Electricity utilization safety detection method and device based on intelligent wearable device

Abstract

The invention provides an electricity utilization safety detection method and device based on intelligent wearable equipment, and relates to the technical field of detection. Acquiring basic electrical detection information sent by the intelligent wearable device for the target electrical device; acquiring environment adaptability detection information sent by the intelligent wearable equipment for the environment where the target electric equipment is located; performing feature selection on the basic electrical detection information and the environmental adaptability detection information by adopting a random forest algorithm to obtain a target feature group; inputting the target feature group into a preset power utilization safety detection model, and determining an abnormal behavior feature point; judging a size relationship between an area corresponding to the abnormal behavior feature region and an area corresponding to a preset region, wherein the abnormal behavior feature region is composed of sub-regions corresponding to a plurality of abnormal behavior feature points; and if the area corresponding to the abnormal behavior feature region is greater than or equal to the area corresponding to the preset region, determining that the target electric equipment has the potential safety hazard of electricity utilization. According to the invention, the accuracy of electricity utilization safety detection is improved.

Description

Technical Field

[0001] The present application relates to the technical field of detection technology, and specifically to a method and device for detecting power safety based on a smart wearable device. Background Art

[0002] In the current power management field, the safety inspection of electrical equipment plays a vital role. It is not only the cornerstone to ensure the continuous and stable operation of the power system, but also the first line of defense to prevent safety accidents such as fire and electric shock. However, the commonly used inspection method is manual inspection. Although it plays a role to a certain extent, its limitations are becoming increasingly prominent and it is difficult to meet the increasingly complex and stringent power safety needs.

[0003] Specifically, manual inspections are highly dependent on the professional skills, rich experience, and current working status of inspectors. The instability and diversity of these factors often lead to the problem of excessive subjectivity in the inspection process. Different inspectors may adopt different inspection standards and processes due to differences in understanding, concentration, or sensitivity to specific safety hazards, which in turn affects the accuracy of the inspection results.

[0004] Therefore, there is an urgent need for a method and device for detecting power safety based on smart wearable devices. Summary of the invention

[0005] The present application provides a method and device for detecting electricity safety based on a smart wearable device, which is convenient for improving the accuracy of electricity safety detection.

[0006] In the first aspect of the present application, a method for electricity safety detection based on a smart wearable device is provided, the method comprising: obtaining basic electrical detection information for a target electrical device sent by a smart wearable device; obtaining environmental adaptability detection information for the environment in which the target electrical device is located and sent by the smart wearable device; using a random forest algorithm to perform feature selection on the basic electrical detection information and the environmental adaptability detection information to obtain a target feature group; inputting the target feature group into a preset electricity safety detection model to determine abnormal behavior feature points; judging the size relationship between an area corresponding to an abnormal behavior feature region and an area corresponding to a preset region, the abnormal behavior feature region being composed of sub-regions corresponding to a plurality of abnormal behavior feature points, and one abnormal behavior feature point corresponding to one sub-region; if the area corresponding to the abnormal behavior feature region is greater than or equal to the area corresponding to the preset region, it is determined that the target electrical device has an electricity safety hazard.

[0007] By adopting the above technical solution, the basic electrical detection information and environmental adaptability detection information of the target electrical equipment can be obtained in real time through smart wearable devices, so that the detection process no longer relies on traditional regular manual inspections, which greatly improves the real-time and proactive nature of the detection. This helps to timely discover and deal with potential safety hazards and reduce the risk of safety accidents caused by delayed discovery. The random forest algorithm is used to select features from the collected data, which can automatically extract the most critical feature combination (target feature group) for the detection of power safety hazards. This process not only reduces human intervention and improves the intelligence level of the detection process, but also improves the accuracy and reliability of the detection results by optimizing the feature combination. The target feature group is input into the preset power safety detection model to accurately identify abnormal behavior feature points. These feature points are directly related to potential power safety hazards, providing a solid data foundation for subsequent hazard assessment. By constructing an abnormal behavior feature area and comparing the area of ​​the area with the area of ​​the preset area, a quantitative assessment of power safety hazards is achieved. This regionalized assessment method is not only intuitive and easy to understand, but also can take different countermeasures according to the severity of the hazard, improving the scientificity and effectiveness of risk management. The system not only focuses on the electrical performance of the electrical equipment itself, but also comprehensively considers the impact of the environment in which the equipment is located on its operating safety. This comprehensive detection method helps to discover safety hazards caused by environmental factors and improves the comprehensiveness and accuracy of the detection.

[0008] Optionally, the obtaining of basic electrical detection information for the target electrical equipment sent by the smart wearable device specifically includes: receiving current information, voltage information and equipment temperature information sent by a sensor group, the sensor group including a current sensor, a voltage sensor and a temperature sensor, and the sensor group is located on the smart wearable device; preprocessing the current information, the voltage information and the equipment temperature information to obtain the basic electrical detection information, and the preprocessing includes denoising, filtering and normalization.

[0009] By adopting the above technical solution, the current, voltage and temperature of the target electrical equipment can be simultaneously acquired through a sensor group that integrates current sensors, voltage sensors and temperature sensors. This multi-source data acquisition method can more comprehensively reflect the operating status of the equipment and provide richer data support for subsequent safety hazard detection. The sensor group is directly installed on the smart wearable device, so that the data acquisition process can be carried out in real time. This real-time performance ensures the freshness and accuracy of the data and helps to promptly detect abnormal conditions in the operation of the equipment. Denoising, filtering and normalizing the received current, voltage and device temperature information are key steps in data preprocessing. Denoising can remove noise interference in the signal and improve the signal-to-noise ratio of the signal; filtering can further smooth the signal and remove high-frequency noise or unnecessary fluctuations; normalization converts all data to the same dimension to facilitate subsequent data analysis and processing. These preprocessing steps can significantly improve the accuracy and reliability of the data and lay a solid foundation for subsequent safety hazard detection. Data preprocessing not only improves the accuracy of the data, but also enhances the robustness of the entire system. Through denoising and filtering, the system can better cope with interference caused by changes in the external environment or equipment failures, ensuring the stability and reliability of the test results. The preprocessed basic electrical test information is more regular and easier to process. This not only facilitates the subsequent random forest algorithm feature selection and power safety test model analysis, but also makes the entire test process smoother and more efficient.

