32 results about "Event risk" patented technology

The invention relates to the technical field of data processing, in particular to a backtracking analysis model construction method based on an attack chain, which comprises the following steps that: a kernel layer security agent acquires process, file and network behavior characteristics in a hardware isolation environment, and generates an event tuple; the tensor network pipeline performs three-dimensional decoupling mapping on the tuple into a behavior fingerprint vector, an orthogonalization noise feature and an asymmetric adjacent tensor, and compresses the behavior fingerprint vector, the orthogonalization noise feature and the asymmetric adjacent tensor into a space-time topology tensor block; the reinforcement learning controller constructs a directed acyclic graph based on the tensor blocks, calculates connectivity loss and outputs an event risk score; the dynamic routing engine constructs a decision tree model according to the risk mark, the burst frequency and the correlation entropy, and implements three-level shunting and a multiple simulation system to generate an anti-interference index; and when the deviation between the physical trajectory and the digital model exceeds the tolerance, the closed-loop feedback weight coefficient updates the loss function parameter and adjusts the channel resource weight. And the problem of threat discovery delay caused by attack chain breakage under massive events is solved.

The invention discloses an intelligent event studying and judging method based on machine learning, which comprises the following steps of: extracting features from multi-source event data, constructing an event fragment set with a uniform structure according to a preset time window, identifying fragments with stable features in the event fragment set as normal samples, constructing a reference model through an MCD algorithm, and analyzing the normal samples. The method comprises the following steps: extracting feature distribution in a normal state, comparing a to-be-analyzed event with a reference model, calculating feature offset, forming a behavior trajectory, determining an anomaly judgment range by adopting an elliptical envelope algorithm, and finally evaluating an event risk level and dynamically adjusting reference sample composition according to a continuous anomaly condition to realize intelligent identification and risk judgment of the event. According to the invention, dynamic perception and intelligent identification of complex events can be realized.

The invention discloses an insurance short video content generation method and device, a medium and a program product, and relates to the technical field of artificial intelligence. Semantic analysis is performed on hot event data to extract core risk elements, so that the system can capture risk features concerned by the current society. The core risk elements are matched with the guarantee demands of the potential users, the guarantee gap is determined, and the association mapping between the hot event risks and the guarantee demands is established, so that the determination of the target insurance product has risk guidance. And determining a cue word generation strategy from a preset strategy library and inputting the cue word generation strategy into the insurance field large language model to generate a first draft of the content, thereby realizing automatic generation of the content. And in combination with a preposed compliance detection mechanism, the compliance of the generated content is ensured. Quick response and generation of the insurance short video content are realized, and the content generation efficiency is improved.

The invention belongs to the field of big data processing, and particularly relates to an event analysis method, device and equipment and a storage medium, target event information is obtained, the target event information is converted into event feature vectors, the event feature vectors are input into multiple analysis models respectively, and the analysis models output corresponding event types and initial risk levels respectively. Performing similarity matching on the event feature vector and a historical event feature vector of a historical event in a preset knowledge base, screening one or more pieces of historical event information of which the similarity score is greater than a preset threshold, and determining the credibility of each analysis model based on the historical event information and the event type, performing weighted fusion on the initial analysis result based on the credibility of each analysis model, and determining a target risk level corresponding to the target event information; according to the method, by combining multi-model analysis, historical data similarity matching and credibility weighted fusion, the accuracy of risk level judgment of the target event is improved.

The embodiment of the invention discloses a news event-based information processing method and a related device, and the method comprises the steps: collecting news events pushed by a plurality of news sources, and extracting feature information in the news events; according to the feature information, eliminating repeated news events from different news sources to obtain a plurality of target news events; marking the plurality of target news events; determining a risk score of each target news event in the plurality of target news events; calculating and determining a push priority of each target news event in the plurality of target news events; and according to the pushing priority, determining a pushing sequence of the plurality of target news events, and sending the plurality of target news events carrying information of the pushing sequence to the terminal equipment. Therefore, event risk analysis is carried out on the news events and the like, and the news pushing sequence is dynamically adjusted according to service requirements, so that the load of the server is effectively reduced, the resource consumption is reduced, meanwhile, the news pushing delay is reduced, and the information processing efficiency is improved.

