6 results about "Cluster coefficient" patented technology

This invention discloses a method for decomposing complex networks based on graph contrastive learning and multi-hop aggregation, comprising the following steps: collecting the number of neighbor nodes, connecting edges, and average clustering coefficients of a complex traffic network to construct a network decomposition model; inputting the original graph into a role graph generation module to obtain a role graph; inputting the original graph and the role graph into a multi-view representation learning module to obtain multi-angle graph representations of the role graph and the original graph; obtaining an importance score for each node; calculating and optimizing the joint loss function to train the network decomposition model; decomposing the traffic network to obtain the importance values ​​of traffic nodes in the traffic network, and setting stronger security measures for traffic nodes with high importance and weaker security measures for nodes with low importance. This invention uses intra-graph contrastive learning and cross-contrast learning to improve graph representation performance and proposes a multi-hop aggregation mechanism to predict node importance by combining multi-hop neighbor information, achieving high-performance network decomposition.

The application discloses a kind of network equipment early warning evaluation method and system based on SNMP, belong to network equipment state monitoring early warning evaluation technical field, method includes: using SNMP protocol and equipment OID information acquisition network equipment's key state information and store to database;Real-time early warning is carried out to key state information based on early warning filter pool, and real-time early warning result is obtained;Current data, historical data are recalled and combined with real-time early warning result, and state evaluation is carried out using improved grey clustering algorithm, with early warning result as the determination reference of index abnormal degree and the basis for grey class correction, the state evaluation result associated with early warning result is output by calculating clustering coefficient and determining grey class.The application realizes the deep fusion of early warning and evaluation, improves the accuracy and timeliness of network equipment state evaluation, provides strong support for preventive maintenance, and can be widely applied to the operation and maintenance of various network equipment.

This invention relates to the field of complex network technology. It provides a method for identifying key nodes in complex networks based on Shannon's theorem and the Matthew effect. The method includes: acquiring the topology of the complex network and modeling it as an undirected graph; calculating the structural features of each node; mapping the node's clustering coefficient and structural hole constraint to channel noise, and mapping the node degree and clustering coefficient to channel bandwidth; quantifying the node's information propagation capability as a relay using a signal-to-noise ratio formula; calculating the node's initial information based on its degree and normalized K-shell value; iteratively calculating to give nodes with high initial information a weight gain when aggregating neighbor contributions, simulating the cumulative process of network resources tilting towards core nodes, and obtaining a Matthew effect information aggregation value; obtaining the node's final influence score based on the Matthew effect aggregation value and information propagation capability; and sorting the nodes in descending order based on the final influence score to identify key nodes in the complex network.

The application discloses a bonding encapsulation equipment health state evaluation method based on twin data, classifies and combs three major functional components of an ultrasonic welding head system, a motion control system and a machine vision system of the bonding encapsulation equipment, establishes a hierarchical structure model and a fault tree, constructs a three-level health evaluation model including a component layer, a functional component layer and a whole machine layer, divides equipment health states into four qualitative grades of excellent, good, general and observation, introduces a health degree into quantitative characterization in combination with a fuzzy mathematics theory, adopts a multi-channel neural network model based on an attention mechanism to recognize the health state of a vibration signal, adopts a grey clustering model for health indexes which are not vibration type and are difficult to directly quantitatively evaluate, calculates clustering coefficients of the health indexes belonging to various health states based on a whitening weight function, and determines the health state; and adopts an entropy weight method based on twin data driving to determine the weight of each health index, carries out grey class weighted fusion, and outputs the real-time health degree and the health state grade of the equipment. The application improves the reliability, accuracy and equipment operation efficiency of the equipment health state evaluation, shortens the maintenance time, and reduces the production cost.

This invention discloses a state assessment method and system for hydropower unit speed regulation systems based on LBWA-ROCOSD-OCC-IEGC. First, a three-level indicator system—target layer, project layer, and indicator layer—is constructed. Based on a unified assessment window, samples of multi-source, heterogeneous periodic indicators are constructed and time-aligned to obtain a historical sample matrix and samples to be assessed. Then, subjective weights are determined based on the LBWA method, objective weights are extracted based on the ROCOSD method, and a comprehensive weight vector is obtained through multiplication synthesis. Next, the comprehensive clustering coefficients for each state level are calculated based on the OCC-IEGC model. Finally, the state level determination results and quantitative scoring results are output, and the mean comprehensive score, standard deviation of the comprehensive score, result stability, and result acceptance conclusion are output through repeated execution of the state assessment.

The application discloses a method for generating infrastructure network attack and defense game strategy based on multi-index fusion, and has the characteristics that the method comprises the following steps: acquiring the topology structure of an infrastructure network, determining the strategy set of player 1 and player 2, and constructing an infrastructure network game model; calculating the payoff matrix of player 1 and player 2 in the infrastructure network game under various strategy profiles respectively by taking three network performance indexes of the maximum connected piece scale, network efficiency and clustering coefficient; constructing three pairs of membership functions and non-membership functions according to the preference of a decision maker; converting the payoff matrix into an intuitionistic fuzzy set payoff matrix by using the three pairs of membership functions and non-membership functions, and obtaining a final payoff matrix by using an intuitionistic fuzzy weighted aggregation operator for weighted fusion; and combining the intuitionistic fuzzy set theory to convert the solution of the infrastructure network game model into the solution of a nonlinear programming problem, so as to obtain the mixed strategy Nash equilibrium solution of player 1 and player 2.