1435 results about "Technical support" patented technology

The invention relates to an engineering document index consistency proofreading method and system based on a multi-modal large model, and the method comprises the steps: Q1. OCR detection and recognition: carrying out the optical character recognition and format analysis of a source document, converting an uploaded PDF document into a processable text message in a Markdown format, and carrying out the format discrimination of a table, a formula and a plain text; and Q2, table and formula processing: adopting a hierarchical processing strategy, intelligently selecting an optimal processing mode according to the complexity of the table, and converting table information into a descriptive long text through a language large model and cue words. According to the method, accurate, reliable and efficient document index checking service can be provided for a user, the quality and efficiency of professional document processing are remarkably improved, the efficiency and quality of knowledge graph construction are remarkably improved, a knowledge verification system capable of being evolved continuously is established, and the method is suitable for popularization and application. And a reliable technical support is provided for knowledge management and professional decision-making in a complex field.

The invention discloses an intelligent contract vulnerability detection and repair system based on a heterogeneous graph neural network, and belongs to the technical field of block chain security, and the system comprises a contract analysis module, a multilayer graph construction module, a heterogeneous graph neural network module, a vulnerability feature library, a vulnerability recognition engine, an automatic repair module and a visual interface. After the source code of the intelligent contract is input, code analysis and standardization are completed by a contract analysis module; the multi-layer graph construction module constructs a contract internal heterogeneous graph, an inter-contract interaction graph and an ecosystem relation graph based on a graph theory; the heterogeneous graph neural network module learns a vulnerability feature mode; the vulnerability recognition engine combines the vulnerability feature library to realize vulnerability classification and risk assessment; the automatic repairing module generates a repairing scheme; and the visual interface realizes detection progress monitoring, result display and encrypted report export. The intelligent contract vulnerability detection and restoration system based on the heterogeneous graph neural network provided by the invention provides technical support for block chain digital asset security and ecological stability.

The invention provides a tunnel fire behavior inversion method based on multi-modal fusion and physical constraint, and aims to solve the problem that the position and power of a fire source are difficult to invert accurately in real time in traditional fire behavior monitoring. According to the method, data, temperature distribution images and physical parameters of distributed temperature sensors in a tunnel are collected, and a spatial-temporal feature fusion network is constructed; designing an information leakage prevention training mechanism, and adopting a modal random discarding and sensor shielding technology to avoid overfitting of the model to a specific input mode; a physical constraint loss function is introduced, and the temperature gradient, the maximum temperature rise and the longitudinal attenuation law are combined to ensure the physical rationality of an inversion result; a coarse-fine two-stage position prediction framework is adopted, and meter-scale precision positioning of the position of a fire source is achieved. According to the invention, the power and position of the fire source can be inversed accurately in real time, and reliable technical support is provided for intelligent monitoring and emergency rescue of tunnel fire.

The embodiment of the invention provides an equipment fault prediction management method and device based on a large model, and the method and device achieve the accurate evaluation of a state through the innovative design of a multi-modal feature fusion model, data integration and feature learning. A fault diagnosis system is constructed, and a reliable root cause analysis mechanism is established in combination with semantic analysis and case retrieval. Maintenance guidance is introduced, and the feasibility of a maintenance scheme is ensured through experience precipitation and priority evaluation. According to the method, the defects of the traditional technology in the aspects of feature extraction, fault diagnosis, maintenance guidance and the like are effectively overcome, and technical guarantee is provided for equipment management.

The invention discloses a method based on a large language model and ATTamp; the invention discloses a CK framework penetration test automation method and device, and the method comprises the steps: firstly carrying out the structural analysis of multi-source input information and tool output, and guaranteeing that key fields are not discarded; then combining a retrieval enhancement generation technology and a network security knowledge base to provide domain knowledge support for the large language model, so as to generate a model with ATTamp; a penetration test task tree marked by CK tactics, technologies and sub-technologies; on the basis, an optimal tool is automatically selected through a tool resource library and a multi-dimensional screening mechanism, an execution instruction is generated, and finally an execution result is returned to the input analysis module to form a self-adaptive optimization test closed loop. According to the method, semantic fidelity compression and standardization processing of long information can be realized aiming at the problems of large output format difference, more information redundancy and the like of different penetration testing tools, and efficient, explainable and auditory technical support can be provided for automatic penetration testing in a complex network environment.

