100 results about "Safety knowledge" patented technology

The invention relates to the technical field of safety monitoring, in particular to a building construction safety monitoring method and system based on artificial intelligence, and the method comprises the steps: obtaining multi-source heterogeneous data of a construction site, carrying out the distributed feature extraction of the multi-source heterogeneous data through employing a federal learning framework, and generating time-space correlated construction site state representation data; based on a preset dynamic risk prediction model, risk prediction is carried out by using the construction site state representation data, a multi-level risk prediction result is output, and the preset dynamic risk prediction model is constructed based on a construction safety knowledge graph and a space-time diagram neural network; and triggering an adaptive feedback mechanism according to the risk level corresponding to the prediction result, generating visual early warning information and an equipment control instruction, and linking a construction site control system to execute emergency response operation. The problems that a traditional monitoring method is tedious in data processing, insufficient in real-time performance, high in cost, lack of prediction capacity and the like are solved.

The invention relates to a knowledge-data dual-drive-based association modeling method and system, and the method comprises the steps: firstly obtaining video monitoring data, sensor data and domain safety specification knowledge, and carrying out the frame extraction and feature extraction, time sequence standardization processing and structured representation and coding; respectively extracting visual features, time sequence features and semantic features to obtain safety knowledge features; modeling the multi-modal data and the high-order association of the multi-modal data and the safety knowledge by using a hypergraph neural network; multi-modal features and security knowledge features are input into the hypergraph neural network, deep fusion of multi-modal data and security knowledge is realized through hypergraph convolution operation, and a unified representation space is generated; and constructing a potential safety hazard identification model, and performing accurate identification and real-time monitoring on the potential safety hazard in the complex scene through the potential safety hazard identification model. The problems of heterogeneity of multi-modal data and semantic gaps between modals are solved, and the accuracy and real-time performance of potential safety hazard recognition are improved.

The invention discloses a dam safety monitoring method and system based on a knowledge association structure, and the method comprises the steps: collecting the multi-source heterogeneous data of a dam, and obtaining a dam safety knowledge graph; time sequence data in the dam safety knowledge graph are preprocessed, a deep learning model is adopted for modeling and analysis, anomaly detection is carried out, and potential safety hazards of the dam are recognized; the method comprises the following steps: constructing an integrated learning model in combination with multiple machine learning algorithms, performing fault diagnosis on potential safety hazards of a dam, generating dam early warning information, feeding back the dam early warning information to a dam safety knowledge graph, dynamically updating the dam safety knowledge graph in combination with historical data, and performing dam safety monitoring. Based on comprehensive integration of dam safety monitoring data, through modeling and analysis of the time series data by the deep learning model and data-based fault diagnosis of the model algorithm, the accuracy and robustness of dam fault diagnosis are improved, and safety monitoring and early warning of the dam are optimized.

The invention discloses an engineering safety early warning method and system based on artificial intelligence real-time risk identification, and relates to the technical field of engineering safety, and the method comprises the steps: collecting scattered engineering safety data from each engineering platform in batches, and carrying out the preprocessing of the data, and constructing a dynamic database; according to the engineering safety data collected in batches, an engineering safety knowledge graph is constructed, and different risk levels are preset according to engineering safety standards. According to the method, multi-source engineering safety data are integrated, dynamically changing risk characteristics are analyzed in real time by using an AI risk identification model, the hysteresis of traditional manual inspection and static analysis is overcome, a nonlinear relationship among the risk characteristics is captured by using a random forest model through integrated learning of multiple decision trees, and the risk characteristics are analyzed in real time. And the probability values of high, medium and low risk levels are output in combination with Softmax probability normalization, so that the evaluation precision is remarkably improved, the risk features are positioned, the scientificity of risk traceability is ensured, and data-driven decision support is provided for engineering safety management.

The invention discloses an automatic driving safety key simulation scene generation method based on adversarial generation and co-evolution. The method comprises the following steps: receiving a basic traffic scene described by a natural language, generating an antagonistic element scene containing security threats by using a large language model in combination with a traffic safety knowledge base, and analyzing the antagonistic element scene into an executable scene script; constructing a multi-agent confrontation collaboration diagram based on the meta-scene, and recognizing a key background vehicle through a cross-timing attention mechanism in combination with a time mask and time decay mechanism; and performing disturbance optimization on the key background vehicle trajectory to generate an automatic driving test scene. According to the method, a scientific and systematic solution with engineering operability is provided for safety verification of the automatic driving system when the automatic driving system faces real traffic challenges such as multi-source intervention and dynamic collaborative threat, and the method has wide adaptation capability and important industrial popularization value.

