Asset data acquisition method based on Internet of Things

Abstract

The invention provides an asset data collection method based on the Internet of Things, and the method comprises the steps: constructing a directed acyclic graph model based on task decomposition and dependency for each node group, determining a task execution sequence and a data transmission mode between the nodes through employing a critical path analysis algorithm, and obtaining a task-oriented node cooperation process; for the data fusion result, dynamically updating a data model and a decision rule of the node by adopting an incremental learning algorithm, and timely discovering abnormal deviation of node data by adopting an anomaly detection algorithm to trigger dynamic adjustment of node marshalling; and constructing a node cooperation incentive mechanism based on the block chain, dynamically adjusting credit values and resource allocation of the nodes according to contribution degrees and task completion quality of the nodes, and constraining and arbitrating cooperation behaviors among the nodes by adopting an intelligent contract technology.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an asset data collection method based on the Internet of Things. Background Art

[0002] In complex asset monitoring scenarios, sensor nodes need to work together to complete data collection, fusion and reporting tasks. How to dynamically group nodes and assign tasks according to the characteristics of the monitored objects and business needs to achieve collaboration and optimization between nodes is a key issue. Collaborative grouping needs to consider factors such as node capabilities, locations, and energy consumption, and use intelligent algorithms to achieve autonomous organization and scheduling of nodes to improve the efficiency and accuracy of data collection. At the same time, it is also necessary to reduce energy consumption and communication overhead to ensure the stable operation of the data collection system. Summary of the invention

[0003] The present invention provides an asset data collection method based on the Internet of Things, which mainly includes:

[0004] Acquire the capability, location and energy consumption attribute information of the sensor nodes, perform cluster analysis on the attribute information using a clustering algorithm, obtain a subset of nodes with similar attributes, determine the role and task of each subset of nodes in the collaborative grouping, and obtain a node grouping solution driven by business needs;

[0005] A distributed optimization algorithm is used to comprehensively consider the communication cost, energy consumption balance and data redundancy factors between the nodes, and the node grouping scheme is dynamically adjusted to obtain a globally optimal node cooperation scheme. If the node capability or network topology changes, the re-optimization of the grouping scheme is triggered;

[0006] For each node grouping, a directed acyclic graph model based on task decomposition and dependency relationships is constructed, and a critical path analysis algorithm is used to determine the task execution order and data transmission method between the nodes to obtain a task-oriented node collaboration process;

[0007] In the process of node collaboration, a distributed data fusion algorithm is used to pre-process, extract features and semantically map the heterogeneous data collected by the nodes to obtain a unified data representation form, and a multi-sensor data association algorithm is used to mine the spatiotemporal correlation between data from different nodes to achieve cross-node data fusion;

[0008] Based on the data fusion results, an incremental learning algorithm is used to dynamically update the data model and decision rules of the node, and an abnormality detection algorithm is used to timely discover abnormal deviations of the node data, triggering dynamic adjustment of the node grouping;

[0009] In the data reporting stage, an adaptive data compression algorithm is used to dynamically adjust the data compression rate according to the relevance and redundancy of the data. A multi-path routing algorithm is used to comprehensively consider link quality, energy consumption balance and load balancing factors to optimize the data reporting path.

[0010] Construct a node collaboration incentive mechanism based on blockchain, dynamically adjust the node's credit value and resource allocation according to the node's contribution and task completion quality, and use smart contract technology to constrain and arbitrate the collaborative behavior between the nodes.

[0011] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0012] The present invention discloses an asset data collection method based on the Internet of Things. The method first performs attribute clustering and role assignment on sensor nodes to form a business-driven node grouping. Then, a distributed optimization algorithm is used to dynamically adjust the grouping scheme by comprehensively considering factors such as communication overhead and energy consumption balance. For each grouping, a task dependency graph model is constructed and a collaboration process is determined. In the collaboration process, distributed data fusion and multi-sensor association algorithms are used to process heterogeneous data. At the same time, incremental learning and anomaly detection algorithms are used to dynamically update the data model and trigger grouping adjustment. In the data reporting stage, adaptive compression and multi-path routing algorithms are used to optimize transmission. Finally, an incentive mechanism based on blockchain is introduced to dynamically adjust resource allocation according to node contribution. The present invention realizes intelligent collaboration and resource optimization configuration of sensor networks, and improves the overall performance and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 The present invention is a flowchart of an asset data collection method based on the Internet of Things.

[0014] Figure 2 It is a schematic diagram of an asset data collection method based on the Internet of Things of the present invention.

[0015] Figure 3 This is another schematic diagram of an asset data collection method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0017] like Figure 1-3 In this embodiment, an asset data collection method based on the Internet of Things may specifically include:

[0018] S101. Acquire the attribute information of sensor nodes, such as capability, location and energy consumption, and use intelligent algorithms to perform cluster analysis on the attribute information to obtain a subset of nodes with similar attributes; for each subset of nodes, determine its role and task in the collaborative grouping to obtain a node grouping solution driven by business needs.

[0019] The sensor node's attribute information such as capability, location and energy consumption is obtained. The K-means clustering algorithm is used to perform cluster analysis on the obtained attribute information, and nodes with similar attributes are divided into multiple subsets. For each node subset, the role of each subset in the collaborative grouping is determined by analyzing its attributes such as capability and location, and corresponding tasks are assigned to each role according to business needs, so as to obtain a node grouping scheme driven by business needs. According to the node grouping scheme, the Ql earning reinforcement learning algorithm is used to train the nodes, with the optimization goal of maximizing the task completion quality and node collaboration efficiency, so that each node can effectively collaborate with other nodes according to its own role and task. In the process of node execution, the energy consumption of each node is monitored in real time, and the energy consumption threshold is dynamically set using the control chart method. When the energy consumption of a node exceeds the threshold, the node is marked as a regrouping node, triggering the node regrouping process. According to the current node attribute information and business needs, the genetic algorithm is used to optimize the node grouping scheme. With the minimum node energy consumption and the maximum task completion quality as the optimization goals, the regrouped nodes are redistributed and the roles are adjusted to achieve dynamic optimization of node grouping. For the regrouped node subset, the instance-based transfer learning algorithm is used to select the source node with the highest task similarity with the target node as the knowledge source, and some training parameters and model structures of the source node are migrated to the target node to accelerate the learning and convergence speed of the target node. In the process of node collaboration, the node collaboration relationship graph is constructed by analyzing the communication data between nodes. The graph convolutional neural network algorithm is used to train the relationship graph with the optimization goal of maximizing the node collaboration efficiency. The attribute information and neighbor information of the nodes are aggregated through graph convolution operations, and the implicit collaboration relationship between nodes is mined to guide the nodes to dynamically adjust the collaboration strategy. Continuously monitor changes in business needs, set business demand change detection rules, compare the gap between current business indicators and expected goals, and when the gap exceeds the preset threshold, trigger a business demand change event and re-trigger the node grouping process. Based on the new business needs and node attributes, use the above method to regenerate the node grouping plan to achieve business-driven dynamic optimization of node grouping.