[0010] Optionally, the obtaining of environmental adaptability detection information sent by the smart wearable device for the environment in which the target electrical device is located specifically includes: receiving ambient temperature information, ambient humidity information and insulation performance information sent by the smart wearable device; performing temperature compensation on the ambient temperature, performing humidity correction on the ambient humidity information, and performing electromagnetic shielding on the insulation performance information to obtain the environmental adaptability detection information.

[0011] By adopting the above technical solution, by receiving the ambient temperature, ambient humidity and insulation performance information, the system can comprehensively consider the impact of the environment in which the target electrical equipment is located on its operating safety. This comprehensive environmental adaptability detection helps to discover safety hazards caused by environmental factors and improve the accuracy and comprehensiveness of the detection. Temperature compensation for ambient temperature can eliminate the impact of temperature changes on equipment performance test results and ensure the accuracy of test data. Similarly, humidity correction for ambient humidity information can eliminate the interference of humidity changes on parameters such as insulation performance and improve the reliability of insulation performance detection. These processing steps jointly improve the accuracy of environmental adaptability detection information. Electromagnetic shielding of insulation performance information is an important measure to prevent external electromagnetic interference from affecting the test results. Electromagnetic shielding can reduce or eliminate the interference of electromagnetic fields on insulation performance detection equipment and ensure the stability and reliability of the test results. This step enhances the anti-interference ability of the system and improves the accuracy of the test results. Through processing steps such as temperature compensation, humidity correction and electromagnetic shielding, the system can more accurately reflect the operating conditions of the target electrical equipment in a specific environment. This test result based on actual environmental conditions is more reliable and helps power companies to formulate more scientific and reasonable safety management measures.

[0012] Optionally, the use of a random forest algorithm to perform feature selection on the basic electrical detection information and the environmental adaptability detection information to obtain a target feature group specifically includes: based on the random forest algorithm, obtaining feature importance scores for multiple basic electrical features included in the basic electrical detection information and multiple environmental adaptability features included in the environmental adaptability detection information, one basic electrical feature corresponds to one feature importance score, and one environmental adaptability feature corresponds to one feature importance score; selecting features from the multiple basic electrical features and the multiple environmental adaptability features, each of which has a corresponding score greater than a preset score, to obtain the target feature group.

[0013] By adopting the above technical solution, in terms of feature selection, random forest can evaluate the importance of each feature in the model construction process and give the corresponding feature importance score. This method can efficiently screen out the most valuable features for classification or regression tasks, avoiding the computational complexity and overfitting problems caused by too high feature dimensions. By selecting features with feature importance scores greater than the preset scores as the target feature group, it can be ensured that these features have a significant contribution to the detection of power safety hazards. This targeted feature selection can improve the performance of subsequent power safety detection models, enabling them to more accurately identify potential power safety hazards. The feature importance scores provided by the random forest algorithm not only help with feature selection, but also enhance the interpretability of the model. By looking at which features have higher scores, we can understand which factors are more important for the detection of power safety hazards, thereby providing valuable reference information for the safety management of power companies. Since the environmental adaptability detection information is taken into account, this process can more comprehensively evaluate the operating status of the target power equipment in a specific environment. By selecting features related to environmental factors, the model can more accurately reflect the impact of environmental factors on the safety performance of the equipment, thereby adapting to the power safety detection needs in different environments. The entire feature selection process is completed automatically based on the random forest algorithm without manual intervention. This automated and intelligent feature selection method not only improves work efficiency, but also reduces the impact of human factors on the results, making the detection results more objective and reliable.

[0014] Optionally, the inputting the target feature group into a preset electricity safety detection model to determine the abnormal behavior feature points specifically includes: obtaining multiple historical feature groups, the historical feature groups including historical basic electrical features and historical environmental adaptability features; matching the target feature group with multiple historical feature groups according to the current time period to obtain a target historical feature group; comparing the target feature group with the target historical feature group to screen out abnormal behavior features, the abnormal behavior features being features that do not meet preset threshold conditions; determining the abnormal behavior feature points based on the correspondence between the abnormal behavior features and the abnormal behavior feature points, the preset electricity safety detection model pre-stores the correspondence between the abnormal behavior features and the abnormal behavior feature points.

[0015] By adopting the above technical solution, by obtaining multiple historical feature groups and matching them with the current target feature group, the historical data closest to the target time period can be found as a reference. This analysis method based on historical data can more accurately reflect the operating status of the equipment under similar conditions in the past, thereby improving the accuracy of anomaly detection. The process can automatically match the corresponding historical data according to the current time period, which means that the system can dynamically adapt to environmental conditions and equipment status changes in different time periods. This dynamic adaptability enables the system to maintain high detection accuracy in different time periods. By comparing the target feature group with the target historical feature group, those abnormal behavior features that do not meet the preset threshold conditions can be accurately screened out. This process effectively filters out fluctuations and changes within the normal range and focuses on identifying abnormal features that may represent safety hazards. The corresponding relationship between abnormal behavior features and abnormal behavior feature points is stored in the preset power safety detection model. This enables the system to quickly and accurately locate specific abnormal behavior feature points after identifying abnormal behavior features. This clear abnormal location helps power companies to quickly respond to and deal with potential safety hazards. The entire process is highly automated and anomaly detection can be completed without human intervention. This greatly improves detection efficiency, allowing power companies to identify and address potential safety hazards more quickly.

[0016] Optionally, the method also includes: sending the abnormal behavior characteristic area and the target electrical equipment to an AR cloud platform; receiving a standard operating procedure generated for the abnormal behavior characteristic area and the target electrical equipment from the AR cloud platform, the standard operating procedure being used to eliminate electrical safety hazards existing in the target electrical equipment; and sending the standard operating procedure to the AR glasses so that the corresponding wearer of the AR glasses can repair the target electrical equipment.

