84 results about "Event analysis" patented technology

The invention discloses a network security event analysis method and system based on multi-agent decision, and a storage medium, and the method mainly comprises the steps: carrying out the deep investigation and judgment through a deep decision agent based on a reinforcement learning network after an abnormal alarm of a monitoring platform is received, triggering the deep investigation when the calculated deep investigation probability is greater than a threshold value, and carrying out the early warning of the network security event. Calling an LLM-based sub-expert agent to carry out deep analysis aiming at specific features; and according to the analysis result of the sub-expert agent and the risk information provided by the risk information platform, the LLM-based comprehensive risk decision assessment agent performs conjoint analysis decision to generate a network security situation comprehensive assessment report. According to the method, the processing analysis capability of massive and heterogeneous security data and the recognition capability of complex attack paths are remarkably improved, and the discovery capability of unknown threats and the intelligent level of security operation and maintenance are effectively enhanced by introducing reinforcement learning optimization decision and the deep analysis capability of LLM.

Embodiments manage context repositories in computing environments to enhance automated security analysis. Embodiments obtain context records containing supplemental information associated with security events and integrates them into prompts for large language models (LLMs) to generate severity scores for event classification. Embodiments apply criteria to invalidate outdated or unreliable context records based on age, source reliability, and usage frequency, then modifies prompts and repositories accordingly. Enhanced prompts incorporate context record summaries and entity relationship mappings to improve subsequent event analysis. Embodiments dynamically evaluates context records through quality filters, consolidates duplicates, and maintains audit trails with provenance tracking. User interfaces are dynamically transformed based on telemetry metrics and user feedback to optimize analyst workflows. Embodiments enable organizations to maintain curated, high-quality context repositories that continuously improve AI-assisted security analysis while reducing false positives and enhancing incident response effectiveness.

The invention discloses a financial abnormal event analysis method, electronic equipment, a medium and a product. The method comprises the steps of obtaining at least one financial clue event, and performing structured element extraction and standardization processing on each financial clue event to obtain a standardized event behavior sequence; performing semantic feature and behavior pattern analysis based on the normalized event behavior sequence, performing event reasoning rule recall in combination with a pre-constructed event reasoning library, and determining a recalled rule set; generating an abnormal event analysis execution plan based on at least one inference rule in the rule set; querying original data in the data system according to an inference rule included in the abnormal event analysis execution plan, generating a data view, executing the abnormal event analysis execution plan based on the data view, and generating an inference execution result set and execution path information; and an event reasoning analysis result is generated according to the reasoning execution result set and the execution path information, and the problems of complex abnormal event analysis modeling, low interpretability and the like are solved.

The invention discloses a power grid operation situation analysis system combined with a knowledge graph, which relates to the technical field of intelligent power grids and comprises a power grid data acquisition module, a power grid feature extraction module, a monitoring information event analysis module, a power grid graph construction module and a power grid event intelligent research and judgment module. The power grid data acquisition module acquires power grid data, the power grid feature extraction module extracts features of the power grid data, the monitoring information event analysis module outputs an overhaul label, a fault label, an associated equipment list and a fault list, and the power grid graph construction module generates a power grid knowledge graph and outputs a fault propagation path and an out-of-limit threshold. And the power grid event intelligent research and judgment module pushes abnormal data and fault information. According to the method, automatic cleaning of massive monitoring signals, intelligent fault research and judgment and cross-station propagation path analysis are realized through natural language processing and machine learning technologies, manual intervention is reduced, the fault recognition accuracy is improved, graded alarms are pushed in real time, and the power grid situation awareness and emergency disposal efficiency is remarkably improved.