[0020] Exemplarily, after obtaining the attribute information of the sensor node such as capability, location and energy consumption, the K-means clustering algorithm is used to divide the nodes into several subsets. Among them, the K value can be set according to the number of nodes and business requirements, for example, 100 nodes are divided into 5 subsets. In the clustering process, the capability, location and energy consumption of the node are selected as feature vectors, and the similarity between nodes is measured by Euclidean distance. The nodes are divided into the nearest cluster center by iterative optimization until the mean square error of the nodes in the cluster is minimized. For each node subset, its capabilities, location and other attributes are analyzed to determine its role in the collaborative grouping. For example, nodes with strong computing power and close to the target area are divided into "execution nodes" responsible for executing specific tasks; nodes with low energy consumption and wide distribution of locations are divided into "relay nodes" responsible for forwarding and aggregation of data. Corresponding tasks are assigned to each role according to business needs, for example, target tracking tasks are assigned to "execution nodes" and data aggregation tasks are assigned to "relay nodes". The Ql earning reinforcement learning algorithm is used to train the nodes. The task completion quality and node collaboration efficiency are set as the reward function. Through continuous trial and error and learning, each node can effectively collaborate with other nodes according to its own role and task. In the process of node execution, the energy consumption of each node is monitored in real time, and the energy consumption threshold is dynamically set using the control chart method. For example, the upper and lower control limits of node energy consumption are determined based on historical data. When the energy consumption of a node exceeds the upper control limit, it is marked as a regrouping node. The genetic algorithm is used to optimize the node grouping scheme. The fitness function is the minimum node energy consumption and the maximum task completion quality. The regrouping nodes are redistributed and the roles are adjusted through selection, crossover, mutation and other operations to achieve dynamic optimization of node grouping. For the node subset after regrouping, the instance-based transfer learning algorithm is used to select the source node with the highest similarity to the target node task as the knowledge source. For example, the node that has performed similar target tracking tasks is selected as the knowledge source, and some of its training parameters and model structure are transferred to the target node to accelerate the learning speed and convergence speed of the target node. In the process of node collaboration, the node collaboration relationship graph is constructed by analyzing the communication data between nodes. The graph convolutional neural network algorithm is used to maximize the node collaboration efficiency as the loss function, and the attribute information and neighbor information of the node are aggregated through the graph convolution operation. For example, the node's capabilities, location and other attributes and the task execution status of the neighboring nodes are used as the node's features. The hidden layer representation of the node is obtained through graph convolution, and the implicit collaboration relationship between nodes is mined to guide the nodes to dynamically adjust the collaboration strategy. Continuously monitor the changes in business needs, and compare the gap between current business indicators and expected goals by setting business demand change detection rules.For example, when the task completion time exceeds the expected target by 20%, a business demand change event is triggered, and the node grouping process is retriggered. According to the new business requirements and node attributes, the node grouping plan is regenerated using the above method to achieve business-driven dynamic optimization of node grouping.

[0021] S102. Adopting a distributed optimization algorithm, comprehensively considering factors such as the communication cost, energy consumption balance and data redundancy between the nodes, dynamically adjusting the node grouping scheme, and obtaining a globally optimal node collaboration scheme; if the node capability or network topology changes, re-optimization of the grouping scheme is triggered.

[0022] Obtain resource information such as computing power, storage capacity, and communication bandwidth of each node in the network, as well as network topology information such as connection relationship between nodes and link quality. Preprocess the obtained node resource information and network topology information, extract key feature parameters, and construct node resource attribute matrix and network topology adjacency matrix. According to the node resource attribute matrix and network topology adjacency matrix, establish a mathematical model for node grouping optimization. In this model, set optimization goals such as minimum communication cost between nodes, balanced node energy consumption, and minimum data redundancy, as well as conditions such as node resource capacity limit and network connectivity constraint. Adopt particle swarm optimization algorithm to search for the optimal node grouping scheme under the premise of meeting the optimization goals and constraints. Through iterative optimization, continuously update particle position and speed, and finally converge to obtain the global optimal node grouping and collaboration scheme. According to the optimized node grouping scheme, generate node grouping and collaboration configuration instructions, and send the configuration instructions to the corresponding nodes. After receiving the configuration instructions, each node adjusts its own working mode and collaboration relationship according to the instructions to form a dynamically optimized node grouping. Deploy monitoring agents for node resources and link quality to collect resource usage and link status information of each node in real time. When the node resource usage rate exceeds the preset threshold or the link quality is lower than the preset threshold, it is determined that the node capacity or network topology has changed. When the monitoring program determines that the node capacity or network topology has changed, it triggers the parameter update and re-solution of the node grouping optimization model. Based on the updated model solution results, a new node grouping scheme is generated, and the updated configuration instructions are issued to achieve dynamic adjustment of node grouping and continuously maintain the global optimal node collaboration state.

