Global situation awareness method based on data processing

Abstract

The embodiment of the present application provides a global situational awareness method based on data processing. The method includes obtaining the actual current detected by the current sensor arranged on the electrical equipment, and the actual temperature detected by the temperature sensor arranged on the heating element. Determine whether there is a fire risk based on the actual current and the actual temperature. If so, obtain the layout position of the temperature sensor and the layout position of each camera, select a target camera from multiple cameras based on the layout position of the temperature sensor and the layout position of each camera, control the target camera to capture the monitoring image of the electrical equipment, obtain the light intensity at the time of capturing the monitoring image, use the fire detection model to identify the monitoring image, and use the light intensity, actual current and actual temperature at the time of capturing to correct the identification process, output the fire detection result, perform global situational awareness, use data processing technology to process the perception data, and detect the fire as early as possible.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a global situation awareness method based on data processing. Background Art

[0002] With the increase of urbanization and building complexity, efficient and reliable fire detection and alarm systems have become an indispensable part of ensuring building safety.

[0003] Smoke alarms or temperature sensors are usually placed in the monitoring area. When the smoke concentration reaches a certain concentration through the smoke alarm or the temperature sensor senses a temperature rise, a fire alarm is sounded. However, smoke alarms usually require the smoke concentration to reach a set concentration, which will delay rescue time. The location of the temperature sensor is relatively important. If it is not placed in an area prone to fire, the fire cannot be detected in time.

[0004] Therefore, the existing solutions for detecting fire through smoke alarms or temperature sensors cannot detect smoke as early as possible, and the reliability of detecting fire is not strong. Summary of the invention

[0005] The embodiment of the present application provides a global situation awareness method based on data processing, which uses current sensors, temperature sensors, and cameras to perform global situation awareness, and uses data processing technology to process the perceived data to achieve the technical effect of detecting fire as early as possible.

[0006] The embodiment of the present application provides a global situation awareness method based on data processing, wherein a plurality of cameras are arranged in a monitoring area, current sensors are arranged on electrical equipment in the monitoring area, and temperature sensors are arranged on heating elements of the electrical equipment. The method is applied to a background server, and the method includes: Acquire the actual current detected by the current sensor arranged on the electrical equipment and the actual temperature detected by the temperature sensor arranged on the heating element; Determine whether there is a fire risk based on the actual current and the actual temperature. If so, obtain the layout position of the temperature sensor and the layout position of each camera; Selecting a target camera from a plurality of cameras according to the arrangement positions of the temperature sensors and the arrangement positions of the cameras; Control the target camera to capture the monitoring image of the electrical equipment, and obtain the light intensity at the time of capturing the monitoring image; The fire detection model is used to identify the monitoring image, and the light intensity, actual current and actual temperature at the time of shooting are used to correct the identification process and output the fire detection results.

[0007] In the above technical scheme, a camera is arranged in the monitoring area, a current sensor is arranged on the electrical equipment in the monitoring area, and a temperature sensor is arranged on the heating element of the electrical equipment. The background server obtains the actual current detected by the current sensor and the actual temperature detected by the temperature sensor, and determines whether there is a fire risk in the monitoring area based on the actual current and the actual temperature. When it is determined that there is a fire risk, the camera is called to shoot the monitoring image, and the light intensity at the shooting time is obtained. The monitoring image is recognized using the fire detection model, and the recognition process is corrected using the light intensity, actual current and actual temperature at the shooting time. In this way, the full-domain state perception of the fire is realized, and the accuracy of fire detection is improved. Compared with the smoke alarm, the camera can detect the fire in time when the fire just occurs, without waiting until the smoke concentration reaches the set threshold. Compared with the sensing area of ​​the temperature sensor, the shooting area of ​​the camera is relatively large, and fewer cameras can achieve blind-angle monitoring of the monitoring area, thereby improving the reliability of fire prevention and control.

[0008] In a possible implementation, the monitoring image is identified using a fire detection model, and the identification process is corrected using the light intensity, actual current, and actual temperature at the time of shooting, and the fire detection result is output, specifically including: Generate input features based on the monitoring image and the light intensity at the time of shooting, and generate classification features based on the actual current and actual temperature; The input features and classification features are concatenated to generate concatenated features, an encoder is used to encode the concatenated features to output encoded features, and a decoder is used to decode the classified data in the encoded features to determine the fire detection results.

[0009] In the above technical solution, input features are generated according to the monitoring image and the light intensity at the time of shooting, the light intensity and the monitoring image are fused, and classification features are generated according to the actual current and the actual temperature. In this way, the classification features are initialized using the actual current and the actual temperature, and the input features and the classification features are spliced ​​to obtain spliced ​​features, so that the spliced ​​features contain more information, and fire identification is performed based on the spliced ​​features, which can improve the accuracy of fire detection results.

[0010] In a possible implementation, the input feature is generated according to the monitoring image and the light intensity at the time of shooting, specifically including: The monitoring image is divided into blocks to obtain a plurality of image blocks and the position of each image block, and the monitoring sub-area corresponding to each image block is determined according to the shooting parameters of the camera; Obtaining the light intensity of each monitoring sub-area at the time of shooting, and using the light intensity of each monitoring sub-area at the time of shooting as the light intensity of the corresponding image block; Each image block, the position of each image block and the light intensity of each image block are fused to obtain fused data of each image block; the fused data of multiple image blocks are spliced ​​to generate input features.

[0011] In a possible implementation, using a decoder to decode the coded feature to determine the fire detection result specifically includes: The first fully connected layer is used to linearize the encoded features, the activation function layer is used to nonlinearly process the output data of the first fully connected layer, the second fully connected layer is used to linearize the output data of the activation function layer, and the residual layer is used to superimpose the output features of the second fully connected layer and the output features of the activation function layer and then output them.

[0012] In the above technical solution, the decoder includes a fully connected layer for linear processing and an activation function layer for nonlinear processing, which can improve the decoding performance of the decoder and improve the accuracy of fire monitoring.

[0013] In a possible implementation, determining whether there is a fire risk according to the actual current and the actual temperature specifically includes: Obtain the rated current and temperature tolerance of electrical equipment; If the actual current is greater than the rated current and the actual temperature is greater than the tolerance temperature, it is determined that there is a fire risk.

[0014] In the above technical solution, the actual temperature of the heating element is collected by a temperature sensor, and the actual current of the electrical equipment is collected by a current sensor. Whether there is a fire risk is determined based on the actual temperature and the actual current, which can improve the accuracy of the preliminary fire judgment.

[0015] In a possible implementation manner, obtaining the tolerance temperature of the electrical equipment specifically includes: Acquire the actual current detected by the current sensor at multiple moments and the actual temperature detected by the temperature sensor at multiple moments; The tolerance temperature prediction model is used to process the actual current at multiple times and the actual temperature at multiple times, and the tolerance temperature of the electrical equipment is output.

[0016] In the above technical solution, by obtaining the actual temperature at multiple moments and the actual current at multiple moments, the actual temperature at multiple moments and the actual current at multiple moments are input into the tolerance temperature prediction model for prediction, and the tolerance temperature is updated in real time. Compared with using a fixed tolerance temperature, it can adapt to the situation where the performance of electrical components changes with the increase of usage time, so that fire risks can be discovered in time.

[0017] In a possible implementation, before obtaining the actual current detected by the current sensor on the electrical device and the actual temperature detected by the temperature sensor arranged on the heating element, the method further includes: Obtain a circuit topology diagram of the monitoring area, and establish a power model in the power simulation software based on the circuit topology diagram; The power model is simulated and analyzed in the power simulation software to obtain the position information of the heating element; and a plurality of temperature sensors are arranged according to the position information of the heating element.

[0018] In the above technical solution, compared with the arrangement of temperature sensors based on experience, an electric model corresponding to the electric topology diagram of the monitoring area is established in the electric power simulation software, the operating temperature of each electrical equipment is determined through simulation analysis, the heating element is selected based on the operating temperature, and the temperature sensors are arranged on the heating element. In this way, the temperature of the heating element can be monitored more accurately and abnormalities can be detected in time.

[0019] The present application embodiment provides a global situation awareness system based on data processing, including: An acquisition module, used to acquire an actual current detected by a current sensor arranged on the electrical device, and an actual temperature detected by a temperature sensor arranged on the heating element; A processing module, used to determine whether there is a fire risk according to the actual current and the actual temperature, and if so, obtain the arrangement position of the temperature sensor and the arrangement position of each camera; The processing module is further used to select a target camera from the plurality of cameras according to the arrangement positions of the temperature sensors and the arrangement positions of the cameras; The processing module is also used to control the target camera to capture the monitoring image of the electrical equipment and obtain the light intensity at the time of capturing the monitoring image; The processing module is also used to use the fire detection model to identify the monitoring image, and use the light intensity, actual current and actual temperature at the time of shooting to correct the identification process and output the fire detection result.

[0020] The embodiment of the present application provides a backend server, including: a memory, a processor; Memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes various possible implementations as described above.

