Electric power operation safety protection positioning method, system and equipment integrated with Beidou navigation

Abstract

The invention discloses an electric power operation safety protection positioning method, system and device fused with Beidou navigation, and relates to the related field of radio wave positioning, and the method comprises the steps: marking a weak positioning region in an electric power operation region; a current electric power operation task is obtained, and if a path of the electric power operation task comprises a weak positioning area, a sliding mode switching positioning module is activated; the sliding mode switching positioning module is used for carrying out behavior mode recognition on a target executing an electric power operation task and outputting behavior mode characteristics; establishing a multi-modal confidence relation matrix according to the behavior pattern characteristics, and outputting a modal switching strategy by using the multi-modal confidence relation matrix; and the multi-modal fusion device performs multi-modal positioning data analysis according to the modal switching strategy and outputs a protection positioning result. The technical problems that positioning signals are unstable and precision is reduced when complex environments are switched in existing electric power operation safety protection positioning are solved, and the technical effect of improving accuracy and reliability of electric power operation safety protection positioning is achieved.

Description

Technical Field

[0001] This application relates to the field of radio wave positioning, and particularly to a power operation safety protection positioning method, system and device integrating Beidou navigation. Background Art

[0002] Power operation safety protection positioning is crucial for ensuring the safety of operators' lives and the stable operation of power facilities. Especially in complex operation environments, accurate positioning is a key link to ensure operation safety. Currently, the main method to solve the problem of power operation safety protection positioning is to use a single positioning technology, such as GPS positioning or indoor positioning systems. Due to the limitations of different positioning technologies, the current methods are difficult for a single technology to adapt to problems such as unstable positioning signals and decreased positioning accuracy caused by the complex environment switching between indoor and outdoor, thus affecting the reliability of power operation safety protection.

[0003] In the related technologies at the present stage, there are technical problems of unstable positioning signals and decreased accuracy during complex environment switching in power operation safety protection positioning. Summary of the Invention

[0004] This application provides a power operation safety protection positioning method, system and device integrating Beidou navigation. By first identifying the weak positioning areas where indoor and outdoor switching occurs in the power operation area, activating the sliding mode switching positioning module if the path of the operation task includes such areas after obtaining the operation task, the module is used to identify the behavior pattern of the operation target and output features, then establishing a multi-modal confidence relationship matrix based on this to output a modal switching strategy, and finally the multi-modal fusion device performs multi-modal positioning data analysis according to this strategy and outputs a protection positioning result and other technical means, solves the technical problems of unstable positioning signals and decreased accuracy during complex environment switching existing in the existing power operation safety protection positioning, and achieves the technical effect of improving the accuracy and reliability of power operation safety protection positioning.

[0005] This application provides a power operation safety protection positioning method integrating Beidou navigation, including: identifying the weak positioning areas in the power operation area, where the weak positioning areas are the transition areas when switching from indoor to outdoor or from outdoor to indoor; obtaining the current power operation task, if the path of the power operation task includes the weak positioning area, activating the sliding mode switching positioning module, the sliding mode switching positioning module is connected to the multi-modal fusion device, and the multi-modal fusion device integrates Beidou navigation; the sliding mode switching positioning module is used to identify the behavior pattern of the target performing the power operation task and output behavior pattern features; establishing a multi-modal confidence relationship matrix according to the behavior pattern features, and outputting a modal switching strategy with the multi-modal confidence relationship matrix; the multi-modal fusion device performs multi-modal positioning data analysis according to the modal switching strategy and outputs a protection positioning result.

[0006] In a possible implementation, the sliding mode switching positioning module is disposed on an edge device. The edge device performs behavior pattern recognition on the target executing the power operation task and performs the following processing: obtaining the target of the power operation task, and collecting real-time behavior data of the target; recognizing the spatial change rate, action mutation points, and change in movement direction of the real-time behavior data, and outputting behavior pattern category features; collecting the number of targets and the target dynamic rate executing the power operation task, and outputting behavior pattern target features; and outputting behavior pattern features according to the behavior pattern category features and the behavior pattern target features.

[0007] In a possible implementation, a multi-modal confidence relationship matrix is established according to the behavior pattern features, and the following processing is performed: obtaining data quality parameters of each mode from the multi-modal fusion device, including RSSI signal strength, data update frequency, historical positioning MSE error, and data packet loss rate; using the behavior pattern features and the data quality parameters of each mode as a joint vector to input into a mode confidence evaluation model, and outputting the confidence score of each mode under the current behavior; and constructing a multi-modal confidence relationship matrix based on the confidence scores of each mode.

[0008] In a possible implementation, the following processing is performed: the mode confidence evaluation model includes a first-layer fully connected network and a second-layer fully connected network. The first-layer fully connected network uses a Tanh activation function, and the second-layer fully connected network uses a Sigmoid activation function; training the first-layer fully connected network and the second-layer fully connected network using mean square error loss with historical sample data, and outputting the first-layer fully connected network and the second-layer fully connected network. The historical sample data includes sample data quality parameters and corresponding confidence annotation samples under different power operation behavior patterns.

[0009] In a possible implementation, a mode switching strategy is output based on the multi-modal confidence relationship matrix, and the following processing is performed: setting a confidence switching rule, where the confidence switching rule includes a mode retention interval, a mode replacement interval, and a mode suppression interval; marking each mode according to the confidence levels in the multi-modal confidence relationship matrix according to the confidence switching rule, and outputting a mode marking result, where the mode marking result includes a retained mode, a standby mode, and a suppressed mode; and comparing the current mode enabled state according to the mode marking result, and outputting a mode switching strategy.

[0010] In a possible implementation, the following processing is performed: the confidence decline rate of the modality retention interval is less than the first preset decline rate, the confidence decline rate of the modality suppression interval is greater than the second preset decline rate, and the confidence decline rate of the modality replacement interval is greater than or equal to the first preset decline rate and less than or equal to the second preset decline rate; wherein, the first preset decline rate is less than the second preset decline rate.

[0011] In a possible implementation, the current modality enabling state is compared according to the modality marking result, and a modality switching strategy is output. The following processing is performed: if the retained modality in the modality marking result is different from the current modality enabling state, a modality switching instruction is obtained, and the modality fusion device is controlled to output modality positioning data according to the retained modality; if the confidence fluctuations of the retained modality and the standby modality in the modality marking result are greater than a preset threshold, the retained modality and the standby modality are combined, and the modality fusion device is controlled to output modality positioning data according to the combined modality; if the suppressed modality in the modality marking result is the same as the current modality, the suppressed modality is removed.

