63 results about "Community structure" patented technology

The invention relates to the technical field of electric power engineering information processing, and discloses a power grid power transformation engineering knowledge graph construction and retrieval method and system, and the method comprises the steps: carrying out the dynamic adaptive partitioning of a power grid power transformation engineering related document, and obtaining semantic coherent and independent text blocks; extracting entities and relationships based on the text blocks, and complementing implicit entities and relationships through a multi-round refining mode; performing fusion and disambiguation on the extracted and complemented entities and relationships to form a unified knowledge graph; performing hierarchical clustering on the formed knowledge graph to generate a multi-granularity community structure and a corresponding community report; intention resolution and pre-judgment guidance are carried out aiming at fuzzy questions of the user, and a retrieval strategy is optimized; and executing multi-hop semantic retrieval based on the optimized retrieval strategy, recalling related knowledge and generating answers. According to the method, automation, precision and intelligentization of power grid power transformation engineering knowledge graph construction and full-link retrieval can be realized.

The invention relates to the technical field of attribute graph collection and release, in particular to an attribute graph collection and release method, system and device based on local differential privacy and a medium. Receiving disturbed data from each client; based on all disturbed data, estimating community division of the original graph structure and triangular counting of each node; obtaining a target graph structure based on community division and triangular counting; and on the basis of the target graph structure and the disturbed data, node attributes are optimized, so that node attribute distribution and community division are kept consistent, and a final publishable target attribute graph is obtained. The method has the advantages that strict requirements of local differential privacy are met on the privacy protection level, and multi-dimensional features such as a community structure, triangular counting and node attribute homogeneity are reserved in the published attribute graph at the same time; and the practical value of the synthetic data in applications such as downstream graph analysis, community discovery and personalized service is greatly improved.

The invention discloses an intelligent decision-making method and system based on deep learning, and relates to the field of data processing. The method comprises the steps of obtaining place data and corresponding attribute data of a to-be-decided project; establishing a fuzzy relation matrix between the places and the attributes; generating a network model reflecting trust relationship strength among users through trust propagation operation of the graph neural network; identifying a community structure containing a community overlapping degree through a community discovery algorithm; and according to the trust relationship strength between the users and the community overlapping degree, calculating an influence weight of a decision maker, forming a group consensus through a robust optimization method, and generating a decision result of the project to be decided. Aiming at low network relation modeling precision caused by multi-source heterogeneous data in bus station layout decision making in the prior art, the method and the device have the advantages that the network relation modeling precision is low through accurate modeling of an information propagation path in a complex trusted network, effective dimension reduction representation of a high-dimensional feature space and robust optimization solution in an uncertain environment; therefore, the calculation precision and robustness of the bus station layout intelligent decision-making system are improved.

The invention relates to a post personnel recommendation interpretation method and device based on gradient features and a community structure. The method comprises the steps of obtaining a pre-trained and converged graph neural network and original embedded features, carrying out subsequent operation according to a knowledge graph in which entities such as personnel, skills, posts and services are stored, and recommending a network for on-duty personnel by using the graph neural network, and combining the original embedded features with gradient vectors obtained by the graph neural network through a back propagation algorithm to form gradient features. And performing community division on the knowledge graph nodes, and generating node community tags by maximizing modularity. Finally, the gradient features, the node community labels and the graph neural network model are input into an interpretation framework together, the graph masks and the feature masks are optimized to maximize information quantitative indexes, and post personnel recommendation results containing the key sub-graphs and the feature masks are generated. By adopting the method, the on-duty personnel recommendation interpretability in different scenes can be continuously improved.