The embodiment of the invention provides an urban rail signal system fault diagnosis method based on a knowledge graph and a large model, and the method comprises the steps: collecting system operation logs, state parameters and fault information in real time, and carrying out the data preprocessing and standardization; based on historical fault data, a fault classification and prediction model is constructed through feature extraction and mode recognition, and automatic fault recognition and risk early warning are achieved; constructing a fault diagnosis knowledge graph, and establishing an association relationship among entities such as equipment, faults, reasons, maintenance schemes and the like; a pre-training large language model and a LoRA technology are adopted for efficient fine tuning, a fault diagnosis reasoning model is trained, and end-to-end generation from fault description to diagnosis and maintenance suggestions is achieved; the knowledge graph and large model output are fused, real-time and historical data are combined, multi-path fault analysis and comprehensive diagnosis are carried out, and a diagnosis report is generated and displayed. The intelligent level, accuracy and efficiency of fault diagnosis can be improved, and technical support is provided for intelligent operation and maintenance management.

The embodiment of the invention discloses a safety monitoring method and system for building construction, and the method comprises the steps: collecting the original video data of a construction site, carrying out the denoising, illumination correction and frame rate adjustment, and outputting a standardized video data stream; extracting attitude features of the constructors and representing the attitude features as a feature matrix to form an attitude feature matrix set containing spatio-temporal information; the sensitivity and correlation of the feature matrix are analyzed, calibration noise is added after dimension reduction, and feature data conforming to differential privacy are generated; and extracting data advanced representation by utilizing a pre-training model, and completing behavior classification, dangerous area judgment and safety violation detection. And the violation risk is evaluated in combination with the risk level of the construction area, graded early warning is generated, and meanwhile violation information is recorded to form a traceable management mechanism. According to the embodiment of the invention, accurate and efficient safety violation behavior detection is realized, and intelligent technical support is provided for safety management of building construction.

The invention discloses an intelligent medical record quality control method based on a rule and large language model hybrid engine, and relates to the technical field of natural languages, and the method comprises the steps: obtaining original electronic medical record data from a medical information system; performing post-structured processing on the original electronic medical record data, and converting an unstructured or semi-structured text in the original electronic medical record data into a unified structured data object readable by a machine; traversing a plurality of quality control points in a preset quality control rule base, and for each quality control point, adaptively selecting and executing a corresponding quality control path based on the converted structured data object; and based on the quality control results of all the quality control points, performing score calculation and generating a quality control report. According to the method, the automatic and deep quality control of the full-dose medical record can be realized, form inspection is covered, connotation logic analysis can be executed, the system is endowed with excellent flexibility and regional expansion capability, and reliable technical support is provided for improving the overall level of medical quality management.

The invention discloses a wind power plant cluster power prediction method. The method comprises the following steps: step 1, embedding priori knowledge into a learning module; step 2, constructing a memory enhanced adaptive graph structure; step 3, an endogenous feature learning module; step 4, an exogenous feature learning module; 5, performing memory enhancement gating fusion on the MAGF; and step 6, outputting and predicting. According to the method, special learning modules are respectively constructed by decoupling endogenous power signals and exogenous meteorological factors, and a dynamic graph structure adaptive to a sample is retrieved by utilizing a meta-memory library, so that context sensing modeling of a complex space-time dependency relationship is realized. Meanwhile, a memory enhanced gating fusion mechanism (MAGF) is introduced, adaptive semantic alignment and fusion of double-flow features are realized, the precision and robustness of the model in multiple prediction time domains are remarkably improved, and more reliable technical support is provided for power grid dispatching and wind field operation.