[0017] By adopting the above technical solution, once the abnormal behavior characteristic area of ​​the target electrical equipment is identified, the system can quickly send relevant information to the AR cloud platform and receive the standard operating procedures for the abnormality in almost real time. This immediate response mechanism greatly shortens the time from discovering hidden dangers to formulating solutions, and improves processing efficiency. The standard operating procedures generated by the AR cloud platform ensure the standardization and consistency of maintenance work. These procedures are based on professional knowledge and accumulated experience, and can guide maintenance personnel wearing AR glasses to follow the correct steps to reduce human errors and omissions and improve maintenance quality. Sending the standard operating procedures to AR glasses allows maintenance personnel to directly see virtual maintenance instructions and prompts on site. This augmented reality technology combines maintenance information with the actual environment, provides more intuitive and vivid operation guidance, reduces maintenance difficulty, and improves maintenance efficiency. Traditional power maintenance work is often accompanied by high safety risks, such as electric shock, misoperation, etc. With AR technology-assisted maintenance, some inspection and diagnosis work can be completed without direct contact with the equipment, reducing direct contact between maintenance personnel and live equipment and reducing safety risks.

[0018] Optionally, the method also includes: obtaining an operating behavior image of the on-site construction personnel; comparing the similarity between the operating behavior image and the non-standard behavior image; if it is determined that the similarity is greater than or equal to a preset similarity threshold, determining that the operating behavior of the on-site construction personnel is non-standard; and alerting the on-site construction personnel of the non-standard operating behavior through the AR glasses.

[0019] By adopting the above technical solution, the system can monitor the operation process of the construction personnel in real time by acquiring the operation behavior images of the on-site construction personnel. Once irregular behavior is found, the system can immediately compare and judge, and provide instant feedback to the construction personnel through AR glasses after confirming that the similarity reaches the preset threshold. This immediacy helps to quickly correct incorrect operations and prevent accidents from expanding. By continuously monitoring and alerting irregular operation behaviors, the system can strengthen the safety awareness of construction personnel. Construction personnel will gradually realize which behaviors are dangerous and irregular, so that they will pay more attention to complying with safety regulations in their daily work and reduce the possibility of accidents. Human error is one of the common causes of power safety accidents. Through the real-time monitoring and alarm functions of AR technology, the system can promptly detect and correct the incorrect operations of construction personnel, thereby reducing the safety risks caused by human errors.

[0020] In a second aspect of the present application, there is provided an electricity safety detection device based on a smart wearable device, the electricity safety detection device comprising an acquisition module and a processing module, wherein the acquisition module is used to acquire basic electrical detection information for a target electrical device sent by the smart wearable device; the acquisition module is also used to acquire environmental adaptability detection information for the environment in which the target electrical device is located sent by the smart wearable device; the processing module is used to perform feature selection on the basic electrical detection information and the environmental adaptability detection information using a random forest algorithm to obtain a target feature group; the processing module is also used to input the target feature group into a preset electricity safety detection model to determine abnormal behavior feature points; the processing module is also used to determine the size relationship between the area corresponding to the abnormal behavior feature area and the area corresponding to the preset area, the abnormal behavior feature area being composed of sub-areas corresponding to a plurality of the abnormal behavior feature points, and one abnormal behavior feature point corresponding to one sub-area; the processing module is also used to determine that the target electrical device has an electricity safety hazard if the area corresponding to the abnormal behavior feature area is greater than or equal to the area corresponding to the preset area.

[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By acquiring the basic electrical detection information and environmental adaptability detection information of the target electrical equipment in real time through smart wearable devices, the detection process no longer relies on traditional regular manual inspections, greatly improving the real-time and proactive nature of the detection. This helps to timely discover and deal with potential safety hazards and reduce the risk of safety accidents caused by delayed discovery. The random forest algorithm is used to select features from the collected data, which can automatically extract the most critical feature combination (target feature group) for the detection of power safety hazards. This process not only reduces human intervention and improves the intelligence level of the detection process, but also improves the accuracy and reliability of the detection results by optimizing the feature combination. By inputting the target feature group into the preset power safety detection model, abnormal behavior feature points can be accurately identified. These feature points are directly related to potential power safety hazards, providing a solid data foundation for subsequent hazard assessment. By constructing an abnormal behavior feature area and comparing the area of ​​the area with the area of ​​the preset area, a quantitative assessment of power safety hazards is achieved. This regionalized assessment method is not only intuitive and easy to understand, but also allows different countermeasures to be taken according to the severity of the hazard, improving the scientificity and effectiveness of risk management. The system not only focuses on the electrical performance of the electrical equipment itself, but also comprehensively considers the impact of the environment in which the equipment is located on its operating safety. This comprehensive detection method helps to discover safety hazards caused by environmental factors and improves the comprehensiveness and accuracy of the detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of a method for detecting power safety based on a smart wearable device is provided in an embodiment of the present application.

[0025] Figure 2 Another flowchart of a method for detecting power safety based on a smart wearable device provided in an embodiment of the present application.

[0026] Figure 3 A schematic diagram of a module of an electricity safety detection device based on a smart wearable device provided in an embodiment of the present application.

[0027] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0028] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0029] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0030] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0031] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0032] In today's power management field, the safety inspection of electrical equipment has become a core link in maintaining the stable operation of the power system, and is also a solid barrier to prevent safety risks such as fire and electric shock. However, the currently widely practiced manual inspection model, although it guarantees power safety to a certain extent, its inherent limitations are becoming more and more obvious with the increasing complexity of the power system, and it is difficult to fully adapt to the increasingly stringent safety management requirements.

[0033] The significant challenge of manual inspections is their high dependence on manpower, which is directly related to the inspectors' professional skills, long-term practical experience, and immediate status when performing tasks. The uncontrollability and diversity of these variables often make the inspection process full of subjectivity, making it difficult to ensure consistency and objectivity. Specifically, different inspectors may adopt different inspection standards and operating procedures due to different understandings of safety regulations, differences in attention allocation, or differences in sensitivity to potential risks, which undoubtedly brings uncertainty to the accuracy and reliability of the inspection results.