The invention discloses a lake and reservoir dominant algae community structure prediction method and system based on machine learning and a storage medium, and relates to the technical field of water environment monitoring and ecological prediction. Comprising the following steps that multi-source heterogeneous spatio-temporal data are obtained and fused, and the multi-source heterogeneous spatio-temporal data are historical time sequence data of a target water area; generating a feature vector from the fused multi-source heterogeneous spatio-temporal data; constructing a multi-output regression machine learning model, and inputting the feature vector into the multi-output regression machine learning model for training to obtain a multi-output prediction model; and inputting real-time monitoring data into the multi-output prediction model to generate a prediction result of a future dominant algae community structure. According to the method, whether cyanobacterial bloom or diatom bloom exists in the future can be clearly early warned, so that a manager can take targeted measures, for example, a specific algicide or ultrasonic equipment is used for the cyanobacteria, blind pesticide application is avoided, and the cost and the secondary pollution risk are reduced.

The invention discloses a structure entropy model for detecting a social robot in real time, particularly relates to the technical field of big data mining, and is used for solving the problem that an existing social robot detection method is difficult to balance between detection precision and processing efficiency. User data is processed through a feature selection weighting module to screen key features and distribute weights, a feature stability evaluation module analyzes the contribution degree of the key features to a community structure to screen features with the most distinguishing power, and a multi-relation graph construction module constructs a user similarity graph based on the key features and the weights thereof. The coding tree community division module initializes a coding tree on the user similarity graph and generates a hierarchical community division structure through iterative calculation of structure entropy change; and the community level classification module forms a comprehensive score for each community fusion structure entropy and behavior statistical characteristics and judges a social robot community through comparison with an optimization threshold.

The invention provides a method and a device for identifying multi-trophic-level aquatic biocenosis stability influence factors, and relates to the technical field of aquatic ecosystem analysis. The method comprises the following steps: acquiring a water body physicochemical parameter data set and a multi-trophic-level aquatic biocenosis data set of a plurality of sampling points of a target water area; constructing a species association network system for stability calculation based on the multi-trophic-level aquatic organism community data set; calculating a stability index representing the overall stability of the community based on the network system; and finally, analyzing the contribution degree of the water physical and chemical parameter data set to the stability index by utilizing a machine learning model, and identifying the key influence factor according to the contribution degree. According to the method, the key physical and chemical factors influencing the stability of the ecological system can be systematically and accurately identified by integrating the multi-nutrition-level community structure and machine learning, and the targeting and management efficiency of the restoration of the water ecological system are improved.

The invention provides an abnormal user identification method and device, electronic equipment, a medium and a program product, and can be applied to the technical field of big data and the technical field of artificial intelligence. The method comprises the following steps: acquiring multi-dimensional discrete feature data of a to-be-detected user set, and converting the multi-dimensional discrete feature data into corresponding number information; generating a continuous embedding vector set based on the number information, and outputting a target distance function; taking the continuous embedded vector set as input, and executing K-means clustering based on a bisection strategy based on a target distance function to obtain a cluster set and a corresponding centroid set; for at least one cluster in the cluster set, constructing a transaction network graph, and obtaining a community structure based on the transaction network graph; executing edge weight analysis based on the community structure and the edge weight information in the transaction network graph; target nodes in the transaction network diagram are removed based on an edge weight analysis result, and a user subset is obtained; and outputting an abnormal user identification result based on the user subset.

This application discloses a comprehensive assessment method and system for multi-source data management and correction of watershed fish resources. The method includes: extracting multi-dimensional features from a first data matrix to obtain a first feature matrix; classifying species data based on anomaly scores, outputting verification results, and correcting the first feature matrix to obtain a second feature matrix; acquiring environmental DNA sequencing data and corresponding environmental data; obtaining a first eDNA dataset from the environmental DNA sequencing data through ecological screening; correcting the species in the first eDNA dataset to obtain a second eDNA dataset; fusing the second eDNA dataset with the second feature matrix; calculating biodiversity indices and analyzing community structure; analyzing long-term trends in population and community structure; and generating a comprehensive assessment report. This application achieves full-process automation and intelligence from data quality control and fusion to assessment, significantly improving the accuracy and efficiency of watershed fish resource assessment.