The invention discloses a safe penetration type management method and system for an engineering construction project, and relates to the technical field of constructional engineering, and the method comprises the steps: collecting engineering entity data in real time, carrying out the preprocessing, and generating an engineering state vector; based on the engineering state vector, constructing a digital twinborn model, calling multi-physics field coupling simulation to simulate the whole construction process, and generating a risk early warning report; uploading the risk early warning report and historical construction data to a federated platform, and constructing a dynamic security knowledge graph; performing hierarchical feature learning on nodes in the dynamic security knowledge graph, simulating decision behaviors of a manager, and generating an optimal management and control rule; based on the optimal management and control rule, driving a construction site management mechanism to operate, and forming a closed loop report; by using the digital twin model and the multi-physics field simulation technology, the accurate prediction of potential safety hazards possibly occurring in the construction process is realized, and the accuracy and timeliness of risk early warning are greatly improved.

The invention discloses a construction method of a bridge member safety knowledge graph based on multi-category monitoring information and hidden danger information, and relates to the technical field of bridge structure safety monitoring, and the method comprises the steps: determining a structure reliability index as a representation index of bridge structure safety, building a two-dimensional collaborative analysis system based on monitoring items and hidden danger items, and obtaining a bridge structure safety knowledge graph; building a multi-source data fusion structure reliability analysis framework by taking a structure reliability index as a final analysis purpose; based on a structure reliability analysis framework, a four-layer ontology model comprising a structure physical layer, a damage monitoring layer, a reliability assessment layer and an auxiliary decision-making layer is designed through Protege software, a knowledge graph is formed, a knowledge representation path of bridge structure safety assessment decision is established, and timely dynamic update and reliable maintenance decision of a bridge structure safety state are realized. According to the method, the knowledge graph is constructed through the four-layer ontology model with the causal conduction mechanism, and a knowledge representation path capable of systematically analyzing the safety of the bridge structure is formed.

The invention relates to the technical field of large language models and network security, in particular to a security large model construction method and application for industrial internet security protection, and the method comprises the following steps: loading a base large model GLM-4, constructing a knowledge retrieval module, and accessing MITRE ATTamp; a CK knowledge base; the MITRE ATTamp; performing knowledge feature embedding vectorization on the safety knowledge in the CK knowledge base; establishing a vector database storage and retrieval module; a retrieval enhancement generation mechanism is started, and a test data set mitre-ttp-mapping is loaded; respectively constructing a local model and a comparison model, and carrying out a model comparison experiment; and evaluating the performance of the constructed security big model in a network security situation analysis task, evaluating the improvement effect of the model after applying a retrieval enhancement generation (RAG) mechanism, and outputting an RAG-based security big model scheme. The method and the device are suitable for security situation assessment in multiple scenes such as enterprises, industries and mobile scenes, and the accuracy and the interpretability of security content generation can be improved.

The invention discloses a gas safety intelligent inspection method and system, and belongs to the crossing field of artificial intelligence technology and safety production management. The method comprises the following steps: acquiring image data through a field data acquisition terminal; a preliminary hidden danger identification module in the cloud server innovatively adopts a scene perception target detection model and a scene reasoning multi-label model for collaborative analysis; and the comprehensive risk assessment module performs deep correlation analysis on the hidden dangers based on a preset gas safety knowledge graph, and determines a quantitative comprehensive risk value by calculating a basic risk accumulated value of each hidden danger and a correlation risk increment generated by a correlated hidden danger pair. According to the method, the defects that traditional inspection depends on subjective experience and composite risks are difficult to quantify are overcome, amplification risks caused by concurrence of multiple hidden dangers can be accurately identified and quantitatively evaluated, continuous self-improvement of system capability is realized through a closed-loop mechanism, and the intelligent level of gas safety management is remarkably improved.