[0021] An embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the various possible implementation methods described above.

[0022] An embodiment of the present application provides a computer program product, including a computer program, which implements the above various possible implementation methods when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0024] Figure 1 An application scenario diagram of the global situation awareness method based on data processing provided in this application; Figure 2 A flowchart of the global situation awareness method based on data processing provided by this application; Figure 3 A schematic diagram of the structure of an encoder provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a decoder provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of the backend server provided for this application.

[0025] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0027] Smoke alarms or temperature sensors are usually placed in the monitoring area. When the smoke concentration reaches a certain concentration through the smoke alarm or the temperature sensor senses a temperature rise, a fire alarm is sounded. However, smoke alarms usually require the smoke concentration to reach a set concentration, which will delay rescue time. The location of the temperature sensor is relatively important. If it is not placed in an area prone to fire, the fire cannot be detected in time.

[0028] Therefore, the existing solutions for detecting fire through smoke alarms or temperature sensors cannot detect smoke as early as possible, and the reliability of detecting fire is not strong.

[0029] The global situation awareness method based on data processing provided by the present application is that a camera is arranged in the monitoring area, a current sensor is arranged on the electrical equipment in the monitoring area, and a temperature sensor is arranged on the heating element of the electrical equipment. The current sensor, the temperature sensor, and the camera are used for global situation awareness, and the perception data is processed by using data processing technology to achieve the technical effect of early detection of fire. More specifically, the background server obtains the actual current detected by the current sensor and the actual temperature detected by the temperature sensor, and determines whether there is a fire risk in the monitoring area based on the actual current and the actual temperature. When it is determined that there is a fire risk, the camera is called to shoot the monitoring image, and the light intensity at the time of shooting is obtained. The monitoring image is identified using the fire detection model, and the identification process is corrected using the light intensity at the time of shooting, the actual current, and the actual temperature. In this way, the global state awareness of the fire is realized, and compared with the smoke alarm, the camera can detect the fire in time when the fire just occurs, without waiting until the smoke concentration reaches the set threshold. Compared with the sensing area of ​​the temperature sensor, the camera's shooting area is relatively large, and fewer cameras can monitor the monitoring area without blind spots, thereby improving the reliability of fire prevention and control.

[0030] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0031] Figure 1 The application scenario diagram of the global situation awareness method based on data processing provided in this application is as follows: Figure 1 As shown, multiple cameras are arranged in the monitoring area, and the cameras are used to capture monitoring images in the monitoring area. There are electrical equipment in the monitoring area, and each electrical equipment is arranged with a current sensor for detecting the actual current of the electrical equipment. A temperature sensor is arranged on the heating element of the electrical equipment, and the temperature sensor detects the actual temperature of the heating element. The backend server is connected to the camera, current sensor and temperature sensor in the monitoring area, receives the monitoring image uploaded by the camera, the actual current uploaded by the current sensor and the actual temperature uploaded by the temperature sensor, and the backend server identifies the fire according to the monitoring image, the actual current and the actual temperature.

[0032] Figure 2 A flowchart of the global situation awareness method based on data processing provided in this application is as follows: Figure 2 As shown, the method comprises the following steps: S101. The backend server obtains the actual current detected by the current sensor on the electrical device and the actual temperature detected by the temperature sensor arranged on the heating element.

[0033] Among them, the background server is communicated with the current sensor. After the current sensor collects the actual current of the electrical equipment, the actual current of the electrical equipment is uploaded to the background server, and the background server stores the actual current.

[0034] The backend server is connected to the temperature sensor in communication. After the temperature sensor collects the actual temperature of the heating element, it uploads the actual temperature of the heating element to the backend server, which stores the actual temperature.

[0035] S102. The backend server determines whether there is a fire risk based on the actual current and the actual temperature. If so, obtains the layout position of the temperature sensor and the layout position of each camera. If not, returns to S101.

[0036] Among them, the background server obtains the set temperature and set current of the electrical equipment, compares the set temperature of the electrical equipment with the actual temperature, compares the set current of the electrical equipment with the actual current, and determines whether there is a fire risk based on the two comparison results.

[0037] More specifically, if it is determined that the actual current is greater than the set current, and the actual temperature is greater than the set temperature, it is determined that there is a fire risk. If it is determined that the actual current is less than or equal to the set current, but the actual temperature is greater than the set temperature, the actual temperature continues to be monitored, and if the temperature rise rate is greater than the preset rate, it is determined that there is a fire risk. If it is determined that the actual current is less than or equal to the set current, and the actual temperature is less than or equal to the set temperature, it is determined that there is no fire risk. If it is determined that the actual current is greater than the set current, but the actual temperature is less than or equal to the set temperature, it is determined that there is no fire risk.

[0038] S103: The backend server selects a target camera from a plurality of cameras according to the arrangement positions of the temperature sensors and the arrangement positions of the cameras.

[0039] The sensor whose actual temperature is greater than the set temperature is obtained and marked as the target sensor. The layout position of the target sensor is obtained, and a camera located near the target sensor is selected from multiple cameras as the target camera according to the position of the target sensor and the layout positions of each camera.

[0040] For example, there are 4 electrical devices in the monitoring area, each of which is equipped with a temperature sensor. The actual temperature detected by 3 temperature sensors is lower than the set temperature, and only the actual temperature detected by 1 temperature sensor is higher than the set temperature. This temperature sensor is used as the target sensor. The location of the target sensor is obtained, and a camera located near the target sensor is selected as the target camera to monitor whether a fire occurs near the target sensor.

[0041] S104: The backend server controls the target camera to capture a monitoring image of the electrical device, and obtains the light intensity at the time of capturing the monitoring image.

[0042] Among them, the background server sends a shooting instruction to the target camera, controls the target camera to shoot the monitoring image of the electrical equipment, and the target camera uploads the captured monitoring image to the background server.

[0043] In some examples, a light intensity sensor is arranged in the monitoring area, and the light intensity sensor detects the light intensity at the time of shooting. In other examples, the background server sends a weather data request to the weather system, so that the weather system returns the light intensity at the time of shooting.

[0044] S105. The backend server uses the fire detection model to identify the monitoring image, and uses the light intensity, actual current and actual temperature at the time of shooting to correct the identification process, and outputs the fire detection result.

[0045] Among them, the fire detection model obtains feature data by extracting features from the monitoring image, and decodes the feature data to output the fire detection results. When extracting features from the monitoring image, the light intensity, actual current and actual temperature at the time of shooting are used to correct the feature extraction process. In this way, the feature data retains the information of light intensity, actual current, actual temperature and monitoring image, and when the decoder is used to decode the feature data, the classification accuracy is improved, thereby improving the accuracy of fire detection.

[0046] In the above technical scheme, a camera is arranged in the monitoring area, a current sensor is arranged on the electrical equipment in the monitoring area, and a temperature sensor is arranged on the heating element of the electrical equipment. The background server obtains the actual current detected by the current sensor and the actual temperature detected by the temperature sensor, and determines whether there is a fire risk in the monitoring area based on the actual current and the actual temperature. When it is determined that there is a fire risk, the camera is called to shoot the monitoring image, and the light intensity at the shooting time is obtained. The monitoring image is recognized using the fire detection model, and the recognition process is corrected using the light intensity, actual current and actual temperature at the shooting time. In this way, the full-domain state perception of the fire is realized, and the accuracy of fire detection is improved. Compared with the smoke alarm, the camera can detect the fire in time when the fire just occurs, without waiting until the smoke concentration reaches the set threshold. Compared with the sensing area of ​​the temperature sensor, the shooting area of ​​the camera is relatively large, and fewer cameras can achieve blind-angle monitoring of the monitoring area, thereby improving the reliability of fire prevention and control.

[0047] Optionally, the above scheme obtains the actual current detected by the current sensor arranged on the electrical equipment and the actual temperature detected by the temperature sensor arranged on the heating element. By integrating these two types of data, comprehensive monitoring of the working status of the electrical equipment can be achieved. When the actual current is greater than the rated current and the actual temperature is greater than the tolerance temperature, the system can quickly determine that there is a fire risk, and this judgment basis is more accurate and reliable than a single sensor.

[0048] Compared with traditional smoke alarms, the above solution can issue an early warning at the beginning of a fire, that is, when the current and temperature are abnormal, without waiting until the smoke concentration reaches the set threshold, thereby greatly shortening the fire response time. After determining that there is a fire risk, the system will intelligently select the camera closest to the risk area as the target camera based on the layout of the temperature sensor and the layout of each camera. Compared with the limited sensing area of ​​the temperature sensor, the camera's shooting area is larger, and a small number of cameras can be reasonably arranged to achieve full coverage of the monitoring area. This not only reduces the cost of monitoring, but also improves the reliability of fire prevention and control. While controlling the target camera to capture the monitoring image, the system also obtains the light intensity information at the time of shooting. This information is then used to correct the recognition process of the fire detection model to eliminate the impact of light changes on the image recognition results.