A data platform monitors a compute environment by performing multi-stage heuristic analysis of event data representing a plurality of events occurring within the environment. The platform utilizes multiple event analyzers, each configured according to a distinct analysis heuristic, to evaluate different subsets of the event data and generate corresponding output signals. A higher-level event analyzer applies a further heuristic to the multiple output signals to generate a composite alert signal, indicating whether the combination of analyzed events collectively represents a security intrusion or other anomalous condition of sufficient severity to warrant alerting. Based on the composite alert signal, the platform performs an alert-based operation, such as generating a user-facing alert, initiating an automated mitigation, or updating a contextual model of system behavior. By combining the analytical outputs of heterogeneous heuristics, the disclosed architecture enhances the accuracy and contextual relevance of automated intrusion detection within complex computing environments.

The invention discloses an event analysis model training method and system based on progressive multi-view exploration, and the method comprises the steps: constructing a multi-view sample generation engine, and generating a multi-view answer set for the same event sample through a differential prompt template by using a heterogeneous knowledge base and a multi-source event corpus; performing semantic deduplication and consistency verification on the multi-view answer set, calculating semantic similarity between answers based on a pre-training language model, performing clustering deduplication on the answers with the similarity exceeding a threshold value, and verifying effectiveness and timeliness of reference information through a knowledge graph; establishing a difficulty quantitative evaluation matrix, performing objective and subjective fusion difficulty grading on the training samples, and calculating a comprehensive difficulty score by combining the two results; and dividing the training sample into a plurality of difficulty grades according to the comprehensive difficulty score, and executing progressive staged training based on a grading result, so that the model is gradually transited from a low-difficulty sample to a high-difficulty sample, and multi-view fusion learning and progressive ability optimization are completed.

The invention discloses an intelligent sports event decision-making system based on causal-driven multi-modal fusion and spatio-temporal dynamic reasoning. The system comprises a multi-modal causal data acquisition and preprocessing module; a causal-oriented multi-modal knowledge graph construction and updating module, wherein the causal-oriented multi-modal knowledge graph construction and updating module is provided with a causal structure learning algorithm and an online learning framework; a space-time perception hybrid agent module; the causal constrained dynamic decision optimization module is provided with a deep reinforcement learning algorithm; and the interpretability analysis and visualization module is used for receiving the decision strategy sent by the space-time perception hybrid agent module, generating decision explanation according to the decision strategy and visually presenting the decision explanation. The objective of the invention is to construct an intelligent system capable of providing high-precision, interpretable and adaptive decision support by integrating causal reasoning, multi-modal learning and reinforcement learning, so as to significantly improve scientificity and effectiveness of sports event analysis and decision.

The invention relates to the technical field of health information processing, and particularly discloses a user health data intelligent acquisition and management system based on data analysis, which performs event analysis and standardized coding on original health data to generate a user-level standardized event sequence; automatically constructing a causal structure network representing the causal relationship between the event types by analyzing the time delay dependence between the event types and executing a conditional independence test; further, instantiating a specific event into a node according to the causal network and a personal event sequence, establishing an edge with tense and causal composite attributes, and constructing a personalized event association network; performing data completion and prediction through multi-hop attribute propagation and multi-path evidence aggregation based on the network, and outputting a result with confidence evaluation; and dynamically optimizing the network by using a high-confidence result, and analyzing an influence propagation path of a key event to generate a personalized health analysis conclusion.

The invention belongs to the technical field of network security, and particularly relates to a highway toll threat event prediction and traceability system based on deep learning, which comprises a highway networked toll system. The network safety work management platform is used for forming a planned management strategy by combing the existing safety management work flow of the highway networked toll collection system; the network security operation and maintenance service risk management system is used for constructing an expressway network toll collection system operation and maintenance service security risk management system; and the abnormal event analysis system is used for constructing a visual safe brain for abnormal event analysis and prediction and has an event tracing function. According to the invention, an efficient and visual management platform is created to deal with emergency situations and task changes, construct a security risk management system, ensure data security and integrity and construct a security brain for anomaly analysis, so that a manager can monitor the network security state in real time and make a response quickly.

