19 results about "Event propagation" patented technology

The invention relates to the technical field of power grid exception handling, and discloses a power grid exception event handling method and system based on a knowledge graph. The method comprises the following steps: collecting time sequence data flow and space coordinate information of a power grid abnormal event in real time through multi-source sensing equipment, and fusing equipment operation parameters to construct a dynamic event data pool; performing graph structure conversion on the dynamic event data pool based on a knowledge graph topological connection relationship, calculating event node propagation path intensity and generating an event propagation network model; key abnormal indexes are separated out from the model by adopting a multi-modal feature extraction technology, risk probability calculation is completed in combination with an adaptive learning algorithm, and an abnormal risk distribution diagram is output; and classifying event levels according to the graph, and automatically generating a processing instruction sequence. According to the method, omnibearing data perception and accurate analysis of the abnormal events of the power grid are realized, an event propagation rule is clearly presented, risk assessment is enabled to be closer to an actual operation state, and accurate guidance is provided for abnormal disposal.

The invention discloses a risk early warning method and system based on a power service sensitive event, and belongs to the technical field of deep learning, and the method comprises the steps: obtaining a customer service voice text, work order data and weather early warning information, and constructing a heterogeneous space-time diagram containing power distribution equipment and power consumers; inputting the heterogeneous space-time diagram into a graph neural network model to obtain event propagation path probability distribution and potential source nodes; generating an early warning work order based on the event propagation path probability distribution and a preset sensitive word library; triggering a supervision process according to the early warning work order, generating a supervision work order and configuring an elink message sending rule; and sending the elink message to a specified person in charge, feeding back a supervision processing result and updating model parameters. According to the method, leap-type upgrading from passive disposal to active prevention and control, from experience judgment to data intelligence and from single-point analysis to system governance is realized, and the method has remarkable technical advancement, management practicability and engineering popularization value.

The invention relates to the technical field of social network information propagation prediction, in particular to an event propagation prediction method based on group influence. The method comprises the following steps: constructing a social network graph of target event participating users, calculating an activation probability matrix among the users by using historical propagation data, and performing social graph structure enhancement based on a threshold value to obtain a de-noised social graph; applying a graph neural network on the de-noised social graph and introducing information bottleneck constrained self-supervised contrast learning optimization node embedding, and reserving features useful for group division and propagation prediction; dynamically dividing user groups related to propagation according to the similarity and propagation context of de-noising node embedding to form a group-level propagation sequence; based on the group representation, utilizing an attention mechanism and a group relation graph to carry out modeling on propagation influence among the groups to obtain global group representation of the event; global group representation is combined with candidate user embedding, propagation probability distribution is calculated, and future participating users of corresponding events are predicted.

The invention relates to the technical field of media content assessment, provides a media content propagation influence assessment method and system based on multi-modal data fusion, and is used for solving the problem of low accuracy of major report event propagation traceability and key node positioning in the prior art. The method comprises the following steps: acquiring multi-modal data and propagation dynamic data of media content on a plurality of platforms, wherein the data are used for constructing a propagation path diagram after being subjected to time alignment and normalization processing and are converted into a vectorization sequence; analyzing sequence generation path correlation intensity, and identifying a core propagation path according to the correlation intensity; performing feature extraction and conversion on the propagation dynamic data based on the core propagation path, generating a time sequence signal, and analyzing the time sequence signal into a bidirectional time sequence feature; and calculating weight coefficients of nodes and edges according to the bidirectional features, forming node mark information, and finally generating a propagation influence index. According to the application, the propagation traceability of the major report event and the accuracy of key node positioning are improved.