[0049] By combining the light intensity, actual current and actual temperature at the time of shooting to correct the recognition process of the fire detection model, the system can more accurately identify fire characteristics and reduce the occurrence of false alarms and missed alarms. The backend server uses data processing technology to perform real-time analysis on the acquired multi-source data, including current, temperature, images and light intensity, to achieve intelligent assessment of fire risks.

[0050] Based on the data analysis results, the system can output accurate fire detection results and provide intelligent decision support for subsequent emergency response. For example, the system can automatically trigger the corresponding early warning mechanism or emergency response process according to the fire risk level.

[0051] The above solution is applicable to various monitoring scenarios, whether it is a home, commercial building or industrial facility, and global situational awareness can be achieved by simply placing current sensors, temperature sensors and cameras at the corresponding locations.

[0052] As the monitoring area expands or the monitoring needs increase, the system can easily expand the monitoring range and functions by increasing the number of sensors and cameras. At the same time, the data processing capacity of the background server can also be further improved by upgrading the hardware or optimizing the algorithm.

[0053] In summary, the global situation awareness method based on data processing provided in the embodiment of the present application realizes early detection, precise positioning and efficient monitoring of fire risks in the monitoring area by integrating multi-source sensor data, intelligently selecting target cameras, correcting light intensity, and processing and analyzing big data. This method not only improves the accuracy and reliability of fire detection, but also provides powerful intelligent decision-making support for subsequent emergency response.

[0054] In a possible implementation, S105, the backend server uses the fire detection model to identify the monitoring image, and uses the light intensity, actual current and actual temperature at the time of shooting to correct the identification process, and outputs the fire detection result, which specifically includes: S201. The backend server generates input features according to the monitoring image and the light intensity at the time of shooting, and generates classification features according to the actual current and the actual temperature.

[0055] The backend server uses the image conversion function to process the monitoring image and generate image features. The light intensity conversion function is used to process the light intensity to generate light features. The sum of the image features and the light features is calculated to obtain the input features. The actual current and actual temperature are converted to obtain classification features.

[0056] The input features are in an m×n matrix, and the classification features are in a 1×n matrix, where m and n are positive integers.

[0057] S202, the backend server concatenates the input features and the classification features to generate concatenated features, uses an encoder to encode the concatenated features to output encoded features, uses a decoder to decode the classification data in the encoded features, and determines the fire detection results.

[0058] The backend server concatenates the input features and classification features along the row direction to generate concatenated features, and the dimension of the concatenated features is (m+1)×n.

[0059] The encoder includes multiple levels of encoding modules. The first-level encoding module encodes the splicing features and outputs them. The next-level encoding module encodes the output data of the previous-level encoding module and outputs them. The last-level encoding module encodes the output data of the penultimate-level encoding module and outputs the encoding features.

[0060] The dimension of the coded feature is the same as that of the concatenated feature, which is (m+1) × n. The last row of data in the coded feature is extracted and decoded using the encoder to obtain the fire detection result.

[0061] The decoder includes a linear processing module and a nonlinear processing module. The linear processing module performs linear processing on the data, and the nonlinear processing module performs nonlinear processing on the data. Combining the linear processing module and the nonlinear processing module to process the classified data in the coding feature can improve the decoding accuracy.

[0062] In the above technical solution, input features are generated according to the monitoring image and the light intensity at the time of shooting, the light intensity and the monitoring image are fused, and classification features are generated according to the actual current and the actual temperature. In this way, the classification features are initialized using the actual current and the actual temperature, and the input features and the classification features are spliced ​​to obtain spliced ​​features, so that the spliced ​​features contain more information, and fire identification is performed based on the spliced ​​features, which can improve the accuracy of fire detection results.

[0063] Optionally, input features are first generated based on the surveillance image and the light intensity at the time of shooting. By integrating the light intensity information directly into the surveillance image, the system can more accurately capture the fire features in the image. For example, when the light intensity is low, the system can automatically adjust the image brightness or contrast to ensure that the fire features are clearly discernible. This fusion method effectively eliminates the impact of light changes on image recognition results and improves the adaptability and accuracy of the fire detection model under different lighting conditions.

[0064] In the process of generating input features, the monitoring image is processed in blocks and the location information of each image block is combined. This processing method not only reduces the amount of data processing and improves the algorithm calculation efficiency, but also enables the system to analyze the fire characteristics in the image more finely. For example, by identifying the flame shape, color and other features in the image block and combining its location information, the system can more accurately determine the location and spread trend of the fire.

[0065] At the same time, the system generates classification features based on the actual current and actual temperature. These physical quantities, as important indicators of fire occurrence, provide additional judgment basis for the fire detection model. For example, when the actual current rises abnormally and the actual temperature exceeds the tolerance temperature of the electrical equipment, the system can quickly determine that there is a fire risk and incorporate this information into the classification features.

[0066] By using actual current and actual temperature to initialize the classification features, the system can capture fire features earlier in the fire detection process. This initialization method makes the classification features highly discriminative at the early stage of a fire, helping the system to more accurately identify fire events.

[0067] After splicing the input features and classification features, the system obtains spliced ​​features that contain more information. These features not only include the fire features in the monitoring image, but also incorporate physical quantity information such as light intensity, actual current, and actual temperature. This fusion of multi-source information enables the system to understand the monitoring scene more comprehensively and improve the accuracy of fire detection.

[0068] Compared with single features, spliced ​​features have higher robustness and accuracy in the fire detection process. For example, when the image is blurred or the lighting is insufficient, the system can rely on the current and temperature information in the classification features to assist in judging the fire event; conversely, when the current and temperature changes are not obvious, the system can rely on the image information in the input features to identify the fire characteristics.

[0069] After encoding the splicing features using the encoder, the system obtains the coded features containing key information. The encoder fully captures the key information in the splicing features through a multi-level encoding module structure and effectively suppresses noise interference. This information extraction method enables the system to more accurately identify fire events.

[0070] The decoder decodes the classification data in the coded features to determine the fire detection results. The decoder achieves accurate decoding of the coded features through the combination of linear processing layers and nonlinear processing layers. This decoding method enables the system to output fire detection results more accurately and provide strong support for subsequent emergency response.

[0071] In summary, through the above-mentioned fire detection model and the correction mechanism of its identification process, the global situation awareness method based on data processing provided by the embodiment of the present application significantly improves the accuracy of fire detection results. This method realizes accurate identification and efficient response to fire risks in the monitoring area by integrating multi-source information, using light intensity correction, and adopting encoding and decoding structures.

[0072] In a possible implementation, S201, the backend server generates input features according to the monitoring image and the light intensity at the time of shooting, specifically including: S301. The backend server divides the monitoring image into blocks to obtain a plurality of image blocks and the position of each image block, and determines the monitoring sub-area corresponding to each image block according to the shooting parameters of the camera.

[0073] As an example, the monitoring image is divided into 2×3 image blocks, with 3 image blocks in each row and 2 image blocks in each column. The positions of the 3 image blocks in the first row are position 1, position 2, and position 3, and the positions of the 3 image blocks in the second row are position 4, position 5, and position 6.

[0074] The camera's shooting parameters include internal and external parameters. The shooting area is determined based on the camera's internal and external parameters, and the shooting area is divided into blocks to obtain the sub-area corresponding to each image block. For example, if the surveillance image is divided into 2×3 areas, the shooting area can be divided into 2×3 shooting sub-areas, and the corresponding relationship between each image block and the shooting sub-area is established.

[0075] S302: The backend server obtains the light intensity of each monitoring sub-area at the shooting time, and uses the light intensity of each monitoring sub-area at the shooting time as the light intensity of the corresponding image block.

[0076] As an example, the background server sends a meteorological data request to the meteorological server to obtain the light intensity and light angle of the monitored area at the time of shooting. The glass position of the monitored area is obtained, and the illuminated area and the unilluminated area are determined according to the glass position and angle of the monitored area. The light intensity of the illuminated area is set to the light intensity returned by the meteorological server, and the light intensity of the unilluminated area is set to the lighting intensity.

[0077] If the monitoring sub-area is located in an illuminated area, the light intensity of the monitoring sub-area is the light intensity returned by the meteorological server. If the monitoring sub-area is located in an unilluminated area, the light intensity of the monitoring sub-area is the intensity of the lighting lamp. If part of the monitoring sub-area is located in an illuminated area and the other part of the monitoring sub-area is located in a non-illuminated area, the average of the light intensity and the intensity of the lighting lamp is used as the light intensity of the monitoring sub-area.

[0078] As another example, a light intensity sensor is laid in the monitoring area, and the light intensity sensor detects the light intensity of the area. If the monitoring sub-area is within the detection range of one light intensity sensor, the light intensity of the monitoring sub-area is the light intensity sensed by the light intensity sensor. If the monitoring sub-area is within the detection range of two light intensity sensors, the light intensity of the monitoring sub-area is the average of the light intensities sensed by the two light intensity sensors. If the monitoring sub-area is within the detection range of three light intensity sensors, the light intensity of the monitoring sub-area is the average of the light intensities sensed by the three light intensity sensors.