The invention discloses an alarm condition space-time positioning method and system based on historical alarm condition data governance, and the method comprises the steps: obtaining historical data, and carrying out the preprocessing of the historical data; performing text analysis and extraction on the preprocessed historical data, and extracting to-be-treated alarm address data from the preprocessed historical data; constructing a multi-task combined learning model based on Transform, and training the multi-task combined learning model by using a training set containing standard alarm data; inputting to-be-governed alarm address data into the trained multi-task joint learning model to obtain governed alarm address data; and extracting alarm condition attribute information according to the treated alarm condition address data, wherein the alarm condition attribute information comprises time attribute information and space attribute information. According to the method, the alarm data are governed by using the Transform-based multi-task joint learning model, the governed standard alarm data are obtained, and a data basis is provided for alarm event analysis based on time-space dimensions.

The invention provides a multi-modal data real-time analysis and feedback method and system, and the method comprises the steps: collecting a video frame and an audio frame, reading a count value of the same monotonic timer when the collection of the video frame and the audio frame is completed, and generating an audio and video sequence; calculating the behavior popularity of each region in each time slice based on the sequence, and generating a region set for multi-modal event analysis in combination with a preset threshold and a quantity upper limit; scheduling the corresponding video sub-blocks to a visual computing power unit for target positioning and action classification, and executing voice activity detection and keyword category judgment on the time-aligned audio clips at the same time; visual and audio results are fused, and a structured event sequence is generated according to time slice and region compression; and constructing a classroom teaching chain through the sequence, identifying a key event, and finally generating a teaching event description. According to the invention, under the condition of domestic chip combination, cost, time delay, multi-modal consistency and data security controllability are considered, and real-time perception and feedback of teaching behaviors are effectively supported.

This invention relates to the field of information extraction technology, and discloses a method and system for extracting elements from long-text news events based on multi-agent collaboration. The method includes the following steps: constructing a large language model multi-agent system architecture; a central coordinating agent receiving unstructured news text; a text segmentation agent outputting logical units and their time descriptions; an event extraction agent extracting the event subject, action, and object, and completing time and entity role information; a scene matching agent determining the fine-grained news scene category to which it belongs; an information extraction agent generating structured event records; and a central coordinating agent performing quality review and anomaly handling on each step of the output to ensure the integrity and consistency of the output data. This invention, through relationship building and contextual analysis agents, can construct static relationships between event subjects based on structured event information, and summarize event situation changes based on a timeline, improving the feasibility and visualization of the system's news event analysis.

The invention provides an event analysis method and related equipment, relates to the field of artificial intelligence, and is used for automatically analyzing a reason for an alarm event during safety alarm analysis so as to help a program to understand an analysis result and facilitate operation and maintenance personnel to locate the reason for system abnormality. In the method, a first device obtains a plurality of system events; the first device analyzes the plurality of system events through a language model to obtain an analysis result, the analysis result comprises whether each system event needs to be alarmed or a reason for alarming the system event needing to be alarmed, a plurality of strategies are configured in the language model, and the system events need to be alarmed. The multiple strategies are used for generating multiple cue words of the language model.

The present invention relates to a method and a system configured for analyzing computer events in the context of cybersecurity. In particular, the present invention relates to event collection, the normalization of elements specific to these events, and the calculation of an overall criticality score based on a similarity analysis with a database of reference events. Fig. 1

The invention relates to the technical field of power grid equipment operation state monitoring, in particular to a power grid main and auxiliary equipment real-time alarm information intelligent confirmation method, which comprises the following steps of S1, acquiring alarm information of main and auxiliary equipment in real time, including acquiring an alarm interface image through an image acquisition module, and extracting alarm text content by adopting an image recognition technology; s2, event analysis is carried out on the extracted alarm information, an event analysis result is generated in combination with a preset defect knowledge base and a deep learning model, and the event analysis result at least comprises event categories, priorities and repair suggestions; s3, alarm confirmation operation is automatically executed according to the priorities and the event types of the event analysis results, system confirmation is directly conducted on low-priority events, and a manual intervention process is triggered for high-priority events.