The invention discloses a semantic routing query question and answer method, system and device and a medium, and the method comprises the steps: determining a person who may participate in project quality management, and obtaining a portrait of the person who may participate in project quality management; extracting a sub-knowledge base selected by semantic routing from a quality safety knowledge base in the engineering field according to the portraits of the personnel possibly participating in the engineering quality management; obtaining a to-be-queried statement, and according to the to-be-queried statement, screening out the most relevant K knowledge fragments from the sub-knowledge bases selected by the semantic routing; and inputting the most relevant K knowledge fragments into the large language model to obtain an answer of the to-be-queried statement, the method, the system, the equipment and the medium can realize question and answer query, and meanwhile, the redundancy of feedback information and the leakage of sensitive information are not easily caused.

The invention relates to a power grid safety regulation question-answering system and method based on knowledge graph collaborative multi-agent, and belongs to the technical field of power grid safety regulation question-answering. The system comprises a power grid safety knowledge graph construction module and a multi-agent collaborative question and answer module. The power grid safety knowledge graph construction module is constructed according to an electric power safety working regulation in a mode of combining a large model and regularization, and professional knowledge support is provided for questions and answers. The multi-agent collaborative question and answer module comprises a key entity recognition agent group, an intention visual angle analysis agent group, a knowledge evidence retrieval agent group, an evidence feedback agent group and a professional answer generation agent group, all the agent groups cooperate in a labor division mode, and deep understanding and professional answering of electric power safety regulation problems are achieved through a knowledge graph. Power grid employees can be effectively assisted in understanding and applying safety regulations, and the power grid operation safety level is improved.

The invention discloses a heterogeneous AI engine interaction system and method based on a cognitive firewall, and relates to the technical field of artificial intelligence, and the system comprises a cognitive isolation channel which is used for building an isolation communication path between an RAG system and an Agent system, and generating standardized knowledge; the three-layer filtering architecture is used for performing grammar layer verification, semantic layer understanding and pragmatic layer evaluation on the standardized knowledge in sequence and outputting safety knowledge passing verification; the bidirectional value alignment module is used for mapping the safety knowledge to a multi-dimensional value space through a forward value alignment mechanism to calculate value conformity, and generating value alignment knowledge according to the value conformity; and the knowledge-instruction conversion engine is used for converting the value alignment knowledge into a structured instruction which can be executed by the Agent system. The method can actively identify, intercept and avoid potential dangerous, misleading, prejudice or ethical inconformity knowledge applications, and greatly reduce negative effects caused by wrong use of knowledge.

The invention provides a large model self-reflection safety knowledge condensation method and system. The method comprises the steps that S1, initial output is generated; s2, carrying out self-reflection, judging whether the output has potential defects or security vulnerabilities or not, and if yes, carrying out iterative optimization; s3, in the iterative optimization process, firstly, based on defects or security vulnerabilities judged by self-reflection and additional security specifications, improving measures are put forward, and optimization and improvement are carried out; then performing self-reflection again, and repeating continuously until the safety requirement is met; and S4, inputting the final reply and the task process into a safety knowledge condensation mechanism, condensing the safety knowledge and the safety concept of the safety specification, and storing the safety knowledge and the safety concept in a self-generated safety knowledge base in a unified preset format. According to the method, the universality of safety knowledge congealing can be effectively improved, the thinking depth of large model generation can be improved, safety knowledge can be used for the generation process in an extensible mode, the safety requirement is met, and the method does not depend on an external knowledge base.

The invention relates to the technical field of intelligent coal mine safety production, and discloses an intelligent coal mine safety early warning method and system based on deep learning, and the method comprises the steps: constructing a difficulty evaluation function, and achieving the progressive learning from simple to complex; based on a difficulty assessment result, a model-independent meta-learning algorithm is realized, so that the model quickly adapts to new mining area characteristics; constructing a privacy protection federated learning framework by using the meta-learning model, and realizing multi-mining-area cooperative training; a continuous learning module is constructed, and original experience is reserved when new knowledge is learned; constructing a meta-knowledge evaluation module to realize cross-mining-area safety knowledge sharing; according to the invention, the security risk identification accuracy is improved; multi-mining-area cooperative training is realized on the premise of protecting data privacy; the method has continuous optimization capability and effectively solves the problem of model drift; and efficient sharing and migration of cross-mining-area safety knowledge are realized.