[0023] Exemplarily, after obtaining the resource information and network topology information of each node in the network, the data is preprocessed. Extract key resource parameters such as node CPU frequency, memory size, storage capacity, etc., and construct a node resource attribute matrix. For example, for a network containing 100 nodes, a 100×5 matrix can be constructed, and each row represents 5 resource attribute values ​​of a node. At the same time, extract the connection relationship between nodes and parameters such as link bandwidth and delay, and construct a network topology adjacency matrix to represent the connectivity and communication cost between nodes. Based on the attribute matrix and the adjacency matrix, a node grouping optimization model is established. Set optimization objective functions such as minimizing communication cost, balancing node energy consumption, and reducing data redundancy, while considering node resource capacity constraints and network connectivity constraints to form a multi-objective optimization problem. Use the particle swarm algorithm to solve, initialize a group of particles, and each particle represents a possible node grouping scheme. In the iterative process, the fitness function is used to evaluate the pros and cons of each particle, and the particle speed and position are updated according to the particle's historical optimal position and the global optimal position until the algorithm converges or reaches the maximum number of iterations. The optimized node grouping scheme is converted into configuration instructions and sent to each node. The node adjusts the working mode according to the instructions, establishes a cooperative relationship with the specified node, and forms a dynamically optimized grouping structure. At the same time, a monitoring agent is deployed to collect information such as node CPU utilization, memory usage, and link bandwidth occupancy in real time. When the CPU utilization of a node exceeds 80% for 5 consecutive minutes or the link bandwidth occupancy exceeds 70% for 5 consecutive minutes, it is determined that the node resources or network topology have changed, triggering the parameter update and re-solution of the grouping optimization model. The model calculates the new optimal node grouping scheme based on the latest resource attribute matrix and adjacency matrix, generates updated configuration instructions, and sends them to each node, so that the node grouping scheme can adapt to dynamic changes in the network and continue to maintain the optimal state.

[0024] S103, for each node grouping, construct a directed acyclic graph model based on task decomposition and dependency relationships; use a critical path analysis algorithm to determine the task execution order and data transfer method between the nodes, and obtain a task-oriented node collaboration process.

[0025] Obtain node grouping information to understand the node groupings and their internal structures in the system. For each node grouping, use the task decomposition method to fine-grainedly decompose the tasks within the node to obtain each subtask, and clarify the input, output and processing logic of the task. Analyze the dependencies between subtasks and identify the order and data dependencies between tasks. Construct a directed acyclic graph model based on the dependencies, with subtasks as nodes of the graph and dependencies as directed edges to form a task dependency graph. Based on the task dependency graph, use the critical path analysis algorithm, including one of the critical path method (CPM) or the program evaluation and review method (PERT), to calculate the earliest start time, latest start time, earliest end time and latest end time of each subtask to determine the critical path; the tasks on the critical path have a decisive impact on the completion time of the entire process and need to be focused on and optimized. Determine the execution order of each subtask based on the results of the critical path analysis. For the tasks on the critical path, strictly sort them according to their earliest start time and latest end time to form a critical task execution sequence. For tasks on non-critical paths, their execution order can be adjusted appropriately without affecting the critical path to achieve reasonable use of resources. For each task in the task execution sequence, analyze its input data and output data to identify the data dependencies between tasks. For each task, clarify which upstream tasks its required input data comes from and which downstream tasks its output data will be used by. According to the data dependencies, build a data dependency graph to indicate the direction of data flow between tasks. The task execution sequence and the data dependency graph are integrated to obtain a task-oriented node collaboration process. This process clarifies the execution order of each task within the node and the data transfer method between tasks. The data generation and consumption relationship is clear, which can guide the actual task execution and data flow. The node collaboration process is optimized with the goal of minimizing the execution time of the entire process while satisfying the task dependencies. Workflow optimization algorithms, such as DAG (Directed Acyc lic Graph) scheduling algorithm or critical path optimization algorithm, are used to adjust the task execution order and data transfer method, reduce the waiting time of tasks and data transmission overhead, and improve the parallelism and efficiency of the process. On the basis of the optimized node collaboration process, further consider the collaboration and communication between node groups. Analyze the task dependency and data dependency between different node groups, and build a global task dependency graph and data dependency graph. Use a distributed workflow management system, such as Apache Airflow or Kubernetes, to coordinate task scheduling and data transmission between different node groups, and achieve global task scheduling and optimization. Through the above steps, an optimized, task-oriented node collaboration process can be obtained, which clarifies the task execution order and data transmission method within and between nodes.This process can guide the actual task deployment and execution, improve the performance and efficiency of the system, and achieve efficient collaboration of node grouping.

[0026] Exemplarily, after obtaining the node grouping information, the tasks within each node grouping are finely decomposed. For example, a data processing task is decomposed into subtasks such as data collection, preprocessing, feature extraction, model training and result evaluation, and the input, output and processing logic of each subtask are clarified. By analyzing the dependencies between subtasks, it is identified that data collection is a prerequisite task for preprocessing, and preprocessing is a prerequisite task for feature extraction, forming a directed acyclic graph model. Using the critical path analysis algorithm, the critical path is calculated as data collection → preprocessing → feature extraction → model training, and these tasks have a decisive influence on the completion time of the entire process. According to the results of the critical path analysis, the execution order of each subtask is determined, and a data dependency graph is constructed to clarify that the output data of the data collection task will be used by the preprocessing task, and the output data of the preprocessing task will be used by the feature extraction task, forming a clear data flow direction. On this basis, the DAG scheduling algorithm is used to optimize the task execution order. By executing independent subtasks in parallel, the waiting time of the model training task is shortened from 2 hours to 1 hour, and the execution time of the entire process is optimized from the original 10 hours to 8 hours. Finally, Apache AI ​​flow is used to coordinate task scheduling and data transmission between different node groups to achieve global task scheduling and optimization. Through the above steps, an optimized, task-oriented node collaboration process is obtained, which provides guidance for actual task deployment and execution and improves the performance and efficiency of the system.

[0027] S104. During the node collaboration process, a distributed data fusion algorithm is used to preprocess, extract features and semantically map the heterogeneous data collected by the nodes to obtain a unified data representation; a multi-sensor data association algorithm is used to mine the spatiotemporal correlation between data from different nodes to achieve cross-node data fusion.