[0012] In a possible implementation, the multi-modal fusion device performs multi-modal positioning data analysis according to the modality switching strategy and outputs a protection positioning result. The following processing is performed: the multi-modal fusion device performs multi-modal positioning data analysis according to the modality switching strategy and outputs the auxiliary positioning data of the weak positioning area; according to the multi-modal fusion device, the indoor positioning data or the outdoor positioning data corresponding to the target of the power operation task is obtained; the indoor positioning data or the outdoor positioning data is assisted and updated according to the auxiliary positioning data, and a protection positioning result is output.

[0013] The present application also provides a power operation safety protection positioning system integrating Beidou navigation, including: a weak positioning area identification module for identifying a weak positioning area in the power operation area, where the weak positioning area is a transition area when switching from indoors to outdoors or from outdoors to indoors; a sliding mode switching positioning activation module for obtaining the current power operation task, and if the path of the power operation task includes the weak positioning area, activating the sliding mode switching positioning module, the sliding mode switching positioning module is connected to the multi-modal fusion device, and the multi-modal fusion device integrates Beidou navigation; a behavior pattern recognition module for performing behavior pattern recognition on the target of the power operation task through the sliding mode switching positioning module and outputting behavior pattern features; a modality switching strategy output module for establishing a multi-modal confidence relationship matrix according to the behavior pattern features and outputting a modality switching strategy with the multi-modal confidence relationship matrix; a protection positioning module for the multi-modal fusion device to perform multi-modal positioning data analysis according to the modality switching strategy and output a protection positioning result.

[0014] The present application also provides an electronic device, including: a memory for storing executable instructions; and a processor for implementing the power operation safety protection positioning method integrating Beidou navigation when executing the executable instructions stored in the memory.

[0015] It is intended to first identify a weak positioning area in the power operation area through the power operation safety protection positioning method, system and device integrating Beidou navigation proposed in the present application. The weak positioning area is a transition area when switching from indoor to outdoor or from outdoor to indoor. Then, the current power operation task is obtained. If the path of the power operation task includes the weak positioning area, a sliding mode switching positioning module is activated. The sliding mode switching positioning module is connected to a multimodal fusion device, and Beidou navigation is integrated in the multimodal fusion device. The sliding mode switching positioning module is used to identify the behavior mode of the target executing the power operation task and output the behavior mode characteristics. Then, a multimodal confidence relationship matrix is established according to the behavior mode characteristics, and a mode switching strategy is output according to the multimodal confidence relationship matrix. Finally, the multimodal fusion device performs multimodal positioning data analysis according to the mode switching strategy and outputs a protection positioning result. The technical effect of improving the accuracy and reliability of power operation safety protection positioning is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, various steps can be processed in reverse order or simultaneously according to needs. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0017] Figure 1 It is a schematic flowchart of the power operation safety protection positioning method integrating Beidou navigation provided by the embodiments of the present application.

[0018] Figure 2 It is a schematic structural diagram of the power operation safety protection positioning system integrating Beidou navigation provided by the embodiments of the present application.

[0019] Figure 3 It is a schematic structural diagram of an electronic device provided by the embodiments of the present application.

[0020] Description of the attached drawing reference numerals: weak positioning area identification module 10, sliding mode switching positioning activation module 20, behavior pattern recognition module 30, mode switching strategy output module 40, protection positioning module 50, input device 301, processor 302, memory 303, output device 304. Detailed implementation manners

[0021] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific implementation manners of this application are specifically given below.

[0022] In order to make the purpose, technical solution and advantages of this application clearer, the following will further describe this application in detail with reference to the attached drawings. The described embodiments should not be regarded as limitations to this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0023] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first\second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0024] The embodiment of this application provides a power operation safety protection positioning method integrating Beidou navigation, as Figure 1 shown. The method includes:

[0025] Step S100, identifying a weak positioning area in the power operation area, where the weak positioning area is a transition area when switching from indoors to outdoors or from outdoors to indoors.

[0026] Specifically, the weak positioning area refers to the transitional area when switching from indoor to outdoor or from outdoor to indoor. The positioning signals in these areas are unstable, resulting in a decrease in positioning accuracy. Deploy a high-precision sensor network within the power operation area, including Wi-Fi signal strength sensors, Bluetooth signal sensors, geomagnetic sensors, etc. These sensors can monitor the signal strength and magnetic field changes in real time to identify the differences between indoor and outdoor environments. Use Geographic Information System (GIS) technology to build a geographic information model of the power operation area, divide the area into indoor and outdoor parts, and mark the transitional areas. The GIS system can combine sensor data to accurately identify the weak positioning areas. Or, analyze the sensor data through machine learning algorithms, and train a model to automatically identify the weak positioning areas. For example, use Support Vector Machine (SVM) or decision tree algorithms to automatically divide the indoor-outdoor transitional area according to the characteristics of signal strength and magnetic field changes. Or, the GIS system can embed machine learning algorithms, combine sensor data and geographic information data, and more accurately identify the weak positioning areas. The GIS system not only provides the visualization of geographic information, but also analyzes the sensor data using machine learning algorithms to automatically identify the weak positioning areas.

[0027] For example, in a power substation, a Wi-Fi signal strength sensor is deployed every 10 meters, and a geomagnetic sensor is deployed every 20 meters around the substation. These sensors collect data in real time and upload it to the central server. In the GIS system, the indoor area of the substation is marked in blue, the outdoor area is marked in green, and the transitional area is marked in yellow. Through sensor data, the GIS system can dynamically update the boundaries of these areas. Or, train an SVM model using historical data, and the input features include Wi-Fi signal strength, Bluetooth signal strength, and geomagnetic strength. The model output is "indoor", "outdoor", or "transitional area". Or, in the GIS system, fuse sensor data (such as Wi-Fi signal strength, geomagnetic strength) with geographic information data (such as building layout, roads) to form a comprehensive dataset. Use the SVM algorithm to train the comprehensive dataset to generate an identification model. Apply the trained model to real-time data to automatically identify the weak positioning areas.

[0028] Step S200, obtain the current power operation task. If the path of the power operation task includes the weak positioning area, activate the sliding mode switching positioning module. The sliding mode switching positioning module is connected to the multi-modal fusion device, and the multi-modal fusion device integrates Beidou navigation.

