Fire-fighting internet-of-things secure transmission method, device, equipment and medium

Abstract

The invention discloses a fire-fighting internet-of-things secure transmission method, device and equipment and a medium. The method comprises the steps that an edge node obtains multi-modal local fire-fighting data and carries out data preprocessing on the local fire-fighting data to obtain target fire-fighting data, and the local fire-fighting data are fire-fighting data collected by local sensing equipment; the edge node performs feature extraction on the target fire-fighting data on a preset feature dimension based on a pre-trained machine learning model to obtain a data feature vector; and the edge nodes perform encryption processing on the data feature vectors, and send encrypted data feature vectors obtained after encryption processing to a cloud server, so that the cloud server performs decryption processing on the encrypted data feature vectors sent by the edge nodes. And based on the decrypted data feature vector obtained after decryption and a local pre-trained machine learning model, monitoring a fire-fighting fire behavior. According to the embodiment of the invention, the network bandwidth occupation and end-to-end response delay can be greatly reduced, and the real-time performance and accuracy of fire early warning are improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of fire-fighting Internet of Things, and in particular to a fire-fighting Internet of Things security transmission method, device, equipment and medium. BACKGROUND

[0002] With the wide application of Internet of Things technology in the field of fire-fighting, a fire-fighting Internet of Things system can collect a large amount of fire-fighting data such as temperature, smoke concentration, and flame image information in real time by deploying a wide range of front-end sensing devices such as temperature sensors, smoke concentration sensors, and high-definition cameras.

[0003] However, the raw data collected by the front-end sensing devices in the above prior art has a large amount of data, which is directly uploaded to the cloud for processing, not only occupying a large amount of network bandwidth resources, but also causing high data transmission delay, affecting the timeliness of fire warning. In addition, there is a risk of sensitive data leakage in the process of uploading data to the cloud, threatening user privacy and fire-fighting information security.

[0004] Therefore, there is an urgent need for a fire-fighting Internet of Things security transmission method with low network bandwidth occupation, low delay, and high security. SUMMARY

[0005] The present application provides a fire-fighting Internet of Things security transmission method, device, equipment and medium, which can realize low network bandwidth occupation, low delay, and high security for fire-fighting data transmission.

[0006] In a first aspect, the embodiments of the present application provide a fire-fighting Internet of Things security transmission method applied to an edge node in a fire-fighting data management system, the fire-fighting data management system comprising a cloud server and a plurality of edge nodes, the edge node being used to perform a data transmission task of transmitting data to the cloud server, the plurality of edge nodes comprising at least one core edge node, the core edge node comprising at least three identical data function modules and a majority voting module, the data function module comprising the functions of data reception, processing and sending; the method comprises:

[0007] obtaining multi-modal local fire-fighting data and performing data preprocessing on the local fire-fighting data to obtain target fire-fighting data, the local fire-fighting data being fire-fighting data collected by local sensing devices, the multi-modal local fire-fighting data comprising at least one of the following: time series signal type, image / video type, and event trigger type;

[0008] perform feature extraction on the target fire-fighting data in a preset feature dimension based on a pre-trained machine learning model, to obtain a data feature vector; the preset feature dimension includes at least one of a fire source area, a high-temperature area, and a fire spread area, and the pre-trained machine learning model is obtained by the cloud server and the plurality of edge nodes through multi-modal federated learning based on parameter aggregation rules for phased collaborative training;

[0009] perform encryption processing on the data feature vector, and send the encrypted data feature vector obtained after the encryption processing to the cloud server, so that the cloud server performs decryption processing on the encrypted data feature vectors sent by each edge node, and monitors a fire situation based on the decrypted data feature vectors obtained after the decryption and a local pre-trained machine learning model;

[0010] For each core edge node, send the data feature vectors output by each data function module to the plurality of majority voting modules, and compare the data feature vectors extracted by each data function module for the target fire-fighting data through the plurality of majority voting modules;

[0011] When there are same data feature vectors in the plurality of data feature vectors, the same data feature vectors with the largest number are determined as target data feature vectors to be finally encrypted and sent to the cloud server by the core edge node through the plurality of majority voting modules.

[0012] In a second aspect, the embodiments of the present application provide a fire-fighting Internet of Things safety transmission method, applied to a cloud server in a fire-fighting data management system, the fire-fighting data management system including the cloud server and a plurality of edge nodes, and the method includes:

[0013] receive encrypted data feature vectors sent by each edge node, the encrypted data feature vectors being data obtained after the edge node acquires local fire-fighting data and sequentially performs data preprocessing, feature extraction, and encryption processing on the local fire-fighting data;

[0014] perform decryption processing on each encrypted data feature vector, and determine a fire situation according to each decrypted data feature vector obtained after the decryption and a local pre-trained machine learning model, the encrypted data feature vector and the decrypted data feature vector corresponding to each other.

[0015] In a third aspect, the embodiments of the present application also provide a fire-fighting Internet of Things secure transmission device, applied to an edge node in a fire-fighting data management system, the fire-fighting data management system comprising a cloud server and a plurality of edge nodes, the edge node being configured to perform a data transmission task of transmitting data to the cloud server, the plurality of edge nodes comprising at least one core edge node, the core edge node comprising at least three same data function modules and a majority voting module, the data function module comprising the functions of data receiving, processing and sending; the device comprising:

[0016] an acquisition module configured to acquire local fire-fighting data in multiple modalities and perform data preprocessing on the local fire-fighting data to obtain target fire-fighting data, the local fire-fighting data being fire-fighting data collected by a local sensing device, the local fire-fighting data in multiple modalities comprising at least one of the following: time series signals, images / videos and event triggers;

[0017] a feature extraction module configured to perform feature extraction on the target fire-fighting data in a preset feature dimension based on a pre-trained machine learning model to obtain a data feature vector; the preset feature dimension comprising at least one of the following: a fire source area, a high-temperature area and a fire spread area, the pre-trained machine learning model being obtained by the cloud server and the plurality of edge nodes through collaborative training in stages based on multi-modal federated learning according to a parameter aggregation rule;

[0018] an encryption module configured to perform encryption processing on the data feature vector and send the encrypted data feature vector obtained after the encryption processing to the cloud server, so that the cloud server performs decryption processing on the encrypted data feature vectors sent by each edge node, and monitors a fire situation based on the decrypted data feature vectors obtained after the decryption and a local pre-trained machine learning model; for each core edge node, the data feature vectors output by each data function module are sent to the majority voting module, and the data feature vectors extracted by each data function module for the target fire-fighting data are compared by the majority voting module; when there are same data feature vectors in a plurality of the data feature vectors, the data feature vectors with the largest number of same data feature vectors are determined as the target data feature vector of the core edge node to be finally encrypted and sent to the cloud server by the majority voting module.

[0019] In a fourth aspect, the embodiments of the present application also provide a fire-fighting Internet of Things secure transmission device, applied to a cloud server in a fire-fighting data management system, the fire-fighting data management system comprising the cloud server and a plurality of edge nodes, the device comprising:

[0020] The receiving module is configured to receive encrypted data feature vectors sent by the edge nodes, wherein the encrypted data feature vectors are obtained by the edge nodes through acquiring local fire-fighting data, and sequentially performing data preprocessing, feature extraction and encryption processing on the local fire-fighting data.

[0021] The determining module is configured to decrypt the encrypted data feature vectors, and determine a fire disaster according to the decrypted data feature vectors and a locally pre-trained machine learning model.

[0022] In a fifth aspect, an electronic device is provided, including:

[0023] one or more processors;

[0024] a memory configured to store one or more programs,

[0025] When the one or more programs are executed by the one or more processors, the one or more processors implement the fire-fighting Internet of Things secure transmission method according to any one of the first aspect, or implement the fire-fighting Internet of Things secure transmission method according to any one of the second aspect.

[0026] In a sixth aspect, a storage medium is provided, which stores a computer program, and when the program is executed by a processor, the fire-fighting Internet of Things secure transmission method according to any one of the first aspect, or the fire-fighting Internet of Things secure transmission method according to any one of the second aspect is implemented.