[0028] Obtain heterogeneous raw data collected by distributed nodes, use corresponding preprocessing methods for data of different types and formats, clean, denoise and standardize the data, and obtain a standardized data set. According to the preprocessed data features, the principal component analysis algorithm is used to extract the key features of the data, reduce the data dimension, and obtain a streamlined feature vector representation. By constructing an ontology knowledge base and semantic mapping rules, the extracted data features are mapped to a unified semantic space, eliminating the semantic differences between different data sources, and obtaining a semantically consistent feature representation. For the semantic feature data of different nodes, the mutual information method is used to calculate the correlation between the data of different nodes, and the degree of correlation is quantified by calculating the mutual information value between the features, and the spatiotemporal correlation pattern of the data is mined. According to the spatiotemporal correlation strength of the data, the network topology structure of cross-node data fusion is constructed, the path and order of data fusion are determined, and a hierarchical data fusion framework is formed. On the basis of the data fusion framework, a distributed data fusion algorithm based on Kalman filtering is adopted, and Kalman filtering is run on each node. Through data exchange and update between nodes, the associated data of multiple nodes are comprehensively utilized to generate the fused consistency results. The fused results are visualized using Tableau, and the effect of data fusion is intuitively presented through charts and dashboards. At the same time, statistical methods such as mean square error and correlation coefficient are used to evaluate the accuracy of data fusion, and the parameters of the Kalman filter algorithm, such as the covariance matrix of process noise and measurement noise, are dynamically adjusted according to the evaluation results to continuously optimize the performance of data fusion. Finally, high-quality fusion data is obtained to provide support for subsequent data analysis and applications.

[0029] Exemplarily, after obtaining heterogeneous raw data collected by distributed nodes, corresponding preprocessing methods are used for different types of data such as text, image, and audio. For text data, regular expressions are used to filter out HTML tags and special characters, and word segmentation and stop word removal are performed; for image data, median filtering is used to remove salt and pepper noise, and histogram equalization is used to enhance contrast; for audio data, wavelet transform is used to reduce noise on the signal and convert it into frequency domain features. After preprocessing, a normalized data set is obtained. According to the preprocessed data features, the principal component analysis algorithm is used to reduce the original data from 1000 dimensions to 50 dimensions through eigenvalue decomposition and the selection of the first 5 principal components, and a simplified feature vector representation is obtained. By constructing an ontology knowledge base containing 500 concepts and 1000 relationships, and defining semantic mapping rules, such as "temperature" corresponds to "air temperature" and "pressure" corresponds to "atmospheric pressure", the extracted data features are mapped to a unified semantic space. For the semantic feature data of different nodes, the mutual information method is used to calculate the correlation between the features. For example, the mutual information value of the "temperature" of node A and the "humidity" of node B is 8, indicating that they have a strong correlation. According to the calculated mutual information matrix, a data fusion network topology containing 10 nodes is constructed, and the hierarchical fusion path of first fusing the temperature and humidity data and then fusing the pressure data is determined. On this basis, the distributed data fusion algorithm based on Kalman filtering is adopted, the initial state estimation value and covariance matrix are set, and the estimation error is reduced from the initial 10% to 5% through 8 iterations, and the consistency result after fusion is generated. Tableau is used to draw line charts and scatter plots for the fusion results, which intuitively show the consistency trend of data from different nodes. At the same time, the mean square error of the data before and after fusion is calculated to drop from 8 to 5, and the correlation coefficient is increased from 6 to 95, which proves the effectiveness of data fusion. According to the evaluation results, the process noise covariance matrix parameters of the Kalman filter algorithm are dynamically adjusted. After 3 adjustments, the fusion accuracy is further improved by 5%. Finally, the high-quality fused data lays the foundation for subsequent data analysis and application.

[0030] S105. Based on the data fusion result, an incremental learning algorithm is used to dynamically update the data model and decision rules of the node; an anomaly detection algorithm is used to timely discover abnormal deviations of the node data and trigger dynamic adjustment of the node grouping.

[0031] Obtain the data fusion results and input them into the incremental learning algorithm, such as random forest or support vector machine, to dynamically update the node data model and decision rules to obtain the updated node data model and decision rules. Apply the updated node data model and decision rules to the node data, and use anomaly detection algorithms such as isolation forest or local anomaly factor to determine whether the node data has abnormal deviation. If there is abnormal deviation, the dynamic adjustment of the node grouping is triggered. According to the statistical characteristics of the abnormal deviation of the node data, such as the deviation mean and variance, the priority of the node grouping adjustment is determined, and the node grouping with a larger degree of abnormal deviation is adjusted first. For the node grouping that needs to be adjusted, obtain its historical data within a certain time range from the historical database, and divide the nodes into different groups through clustering algorithms such as K-means, so that the data model and decision rules of the nodes in the group are highly similar. For each newly divided node grouping, based on the data model and decision rules of its internal nodes, the overall data model and decision rules of the grouping are generated through integrated learning algorithms such as Bagging or Boosting. The newly generated node grouping data model and decision rules are updated to the local storage or memory of the corresponding node through the configuration file or API interface to complete the dynamic adjustment of the node grouping. Set a fixed time interval, such as 5 minutes, to continuously monitor the data fusion results and node data. When an abnormal deviation is detected or the preset adjustment threshold is reached, repeat the above steps to achieve continuous optimization and dynamic evolution of the node data model, decision rules, and grouping.

[0032] Exemplarily, the data fusion results are input into the random forest algorithm for incremental learning, the number of trees is set to 100, the maximum depth is 10, and after 5 iterations of training, the data model accuracy of node A is increased from 85% to 92%, and the decision rule coverage of node B is increased from 90% to 96%. The updated data model and decision rules are applied to detect abnormalities in the node data. The isolation forest algorithm is used, the number of trees is set to 50, the subsampling ratio is set to 8, and the abnormal threshold is set to 6. The abnormal deviation of the data of node C is detected to be 7, which is higher than the threshold, triggering the node grouping adjustment. According to the mean of the abnormal deviation of node C, which is 7 and the variance is 2, its adjustment priority is determined to be high. The historical data of node C in the last hour is obtained, and the K-means algorithm is used for clustering. The number of clusters k is set to 3 and the number of iterations is 10. Node C is divided into 2 new groups. Group 1 contains 3 nodes and group 2 contains 2 nodes. The data model similarity of the nodes in the group reaches more than 95%. The Bagging algorithm is used for ensemble learning of group 1, and the base learner is set as decision tree, the ensemble number is 50, and the overall data model of group 1 is generated; the AdaBoost algorithm is used for ensemble learning of group 2, and the base learner is set as SVM, the ensemble number is 30, and the overall decision rule of group 2 is generated. The new grouping model and rules are updated to the corresponding nodes through the API interface to complete the dynamic adjustment. The fusion results and node data are monitored every 5 minutes. When the abnormal deviation of node D reaches 8, the above adjustment process is repeated to continuously optimize the overall performance of node grouping, the accuracy of abnormal detection is increased from 90% to 95%, and the generalization ability of the node data model is increased from 92% to 98%, realizing the dynamic evolution of node grouping.