The invention relates to the technical field of artificial intelligence session processing, and discloses a context intention recognition-based instruction chain generation method, which comprises the following steps of: extracting an event type from a user session request, determining an event risk level, establishing an intelligent session window for a low-risk or medium-risk event, and generating a context intention recognition instruction chain; dynamically capturing user input and context information to form basic session features, and inputting the basic session features into a dominant intention recognition network to obtain first intention information and confidence; generating and displaying a reply based on the first intention, and performing real-time scoring through an emotion perception model; when the emotion or intention confidence of the user is lower than a threshold value, constructing an enhanced session feature and inputting the enhanced session feature into the implicit intention recognition network to obtain second intention information; and finally, generating an ordered instruction chain in combination with the first intention and the second intention. Therefore, accurate intention recognition, intelligent reply and automatic business operation in multiple rounds of sessions are realized.

The invention provides an electric power marketing service event risk hierarchical identification method and system based on knowledge graph semantic modeling, belongs to the technical field of electric power marketing service event risk identification, and solves the problems of data islanding, semantic understanding deviation, poor scene adaptation and high manual dependence in the prior art. According to the technical scheme, the method comprises the steps that multi-source data including 95598 appeals, electric vehicle charging / live broadcast electricity utilization and the like are collected, a knowledge graph with entity links is constructed, and risk identification is achieved through hierarchical semantic modeling, three-level risk identification and dynamic optimization. According to the method, the data association rate and the risk identification precision can be improved, the enterprise operation cost is reduced, and the digital transformation of enterprise power marketing is promoted.

The invention discloses a news event risk indicator association relationship prediction method based on an equilibrium manifold graph, and belongs to the technical field of risk assessment. The method comprises the steps of collecting an original text of a news event, labeling risk indexes, and constructing a training set, a verification set and a test set; constructing a graph neural network based on a balanced manifold graph; using the samples in the training set to train the balanced manifold network, verifying through the verification set, and obtaining the risk index prediction accuracy on the test set; and collecting a news event text to be analyzed, and predicting the event risk index by using the trained model to obtain one or more indexes with the highest association degree. According to the method, the incidence relation between the event and the waiting index can be fully mined, and the precision is improved.

This invention belongs to the field of overflow events, specifically relating to a hierarchical multi-joint learning-based method, system, and equipment for predicting well control overflow events. It aims to address the problems of equipment damage, production interruption, safety accidents, and environmental pollution caused by overflow event risks. The invention includes: training multiple well control overflow event prediction base models based on the training set; obtaining prediction results based on the test set; calculating the accuracy of the base models and selecting retained models to obtain a final feature set; integrating the retained models based on the final feature set to construct a voting-based ensemble model; and inputting the data to be predicted into the ensemble model to obtain the well control overflow event prediction result. This invention improves prediction accuracy and robustness by constructing an ensemble model, optimizes resource utilization, enhances operational safety and decision-making efficiency, effectively prevents well control overflow events, and ensures the safety and economic benefits of oilfield operations.

A computer system for analyzing and mitigating risks associated with an event is provided. The computer system is configured to: (i) receive at least one of a city risk profile and a building risk profile from a database; (ii) receive city systems data from the city services computer system; (iii) utilize a trained machine learning model to determine at least one potential risk associated with the event; (iv) generate an event risk profile that includes the at least one potential risk associated with the event; and / or (v) generate a risk mitigation output based upon at least one of the city risk profile and the at least one potential risk, wherein the risk mitigation output includes at least one of a risk alert, a risk mitigation recommendation, and risk mitigation instructions. Computer systems for analyzing and mitigation risks associated with a city, a building, and a user are also provided.