[0027] The embodiment of the application provides a fire-fighting Internet of Things safety transmission method, device, equipment and medium. The method is applied to an edge node in a fire-fighting data management system, the fire-fighting data management system comprises a cloud server and a plurality of edge nodes, the edge node is used for executing a data transmission task of transmitting data to the cloud server, and the method comprises the following steps: acquiring local fire-fighting data in multiple modes and performing data preprocessing on the local fire-fighting data to obtain target fire-fighting data. The local fire-fighting data is fire-fighting data collected by a local sensing device, and the local fire-fighting data in multiple modes comprises at least one of the following: a time sequence signal type, an image / video type and an event trigger type; a pre-trained machine learning model is used to extract features of the target fire-fighting data in a preset feature dimension to obtain a data feature vector; the preset feature dimension comprises at least one of the following: a fire source area, a high-temperature area and a fire spread area, and the pre-trained machine learning model is obtained through stage-by-stage collaborative training of the cloud server and the plurality of edge nodes based on multi-modal federated learning according to a parameter aggregation rule; the data feature vector is encrypted, and the encrypted data feature vector obtained after the encryption is sent to the cloud server, so that the cloud server decrypts the encrypted data feature vector sent by each edge node, and monitors a fire situation based on the decrypted data feature vector and the local pre-trained machine learning model.

[0028] In other words, the technical solution of this application, by performing localized preprocessing on the raw fire data collected by local sensing devices at the edge node, effectively filters out redundancy, noise, and invalid information, generating concise target fire data with fire discrimination value, thereby significantly reducing the amount of data transmitted subsequently. Furthermore, the edge node utilizes a pre-trained machine learning model, collaboratively trained by the cloud server and multiple edge nodes, to extract features from the target fire data, obtaining highly representative data feature vectors. This collaborative training mechanism ensures the model's generalization ability to fire features across multiple scenarios and regions, while avoiding cross-domain transmission of raw sensitive data, thus improving model adaptability and privacy security. Based on this, the edge node encrypts the data feature vectors and uploads them to the cloud server, ensuring the confidentiality and integrity of the feature data during transmission. After receiving and decrypting each encrypted data feature vector, the cloud server performs a fusion analysis based on the one-to-one correspondence of the decrypted data feature vectors and its locally deployed pre-trained machine learning model to accurately determine the fire situation. Therefore, compared with existing technologies, the fire protection IoT secure transmission method proposed in this application not only significantly reduces network bandwidth consumption and end-to-end response latency, improving the real-time performance and accuracy of fire early warning, but also effectively avoids user privacy leaks and data security risks through encryption mechanisms and collaborative model training. Thus, while ensuring the security and reliability of the fire protection data management system, it constructs a highly efficient, low-latency, and privacy-protected intelligent fire protection data processing and fire assessment system. Furthermore, the technical solution of this application is simple and convenient to implement, easy to popularize, and has a wider range of applications. Attached Figure Description

[0029] Figure 1 This is a schematic diagram illustrating an application scenario of the fire protection IoT security transmission method provided in an embodiment of this application.

[0030] Figure 2 A schematic flowchart illustrating a fire protection IoT security transmission method provided in an embodiment of this application;

[0031] Figure 3 A schematic flowchart of a model pre-training method provided in an embodiment of this application;

[0032] Figure 4 A flowchart illustrating a fire protection IoT security transmission method provided in another embodiment of this application;

[0033] Figure 5 A flowchart illustrating a fire protection IoT security transmission method provided in another embodiment of this application;

[0034] Figure 6 This is a schematic diagram of the structure of a fire protection IoT safety transmission device provided in an embodiment of this application;

[0035] Figure 7 A structural schematic diagram of a fire-fighting Internet of Things safety transmission device provided for another embodiment of the present application is shown in the figure.

[0036] Figure 8 A structural schematic diagram of an electronic device provided for an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0037] In order to make the purposes, advantages and features of the present application clearer, the present application will be described clearly and completely below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, but not all the structures.

[0038] In order to facilitate the understanding of the technical solutions of the present application, first, the related concepts involved in the present application are introduced.

[0039] Server Cluster refers to a group of servers that are loosely or tightly connected together to work, usually used to perform large jobs. Clustered servers usually have higher computing efficiency than single servers with comparable speed or availability. By using multiple servers for parallel computation and multiple computing resources to solve problems, the computing speed and processing speed of the cluster system can be improved, and the overall performance of the cluster system can be improved. Each server in the cluster is connected to each other through a network, and each server runs its own operating system.

[0040] Containers can make different application programs run in a relatively isolated and secure environment to achieve isolation between application programs and isolation between application programs and the outside environment. Containers are a kind of lightweight virtualization technology, which has the advantages of fast startup, easy deployment and migration, good security and scalability, and is widely used in AI and cloud computing fields.

[0041] Distributed tasks refer to a large computing task that is decomposed into multiple subtasks, which are distributed to each computing node (e.g., an edge node that can execute a computing task) in a server cluster. Each computing node independently executes its assigned subtask, and each computing node can exchange data and work together through a network. Typical distributed tasks include distributed training of AI models. The training data set can be divided into multiple batches, and each batch of data set is trained in parallel by each computing node, thereby improving the training efficiency.

[0042] Next, the prior art and problems existing in the prior art related to the present application are described:

[0043] With the wide application of Internet of Things technology in the field of fire protection, the fire protection Internet of Things system can collect a large amount of fire protection data such as temperature, smoke concentration, flame image and the like in real time by deploying a wide range of front-end sensing devices such as temperature sensors, smoke concentration sensors and high-definition cameras.

[0044] However, in the process of implementing the present application, the applicant found that at least the following technical problems exist in the existing fire protection Internet of Things data transmission process:

[0045] Problem one, the raw data collected by the front-end sensing device is large in data volume, and directly uploading to the cloud for processing will not only occupy a large amount of network bandwidth resources, but also cause high data transmission delay, affecting the timeliness of fire warning. Problem two, there is a risk of sensitive data leakage in the process of uploading data to the cloud, threatening user privacy and fire safety information security. Problem three, the reliability of the traditional transmission node architecture is low, and once the key transmission node fails, it may cause the data transmission of the entire fire protection Internet of Things system to be interrupted, and the fire information cannot be transmitted in time, delaying the opportunity for fire rescue.

[0046] In order to solve at least part of the above technical problems, the present application provides a fire protection Internet of Things safe transmission method, a fire protection Internet of Things safe transmission device corresponding to the method, an electronic device capable of implementing the fire protection Internet of Things safe transmission method, a computer readable storage medium and a computer program product. The following embodiments are provided to explain the above method, device, electronic device and computer readable storage medium in detail.

[0047] The application scenario of the fire protection Internet of Things safe transmission method provided by an embodiment of the present application is introduced below in combination with Figure 1 , the application scenario of the fire protection Internet of Things safe transmission method provided by an embodiment of the present application is introduced below in combination with Figure 1 , the application scenario of the fire protection Internet of Things safe transmission method provided by an embodiment of the present application is introduced below in combination with

[0048] As shown in Figure 1 , the application scenario at least includes a fire protection data management system, which includes a cloud server 110 and edge nodes 120 (for example: edge node 1, edge node 2, …, edge node n, n is a natural number greater than or equal to 1), the cloud server 110 and the edge nodes 120 are connected, and an AI development platform is deployed on the cloud server 110. The AI development platform refers to a comprehensive platform that provides a series of tools, libraries, frameworks and services, which can help developers design, train, deploy and manage AI models more quickly and efficiently.

[0049] The edge node 120 refers to a node responsible for performing sub-tasks assigned by the cloud server 110 in a distributed system. These sub-tasks are executed in parallel on different edge nodes 120, and the entire distributed task (such as the task of training the distributed collaborative model in the embodiments of the present application) is completed through mutual cooperation.

[0050] The edge node 120 can be different types of servers, such as CPU servers, GPU servers, neural network processing unit (NPU) servers, service clusters, etc., based on the different functions implemented by different types of AI models. Among them, the CPU server has strong versatility and is suitable for deep learning fields such as pattern recognition, target detection, and image processing; the GPU server can be used to specifically process image computing tasks and can accelerate graphics rendering; the NPU server can be used to accelerate the training and inference calculation of artificial neural networks and can efficiently perform large-scale neural network calculations.