The invention discloses a power equipment identification and anomaly detection method and system based on cross-modal alignment and a storage medium, and relates to the technical field of power inspection, and the method comprises the steps: collecting historical power equipment inspection images, and constructing a historical power equipment inspection image data set; constructing a power equipment identification and anomaly detection model; training a power equipment identification and anomaly detection model by using the historical power equipment inspection image data set to obtain a trained power equipment identification and anomaly detection model; and inputting a to-be-detected power equipment inspection image into the trained power equipment identification and anomaly detection model to obtain a detection result. According to the invention, through the design of a two-stage contrast learning framework, the model realizes effective balance between global semantic understanding and local defect identification. Therefore, multi-level optimization from semantic understanding to abnormal positioning is realized, and powerful technical support can be provided for intelligent inspection and safe operation and maintenance of a power system.

The embodiment of the invention provides an AI large model training resource dynamic scheduling method and device based on a VGPU, and effective planning of resources is realized through innovatively designing a resource prediction system and through index analysis and demand prediction. A multi-target scheduling mechanism is constructed, and a reliable scheduling strategy is established in combination with competition analysis and scheme screening. Virtualized isolation is introduced, and the training stability is ensured through VGPU and resource control. According to the method, the defects of the traditional technology in the aspects of resource prediction, scheduling optimization, virtualization isolation and the like are effectively overcome, and technical support is provided for large model training.

The invention relates to a thermal simulation numerical simulation method of a multi-physics field architecture with CFD as a core, and belongs to the technical field of cross of computational fluid mechanics and heat transfer science. The method comprises the following steps: constructing a geometry and a conformal / non-conformal grid, presetting a model library, establishing association between a region and a physical field through physical group division, confirming a boundary and initial parameters, and screening a core simulation model; dividing an independent control volume based on a core numerical model, converting an area component and a volume component through integral operation, discretizing a boundary flux to construct a parameter matrix, then solving an equation set, and synchronously optimizing the grid quality; calculating a boundary flux and matching a discrete format, a turbulence model and a corresponding multi-physical field coupling model; original data are screened and processed, and cloud picture results such as temperature and flow field are generated through visualization. Accurate simulation of a multi-physics coupling scene is achieved, the precision and stability of thermal simulation under complex working conditions are improved, and efficient and reliable technical support is provided for engineering design optimization and performance evaluation.

The invention discloses an edge cloud collaborative industrial equipment health management and predictive maintenance method, and the method comprises the steps: forming a closed-loop system through four deep coupling steps: edge adaptive fusion perception, cloud knowledge enhancement reasoning, edge cloud collaborative self-evolution prediction, and risk-driven maintenance decision. The edge end dynamically adjusts a sensor acquisition and feature fusion strategy according to the equipment health state, the cloud end performs causal reasoning and situation evaluation by using a physical-data mixed knowledge graph, and the edge cloud collaboratively optimizes a prediction model through federal element learning and bidirectional knowledge distillation; maintenance decision is based on multi-objective optimization, the actual effect is fed back to the perception and prediction link, the method achieves accurate assessment of the equipment health state, early fault prediction and maintenance intelligent decision, the availability of the equipment is remarkably improved, the maintenance cost is reduced, and core technical support is provided for intelligent manufacturing.

The embodiment of the invention provides a heterogeneous unmanned cluster multi-mode multi-layer task modeling method and device, and the method and device achieve the effective expression of a system through the innovative design of a space-time hybrid network system and the state mapping and relation modeling. And a logic event mechanism is constructed, rule judgment and time sequence analysis are combined, and a reliable decision model is established. And capability classification is introduced, and distribution reasonability is ensured through strategy matching and task decomposition. According to the method, the defects in the aspects of state modeling, logic judgment, capability allocation and the like in the traditional technology are effectively overcome, and technical guarantee is provided for unmanned cluster collaboration.

The invention provides an aviation composite material hot-press forming workpiece loading method based on a hybrid optimization algorithm. The method comprises the steps that workpiece demand information and autoclave platform information in composite material hot-press forming manufacturing are obtained; minimizing the opening times of the autoclave as a target function; establishing a two-dimensional multi-layer platform hot press molding workpiece loading model, defining space constraints, distribution constraints, resource constraints and type constraints among workpieces, and incorporating the constraints into model constraint conditions; a GA-SP is adopted to optimize a workpiece loading sequence and a rotation state, an optimal layout is generated through chromosome coding, decoding, selection, intersection and mutation operations, a hybrid optimization algorithm is constructed in combination with a neighborhood search strategy, efficient arrangement of workpieces on different platforms is realized in combination with a simulated annealing criterion, and an optimized loading scheme is output. The production efficiency of the hot press molding procedure can be improved, the manufacturing cost is reduced, and efficient technical support is provided for intelligent manufacturing of aviation composite materials.

