18 results about "Event structure" patented technology

The invention provides a block chain-based clinical test data traceability and sharing platform. The block chain-based clinical test data traceability and sharing platform comprises the following modules: a life cycle state definition module, an on-chain event generation module, an identity verification module, a state transition logic unit and an event chain construction module. According to the invention, through cooperation of a life cycle state definition module, an on-chain event generation module, a state transition logic unit and an event chain construction module, key behaviors generated by a subject in the stages of screening, informed agreement, group entering, visit, adverse event processing, follow-up visit and the like are solidified into a chain event structure according to a time sequence; each event node comprises a behavior abstract, a preorder node hash and a timestamp, continuous association and accurate positioning of cross-stage operation are achieved, a clinical test is converted into a state transition chain capable of tracking the whole process from a fragment type data uplink, and the problem that a continuous behavior chain cannot be constructed in the prior art is solved.

The invention discloses a document-level event argument extraction method and system based on a semantic fusion graph, and the method comprises the steps: building a semantic mention graph by taking entity mentions in a document as nodes of the graph and semantic relationships as edges, fusing a graph structure into a large language model for embedding representation through a multi-layer encoder, and dynamically updating node and edge information through an attention mechanism. The embedded representation of the enhanced context semantics is obtained; constructing an event graph based on all event structures in the document, modeling a multi-event association relationship, and fusing the multi-event association relationship into a large language model decoder to strengthen the understanding of the model on the association between events; the method comprises the following steps: constructing cue sentences according to event types, synchronously inputting multi-event cue sentences in a training stage, designing a weighted loss function, guiding a model to learn multi-event information interaction, inputting the multi-event cue sentences in a reasoning stage, and only taking a target event argument result as an evaluation standard. According to the method, document noise can be suppressed, the problems of scattered distribution and long-distance dependence of events and arguments are solved, and the accuracy and robustness of argument extraction are improved.

The invention relates to the technical field of network security monitoring, in particular to a block chain-based network data security monitoring system, which comprises a pre-chain event integration module, a field writing constraint module, an event evolution verification module, a structure association verification module and an evidence storage control module. According to the method, semantic-level integration and session-level continuous identification are carried out on the communication flow, so that the security event forms a record by taking complete communication semantics as a basic unit, the event field state has consistency and interpretability, the evolution sequence is corrected in the event time direction and the connection state level, the communication process is prevented from being mistakenly split, and the communication efficiency is improved. Through cooperative verification of communication object behaviors and response states, a single event structure is ensured to be complete and conform to security monitoring semantics, and a condition matching and sequence adjusting mechanism is introduced in a writing process, so that event records have verifiable evolution trajectories and non-repudiation evidence storage results, and the reliability of the event records is improved. And the credibility and audit value of network security monitoring are improved.

The invention relates to a traffic network security event extraction method based on machine reading understanding, which performs joint training and optimization on a trigger word prediction module and an argument extraction module by sharing a coding layer of a pre-training language model, so that two tasks promote each other in a shared semantic space. Accurate context constraints are provided for argument role judgment through trigger word recognition, disambiguation of trigger word types is facilitated through argument information, and the deep interactive optimization mechanism enables the model to learn collaborative representation sensitive to the whole event structure. Therefore, the overall accuracy of event extraction and the generalization ability of the model are remarkably improved, and the inherent error propagation problem in a traditional assembly line method is solved.

The invention relates to the technical field of data processing, in particular to a negative information real-time capturing method and system based on a web crawler, and provides the following scheme that cross-platform and multi-mode observation data are obtained through a distributed crawler, and a narrative graph is constructed in a topological manifold space. A topological evolution mechanism based on curvature contraction is adopted for a narrative graph, and a topological gravitation well structure reflecting event consistency is generated through sequential aggregation and cross-layer folding operation of a local neighborhood. And measuring the generation and disappearance processes of the topological gravitational well structure, and judging whether multi-source observation data is derived from the same event or not according to a persistence parameter, so that real-time identification and early warning of negative information are realized. The method is suitable for a social media environment which changes rapidly and is dense in noise, stable tracking of an event structure can be kept under the conditions that semantic expression is unstable and information is carried or rewritten for multiple times, and the accuracy and timeliness of negative information detection are improved.

The application relates to the field of artificial intelligence and knowledge graph, and discloses a time sequence event question and answer method based on structured subgraph retrieval, which comprises the following steps: performing text retrieval on event facts to obtain background information according to a question and answer request; analyzing the request in combination with the background information, extracting corresponding event structure constraints and time constraints; strictly screening event facts from a time sequence knowledge graph according to the constraints, and constructing an event subgraph with time attributes; performing adaptive retrieval generation on the subgraph, uniformly compressing along the time dimension or supplementing knowledge by using text retrieval, and obtaining a final subgraph after adaptive processing; and generating a time sequence question and answer result based on the subgraph. The application retains the structure and time constraints of the time sequence graph, overcomes the input length limitation of the model, and can significantly improve the question and answer accuracy and stability without fine-tuning the model.