The invention discloses a building safety education training system based on interactive experience, relates to the technical field of construction site safety education, and aims to solve the problems that traditional building worker safety education lacks pertinence and is difficult to meet specific safety requirements of various types of work, and the teaching mode is relatively single. The system comprises a database, a personalized learning recommendation module, an interactive learning module and a learning progress and achievement tracking module. The database is used for pre-storing safety knowledge of various construction work types; the personalized learning recommendation module is used for screening and recommending learning content suitable for the worker from a pre-stored database covering safety knowledge of various construction work types according to the work type information and learning history of the construction worker, and the learning content comprises a document and a video course. The method has the advantages that precise education content conforming to the work type and the knowledge level of each worker is provided for the worker, and the safety awareness and the skill level of the building worker are improved.

The invention discloses a sensitive data identification method, system and device based on rule matching and LLM deep semantic analysis, a medium and a product, and relates to the field of artificial intelligence, the method comprises the following steps: preprocessing data in an information data set; the information data set comprises multi-industry corpora, personal information and safety knowledge; the multi-industry corpora cover structured data format features and unstructured text semantic scenes; according to the preprocessed data, a LoRA technology is adopted to carry out field adaptation fine tuning on the large language model; the large language model comprises a rule matching layer and an LLM depth recognition layer; the rule matching layer screens and identifies the structured data; the LLM depth recognition layer recognizes unstructured data and implicit sensitive data; performing semantic recognition on the to-be-tested data according to the fine-tuned large language model, and outputting sensitive data; the sensitive data comprises information such as an identity card number, a home address and a mobile phone number, and the sensitive data can be accurately recognized.

The invention discloses a personalized safety training content generation method, system and device and a medium. The personalized safety training content generation method comprises the steps that answer data, historical performance data and future operation tasks of operators in safety training are collected; safety knowledge weak points and learning behavior modes of the operating personnel are identified, and related risk association points are determined; based on the safety knowledge weak point, the learning behavior mode and the risk association point, constructing a structured user portrait, based on a deep neural network model fused with an attention mechanism, screening basic training content matched with the user portrait from a dynamic training material library, and adjusting the basic training content to obtain a basic training result; according to the method, the personalized target safety training content is generated, and the safety training is performed on the operator according to the target safety training content, so that the generation efficiency of the personalized safety training content can be improved.

The invention provides a plug-and-play security enhancement method and system based on a large model self-reflection mechanism, and the method comprises the steps: S1, receiving a user input demand, generating a preliminary code, and extracting a potential risk; s2, starting a security detection module to perform reflection verification, identifying potential security issues, and marking the security issues through a self-generated security knowledge base; s3, calling a correction module to perform code optimization, dynamically retrieving a security knowledge base to perform security problem matching as reference content, performing automatic correction and code optimization, and returning to extract potential risks and perform reflection verification; and S4, outputting a final code, generating a safety analysis report, summarizing the accumulated safety knowledge, and updating and expanding a safety knowledge base. According to the method, automatic correction, code optimization and reflection verification can be performed through a self-reflection mechanism in each stage of the code generation process, and it is ensured that each output result meets the safety requirement so as to meet the requirement for universality between different models.

The invention discloses an electric power safety knowledge testing method based on a large language model and enhanced retrieval generation. The method mainly comprises the steps of constructing a vector knowledge base, constructing a dynamic interaction generation workflow framework driven by a multi-role large language model, performing safety knowledge testing and quantifying the electric power operation safety awareness of a user. According to the invention, the problem with high scene adaptation degree can be dynamically generated in combination with the scene of the operation work order and the user interaction result, so that the test problem accuracy is improved; the quality of test content is improved through cooperative work of a multi-role large language model and in combination with an enhanced retrieval generation module; a dynamic adjustment strategy is implemented according to a user feedback mechanism, so that knowledge blind spots of the user can be effectively identified; the safety awareness of the user is quantified, targeted consolidation is carried out, and the electric power safety knowledge level of the user is improved.