The invention relates to a public multi-mode cloud network resource software security enhancement method based on neural symbol fusion reasoning, which comprises the following steps: an intermediate representation generation stage: generating and optimizing an intermediate representation of a program through a fine-tuned large language model, and establishing semantic mapping from a source code to a structured logic representation; in the symbol language conversion stage, the intermediate representation generated by the large language model is converted into a domain-specific language fact set which can be recognized in the symbol logic reasoning stage, and formal and logic expression of program semantics is achieved; and a symbol logic reasoning stage: matching the fact set with the rule base through a symbol logic reasoning engine, performing detection and verification according to the safety rule, generating a structured report, and feeding back a result for optimization. The method is suitable for security enhancement of various core software systems in a public cloud network multi-modal network environment, high-precision security analysis is carried out on cross-modal and cross-subsystem fragmented codes in a compiling-free environment, and verifiable technical support is provided for public cloud network security control.

The invention provides an intelligent prediction model construction method based on multi-modal data fusion, and the method comprises the following steps: collecting multi-modal data in different electric power scenes, and carrying out the preprocessing of the multi-modal data, the electric power scenes including electric power inspection, electric power transaction and electric power equipment operation and maintenance; performing feature extraction, semantic association and space-time alignment on the preprocessed multi-modal data through a cross-modal attention mechanism and association analysis; constructing an intelligent prediction model, and performing knowledge injection on the intelligent prediction model through a retrieval enhancement generation technology and a lightweight adapter; a multi-task learning framework is introduced into the intelligent prediction model, exclusive output heads are set for different power scenes, and training is carried out through multi-modal data; after training is completed, lightweight compression is carried out on the intelligent prediction model through a knowledge distillation technology, a multi-modal data fusion technology system suitable for the power industry is formed, and key technology support is provided for deepening application of the intelligent prediction model of the power system.

The invention discloses a full-link quality tracing method driven by batch of a process card, relates to the technical field of intelligent manufacturing and quality tracing, and aims to automatically generate a dynamic process card batch number through PDA code scanning and work reporting and realize full-process seamless association and tracing from material picking, film spraying, bag making to inspection. According to the method, a defect propagation path prediction mechanism is innovatively introduced, all associated batches are automatically locked when a certain batch is detected to be bad based on the BOM topological relation, the traditional tracing time is compressed from the hour level to the second level, and the quality problem response speed and accuracy are greatly improved. Meanwhile, the system intelligently recommends the optimal reworking path in combination with historical reworking data, the reworking time can be reduced by about 40%, and the production efficiency and the resource utilization rate are remarkably improved. According to the technology, real-time acquisition, dynamic analysis and intelligent decision support of quality data are realized, and core technical support is provided for an enterprise to construct an efficient, transparent and traceable full-link quality management system.

The invention discloses a transformer substation scene three-dimensional semantic segmentation method fusing local geometry and global context, and the method comprises the steps: obtaining the three-dimensional point cloud data of a transformer substation scene, and constructing a semantic segmentation data set; a three-dimensional semantic segmentation model is constructed, and fusion features integrating local geometric information, global context information and neighborhood information are extracted through a down-sampling module, a position coding module, a local-global fusion module and a neighborhood propagation unit in sequence; integrating the multi-scale fusion features through an up-sampling propagation module, and outputting a semantic category prediction result by using a semantic segmentation head; designing a loss function, and training the model; and loading the trained three-dimensional semantic segmentation model to realize refined segmentation of the substation scene. According to the method, the understanding capability of the complex three-dimensional structure of the transformer substation is effectively enhanced, the segmentation precision of refined power equipment parts is remarkably improved, and reliable technical support is provided for intelligent operation and maintenance of the transformer substation.