The application discloses a kind of long-distance water transfer project water demand probability prediction method, comprising: collecting basic information, calculating the historical water demand sequence of water transfer project water receiving area, generating node level dynamic water demand characteristic vector;Based on dynamic water demand characteristic vector, through multiple directed dependence measure, identify the time-space dependence structure between nodes changing with time, dynamically divide high correlation, weak correlation and independent community, and track the evolution event of community;Based on community structure, fuse the geographical distance between community and water supply relationship, impose cross-domain cost factor, construct hierarchical water transfer area;Based on time-space dependence structure and hierarchical water transfer area, adopt differentiated probability prediction model and cascade time propagation mechanism, construct system level joint probability distribution.The application can accurately depict the dynamic dependence and hierarchical structure of system, improve the accuracy and reliability of prediction.

This invention relates to the field of internet information technology and discloses a method for evaluating the dissemination effectiveness of self-media promotion content. This invention constructs a directed weighted graph by collecting user interaction data and comprehensively calculates three core graph signal indicators: structural cohesion, interaction persistence, and influence anchoring degree. Finally, a comprehensive effectiveness score is obtained through a nonlinear fusion model. This method can effectively identify and filter invalid interactions, quantify the tightness of the community structure, the depth of dialogue, and the anchoring degree of core users. It overcomes the shortcomings of existing technologies, such as poor anti-interference capabilities and limited insight dimensions, achieving a multi-dimensional and interpretable accurate evaluation of community dissemination effectiveness, and providing partners with objective priority decision-making basis.

The application relates to the technical field of attack traceability data security, in particular to an information system APT attack process tracing method and system and a medium. The method comprises the following steps: acquiring log information of an information system, converting the log information into a traceability graph, identifying each community in the traceability graph, calculating community structure singularity of each community, clustering the community structure singularity of all communities, acquiring abnormal behavior significance of each community according to deviation and outlying conditions of the community structure singularity of each community in the cluster, identifying each abnormal community, obtaining behavior credit of each node in each abnormal community in combination with abnormal conditions of difference degrees of out-degree and in-degree of each node in each abnormal community, identifying abnormal nodes under APT network attack, and tracing paths under APT network attack by using an STP steiner tree algorithm. The application can improve the accuracy of APT attack process tracing.

The application discloses a stable anti-reversibility microbial community structure and a construction method and application thereof, and relates to the technical field of microbial community construction, and in particular to a stable anti-reversibility microbial community structure and a construction method and application thereof.

The application provides a power distribution network scheduling method and a scheduling device. The method comprises the following steps: constructing a power distribution network adjacency matrix and a power distribution network weight matrix according to a topology structure of the power distribution network; dividing the power distribution network into a plurality of power distribution network communities according to the power distribution network weight matrix by using a Louvain community finding algorithm to obtain a first community structure; establishing a constraint condition to optimize the first community structure to obtain a second community structure; constructing a communication network adjacency matrix of a communication network according to a hierarchical structure of the communication network; constructing a coupling network adjacency matrix according to the power distribution network adjacency matrix, the second community structure and the communication network adjacency matrix, the coupling network adjacency matrix being used to describe a coupling relationship between the power distribution network and the communication network; and performing power scheduling on the power distribution network according to the coupling network adjacency matrix to balance power supply and demand of the power distribution network. The method solves the problem of low power scheduling efficiency caused by a low coupling relationship between the power distribution network and the communication network in the prior art.

The application relates to a recommendation method based on social network user behavior information, which comprises the following steps: obtaining user behavior data and obtaining user activity holding location preference and holding time preference; constructing a preference similar network by using the obtained user preference, and then fusing a user online social relationship network to obtain a plurality of non-overlapping community structures reflecting the social connection and preference similarity between users; calculating the value of each hidden point representing the user's decision on a project by using a hybrid pairwise Markov random field model; calculating all node states of each project, and then selecting a recommendation list by sorting. The application aims to recommend the optimal activity holding location and holding time for an activity organizer, so as to maximize the number of participants in the activity and meet the decision planning needs of the activity organizer.