[0034] In order to solve the above technical problems, the present application provides a method for detecting power safety based on a smart wearable device. Figure 1 , Figure 1A schematic diagram of a flow chart of a power safety detection method based on a smart wearable device provided in an embodiment of the present application. The power safety detection method is applied to a server, and includes steps S110 to S160, which are as follows: S110: Obtain basic electrical detection information for a target electrical device sent by a smart wearable device.

[0035] Specifically, smart wearable devices refer to electronic devices that can be worn on the human body and have intelligent functions. These devices usually integrate sensors, processors and wireless communication modules, and can collect and transmit various types of data. In an embodiment of the present application, the smart wearable device is configured to be able to receive or directly measure electrical parameters related to electrical equipment. This is usually achieved by establishing a wireless connection with the electrical equipment (such as Bluetooth, Wi-Fi, Zigbee, etc.) or through other indirect methods (such as through an intermediate device or a cloud platform). Basic electrical detection information refers to various parameters and indicators related to the electrical performance of electrical equipment. These parameters include but are not limited to voltage, current, power, power factor, harmonic content, etc. This information is crucial for evaluating the safety and operating efficiency of electrical equipment. By monitoring these parameters, potential safety hazards such as electrical faults, overloads, short circuits, etc. can be discovered in a timely manner, and corresponding measures can be taken to prevent or repair them. The target electrical equipment refers to a specific device or system that the smart wearable device pays attention to and performs electrical detection on. These devices can be household appliances (such as refrigerators, air conditioners), machines on industrial production lines, or transformers in power grids. In actual applications, smart wearable devices may need to identify and associate with target electrical equipment in some way (such as QR code scanning, device number input, etc.). A server refers to a computer program or device that provides services in a network. In this scenario, the server is responsible for receiving basic electrical detection information sent by smart wearable devices and storing, processing and analyzing it. The server may be located in the cloud or a local data center and has powerful data processing capabilities and a secure and reliable storage mechanism. Through the server, power companies or users can access and view the electrical detection data of electrical equipment at any time.

[0036] In a possible implementation, basic electrical detection information for a target electrical device sent by a smart wearable device is obtained, specifically including: receiving current information, voltage information and device temperature information sent by a sensor group, the sensor group including a current sensor, a voltage sensor and a temperature sensor, and the sensor group is located on the smart wearable device; preprocessing the current information, voltage information and device temperature information to obtain basic electrical detection information, the preprocessing including denoising, filtering and normalization.

[0037] Specifically, the sensor group is a group of sensors on the smart wearable device, which is used to collect electrical parameters related to the electrical equipment. In this scenario, the sensor group includes current sensors, voltage sensors and temperature sensors. The current sensor is used to measure the current passing through the electrical equipment; the voltage sensor is used to measure the voltage value at both ends of the electrical equipment; and the temperature sensor is used to monitor the temperature of the electrical equipment or the surrounding environment. The smart wearable device receives real-time data from the sensor group through its built-in communication module (such as Bluetooth, Wi-Fi, etc.). These data include current information, voltage information and device temperature information. Preprocessing is the process of processing the raw data to eliminate noise, improve data quality and make it more suitable for subsequent analysis. In this scenario, preprocessing includes denoising, filtering and normalization. Denoising: remove random errors and interference signals in the data to improve the accuracy and reliability of the data. This is usually achieved through digital filtering techniques, such as low-pass filtering, median filtering, etc. Filtering: further smooth the data, reduce high-frequency noise and fluctuations, and make the data smoother and more stable. Filtering can remove unnecessary detail information and retain the main features useful for analysis. Normalization: Scale the data to a certain ratio so that it falls into a small specific interval (such as between 0 and 1). Normalization helps eliminate the impact of different dimensions on data analysis and improve the convergence speed and accuracy of the algorithm. The pre-processed current information, voltage information and equipment temperature information are integrated into basic electrical detection information. This information reflects the electrical characteristics and operating status of the electrical equipment and is an important basis for subsequent analysis and evaluation.

[0038] For example, the current sensor measures the current value at the input and output of the transformer in real time; the voltage sensor measures the voltage value at both ends of the transformer; and the temperature sensor monitors the temperature of the transformer body or the surrounding environment. These data are transmitted to the processing unit on the smart wearable device in real time via wireless means (such as Bluetooth). The processing unit first denoises the received raw data to remove noise signals caused by electromagnetic interference, equipment vibration and other factors. Then, the data is filtered to smooth the data curve and reduce high-frequency fluctuations and noise. Finally, the data is normalized to convert all current, voltage and temperature values ​​to the same magnitude (such as 0-100%) to facilitate subsequent data analysis and comparison.

[0039] S120: Obtain environmental adaptability detection information sent by the smart wearable device for the environment in which the target electrical device is located.

[0040] Specifically, environmental adaptability detection information refers to various parameters and conditions about the environment in which the target electrical equipment is located, which may affect the normal operation and performance of the equipment. This information includes but is not limited to temperature, humidity, air pressure, light intensity, electromagnetic radiation level, dust concentration, etc. By monitoring these environmental parameters, the adaptability and stability of electrical equipment in different environments can be evaluated, so as to discover potential environmental influencing factors in advance and take corresponding measures to prevent or adjust them. In this scenario, smart wearable devices may integrate a variety of environmental sensors, such as temperature sensors, humidity sensors, air pressure sensors, light sensors, etc., to collect data about the environment in which the target electrical equipment is located in real time. Alternatively, smart wearable devices may indirectly obtain environmental adaptability detection information through communication with other environmental monitoring devices (such as independent environmental monitoring stations, IoT sensor networks, etc.).

[0041] In a possible implementation, environmental adaptability detection information for the environment in which the target electrical equipment is located is obtained and sent by the smart wearable device, specifically including: receiving ambient temperature information, ambient humidity information and insulation performance information sent by the smart wearable device; performing temperature compensation on the ambient temperature, performing humidity correction on the ambient humidity information, and performing electromagnetic shielding on the insulation performance information to obtain environmental adaptability detection information.