[0051] In one embodiment, the edge node 120 can be an NPU server, which can include multiple NPU acceleration cards, such as NPU1 to NPU8. The cloud server 110 refers to a node responsible for coordinating and managing the execution of the entire distributed task in a distributed system, and can schedule the task to an edge node that meets the resource configuration information when the user 100 (such as an algorithm engineer) issues a model training task according to the resource configuration information.

[0052] Figure 2 The flowchart of the fire-fighting Internet of Things safety transmission method provided by an embodiment of the present application is shown in the figure. The method is applied to a fire-fighting data management system, which includes a cloud server and multiple edge nodes. The method can be executed by a fire-fighting Internet of Things safety transmission device or an electronic device, which can be realized by software and / or hardware. The device or electronic device can be integrated into any intelligent device with network communication function. As shown in the figure, the fire-fighting Internet of Things safety transmission method can include the following steps: Figure 2

[0053] S201, the edge node acquires multi-modal local fire-fighting data and performs data preprocessing on the local fire-fighting data to obtain target fire-fighting data. The local fire-fighting data is fire-fighting data collected by a local sensing device.

[0054] Among them, the multi-modal local fire-fighting data includes at least one of the following: time series signal type, image / video type, and event trigger type.

[0055] ​In this application, the edge node in the fire data management system refers to an intelligent processing unit with local computing, storage, and communication capabilities, deployed near fire sensing equipment or on-site terminals. As an intermediate layer connecting the front-end sensing layer and the cloud server, it undertakes key functions such as data acquisition, local processing, preliminary analysis, and secure transmission. Local sensing equipment (such as temperature sensors, smoke concentration sensors, and high-definition cameras) can collect large amounts of fire data in real time (such as temperature, smoke concentration, and flame images). The edge node also stores certain sensitive data, including: user privacy data: the distribution of people in the building, resident information, and the location of raw material storage for enterprise production (in a chemical industrial park scenario); fire safety sensitive data: the operational status of fire protection facilities (such as fire hydrant water pressure and fire extinguisher expiration dates), real-time sensor monitoring data (temperature, smoke concentration, and gas composition), and historical fire hazard records.

[0056] The edge nodes are equipped with local sensors of varying data types, quantities, and sampling frequencies. The collected multimodal local fire protection data includes time-series signal data (such as temperature, humidity, smoke concentration, etc.). Data such as gas concentration, image / video data (such as visible light cameras, infrared thermal imaging, flame recognition images, etc.), and event-triggered signals (such as manual alarm button status, water pressure switch signals, electrical fire monitoring signals, etc.) exhibit significant modal heterogeneity.

[0057] In this step, the edge node acquires raw fire sensing data from the local sensing devices it communicates with, serving as local fire data. Subsequently, the edge node performs data preprocessing on the local fire data. This preprocessing includes, but is not limited to, one or more of the following: data cleaning, noise filtering, format standardization, feature extraction, or data compression, to remove redundant or invalid information and retain key features relevant to fire risk identification, thereby generating optimized target fire data.

[0058] Optionally, when the local fire protection data includes image data, the image data preprocessing method can be: based on the image recognition model, identify the target image data containing the target image in the local fire protection data, and perform image preprocessing on the target image data to obtain the preprocessed target image data. The image preprocessing includes at least one of the following: noise reduction and image information enhancement.

[0059] In this step, when local fire protection data includes image data, the edge node is configured with a pre-installed image recognition model to intelligently analyze the image data to identify target objects related to fire risk (such as flames, smoke, abnormally high temperature areas, or the status of specific fire protection facilities), thereby extracting the image region containing the target object as the target image data. The image recognition model may include, but is not limited to, convolutional neural networks (CNN), lightweight target detection models (such as YOLO-Lite, MobileNet-SSD), or rule-based image feature matching algorithms, deployed locally on the edge node to achieve low-latency, high-efficiency target recognition. Afterward, the edge node performs image preprocessing operations on the extracted target image data. Image preprocessing includes at least one of the following: noise reduction to suppress unstructured interference information introduced by changes in illumination, sensor noise, or transmission interference; and image enhancement to improve the recognizability of key visual features. Enhancement includes, but is not limited to, contrast stretching, histogram equalization, edge sharpening, or local brightness adjustment. Through the above image preprocessing, the quality and discriminative power of the target image data can be effectively improved, while reducing data redundancy in subsequent transmission and analysis.

[0060] S202. Edge nodes extract features from target fire data in preset feature dimensions based on pre-trained machine learning models to obtain data feature vectors. The preset feature dimensions include at least one of the following: fire source area, high temperature area, and fire spread area. The pre-trained machine learning model is obtained by cloud servers and multiple edge nodes through phased collaborative training based on multimodal federated learning and parameter aggregation rules.

[0061] In this embodiment, the pre-trained machine learning model used by the edge nodes not only possesses general fire discrimination capabilities but is also specifically optimized for refined fire situation perception. Specifically, the model is configured to extract structured features from target fire data across preset feature dimensions, including but not limited to: the fire source area (i.e., the most likely initial location of the fire), the high-temperature area (representing the current heat release intensity and the core danger zone), and the fire spread area (reflecting the direction of fire spread and potential risk diffusion paths). These dimensions correspond to key decision-making elements in fire emergency response, enabling the generated data feature vectors to possess both semantic interpretability and task orientation.

[0062] To achieve accurate extraction of the aforementioned preset feature dimensions, the pre-trained machine learning model employs a multimodal input fusion architecture. For example, when the target fire data includes infrared images, the model uses lightweight convolutional branches to locate high-temperature connected regions and output their spatial coordinates and area. When the input is time-series data from a distributed temperature sensor array, the model utilizes a temporal modeling module (such as LSTM or Temporal ConvNet) to identify temperature spikes and gradient propagation directions, inferring the fire source and its spread trend. If visible light video is also present, an attention mechanism is used to fuse visual flame features and thermal distribution, improving the robustness of fire source localization. Finally, the outputs of each modal branch are mapped to a unified feature space, forming a data feature vector containing structured information such as the fire source (x, y), high-temperature region mask, and spread velocity vector.

[0063] Crucially, the model's pre-training process employs a cloud-edge collaborative mechanism based on multimodal federated learning to address the challenge of highly heterogeneous edge node sensor configurations in real-world deployments. Different edge nodes may only possess partial modal data (e.g., only temperature sensing without images, or only smoke sensing without gas sensors), making traditional centralized training insufficient to cover such scenarios. In this application, each edge node independently performs forward inference and backward updates based on local real-world fire data (including historical fire alarms, drills, or normal operating condition data), uploading only encrypted model parameter increments or semantic embeddings to the cloud server. The cloud server aggregates multi-source heterogeneous knowledge according to parameter aggregation rules, which generate globally optimized model parameters through distillation or weighted averaging strategies, and then distributes these parameters to each edge node to complete model parameter synchronization.

[0064] The aforementioned phased collaborative training refers to dividing the pre-training process into multiple progressively advancing training phases. Each phase sets specific training objectives, input modality ranges, and model optimization strategies: the initial phase focuses on building basic single-modality fire situation discrimination capabilities; the middle phase introduces multimodal fusion to enhance the robustness of complex scene recognition; and the later phase fine-tunes high-order fire situation semantics (such as fire source location and spread prediction). In each phase, the cloud server fuses the encrypted model updates uploaded by edge nodes according to preset parameter aggregation rules (such as modality weighted averaging and task-oriented aggregation), and dynamically adjusts the communication frequency, security strategy, and model structure. This allows for the gradual evolution of a fire-specific machine learning model that combines generalization, accuracy, and interpretability while ensuring privacy and resource efficiency.