The invention belongs to the field of overlapping community detection, discloses an overlapping community detection method based on gradient guide graph contrast learning, and provides a gradient guide dynamic capturer to eliminate message contrast conflicts by sensing gradient changes of positive and negative sample pairs. Key negative samples inducing message comparison conflicts can be accurately captured, and a model is promoted to accurately identify communities to which nodes belong. Besides, aiming at false negative samples and LCE problems, the invention respectively provides a new false negative strategy and a message passing mechanism based on pheromones so as to enhance the modeling capability of the model for a complex community structure.

The invention belongs to the technical field of computers, and discloses a query method for a closely associated transaction account group, which comprises the following steps of: 1, extracting all connected k-trus communities in a global time interval of an account transaction network, and calculating a real time interval; step 2, carrying out forward evolution refinement; step 3, carrying out backward evolution refinement; step 4, constructing a DAG index structure of the time evolution community; step 5, querying the maximum connected k-trus community of the given account in a specified time interval by using the index; and step 6, returning a query result. According to the method, by constructing the account community structure diagram evolved in the time interval, the repeatedly stored community information is effectively compressed, and the expression ability and query efficiency of account community evolution in a cross-time range are improved. Through recursive stripping and sharing of edge sets among communities, minimum redundant community representation across multiple time windows is realized, and the storage overhead is remarkably reduced while the historical integrity of the communities is ensured.

The application relates to the technical field of network analysis, and discloses a network community discovery system and method through matrix analysis, which comprises the following modules: a network module, which converts a static network topology into an information propagation model, and establishes a node state time sequence dynamic model by defining a node information processing rule and a multi-round propagation mechanism; a phase space reconstruction module, which maps high-dimensional time sequence data to low-dimensional phase space through a nonlinear dimension reduction method to form node trajectory distribution data; a community feature module, which analyzes the convergence, oscillation mode and attractor feature of the node trajectory, and generates community structure feature data through trajectory similarity; and a community division module, which identifies a community boundary through density clustering, and constructs a hierarchical community organization through multi-scale analysis. The application can deeply mine the internal community structure of a network from the perspective of dynamic information propagation, and overcomes the limitation that traditional methods only consider static topology.

Multi-tenancy system to perform tactical and permanent database and communication operations including secure handling of personally identifiable and / or health information (PII / PHI), data collection, data management, reporting, data analytics, secure communications, document sharing and microservices (e.g., capturing biomarkers, determining presence of certain conditions by comparing captured biomarkers to biometrics associated with condition). System includes security platform meeting stringent data protection mandates including firewall with extensive security protocols, encrypting communications between components of system (in transit) and information within each of the components (at rest). PII / PHI information is further encrypted and only visible with appropriate decryption key. System utilizes low code / no code database platform to address increasing demand for rapid, iterative and collaborative application development. System includes form builder to easily add dynamic fields. System includes a collaborative database development with a community structure approach of “who” data is needed from rather than “what” data is needed. Community structure controls operation thereof.

The application discloses a voltage partition method based on a community structure theory and regional reactive power supply and demand balance, and is characterized by comprising the following steps: step S1: according to the topological structure of a power system network, lossless processing is performed on the power system network, and reactive power loss on a line of the power system network is equivalent to reactive power load at nodes at two ends of the line; step S2: the community structure theory is used to perform reactive power partition on the power system network, a penalty function is set according to a difference between reactive power demand and reactive power supply in a community, and a reactive power imbalance degree is set according to a ratio between the reactive power demand and the reactive power supply in the community; a community structure quantitative evaluation index modularization function Q' is established in combination with the penalty function and the reactive power imbalance degree; step S3: arrangement and combination are performed on community partition, the community structure quantitative evaluation index modularization function Q' is calculated and updated, and the community partition with the maximum modularization function Q' value is selected as a final reactive power partition result. Therefore, the best reactive power partition result is obtained.