The invention belongs to the field of information network management, and particularly relates to an information network management system and method. The record network comprises a plurality of element sets, each element set comprises at least one segment, the segment comprises a plurality of elements, different segments are associated or not associated, and when the segments are associated, the segments are associated through links; the recording network management subsystem comprises an event generation module, when an element is updated, the event generation module generates an event, and the event comprises related data of current element updating; the pipeline modules are arranged on the links, the pipeline modules are used for being connected with the corresponding event generation modules through the corresponding links, and the event generation modules are used for transmitting the updated related data to the pipeline modules; and the loop control module is used for judging whether the event propagation is loop propagation and terminating the loop propagation. According to the system, the updating efficiency and the updating accuracy can be improved.

The application relates to the field of event propagation path analysis methods, discloses an event propagation path analysis method based on RAG retrieval and information extraction technology, and discloses an event propagation path analysis method and system based on RAG retrieval and information extraction technology.The method first constructs a standardized data pool containing unique content fingerprints, realizes data deduplication and tracing by using SimHash; then constructs an exclusive RAG vector knowledge base, converts the seed context into an initial query vector; performs iterative retrieval, extracts propagation triples by using a model, and converts new entities into query vectors to trigger multi-hop retrieval to mine implicit correlations; merges nodes by using co-reference resolution and constructs a time-series directed graph; and finally calculates node centrality and vector semantic offset.The application solves the problems of propagation path breakage and content alienation recognition by iterative retrieval and semantic quantitative analysis, and realizes accurate analysis of event evolution.

The application belongs to the technical field of parallel discrete event simulation and network system simulation, and discloses an intelligent hybrid parallel synchronization method for large-scale distributed simulation, which collects key operation indexes such as neighborhood timestamp lower bound, next event time, round-trip delay quantile value, cross-partition event output rate and virtual time jitter, evaluates system load and communication state in real time, judges the best time to enter optimism or rollback conservation based on the collected key operation indexes, prevents frequent switching by using hysteresis mechanism and minimum residence time, sets time-bounded gates at the mode switching boundary, only allows events within the safe range to propagate, temporarily stores events exceeding the range and sends them in batches when the conditions are met, and thus guarantees causal consistency. The application takes into account real-time performance and robustness, shortens the global empty waiting time, facilitates real-time online acceleration and stable submission in a simulation platform and a message passing interface, and has both performance and interpretability.

The invention relates to a hot event propagation path prediction method and system based on multi-modal big data. The method comprises the following steps: based on a preset trigger, identifying seed content from a content publishing data stream, and acquiring propagation behavior data by taking the seed content as a center; based on the seed content and the propagation behavior data, constructing a preliminary propagation network structure to obtain an early propagation network; analyzing a propagation chain in the early propagation network to obtain a propagation chain analysis result, and based on the propagation chain analysis result, evaluating a user tendency response behavior to obtain a response tendency prediction matrix; and performing propagation simulation based on the early propagation network, the propagation chain analysis result and the response tendency prediction matrix to obtain propagation probability distribution. By adopting the method, the accuracy of propagation prediction can be improved by utilizing multi-modal data and social network analysis, the combination of content semantics and user behaviors is emphasized, and the method is suitable for the hotspot event propagation analysis of platforms such as social media and the like.

The application discloses a precise prediction and multi-scene cooperative control system for container truck arrival time sequence, and relates to the technical field of port logistics scheduling. The system comprises an event propagation module, a time delay processing module, an inter-chain constraint module, an archive self-correction module and a deduction control module. The event propagation module constructs a causal propagation network and triggers associated event concomitant time delay. The time delay processing module performs non-accumulative logical operation on multiple time delays with causal correlation or time overlap based on a time delay fusion rule set. The inter-chain constraint module maintains a set of conditional constraint relationships between event chains. The archive self-correction module maintains an individual logical archive composed of logical state bits for each transportation unit, dynamically adjusts the logical state bits and ignores misjudgment event chains. The deduction control module obtains the individual logical archive, performs conditional verification with the logical state bits in deduction, executes inter-chain constraint rules and generates a time sequence prediction result.