The invention discloses an event inducement discovery system and method fusing deep reasoning and a graph neural network, and relates to the field of event analysis and processing. The system comprises: a knowledge base construction module, which is based on a news event database, constructs an event knowledge base through operations such as text partitioning, vector embedding, database foreign key association and the like, and is used for retrieval enhancement generation; the deep reasoning module is used for autonomously reasoning and collecting potential effective information of event inducements through operations such as retrieval statement generation, knowledge base retrieval, effective information extraction and sufficiency test by taking a large reasoning model as a base; the graph neural network module is based on the event relation graph, and assists in reasoning to obtain potential causal relations in the interlaced complex event text; the inducement mining module is used for mining event inducements from related materials by fully utilizing the reasoning capability of a large reasoning model through a professional cue word template; the invention further provides a method. The problems that event relations are complex and interlaced, and event inducements are difficult to analyze are solved.

The invention discloses an event simulation display method and device of an MEMS test system and a medium. The method comprises the steps that log data are collected from at least one subsystem; performing timestamp synchronization on each log data, determining at least one event arranged along a timeline according to each log data, and generating an event sequence; determining a target event from the event sequence; and based on the user interface state model, according to the log data corresponding to the target event, reconstructing the user interface when the target event occurs, and displaying the user interface, thereby solving the problem that the isolation state of the multi-source log is not synchronous with time, automatically establishing an event causal chain, reducing the cost and error rate of manual data association, and improving the user experience. The event analysis and fault diagnosis period is shortened, the shutdown loss of equipment is reduced, the complete operation context of the target event can be restored in a visual mode, the technical threshold of system operation and maintenance is reduced, and the accuracy, usability and universality of root cause analysis are improved.

This invention discloses a method, device, and system for automatically generating power outage event analysis reports in distribution networks using an artificial intelligence large-scale model. The method includes: automatically acquiring multi-source data (unstructured data) in response to a power outage event in the distribution network; using artificial intelligence technology to extract and clean the acquired multi-source data into a structured form, creating a unified event data model; performing FA action inversion, terminal status analysis, network weak point diagnosis, and emergency repair process inversion based on the line topology and the event data model to generate analysis results; and inputting the analysis results into a pre-trained power large-scale language model for root cause analysis, problem exposure summary, and rectification measure recommendation to automatically generate a structured fault analysis report. This invention can completely solve the problems of difficult data collection, low analysis efficiency, strong report subjectivity, and poor implementation of rectification plans in existing technologies.

The application belongs to the technical field of time series data analysis, and discloses an online time series event analysis method and system based on heterogeneous memory fusion, which comprises the following steps: acquiring streaming time series data and preprocessing, extracting features from the preprocessed data to obtain time series feature sequences; long-term feature memory, event state probability memory and event-level semantic memory are constructed and fused to form a fusion memory; an event query representation is initialized, and the event query representation is enhanced through a short-term memory and a fusion memory in turn to generate a final event query representation; based on the final event query representation, an instantaneous event state and a candidate event instance at the current time are generated, the candidate event instance is de-redundant and cross-time deduplication processed, and a final event set is output. By constructing and fusing heterogeneous historical memories, the application realizes effective utilization of multi-granularity time series knowledge, thereby significantly improving the accuracy, stability and real-time performance of online event analysis under strict causal constraints.

The invention discloses a virtual resource allocation method and device and electronic equipment. The method comprises the following steps: receiving a virtual resource allocation request for a target object; in response to the virtual resource allocation request, dynamic interaction data, related to the credit rating, of the target object in the virtual space is determined, and the dynamic interaction data carries a target label; the dynamic interaction data carrying the target label is input into a behavior event analysis model, a first credit level corresponding to the credit level is obtained, a path selection layer of the behavior event analysis model comprises M model paths, and the M model paths correspond to different network architectures; and determining a virtual resource allocated to the target object according to the first credit level. According to the method and the device, the technical problem that the credit rating of the user is difficult to accurately determine because the mode of determining the credit rating of the user is limited in related technologies is solved.