This invention provides a method and system for detecting community structure in spatially concurrent extreme climate events, comprising: collecting gridded temperature and precipitation data of the study area, extracting binary time series of heat waves and extreme precipitation events, and performing event synchronization determination calculations and significance tests; constructing a two-layer coupled heat wave-extreme precipitation network based on the inter-layer adjacency matrix; obtaining stable community classification results based on the two-layer coupled network using a community detection method combining the Leiden algorithm and consensus clustering; performing lead-lag correlation analysis on all community pairs to identify key community pairs with strong correlations and their lag times, and further exploring the spatiotemporal propagation characteristics of climate events. This invention fully utilizes the advantages of two-layer coupled climate network analysis, combining the Leiden algorithm and consensus clustering method to improve the accuracy and stability of community detection, and can effectively reveal the spatial concurrency characteristics and spatiotemporal propagation patterns of global extreme climate events.

The invention relates to the technical field of natural language processing, in particular to a cold start false news detection method based on a propagation path and a greedy algorithm, which comprises the following steps: S1, constructing a news propagation graph, generating propagation paths based on interaction behaviors of users and news, and calculating the similarity of the propagation paths among the users; s2, based on the propagation path similarity, performing unsupervised community initialization by adopting a greedy strategy to form a user community with cohesiveness; s3, injecting a community structure as a structure prior into the graph neural network, and enhancing the propagation structure perception capability of the model in a cold start stage; and S4, carrying out true and false classification on the news events by utilizing the graph neural network with the injection structure prior, and realizing early false news detection. The method does not need to depend on a large number of labels and complete propagation structures, high detection precision and robustness can be kept in the early stage that information is sparse and communities are not formed, experiments show that the method is superior to an existing method on mainstream data sets, and the method has high practical application value.

The invention provides a risk early warning method and device, electronic equipment, a storage medium and a product. The method comprises the following steps: acquiring at least two community division results corresponding to a supply chain entity; generating first community structure information based on the similarity of the at least two community division results; in response to a transaction change event in the block chain, updating the first community structure information to obtain second community structure information; determining a risk score of each supply chain entity according to the second community structure information and the first community structure information; and in response to the risk score exceeding a target abnormal threshold, triggering the block chain smart contract to execute a risk response operation.

The application discloses a kind of arid region small watershed vegetation ecological environment monitoring method, comprising: obtaining arid region small watershed surface image, arid region small watershed surface image is handled, obtains first vegetation distribution image;According to the matching of first vegetation distribution image and spectral feature library, obtain second vegetation distribution image;From second vegetation distribution image, the spatial distribution characteristics of vegetation community are extracted, the dynamic change trend of spatial distribution characteristics is calculated, and community structure change dataset is obtained;Based on community structure change dataset, short-term evolution trend of vegetation community structure is predicted using long short-term memory network, and dynamic change prediction result of vegetation community structure is obtained;According to dynamic change prediction result, combined with community structure change dataset, quantify biodiversity level, and obtain biodiversity evaluation result;From biodiversity evaluation result, key indicators are extracted, and according to key indicators, real-time monitoring vegetation ecological environment state data.

This disclosure provides a method, apparatus, electronic device, and storage medium for analyzing learning progress. The method includes: acquiring a user dataset from a platform; determining an instant learning performance score for each learner based on their learning outcomes and learning objectives within the user dataset; acquiring valid course selection information for all learners; determining a dynamic relationship network based on the valid course selection information and the instant learning performance score; acquiring the clustering characteristics and community structure within the dynamic relationship network; and determining the learning progress based on the clustering characteristics and community structure. Determining the learning progress through a dynamic network based on the instant learning performance score effectively grasps the learning progress patterns of open online courses, thereby enabling real-time monitoring of the learning progress of all users on the platform. This plays a crucial role for educators in real-time evaluation of teaching quality, control of teaching direction, course recommendations, and learning progress early warnings.