[0065] In this application, the collaborative training mechanism not only ensures that sensitive data such as original images, locations, and sensor sequences are always retained locally, meeting compliance requirements for public safety information, but also significantly improves the model's generalization ability to recognize complex fire patterns (such as smoldering lithium batteries accompanied by localized high temperatures and nonlinear spread caused by smoke backflow in underground spaces) through cross-regional and multi-scenario knowledge fusion. Especially in high-risk tasks such as fire source location and spread prediction, the model, by incorporating collaborative experience from diverse environments such as shopping malls, factories, and tunnels, demonstrates robustness and accuracy far superior to single-point trained models.

[0066] This application explicitly embeds the physical semantic dimensions of fire (fire source, high temperature zone, and spread zone) into the feature extraction target and combines it with a collaborative pre-training architecture driven by multimodal federated learning. This enables edge nodes to output high-value, structured fire feature vectors even under resource-constrained conditions. This provides accurate, real-time, and secure data support for subsequent cloud-based fire level determination, emergency resource scheduling, and evacuation route planning, achieving an intelligent leap from "whether there is a fire" to "where the fire started, how it developed, and how to respond."

[0067] S203. The edge node encrypts the data feature vector and sends the encrypted data feature vector to the cloud server.

[0068] In this step, after generating the data feature vector, the edge node invokes its built-in security encryption module. It can employ symmetric encryption algorithms (such as AES, SM4) or asymmetric encryption algorithms (such as RSA, SM2) to encrypt the extracted data feature vector, generating an encrypted data feature vector. Subsequently, the edge node transmits the encrypted data feature vector to the cloud server via a secure communication protocol (such as TLS, DTLS, or IPSec). This ensures the confidentiality, integrity, and anti-eavesdropping capabilities of the encrypted data feature vector during transmission, preventing the leakage or malicious tampering of sensitive fire information. This significantly reduces the bandwidth consumption of the original image data transmission while ensuring the security of the fire data management system, and improves the response speed and security of the entire fire data management system. Ultimately, this supports the cloud server's centralized analysis and collaborative decision-making regarding fire risks.

[0069] S204. The cloud server receives encrypted data feature vectors sent by each edge node.

[0070] In this step, the cloud server can receive encrypted data feature vectors uploaded from multiple edge nodes through a secure communication interface.

[0071] S205, the cloud server decrypts each encrypted data feature vector, and determines the fire situation based on the decrypted data feature vectors and the local pre-trained machine learning model. The encrypted data feature vectors correspond one-to-one with the decrypted data feature vectors.

[0072] In this step, after receiving the encrypted data feature vectors uploaded by each edge node, the cloud server performs corresponding decryption processing on the encrypted data feature vectors based on the key information pre-negotiated or configured with each edge node to recover the original data feature vectors. Each encrypted data feature vector and its decrypted counterpart form a one-to-one correspondence, ensuring data traceability and semantic consistency. Subsequently, the cloud server inputs multiple decrypted data feature vectors into its locally deployed pre-trained machine learning model. Based on the model's output classification or regression results, the cloud server determines the fire situation in the current fire scenario. This pre-trained machine learning model has been trained on a large amount of historical fire data and possesses the ability to perform multi-source feature fusion analysis and fire situation identification.

[0073] The fire protection IoT security transmission method proposed in this application involves edge nodes acquiring multimodal local fire protection data and preprocessing it to obtain target fire protection data. The local fire protection data refers to fire protection data collected by local sensing devices. The multimodal local fire protection data includes at least one of the following: time-series signals, images / videos, and event-triggered data. Based on a pre-trained machine learning model, features are extracted from the target fire protection data in preset feature dimensions to obtain data feature vectors. The preset feature dimensions include at least one of the following: fire source area, high-temperature area, and fire spread area. The pre-trained machine learning model is obtained through phased collaborative training between a cloud server and multiple edge nodes based on multimodal federated learning and parameter aggregation rules. The edge nodes encrypt the data feature vectors and send the encrypted data feature vectors to the cloud server. The cloud server receives the encrypted data feature vectors sent by each edge node. The cloud server decrypts each encrypted data feature vector and determines the fire situation based on the decrypted data feature vectors and the local pre-trained machine learning model. There is a one-to-one correspondence between the encrypted and decrypted data feature vectors.

[0074] In other words, the technical solution of this application, by performing localized preprocessing on the raw fire data collected by local sensing devices at the edge node, effectively filters out redundancy, noise, and invalid information, generating concise target fire data with fire discrimination value, thereby significantly reducing the amount of data transmitted subsequently. Furthermore, the edge node utilizes a pre-trained machine learning model, collaboratively trained by the cloud server and multiple edge nodes, to extract features from the target fire data, obtaining highly representative data feature vectors. This collaborative training mechanism ensures the model's generalization ability to fire features across multiple scenarios and regions, while avoiding cross-domain transmission of raw sensitive data, thus improving model adaptability and privacy security. Based on this, the edge node encrypts the data feature vectors and uploads them to the cloud server, ensuring the confidentiality and integrity of the feature data during transmission. After receiving and decrypting each encrypted data feature vector, the cloud server performs a fusion analysis based on the one-to-one correspondence of the decrypted data feature vectors and its locally deployed pre-trained machine learning model to accurately determine the fire situation. Therefore, compared with existing technologies, the fire protection IoT secure transmission method proposed in this application not only significantly reduces network bandwidth consumption and end-to-end response latency, improving the real-time performance and accuracy of fire early warning, but also effectively avoids user privacy leaks and data security risks through encryption mechanisms and collaborative model training. Thus, while ensuring the security and reliability of the fire protection data management system, it constructs a highly efficient, low-latency, and privacy-protected intelligent fire protection data processing and fire assessment system. Furthermore, the technical solution of this application is simple and convenient to implement, easy to popularize, and has a wider range of applications.

[0075] Another embodiment of this application also provides a model training method. Based on the above technical solution, further optimizations and extensions are possible, and it can be combined with the various optional implementation methods described above. Figure 3 This is a schematic flowchart illustrating a model pre-training method provided in an embodiment of this application. Figure 3 As shown, the model pre-training method includes the following steps:

[0076] S311. Edge nodes acquire local fire protection data and determine training sample data based on the local fire protection data.

[0077] S312. Edge nodes train the initial model based on training sample data to obtain a machine learning model with updated model parameters.

[0078] S313. The edge node encrypts the model update parameters and sends the encrypted model update parameters to the cloud server.

[0079] S314. The cloud server receives the encrypted model update parameters sent by each edge node, and decrypts, aggregates, and encrypts the encrypted model update parameters sent by each edge node in sequence to obtain the encrypted global model update parameters. The model update parameters refer to the updated model parameters obtained in this training.

[0080] S315, the cloud server sends global model update parameters to each edge node.

[0081] S316. The edge node receives the global model update parameters sent from the cloud server, decrypts the global model update parameters, and updates the model parameters of the initial model based on the decrypted global model update parameters.

[0082] S317. The edge node determines whether the machine learning model has reached the preset convergence condition. If yes, execute S318; otherwise, repeat S311-S317.

[0083] S318. Pre-training is complete, and the pre-trained machine learning model is obtained.

[0084] The following is a detailed explanation of S311-S318.

[0085] In this step, the initial model refers to the machine learning model before pre-training the pre-trained machine learning model. Optionally, the untrained initial model in the edge nodes is the machine learning model received by the edge nodes from the cloud server. Distributing the untrained initial machine learning model uniformly to each edge node through the cloud server ensures consistency in model structure and initial parameters across all edge nodes within the fire data management system, laying a standardized foundation for subsequent collaborative training. Simultaneously, this approach avoids convergence bias or training instability issues that may arise from independent model initialization by each edge node, improving the efficiency of the federated learning process and the generalization ability of the global model, thereby enhancing the collaborative intelligence and response consistency of the entire fire data management system.