The invention provides a large model event analysis enhancement method based on multi-dimensional retrieval enhancement generation, and relates to the technical field of artificial intelligence and information analysis crossing. After to-be-retrieved information is obtained, on one hand, a network retrieval result is inquired on a network, an image-text consistency evaluation result and a semantic authenticity evaluation result are obtained according to the network retrieval result, and first corpus data are obtained by integrating the network retrieval result, the image-text consistency evaluation result and the semantic authenticity evaluation result; on the other hand, the to-be-retrieved information generates retrieval vectors in multiple dimensions, a knowledge retrieval result of each dimension is obtained through retrieval in a corresponding preset knowledge database, and the knowledge retrieval results of multiple dimensions are integrated to obtain second corpus data. And combining the first corpus data and the second corpus data to obtain an enhanced corpus, and taking the enhanced corpus as semantic data to be analyzed by a large model. When a large model executes an analysis task by using the semantic data provided by the scheme of the invention, an analysis result with higher credibility can be obtained.

The application relates to the technical field of data life cycle management, and discloses a dynamic self-adaptive data life cycle management system and method, which comprises the following steps: logically binding a data object with a business genealogy log of the data object, calculating a genealogy entropy value in a non-semantic counting manner based on the log, and directly determining a life cycle strategy of the data object in a preset strategy mapping relationship according to the entropy value. The application establishes a data management path which does not depend on an external complex rule engine for event analysis, so that the management strategy can be endogenously and deterministically generated from the business history record of the data itself, and meanwhile, the application can also realize the automatic rollback of the control level of the data which is placed in a high-level control due to an accidental high-risk event after the risk of the data has actually dissipated, thereby reducing the coupling degree and maintenance complexity of the whole management system.

The invention discloses a classroom event analysis method and an analysis model optimization method and system, and relates to the technical field of edge computing. The method comprises the following steps: acquiring real-time classroom data acquired by classroom sensing equipment by edge equipment, and storing the real-time classroom data into an offline classroom file; detecting a real-time event stream in the real-time classroom data through a preset lightweight detection model; the lightweight detection model is optimized through an off-line event stream of an off-line classroom file after class, and the off-line event stream is obtained by analyzing the off-line classroom file through a high-precision detection model; and sending the real-time event stream to visual equipment, so that the visual equipment displays the real-time event stream in real time. Through the above technical means, the lightweight detection model rapidly analyzes the real-time classroom data to obtain a high-timeliness real-time event stream, the after-class model optimization can continuously improve the detection precision of the lightweight detection model, the timeliness and precision of the real-time event stream are considered, and instant and reliable decision support is provided for current teaching.

The invention provides a training method and an analysis method of a financial event analysis model, equipment and a storage medium. According to the financial event analysis model training method provided by the invention, an original supervision data set is automatically enhanced by introducing a knowledge graph and a thinking chain prompt template, a high-quality instruction fine tuning data set containing clear reasoning logic is generated, and then fine tuning training of a base large language model is guided; according to the method, the technical problem that domain knowledge is injected into a shallow layer and the model reasoning process is uncontrollable is effectively solved, and the performance of the financial event analysis model obtained through final training in the aspects of specialty, accuracy, interpretability and output structuring degree is remarkably improved.

The invention discloses a power distribution network operation state evaluation and fault early warning method and system based on data fusion and deep learning. The method comprises the following steps: collecting and preprocessing multi-source heterogeneous data to obtain preprocessed data; based on the preprocessed data, high-dimensional feature extraction and fusion are carried out to obtain a fusion feature vector; performing operation state evaluation and risk quantification based on the fusion feature vector to obtain a risk index; and based on the risk index, carrying out fault early warning and positioning. According to the application, a data island is broken through, effective fusion and collaborative analysis of electrical, physical, chemical, environmental and other multi-dimensional data are realized through the deep learning model, and perception is more comprehensive; unsupervised or self-supervised learning is utilized, unknown and weak fault precursor features can be found, transformation from post analysis to pre-warning is achieved, and a pre-warning time window is greatly advanced.