[0029] Specifically, a power operation task management system is established, which records the path, schedule, and operation area of each operation task. The task management system communicates with the multi-modal fusion device to obtain task information in real time. Among them, the multi-modal fusion device is a device that integrates multiple positioning technologies (such as Beidou navigation, Wi-Fi positioning, Bluetooth positioning, etc.), and can fuse data of different modalities for high-precision positioning. A path analysis algorithm is developed to check whether the operation task path passes through a weak positioning area. Among them, the algorithm can automatically determine whether the path contains a weak positioning area based on the GIS map and task path data. When the path analysis algorithm confirms that the path contains a weak positioning area, the sliding mode switching positioning module is activated through the communication interface. The sliding mode switching positioning module is an intelligent module that can dynamically switch different positioning modalities according to the behavior pattern of the target and sensor data to improve the positioning accuracy.

[0030] For example, the task management system stores the detailed information of each operation task, including the operation personnel, the start and end points of the task, the expected path, etc. The path analysis algorithm inputs the task path coordinates and GIS map data. The algorithm determines whether the path passes through a weak positioning area by comparing the path coordinates with the weak positioning area coordinates in the GIS map. For example, the starting point of task T1 is point A indoors, and the end point is point B outdoors. The path coordinates of task T1 overlap with the coordinates of the yellow area in the GIS map, and the algorithm output is "the path contains a weak positioning area". When the path analysis algorithm outputs "the path contains a weak positioning area", the task management system sends an activation instruction to the multi-modal fusion device through the serial port or network interface to activate the sliding mode switching positioning module.

[0031] Step S300, the sliding mode switching positioning module is used to recognize the behavior pattern of the target performing the power operation task and output the behavior pattern features.

[0032] Specifically, the sliding mode switching positioning module collects a variety of sensor data, including accelerometers, gyroscopes, barometers, etc., for recognizing the behavior pattern of the target. Machine learning algorithms (such as Hidden Markov Model HMM or deep learning algorithms) are used to analyze the sensor data, and features are extracted from the sensor data, such as the mean and variance of acceleration, the rotation angle of the gyroscope, etc., as the input features for behavior pattern recognition, to recognize the behavior pattern of the target, such as walking, running, standing still, etc.

[0033] For example, the sliding mode switching positioning module collects accelerometer data, collecting 100 data points per second. At the same time, gyroscope data is collected, collecting 50 data points per second. The HMM algorithm is used to analyze the accelerometer and gyroscope data, extracting the mean and variance from the accelerometer data and the rotation angle from the gyroscope data. These features are used as the input of the HMM algorithm for behavior pattern recognition. The algorithm identifies the behavior pattern of the target based on the data features. For example, when the mean of the accelerometer data is 0.5g, the variance is 0.1g, and the rotation angle of the gyroscope data is 10 degrees per second, it is identified as the "walking" mode.

[0034] In a possible implementation, the sliding mode switching positioning module is set on the edge device, and the edge device is used to perform behavior pattern recognition on the target executing the power operation task. Step S300 further includes step S310 of acquiring the target of the power operation task and collecting the real-time behavior data of the target. Specifically, the sliding mode switching positioning module is set on the edge device, and the edge device is used to perform behavior pattern recognition on the target executing the power operation task. Multiple sensors such as accelerometers, gyroscopes, barometers, GPS / Beidou positioning modules, etc. are deployed on the edge device to collect the real-time behavior data of the target. The acceleration, angular velocity, barometric change, position coordinates, etc. of the target are collected in real time. For example, the accelerometer collects 100 data points per second, the gyroscope collects 50 data points per second, and the GPS / Beidou positioning module collects 1 position coordinate data per second.

[0035] For example, an accelerometer, a gyroscope, and a GPS / Beidou positioning module are installed on the smart safety helmet or handheld terminal worn by the power operation personnel. The acceleration data collected by the accelerometer is [a x ,a y ,a z , the angular velocity data collected by the gyroscope is [ω x ,ω y ,ω z , and the position coordinates collected by the GPS / Beidou positioning module are (lat, lon).

[0036] Step S320, identifying the spatial change rate, action mutation points, and change in movement direction of the real-time behavior data, and outputting the behavior pattern category features. Specifically, the change rates of acceleration and angular velocity are calculated to identify the motion state of the target. For example, the acceleration change rate , and the angular velocity change rate , where represents the acceleration value at time point t, represents the acceleration value at time point t−1, represents the angular velocity value at time point t, represents the angular velocity value at time point t−1, represents the time interval, that is, the time length from time point t−1 to time point t. Signal processing algorithms (such as wavelet transform or threshold detection) are used to identify the mutation points of acceleration and angular velocity, and these mutation points indicate the start or end of an action. By analyzing the change of the position coordinates of the GPS / Beidou positioning module, the change rate of the movement direction is calculated. For example, the movement direction change rate , where θ is the angle of the movement direction, represents the movement direction angle at time point t, represents the movement direction angle at time point t−1. According to the above calculation results, the behavioral pattern category features are output, such as "walking", "stopping", "turning", etc.

[0037] Step S330, collect the target quantity and target dynamic rate for executing the power operation task, and output the behavioral pattern target features. Specifically, through the sensor network of the edge device, the number of targets executing tasks in the same operation area is counted. For example, the Wi-Fi signal strength or Bluetooth signal strength is used to detect and count the number of targets. The dynamic rate of the target is calculated, that is, the change frequency of the movement state of the target per unit time. For example, the dynamic rate can be calculated by counting the number of action mutation points of the target within a certain time. According to the target quantity and dynamic rate, the behavioral pattern target features are output, such as "single-person operation", "multi-person operation", "high dynamic rate", etc.

[0038] For example, in a certain operation area, 3 targets are detected to be executing tasks through the Wi-Fi signal strength. Target A has 5 action mutation points within 1 minute, and the dynamic rate is 5 times / minute.

[0039] Step S340, output the behavioral pattern features according to the behavioral pattern category features and the behavioral pattern target features. Specifically, the behavioral pattern category features and the behavioral pattern target features are fused to form comprehensive behavioral pattern features. For example, the category features such as "walking", "stopping", "turning", etc. are combined with the target features such as "single-person operation", "multi-person operation", "high dynamic rate", etc.

[0040] For example, the behavioral pattern category feature of Target A is "walking", and the behavioral pattern target features are "single-person operation" and "high dynamic rate". The finally output behavioral pattern feature is "single-person operation, high dynamic rate, walking". This implementation method divides the behavioral pattern features into category features and target features, realizes high-precision behavioral pattern recognition and adaptability to dynamic environments, and at the same time uses edge computing to improve the real-time performance and system response speed, thereby enhancing the safety protection ability of power operations, being able to detect and warn potential safety risks in a timely manner, and effectively ensuring the safety of operators.