[0086] In this embodiment, the machine learning model pre-training method employs an iterative federated learning mechanism based on an edge-cloud collaborative architecture. By repeatedly executing training loops S311 to S316, the initial model is optimized multiple times until it meets preset convergence conditions, such as a loss function threshold, accuracy metric, or maximum number of iterations, thereby obtaining a pre-trained machine learning model. Specifically, in each training round, each edge node first obtains raw local fire data from locally deployed fire sensors and constructs local training sample data suitable for model training. Subsequently, the edge node uses this training sample data to perform local forward and backward propagation calculations on the current version of the initial model, generating model parameter updates and obtaining the locally updated machine learning model. To ensure data privacy and communication security during model training, the edge nodes do not upload the raw data; instead, they encrypt the model update parameters, forming encrypted model update parameters, and send them to the cloud server. After receiving encrypted model update parameters from multiple edge nodes, the cloud server sequentially decrypts them to restore the model update parameters of each node. Then, it uses an aggregation algorithm (such as weighted average or FedAvg) to fuse all the decrypted parameters, generating global model update parameters representing global knowledge. These global parameters are then encrypted again to form encrypted global model update parameters. Subsequently, the cloud server broadcasts these encrypted global model update parameters to all participating edge nodes. Each edge node receives and decrypts them, then synchronously updates the parameters of its local initial model based on the decrypted global model update parameters, completing this round of collaborative training. This process is repeated until the model performance reaches a preset convergence condition, ultimately outputting a pre-trained machine learning model with high generalization ability.

[0087] The core idea of ​​Federated Learning (FL) is that the computation process of model training is completed at the edge nodes where the data is located, and the updated model parameters (such as gradients and weight increments) are only exchanged between nodes or with the cloud, and finally aggregated to form the globally optimal model.

[0088] The model training method provided in this application adopts a federated learning approach during the model pre-training stage, where "local fire data does not leave the domain, and only encrypted parameters for model updates are transmitted." This effectively avoids the centralized uploading of original sensitive fire data, significantly improving user privacy and system information security. Simultaneously, through the decryption-aggregation-re-encryption processing of encrypted parameters from multiple edge nodes on a cloud server, and the synchronous distribution of global model parameters, knowledge fusion of fire data across regions and multiple scenarios is achieved, giving the resulting pre-trained model both local adaptability and global generalization capabilities. Furthermore, this collaborative training method is naturally adapted to fire deployment environments with limited edge computing resources, and can continuously optimize model performance without relying on large-scale centralized labeled datasets. Therefore, the obtained pre-trained machine learning model, when subsequently used for feature extraction on edge nodes and fire situation determination on cloud servers, not only possesses higher accuracy and robustness, but also ensures end-to-end trustworthiness of the entire fire data management system due to the embedded security encryption mechanism during the training process. This significantly improves the intelligence level, response timeliness, and system scalability of fire early warning while ensuring data security.

[0089] Furthermore, to overcome the dependence of federated learning on input isomorphism, this application also provides another possible implementation for collaborative pre-training of machine learning models, including the following steps:

[0090] S321. Each edge node collects raw local fire data based on locally deployed heterogeneous fire sensing devices, and constructs an adapted local student model according to its sensing configuration. The local fire data includes at least one of time-series signal type, image / video type and event-triggered type. The structure of the local student model of each edge node is adaptively determined according to the available modes.

[0091] S322: Each edge node uses local fire data to perform forward reasoning on the local student model, generating soft logits or normalized embedding vectors that represent the semantics of the current fire situation as knowledge carriers, and encrypting the knowledge carriers to obtain encrypted knowledge data.

[0092] S323: Each edge node uploads encrypted knowledge data to the cloud server; after receiving it, the cloud server decrypts it to obtain the soft label or embedding vector of each edge node, and compares it with the output of the global teacher model on the multimodal synthetic input to construct the distillation loss function.

[0093] S324: The cloud server updates the parameters of the global teacher model based on the distillation loss function, and generates corresponding distillation guidance signals according to the modal capability differences of each edge node. The distillation guidance signals are then encrypted and sent to the corresponding edge nodes.

[0094] S325: Each edge node receives and decrypts the distillation guidance signal from the cloud server. Using this signal as the supervision target, it fine-tunes the parameters of the local student model using a self-supervised distillation method, so that its output is aligned with the global teacher model in the unified fire semantic space.

[0095] S326: Repeat S322 to S325 until the global teacher model meets the preset convergence conditions to obtain a pre-trained machine learning model. The preset convergence conditions include at least one of the following: fire identification accuracy threshold, verification loss stability, and / or maximum number of iterations.

[0096] The following is a detailed explanation of S321-S326.

[0097] In this embodiment, the collaborative pre-training method provided by the present invention first involves each edge node collecting corresponding raw local fire protection data based on the type of sensing device it actually deploys (e.g., a low-cost node containing only temperature / smoke sensors, or a high-performance node equipped with an infrared camera and a gas sensor). This data naturally possesses characteristics such as multimodality, non-alignment, and non-independent identically distributed (Non-IID). To adapt to such heterogeneous inputs, each edge node dynamically configures a local student model that matches its sensing capabilities—for example, nodes with only temporal inputs use LSTM or 1D-CNN structures, while nodes with image inputs integrate lightweight visual backbone networks (such as MobileNet or EfficientNet-Lite). This avoids a "one-size-fits-all" model deployment and ensures efficient utilization of local computing resources.

[0098] In this application, each edge node no longer uploads raw data or complete model parameters. Instead, it performs forward inference to generate a highly semantically abstract knowledge carrier. This carrier can be a temperature-scaled soft logits (i.e., a classification probability distribution without argmax) or a normalized embedding vector output by the intermediate layer of the model. Its dimensions are fixed (e.g., 128-dimensional) and it effectively represents the semantic features of the current fire situation (e.g., "initial smoldering" or "open flame spread"). Subsequently, this knowledge carrier is encrypted using a pre-set key (e.g., AES-256 or SM4), forming encrypted knowledge data. This significantly reduces the risk of data leakage and compresses the communication load to the KB level, far lower than traditional parameter uploading methods.

[0099] Subsequently, the cloud server, acting as the collaborative training hub, receives and decrypts encrypted knowledge data from all participating edge nodes. Since each node uploads semantically aligned soft tags or embeddings, the cloud server doesn't need to concern itself with the original modal differences. The cloud server compares this local knowledge with the output of its own maintained global teacher model (e.g., a Transformer-based multimodal fusion model) under synthetic multimodal input, constructing a distillation loss function centered on KL divergence. This loss function not only measures prediction consistency but also introduces dynamic weights (such as based on node historical accuracy or regional risk level) to prioritize learning the knowledge of high-confidence nodes.

[0100] After updating the global teacher model based on distillation loss, the cloud server does not distribute the complete model. Instead, it generates lightweight distillation guidance signals—such as target soft labels, intermediate layer feature maps, or gradient direction cues—and distributes them with encryption tailored to the capabilities of each node. Each edge node receives and decrypts these signals, using the difference between its local student model's current output and the guidance signal as a supervision signal to perform local fine-tuning (such as a single-round SGD update). This process achieves a dual optimization of "global semantic guidance and local personalized adaptation," ensuring both overall system cognition consistency and preserving the flexibility of the edge side.

[0101] Finally, the aforementioned collaborative training loop continues to iterate until the model meets the preset convergence criteria. These criteria can be composite: for example, a fire detection accuracy greater than or equal to 96% on the global validation set, a loss reduction of less than 0.5% for three consecutive rounds, and local accuracy at all high-risk area edge nodes meeting the standard. Once converged, the resulting model can be used for subsequent real-time fire monitoring.

[0102] Therefore, this application effectively solves the problems of data misalignment and model heterogeneity caused by differences in sensor configuration, while ensuring that the original fire data does not leave the domain. It significantly reduces communication overhead, improves the robustness and generalization ability of the model in recognizing complex fire situations (such as smoldering accompanied by gas leakage or local high temperature), and supports personalized deployment and efficient inference of edge nodes. It provides a model training technology solution for a highly reliable, large-scale intelligent fire data management system that combines privacy and security, communication efficiency and intelligent collaboration capabilities.

[0103] An optional implementation includes at least one core edge node among multiple edge nodes. The core edge node includes at least three identical data function modules and a majority voting module. The data function modules include functions for receiving, processing, and sending data. Figure 4 This is a flowchart illustrating a fire protection IoT security transmission method according to another embodiment of this application. Figure 4 As shown in the embodiments of this application, the fire protection IoT security transmission method further includes the following steps:

[0104] S401. For each core edge node, the data feature vectors output by each data function module are sent to the majority voting module. The majority voting module compares the data feature vectors extracted by each data function module for the target fire data.