Techniques for dynamically generating playback clips for key events occurring are disclosed herein. According to some embodiments, a technique can be implemented at a computing device and includes the steps of: (1) providing media content to at least one machine learning model to output a plurality of segments of the media content, where each segment is marked with a respective at least one classification describing a property of the segment; (2) receiving a plurality of key events; and (3) for each of the plurality of key events: analyzing at least one of the plurality of segments according to the key event to determine a start point and an end point of a playback clip for the key event, and generating the playback clip based on (i) the media content and (ii) the start point and the end point.

The invention discloses a multi-agent cooperative urban event handling system based on a large model, relates to the technical field of artificial intelligence, and solves the problems of tedious event task handling process and repeated dispatching of event tasks. The urban event disposal system comprises an intelligent agent module and a collaboration module. The agent module comprises an event reporting agent, an event acceptance agent, an event distribution agent, an event handling agent, an event checking agent and an event analysis agent; performing pre-recommendation of event handling departments on the event semantic vectors through a distribution reasoning model to generate a candidate department list; determining a business property, a liability list and an event responsible department of the city event through a dynamic discrimination algorithm; checking a problem area of an event report image through an automatic review model, and calculating probability values of event disposal completion and case settlement completion so as to assist a checker in checking an event state; the event task disposal process is simplified, and the situation of repeated dispatch of the event tasks is reduced.

The invention provides a method and device for creating an intelligent decision data set based on log data, and relates to the technical field of cloud computing, cluster management, big data processing and artificial intelligence, and the method comprises the steps: collecting original log data from a server and a cluster, and achieving the collection and preprocessing of the log data; key information is extracted from the preprocessed log data, and log event analysis and structured processing are realized based on a self-attention mechanism; high-quality features are extracted and constructed from structured log data, and feature engineering and data enhancement are achieved; and combining the enhanced feature set with a predefined decision target to generate an intelligent decision data set for model training and evaluation, thereby realizing construction and evaluation of the intelligent decision data set. According to the method, high-quality data support is provided for the intelligent decision model, the system resource demand, the task execution time and the failure risk can be effectively predicted, the resource allocation efficiency is greatly optimized, and a solid foundation is provided for large-scale computing system resource management and scheduling.

The invention discloses a public opinion risk staged dynamic evaluation method and system based on CAMEO-ARO event analysis. The method comprises the following steps: acquiring and preprocessing multi-source public opinion data; identifying an event cluster and deconstructing the event cluster into an event ARO main body and an event context; based on a CAMEO standard, carrying out classification coding and preliminary quantification on the event ARO main body to generate an event CAMEO-ARO main body; dynamically identifying the life cycle stage of the event by adopting a double-engine hybrid model combining rules and unsupervised point change detection; constructing a multi-dimensional index system fusing the event CAMEO-ARO subject risk and the propagation situation risk, dynamically adjusting the weights of the two according to the life cycle stage, and calculating a comprehensive risk score; and performing risk trend prediction by using the time sequence prediction model, and establishing a dynamic adaptive closed-loop learning mechanism. The public opinion risk assessment method improves scientificity, accuracy, dynamics and interpretability of public opinion risk assessment.

This invention provides a method and system for understanding long-form traffic videos that combines generation and cognition. Through latent semantic modeling and a perceptual reflection loop mechanism, it achieves continuous cognition of traffic scenes over long time scales, avoiding reliance on only local fragment information and improving the overall understanding of long-form traffic videos. By introducing traffic scene generation and future state prediction, the system can simultaneously consider past and potential states, improving its ability to judge complex traffic problems and enhancing its cognitive and reasoning abilities regarding future traffic states. By unifying the representation of historical perception information and future generated information, information fragmentation is reduced, improving the consistency and stability of cognitive reasoning. This solution integrates historical perception and future generation of traffic scenes into a perceptual reflection loop, achieving a forward-looking and holistic cognitive understanding of long-form traffic videos, providing a sound theoretical foundation for intelligent traffic monitoring and event analysis systems.