[0033] S106. In the data reporting stage, an adaptive data compression algorithm is used to dynamically adjust the data compression rate according to the relevance and redundancy of the data; a multi-path routing algorithm is used to comprehensively consider factors such as link quality, energy consumption balance and load balancing to optimize the data reporting path.

[0034] Obtain the raw data to be reported, preprocess the data, and use the median filter method to remove obvious noise and outliers to improve data quality. Analyze the preprocessed data, use the Pearson correlation coefficient to calculate the correlation between different data segments, and determine the degree of data correlation based on the size of the correlation coefficient. According to the degree of data correlation, an adaptive data compression algorithm is used to set different compression rate thresholds for data segments with different degrees of correlation. The threshold can be set based on historical data and experience. If the correlation coefficient of the data segment is greater than the corresponding threshold, the compression rate of the data segment is increased, otherwise the original compression rate is maintained. The compressed data packet uses the multi-attribute decision method to dynamically select the appropriate data transmission path according to its size and priority. For data packets with large data volume and high priority, a path with short delay and large bandwidth is selected. During the data transmission process, the CPU occupancy and memory usage of each node are monitored in real time. When the CPU occupancy of a node exceeds 80% or the memory usage exceeds 90%, the load balancing mechanism between nodes is started, and the consistent hashing algorithm is used to dynamically migrate some data packets to other nodes with lower load for processing. After the data packet arrives at the aggregation node, the corresponding decompression algorithm is used to restore the data, and the cyclic redundancy check (CRC) method is used to check the integrity. The data that passes the check is reported to the data center to complete the entire data reporting process.

[0035] Exemplarily, after obtaining the raw data to be reported, the data is first preprocessed, and the median filtering method is used to remove obvious noise and outliers. The sliding window size is set to 5, and the raw data is replaced by finding the median of the data in the window, which effectively improves the data quality. Then the preprocessed data is analyzed, and the Pearson correlation coefficient is used to calculate the correlation between different data segments. The correlation degree of the data is determined by setting a threshold of 8. If the correlation coefficient is greater than 8, the data is considered to be highly correlated. According to the correlation degree of the data, an adaptive data compression algorithm is used, and the compression rate is set to 60% for the data segment with a correlation coefficient greater than 9, and the compression rate is set to 40% for the data segment with a correlation coefficient between 8 and 9. The original compression rate of 20% is maintained for the data segment with a correlation coefficient less than 8. The compressed data packet uses a multi-attribute decision method to dynamically select a suitable data transmission path according to its size and priority, and comprehensively considers factors such as data packet size, priority, path delay and bandwidth, and calculates the comprehensive score of each path by weighted summation, and selects the path with the highest score for transmission. During the data transmission process, the CPU occupancy rate and memory usage rate of each node are monitored in real time. When the CPU occupancy rate of node A reaches 85%, the load balancing mechanism between nodes is started, and the consistent hashing algorithm is used to dynamically migrate 30% of the data packets to nodes B and C with lower loads for processing, ensuring the efficiency of data transmission. After the data packet arrives at the aggregation node, the corresponding decompression algorithm is used to restore the data, and the cyclic redundancy check (CRC) method is used for integrity verification. The generating polynomial is set to CRC-16. By comparing the CRC check value of the data packet with the recalculated CRC value, it is ensured that there is no loss or error in the data transmission process. Finally, the verified data is reported to the data center, completing the entire data reporting process, and realizing the full-link optimization and guarantee of data from collection to reporting.

[0036] S107. Construct a node collaboration incentive mechanism based on blockchain, dynamically adjust the credit value and resource allocation of the node according to the contribution of the node and the quality of task completion; use smart contract technology to constrain and arbitrate the collaborative behavior between the nodes.

[0037] According to the pre-established node credit evaluation model, combined with the historical behavior data of the node in the blockchain network, the support vector machine algorithm is used to dynamically calculate the comprehensive credit score of the node. The credit score is mapped to the corresponding credit level according to the preset interval, and the credit level is written into the blockchain account book for other nodes to query and reference. The behavior data of the node participating in the task collaboration, including the task completion time, task quality score, etc., are obtained through the smart contract rules. According to the task characteristics and the historical performance of the node, the weight coefficients of each indicator are preset, and the contribution of the node in the current task is calculated by the weighted average algorithm, and the resource allocation weight of the node is dynamically adjusted according to the contribution. The expected standard of task completion quality is set and used as the threshold for judging the performance of the node. If the task completion quality of the node is lower than the preset threshold, the smart contract is triggered to deduct the credit value of the node and reduce its resource allocation weight; if the task completion quality is higher than the preset threshold, the credit value and resource allocation weight of the node are increased to encourage the contribution of high-quality nodes. When a collaboration dispute occurs between nodes, the dispute behavior is judged through the blockchain arbitration mechanism. The arbitration mechanism votes on the dispute event through multiple trusted nodes and makes a final decision based on the voting results. According to the judgment results, the credit value of the relevant nodes is rewarded or punished, the credit value of the offending nodes is deducted until it is downgraded, and its resource allocation weight is reduced in the subsequent task allocation. Asymmetric encryption algorithms (such as RSA) are used to encrypt the collaborative behavior data between nodes to ensure the confidentiality and integrity of the data. The encrypted behavior data is written into the blockchain, and the tamper-proof and traceable characteristics of the blockchain are used to achieve reliable recording and auditing of the node collaborative behavior. Deep reinforcement learning algorithms, such as Deep Q-Network (DQN), are introduced to learn and optimize the parameter weights in the node credit evaluation model and the decision rules in the resource allocation strategy by continuously interacting with the environment and obtaining feedback. According to the operation status of the blockchain network, such as the credit level distribution of the nodes, the quality of task completion and other indicators, the incentive and penalty rules in the smart contract are dynamically adjusted to achieve the adaptive evolution of the incentive mechanism. The blockchain consensus mechanism (such as proof of work or proof of equity) is used to achieve consistency verification of node collaborative behavior, and the authenticity and reliability of the recorded collaborative behavior data are ensured through multi-party verification. Use blockchain technology to build a trusted collaborative environment, promote nodes to actively participate in collaboration and improve the quality of task completion, and maintain the healthy operation of the blockchain network.