The invention relates to the technical field of artificial intelligence, in particular to an intelligent pre-auditing system and method for public data resource registration elements with a large model, and the method comprises a management side rule base construction step and an operation side auditing step. The method has the beneficial effects that automatic extraction, structured conversion and compliance pre-auditing of registration elements are realized by applying a multi-modal data analysis engine and a large model technology, and manual intervention links are reduced by more than 40%. A multi-dimensional rule knowledge base containing national standards, industry specifications and local regulations is constructed, dynamic loading and self-adaptive updating of verification rules are supported, and the adaptability to different types of data resources is improved. And a pre-auditing device based on the micro-service architecture is designed, and technical support is provided for marketization configuration of data elements. Through pre-auditing quality problem big data of process precipitation, the standard conformity of a data production end is reversely optimized, and a'registration-feedback-improvement 'closed-loop treatment mechanism is formed.

The invention discloses a technology development analysis method and system based on a patent big language model, and relates to the field of big data analysis. The problems that an existing artificial intelligence patent analysis method is difficult to accurately analyze a technical structure in a patent text, cannot describe a technical hierarchical relationship, is difficult to eliminate technical semantic diversity, cannot systematically analyze a technical evolution process and the like are solved. And the network structure characteristics and the technology node importance are analyzed, and the evolution characteristics of the technology system in different stages, the key technology nodes and the change trend of the technology community structure can be identified, so that technical support is provided for artificial intelligence technology development situation research and judgment and technology layout decision. The method is suitable for a technical analysis scene of million-level patent data.

The invention discloses a data acquisition-based dynamic path planning method and system for an intelligent industrial robot with a body, and relates to the technical field of industrial robots. The method comprises the core steps of system calibration and parameter presetting before machining, multi-mode sensor dynamic acquisition, point cloud preprocessing, curvature sensing dynamic ICP registration, micro-inertia disturbance compensation, dynamic path planning, procedure adaptation adjustment, real-time feedback correction and the like. The point cloud quality is guaranteed through multi-sensor cooperation and dynamic switching, the registration effect is adjusted and optimized through curvature correlation parameters, dynamic compensation is achieved through a disturbance prediction model, the connection efficiency is improved through procedure parameter mapping, and accurate fitting of paths is guaranteed through graded feedback correction. The method is suitable for machining complex curved surfaces such as artificial joints, machining precision and stability can be remarkably improved, and the method has extremely high scene migration capacity, can provide reliable technical support for precision machining of similar complex curved surfaces and has remarkable popularization value.

The invention discloses a target-level three-dimensional point cloud cross-modal semantic retrieval method and device and electronic equipment. The target-level three-dimensional point cloud cross-modal semantic retrieval method comprises the steps that independent three-dimensional target point clouds are segmented from three-dimensional scene point clouds, and unique identifiers are given to the independent three-dimensional target point clouds; projecting each target point cloud to three orthogonal two-dimensional observation planes to generate a multi-view composite image; a pre-trained vision-language basic model is adopted to code and fuse the synthesized image, and a unified multi-modal feature vector is generated; a vector database in which the feature vectors are associated with their identifiers is constructed. And encoding a natural language query text into a text query vector by using the model, calculating the semantic similarity between the text query vector and the feature vector in the database, and positioning and returning the corresponding three-dimensional target point cloud. According to the method, accurate and efficient cross-modal retrieval from a natural language to a three-dimensional point cloud target is realized, the problem that a traditional method is difficult to support semantic fine-grained retrieval of the three-dimensional target point cloud is solved, and a key technical support is provided for training data management in the fields of intelligence and the like.

The invention provides a BIM (Building Information Modeling) full life cycle splitting and cross-model synchronization method and system. The method comprises the steps that BIM model components are coded based on a full life cycle coding rule, private attributes of all engineering stages and component codes of the engineering stages are bound and stored in component extension attributes, and a BIM master model containing multi-stage attribute information is generated; setting a BIM model splitting rule based on a rule engine; the code of each component in the BIM model is analyzed, the codes are compared with screening conditions in the splitting rules according to levels, and component data corresponding to the successfully matched codes are packaged and stored as sub-models; establishing association mapping between the models; and when the source model is modified, the synchronization engine executes synchronous updating of the target model according to the association mapping between the source model and the target model associated with the source model, so that the cross-stage multi-participant cooperation efficiency is improved, and a solid technical support is provided for digital transformation of the construction industry.