[0042] Specifically, the server receives three key environmental information sent from the smart wearable device: ambient temperature information, ambient humidity information, and insulation performance information. This information is an important basis for evaluating the operating stability and safety of the target electrical equipment in a specific environment. The ambient temperature information reflects the temperature condition of the environment in which the target electrical equipment is located. Temperature is one of the key factors affecting the performance of electronic equipment. Too high or too low temperature may cause equipment performance degradation or failure. Temperature compensation for ambient temperature is to eliminate the influence of temperature on the electrical performance measurement of electrical equipment. Since the electrical parameters of electronic components (such as resistance, capacitance, etc.) change with temperature, it is necessary to perform temperature correction on the measurement results to obtain more accurate electrical parameter values. The ambient humidity information reflects the humidity condition of the environment in which the target electrical equipment is located. Excessive humidity may cause condensation, corrosion or short circuit inside the equipment, thereby affecting the operating stability and safety of the equipment. Humidity correction of ambient humidity information is to eliminate the interference of humidity on the electrical performance measurement of electrical equipment. Humidity correction may involve adjustment of the measurement results to reflect the true performance of the equipment under different humidity conditions.

[0043] S130. Use a random forest algorithm to perform feature selection on basic electrical detection information and environmental adaptability detection information to obtain a target feature group.

[0044] Specifically, random forest is an ensemble learning method that improves the accuracy of classification or regression by building multiple decision trees and aggregating their prediction results. In terms of feature selection, random forest can evaluate the importance of each feature when building a decision tree, thereby helping to identify the features that have the greatest impact on the prediction target. These two types of information include the electrical characteristics of the target electrical equipment and multiple parameters of the environment in which it is located. Basic electrical detection information may include current, voltage, power factor, etc.; environmental adaptability detection information may include temperature, humidity, insulation performance, etc. Feature selection is an important step in machine learning, which aims to select the most useful feature subset from the original data set for predicting the target. This can not only reduce the amount of calculation and improve the training efficiency of the model, but also avoid overfitting and improve the generalization ability of the model. In this scenario, the server uses the random forest algorithm to select features for basic electrical detection information and environmental adaptability detection information. The algorithm builds multiple decision trees based on this data and evaluates the importance of each feature during the construction process. Importance is usually measured by the total amount of impurity (such as Gini impurity or information gain) reduced when the feature splits the decision tree. After the feature selection of the random forest algorithm, the server will obtain a target feature group, which contains the most critical features for subsequent analysis or prediction tasks. These features will be used as input data for training machine learning models or for further data analysis.

[0045] In a possible implementation, a random forest algorithm is used to perform feature selection on basic electrical detection information and environmental adaptability detection information to obtain a target feature group, specifically including: based on the random forest algorithm, feature importance scores are obtained for multiple basic electrical features included in the basic electrical detection information and multiple environmental adaptability features included in the environmental adaptability detection information, one basic electrical feature corresponds to one feature importance score, and one environmental adaptability feature corresponds to one feature importance score; features whose corresponding scores are greater than preset scores are selected from multiple basic electrical features and multiple environmental adaptability features to obtain a target feature group.

[0046] Specifically, when using the random forest algorithm to process data, the algorithm assigns an importance score to each feature based on its performance in the process of building a decision tree. This score reflects the role of the feature in predicting the target variable. For each basic electrical feature in the basic electrical detection information and each environmental adaptability feature in the environmental adaptability detection information, there will be a corresponding feature importance score. Before feature selection, a preset score needs to be set as a screening criterion. This score is determined based on actual application requirements, data characteristics, and model performance requirements. Only those features whose feature importance scores are greater than this preset score will be selected into the target feature group. After obtaining the importance scores of all features, the server will traverse these scores and select the features whose corresponding scores in the basic electrical features and environmental adaptability features are greater than the preset scores. These selected features together constitute the target feature group. The target feature group is the basis for subsequent data analysis or model training. It contains the most critical features for predicting the target variable, which can effectively reduce the amount of calculation and improve the training efficiency and prediction accuracy of the model.

[0047] For example, the preprocessed data is processed using the random forest algorithm to calculate feature importance scores for each basic electrical feature (such as current, voltage) and environmental adaptability feature (such as temperature, humidity). For example, current may get a score of 0.8, indicating that it is very important in predicting motor failures; while an unrelated vibration feature may only get a score of 0.1. Assume that based on past experience and analysis, the factory sets the preset score to 0.5. This means that only features with a feature importance score greater than 0.5 are considered important. The server traverses the importance scores of all features and selects features with a score greater than 0.5. Assume that the scores of the three features of current, voltage, and temperature are all greater than 0.5, while the scores of other features are lower than this threshold. Therefore, the three features of current, voltage, and temperature are selected as the target feature group. These features will be used as input data to train a machine learning model for predicting motor failures.

[0048] S140: Input the target feature group into a preset power safety detection model to determine abnormal behavior feature points.

[0049] Specifically, the target feature group is a set of key features selected from the basic electrical detection information and environmental adaptability detection information through the feature selection process. These features have an important impact on the subsequent power safety detection tasks. The preset power safety detection model is a trained random forest model, which aims to detect abnormal behaviors or safety hazards that may occur in the operation of power equipment. This model is usually built based on a large amount of historical data and expert knowledge, and can identify feature combinations that are different from normal behavior patterns. The server passes the target feature group as input data to the preset power safety detection model. This process involves preprocessing steps such as data format conversion and normalization to ensure that the input data meets the requirements of the model. After receiving the target feature group, the preset power safety detection model will perform a series of calculations and inferences to identify whether there are feature points related to abnormal behavior. These feature points may represent some abnormal states or potential safety hazards of power equipment during operation. The model will return the identified abnormal behavior feature points to the server as output results. The server can further judge the safety status of the power equipment based on these results and take corresponding measures, such as sending alarms, recording logs, or adjusting equipment operating parameters.

[0050] In a possible implementation, the target feature group is input into a preset electricity safety detection model to determine abnormal behavior feature points, specifically including: obtaining multiple historical feature groups, the historical feature groups including historical basic electrical features and historical environmental adaptability features; matching the target feature group with multiple historical feature groups according to the current time period to obtain a target historical feature group; comparing the target feature group with the target historical feature group to screen out abnormal behavior features, the abnormal behavior features being features that do not meet preset threshold conditions; determining abnormal behavior feature points based on the correspondence between the abnormal behavior features and the abnormal behavior feature points, the preset electricity safety detection model pre-stores the correspondence between the abnormal behavior features and the abnormal behavior feature points.