[0041] Step S400: Establish a multi-modal confidence relationship matrix according to the described behavior pattern characteristics, and output a modal switching strategy based on the multi-modal confidence relationship matrix.

[0042] Specifically, the multi-modal confidence relationship matrix is a matrix used to represent the confidence levels of each positioning modality under different behavior patterns. Develop a confidence evaluation algorithm to evaluate the confidence level of each positioning modality based on the quality of sensor data and behavior pattern characteristics. For example, evaluate the confidence level according to Wi-Fi signal strength, Beidou signal strength, etc. Construct a multi-modal confidence relationship matrix, where the rows of the matrix represent different positioning modalities, the columns represent different behavior patterns, and the matrix elements represent the confidence level of a certain positioning modality under a specific behavior pattern. Generate a modal switching strategy based on the multi-modal confidence relationship matrix to guide the multi-modal fusion device to select the optimal positioning modality under different behavior patterns, that is, select the optimal positioning modality for switching according to the modality with the highest confidence level.

[0043] For example, the confidence evaluation algorithm is as follows: For the Wi-Fi positioning modality, when the signal strength is greater than -50 dBm, the confidence level is 0.9; when the signal strength is between -50 dBm and -70 dBm, the confidence level is 0.6; when the signal strength is less than -70 dBm, the confidence level is 0.3. For the Beidou positioning modality, when the number of satellites is greater than 10, the confidence level is 0.9; when the number of satellites is between 5 and 10, the confidence level is 0.6; when the number of satellites is less than 5, the confidence level is 0.3. An example of the multi-modal confidence relationship matrix is shown in Table 1.

[0044] Table 1: Example 1 of the multi-modal confidence relationship matrix

[0045] According to the multi-modal confidence relationship matrix in Table 1, when the target is in the "walking" mode, select the Beidou positioning modality; when the target is in the "stationary" mode, select the Wi-Fi positioning modality; when the target is in the "running" mode, select the Beidou positioning modality.

[0046] In a possible implementation, a multi-modal confidence relationship matrix is established according to the behavior pattern characteristics. Step S400 further includes step S410 of obtaining data quality parameters of each modality from the multi-modal fusion device, including RSSI signal strength, data update frequency, historical positioning MSE error, and data packet loss rate. Specifically, the received signal strength indication (RSSI) value is obtained from modalities such as Wi-Fi, Bluetooth, or Beidou to evaluate the signal strength and stability. The data update frequency of each modality is recorded, that is, the number of updates per second, to evaluate the real-time nature of the data. The historical positioning mean square error (MSE) of each modality is statistically calculated to evaluate the accuracy of positioning. The data packet loss rate of each modality is recorded, that is, the proportion of lost data packets in the total data packets, to evaluate the reliability of the data.

[0047] For example, the RSSI of the Wi-Fi modality is -60 dBm, the RSSI of the Bluetooth modality is -70 dBm, and the RSSI of the Beidou modality is -50 dBm. The Wi-Fi modality updates 10 times per second, the Bluetooth modality updates 5 times per second, and the Beidou modality updates 1 time per second. The MSE of the Wi-Fi modality is 1.2 meters, the MSE of the Bluetooth modality is 2.0 meters, and the MSE of the Beidou modality is 0.5 meters. The packet loss rate of the Wi-Fi modality is 5%, the packet loss rate of the Bluetooth modality is 10%, and the packet loss rate of the Beidou modality is 2%.

[0048] Step S420, input the behavior pattern characteristics and the data quality parameters of each modality as a joint vector into the modality confidence evaluation model, and output the confidence score of each modality under the current behavior. Specifically, the behavior pattern characteristics (such as "single-person operation, high dynamic rate, walking") and the data quality parameters (RSSI, update frequency, MSE, packet loss rate) are combined into a joint vector. A machine learning model (such as support vector machine SVM, random forest, or neural network) is used to evaluate the joint vector and output the confidence score of each modality under the current behavior.

[0049] For example, for target A, the joint vector is [current operation mode, target dynamic rate, target behavior mode, RSSI value of Wi-Fi mode, data update frequency of Wi-Fi mode, historical positioning MSE error of Wi-Fi mode, data packet loss rate of Wi-Fi mode, RSSI value of Bluetooth mode, data update frequency of Bluetooth mode, historical positioning MSE error of Bluetooth mode, data packet loss rate of Bluetooth mode, RSSI value of Beidou mode, data update frequency of Beidou mode, historical positioning MSE error of Beidou mode, data packet loss rate of Beidou mode], and the specific data is: [single-person operation, high dynamic rate, walking, -60, 10, 1.2, 5, -70, 5, 2.0, 10, -50, 1, 0.5, 2]. The random forest model is used to evaluate the joint vector, and the confidence score of each mode is output. For example, the confidence of the Wi-Fi mode is 0.7, the confidence of the Bluetooth mode is 0.4, and the confidence of the Beidou mode is 0.9.

[0050] Step S430, construct a multi-modal confidence relationship matrix based on the confidence scores of each mode. Specifically, according to the confidence scores of each mode, a multi-modal confidence relationship matrix is constructed. The rows of the matrix represent different behavior modes, the columns represent different modes, and the matrix elements represent the confidence of a certain positioning mode under a specific behavior mode. An example of the multi-modal confidence relationship matrix is shown in Table 2. This implementation method combines the behavior mode characteristics and data quality parameters to construct a multi-modal confidence relationship matrix, which realizes the accurate evaluation of the confidence of different modes under different behavior modes. This not only improves the accuracy and reliability of positioning, but also enhances the adaptive ability of the system, and can dynamically adjust the positioning mode according to real-time data, improving the safety and efficiency of power operations.

[0051] Table 2: Example of multi-modal confidence relationship matrix 2

[0052] In a possible implementation, step S420 further includes step S421. The modal confidence evaluation model includes a first fully connected network and a second fully connected network. The first fully connected network uses the Tanh activation function, and the second fully connected network uses the Sigmoid activation function. Specifically, the structure of the modal confidence evaluation model includes a first fully connected network and a second fully connected network. The first fully connected network is a fully connected network layer using the Tanh activation function, which is used to perform a non-linear transformation on the input joint vector and extract features. The second fully connected network is a fully connected network layer using the Sigmoid activation function, which is used to map the extracted features to the [0, 1] interval and output the confidence score of each mode.