[0038] Exemplarily, in the node credit assessment model, the support vector machine algorithm is used to train the historical behavior data of the node, and the optimal credit assessment model is constructed by setting the RBF kernel function parameter γ = 1 and the penalty coefficient C = 10. According to the comprehensive credit score of the node calculated by the model, it is mapped into 5 credit levels: 90 points or more is A level, 80-90 points is B level, 70-80 points is C level, 60-70 points is D level, and 60 points or less is E level. The behavior data of the node participating in task collaboration is obtained by using the smart contract rules, including task completion time, quality score, etc., where the task completion time weight coefficient is set to 6, the quality score weight coefficient is set to 4, and the weighted average algorithm is used to obtain the node's contribution. If the quality of the node's task completion is lower than the preset threshold of 85 points, the smart contract is triggered to deduct 20 points from the node's credit value, and reduce its resource weight by 20% in subsequent task allocation; if it is higher than 95 points, the credit value is increased by 10 points and the resource weight is increased by 10%. When a collaboration dispute occurs between nodes, 5 trusted nodes will conduct arbitration voting. If more than 3 nodes vote to determine that node A has violated the rules, 50 points will be deducted from A's credit value, and its resource weight will be reduced by 50% in subsequent tasks. The collaboration behavior data between nodes is encrypted using the 2048-bit RSA algorithm to ensure data security. The DQN algorithm is introduced. By setting the learning rate α=01 and the discount factor γ=9, the learning iteration of "state-action-reward" is continuously carried out to optimize the node credit evaluation model and resource allocation strategy. According to the operation status of the blockchain network, the incentive and penalty rules in the smart contract are dynamically adjusted. For example, when the average credit rating of the node is lower than level C, the task completion quality threshold is increased to 90 points to promote the node to improve its collaboration performance. Finally, the proof-of-work consensus mechanism is used to require nodes to provide proof of work with a hash value difficulty of 10^20 to verify the authenticity of the recorded collaboration behavior data and maintain the trusted collaboration environment of the blockchain network.

[0039] Based on the above embodiments of the present invention, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the content in the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. A method for collecting asset data based on the Internet of Things, characterized in that: The method comprises: Acquire the capability, location and energy consumption attribute information of the sensor nodes, perform cluster analysis on the attribute information using a clustering algorithm, obtain a subset of nodes with similar attributes, determine the role and task of each subset of nodes in the collaborative grouping, and obtain a node grouping solution driven by business needs; A distributed optimization algorithm is used to comprehensively consider the communication cost, energy consumption balance and data redundancy factors between the nodes, and the node grouping scheme is dynamically adjusted to obtain a globally optimal node cooperation scheme. If the node capability or network topology changes, the re-optimization of the grouping scheme is triggered; For each node grouping, a directed acyclic graph model based on task decomposition and dependency relationships is constructed, and a critical path analysis algorithm is used to determine the task execution order and data transmission method between the nodes to obtain a task-oriented node collaboration process; In the process of node collaboration, a distributed data fusion algorithm is used to pre-process, extract features and semantically map the heterogeneous data collected by the nodes to obtain a unified data representation form, and a multi-sensor data association algorithm is used to mine the spatiotemporal correlation between data from different nodes to achieve cross-node data fusion; Based on the data fusion results, an incremental learning algorithm is used to dynamically update the data model and decision rules of the node, and an abnormality detection algorithm is used to timely discover abnormal deviations of the node data, triggering dynamic adjustment of the node grouping; In the data reporting stage, an adaptive data compression algorithm is used to dynamically adjust the data compression rate according to the relevance and redundancy of the data. A multi-path routing algorithm is used to comprehensively consider link quality, energy consumption balance and load balancing factors to optimize the data reporting path. Construct a node collaboration incentive mechanism based on blockchain, dynamically adjust the node's credit value and resource allocation according to the node's contribution and task completion quality, and use smart contract technology to constrain and arbitrate the collaborative behavior between the nodes.

2. The method according to claim 1, characterized in that The capability, location and energy consumption attribute information of the sensor nodes are obtained, and the attribute information is clustered and analyzed by a clustering algorithm to obtain a subset of nodes with similar attributes; for each subset of nodes, its role and task in the collaborative grouping is determined to obtain a node grouping scheme driven by business needs, including: The capability, location and energy consumption attribute information of sensor nodes are obtained. K-means clustering algorithm is used to perform cluster analysis on the acquired attribute information, and nodes with similar attributes are divided into multiple subsets. For each node subset, by analyzing its capabilities and location attributes, determine the role of each subset in the collaborative grouping, and assign corresponding tasks to each role according to business needs, so as to obtain a node grouping solution driven by business needs; According to the node grouping plan, the Q-learning reinforcement learning algorithm is used to train the nodes, with the optimization goal of maximizing the task completion quality and node collaboration efficiency, so that each node can effectively collaborate with other nodes according to its own role and task; During the process of node execution, the energy consumption of each node is monitored in real time, and the energy consumption threshold is dynamically set using the control chart method. When the energy consumption of a node exceeds the threshold, the node is marked as a regrouping node, triggering the node regrouping process; According to the current node attribute information and business needs, the genetic algorithm is used to optimize the node grouping scheme, with the minimum node energy consumption and the maximum task completion quality as the optimization goals, and the regrouped nodes are reallocated and the roles are adjusted to achieve dynamic optimization of node grouping; For the reorganized node subset, an instance-based transfer learning algorithm is used to select the source node with the highest task similarity with the target node as the knowledge source, and some training parameters and model structures of the source node are transferred to the target node to accelerate the learning speed and convergence speed of the target node. In the process of node collaboration, the communication data between nodes is analyzed to construct a node collaboration relationship graph. The graph convolutional neural network algorithm is used to train the relationship graph with the optimization goal of maximizing the node collaboration efficiency. The attribute information and neighbor information of the nodes are aggregated through graph convolution operations to mine the implicit collaboration relationship between nodes and guide the nodes to dynamically adjust the collaboration strategy. Continuously monitor changes in business needs, set business demand change detection rules, compare the gap between current business indicators and expected goals, and when the gap exceeds the preset threshold, trigger a business demand change event and re-trigger the node grouping process. Based on the new business needs and node attributes, use the above method to regenerate the node grouping plan to achieve business-driven dynamic optimization of node grouping.