A system can maintain a function-as-a-service architecture that comprises a group of executable serverless functions, a group of message consumers, and a group of message brokers, wherein respective message brokers of the group of message brokers are configured to transmit respective messages to respective message consumers of the group of message consumers, and wherein the respective message consumers are configured to transmit the respective messages to respective functions of the group of executable serverless functions. The system can determine respective utilization metrics of the respective message consumers. The system can determine that a utilization metric of the respective utilization metrics satisfies a misutilization criterion. The system can adjust which ones of the message brokers communicate with which ones of the message consumers based on the utilization metric being determined to satisfy the misutilization criterion.

The application discloses a regional traffic system resilience evaluation and simulation deduction method based on an inclined orbit satellite, relates to the technical field of data processing, and collects fine-grained space-time data of traffic operation by using the multi-orbit covering characteristics of the inclined orbit satellite to form a traffic state feature set; in the process of space-time sequence preprocessing of the traffic state feature set, an event influence feature set is generated, and combined with structure information extracted from a traffic network topology set, an event propagation initial state set is constructed, thereby avoiding the problem that previous methods only rely on average flow or average speed indexes and ignore the initial disturbance difference of events; further, by diffusing and deducing the event propagation initial state set under the network node and path space adjacency relationship, an event diffusion stage feature set is generated, layered representation of event propagation dynamics is realized, and the resilience level of the traffic system under different event conditions can be clearly shown.

This application discloses an event handling method and apparatus based on Echarts, relating to the field of data visualization technology. The method includes: acquiring all data points bound to Echarts and the data types included in all data points; establishing an index data structure for all data points based on their data types; acquiring the trigger coordinate information and trigger type corresponding to the event trigger command; determining the target data type identifier corresponding to the event trigger command based on the trigger coordinate information and the index data structure; determining the corresponding target data point based on the trigger type, trigger coordinate information, and data point information corresponding to the target data type identifier; and responding to the event trigger command based on the target data point. In this application, by optimizing the event propagation path and reducing unnecessary redrawing operations, users can easily perform various operations on the chart, improving the efficiency and satisfaction of data exploration and analysis.

The invention discloses an intelligent linkage strategy generation and optimization method and device for multiple safety devices and a medium, and belongs to the technical field of linkage of the multiple safety devices. Comprising the five steps of multi-safety-device information collection and standardization processing, safety event association model construction, initial linkage strategy generation, strategy optimization and dynamic adjustment and strategy deployment and verification, in the information collection stage, device types, states, protocols and network topology attributes are obtained in real time, abnormities are marked through a data verification sub-module, and re-collection is triggered; unstructured data is converted into structured data based on a preset protocol, field-level verification is supported, data accuracy and integrity are guaranteed, a dynamic weighted graph structure is adopted in association model construction to represent equipment nodes and event paths, node attributes contain real-time state indexes, edge attributes contain transmission probabilities and time delay parameters, and the real-time state indexes of the equipment nodes and the event paths of the equipment nodes are obtained. And a node health degree evaluation mechanism is set, graph structure reconstruction is triggered when the node health degree is lower than a threshold value, and equipment association and event propagation characteristics are accurately described.

The invention discloses an automobile development full life cycle automation system and method based on event driving and a large language model, and the system employs a large language model agent to automatically execute each development stage from demand analysis to code realization and test verification through a plurality of heterogeneous information systems. The system adopts a bidirectional event propagation mechanism, not only supports a forward automatic process from a demand to a code, but also can perform automatic back propagation according to technical or time constraints encountered in a development process, generate demand change suggestions and keep the consistency of a whole life cycle. The sandbox environment is executed in an isolated mode, agent operation is prevented from influencing a production system, and the failure state can be stored for debugging; and multi-stage propagation coordination change: supporting cascade change across multiple systems. According to the method, the development efficiency is remarkably improved, meanwhile, the traditional workflow is completely compatible, and an innovative path is provided for intelligent transformation of automobile software development.