[0105] S402. Determine whether there are any identical data feature vectors among the multiple data feature vectors. If yes, execute S403; otherwise, execute S404-S405.

[0106] S403. When there are identical data feature vectors among multiple data feature vectors, the data feature vector with the largest number of identical data feature vectors shall be determined as the target data feature vector that the core edge node will ultimately encrypt and send to the cloud server.

[0107] S404. When there are no identical data feature vectors among multiple data feature vectors, trigger the monitoring of the running status of at least three identical data function modules.

[0108] The operating status includes at least one of the following: CPU utilization, memory usage ratio, and data processing latency.

[0109] S405. When a fault is detected in the target data function module, the target data function module is isolated so that the data transmission task can be completed by a data function module other than the target data function module.

[0110] The following is a detailed explanation of S401-S405.

[0111] In this embodiment, at least one core edge node is provided among the aforementioned multiple edge nodes. This core edge node integrates at least three data function modules with identical structure and function, as well as a majority voting module. Each data function module possesses complete data reception, local processing (including preprocessing and feature extraction), and encrypted transmission functions, capable of independently performing feature extraction processing on the same target fire data and outputting the corresponding data feature vector. Based on this, this embodiment further introduces a redundancy fault-tolerant mechanism, specifically including the following steps:

[0112] In S401, each core edge node inputs the data feature vectors output by its internal data function modules into the majority voting module. The majority voting module performs a consistency comparison on these parallel-generated data feature vectors. If, in S402, it is determined that two or more identical data feature vectors exist (i.e., majority consensus is achieved), then S403 is executed, and the data feature vector with the highest frequency is determined as the target data feature vector that the core edge node will ultimately use for encrypted uploading to the cloud server. This utilizes redundant computation to improve the reliability and anti-interference capability of the results. Conversely, if, in S402, it is determined that all data feature vectors are different (i.e., majority consensus is not achieved), then the fault diagnosis process begins: In S404, real-time monitoring of the operating status of each data function module is triggered. The operating status includes, but is not limited to, health indicators such as CPU utilization, memory usage ratio, and data processing latency. Subsequently, in S405, if a data function module (referred to as the "target data function module") is found to have performance abnormalities or suspected faults, the module is immediately logically or physically isolated, causing it to exit the current data processing flow. The remaining normally operating data function modules continue to complete the subsequent data feature extraction and data transmission tasks to the cloud server, ensuring continuous availability.

[0113] The fire protection IoT secure transmission method proposed in this application deploys at least three homogeneous data function modules in the core edge node and introduces a majority voting mechanism. This ensures that even if individual modules produce erroneous outputs due to hardware disturbances, software anomalies, or environmental interference, the correct results can be selected through majority consensus, significantly improving the accuracy and robustness of feature extraction. Furthermore, when all module outputs are inconsistent, the fire protection data management system automatically activates the operational status monitoring mechanism and executes a fault module isolation strategy, achieving a closed-loop fault tolerance capability from "error tolerance" to "fault self-healing." This not only effectively mitigates the risk of single-point failure and ensures the high reliability and continuity of critical fire protection data processing and uploading at the edge, but also avoids the problem of service interruption of the entire edge node due to local module failures. Combined with the aforementioned encrypted transmission and collaborative training mechanisms, this application further enhances the edge-side resilience and industrial-grade availability of the fire protection data management system while ensuring data security and model intelligence. It is particularly suitable for high-risk fire protection scenarios such as high-rise buildings, underground spaces, or chemical industrial parks with stringent reliability requirements.

[0114] One possible implementation is that fire situations can include multiple fire situation levels, such as general, major, serious, and extremely serious fire situation levels, to characterize the development trend, scope of impact, and emergency response level of a fire event. Figure 5 This is a flowchart illustrating a fire protection IoT security transmission method provided in another embodiment of this application. Figure 5As shown, in order to dynamically adapt to the data sensing and transmission needs under different fire levels, the fire protection IoT security transmission method provided in this application embodiment further includes the following steps:

[0115] S501. When a fire escalation is detected, the cloud server controls the addition of a first number of edge nodes to begin data transmission tasks based on the current fire escalation level.

[0116] In this process, when the cloud server detects an escalation in the current fire severity level, such as from "general" to "significant" or from "major" to "extremely serious," the cloud server will automatically trigger a resource scheduling strategy based on the upgraded fire severity level. This will control and activate an additional number of edge nodes to join the fire data acquisition and transmission task. The initial number can be a preset value or dynamically calculated based on the fire severity level. For example, the higher the fire severity level, the more newly activated edge nodes will be, enhancing the perception density, data coverage, and information update frequency of the surrounding area. Activated edge nodes may include nodes that were previously in dormant, low-power, or standby states. Upon receiving the scheduling command, these nodes immediately initiate the data acquisition, preprocessing, feature extraction, and encrypted upload processes of their local sensing devices, thereby forming a flexible data transmission network that matches the severity of the fire.

[0117] S502. When a fire severity level downgrade is detected, the cloud server controls a second number of edge nodes to stop performing data transmission tasks based on the current fire severity level, and performs data archiving and / or model parameter update processing on the second number of edge nodes.

[0118] In this step, when the cloud server detects a downgrade in the current fire situation level, such as from "major" to "relatively serious" or from "relatively serious" to "general," in order to optimize resource utilization efficiency and reduce energy consumption, this embodiment of the application can dynamically control a second number of edge nodes to stop performing real-time fire data acquisition and transmission tasks based on the downgraded current fire situation level. The value of the second number can be determined dynamically based on a preset strategy or the current fire situation level and the edge node load status, ensuring that the scale of edge nodes participating in data transmission is reasonably reduced while maintaining necessary monitoring capabilities.

[0119] Optionally, the multiple edge nodes include at least one core edge node, and the core edge node includes at least three identical data function modules and a majority voting module. The data function modules include data receiving, processing, and sending functions. Therefore, one possible implementation of "controlling a second number of edge nodes to stop performing data transmission tasks according to the current fire situation level" can be: controlling a second number of edge nodes (excluding the core edge node) to stop performing data transmission tasks according to the current fire situation level.

[0120] In this step, the core edge nodes are prioritized for continued operation, while tasks are only reduced for non-core edge nodes. Specifically, when a fire severity level downgrade is detected and data transmission resources need to be reduced, the cloud server determines the number of edge nodes to be shut down (i.e., the second number) based on the current fire severity level, and selects an appropriate number of ordinary edge nodes (excluding core edge nodes) to stop them from performing fire data collection, processing, and uploading tasks. This ensures that a highly reliable and high-confidence data channel provided by the core edge nodes is maintained during the fire mitigation phase, guaranteeing continuous monitoring capabilities for key areas or critical facilities. At the same time, shutting down some non-core nodes effectively reduces overall energy consumption and network load, achieving a balance between refined resource scheduling and security.

[0121] Figure 6 This is a schematic diagram of the structure of a fire protection IoT security transmission device provided in an embodiment of this application. This device is applied to an edge node in a fire protection data management system. The fire protection data management system includes a cloud server and multiple edge nodes, which are used to perform data transmission tasks to transmit data to the cloud server. Figure 6 As shown, the fire protection IoT security transmission device includes: an acquisition module 601, a feature extraction module 602, and an encryption module 603; wherein,

[0122] The acquisition module 601 is used to acquire multimodal local fire data and perform data preprocessing on the local fire data to obtain target fire data. The local fire data is fire data collected by local sensing devices. The multimodal local fire data includes at least one of the following: time-series signal type, image / video type and event-triggered type.

[0123] The feature extraction module 602 is used to extract features from the target fire data on a preset feature dimension based on a pre-trained machine learning model to obtain a data feature vector; the preset feature dimension includes at least one of the following: fire source area, high temperature area and fire spread area; the pre-trained machine learning model is obtained by the cloud server and multiple edge nodes through phased collaborative training based on multimodal federated learning and parameter aggregation rules.