The invention discloses an interactive biological virtual experiment teaching system based on deep learning, and the system comprises a dynamic scene intelligent construction module, a multi-modal operation perception module, a real-time feedback guidance module, a comprehensive report generation module, and a self-adaptive learning optimization module. Component interaction, state simulation and parameter adaptive adjustment are supported, learning progress and difficulty data are received to realize linkage, a knowledge graph contains principle, specification, equipment characteristics and safety knowledge, staged loading, dangerous operation early warning and real-time knowledge node pushing are supported, and the knowledge graph is used for learning. The multi-mode operation sensing module integrates computer vision and sensor technologies to collect action data, identifies an operation sequence and a pre-judgment intention based on a space-time sequence model, adopts an environment adaptability algorithm to adjust collected parameters, and achieves autonomous optimization of the parameters through historical data analysis.

The invention provides an engineering quality safety digital management method integrated with a large language model, and the method comprises the following steps: S1, extracting engineering feature data from a basic database, and building an engineering quality safety knowledge graph according to the engineering feature data, the engineering feature data including process feature data, material feature data and safety monitoring data; s2, acquiring engineering field data of a current engineering project; and S3, according to the established engineering quality safety knowledge graph, performing engineering quality safety analysis on the engineering field data based on the knowledge graph enhanced large language model, and generating an engineering quality safety evaluation result. According to the method, the pertinence and the application effect of the large language model on quality safety management and control of the engineering project can be improved, and the intelligent level of digital management of the engineering project is improved.

The invention provides a construction site safety management and control method and system based on enhanced retrieval generation, and belongs to the technical field of data processing. Comprising the following steps: constructing a construction safety knowledge base, and vectorizing text data in the knowledge base; field self-adaptive fine tuning is carried out on the visual language large model through a low-rank self-adaptive method, and perception, cognition and decision-making processes of construction site safety management and control are executed: in a perception stage, construction safety hidden dangers are dynamically identified and positioned, and violation descriptions containing hidden danger types are generated; in the cognition stage, an enhanced retrieval generation process is started, and construction specification information associated with hidden dangers is obtained through multi-level semantic matching and retrieval; in a decision-making stage, based on violation description and construction specification information, a visual language large model is driven to automatically generate a structured security log through a preset structured cue word template. According to the invention, unsafe behaviors of the construction site can be timely and accurately warned, and effective data support is provided for the safety of the construction site.

The application provides a full-chain meat safety knowledge graph construction method and retrieval device, which has the following characteristics: steps S1-S2, entity and relationship extraction is performed on all meat safety standard files; step S3, meat product nodes and corresponding subordinate nodes are constructed and relationships are set; steps S4-S6, corresponding multistage nodes are set for each subordinate node; step S7, the extracted entities and relationships are assigned to the corresponding nodes; step S8, CCP selection nodes including specific hazards and corresponding control measures are set according to the HACCP principle; steps S9-S10, non-directly connected nodes are directly connected as needed through artificial relationships. In summary, the method can construct a more comprehensive meat safety knowledge graph, and the retrieval device can more quickly, conveniently and accurately retrieve and display the data of the meat safety knowledge graph.

The invention discloses a method for improving an industrial safety education training effect based on an AI large model. The method comprises the following steps: analyzing, vectorizing and storing latest industrial safety related documents to obtain a safety knowledge base; the related documents comprise industrial standard specifications, laws and regulations and enterprise specifications related to industrial safety; the knowledge base comprises a plurality of sub knowledge bases with different themes and different types; matching an associated target sub-knowledge base from the safety knowledge base based on the training plan, so as to generate an employee training task based on the target sub-knowledge base; based on the training task, utilizing an AI large model to generate a training problem in the training process, and using the training problem for employee training to obtain a training result of the employee; and based on the training result, using an AI large model to generate test questions corresponding to different employees, and examining the employees based on the test questions to obtain an examination result. The training effect of employee safety education can be improved, and potential safety hazards are reduced.

This invention discloses a big data-based safety design management method for chemical projects, relating to the field of big data technology in chemical safety. The method includes: collecting multi-source heterogeneous data and preprocessing it to form a project baseline dataset; collecting design change data and performing differential comparison with a safety knowledge graph to identify differential objects; starting from the differential objects, performing dependency propagation analysis along the safety dependencies in the safety knowledge graph to output affected objects and risk propagation chains; determining the review order of affected objects based on the risk propagation chains, sequentially extracting the specifications to be reviewed that match the affected objects from the specification knowledge base, determining whether the affected objects meet the specifications to be reviewed, and outputting the specification review conclusion. This invention realizes dynamic and precise management and automated compliance review of chemical project safety design, shifting from experience-driven to big data-driven management.