This application provides a method and system for campus security situation assessment and early warning based on multi-source data fusion, relating to the field of campus security management technology. First, it collects multi-source data streams from campus video surveillance, IoT sensors, information system logs, and access control systems, parsing out security-related event fragments. Then, it matches and associates these security-related event fragments with a pre-built campus event knowledge base to construct a campus event network diagram. Based on this campus event network diagram, it drives simulation and constraint-based inference models to perform event propagation inferences. The fusion results generate a set of snapshots of inference scenarios. The snapshots are processed to generate representative future security scenarios and trace key event fragment sequences. Based on these, a set of campus security early warning and response instructions is generated. This invention can comprehensively and accurately assess the campus security situation and provide timely early warnings.

The invention discloses a regional traffic system toughness evaluation and simulation deduction method based on different-orbit satellites, and relates to the technical field of data processing, and the method comprises the steps: collecting the fine-grained spatio-temporal data of traffic operation through the multi-orbit coverage characteristics of the different-orbit satellites, and forming a traffic state feature set; in the process of carrying out space-time sequence preprocessing on the traffic state feature set, an event influence feature set is generated, and an event propagation initial state set is constructed in combination with structural information extracted from a traffic network topology set; the problem that the previous method only depends on the average flow or average speed index and neglects the initial disturbance difference of the event is avoided; furthermore, through diffusion deduction of the event propagation initial state set under the network node and path space adjacency relation, an event diffusion stage feature set is generated, layered representation of event propagation dynamics is realized, and the toughness level of the traffic system under different event conditions can be clearly displayed.

The application relates to the technical field of big data management, and particularly discloses a grid event closed-loop treatment method and system based on big data, which comprises the following steps: traversing out-degree directed edges in a causal graph of a big data platform with a current event as a starting point, taking events with a propagation probability weight greater than a preset probability threshold as derivative prediction events of a next level, and connecting the derivative prediction events as an event propagation path; calculating a composite emergency index of the current event according to conditional probabilities of events in the event propagation path; generating a differentiated treatment instruction of the current event according to the composite emergency index and reusable pre-action nodes in a historical closed-loop event library, and dispatching the differentiated treatment instruction to a corresponding grid treatment terminal; and the application can improve the response efficiency and resource utilization effect of grid event closed-loop treatment.

The application discloses a precise prediction and multi-scene cooperative control system for container truck arrival time sequence, and relates to the technical field of port logistics scheduling. The system comprises an event propagation module, a time delay processing module, an inter-chain constraint module, an archive self-correction module and a deduction control module. The event propagation module constructs a causal propagation network and triggers associated event concomitant time delay. The time delay processing module performs non-accumulative logical operation on multiple time delays with causal correlation or time overlap based on a time delay fusion rule set. The inter-chain constraint module maintains a set of conditional constraint relationships between event chains. The archive self-correction module maintains an individual logical archive composed of logical state bits for each transportation unit, dynamically adjusts the logical state bits and ignores misjudgment event chains. The deduction control module obtains the individual logical archive, performs conditional verification with the logical state bits in deduction, executes inter-chain constraint rules and generates a time sequence prediction result.

The invention discloses an event prediction method and device fusing various historical information, equipment and a storage medium. The method comprises the following steps: constructing a historical event semantic embedding library by utilizing a disclosed time sequence event atlas and a semantic embedding model; extracting a continuous historical event sequence from the time sequence event graph to capture a time dependency relationship between events; identifying event modes which repeatedly occur in similar situations, constructing a repeated historical information graph, and modeling periodic features of events; and designing a self-supervised related information filter, automatically mining historical events related to the current prediction request based on event propagation characteristics and semantic correlation of the historical events, and generating a related historical information graph. And the information integration module based on the graph neural network generates an integrated event representation, trains an event prediction model, and outputs a candidate list of possible events. According to the method, the accuracy and reliability of event prediction are improved by integrating different types of historical information, and the method has relatively high application value and can be widely applied to various event prediction scenes.