[0051] Specifically, the server first collects and stores a large amount of historical data, which includes basic electrical characteristics and environmental adaptability characteristics in the past time period, forming multiple historical feature groups. These historical feature groups provide the model with rich background information about the normal and abnormal operating status of the equipment. In order to compare the current target feature group with the past situation, the server will match the corresponding historical feature group according to the current time period (such as date, time range, etc.). This step is to find the historical data that is closest or similar in time to the target feature group for subsequent comparative analysis. Through the matching process, the server can determine one or more historical feature groups that are closest to the target feature group. These selected historical feature groups are called target historical feature groups. They will serve as the benchmark for comparison with the target feature group. Next, the server performs a detailed feature comparison between the target feature group and the target historical feature group. This step involves comparing the corresponding features in the two groups one by one to identify any significant differences or anomalies. During the comparison process, the server applies preset threshold conditions to determine whether a feature meets the standard for normal operation. Features that do not meet these threshold conditions are considered abnormal behavior features. Finally, the server determines the abnormal behavior feature points based on the preset corresponding relationships. This correspondence is usually established during the model training phase, which clarifies which abnormal behavior features correspond to which specific abnormal behavior feature points. By finding this correspondence, the server can convert the screened abnormal behavior features into specific abnormal behavior feature points, which represent the specific potential risk locations that may exist in the operation of the equipment.

[0052] S150: Determine the size relationship between the area corresponding to the abnormal behavior feature region and the area corresponding to the preset region, wherein the abnormal behavior feature region is composed of sub-regions corresponding to a plurality of abnormal behavior feature points, and one abnormal behavior feature point corresponds to one sub-region.

[0053] Specifically, these points are identified by a preset power safety detection model, representing the specific location or characteristics of abnormal behaviors or hidden dangers that may exist in the operation of the equipment. Each abnormal behavior feature point corresponds to a specific problem or anomaly in the operation state of the equipment. Each abnormal behavior feature point is assigned a corresponding sub-area. This sub-area can be a specific spatial range (such as an area in a two-dimensional or three-dimensional space) or an interval in a parameter space. The size and shape of the sub-area may vary depending on the actual application and model design. This is a larger area composed of the sub-areas corresponding to multiple abnormal behavior feature points. This area combines all the identified abnormal behavior feature points and reflects the overall abnormal behavior distribution and range in the operation state of the equipment. The preset area is one or more pre-defined areas for comparison with the abnormal behavior feature area. These areas may be determined based on the design specifications, safety standards or historical experience of the equipment, and are used to evaluate the safety and normality of the current operation state of the equipment. After determining the abnormal behavior feature area and the preset area, the system needs to compare the size relationship between the two areas in terms of area. This comparison can help evaluate the severity and scope of the abnormal behavior of the equipment, and whether corresponding measures need to be taken to deal with it.

[0054] S160: If the area corresponding to the abnormal behavior characteristic region is greater than or equal to the area corresponding to the preset region, it is determined that the target electrical equipment has an electrical safety hazard.

[0055] Specifically, the server calculates the total area of ​​the abnormal behavior feature area and compares it with the area of ​​the preset area. This comparison is based on the principle of spatial geometry and aims to quantitatively evaluate the scope and severity of abnormal behavior. If the area of ​​the abnormal behavior feature area is greater than or equal to the area of ​​the preset area, the server will make a judgment based on the comparison result and believe that the target electrical equipment has electrical safety hazards. This is because the scope and degree of abnormal behavior have exceeded the allowable range for normal operation of the equipment and may have an adverse effect on the performance, reliability or safety of the equipment.

[0056] For example, suppose that the server identifies multiple abnormal behavior feature points on the motor through a preset power safety detection model. These points correspond to potential problems such as overheating of the motor bearing and aging of the winding insulation. The server assigns a corresponding sub-region to each feature point based on the distribution of these feature points on the motor. These sub-regions may cover key components or vulnerable areas of the motor. The server then merges these sub-regions into an overall abnormal behavior feature region. The factory sets a preset region based on the design specifications and safety standards of the motor. This region may be a circular or rectangular area around the key components of the motor, which is used to evaluate the maximum range of abnormal behavior that may occur in the motor under normal operating conditions. The server calculates the area of ​​the abnormal behavior feature region and compares it with the area of ​​the preset region. Assuming that the area of ​​the abnormal behavior feature region exceeds the area of ​​the preset region, this means that the abnormal behavior on the motor has exceeded the normal range and may have a serious impact on the performance and safety of the motor.

[0057] In one possible implementation, the abnormal behavior characteristic area and the target electrical equipment are sent to an AR cloud platform; a standard operating procedure generated for the abnormal behavior characteristic area and the target electrical equipment and sent by the AR cloud platform is received, the standard operating procedure being used to eliminate electrical safety hazards existing in the target electrical equipment; and the standard operating procedure is sent to the AR glasses so that the corresponding wearer of the AR glasses can repair the target electrical equipment.

[0058] Specifically, when the server identifies the target electrical equipment with abnormal behavior feature areas through the preset power safety detection model and determines that the equipment has power safety hazards, it will send this information (including the specific location and range of the abnormal behavior feature areas, and the identification information of the target electrical equipment) to the AR cloud platform. This step is the beginning of the entire process, which enables the AR cloud platform to understand the specific problems and target objects that need to be dealt with. After receiving the information sent by the server, the AR cloud platform will generate a detailed standard operating procedure for the abnormal behavior feature areas and target electrical equipment based on its internal knowledge base, expert system or machine learning algorithm. This process may include the steps required to eliminate safety hazards, the required tools, materials, safety precautions, etc., in order to guide maintenance personnel to operate in accordance with the specifications and ensure the effectiveness and safety of maintenance work. The standard operating procedure generated by the AR cloud platform will be sent back to the server, and then the server will forward it to the maintenance personnel wearing AR glasses. This step is a key link in information transmission, which enables maintenance personnel to obtain guidance information for maintenance work in real time and intuitively. Maintenance personnel wearing AR glasses can see virtual information superimposed on the real world through the display screen on the glasses, including instructions for standard operating procedures, the specific location of target electrical equipment, and highlighted areas of abnormal behavior characteristics. This information can help maintenance personnel locate problems more accurately, understand maintenance steps, and reduce errors and omissions in actual operations. At the same time, AR glasses may also provide remote assistance functions, allowing experts to provide real-time guidance to maintenance personnel through video calls and other means.