3. The method according to claim 1, characterized in that The distributed optimization algorithm is used to comprehensively consider the communication cost, energy consumption balance and data redundancy factors between the nodes, dynamically adjust the node grouping scheme, and obtain the global optimal node cooperation scheme; If the node capability or network topology changes, re-optimization of the grouping scheme is triggered, including: Obtain node resource information of each node in the network, including the computing power, storage capacity and communication bandwidth of each node, as well as network topology information, including the connection relationship and link quality between each node; Preprocess the acquired node resource information and network topology information, extract key feature parameters, and construct the node resource attribute matrix and network topology adjacency matrix; According to the node resource attribute matrix and the network topology adjacency matrix, a mathematical model for node grouping optimization is established; In this model, optimization objectives are set, including minimum communication cost between nodes, balanced node energy consumption, and minimum data redundancy, as well as constraints, including node resource capacity limitations and network connectivity; The particle swarm optimization algorithm is used to search for the optimal node grouping scheme under the premise of meeting the optimization objectives and constraints; Through iterative optimization, the particle positions and velocities are continuously updated, and finally convergence is achieved to obtain the global optimal node grouping and collaboration solution; According to the optimized node grouping scheme, generate node grouping and collaboration configuration instructions, and send the configuration instructions to the corresponding nodes; After receiving the configuration instructions, each node adjusts its own working mode and cooperation relationship according to the instructions to form a dynamically optimized node grouping; Deploy monitoring agents for node resources and link quality to collect resource usage and link status information of each node in real time; When the node resource usage exceeds a preset threshold or the link quality is lower than a preset threshold, it is determined that the node capability or network topology has changed; When the monitoring program determines that the node capacity or network topology has changed, it triggers the parameter update and re-solution of the node grouping optimization model; Based on the updated model solution results, a new node grouping plan is generated, and updated configuration instructions are issued to achieve dynamic adjustment of node grouping and continuously maintain the global optimal node collaboration state.

4. The method according to claim 1, characterized in that: For each node grouping, a directed acyclic graph model based on task decomposition and dependency relationships is constructed; a critical path analysis algorithm is used to determine the task execution order and data transmission method between the nodes, and a task-oriented node collaboration process is obtained, including: Obtain node grouping information to understand the node groups existing in the system and their internal structures; For each node grouping, the task decomposition method is used to decompose the tasks within the node into fine-grained parts to obtain various subtasks, and to clarify the input, output and processing logic of the tasks; Analyze the dependencies between subtasks and identify the order and data dependencies between tasks; A directed acyclic graph model is constructed based on dependency relationships, with subtasks as nodes of the graph and dependency relationships as directed edges to form a task dependency graph. Based on the task dependency graph, a critical path analysis algorithm, including the critical path method (CPM) or the program evaluation and review method (PERT), is used to calculate the earliest start time, latest start time, earliest finish time, and latest finish time of each subtask to determine the critical path; The tasks on the critical path have a decisive impact on the completion time of the entire process and need to be focused on and optimized; Determine the execution order of each subtask based on the results of critical path analysis; For tasks on the critical path, they are strictly sorted according to their earliest start time and latest end time to form a critical task execution sequence; For tasks on non-critical paths, their execution order can be adjusted without affecting the critical path to achieve reasonable utilization of resources; For each task in the task execution sequence, analyze its input data and output data and identify the data dependencies between tasks; For each task, clearly identify the upstream tasks from which its input data comes, and the downstream tasks that will use its output data. According to the data dependency, a data dependency graph is constructed to indicate the data flow direction between tasks; The task execution sequence and data dependency graph are integrated to obtain the task-oriented node collaboration process; This process clarifies the execution order of each task within the node and the data transmission method between tasks; The relationship between data generation and consumption is clear, which can guide the actual task execution and data flow; Optimize the node collaboration process, with the goal of minimizing the execution time of the entire process while satisfying task dependencies; Adopt workflow optimization algorithms, including directed acyclic graph (DAG) scheduling algorithms or critical path optimization algorithms, to adjust the task execution order and data transmission method, reduce task waiting time and data transmission overhead, and improve process parallelism and efficiency; On the basis of the optimized node collaboration process, the collaboration and communication between node groups are further considered; Analyze the task dependency and data dependency between different node groups, and build a global task dependency graph and data dependency graph; Use a distributed workflow management system, including Apache Airflow or Kubernetes, to coordinate task scheduling and data transmission between different node groups to achieve global task scheduling and optimization; Through the above steps, an optimized and task-oriented node collaboration process can be obtained, which clarifies the task execution order and data transmission method within and between nodes; This process can guide the actual task deployment and execution, improve the performance and efficiency of the system, and achieve efficient collaboration of node grouping.

5. The method according to claim 1, characterized in that In the node collaboration process, a distributed data fusion algorithm is used to pre-process, extract features and perform semantic mapping on the heterogeneous data collected by the nodes to obtain a unified data representation; a multi-sensor data association algorithm is used to mine the spatiotemporal correlation between data from different nodes to achieve cross-node data fusion, including: Obtain heterogeneous raw data collected by distributed nodes, use corresponding preprocessing methods for data of different types and formats, clean, denoise and standardize the data to obtain a standardized data set; According to the characteristics of the preprocessed data, the principal component analysis algorithm is used to extract the key features of the data, reduce the data dimension, and obtain a simplified feature vector representation; By building an ontology knowledge base and semantic mapping rules, the extracted data features are mapped to a unified semantic space, eliminating the semantic differences between different data sources and obtaining a semantically consistent feature representation. For the semantic feature data of different nodes, the mutual information method is used to calculate the correlation between the data of different nodes. The degree of correlation is quantified by calculating the mutual information value between the features, and the spatiotemporal correlation pattern of the data is mined; According to the temporal and spatial correlation strength of the data, a network topology structure for cross-node data fusion is constructed, the path and sequence of data fusion are determined, and a hierarchical data fusion framework is formed; Based on the data fusion framework, a distributed data fusion algorithm based on Kalman filtering is adopted. Kalman filtering is run on each node. Through data exchange and update between nodes, the associated data of multiple nodes are comprehensively utilized to generate the fused consistency results. Tableau is used to visualize the fusion results, and the effect of data fusion is intuitively presented through charts and dashboards; At the same time, statistical methods, including any one of the mean square error and correlation coefficient methods, are used to evaluate the accuracy of data fusion, and the parameters of the Kalman filter algorithm, including the covariance matrix of process noise and measurement noise, are dynamically adjusted according to the evaluation results to continuously optimize the performance of data fusion; Ultimately, high-quality fused data is obtained to provide support for subsequent data analysis and applications.