[0053] For example, the first layer has 128 neurons and uses the Tanh activation function. After the input joint vector passes through the first fully connected network, a 128-dimensional feature vector is output. The second layer has 3 neurons (corresponding to three modalities: Wi-Fi, Bluetooth, and Beidou) and uses the Sigmoid activation function. After inputting the 128-dimensional feature vector, 3 confidence scores are output, such as [0.7, 0.4, 0.9].

[0054] Step S422: Use historical sample data to perform mean squared error loss training on the first fully connected network and the second fully connected network, and output the first fully connected network and the second fully connected network. The historical sample data includes sample data quality parameters and corresponding confidence annotation samples under different power operation behavior patterns. Specifically, collect sample data quality parameters and corresponding confidence annotation samples under different power operation behavior patterns. These sample data are used to train the model. Use the mean squared error (MSE) as the loss function and train the model through the backpropagation algorithm to optimize the model parameters and make the predicted confidence scores as close as possible to the annotated confidence scores.

[0055] For example, the historical sample data includes 1000 samples, and each sample contains behavior pattern features, RSSI signal strength, data update frequency, historical positioning MSE error, data packet loss rate, and corresponding confidence annotation. Use the mean squared error loss function to train the model. Assuming the annotated confidence scores are [0.7, 0.4, 0.9] and the confidence scores predicted by the model are [0.65, 0.38, 0.88], then the mean squared error is: MSE = 0.0011. Adjust the weights and biases of the model through the backpropagation algorithm to minimize the mean squared error. This implementation method realizes the accurate evaluation of the confidence of different modalities under different behavior patterns by designing a modality confidence evaluation model containing two fully connected layers and using historical sample data for mean squared error loss training.

[0056] In a possible implementation, the modality switching strategy is output based on the multi-modal confidence relationship matrix. Step S400 further includes step S440 of setting a confidence switching rule, where the confidence switching rule includes a modality retention interval, a modality replacement interval, and a modality suppression interval. Specifically, a confidence range is defined. When the confidence of a modality is within this range, the modality is marked as a retained modality, i.e., the main modality to be used. A confidence range is defined. When the confidence of a modality is within this range, the modality is marked as a standby modality, i.e., a modality that can be switched to when the main modality is unavailable. A confidence range is defined. When the confidence of a modality is within this range, the modality is marked as a suppressed modality, i.e., a modality that is not recommended for use. For example, the confidence switching rule is as follows: Modality retention interval: confidence greater than 0.8; Modality replacement interval: confidence between 0.5 and 0.8; Modality suppression interval: confidence less than 0.5.

[0057] Step S450: According to the confidence levels in the multi-modal confidence relationship matrix, each modality is marked according to the confidence switching rule, and a modality marking result is output. The modality marking result includes a retained modality, a standby modality, and a suppressed modality. Specifically, based on the confidence values in the multi-modal confidence relationship matrix, each modality is evaluated. According to the confidence switching rule, each modality is marked as a retained modality, a standby modality, or a suppressed modality. For example, for the multi-modal confidence relationship matrix in Table 2, the modality marking result is shown in Table 3.

[0058] Table 3: Example of modality marking result

[0059] Step S460: Compare the current modality enabled state according to the modality marking result, and output a modality switching strategy. Specifically, the modality marking result is compared with the enabled state of the current modality to determine whether modality switching is required. According to the comparison result, a modality switching strategy is output to decide whether to switch to the standby modality or suppress the current modality. This implementation method not only improves the accuracy and reliability of positioning by setting a confidence switching rule and marking each modality according to the multi-modal confidence relationship matrix, but also enhances the adaptive ability of the system, can dynamically adjust the positioning modality according to real-time data, and improves the safety and efficiency of power operations.

[0060] In a possible implementation, step S440 further includes step S441. The confidence level decrease rate in the mode retention interval is less than the first preset decrease rate, the confidence level decrease rate in the mode suppression interval is greater than the second preset decrease rate, and the confidence level decrease rate in the mode replacement interval is greater than or equal to the first preset decrease rate and less than or equal to the second preset decrease rate; wherein, the first preset decrease rate is less than the second preset decrease rate.

[0061] Specifically, the confidence level decrease rate refers to the rate at which the confidence level of a mode changes over time, which is the change in confidence level divided by the time interval. For example, if the confidence level of a mode decreases from 0.8 to 0.7 in 1 second, then the decrease rate is (0.8 - 0.7) / 1 = 0.1 / second.

[0062] Define a confidence level range. When the confidence level of a mode is within this range, the mode is marked as a retained mode. At the same time, define a confidence level decrease rate threshold. When the confidence level decrease rate of a mode is less than the first preset decrease rate, the mode is still retained. Define a confidence level range. When the confidence level of a mode is within this range, the mode is marked as a suppressed mode. At the same time, define a confidence level decrease rate threshold. When the confidence level decrease rate of a mode is greater than the second preset decrease rate, the mode is suppressed. Define a confidence level range. When the confidence level of a mode is within this range, the mode is marked as a standby mode. At the same time, define a confidence level decrease rate threshold. When the confidence level decrease rate of a mode is greater than or equal to the first preset decrease rate and less than or equal to the second preset decrease rate, the mode is marked as a standby mode.

[0063] For example, assume the first preset decrease rate is 0.05 / second and the second preset decrease rate is 0.1 / second. If the confidence level of Wi-Fi positioning is 0.7 and the decrease rate is 0.03 / second. 0.7 is between 0.5 and 0.8, belonging to the mode replacement interval; 0.03 / second is less than the first preset decrease rate (0.05 / second). According to the rules, although the confidence level of Wi-Fi positioning is within the mode replacement interval, since its decrease rate is less than the first preset decrease rate, it is marked as a retained mode.

[0064] With this implementation, through the confidence level decrease rate, the system can more accurately judge the stability of the mode. For example, even if the confidence level of a mode is within the mode replacement interval, but if its decrease rate is low, it indicates that the mode is still relatively stable and can be retained. At the same time, the system can dynamically adjust the mode according to real-time data. For example, when the confidence level decrease rate of a mode exceeds the threshold, the system can timely mark it as a suppressed mode to avoid using unstable modes. Through more accurate mode selection, the system can improve the accuracy and reliability of positioning, thereby enhancing the safety and efficiency of power operations.