[0059] In one possible implementation, refer to Figure 2 , Figure 2 Another flow chart of a method for detecting power safety based on a smart wearable device provided in an embodiment of the present application. The method includes steps S210 to S240, which are as follows: S210, obtaining an operation behavior image of a construction worker on site; S220, comparing the similarity between the operation behavior image and the non-standard behavior image; S230, if it is determined that the similarity is greater than or equal to a preset similarity threshold, determining that the operation behavior of the construction worker on site is non-standard; S240, using AR glasses to warn the construction worker of the non-standard operation behavior.

[0060] Specifically, the server first captures the operation behavior images of the on-site construction personnel in real time through a camera (which may be a surveillance camera fixed on the site or a camera built into the AR glasses). These images are the basis for subsequent analysis and comparison. The server compares the captured operation behavior images with the preset irregular behavior image library. This image library contains a variety of known example images of irregular operation behaviors. The comparison process usually involves image processing techniques, such as feature extraction, pattern matching, etc., to calculate the similarity between the two images. The server sets a similarity threshold to determine which image in the irregular behavior image library the captured operation behavior image is most similar to, and whether the degree of similarity reaches a level that requires attention. If the calculated similarity is greater than or equal to this threshold, the server believes that the operation behavior of the on-site construction personnel may be similar to a certain irregular behavior. Once it is determined that the similarity exceeds the preset threshold, the server will determine that the operation behavior of the on-site construction personnel is irregular. This judgment is the premise for taking corrective measures later. In order to promptly remind the on-site construction personnel to pay attention to and correct their irregular behavior, the server will send an alarm message to the wearer through the AR glasses. This information may appear in the form of text, sound, vibration or virtual images, directly pointing to the specific location of the irregular behavior and giving corresponding improvement suggestions or precautions.

[0061] The present application also provides a power safety detection device based on a smart wearable device, referring to Figure 3 , Figure 3 A schematic diagram of a module of an electric safety detection device based on a smart wearable device provided in an embodiment of the present application. The electric safety detection device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires basic electrical detection information for a target electric device sent by the smart wearable device; the acquisition module 31 acquires environmental adaptability detection information for the environment in which the target electric device is located sent by the smart wearable device; the processing module 32 uses a random forest algorithm to perform feature selection on the basic electrical detection information and the environmental adaptability detection information to obtain a target feature group; the processing module 32 inputs the target feature group into a preset electric safety detection model to determine abnormal behavior feature points; the processing module 32 determines the size relationship between the area corresponding to the abnormal behavior feature area and the area corresponding to the preset area, and the abnormal behavior feature area is composed of sub-areas corresponding to multiple abnormal behavior feature points, and one abnormal behavior feature point corresponds to one sub-area; if the area corresponding to the abnormal behavior feature area is greater than or equal to the area corresponding to the preset area, the processing module 32 determines that there is an electric safety hazard in the target electric device.

[0062] In a possible implementation, the acquisition module 31 acquires basic electrical detection information for the target electrical equipment sent by the smart wearable device, specifically including: the acquisition module 31 receives current information, voltage information and device temperature information sent by the sensor group, the sensor group includes a current sensor, a voltage sensor and a temperature sensor, and the sensor group is located on the smart wearable device; the processing module 32 preprocesses the current information, voltage information and device temperature information to obtain basic electrical detection information, and the preprocessing includes denoising, filtering and normalization.

[0063] In a possible implementation, the acquisition module 31 acquires environmental adaptability detection information for the environment in which the target electrical equipment is located, which is sent by the smart wearable device. Specifically, the acquisition module 31 receives the ambient temperature information, ambient humidity information and insulation performance information sent by the smart wearable device; the processing module 32 performs temperature compensation on the ambient temperature, performs humidity correction on the ambient humidity information, and performs electromagnetic shielding on the insulation performance information to obtain environmental adaptability detection information.

[0064] In one possible implementation, the processing module 32 uses a random forest algorithm to perform feature selection on the basic electrical detection information and the environmental adaptability detection information to obtain a target feature group, specifically including: the processing module 32 obtains feature importance scores for the multiple basic electrical features included in the basic electrical detection information and the multiple environmental adaptability features included in the environmental adaptability detection information based on the random forest algorithm, one basic electrical feature corresponds to one feature importance score, and one environmental adaptability feature corresponds to one feature importance score; the processing module 32 selects features from the multiple basic electrical features and the multiple environmental adaptability features, each of which has a corresponding score greater than a preset score, to obtain a target feature group.

[0065] In one possible implementation, the processing module 32 inputs the target feature group into a preset electricity safety detection model to determine abnormal behavior feature points, specifically including: the acquisition module 31 acquires multiple historical feature groups, the historical feature groups include historical basic electrical features and historical environmental adaptability features; the processing module 32 matches the target feature group with multiple historical feature groups according to the current time period to obtain a target historical feature group; the processing module 32 compares the target feature group with the target historical feature group to screen out abnormal behavior features, which are features that do not meet preset threshold conditions; the processing module 32 determines the abnormal behavior feature points based on the correspondence between the abnormal behavior features and the abnormal behavior feature points, and the preset electricity safety detection model pre-stores the correspondence between the abnormal behavior features and the abnormal behavior feature points.

[0066] In one possible implementation, the processing module 32 sends the abnormal behavior characteristic area and the target electrical equipment to the AR cloud platform; the acquisition module 31 receives the standard operating procedure generated for the abnormal behavior characteristic area and the target electrical equipment sent by the AR cloud platform, and the standard operating procedure is used to eliminate the electrical safety hazards existing in the target electrical equipment; the processing module 32 sends the standard operating procedure to the AR glasses, so that the corresponding wearer of the AR glasses can repair the target electrical equipment.