This invention relates to the field of artificial intelligence conversation processing technology, and discloses a method for generating instruction chains based on contextual intent recognition. The method includes: extracting event types and determining event risk levels from user conversation requests; for low-risk or medium-risk events, establishing an intelligent conversation window; dynamically capturing user input and contextual information to form basic conversation features; inputting these features into an explicit intent recognition network to obtain first intent information and confidence level; generating and displaying a response based on the first intent, while simultaneously scoring it in real time using an emotion perception model; when the user's emotion or intent confidence level is below a threshold, constructing enhanced conversation features and inputting them into a implicit intent recognition network to obtain second intent information; finally, combining the first and second intents to generate an ordered instruction chain. This achieves accurate intent recognition, intelligent response, and automated business operations in multi-turn conversations.

The invention discloses a chronic disease whole-process digital medical treatment cloud service and medical insurance real-time supervision unified large model. The model comprises a technical architecture and a combination engine; the technical architecture comprises an infrastructure layer, a data base layer, a core technology layer, a business application layer and an ecological collaboration layer. The combination engine comprises federated learning and block chain combination, digital twinning and AI and big data combination, edge calculation and 5G and Internet of Things combination, NLP and knowledge graph and AR combination, quantum encryption and zero knowledge proof combination, and Web3.0 and DAO combination. Through cross-layer cooperation of a five-layer technical architecture and six technology combination engines, balance between data sharing and privacy protection is realized, cross-mechanism data islands are broken, data security compliance is guaranteed through technologies such as federal learning block chain quantum encryption, and the contradiction between data intercommunication and privacy protection in the prior art is solved; according to the digital twinborn AI big data combination, a full-process risk control system is constructed, and risk pre-prediction in-event intervention and post-event optimization are realized.

The embodiment of the invention provides a risk early warning method for medicine production, electronic equipment and a medium, and belongs to the technical field of medicine production and artificial intelligence. The method comprises the following steps: acquiring at least one of personnel behavior data, equipment operation data, process data, material data and environment data in a drug production area, performing risk detection on each source data, and generating a reference event according to other source data in multi-source data to predict the risk of a risk event, and executing an early warning operation matched with the risk event and the event risk degree corresponding to the source data. According to the embodiment of the invention, real-time risk event detection and early warning operation are carried out on the drug production area, so that the final influence of risk events such as non-standard operation on the drug quality can be reduced fundamentally.

This application relates to the field of public safety decision-making technology, specifically disclosing an artificial intelligence-driven public safety decision support system. First, it utilizes a security event element extraction module to extract event elements from historical public safety events, and then uses an event spatial distribution clustering module to geographically divide the target area based on a planning map. Next, an event temporal distribution sorting module arranges these event elements chronologically, forming a time series. Subsequently, an event semantic information analysis module uses organic propagation analysis of event semantic information to generate organically encoded representations of the semantic information transmission of public safety events in multiple historical regions, capturing the dynamic semantic relationships between events. Finally, an event risk discrimination module combines the above encoded representations and the planning map to identify the public safety risks in the target area. This effectively integrates information from both temporal and spatial dimensions, enhancing the understanding and prediction capabilities of the complex dynamic interactions of public safety events.

The invention relates to a large-energy micro-seismic event risk evaluation method based on deep learning, which constructs a multi-dimensional feature data set by fusing signal space-time attributes and geologic features, and provides comprehensive information for model training. The Bi-LSTM is adopted to capture the time sequence characteristics of the micro-seismic signals, and the geological structure information is combined to realize the accurate assessment of the risk of the micro-seismic event. A training set and a test set are reasonably divided, and an RMSE performance index is adopted for evaluation, so that the model is ensured to have good generalization ability and prediction precision. The method optimizes the model structure and parameter setting, improves the training efficiency and stability, and is suitable for a complex coal mine production environment. Finally, the method can effectively warn rock burst disasters in an early warning mode, reduce casualties and equipment damage risks and optimize mine mining plans and safety management, and has important practical value and application prospects.