[0065] In a possible implementation, the current modality enabling state is compared according to the modality marking result, and a modality switching strategy is output. Step S460 further includes step S461. If the reserved modality in the modality marking result is different from the current modality enabling state, a modality switching instruction is obtained, and the modality fusion device is controlled to output modality positioning data according to the reserved modality. Specifically, the reserved modality in the modality marking result is compared with the current modality enabling state. If the reserved modality is different from the current enabled modality, a modality switching instruction is obtained. According to the modality switching instruction, the modality fusion device is controlled to output modality positioning data according to the reserved modality, ensuring that the system always uses the most reliable modality for positioning. For example, the modality marking result is: reserved modality: Beidou positioning; standby modality: Wi-Fi positioning; suppressed modality: Bluetooth positioning. The current modality enabling state is: current enabled modality: Wi-Fi positioning. The comparison result is: the reserved modality (Beidou positioning) is different from the current enabled modality (Wi-Fi positioning). The modality switching instruction is: switch to Beidou positioning. The modality fusion device is controlled to output modality positioning data according to Beidou positioning.

[0066] Step S462, if the confidence fluctuations of the reserved modality and the standby modality in the modality marking result are greater than a preset threshold, the reserved modality and the standby modality are combined, and the modality fusion device is controlled to output modality positioning data according to the combined modality. Specifically, it is detected whether the confidence fluctuations of the reserved modality and the standby modality are greater than the preset threshold. If the confidence fluctuations are greater than the preset threshold, the reserved modality and the standby modality are combined. The modality fusion device is controlled to output modality positioning data according to the combined modality to improve the stability and reliability of positioning and reduce the influence of the instability of a single modality on the positioning accuracy.

[0067] Step S463, if there is the same modality between the suppressed modality in the modality marking result and the current modality, the suppressed modality is removed. Specifically, the suppressed modality in the modality marking result is compared with the current modality enabling state. If the suppressed modality is the same as the current enabled modality, the suppressed modality is removed to avoid using an unstable modality for positioning. This implementation method dynamically adjusts the output modality of the modality fusion device by comparing the modality marking result with the current modality enabling state in detail, not only improving the accuracy and reliability of positioning, but also enhancing the adaptive ability of the system, being able to dynamically adjust the positioning modality according to real-time data, and improving the safety and efficiency of power operations.

[0068] Step S500, the multi-modal fusion device analyzes the multi-modal positioning data according to the modality switching strategy and outputs a protection positioning result.

[0069] Specifically, a multi-modal positioning algorithm is developed to fuse data from different positioning modalities according to the modality switching strategy for high-precision positioning. For example, the Kalman filter algorithm is used to fuse Beidou and Wi-Fi positioning data. The fused positioning data is combined with the safety protection rules to output the protected positioning result, which is used to guide the safe operation of the operators. For example, an alarm is issued when the target approaches a dangerous area.

[0070] For example, the Kalman filter algorithm is used to fuse Beidou positioning data and Wi-Fi positioning data. The Kalman filter dynamically adjusts the weights according to the confidence levels of the Beidou and Wi-Fi positioning data and outputs a high-precision positioning result. The positioning result is combined with the safety protection rules for the power operation area. For example, when the target approaches a high-voltage area, the system issues an alarm to remind the operator to pay attention to safety.

[0071] In a possible implementation, the multi-modal fusion device performs multi-modal positioning data analysis according to the modality switching strategy and outputs the protected positioning result. Step S500 further includes step S510, where the multi-modal fusion device performs multi-modal positioning data analysis according to the modality switching strategy and outputs the auxiliary positioning data for the weak positioning area. Specifically, according to the modality switching strategy, the multi-modal fusion device analyzes the positioning data of different modalities to generate the auxiliary positioning data. The auxiliary positioning data is used to provide more accurate positioning information in the weak positioning area (such as the indoor-outdoor transition area). For example, if the reserved modality is Beidou positioning and the backup modality is Wi-Fi positioning. In the weak positioning area, the confidence level of Beidou positioning is 0.8, and the confidence level of Wi-Fi positioning is 0.7. The generated auxiliary positioning data includes the high-precision position information of Beidou positioning and the auxiliary information of Wi-Fi positioning, which is used to improve the positioning accuracy.

[0072] Step S520, according to the multi-modal fusion device, obtain the indoor positioning data or outdoor positioning data corresponding to the target performing the power operation task. Specifically, indoor positioning technologies (such as Wi-Fi, Bluetooth, UWB, etc.) are used to obtain the indoor positioning data of the target, which contains inaccurate information in the weak positioning area. Outdoor positioning technologies (such as Beidou, GPS, etc.) are used to obtain the outdoor positioning data of the target, which also contains inaccurate information in the weak positioning area.

[0073] Step S530: Assist in updating indoor positioning data or outdoor positioning data according to the auxiliary positioning data, and output a protection positioning result. Specifically, update the indoor or outdoor positioning data according to the auxiliary positioning data to improve the positioning accuracy. The auxiliary positioning data provides more accurate positioning information, especially in weak positioning areas. Output the final protection positioning result to ensure high-precision positioning information can also be provided in weak positioning areas. This implementation method generates auxiliary positioning data in weak positioning areas and updates indoor or outdoor positioning data according to the auxiliary positioning data, significantly improving the accuracy and reliability of positioning. This not only enhances the adaptive ability of the system but also ensures high-precision positioning in complex environments, significantly improving the safety and efficiency of power operations.

[0074] The embodiment of the present application first identifies the weak positioning areas for indoor-outdoor switching in the power operation area. After obtaining the operation task, if the path contains such an area, the sliding mode switching positioning module is activated. The module performs behavior pattern recognition on the operation target and outputs features, then establishes a multi-modal confidence relationship matrix based on this to output a mode switching strategy. Finally, the multi-modal fusion device performs multi-modal positioning data analysis according to this strategy and outputs a protection positioning result and other technical means, solving the technical problems of unstable positioning signals and decreased accuracy during complex environment switching in existing power operation safety protection positioning, and achieving the technical effect of improving the accuracy and reliability of power operation safety protection positioning.

[0075] In the above text, reference is made to Figure 1 The power operation safety protection positioning method integrating Beidou navigation according to the embodiment of the present invention is described in detail. Next, reference will be made to Figure 2 Describe the power operation safety protection positioning system integrating Beidou navigation according to the embodiment of the present invention.

[0076] The power operation safety protection positioning system integrating Beidou navigation according to the embodiment of the present invention is used to solve the technical problems of unstable positioning signals and decreased accuracy during complex environment switching in existing power operation safety protection positioning, and achieve the technical effect of improving the accuracy and reliability of power operation safety protection positioning. The power operation safety protection positioning system integrating Beidou navigation includes: a weak positioning area identification module 10, a sliding mode switching positioning activation module 20, a behavior pattern recognition module 30, a mode switching strategy output module 40, and a protection positioning module 50.