[0067] In a possible implementation, the acquisition module 31 acquires the operation behavior image of the on-site construction personnel; the processing module 32 compares the similarity between the operation behavior image and the non-standard behavior image; if the processing module 32 determines that the similarity is greater than or equal to a preset similarity threshold, it determines that the operation behavior of the on-site construction personnel is non-standard; the processing module 32 warns the on-site construction personnel of the non-standard operation behavior through AR glasses.

[0068] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0069] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0070] The communication bus 42 is used to realize the connection and communication between these components.

[0071] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0072] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0073] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0074] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a power safety detection method based on a smart wearable device.

[0075] exist Figure 4In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program stored in the memory 45 for an electricity safety detection method based on a smart wearable device. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0076] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0077] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0078] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0082] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0083] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for detecting electricity safety based on smart wearable devices. It is characterized in that The method comprises: Obtain basic electrical detection information for target electrical equipment sent by smart wearable devices; Obtaining environmental adaptability detection information sent by the smart wearable device for the environment in which the target electrical device is located; Using a random forest algorithm to perform feature selection on the basic electrical detection information and the environmental adaptability detection information to obtain a target feature group; Inputting the target feature group into a preset power safety detection model to determine abnormal behavior feature points; Determine the size relationship between the area corresponding to the abnormal behavior feature area and the area corresponding to the preset area, wherein the abnormal behavior feature area is composed of sub-areas corresponding to a plurality of the abnormal behavior feature points, and one abnormal behavior feature point corresponds to one sub-area; If the area corresponding to the abnormal behavior characteristic area is greater than or equal to the area corresponding to the preset area, it is determined that there is a potential electrical safety hazard in the target electrical equipment.

2. According to claim 1, the power safety detection method based on the smart wearable device, It is characterized in that The obtaining of basic electrical detection information for the target electrical equipment sent by the smart wearable device specifically includes: Receiving current information, voltage information and device temperature information sent by a sensor group, wherein the sensor group includes a current sensor, a voltage sensor and a temperature sensor, and the sensor group is located on the smart wearable device; The current information, the voltage information and the device temperature information are preprocessed to obtain the basic electrical detection information, wherein the preprocessing includes denoising, filtering and normalization processing.

3. According to the method for detecting power safety based on smart wearable devices according to claim 1, It is characterized in that The obtaining of the environmental adaptability detection information sent by the smart wearable device for the environment in which the target electrical device is located specifically includes: Receiving ambient temperature information, ambient humidity information, and insulation performance information sent by the smart wearable device; The environmental temperature is temperature compensated, the environmental humidity information is humidity corrected, and the insulation performance information is electromagnetically shielded to obtain the environmental adaptability detection information.

4. The power safety detection method based on the smart wearable device according to claim 1, It is characterized in that The random forest algorithm is used to perform feature selection on the basic electrical detection information and the environmental adaptability detection information to obtain a target feature group, which specifically includes: Based on the random forest algorithm, feature importance scores are obtained for the multiple basic electrical features included in the basic electrical detection information and the multiple environmental adaptability features included in the environmental adaptability detection information, where one basic electrical feature corresponds to one feature importance score, and one environmental adaptability feature corresponds to one feature importance score; Among the plurality of the basic electrical features and the plurality of the environmental adaptability features, features whose corresponding scores are greater than preset scores are selected to obtain the target feature group.

5. The power safety detection method based on smart wearable devices according to claim 1, It is characterized in that The step of inputting the target feature group into a preset power safety detection model to determine abnormal behavior feature points specifically includes: Acquire a plurality of historical feature groups, wherein the historical feature groups include historical basic electrical features and historical environmental adaptability features; According to the current time period, the target feature group is matched with the plurality of historical feature groups to obtain a target historical feature group; Comparing the target feature group with the target historical feature group, and screening out abnormal behavior features, wherein the abnormal behavior features are features that do not meet a preset threshold condition; The abnormal behavior feature point is determined according to the correspondence between the abnormal behavior feature and the abnormal behavior feature point, and the preset power safety detection model pre-stores the correspondence between the abnormal behavior feature and the abnormal behavior feature point.

6. The power safety detection method based on smart wearable devices according to claim 1, It is characterized in that The method further comprises: Sending the abnormal behavior feature area and the target electrical device to the AR cloud platform; Receiving a standard operating procedure generated for the abnormal behavior feature area and the target electrical equipment and sent by the AR cloud platform, wherein the standard operating procedure is used to eliminate electrical safety hazards existing in the target electrical equipment; The standard operating procedure is sent to the AR glasses so that the corresponding wearer of the AR glasses can repair the target electrical equipment.

7. The power safety detection method based on the smart wearable device according to claim 6, It is characterized in that The method further comprises: Obtain operation behavior images of on-site construction workers; comparing the similarity between the operation behavior image and the irregular behavior image; If it is determined that the similarity is greater than or equal to a preset similarity threshold, it is determined that the operation behavior of the on-site construction personnel is not standardized; The AR glasses are used to warn the on-site construction personnel of irregular operating behaviors.

8. An electricity safety detection device based on smart wearable devices, It is characterized in that The electricity safety detection device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to acquire basic electrical detection information for a target electrical device sent by a smart wearable device; The acquisition module (31) is further used to acquire the environmental adaptability detection information sent by the smart wearable device for the environment in which the target electrical device is located; The processing module (32) is used to use a random forest algorithm to perform feature selection on the basic electrical detection information and the environmental adaptability detection information to obtain a target feature group; The processing module (32) is further used to input the target feature group into a preset power safety detection model to determine abnormal behavior feature points; The processing module (32) is further used to determine the size relationship between the area corresponding to the abnormal behavior feature area and the area corresponding to the preset area, wherein the abnormal behavior feature area is composed of sub-areas corresponding to a plurality of abnormal behavior feature points, and one abnormal behavior feature point corresponds to one sub-area; The processing module (32) is further configured to determine that the target electrical equipment has an electrical safety hazard if the area corresponding to the abnormal behavior characteristic area is greater than or equal to the area corresponding to the preset area.

9. An electronic device, It is characterized in that The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images