[0124] The encryption module 603 is used to encrypt the data feature vector and send the encrypted data feature vector to the cloud server so that the cloud server can decrypt the encrypted data feature vector sent by each edge node and monitor the fire situation based on the decrypted data feature vector and the local pre-trained machine learning model.

[0125] In one optional implementation, the initial model is the machine learning model before the pre-trained machine learning model was pre-trained. The apparatus further includes a model training module, which is specifically used for:

[0126] Acquire local fire protection data and determine training sample data based on the local fire protection data;

[0127] The initial model is trained based on the training sample data to obtain a machine learning model with updated model parameters.

[0128] The model update parameters are encrypted, and the encrypted model update parameters are sent to the cloud server. The cloud server then decrypts, aggregates, and encrypts the encrypted model update parameters sent by each edge node in sequence to obtain the encrypted global model update parameters. The model update parameters refer to the updated model parameters obtained in this training.

[0129] Receive the global model update parameters sent from the cloud server, decrypt the global model update parameters, and update the model parameters of the initial model based on the decrypted global model update parameters;

[0130] Determine whether the machine learning model has reached the preset convergence condition. If yes, the pre-training ends and the pre-trained machine learning model is obtained. If no, repeat the above steps of obtaining local fire data, determining training sample data, training the model, obtaining model update parameters and sending them to the cloud server, receiving global model update parameters sent by the cloud server, and updating the model parameters based on the global model update parameters.

[0131] In one optional implementation, the plurality of edge nodes includes at least one core edge node, and the core edge node includes at least three identical data function modules and a majority voting module. The data function modules include data receiving, processing, and sending functions. The device further includes a verification module, which is specifically used for:

[0132] For each of the core edge nodes, the data feature vectors output by each of the data function modules are sent to the majority voting module, and the majority voting module compares the data feature vectors extracted by each of the data function modules for the target fire data.

[0133] When multiple data feature vectors contain the same data feature vector, the majority voting module determines the data feature vector with the largest number of identical data feature vectors as the target data feature vector that the core edge node will ultimately encrypt and send to the cloud server.

[0134] In one optional implementation, the verification module is further configured to:

[0135] When there are no identical data feature vectors among the multiple data feature vectors, the monitoring of the running status of the at least three identical data function modules is triggered. The running status includes at least one of the following: CPU utilization, memory usage ratio, and data processing latency.

[0136] If a fault is detected in the target data function module, the target data function module is isolated so that the data transmission task can be completed by the data function modules other than the target data function module.

[0137] The aforementioned fire protection IoT safety transmission device can execute the edge node-side technical solution provided in any of the method embodiments of the first aspect of this application, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment can be found in the fire protection IoT safety transmission method provided in any of the method embodiments of the first aspect of this application.

[0138] Figure 7 This is a schematic diagram of a fire protection IoT security transmission device provided in another embodiment of this application. This device is applied to a cloud server in a fire protection data management system, which includes the cloud server and multiple edge nodes. Figure 7 As shown, the fire protection IoT safety transmission device includes: a receiving module 701 and a determining module 702; wherein,

[0139] The receiving module 701 is used to receive the encrypted data feature vector sent by each of the edge nodes. The encrypted data feature vector is the data obtained by the edge nodes after acquiring local fire data and performing data preprocessing, feature extraction and encryption processing on the local fire data in sequence.

[0140] The determination module 702 is used to decrypt each of the encrypted data feature vectors and determine the fire situation based on each of the decrypted data feature vectors and the local pre-trained machine learning model, wherein the encrypted data feature vectors correspond one-to-one with the decrypted data feature vectors.

[0141] In one optional implementation, the fire situation includes multiple fire situation levels; the device further includes a control module, which is specifically used for:

[0142] When an escalation of the fire situation is detected, the system controls the addition of a first set of edge nodes to begin data transmission tasks, based on the current fire situation level; or...

[0143] When a downgrade of the fire situation is detected, the second number of edge nodes are controlled to stop performing data transmission tasks according to the current fire situation level, and data archiving and / or model parameter update processing is performed on the second number of edge nodes.

[0144] In one optional implementation, the plurality of edge nodes includes at least one core edge node, and the core edge node includes at least three identical data function modules and a majority voting module. The data function modules include data receiving, processing, and sending functions; the control module is further configured to:

[0145] Based on the current fire situation level, control a second number of edge nodes (excluding the core edge node) to stop performing data transmission tasks.

[0146] The aforementioned fire protection IoT security transmission device can execute the cloud server-side technical solution provided in any of the method embodiments of the second aspect of this application, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the fire protection IoT security transmission method provided in any of the method embodiments of the second aspect of this application.

[0147] This application also provides a computer program product.

[0148] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), payload programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer program products, which may include one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be an application-specific or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0149] Figure 8 This is a schematic diagram of an electronic device according to an embodiment of this application. The electronic device in this embodiment can be a cloud server or an edge node. (See reference...) Figure 8 , Figure 8 The electronic device 12 shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application. Figure 8As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0150] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, industry-standard architecture buses, microchannel architecture buses, enhanced industry-standard architecture buses, Video Electronics Standards Association (VESA) local buses, and peripheral component interconnect buses.

[0151] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0152] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory 30 and / or cache memory 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 8 Not shown; usually referred to as a "hard drive"). Although Figure 8 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0153] A program / utility 40 having a set (at least one) of program modules 46 may be stored, for example, in system memory 28. Such program modules 46 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 46 typically perform the functions and / or methods described in the embodiments of this application.

[0154] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 12, and / or with any device that enables electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network, wide area network, and / or public network, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although... Figure 8 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, independent disk redundant array systems, tape drives, and data backup storage systems.

[0155] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the fire protection IoT security transmission method provided in any embodiment of the first aspect of this application: acquiring multimodal local fire protection data and performing data preprocessing on the local fire protection data to obtain target fire protection data, wherein the local fire protection data is fire protection data collected by local sensing devices, and the multimodal local fire protection data includes at least one of the following: time-series signal type, image / video type, and event-triggered type; and extracting features from the target fire protection data on a preset feature dimension based on a pre-trained machine learning model to obtain... The data feature vector; the preset feature dimensions include at least one of the following: fire source area, high temperature area, and fire spread area; the pre-trained machine learning model is obtained by the cloud server and multiple edge nodes through phased collaborative training based on multimodal federated learning and parameter aggregation rules; the data feature vector is encrypted, and the encrypted data feature vector is sent to the cloud server so that the cloud server can decrypt the encrypted data feature vector sent by each edge node, and monitor the fire situation based on the decrypted data feature vector and the local pre-trained machine learning model.

[0156] For example, implementing the fire protection IoT security transmission method provided in any embodiment of the second aspect of this application: receiving encrypted data feature vectors sent by each of the edge nodes, wherein the encrypted data feature vectors are data obtained by the edge nodes after acquiring local fire protection data and sequentially performing data preprocessing, feature extraction and encryption processing on the local fire protection data; decrypting each of the encrypted data feature vectors, and determining the fire situation based on each of the decrypted data feature vectors and a local pre-trained machine learning model, wherein the encrypted data feature vectors correspond one-to-one with the decrypted data feature vectors.

[0157] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the fire protection IoT security transmission method provided in any of the method embodiments of the first aspect of this application: acquiring multimodal local fire protection data and performing data preprocessing on the local fire protection data to obtain target fire protection data, wherein the local fire protection data is fire protection data collected by local sensing devices, and the multimodal local fire protection data includes at least one of the following: time-series signal type, image / video type, and event-triggered type; extracting features from the target fire protection data on a preset feature dimension based on a pre-trained machine learning model to obtain a data feature vector; wherein the preset feature dimension includes at least one of the following: fire source area, high temperature area, and fire spread area, and the pre-trained machine learning model is obtained by the cloud server and multiple edge nodes through phased collaborative training based on multimodal federated learning and parameter aggregation rules; encrypting the data feature vector and sending the encrypted data feature vector obtained after encryption to the cloud server, so that the cloud server decrypts the encrypted data feature vector sent by each edge node, and monitors the fire situation based on the decrypted data feature vector obtained after decryption and the local pre-trained machine learning model.