[0079] S303, the background server fuses each image block, the position of each image block and the light intensity of each image block to obtain fused data of each image block; and splices the fused data of multiple image blocks to generate input features.

[0080] The backend server converts each image block into an image vector, converts the position of each image block into a position vector, converts the illumination intensity of each image block into a light intensity vector, calculates the sum of the image vector, the position vector and the light intensity vector, and obtains the fusion vector of each image block. The fusion vectors of each image block are concatenated to generate input features. For example, the dimension of the fusion vector of each image block is n×1, and each surveillance image is divided into m image blocks. The fusion vectors of the m image blocks are concatenated and transposed along the row to generate input features of size m×n.

[0081] In the above technical solution, the monitoring image is divided into multiple image blocks, and the position and light intensity of each image block are obtained. The image block, the position of the image block and the light intensity of the image block are fused with each image block as a unit to obtain the fusion data of the image block. The fusion data of each image block is then spliced ​​to generate input features. Compared with processing the entire image as a unit, the amount of data processing can be reduced and the algorithm calculation efficiency can be improved.

[0082] Optionally, the monitoring image is first processed into blocks to obtain multiple image blocks and specific location information of each image block. This step not only converts complex image data into small blocks that are easier to process, but also retains the spatial position relationship of the image blocks in the original image.

[0083] Next, the monitoring sub-area corresponding to each image block is determined based on the camera’s shooting parameters (such as focal length, viewing angle, etc.). This mapping relationship provides an accurate spatial reference for subsequent illumination intensity acquisition and feature fusion.

[0084] By processing surveillance images in blocks, the originally huge image data can be broken down into multiple small units for processing. This method significantly reduces the amount of data processed at a time, reduces the computational complexity, and thus improves the computational efficiency of the algorithm.

[0085] For each monitored sub-area corresponding to each image block, its light intensity information at the time of shooting is obtained. This step ensures the accurate correspondence between light intensity and image content, providing a reliable data basis for subsequent light correction.

[0086] After obtaining each image block, its position and the corresponding light intensity, this information is fused to generate fused data for each image block. This fusion process not only retains the visual features in the image block, but also incorporates the spatial position information and light conditions, providing more comprehensive information support for subsequent fire detection.

[0087] After splicing the fused data of multiple image blocks, the final input feature is generated. This input feature not only contains rich visual information in the monitoring image, but also incorporates multi-dimensional information such as light intensity and image block position, providing more comprehensive input data for the fire detection model.

[0088] Compared with the method of processing the entire image as a unit, the amount of data processed at a single time can be significantly reduced through steps such as image segmentation, light intensity acquisition, and fusion data splicing. This block processing method not only reduces the computational complexity, but also improves the computational efficiency of the algorithm, allowing the system to respond to fire detection tasks more quickly.

[0089] In summary, the global situation awareness method based on data processing provided by the embodiment of the present application significantly optimizes the generation process of input features through technical means such as monitoring image block processing, light intensity acquisition and image block fusion. This method not only reduces the amount of data processing and improves computing efficiency, but also provides more comprehensive and accurate input data for the fire detection model, thereby improving the accuracy and reliability of the fire detection algorithm.

[0090] In a possible implementation, S303, the backend server fuses each image block according to the position of each image block and the illumination intensity of each image block to obtain fused data of each image block, specifically including: S401. The background server uses multiple convolution kernels to perform multiple convolution processes on the image block to obtain an image vector of the image block.

[0091] Among them, multiple convolution kernels are used to perform multiple convolution processes on the image block, and each convolution process obtains an element of the image vector of the image block. After multiple convolution processes, multiple elements of the image vector of the image block can be obtained.

[0092] S402: The backend server processes the position of the image block using a position conversion function to obtain a position vector of the image block.

[0093] The position conversion function includes multiple position conversion sub-functions, each of which converts the position of the image block into an element of the position vector of the image block. The position of the image block is processed multiple times using multiple position conversion sub-functions to obtain multiple elements of the position vector of the image block.

[0094] The dimension of the image vector of the image block is the same as the dimension of the position vector of the image block. That is, the number of convolution kernels is the same as the number of position conversion subfunctions, so the number of convolution calculations of the image block is the same as the number of position conversion processing of the image block. For example: if the dimension of the image vector of the image block is n×1, the dimension of the position vector of the image block is also n×1.

[0095] S403: The background server uses the illumination conversion function to process the illumination intensity of the image block to obtain an illumination vector of the image block.

[0096] The illumination conversion function includes multiple illumination conversion sub-functions, each of which converts the illumination intensity to obtain an element of the illumination vector of the image block. The illumination intensity is converted multiple times using multiple illumination conversion sub-functions to obtain multiple elements of the illumination vector of the image block.

[0097] The dimension of the image vector of the image block is the same as the dimension of the illumination vector of the image block, and the number of convolution kernels is the same as the number of illumination conversion sub-functions, so the number of convolution calculations performed on the image block is the same as the number of illumination intensity conversions. For example: if the dimension of the image vector of the image block is n×1, the dimension of the illumination vector of the image block is n×1.

[0098] S404: The backend server calculates, for each image block, the sum of the image vector of the image block, the position vector of the image block, and the illumination vector of the image block to obtain a fusion vector of each image block.

[0099] For each image block, the background server calculates the sum of the i-th element of the image vector of the image block, the i-th element of the position vector of the image block, and the i-th element of the illumination vector of the image block as the i-th element of the fusion vector of the image block. Each element in the fusion vector of the image block is obtained by traversing i from 1 to n.

[0100] In the above technical solution, the image block, the position of the image block and the illumination intensity of the image block are converted into vectors of the same dimension, and the sum of the image vector, the position vector and the illumination vector is calculated to achieve the fusion of the position information and the illumination information into the image, so that the fusion vector contains more information, thereby improving the accuracy of fire identification.

[0101] Optionally, multiple convolution kernels are used to perform multiple convolution processing on the image block to obtain an image vector of the image block. As a feature extractor, the convolution kernel can automatically learn key features in the image, such as the shape, color, texture, etc. of the flame. Through multiple convolution processing, the fire features in the image block are effectively extracted and encoded into an image vector, providing a visual information basis for subsequent feature fusion.

[0102] The position of the image block is processed using the position transformation function to obtain the position vector of the image block. The position vector encodes the spatial position information of the image block in the original image, which is crucial for understanding the location and spread trend of the fire. By vectorizing the position information, the spread path of the fire and the potential risk area can be judged more accurately.

[0103] The illumination intensity of the image block is processed using the illumination conversion function to obtain the illumination vector of the image block. As an important factor affecting the visual characteristics of the image, the change of illumination intensity will directly affect the recognition effect of fire characteristics. By vectorizing the illumination intensity, the recognition threshold of the fire characteristics in the image can be automatically adjusted to improve the recognition accuracy under different illumination conditions.

[0104] For each image block, the sum of its image vector, position vector and illumination vector is calculated to obtain the fusion vector of each image block. This fusion process closely combines visual features, spatial position information and illumination conditions to form a multi-dimensional feature representation containing rich information. The fusion vector not only retains the original visual features in the image block, but also incorporates the influence of position information and illumination conditions on fire characteristics, providing a more comprehensive and accurate information basis for subsequent fire identification.

[0105] By fusing multi-source information into a fusion vector, we can more comprehensively understand the characteristics of fires in the monitoring scene. For example, when the light intensity is low, we can rely on the flame shape and color features in the image vector to identify the fire; at the same time, the integration of position vectors and light vectors helps the system to more accurately determine the location and spread of the fire. This fusion of multi-source information significantly enhances the accuracy of fire identification and improves the system's adaptability in different environments.

[0106] The image vector, position vector, and illumination vector contained in the fusion vector together constitute a multi-dimensional feature representation containing rich information. This feature representation not only improves the accuracy of fire identification, but also enhances the system's adaptability to complex monitoring scenarios. For example, when there are multiple potential fire sources in the monitoring area, the system can accurately distinguish different fire characteristics and avoid false alarms and missed alarms.

[0107] By processing the monitoring image in blocks and generating fusion vectors, the accuracy of fire identification can be improved while maintaining computational efficiency. Compared with the method of processing the entire image as a unit, the block processing method significantly reduces the amount of data processed at a time and improves the algorithm's computational efficiency; at the same time, by fusing multi-source information to generate fusion vectors, the system can more accurately identify fire features and improve recognition accuracy.

[0108] In summary, through the image block fusion technology, the global situation awareness method based on data processing provided by the embodiment of the present application significantly improves the accuracy of fire identification. Through multi-source information vectorization, multi-source information fusion and feature enhancement, etc., it realizes the comprehensive and accurate identification of fire characteristics in the monitoring scene, providing strong support for subsequent emergency response.

[0109] In a possible implementation, S202, the backend server generates classification features according to the actual current and the actual temperature, specifically including: S501. The backend server uses a current conversion function to process the actual current to obtain a current vector, and uses a temperature conversion function to process the actual temperature to obtain a temperature vector.