6. The method according to claim 1, characterized in that The method adopts an incremental learning algorithm to dynamically update the data model and decision rules of the node based on the data fusion result; adopts an abnormality detection algorithm to timely discover abnormal deviations of the node data and trigger dynamic adjustment of the node grouping, including: Obtaining data fusion results, inputting them into an incremental learning algorithm, including at least one of a random forest or a support vector machine, dynamically updating a data model and a decision rule of a node, and obtaining an updated node data model and decision rule; Applying the updated node data model and decision rules to the node data, determining whether the node data has abnormal deviations through an anomaly detection algorithm including at least one of an isolation forest or a local anomaly factor; If there is an abnormal deviation, dynamic adjustment of node grouping is triggered; According to the statistical characteristics of abnormal deviation of node data, including deviation mean and variance, the priority of node grouping adjustment is determined, and node grouping with greater abnormal deviation is adjusted first; For the node groups that need to be adjusted, historical data within a certain time range is obtained from the historical database, and the nodes are divided into different groups using the K-means clustering algorithm, so that the data models and decision rules of the nodes in the group are more similar; For each newly divided node grouping, based on the data model and decision rules of its internal nodes, an integrated learning algorithm, including Bagging or Boosting, is used to generate the overall data model and decision rules of the grouping; Update the newly generated node grouping data model and decision rules to the local storage or memory of the corresponding node through the configuration file or API interface to complete the dynamic adjustment of the node grouping; Set a fixed time interval, such as 5 minutes, to continuously monitor the data fusion results and node data; When an abnormal deviation is detected or the preset adjustment threshold is reached, the above steps are repeated to achieve continuous optimization and dynamic evolution of the node data model, decision rules and formation.

7. The method according to claim 1, characterized in that In the data reporting stage, an adaptive data compression algorithm is used to dynamically adjust the data compression rate according to the relevance and redundancy of the data; a multi-path routing algorithm is used to comprehensively consider the link quality, energy consumption balance and load balancing factors to optimize the data reporting path, including: Obtain the raw data to be reported, pre-process the data, use the median filter method to remove obvious noise and outliers, and improve data quality; Analyze the preprocessed data, use the Pearson correlation coefficient to calculate the correlation between different data segments, and determine the degree of data correlation based on the size of the correlation coefficient; According to the relevance of the data, an adaptive data compression algorithm is used to set different compression rate thresholds for data segments with different relevance. The thresholds can be set based on historical data. If the correlation coefficient of the data segment is greater than the corresponding threshold, the compression rate of the data segment is increased, otherwise the original compression rate is maintained; The compressed data packets are dynamically selected to have a suitable data transmission path according to their size and priority using a multi-attribute decision-making method; For packets with large data volume and high priority, a path with short latency and large bandwidth is selected; During data transmission, the CPU usage and memory usage of each node are monitored in real time. When the CPU usage of a node exceeds 80% or the memory usage exceeds 90%, the load balancing mechanism between nodes is started, and the consistent hashing algorithm is used to dynamically migrate some data packets to other nodes with lower loads for processing; After the data packet arrives at the aggregation node, the corresponding decompression algorithm is used to restore the data, and the cyclic redundancy check (CRC) method is used to check the integrity. The data that passes the check is reported to the data center to complete the entire data reporting process.

8. The method according to claim 1, characterized in that The node collaboration incentive mechanism based on blockchain is constructed to dynamically adjust the node's credit value and resource allocation according to the node's contribution and task completion quality; and the smart contract technology is used to constrain and arbitrate the collaborative behavior between the nodes, including: Based on the pre-established node credit assessment model and combined with the node’s historical behavior data in the blockchain network, the support vector machine algorithm is used to dynamically calculate the node’s comprehensive credit score; Map the credit score to the corresponding credit rating according to the preset interval, and write the credit rating into the blockchain ledger for other nodes to query and reference; Obtain the behavior data of nodes participating in task collaboration through smart contract rules, including task completion time and task quality score; According to the task characteristics and the historical performance of the node, the weight coefficients of each indicator are preset, and the contribution of the node in the current task is calculated using the weighted average algorithm, and the resource allocation weight of the node is dynamically adjusted according to the contribution; Set expected standards for task completion quality and use them as thresholds for judging node performance; If the task completion quality of a node is lower than the preset threshold, the smart contract will be triggered to deduct the credit value of the node and reduce its resource allocation weight; If the task completion quality is higher than the preset threshold, the node's credit value and resource allocation weight will be increased to encourage the contribution of high-quality nodes; When a collaboration dispute occurs between nodes, the disputed behavior is judged through the blockchain arbitration mechanism; The arbitration mechanism uses multiple trusted nodes to vote on disputed events and make a final decision based on the voting results; Reward or punish the credit value of the relevant nodes based on the judgment results. Deduct the credit value of the offending nodes until they are downgraded, and reduce their resource allocation weight in subsequent task allocation. An asymmetric encryption algorithm (RSA) is used to encrypt the collaborative behavior data between nodes to ensure the confidentiality and integrity of the data; Write the encrypted behavior data into the blockchain, and use the blockchain's tamper-proof and traceability features to achieve credible recording and auditing of node collaboration behaviors; Introducing deep reinforcement learning algorithms, including DeepQ-Network, which learns to optimize parameter weights in node credit assessment models and decision rules in resource allocation strategies by continuously interacting with the environment and obtaining feedback; According to the operation status of the blockchain network, including the credit rating distribution of nodes and the quality indicators of task completion, the incentive and penalty rules in the smart contract are dynamically adjusted to achieve the adaptive evolution of the incentive mechanism; The blockchain consensus mechanism is used to realize the consistency verification of node cooperation behavior, and the authenticity and reliability of the recorded cooperation behavior data are ensured through multi-party verification; Use blockchain technology to build a trusted collaboration environment, promote nodes to actively participate in collaboration and improve the quality of task completion, and maintain the healthy operation of the blockchain network.

Images