The invention discloses an intelligent civil air defense space safety evaluation method and system based on environment detection, and relates to the technical field of data processing, and the method comprises the steps: constructing a disturbance event library, selecting a disturbance event to execute safety disturbance simulation, and guiding an intelligent civil air defense space to enter an emergency state; establishing a safety knowledge graph of the intelligent civil air defense space in a normal environment; configuring a stage life cycle of the intelligent civil air defense space, and executing node response data acquisition of the intelligent civil air defense space in the stage life cycle so as to respond to a data acquisition result and update a graph state of the security knowledge graph; performing multi-dimensional atlas security scoring on the security knowledge atlas subjected to time sequence updating, and establishing a multi-dimensional atlas security scoring matrix; and outputting a security level evaluation result by using the multi-dimensional atlas security score matrix. The technical problem that comprehensive safety assessment means are lacked in civil air defense space safety assessment in the prior art is solved, and the technical effect of assessing the safety state of the intelligent civil air defense space in real time is achieved.

A drowning safety teaching aid comprises a pool model defined by a ground plate, a first side panel, a second side panel, steps and a pool bottom plate, the pool model is provided with a first water depth area plate, a second water depth area plate and a third water depth area plate which represent different water depths, and the pool bottom plate, the first water depth area plate and the second water depth area plate are arranged on the pool model. A circuit control board is installed on the back face of each third water depth area board, each circuit control board is provided with a control circuit, the control circuit induces the position and the moving position of the simulation human model, a magnet is arranged at the bottom of the simulation human model, and an inductive switch in the control circuit is inducted through the magnet. According to the utility model, the pool model is provided with the first water depth area plate, the second water depth area plate and the third water depth area plate which represent different water depths and are matched with the position movement of the simulation human model to send voice information of different areas, so that field scene type drowning safety knowledge education is carried out.

This invention discloses a method and system for power operation safety monitoring and question answering based on a multimodal large model. The method includes the following steps: a data acquisition step, acquiring visual data and safety regulation text data from the power operation site; a multimodal semantic fusion step, generating a unified fused semantic vector through feature extraction and cross-modal alignment fusion technology; a knowledge reasoning step, matching the fused semantic vector with a pre-constructed power safety knowledge graph and performing compliance reasoning based on a graph neural network; and an intelligent question answering generation step, inputting the fused semantic vector and the reasoning results into a large language model to generate natural language question answering information. This invention, through the synergistic innovation of multimodal semantic fusion, knowledge graph reasoning, and a large language model, solves the technical problems of insufficient semantic understanding, disconnect between the question answering system and the field, and unstructured knowledge representation in existing technologies, achieving fully automated and interpretable intelligent safety supervision from perception to cognition.

The present invention discloses a coal mining AI safety personalized learning method and system combined with personnel data, which relates to the field of coal mining technology, including: determining at least one type of work; determining at least one risk operation corresponding to the risk of coal mining hazards; attaching an initial learning focus index to each risk operation; determining the mutual correlation relationship between multiple risk operations; based on the mutual correlation relationship between multiple risk operations and the initial learning focus index of each risk operation, through an AI iterative algorithm, determining the final learning focus index of each risk operation. The advantages of the present invention are: it realizes the personalized scheme design of coal mining safety learning, and the learning content focuses on multiple operations that may have hidden dangers, which facilitates practitioners to quickly master the safety knowledge related to their own work type and meets the comprehensive safety learning needs of multiple types of work in coal mines.

The application relates to the technical field of safety monitoring, in particular to a building construction safety monitoring method and system based on artificial intelligence, which comprises the following steps: acquiring multi-source heterogeneous data of a construction site, performing distributed feature extraction on the multi-source heterogeneous data by adopting a federal learning framework, and generating site state representation data associated with time and space; performing risk prediction on the site state representation data by using a preset dynamic risk prediction model, outputting a multi-level risk prediction result, and constructing the preset dynamic risk prediction model based on a construction safety knowledge graph and a space-time graph neural network; triggering an adaptive feedback mechanism according to a risk level corresponding to the prediction result, generating visual warning information and equipment control instructions, and linking the construction site control system to execute emergency response operations. The problems of traditional monitoring methods, such as complicated data processing, insufficient real-time performance, high cost and lack of prediction ability, are solved.