[0110] The current conversion function includes multiple current conversion sub-functions, one current conversion sub-function processes the actual current to obtain one element of the current vector, and multiple current conversion sub-functions are used to process the actual current multiple times to obtain multiple elements of the current vector.

[0111] The dimension of the current vector is the same as the dimension of the image vector of the image block. The number of convolution kernels is the same as the number of current conversion sub-functions, so the number of convolution calculations performed on the image block is the same as the number of actual current conversions. For example: if the dimension of the image vector of the image block is n×1, then the dimension of the current vector is also n×1.

[0112] The temperature conversion function includes multiple temperature conversion sub-functions. One temperature conversion sub-function processes the actual temperature to obtain an element of the temperature vector. Multiple temperature conversion sub-functions are used to process the actual temperature multiple times to obtain multiple elements of the temperature vector.

[0113] The dimension of the temperature vector is the same as the dimension of the image vector of the image block. The number of convolution kernels is the same as the number of temperature conversion subfunctions, so the number of convolution calculations performed on the image block is the same as the number of actual temperature conversions. For example: if the dimension of the image vector of the image block is n×1, then the dimension of the temperature vector is also n×1.

[0114] S502: The backend server obtains a classification position according to the sorting results of the multiple image blocks and the classification features, and processes the classification position using a position conversion function to obtain a classification position vector.

[0115] Among them, the classification features and multiple image blocks are numbered by position. In order to ensure the continuity of the image blocks, the classification features are arranged at the head, and the multiple image blocks are sorted according to their positions in the image. For example: the monitoring image is divided into 2×3 image blocks, the classification position is set to position 0, the position of the image block in the first row and the first column is set to position 1, the position of the image block in the first row and the second column is set to position 2, the position of the image block in the first row and the third column is set to position 3, the position of the image block in the second row and the first column is set to position 4, the position of the image block in the second row and the second column is set to position 5, and the position of the image block in the second row and the third column is set to position 6.

[0116] One position conversion sub-function converts the classification position to obtain one element of the classification position vector, and multiple position conversion sub-functions convert the classification position multiple times to obtain multiple elements of the classification position vector.

[0117] S503: The backend server superimposes the current vector, the temperature vector and the classification position vector to generate classification features.

[0118] The backend server calculates the sum of the i-th element of the current vector, the i-th element of the temperature vector, and the i-th element of the classification position vector as the i-th element of the classification feature. Each element in the classification feature is obtained by traversing i from 1 to n.

[0119] In the above technical solution, the actual current and actual temperature are converted into vectors, the position of the classification feature is determined according to the classification feature and the sorting results of multiple image blocks, and the classification feature is initialized based on the temperature vector, current vector and classification position feature, so that the initial value of the classification feature contains more information, thereby improving the monitoring accuracy when performing fire monitoring based on the classification feature.

[0120] Optionally, the actual current is processed using a current conversion function to obtain a current vector. This step converts the continuously changing current value into a vector representation with clear physical meaning, which is convenient for subsequent feature fusion and calculation. The actual temperature is processed using a temperature conversion function to obtain a temperature vector. Similarly, the temperature vector maps the temperature value to a high-dimensional space, retaining the trend and characteristics of temperature changes, and providing important thermal information for fire monitoring.

[0121] By converting current and temperature into vector form, these multi-source information can be processed more flexibly. The vector representation not only retains the physical meaning of the original data, but also facilitates mathematical operations and feature fusion, laying the foundation for subsequent classification feature generation.

[0122] The classification position is obtained based on the classification features and the sorting results of multiple image blocks. This step combines the classification features with the spatial position information of the image blocks and determines the specific position of the classification features in the monitoring scene through the sorting results.

[0123] The classification position is processed using the position conversion function to obtain the classification position vector. The classification position vector encodes the spatial position information of the classification feature in the monitoring scene, providing an important spatial reference for subsequent fire monitoring.

[0124] The introduction of classification position vectors enables classification features to include not only physical quantity information such as current and temperature, but also spatial location information. This multi-dimensional feature representation helps the system to more accurately understand the location and spread of fires, and improve the accuracy and timeliness of fire monitoring.

[0125] The current vector, temperature vector and classification position vector are superimposed to generate classification features. This step integrates multi-source information into a classification feature vector containing rich information, providing a comprehensive feature representation for subsequent fire monitoring.

[0126] The classification features initialized based on temperature vector, current vector and classification position features have already included information on current, temperature and spatial position. This initialization method enables the classification features to more accurately reflect the occurrence and development trend of fires in the subsequent monitoring process.

[0127] During the fire monitoring process, the system can determine whether a fire has occurred based on the changing trends and feature patterns of the classification features. Since the classification features contain richer information, the system can more accurately identify fire features, reduce the occurrence of false alarms and missed alarms, and improve the accuracy of fire monitoring.

[0128] In summary, through the classification feature generation technology, the fire monitoring system provided by the embodiment of the present application significantly improves the monitoring accuracy. This technology realizes comprehensive and accurate identification of fire characteristics through means such as multi-source information vectorization integration, introduction of classification position vectors, and generation of classification features, providing strong support for subsequent emergency response.

[0129] In a possible implementation, S202, the backend server encodes the splicing feature and outputs the encoded feature, specifically including: S601. Use the first-level encoding module to encode the splicing features, use the second-level encoding module to process the encoding features output by the first-level encoding module, use the third-level encoding module to process the encoding features output by the second-level encoding module, until the last-level encoding module processes the encoding features output by the penultimate-level encoding module.

[0130] Each encoding module includes a multi-head attention mechanism module and a feedforward neural network module. The multi-head attention mechanism module includes a multi-head attention mechanism layer and a residual normalization layer, and the feedforward neural network module includes a feedforward neural network layer and a residual normalization layer.

[0131] like Figure 3 As shown, the encoder includes multiple cascaded encoding modules, the output end of the encoding module at the first level is connected to the input end of the encoding module at the second level, the output end of the encoding module at the second level is connected to the input end of the encoding module at the third level, and so on, until the output end of the encoding module at the second-to-last level is connected to the input end of the encoding module at the last level.

[0132] The first-level encoding module processes the splicing features. More specifically, the splicing features are first processed by the multi-head attention mechanism layer and then output the first intermediate data. The first intermediate data enters the residual normalization layer for processing and outputs the second intermediate data. The second intermediate data enters the feedforward neural network layer for processing and outputs the third intermediate data. The third intermediate data is processed by the residual normalization layer and then outputs the fourth intermediate data. The fourth intermediate data is used as the data output by the first encoding module.

[0133] The residual normalization layer includes the residual layer and the normalization layer. The input data is normalized before the residual calculation.

[0134] The second-level encoding module encodes the encoding features output by the first-level encoding module. The encoding process of the second-level encoding module is the same as that of the first-level encoding module, which will not be repeated here. After multiple encoding modules perform multiple encoding processes, the encoding features are output.

[0135] In the above technical solution, the encoder includes multiple cascaded encoding modules, each encoding module includes a multi-head attention mechanism layer, a feedforward neural network layer and a residual normalization layer. Since the encoding module includes a multi-head attention mechanism layer, it can pay attention to the fusion vector itself and the mutual influence between adjacent fusion vectors, so that the encoding features contain more information and the accuracy of fire detection is improved.

[0136] Optionally, the encoder in the above technical solution is composed of multiple cascaded encoding modules, each of which processes the input features in turn. This cascade structure allows the feature information to be continuously refined and enhanced during the layer-by-layer transmission process, which helps to extract deeper feature representations.

[0137] Through the cascade processing of multi-level encoding modules, the complex patterns and associations in the spliced ​​features can be gradually captured. Each level of encoding module further optimizes the feature representation based on the previous level, thereby improving the quality and effectiveness of the features.

[0138] Each encoding module contains a multi-head attention mechanism module, which can simultaneously focus on the fusion vector itself and the mutual influence between adjacent fusion vectors by introducing multiple parallel attention heads. This mechanism enables a more comprehensive understanding of the correlation between features and captures more subtle feature changes. The multi-head attention mechanism layer is followed by a residual normalization layer. Through residual connection and normalization processing, the gradient vanishing problem is effectively alleviated, and the stability and training efficiency of the model are improved.

[0139] The feedforward neural network module further enhances the expressiveness of features through nonlinear transformation. The feedforward neural network layer further processes the output of the multi-head attention mechanism layer to extract higher-level feature representations. Similarly, the feedforward neural network layer also includes a residual normalization layer to ensure the stability and effectiveness of feature information during transmission.

[0140] The multi-head attention mechanism module and the feedforward neural network module work together to complete the deep encoding of the spliced ​​features. The multi-head attention mechanism module is responsible for capturing the correlation between features, while the feedforward neural network module is responsible for further refining and enhancing feature representation. This synergy enables the system to extract richer and more effective feature information.

[0141] In addition, since the encoding module includes a multi-head attention mechanism layer, the system can simultaneously focus on the fusion vector itself and the mutual influence between adjacent fusion vectors. This mechanism allows the encoded features to contain more information about the relationship between features, improving the richness and effectiveness of the features.

