determine the eigenvalue corresponding to the feature dimension; Determine the feature weight corresponding to the feature dimension; Generate a comprehensive feature score based on the eigenvalue and the feature weight; Select the comprehensive feature scores that meet the preset score condition from the generated comprehensive feature scores as the target comprehensive feature scores; Determine the target comprehensive feature scores and the personnel information as the behavior feature information.

9. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-8.

10. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the method according to any one of claims 1-8.

Images