[0077] The weak positioning area identification module 10 is used to identify the weak positioning area in the power operation area, where the weak positioning area is the transition area when switching from indoor to outdoor or from outdoor to indoor; the sliding mode switching positioning activation module 20 is used to obtain the current power operation task. If the path of the power operation task includes the weak positioning area, the sliding mode switching positioning module is activated. The sliding mode switching positioning module is connected to the multi-modal fusion device, and the Beidou navigation is integrated in the multi-modal fusion device; the behavior mode recognition module 30 is used to recognize the behavior mode of the target executing the power operation task through the sliding mode switching positioning module and output the behavior mode characteristics; the mode switching strategy output module 40 is used to establish a multi-modal confidence relationship matrix according to the behavior mode characteristics and output the mode switching strategy with the multi-modal confidence relationship matrix; the protection positioning module 50 is used for the multi-modal fusion device to perform multi-modal positioning data analysis according to the mode switching strategy and output the protection positioning result.

[0078] Next, the specific configuration of the behavior mode recognition module 30 will be described in detail. As described above, the sliding mode switching positioning module is set in the edge device, and the behavior mode of the target executing the power operation task is recognized through the edge device. The behavior mode recognition module 30 may further include: a real-time behavior data acquisition unit for obtaining the target of the power operation task and acquiring the real-time behavior data of the target; a behavior mode category feature output unit for recognizing the spatial change rate, action mutation point and movement direction change of the real-time behavior data and outputting the behavior mode category characteristics; a behavior mode target feature output unit for acquiring the number of targets and the target dynamic rate of the target executing the power operation task and outputting the behavior mode target characteristics; a behavior mode feature output unit for outputting the behavior mode characteristics according to the behavior mode category characteristics and the behavior mode target characteristics.

[0079] Next, the specific configuration of the mode switching strategy output module 40 will be described in detail. As described above, a multi-modal confidence relationship matrix is established according to the behavior mode characteristics. The mode switching strategy output module 40 may further include: a data quality parameter acquisition unit for acquiring the data quality parameters of each mode from the multi-modal fusion device, including RSSI signal strength, data update frequency, historical positioning MSE error and data packet loss rate; a mode confidence evaluation unit for inputting the behavior mode characteristics and the data quality parameters of each mode as a joint vector into the mode confidence evaluation model and outputting the confidence score of each mode under the current behavior; a multi-modal confidence relationship matrix construction unit for constructing a multi-modal confidence relationship matrix based on the confidence scores of each mode.

[0080] Among them, the modal confidence evaluation unit may further include: a modal confidence evaluation model construction subunit for constructing a modal confidence evaluation model, the modal confidence evaluation model including a first fully-connected network and a second fully-connected network, the first fully-connected network using a Tanh activation function, and the second fully-connected network using a Sigmoid activation function; a training subunit for performing mean squared error loss training on the first fully-connected network and the second fully-connected network using historical sample data, and outputting the first fully-connected network and the second fully-connected network, the historical sample data including sample data quality parameters and corresponding confidence annotation samples under different power operation behavior modes.

[0081] Among them, a modal switching strategy is output based on the multi-modal confidence relationship matrix. The modal switching strategy output module 40 may further include: a confidence switching rule setting unit for setting confidence switching rules, the confidence switching rules including a modal retention interval, a modal replacement interval, and a modal suppression interval; a modal marking unit for marking each modality according to the confidence levels in the multi-modal confidence relationship matrix in accordance with the confidence switching rules, and outputting a modal marking result, the modal marking result including a retained modality, a standby modality, and a suppressed modality; a modal switching strategy output unit for comparing the current modal enabled state according to the modal marking result, and outputting a modal switching strategy.

[0082] Among them, the confidence switching rule setting unit may further include: the confidence decline rate of the modal retention interval is less than a first preset decline rate, the confidence decline rate of the modal suppression interval is greater than a second preset decline rate, and the confidence decline rate of the modal replacement interval is greater than or equal to the first preset decline rate and less than or equal to the second preset decline rate; wherein, the first preset decline rate is less than the second preset decline rate.

[0083] Among them, when comparing the current modal enabled state according to the modal marking result and outputting a modal switching strategy, the modal switching strategy output unit may further include: a first modal positioning data output subunit for, if the retained modality in the modal marking result is different from the current modal enabled state, obtaining a modal switching instruction, and controlling the modal fusion device to output modal positioning data according to the retained modality; a second modal positioning data output subunit for, if the confidence fluctuations of the retained modality and the standby modality in the modal marking result are greater than a preset threshold, combining the retained modality and the standby modality, and controlling the modal fusion device to output modal positioning data according to the combined modality; a suppressed modality elimination subunit for, if the suppressed modality in the modal marking result is the same as the current modality, eliminating the suppressed modality.

[0084] Next, the specific configuration of the protection positioning module 50 will be described in detail. As described above, the multi-modal fusion device performs multi-modal positioning data analysis according to the mode switching strategy and outputs a protection positioning result. The protection positioning module 50 may further include: an auxiliary positioning data output unit for the multi-modal fusion device to perform multi-modal positioning data analysis according to the mode switching strategy and output the auxiliary positioning data of the weak positioning area; an indoor / outdoor positioning data acquisition unit for acquiring indoor positioning data or outdoor positioning data corresponding to the target of the power operation task according to the multi-modal fusion device; and a protection positioning result output unit for assisting in updating the indoor positioning data or outdoor positioning data according to the auxiliary positioning data and outputting a protection positioning result.

[0085] The power operation safety protection positioning system integrating Beidou navigation provided by the embodiments of the present invention can execute the power operation safety protection positioning method integrating Beidou navigation provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0086] Although various references are made to certain modules in the systems of the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0087] Based on the foregoing embodiments, the embodiments of the present application further provide an electronic device. Figure 3 It is a schematic structural diagram of the electronic device provided by the embodiments of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 3 The electronic device shown is only an example and should not bring any limitations to the functions and usage scope of the embodiments of the present invention. The electronic device is presented in the form of a general computing device, and its components may include, but are not limited to, an input device 301, a processor 302, a memory 303, and an output device 304. Among them, the processor 302 may be one or more; the memory 303 may include a computer-readable medium and at least one program product, and the program product has a set (at least one) of program modules configured to execute the functions of the embodiments of the present application.