[0142] Based on the coding features that contain rich information, the system can more accurately identify fire features. During the fire monitoring process, the system can determine whether a fire has occurred based on the changing trends and feature patterns of the coding features. Since the coding features contain more information about the correlation between features, the system can more keenly capture the subtle changes in fire features, thereby improving the accuracy and timeliness of fire detection.

[0143] In summary, the fire detection system proposed in the embodiment of the present application significantly improves the accuracy of fire detection by using a multi-level encoding module to perform deep encoding processing on the splicing features. The encoder structure in this technical solution is unique, integrating the multi-head attention mechanism with the feedforward neural network, and combined with the residual normalization layer, it realizes the fine encoding and efficient processing of the splicing features. This technical solution not only improves the quality and effectiveness of the features, but also provides more accurate and timely decision support for fire detection.

[0144] In a possible implementation, S202, using a decoder to decode the coded feature to determine the fire detection result, specifically includes: S602. Use the first fully connected layer to linearize the encoded features, use the activation function layer to nonlinearly process the output features of the first fully connected layer, use the second fully connected layer to linearize the output features of the activation function layer, and use the residual layer to superimpose the output features of the second fully connected layer and the output features of the activation function layer and then output them.

[0145] Among them, Figure 4As shown, the decoder includes a first fully connected layer, an activation function layer, a second fully connected layer, and a residual layer. The output end of the first fully connected layer is connected to the input end of the activation function layer, the output end of the activation function layer is connected to the input end of the second fully connected layer, and the input end of the residual layer is connected to the output end of the second fully connected layer.

[0146] The first fully connected layer is used to linearize the encoding features and output the fifth intermediate data. The activation function layer is used to nonlinearly process the fifth intermediate data output by the first fully connected layer and output the sixth intermediate data. The second fully connected layer is used to linearize the sixth intermediate data output by the activation function layer and output the seventh intermediate data. The residual layer is used to superimpose the seventh intermediate data output by the second fully connected layer and the sixth intermediate data output by the activation function layer and then output them. A normalized exponential layer (softmax) can also be added after the residual layer to output the probability of each category.

[0147] In the above technical solution, the decoder includes a fully connected layer for linear processing and an activation function layer for nonlinear processing, which can improve the decoding performance of the decoder and improve the accuracy of fire monitoring.

[0148] Optionally, the decoder is mainly composed of a first fully connected layer, an activation function layer, a second fully connected layer, and a residual layer. This structure combines linear processing and nonlinear processing to fully extract effective information from the encoded features and make accurate fire judgments based on this.

[0149] Among them, for the first fully connected layer, it linearizes the encoded features and maps them to a higher-dimensional space so that the subsequent nonlinear processing can better capture the complex relationship between features. Through linear transformation, the first fully connected layer effectively retains the key information in the encoded features and provides a good input basis for subsequent nonlinear processing.

[0150] As for the activation function layer, the output data of the first fully connected layer is processed nonlinearly, and nonlinear factors are introduced to enable the decoder to learn more complex feature patterns. The activation function layer enhances the expressive power of the decoder by introducing nonlinear factors, enabling it to handle more complex fire monitoring tasks. At the same time, nonlinear processing also helps the decoder capture subtle changes in the coding features and improve the sensitivity of fire monitoring.

[0151] As for the second fully connected layer, the output data of the activation function layer is linearized, and the features after nonlinear processing are mapped back to the original space or a more appropriate decision space. The second fully connected layer integrates the features after nonlinear processing into the final decision basis through linear transformation. This step ensures that the decision results output by the decoder have both the flexibility brought by nonlinear processing capabilities and the stability and interpretability brought by linear transformation.

[0152] In addition, for the residual layer, the output features of the second fully connected layer and the output features of the activation function layer are superimposed to form the final decoded output. By introducing residual connections, the residual layer effectively alleviates the common gradient vanishing problem in deep networks and improves the training stability and convergence speed of the model. At the same time, the residual connection also enables the decoder to better retain the original feature information and improve the accuracy of fire monitoring.

[0153] Through the synergy of the above components, the decoder achieves efficient decoding of the coded features. Specifically, the decoder effectively extracts the effective information in the coded features by fusing linear processing with nonlinear processing, and makes accurate fire judgments based on this. This processing method not only improves the expressiveness of the decoder, but also enhances its generalization ability and robustness. Since the decoder can more accurately capture the key information in the coded features and make decisions based on it, the accuracy of fire monitoring is improved. This is of great significance for fire warning and emergency response in practical application scenarios.

[0154] In summary, the decoder structure in the fire monitoring system proposed in the embodiment of the present application effectively improves the decoding performance of the decoder and the accuracy of fire monitoring through carefully designed components and synergy mechanisms. This technical solution provides a new and efficient solution for the field of fire monitoring.

[0155] Some other embodiments of the present application provide a global situation awareness method based on data processing, the method comprising the following steps: S701. The backend server obtains a circuit topology diagram of the monitoring area, and establishes a power model in the power simulation software based on the circuit topology diagram.

[0156] Among them, the background server obtains the circuit topology diagram of the monitoring area based on the monitoring area design data, and establishes an electric model corresponding to the circuit topology diagram of the monitoring area in the electric power simulation software, so that the simulation software can be used to simulate the working temperature of each electrical equipment in the monitoring area.

[0157] S702: The backend server performs simulation analysis on the power model in the power simulation software to obtain the position information of the heating element and arranges the temperature sensor according to the position information of the heating element.

[0158] The backend server runs the power simulation software, uses the power simulation software to simulate and analyze the power model, and obtains the operating temperature of each electrical device. According to the operating temperature of each electrical device, a heating element is selected from each electrical device to obtain the location information of the heating element. After obtaining the location information of the heating element, the temperature sensor is arranged according to the location information of the heating element.

[0159] Compared with the arrangement of temperature sensors based on experience, by establishing an electric model corresponding to the electric topology diagram of the monitoring area in the electric power simulation software, determining the operating temperature of each electrical equipment through simulation analysis, selecting the heating element based on the operating temperature, and arranging temperature sensors on the heating element, the temperature of the heating element can be monitored more accurately and abnormalities can be detected in time.

[0160] Optionally, the above scheme first constructs a power network structure model of the area by acquiring a circuit topology diagram of the monitoring area. Subsequently, an accurate power model is established based on the topology diagram in the power simulation software. By simulating and analyzing the power model, the working status of each electrical device and the location of its heating element can be accurately predicted. Finally, according to the simulation results, multiple temperature sensors are arranged on the heating element to realize real-time monitoring of the device temperature.

[0161] By obtaining the circuit topology of the monitoring area, the basic structure of the power network was constructed. Based on the topology, a power model was established in the power simulation software, providing a basis for subsequent simulation analysis. This step ensures the accuracy and completeness of the power model and provides a scientific basis for the subsequent layout of temperature sensors.

[0162] The power model is simulated and analyzed in the power simulation software to predict the working status of each electrical device and the location of its heating elements. Through simulation analysis, the location of the heating element can be accurately identified, avoiding the blindness of the traditional method of arranging temperature sensors based on experience, and improving the accuracy and efficiency of monitoring.

[0163] Based on the location information of the heating element obtained through simulation analysis, multiple temperature sensors are arranged on the heating element to achieve real-time monitoring of the equipment temperature. By directly arranging temperature sensors on the heating element, the temperature changes of the equipment can be monitored more accurately, abnormal conditions can be discovered in time, and strong support can be provided for the prevention of fire risks.

[0164] By determining the location of the heating element through simulation analysis and arranging the temperature sensor on it, the temperature change of the equipment can be monitored more accurately. Compared with the method of arranging temperature sensors based on experience, this technical solution significantly improves the accuracy of monitoring and reduces the occurrence of false alarms and missed alarms.

[0165] The above technical solution determines the positions of all heating elements at one time through simulation analysis, avoiding the process of multiple attempts and adjustments required in traditional methods. This not only improves monitoring efficiency, but also reduces manpower and time costs.

[0166] In the case of complex monitoring area environment and numerous electrical equipment, it is difficult to accurately arrange temperature sensors using traditional methods. However, this technical solution can easily cope with complex environments and ensure accurate arrangement of temperature sensors through simulation analysis.

[0167] This technical solution combines power simulation technology and temperature sensing technology to achieve intelligent monitoring of the temperature of electrical equipment. This not only improves the accuracy and efficiency of monitoring, but also provides strong support for subsequent fire risk assessment and early warning.

[0168] By monitoring the temperature of the equipment in real time, this technical solution can promptly detect abnormal conditions of the equipment and provide a scientific basis for the maintenance and management of the equipment. This helps to extend the service life of the equipment, reduce maintenance costs, and improve the safety and reliability of the equipment.

[0169] S703: The backend server obtains the actual current detected by the current sensor on the electrical device and the actual temperature detected by the temperature sensor arranged on the heating element.

[0170] S704: The backend server obtains the rated current of the electrical device and the tolerable temperature of the electrical device.