[0158] Alternatively, the fire protection IoT security transmission method provided in any embodiment of the second aspect of this application can be implemented as follows: receiving encrypted data feature vectors sent by each of the edge nodes, wherein the encrypted data feature vectors are data obtained by the edge nodes after acquiring local fire protection data and sequentially performing data preprocessing, feature extraction, and encryption processing on the local fire protection data; decrypting each of the encrypted data feature vectors, and determining the fire situation based on each of the decrypted data feature vectors and a local pre-trained machine learning model, wherein the encrypted data feature vectors correspond one-to-one with the decrypted data feature vectors. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electronic device, apparatus, or device that is electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (erasable programmable read-only memory or flash memory), optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an electronic device, apparatus, or device that executes instructions.

[0159] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in conjunction with an electronic device, apparatus, or device that executes instructions.

[0160] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, radio frequency, etc., or any suitable combination thereof.

[0161] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages, such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0162] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A fire protection IoT security transmission method, characterized in that, An edge node is applied in a fire data management system, which includes a cloud server and multiple edge nodes. The edge nodes perform data transmission tasks to transmit data to the cloud server. The multiple edge nodes include at least one core edge node, which includes at least three identical data function modules and a majority voting module. The data function modules include data receiving, processing, and sending functions. The method includes: Acquire multimodal local fire protection data and perform data preprocessing on the local fire protection data to obtain target fire protection data. The local fire protection data is fire protection data collected by local sensing devices. The multimodal local fire protection data includes at least one of the following: time-series signal type, image / video type, and event-triggered type. Based on a pre-trained machine learning model, features are extracted from the target fire data in a preset feature dimension to obtain a data feature vector. The preset feature dimension includes at least one of the following: fire source area, high temperature area, and fire spread area. The pre-trained machine learning model is obtained by the cloud server and multiple edge nodes through phased collaborative training based on multimodal federated learning and parameter aggregation rules. The data feature vector is encrypted, and the encrypted data feature vector is sent to the cloud server so that the cloud server can decrypt the encrypted data feature vector sent by each edge node and monitor the fire situation based on the decrypted data feature vector and the local pre-trained machine learning model. For each of the core edge nodes, the data feature vectors output by each of the data function modules are sent to the majority voting module, and the majority voting module compares the data feature vectors extracted by each of the data function modules for the target fire data. When multiple data feature vectors contain the same data feature vector, the majority voting module determines the data feature vector with the largest number of identical data feature vectors as the target data feature vector that the core edge node will ultimately encrypt and send to the cloud server.

2. The method according to claim 1, characterized in that, The initial model is the machine learning model before the pre-trained machine learning model was pre-trained. The steps for pre-training the initial model include: Acquire local fire protection data and determine training sample data based on the local fire protection data; The initial model is trained based on the training sample data to obtain a machine learning model with updated model parameters. The model update parameters are encrypted, and the encrypted model update parameters are sent to the cloud server. The cloud server then decrypts, aggregates, and encrypts the encrypted model update parameters sent by each edge node in sequence to obtain the encrypted global model update parameters. The model update parameters refer to the updated model parameters obtained in this training. Receive the global model update parameters sent from the cloud server, decrypt the global model update parameters, and update the model parameters of the initial model based on the decrypted global model update parameters; Determine whether the machine learning model has reached the preset convergence condition. If yes, the pre-training ends and the pre-trained machine learning model is obtained. If no, repeat the above steps of obtaining local fire data, determining training sample data, training the model, obtaining model update parameters and sending them to the cloud server, receiving global model update parameters sent by the cloud server, and updating the model parameters based on the global model update parameters.

3. The method according to claim 1, characterized in that, The method further includes: When there are no identical data feature vectors among the multiple data feature vectors, the monitoring of the running status of the at least three identical data function modules is triggered. The running status includes at least one of the following: CPU utilization, memory usage ratio, and data processing latency. If a fault is detected in the target data function module, the target data function module is isolated so that the data transmission task can be completed by the data function modules other than the target data function module.

4. A fire protection IoT security transmission method, characterized in that, A cloud server is used in a fire data management system, the fire data management system including the cloud server and multiple edge nodes, and the method includes: The edge node receives encrypted data feature vectors sent by each edge node. The encrypted data feature vectors are data obtained by the edge node after acquiring local fire data and performing data preprocessing, feature extraction and encryption processing on the local fire data in sequence. The encrypted data feature vectors are decrypted, and the fire situation is determined based on the decrypted data feature vectors and the local pre-trained machine learning model. The encrypted data feature vectors correspond one-to-one with the decrypted data feature vectors.

5. The method according to claim 4, characterized in that, The fire situation includes multiple fire severity levels; the method further includes: When an escalation of the fire situation is detected, a first number of edge nodes are added to the fire suppression system to begin data transmission tasks, based on the current fire situation level; or... When the fire situation level is downgraded, the second number of edge nodes are controlled to stop performing data transmission tasks according to the current fire situation level, and data archiving and / or model parameter update processing is performed on the second number of edge nodes.

6. The method according to claim 5, characterized in that, The plurality of edge nodes includes at least one core edge node, and the core edge node includes at least three identical data function modules and a majority voting module. The data function modules include data receiving, processing, and sending functions. The step of controlling a second number of edge nodes to stop performing data transmission tasks according to the current fire situation level also includes: Based on the current fire situation level, control a second number of edge nodes (excluding the core edge node) to stop performing data transmission tasks.

7. A fire protection IoT safety transmission device, characterized in that, An edge node is used in a fire data management system, which includes a cloud server and multiple edge nodes. The edge nodes perform data transmission tasks to transmit data to the cloud server. The multiple edge nodes include at least one core edge node, which includes at least three identical data function modules and a majority voting module. The data function modules include data receiving, processing, and sending functions. The device includes: The acquisition module is used to acquire multimodal local fire protection data and perform data preprocessing on the local fire protection data to obtain target fire protection data. The local fire protection data is fire protection data collected by local sensing devices. The multimodal local fire protection data includes at least one of the following: time-series signal type, image / video type, and event-triggered type. The feature extraction module is used to extract features from the target fire data on a preset feature dimension based on a pre-trained machine learning model to obtain a data feature vector. The preset feature dimension includes at least one of the following: fire source area, high temperature area and fire spread area. The pre-trained machine learning model is obtained by the cloud server and multiple edge nodes through phased collaborative training based on multimodal federated learning and parameter aggregation rules. An encryption module is used to encrypt the data feature vectors and send the encrypted data feature vectors to the cloud server. The cloud server then decrypts the encrypted data feature vectors sent by each edge node and monitors fire conditions based on the decrypted data feature vectors and a locally pre-trained machine learning model. For each core edge node, the data feature vectors output by each data function module are sent to the majority voting module. The majority voting module compares the data feature vectors extracted by each data function module for the target fire data. When multiple data feature vectors contain the same data feature vector, the majority voting module determines the data feature vector with the most identical data feature vectors as the target data feature vector that the core edge node will ultimately encrypt and send to the cloud server.

8. A fire protection IoT safety transmission device, characterized in that, A cloud server used in a fire data management system, the fire data management system including the cloud server and multiple edge nodes, the device comprising: The receiving module is used to receive encrypted data feature vectors sent by each of the edge nodes. The encrypted data feature vectors are data obtained by the edge nodes after acquiring local fire protection data and performing data preprocessing, feature extraction and encryption processing on the local fire protection data in sequence. The determination module is used to decrypt each of the encrypted data feature vectors and determine the fire situation based on the decrypted data feature vectors and the local pre-trained machine learning model. The encrypted data feature vectors correspond one-to-one with the decrypted data feature vectors.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the fire protection IoT security transmission method as described in any one of claims 1 to 3, or implement the fire protection IoT security transmission method as described in any one of claims 4 to 6.

10. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the fire protection IoT security transmission method as described in any one of claims 1 to 3, or implements the fire protection IoT security transmission method as described in any one of claims 4 to 6.

Images