The invention provides an intelligent identification method and system for abnormal auditing data of a hospital. The intelligent identification method comprises the steps of obtaining a multi-dimensional data set of the hospital, calculating a local outlier factor LOF of each data record, distributing a differential privacy budget and generating a privacy data set; constructing a weighted K nearest neighbor graph based on the privacy data set and the LOF value, and performing community division on the graph; calculating weighted intermediary centrality, community connection strength and average path length of each node, fusing the weighted intermediary centrality, the community connection strength and the average path length into a structural anomaly score, and screening data records of which the scores are higher than a first threshold value as first-level candidate anomaly data; for each piece of first-level candidate abnormal data, mapping the data structure abnormal score into a time window, extracting a time sequence track, and calculating an average time sequence track of the community as a prototype track; outputting a time sequence similarity distance; constructing a confirmation threshold value, wherein the threshold value is adjusted based on community structure characteristics, data differential privacy budget and a structure anomaly score; and when the time sequence similarity distance is greater than the threshold value, identifying the data as abnormal data.

The application provides a label propagation overlapping community detection method based on a core community attraction mechanism, comprising the following steps: constructing a network model and preprocessing; identifying core communities in the network model and assigning a unique label to each core community; propagating the label and adjusting the propagation weight; allowing a node to belong to multiple core communities at the same time, adjusting the label assignment of the node according to the association degree of the node with different core communities, and forming an overlapping core community structure; evaluating the label propagation result; and adjusting the core community attraction mechanism and the label propagation parameter according to the evaluation result, and optimizing the core community detection effect. The application identifies the core communities in the network, and uses the core communities to guide the label propagation process, thereby enhancing the precision of the label propagation. The application adopts an adaptive mechanism, adjusts the label propagation path and weight in real time according to the interaction frequency and association degree between nodes, reduces unnecessary calculation overhead, and improves the propagation efficiency.

The invention relates to the technical field of attack traceability data security, in particular to an APT attack process traceability method and system for an information system and a medium, and the method comprises the steps: obtaining log information of the information system, converting the log information into a traceability graph, recognizing each community in the traceability graph, calculating the community structure singularity of each community, and determining the information system APT attack process according to the community structure singularity. Clustering the community structure singularity of all communities, obtaining the abnormal behavior significance of each community according to the deviation outlier condition of the community structure singularity of each community in a clustering cluster so as to identify each abnormal community, and combining the abnormal condition of the difference degree between the out-degree and the in-degree of each node in each abnormal community so as to identify each abnormal community. The method comprises the following steps of: acquiring behavior reliability of each node in each abnormal community, identifying abnormal nodes under APT network attacks, and tracing paths under the APT network attacks by using an STP Steiner tree algorithm. According to the invention, the accuracy of APT attack process tracing can be improved.

The application belongs to the technical field of comprehensive energy optimization operation, and provides a comprehensive energy optimization control method and system based on community game, comprising: obtaining a directed weighted graph of comprehensive energy; taking all nodes in the obtained directed weighted graph as game participants, and constructing a detection model based on community game; hierarchically solving the constructed detection model based on community game to obtain single-layer community structure; merging the obtained single-layer community structure to form comprehensive energy community structure; performing cooperative game benefit distribution in the formed comprehensive energy community structure, processing multi-objective optimization priority through a hierarchical sequence method to obtain optimal weight coefficients and income distribution of all nodes, and completing optimization control of comprehensive energy based on community game.

This invention discloses a federated graph synthesis method and system based on a differential privacy model, belonging to the field of federated learning technology. It is applied to a federated graph synthesis system comprising one server and multiple clients. The method includes a community detection stage, an information extraction stage, and a graph reconstruction stage. This method achieves global graph synthesis that satisfies edge differential privacy without centralized original sensitive edge data or cross-client interaction of original data, thus ensuring data privacy from an architectural perspective. It designs a noise-resistant edge statistics mechanism between supernodes, converting the weighted supernode graph into an unweighted undirected graph to reduce the impact of high noise on community detection in federated scenarios. It also designs a local community optimization mechanism to improve the accuracy of community structure detection. Furthermore, it proposes a fine-grained edge construction strategy, adaptively stopping client contribution value collection based on the connection strength of supernode pairs. Finally, it designs a heterogeneity-aware information extraction mechanism, allocating differentiated privacy budgets based on edge participation patterns.