[0171] Among them, when electrical equipment operates at a current higher than the rated current for a long time, it is easy to cause damage to the electrical equipment. When electrical equipment operates at a temperature higher than the tolerance temperature for a long time, it is easy to cause the temperature to be too high and the insulation layer to melt, which in turn causes a short circuit and fire. By obtaining the rated current and tolerance temperature of the electrical equipment, it is possible to determine whether there is a risk of fire based on the rated current and tolerance temperature.

[0172] In some examples, obtaining the tolerance temperature of the electrical equipment specifically includes: S81. The background server obtains actual currents detected by a current sensor at multiple moments and actual temperatures detected by a temperature sensor at multiple moments.

[0173] Among them, after the current sensor collects the actual current of the electrical equipment at each moment, it uploads the actual current at each moment to the background server. After the temperature sensor collects the actual temperature of the electrical equipment at each moment, it uploads the actual temperature at each moment to the background server. The background server saves the actual current and actual temperature at each moment received.

[0174] S82. The backend server uses a tolerance temperature prediction model to process actual currents at multiple moments and actual temperatures at multiple moments, and outputs the tolerance temperature of the electrical equipment.

[0175] Among them, the withstand temperature of the insulation layer is lower than that of the conductive metal. Therefore, the withstand temperature of electrical equipment is mainly determined by the insulation layer. The performance of the insulation layer will change with the increase of usage time.

[0176] The actual current at multiple test moments, the actual temperature at multiple test moments and the tolerance temperature at multiple test moments are obtained by testing the electrical equipment. The actual current at multiple test moments, the actual temperature at multiple test moments and the tolerance temperature at multiple test moments are regressed and analyzed using a regression model to obtain a tolerance temperature prediction model.

[0177] The background server obtains the actual temperature at multiple moments collected by the temperature sensor, and the background server also obtains the actual current at multiple moments collected by the current sensor, inputs the actual temperature at multiple moments and the actual current at multiple moments into the tolerance temperature prediction model to obtain the tolerance temperature at the current moment.

[0178] By obtaining the actual temperature at multiple moments and the actual current at multiple moments, the actual temperature at multiple moments and the actual current at multiple moments are input into the tolerance temperature prediction model for prediction, and the tolerance temperature is updated in real time. Compared with using a fixed tolerance temperature, it can adapt to the situation where the performance of electrical components changes with the increase of usage time, so that fire risks can be discovered in time.

[0179] Optionally, the core of the above solution is to use the temperature tolerance prediction model to process the actual current and actual temperature data of the electrical equipment at multiple times to dynamically predict and update the temperature tolerance of the equipment. This approach fully considers the performance changes that may occur in electrical components as they are used for a longer time, making the fire risk assessment more in line with the actual operating status of the equipment.

[0180] Among them, for current sensors and temperature sensors, the actual current and actual temperature data of electrical equipment at multiple times are collected respectively. These data provide rich input information for the tolerance temperature prediction model, enabling the model to more accurately capture the changing trend of equipment performance.

[0181] For the temperature tolerance prediction model, the actual current and actual temperature data at multiple moments are processed to output the temperature tolerance of the electrical equipment. By learning and analyzing historical data, the model can predict the temperature tolerance of the equipment under different working conditions in real time, thereby adapting to changes in equipment performance.

[0182] As electrical equipment is used for a longer time, its internal components may degrade in performance due to aging, wear, etc. This technical solution can accurately reflect changes in equipment performance by updating the tolerance temperature in real time, thereby avoiding risk assessment errors caused by fixed tolerance temperature.

[0183] Taking into account the actual current and actual temperature data at multiple times, the temperature tolerance prediction model can more comprehensively evaluate the operating status of the equipment. Compared with the single factor or fixed threshold evaluation method, this multi-dimensional and dynamic evaluation method can significantly improve the accuracy of fire risk assessment.

[0184] Since the tolerance temperature is updated in real time, the system can promptly detect fire risks caused by equipment performance degradation. Once the actual current or actual temperature approaches or exceeds the predicted tolerance temperature, the system can trigger an early warning mechanism to buy valuable time for fire prevention.

[0185] The above technical solution supports customized adjustments according to different types of electrical equipment and different working environments. By adjusting the parameters or structure of the temperature tolerance prediction model, it can be more adapted to the performance change characteristics of specific equipment, thereby enhancing the flexibility and applicability of the system.

[0186] By introducing the tolerance temperature prediction model, the above technical solution realizes the intelligent perception and evaluation of the performance changes of electrical equipment. This intelligent monitoring method not only improves the accuracy of fire risk assessment, but also provides data support for equipment maintenance and performance optimization.

[0187] In summary, the above technical solution significantly improves the accuracy and timeliness of fire risk assessment by introducing a tolerance temperature prediction model and using actual current and actual temperature data at multiple moments to predict and update the tolerance temperature of electrical equipment in real time. This technical solution provides a more intelligent and accurate solution for fire prevention and control of electrical equipment.

[0188] S705a: If the actual current is greater than the preset current difference threshold and the actual temperature is greater than the tolerance temperature, it is determined that there is a fire risk and the process proceeds to S706.

[0189] S705b. If it is determined that the actual current is less than or equal to the set current, but the actual temperature is greater than the set temperature, continue to monitor the actual temperature. If the temperature rise rate is greater than the preset rate, it is determined that there is a fire risk and enter S706.

[0190] S705c: If it is determined that the actual current is less than or equal to the set current, and the actual temperature is less than or equal to the set temperature, it is determined that there is no fire risk, and the process proceeds to S701.

[0191] S705d. If it is determined that the actual current is greater than the set current, but the actual temperature is less than or equal to the set temperature, it is determined that there is no fire risk, and the process proceeds to S701.

[0192] The actual temperature of the heating element is collected by the temperature sensor, and the actual current of the electrical equipment is collected by the current sensor. Based on the actual temperature and actual current, it is determined whether there is a fire risk, which can improve the accuracy of the initial fire judgment.

[0193] Optionally, the above scheme first relies on high-precision temperature sensors and current sensors, which are used to collect the actual temperature of the heating elements in the electrical equipment and the actual current of the electrical equipment respectively. These sensors can capture the key parameters of the equipment's operating status in real time and accurately, providing a solid data basis for subsequent risk assessment. After obtaining the actual current and actual temperature data, these data are further compared and analyzed with the rated current and tolerance temperature of the electrical equipment. The rated current is the upper limit of the normal working current specified when the equipment is designed, and the tolerance temperature is the highest temperature that the equipment material can withstand under long-term operation. Through this comparison, it is possible to scientifically and reasonably evaluate whether the current working state of the equipment exceeds the limit of its safe operation. When the actual current is greater than the rated current and the actual temperature is greater than the tolerance temperature, the system immediately determines that there is a fire risk. This judgment logic is based on the fact that current overload and high temperature are the two main factors that cause electrical fires, so it can quickly respond to abnormal equipment conditions and provide a valuable time window for timely preventive measures (such as cutting off the power supply, starting the alarm, etc.).

[0194] Compared with single parameter monitoring (such as monitoring only current or temperature), this solution effectively avoids false alarms or missed alarms caused by single parameter abnormalities by comprehensively considering the two dimensions of current and temperature. This multi-dimensional and comprehensive risk assessment method significantly improves the accuracy of initial fire judgment and provides a more reliable basis for subsequent emergency response and disaster control.

[0195] In the long run, the implementation of this technical solution will help to timely discover and deal with potential safety hazards of electrical equipment, reduce fire accidents caused by equipment failure or overheating, and thus ensure the safety of production and life. At the same time, through continuous monitoring and analysis of the equipment's operating status, it can also provide data support for equipment maintenance, extend equipment life, and reduce operating costs.

[0196] S706: Obtain the arrangement position of the temperature sensor and the arrangement position of each camera.

[0197] S707: The backend server selects a target camera from multiple cameras according to the arrangement positions of the temperature sensors and the arrangement positions of the cameras.

[0198] S708. The background server controls the target camera to capture the monitoring image of the electrical device, and obtains the light intensity at the time of capturing the monitoring image.

[0199] S709. The backend server uses the fire detection model to identify the monitoring image, and uses the light intensity, actual current and actual temperature at the time of shooting to correct the identification process, and outputs the fire detection result.

[0200] In the above technical solution, current sensors, temperature sensors, and cameras are used to perform global situation awareness, and data processing technology is used to process the perceived data to achieve the technical effect of discovering fires as early as possible.

[0201] In addition, based on the above embodiment, when acquiring data from the current sensor, temperature sensor and camera, time synchronization is first performed to ensure that the timestamps of all data are consistent. Then, the sensor data is calibrated. For example, for the temperature sensor, the offset and gain of the sensor can be adjusted by comparing it with a standard temperature source. Next, the acquired data is cleaned to remove obviously abnormal data points, such as data with sudden jumps in current values ​​or temperature values ​​outside the normal range. Finally, through data filtering, only key information related to fire detection is retained, such as the rate of change of current, the rate of rise of temperature, and the monitoring image of the camera.