[0088] The memory 303 shown in the embodiments of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be, but is not limited to, infrared rays, semiconductor systems, devices or components, or any combination of the above, for storing software programs, computer-executable programs and modules, such as the program instructions / modules corresponding to the power operation safety protection positioning method integrating Beidou navigation in the embodiments of the present invention. The processor 302 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 303, that is, implements the above-mentioned power operation safety protection positioning method integrating Beidou navigation.

[0089] The above specific embodiments do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recited in the present application may be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A power operation safety protection positioning method integrating Beidou navigation, characterized in that The method includes: Identifying a weak positioning area in the power operation area, where the weak positioning area is a transition area when switching from indoor to outdoor or from outdoor to indoor; Obtaining the current power operation task. If the path of the power operation task includes the weak positioning area, activating a sliding mode switching positioning module, which is connected to a multi-modal fusion device, and the multi-modal fusion device integrates Beidou navigation; The sliding mode switching positioning module is used to identify the behavior pattern of the target performing the power operation task and output the behavior pattern features; Establishing a multi-modal confidence relationship matrix according to the behavior pattern features and outputting a mode switching strategy based on the multi-modal confidence relationship matrix; The multi-modal fusion device performs multi-modal positioning data analysis according to the mode switching strategy and outputs a protection positioning result.

2. The power operation safety protection positioning method integrating Beidou navigation according to claim 1, wherein The sliding mode switching positioning module is set in an edge device. The method for identifying the behavior pattern of the target performing the power operation task through the edge device includes: Obtaining the target of the power operation task and collecting the real-time behavior data of the target; Identifying the spatial change rate, action mutation points, and change in the movement direction of the real-time behavior data and outputting the behavior pattern category features; Collecting the number of targets and the target dynamic rate of the power operation task and outputting the behavior pattern target features; Outputting the behavior pattern features according to the behavior pattern category features and the behavior pattern target features.

3. The power operation safety protection positioning method integrating Beidou navigation according to claim 1, characterized in that The method for establishing a multi-modal confidence relationship matrix according to the behavior pattern features includes: Obtaining the data quality parameters of each mode from the multi-modal fusion device, including RSSI signal strength, data update frequency, historical positioning MSE error, and data packet loss rate; Taking the behavior pattern features and the data quality parameters of each mode as a joint vector and inputting them into a mode confidence evaluation model to output the confidence score of each mode under the current behavior; Constructing a multi-modal confidence relationship matrix based on the confidence scores of each mode.

4. The power operation safety protection positioning method integrating Beidou navigation according to claim 3, characterized in that, The mode confidence evaluation model includes a first-layer fully connected network and a second-layer fully connected network. The first-layer fully connected network uses a Tanh activation function, and the second-layer fully connected network uses a Sigmoid activation function; Training the first-layer fully connected network and the second-layer fully connected network with mean square error loss using historical sample data, and outputting the first-layer fully connected network and the second-layer fully connected network. The historical sample data includes sample data quality parameters and corresponding confidence annotation samples under different power operation behavior patterns.

5. The power operation safety protection positioning method integrating Beidou navigation according to claim 1, characterized in that, The method for outputting a mode switching strategy based on the multi-modal confidence relationship matrix includes: Setting a confidence switching rule, which includes a mode retention interval, a mode replacement interval, and a mode suppression interval; Marking each mode according to the confidence level in the multi-modal confidence relationship matrix according to the confidence switching rule and outputting a mode marking result, where the mode marking result includes a retained mode, a standby mode, and a suppressed mode; Comparing the current mode enabled state according to the mode marking result and outputting a mode switching strategy.

6. The power operation safety protection positioning method integrating Beidou navigation according to claim 5, characterized in that The confidence decline rate of the modal retention interval is less than the first preset decline rate, the confidence decline rate of the modal suppression interval is greater than the second preset decline rate, and the confidence decline rate of the modal replacement interval is greater than or equal to the first preset decline rate and less than or equal to the second preset decline rate; wherein, the first preset decline rate is less than the second preset decline rate.

7. The power operation safety protection positioning method integrating Beidou navigation according to claim 5, characterized in that, Compare the current modal enabled state according to the modal marking result, and output a modal switching strategy. The method includes: If the retained mode in the modal marking result is different from the current modal enabled state, obtain a modal switching instruction, and control the modal fusion device to output modal positioning data according to the retained mode; If the confidence fluctuations of the retained mode and the standby mode in the modal marking result are greater than a preset threshold, combine the retained mode and the standby mode, and control the modal fusion device to output modal positioning data according to the combined mode; If the suppressed mode in the modal marking result has the same mode as the current mode, eliminate the suppressed mode.

8. The power operation safety protection positioning method integrating Beidou navigation according to claim 1, characterized in that, The multi-modal fusion device performs multi-modal positioning data analysis according to the modal switching strategy and outputs a protection positioning result. The method includes: The multi-modal fusion device performs multi-modal positioning data analysis according to the modal switching strategy and outputs the auxiliary positioning data of the weak positioning area; According to the multi-modal fusion device, obtain the indoor positioning data or outdoor positioning data corresponding to the target of performing the power operation task; Assist in updating the indoor positioning data or outdoor positioning data according to the auxiliary positioning data, and output a protection positioning result.

9. The power operation safety protection positioning system integrating Beidou navigation is characterized in that, The system is used to implement the power operation safety protection positioning method integrating Beidou navigation according to any one of claims 1-8. The system includes: A weak positioning area identification module for identifying the weak positioning area in the power operation area, where the weak positioning area is a transition area when switching from indoor to outdoor or from outdoor to indoor; A sliding mode switching positioning activation module for obtaining the current power operation task. If the path of the power operation task includes the weak positioning area, activate the sliding mode switching positioning module. The sliding mode switching positioning module is connected to the multi-modal fusion device, and the multi-modal fusion device integrates Beidou navigation; A behavior pattern recognition module for recognizing the behavior pattern of the target performing the power operation task through the sliding mode switching positioning module and outputting behavior pattern features; A modal switching strategy output module for establishing a multi-modal confidence relationship matrix according to the behavior pattern features and outputting a modal switching strategy with the multi-modal confidence relationship matrix; A protection positioning module for the multi-modal fusion device to perform multi-modal positioning data analysis according to the modal switching strategy and output a protection positioning result.

10. An electronic device, characterized in that, The electronic device includes: A memory for storing executable instructions; A processor for implementing the power operation safety protection positioning method integrating Beidou navigation according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

Images