The utility model discloses an environmental event structuring device based on adaptive baseline tracking. The device comprises a voltage follower, an operational amplifier, an integral switching network, an AND gate, a timing pulse generator, an inverter and a reset switch, an input signal is compared with a baseline voltage generated by the integral network through the operational amplifier, and the output of the baseline voltage and a timing pulse are subjected to logical operation in the AND gate to generate a self-adaptive control signal; after phase reversal by the phase inverter, the reset switch is controlled to quickly discharge the integrating capacitor, and the integrating switching network is controlled to switch the integrating time constant, so that closed-loop control is formed, and slow baseline tracking in a quiet period and quick reset response in an event period are realized; the device outputs three analog signals of baseline voltage, peak voltage and pulse width voltage in real time through closed-loop control of a hardware circuit, and original signal transmission load is reduced from the source.

The invention is suitable for the technical field of document processing, and provides a document-level event element extraction method and system based on a pre-training language model.The method comprises the following steps that a document is loaded and preprocessed, and the document is segmented into a plurality of text segments through a sliding window method; a word segmentation device corresponding to the pre-training language model is used for marking the text segments, and the text is converted into a token sequence; inputting the token sequences into a pre-training language model, encoding each fragment, fusing the document-level global context, and determining the final representation of each token sequence; event element boundaries are recognized from the final representation of the token sequence, and element types are determined; and taking all the obtained elements as nodes, constructing an element graph, modeling the element graph through a graph neural network, and determining an event structure relationship. According to the method, the global semantics of the long document can be better modeled, the context information of the document can be deeply understood, and the event element extraction quality is improved.

The embodiment of the invention provides a data processing method and device. The method comprises the steps that a target event is converted into an initial event intermediate representation of a preset event structure; determining an event processing pipeline according to the task type corresponding to the target event; performing transformation processing on the initial event intermediate representation according to a plurality of transformation processing stages to generate candidate event intermediate representations; determining a target model according to the candidate event intermediate representation, and determining a rendering processing stage according to the candidate event intermediate representation and model configuration of the target model; and performing rendering processing on the candidate event intermediate representation according to the rendering processing stage, and generating a target event intermediate representation matched with the target model input format. Through the layered, configurable and dynamically adaptive context construction method, the problem of low context generation quality caused by model capability difference, long-range dependency loss, tool calling complexity and insufficient control constraint is solved, and the adaptability, reliability and execution efficiency of a complex agent system are improved.

This application provides a method and system for extracting technical and economic risk events based on monitored entities, belonging to the field of entity extraction technology. The method includes: performing entity recognition on multi-source scientific and technological texts, comparing and filtering technical and economic monitoring entities, and outputting a candidate monitoring entity list; extracting semantic segments using the candidate monitoring entity list as anchors, and determining event types based on trigger word matching rules; performing dependency parsing and semantic role labeling on the trigger word set, constructing a standardized event structure, extracting semantic relationships, and outputting a risk event candidate structure set; identifying chapter-level main events, aggregating paragraph-level related events to form a master-slave event structure; assembling event chains based on the master-slave event structure, and performing standardized output. This application can solve the technical problem of poor reliability in the extraction of economic risk events in the prior art, achieving the technical effect of improving the reliability of extraction.

The application discloses a high-concurrency processor architecture based on an instruction-level event structure and a scheduling method thereof, is based on RISC-V instructions, and defines the stagnation, successful termination, sequential execution, conditional branching and merging operation of a program through a process algebra (PA-ISA) oriented to an instruction set architecture (ISA). On the basis of the PA-ISA, the dependence relationship between instructions in program execution is described through an instruction-level event structure (IES). The instruction-level event structure model is adopted to describe the dependence relationship between instructions in the program, the instruction concurrency is improved, and good expansibility is achieved. The high-concurrency processor architecture based on the IES is combined with an asynchronous circuit, an event triggering is taken as a basic execution advancing mode, the frequency or energy efficiency is improved, the bypass control mechanism in the out-of-order execution is simplified, and the system reliability is improved. The instruction-level event structure is combined with a double-path instruction fetching mechanism, the instruction waste and performance loss are reduced, and the fault tolerance capability under a large-scale instruction fetching strategy is optimized.