The embodiment of the application discloses a kind of event risk detection methods, equipment and medium based on large model, belong to risk detection technical field, solve the problems that prior art scene poor adaptability, rely on sample and artificial rule, so that the risk detection accuracy and efficiency of complex and diverse event are lower. Including, based on the industry knowledge and industry scene information obtained, event risk detection processing template is constructed;Wherein, event risk detection processing template is used to provide detection processing logic for event risk detection model;Obtain the event basic data corresponding to the event to be detected, retrieve event related knowledge data in the preset vector database based on event basic data;Event basic data and event related knowledge data are filled into event risk detection processing template to obtain input prompt word;Call event risk detection model, based on event risk detection model and input prompt word carry out event risk detection, and output detection conclusion.

The present application relates to the technical field of public opinion monitoring, and particularly relates to a public opinion dynamic monitoring and early warning system based on text clustering analysis. In the clustering process, the semantic center of historical event clusters is introduced as a constraint condition, so that the semantic continuity of existing events can be fully considered when the public opinion text is classified, and event misjudgment or repeated generation caused by short-term expression changes can be effectively avoided. By constructing a drift suppression mechanism based on the semantic center change amplitude, the unstable event clusters are adjusted, the stability and accuracy of event evolution modeling are improved, the cross-time window event clusters are associated and determined, the stable event clusters are formed, the tracking management of public opinion events is realized, the text scale, the emotional mean, the emotional heterogeneity, the evolution characteristics of the scale and the emotion are introduced, and the low sample compensation mechanism is combined to model the public opinion event risk, so that the high-risk events are not ignored, the mature event risk is not excessively enlarged, and the timeliness and accuracy of public opinion early warning are improved.

The invention relates to a nuclear power plant external event configuration risk management assessment method and system, a medium and equipment. The method comprises the following steps: acquiring configuration change information of a nuclear power plant; analyzing the configuration change information to judge whether the current configuration change has an external event risk influence on the nuclear power plant or not; if yes, carrying out qualitative screening evaluation on the current configuration change, and obtaining external event risk influences of all current configuration changes; performing quantitative evaluation on the external event risk influence of all the current configuration changes to obtain a quantitative evaluation result; and generating a risk management action strategy based on the quantitative evaluation result. According to the method, external events are included in a configuration risk management range, so that the problem that a nuclear power plant only considers internal event risk assessment management at present is solved, the situation that important risks are ignored or risk management is too conservative is avoided, risk management is carried out on unavailable safety relief equipment with significant external event risks, and the risk management efficiency is improved. And extra safety and economic benefits are realized.

The invention discloses a listed company financial condition intelligent identification and audit simulation analysis platform, and the platform comprises a data fusion module which integrates multi-source data; the financial knowledge graph module is used for extracting an entity relationship to construct a graph; the financial health degree identification module is used for carrying out risk assessment based on a map and a model; the auditing simulation analysis module is used for receiving the auditing hypothesis, performing simulation deduction and outputting an influence path; the visualization module is used for displaying a result and generating an audit report; according to the method, an analysis platform integrating data fusion, knowledge graph, intelligent identification and simulation is constructed, dynamic pre-event and in-event risk early warning is realized, the method can penetrate through a complex company association network, financial statement data and commercial essence, market emotion and association relationships behind the financial statement data are dynamically associated, and the risk early warning efficiency is improved. Therefore, a tool capable of insighting the truth of the business is provided for an auditor and a financial analyst, and the depth and the breadth of financial auditing are greatly enhanced.

The invention relates to the technical field of data management, and discloses an abnormal event discrimination city one-network unified management system based on big data. Comprising an effective work order screening module, a sensitive event screening module, a sensitive event screening module, an abnormal event identification module, an abnormal event identification module, an event risk alarm module, a risk alarm prompt judgment module, an abnormal event analysis module, a risk alarm prompt judgment module, a risk alarm prompt judgment module, a risk alarm prompt judgment module and an abnormal event analysis module, wherein the effective work order is screened from original work orders; the sensitive event screening module is used for screening sensitive events from public events; the abnormal event identification module is used for identifying abnormal events from the sensitive events; the emergency measures are combined into an emergency strategy; according to the invention, potential high-risk events in the society can be accurately informed, and subject departments and emergency measures involved in the high-risk events can be accurately identified and positioned, so that related departments of a city can intervene and manage the high-risk events from the source, continuous aggravation of sudden problems is avoided, and the safety of the high-risk events is improved. The satisfaction of social public opinions and conditions is effectively enhanced, and the healthy and rapid development of urban one-network unified management system construction is promoted.