[0202] After determining that there is a fire risk, the system first calculates the weight of each camera based on the location of the temperature sensor and the fire risk level. The weights take into account factors such as the distance between the camera and the fire source, the camera's viewing angle range, and the camera's image quality. Then, the target camera is selected from high to low based on the weight value. If the fire risk level is high, the system may select multiple cameras for simultaneous monitoring to obtain more comprehensive fire information. In addition, the system will dynamically adjust the target camera selection strategy based on the spread trend of the fire and changes in the monitoring area to ensure that the latest developments of the fire can always be captured.

[0203] Optionally, when acquiring data from current sensors, temperature sensors, and cameras, time synchronization is performed to ensure that all data are consistent in timeliness. At the same time, the sensor data is calibrated to eliminate data deviations caused by sensor errors. The acquired multi-source data is cleaned to remove outliers and noise data to improve data quality. Through data filtering, only key information useful for fire detection is retained. Through data synchronization and calibration, data cleaning and filtering, the accuracy and reliability of the data are improved, providing a high-quality data foundation for subsequent fire detection.

[0204] After determining that there is a fire risk, not only the location of the temperature sensor is considered, but also the fire risk level is combined to give priority to selecting cameras that are closer to the fire source and have a better viewing angle as target cameras. Dynamically adjust the camera selection strategy: According to the spread trend of the fire and changes in the monitored area, dynamically adjust the target camera selection strategy to ensure that the latest fire dynamics can always be captured. The intelligent target camera selection algorithm improves the pertinence and efficiency of fire monitoring, reduces the collection and processing of useless information, and speeds up the fire response speed.

[0205] In the fire detection model, not only the light intensity at the time of shooting is considered, but also the historical light data and weather forecast information are combined to dynamically compensate for the light intensity to eliminate the impact of light changes on image recognition results. According to the lighting environment of the monitored area, the light intensity threshold is automatically adjusted to meet the needs of fire detection under different lighting conditions. Through the light intensity adaptive adjustment technology, the adaptability and accuracy of the fire detection model under different lighting conditions are improved, reducing the occurrence of false alarms and missed alarms.

[0206] Continuously collect new fire and non-fire sample data to train and optimize the fire detection model to improve the generalization ability and accuracy of the model. Establish an online model update mechanism to automatically update model parameters when new fire features or patterns are detected to adapt to the changing fire detection needs. Through the optimization and update of the fire detection model, the advancement and accuracy of the model are maintained, and the reliability and real-time performance of fire detection are improved.

[0207] Integrate components such as current sensors, temperature sensors, cameras, backend servers, and fire detection models into a unified global situational awareness system to achieve seamless data transmission and sharing. The system design has good scalability and can easily add new sensors and cameras to expand the monitoring range and functions. Through system integration and expansion, the overall performance and flexibility of the global situational awareness system are improved, providing customized solutions for fire detection in different scenarios.

[0208] The present application embodiment provides a global situation awareness system based on data processing, including: An acquisition module, used to acquire an actual current detected by a current sensor arranged on the electrical device, and an actual temperature detected by a temperature sensor arranged on the heating element; A processing module, used to determine whether there is a fire risk according to the actual current and the actual temperature, and if so, obtain the arrangement position of the temperature sensor and the arrangement position of each camera; The processing module is further used to select a target camera from the plurality of cameras according to the arrangement positions of the temperature sensors and the arrangement positions of the cameras; The processing module is also used to control the target camera to capture the monitoring image of the electrical equipment and obtain the light intensity at the time of capturing the monitoring image; The processing module is also used to use the fire detection model to identify the monitoring image, and use the light intensity, actual current and actual temperature at the time of shooting to correct the identification process and output the fire detection result.

[0209] Figure 5 A schematic diagram of the structure of the backend server provided for this application. Figure 5 As shown, the background server 80 provided in this embodiment includes: at least one processor 801 and a memory 802. Optionally, the background server 80 also includes a communication component 803. The processor 801, the memory 802 and the communication component 803 are connected via a bus.

[0210] In a specific implementation process, at least one processor 801 executes the computer-executable instructions stored in the memory 802, so that at least one processor 801 executes the above method.

[0211] The specific implementation process of the processor 801 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0212] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0213] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0214] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0215] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0216] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0217] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0218] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0219] The division of units is only a logical function division, and there may be other divisions 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 an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0220] 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.

[0221] In addition, each functional unit in each embodiment of the present invention 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.

[0222] If the function 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 storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0223] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0224] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A global situation awareness method based on data processing, characterized in that: A plurality of cameras are arranged in the monitoring area, a current sensor is arranged on the electrical equipment in the monitoring area, and a temperature sensor is arranged on the heating element of the electrical equipment. The method is applied to a background server, and the method includes: Acquire the actual current detected by the current sensor arranged on the electrical device, and the actual temperature detected by the temperature sensor arranged on the heating element; Determine whether there is a fire risk according to the actual current and the actual temperature, and if so, obtain the arrangement position of the temperature sensor and the arrangement position of each camera; Selecting a target camera from a plurality of cameras according to the arrangement position of the temperature sensor and the arrangement position of each camera; Controlling the target camera to capture a monitoring image of the electrical device, and obtaining the light intensity at the time of capturing the monitoring image; The monitoring image is identified using a fire detection model, and the identification process is corrected using the light intensity at the shooting moment, the actual current and the actual temperature, and a fire detection result is output.

2. The global situation awareness method according to claim 1, characterized in that: The monitoring image is identified using a fire detection model, and the identification process is corrected using the light intensity at the shooting time, the actual current, and the actual temperature, and a fire detection result is output, specifically including: generating an input feature according to the monitoring image and the light intensity at the shooting time, and generating a classification feature according to the actual current and the actual temperature; The input feature and the classification feature are concatenated to generate a concatenated feature, an encoder is used to encode the concatenated feature to output a coded feature, a decoder is used to decode the classification data in the coded feature, and the fire detection result is determined.

3. The global situation awareness method according to claim 2, characterized in that: Generating input features according to the monitoring image and the light intensity at the shooting time specifically includes: Divide the monitoring image into blocks to obtain a plurality of image blocks and the position of each image block, and determine the monitoring sub-area corresponding to each image block according to the shooting parameters of the camera; Obtaining the light intensity of each monitoring sub-area at the time of shooting, and using the light intensity of each monitoring sub-area at the time of shooting as the light intensity of the corresponding image block; Each image block, the position of each image block and the light intensity of each image block are fused to obtain fused data of each image block; and the fused data of multiple image blocks are spliced ​​to generate the input feature.

4. The global situation awareness method according to claim 2, characterized in that: Decoding the coded features using a decoder to determine a fire detection result specifically includes: The first fully connected layer is used to linearize the encoding features, the activation function layer is used to nonlinearly process the output data of the first fully connected layer, the second fully connected layer is used to linearize the output data of the activation function layer, and the residual layer is used to superimpose the output features of the second fully connected layer and the output features of the activation function layer and then output them.

5. The global situation awareness method according to any one of claims 1 to 4, characterized in that: Determine whether there is a fire risk based on the actual current and actual temperature, including: Obtain the rated current and temperature tolerance of electrical equipment; If the actual current is greater than the rated current, and the actual temperature is greater than the tolerance temperature, it is determined that there is a fire risk.

6. The global situation awareness method according to claim 5, characterized in that: Get the tolerance temperature of electrical equipment, including: Acquire actual currents detected by the current sensor at multiple moments and actual temperatures detected by the temperature sensor at multiple moments; The actual current at multiple moments and the actual temperature at multiple moments are processed using a tolerance temperature prediction model to output the tolerance temperature of the electrical device.

7. The global situation awareness method according to any one of claims 1 to 4, characterized in that: Before obtaining the actual current detected by the current sensor on the electrical device and the actual temperature detected by the temperature sensor arranged on the heating element, the method further includes: Obtaining a circuit topology diagram of the monitoring area, and establishing a power model in power simulation software based on the circuit topology diagram; The power model is simulated and analyzed in the power simulation software to obtain the position information of the heating element; and the plurality of temperature sensors are arranged according to the position information of the heating element.

8. A global situation awareness system based on data processing, characterized in that: include: An acquisition module, used to acquire an actual current detected by a current sensor arranged on the electrical device, and an actual temperature detected by a temperature sensor arranged on the heating element; a processing module, configured to determine whether there is a fire risk according to the actual current and the actual temperature, and if so, to obtain a layout position of a temperature sensor and a layout position of each camera; The processing module is further used to select a target camera from a plurality of cameras according to the arrangement position of the temperature sensor and the arrangement position of each camera; The processing module is further used to control the target camera to capture the monitoring image of the electrical device and obtain the light intensity at the time of capturing the monitoring image; The processing module is further used to identify the monitoring image using a fire detection model, and to correct the identification process using the light intensity at the shooting moment, the actual current and the actual temperature, and output a fire detection result.

9. A backend server, characterized in that: include: processor; as well as, A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images