The application discloses a network attack path tracking method and system based on a three-domain communication event structure, relates to the technical field of network security, and comprises the following steps: converting the three-domain communication event structure into a heterogeneous graph structure composed of nodes and multi-dimensional label edges, and generating an industrial network topology graph; training a graph neural network model by using the industrial network topology graph, identifying abnormal jump paths and attack chain segments, and generating a suspicious path set; performing consistency calculation and weighted fusion on communication behaviors, protocol calling logic and physical state responses in the suspicious path set, and generating a credibility score vector; performing fusion calculation on the credibility score vector, selecting a path with the lowest credibility as a high-risk attack path, and combining a time sequence, the industrial network topology graph and an abnormal jump path to backtrack and reconstruct an attack path starting point, so that an attack propagation chain is obtained. The application improves the precision and efficiency of industrial network security situation awareness.

The embodiment of the specification provides a data processing method and device, the method comprises the following steps: converting a target event into an initial event intermediate representation of a preset event structure; determining an event processing pipeline according to a task type corresponding to the target event; performing transformation processing on the initial event intermediate representation according to a plurality of transformation processing stages to generate a candidate event intermediate representation; determining a target model according to the candidate event intermediate representation, and determining a rendering processing stage according to the candidate event intermediate representation and a model configuration of the target model; and performing rendering processing on the candidate event intermediate representation according to the rendering processing stage to generate a target event intermediate representation matched with a target model input format. Through this layered, configurable and dynamically adaptive context construction method, the problem of low quality of context generation caused by differences in model capabilities, loss of long-range dependencies, complexity of tool calls and insufficient control constraints is solved, and the adaptability, reliability and execution efficiency of a complex intelligent agent system are improved.

The application belongs to the field of artificial intelligence and natural language processing, and relates to an efficient event extraction method based on controllable pattern generation, which comprises the following steps: obtaining a text sequence to be tested, performing entity extraction on the text sequence to be tested to obtain an event entity set, a trigger word set and a position vector sequence; constructing multiple events according to the event entity set and the trigger word set; the event contains the relationship between the entity and the trigger word; inputting the event and the position vector sequence into a trained event pattern generation model to obtain an event pattern; merging and filtering the event pattern to obtain an event structure; the application learns the definition process of the event pattern based on the candidate mentioned entity by using the generation model, and then automatically generates the event pattern, thereby avoiding modeling of all pre-defined event types and improving the generation efficiency; and the application designs a decoding constraint algorithm to finely control the pattern generation process, prevents obtaining non-standard results and ensures that the number of generated roles corresponds to the number of entities.

The application discloses a kind of ship intelligent monitoring information terminal based on multi-channel aggregation, it is related to ship intelligent monitoring technical field, comprising the following steps: S1, construct the unified element expression set of multi-source monitoring data;S2, using multi-source monitoring data element set carries out event structure mapping;S3, using event structure set and channel state set carries out coupling mapping processing;S4, using transmission mapping set carries out multi-channel transmission execution and local cache processing;S5, using local cache set and transmission result set carries out event integrity reorganization processing.The application is synchronized by being arranged under unified time window constraint, and is organized to multi-source data, and unified event structure including time range, behavior information and state information is constructed by the joint mapping of behavior characteristics and state parameters, effectively solve the problem of multi-source data semantic fragmentation, so that monitoring data is converted from discrete information into structured event with complete semantic expression.

The invention relates to a container escape real-time detection method based on an eBPF and a knowledge graph, and belongs to the field of network security. The method comprises the following steps: capturing multiple types of key events related to container escape in real time through a kernel-level probe by adopting an eBPF technology, and filtering irrelevant behaviors according to a preset triggering condition, extracting corresponding key information fields from the key events, and uniformly packaging the key information fields into a standard event structure; converting event data of the collected standard event structure into nodes and relationships in a container security knowledge graph, forming a semantic network representing a system operation state, and constructing the container security knowledge graph; and according to information in the container security knowledge graph, carrying out mapping analysis on a key event accessed in real time, and judging whether container escape occurs or not through predefined rule matching and abnormal behavior analysis. According to the method, implementation does not depend on a probe in a container, and eBPF deployment is convenient and fast; known mode recognition and unknown anomaly discovery are both considered, and missing report is reduced.

This invention discloses a machine learning-based method for accurate acquisition of environmentally adaptive hydrological and sediment data, belonging to the field of water conservancy information technology. The method utilizes existing monitoring systems to receive raw hydrological and sediment monitoring data in real time. After data preprocessing and time segmentation, a candidate analysis segment set is formed. A convolutional neural network recognition model is constructed to identify the segment labeling status of the candidate analysis segments, generating abrupt event data. First-order difference and symbolic encoding are performed on the time-series data within each window to generate potential constraint codes. The potential constraint codes are sequentially concatenated to generate event structure codes. Based on the event structure codes, each abrupt segment is graded to obtain event grading groups and annotate them. The acquisition mode is determined, and corresponding records in the candidate analysis segment set are extracted and event identifiers are added to generate event-based acquisition data. This invention is used for event identification, tiered acquisition, and data organization in the process of hydrological and sediment monitoring.