The invention discloses a monitoring point layout method, device and equipment, a medium and a product. The method comprises the following steps: acquiring a monitoring point data set and an event data set corresponding to a target area; determining a monitoring thermal grid map corresponding to the target area according to the monitoring point data set; the monitoring heating power is used for representing the coverage density of monitoring points in the grid units; determining an event thermal grid map corresponding to the target area according to the event data set; the event heat is used for representing the risk level intensity of the event occurring in the grid unit; performing intersection negation operation on the monitoring thermal grid map and the event thermal grid map to obtain a to-be-monitored area corresponding to the target area; and determining a monitoring point layout scheme corresponding to the target area according to the to-be-deployed and controlled area. Through the technical scheme of the invention, the monitoring point location layout can be optimized based on the thermal grid map, and the event risk area is reasonably covered while the investment of redundant equipment is reduced.

To evaluate an event occurrence risk with high accuracy according to an event occurrence time.SOLUTION: A risk analysis support system includes a processor and a storage device connected to the processor, wherein the storage device stores information indicating a health condition of each of a plurality of persons in each period, and the processor is configured to construct a plurality of risk models for predicting a predetermined risk outcome in accordance with a length of an elapsed period from a reference time point based on the information indicating the health condition of each of the plurality of persons in each period, and predict a risk outcome of a person to be analyzed in accordance with a length of an elapsed period from a predetermined time point by inputting information indicating the health condition of the person to be analyzed into the plurality of risk models.SELECTED DRAWING: Figure 1

The invention discloses an event risk indicator association relationship prediction method based on multi-level graph representation learning, and belongs to the technical field of graph neural network model design. The method comprises the following steps: collecting events within a certain time and corresponding risk assessment index weights and hit scores; the method comprises the following steps: training a Word2Vec model to convert text data into vectors, constructing a graph structure data sample, fusing semantic information of a text and graph embedding feature representation learning of multi-level indexes by using a graph attention network, carrying out risk assessment and prediction by using feature representation of the lowest-level index, and carrying out multi-level index weight updating based on risk true value loss. Meanwhile, a mask strategy is introduced to remove the influence of an irrelevant relation, and a model is trained; and performing event risk index association relationship prediction by using the trained model. According to the method, the incidence relation between the waiting indexes can be fully mined, and the precision is improved.

The invention relates to an emergency broadcast intelligent fragmentation broadcasting method and system based on event risk level assessment, and the method comprises the following steps: obtaining an emergency event information set, constructing a multi-dimensional assessment model, and synthesizing the severity of an event, the population density and the fragility of infrastructure to generate a priority queue; delimiting three-level broadcasting levels of a core influence area, a secondary risk area and an associated area based on a GIS (Geographic Information System); updating the regional risk value in real time by using a sliding time window algorithm, and triggering dynamic adjustment of a priority queue; according to the method, a geographical hash fragmentation technology is adopted for a high-priority area, and Spark memory calculation and distributed parallel processing are combined, so that high-efficiency broadcasting under a large data volume is ensured, and the problems of extensive area division, rigid resource allocation and insufficient information adaptation of traditional emergency broadcasting are solved.

The invention provides a power distribution network fault handling method and system based on event driving and case inversion. The method comprises the following steps: acquiring power distribution network alarm and topological data in real time; performing semantic standardization and invalid filtering on the alarm; based on alarm synthesis of an event template library, the filtered alarms are synthesized into events according to time, topology and causality; event risk weight calculation and sorting; searching and matching a historical case library; generating a disposal suggestion and outputting an operation order; performing closed-loop learning and case library updating; the fault interval positioning time is shortened, the case matching precision is improved, the automatically generated operation order is available, the daily invalid alarm amount is reduced, and correct handling and the system closed-loop updating period of young watchmen in simulation fault drilling are promoted.

This invention relates to a method and system for detecting anomalies in container system calls based on multi-level context. The technical solution employed is as follows: Low-level context data containing process causal relationships and call parameters is captured through a kernel-mode monitoring mechanism. System calls are deconstructed in parallel into three types of feature vectors: at the parameter level, an Event Risk Index (ERI) is generated by analyzing data entropy and error codes to address the semantic vacuum problem; at the temporal level, a deep sequence model is used to capture long-range dependencies and quantify them into an Anomaly Sequence Index (ASI) to overcome local dependency problems; at the causal level, a Control Index (CI) is generated by constructing a process family graph and applying graph representation learning to overcome the structural flattening problem. The three types of heterogeneous vectors are dynamically fused through an adaptive gating fusion network, input into an unsupervised autoencoder model, and the reconstruction error is compared with a threshold to make a decision. This invention can accurately identify advanced threats such as process spoofing and parameter injection, improving the security of container runtime and possessing significant practical application value.

The embodiment of the invention discloses an event risk detection method and device based on a large model, and a medium, belongs to the technical field of risk detection, and solves the problems of low risk detection accuracy and efficiency of complex and diverse events due to poor scene adaptability and dependence on samples and manual rules in the prior art. Comprising the following steps: constructing an event risk detection processing template based on acquired industry knowledge and industry scene information; wherein the event risk detection processing template is used for providing detection processing logic for the event risk detection model; obtaining event basic data corresponding to the to-be-detected event, and retrieving event-related knowledge data in a preset vector database based on the event basic data; filling the event basic data and the event related knowledge data into an event risk detection processing template to obtain an input prompt word; and calling the event risk detection model, performing event risk detection based on the event risk detection model and the input prompt word, and outputting a detection conclusion.

The embodiment of the application discloses a news event-based information processing method and related device, the method comprises the following steps: collecting news events pushed by multiple news sources, and extracting feature information in the news events; according to the feature information, excluding repeated news events from different news sources to obtain multiple target news events; tagging the multiple target news events; determining a risk score of each target news event in the multiple target news events; calculating and determining a push priority of each target news event in the multiple target news events; according to the push priority, determining a push order of the multiple target news events, and sending the multiple target news events carrying information of the push order to a terminal device. In this way, the event risk analysis of news events and the dynamic adjustment of news push order according to business needs effectively reduce the load of the server, reduce resource consumption, reduce news push delay, and improve information processing efficiency.

The invention discloses a digital content popularity modeling method on a multi-segment Sigmoid chain based on security risk adjustment, which identifies a key turning point by introducing a moving average difference method (MAD), and sets a threshold value based on a mean value and a standard deviation or a percentile to effectively screen out a real market change signal. And carrying out quantitative modeling by using a segmented Sigmoid function, respectively carrying out fitting on each screened interval, and optimizing parameters of each segment of Sigmoid function by using a trusted region reflection (TRR) algorithm. And finally, carrying out weighted summation on each section of Sigmoid function, so as to obtain a popularity quantification result of each color. In addition, a systematic security event risk analysis module is introduced for the first time to dynamically adjust an original modeling result. Therefore, the method has remarkable innovation and optimization in the aspects of data sources, processing methods, dynamic change capture and quantitative modeling, the defects in the prior art can be effectively overcome, and a comprehensive, accurate and dynamic popularity quantitative tool is provided.

Provided is a method for constructing a backtracking analysis model based on an attack chain, including: a kernel-layer security agent collects process, file, and network behavior features in a hardware-isolated environment to generate event tuples; a tensor network pipeline performs three-dimensional decoupling mapping of the tuples into behavior fingerprint vectors, orthogonalized noise features, and asymmetric adjacency tensors, and compresses them into spatio-temporal topological tensor block; a reinforcement learning controller constructs a directed acyclic graph based on the tensor block, calculates connectivity loss, and outputs event risk scores; a dynamic routing engine constructs a decision tree model based on risk markers, burst frequency, and correlation entropy to implement three-level shunting, and a multi-simulation system generates anti-interference index; when the deviation between a physical trajectory and a digital model exceeds a tolerance, a closed-loop feedback weight coefficient is used to updates loss function parameters and adjust channel resource weights.