The invention discloses a laboratory sample detection management method, system, equipment and medium based on automatic scheduling, and belongs to the technical field of laboratory intelligent scheduling, and the method comprises the following steps: collecting task and equipment data in real time, binding and storing, and quantifying an initial priority by calculating task complexity; the priority is dynamically adjusted by combining the fault severity, queuing duration attenuation and environment temperature and humidity overrun correction, the completion time is predicted based on the historical efficiency of the equipment and the current load, the task is preferentially allocated to the automatic equipment for execution according to the corrected priority score, and the progress is updated in real time. The intelligent scheduling capability, the resource utilization efficiency and the operation stability of laboratory detection tasks are improved, and efficient and reliable technical support is provided for a complex and changeable experiment environment.

The invention relates to the technical field of engineering construction informatization and data security, and provides an engineering supervision transparency platform based on a block chain, the platform adopts a three-layer collaborative architecture of terminal acquisition, edge processing and on-chain consensus: field data and space-time and identity information are bound in a hardware security area through a special intelligent terminal; a local server is used for data buffering and distributed storage; the data fingerprints are stored without being tampered based on the alliance block chain network and the smart contract, and a multi-party verification process is automatically executed. According to the method, the whole process of supervision data from the source to the evidence storage is credible, the authenticity and integrity of the data are guaranteed, the collaboration efficiency is improved, offline synchronization and visual tracing are supported, and transparent and reliable technical support is provided for project quality management.

The invention belongs to the field of unmanned aerial vehicle (UAS) traffic management (UTM) and computer science, and particularly relates to a method and system for airspace modeling and path planning of a logistics unmanned aerial vehicle, and the method comprises the steps: S1, receiving multi-source data, and constructing a hierarchical mixed data model; s2, coding the control constraint data and the dynamic environment data into semantic attributes of nodes in a two-dimensional quadtree layer and / or voxels in a three-dimensional octree layer so as to generate a semantic airspace model containing computable rules; s3, based on the semantic airspace model, executing a hierarchical path planning algorithm to determine a flight path from the starting point to the ending point; and S4, combining the refined paths, and outputting a four-dimensional flight path containing a timestamp. The airspace rule is internalized into the model attribute, the real-time performance, safety and compliance of path planning are remarkably improved, the airspace resource utilization efficiency is improved, and key technical support is provided for large-scale urban unmanned aerial vehicle logistics operation.

The invention discloses a multi-machine system number-real consistency error collaborative prediction method and system based on multi-agent reinforcement learning, and belongs to the technical field of multi-robot systems and artificial intelligence. According to the method, each robot is modeled as an intelligent agent, a centralized training distributed execution framework is adopted, and collaborative prediction of errors is achieved. Each agent collects own, neighbor and environment state information in real time, multi-source information integration is carried out through feature embedding and gating fusion, the influence of different information sources on errors is dynamically evaluated by adopting a layered attention mechanism, and propagation and coupling rules of the errors in a cluster are effectively modeled. In the training stage, the centralized commentator network is utilized to evaluate the global prediction performance, the cooperative optimization of each executor network is guided, and the prediction precision is improved. According to the method, active and collaborative prediction of the multi-machine system number-real consistency error is realized, and a key technical support is provided for error feed-forward compensation and system reliability guarantee.

The invention relates to the technical field of engineering performance intelligent detection, in particular to a concrete main tower circumferential prestressed reinforcement anti-cracking prediction method based on machine learning, which is characterized in that fiber grating strain sensors are arranged on the sections of main tower circumferential prestressed reinforcements, and strain data and environmental parameters in tensioning and operation stages are acquired; marking a cracking state to construct a sample data set; carrying out adaptive segmentation and abnormal value elimination operation on the strain sequence to realize data cleaning; constructing a cracking probability prediction model to process the cleaned data to obtain a cracking prediction probability; and calculating the total loss of the model, training the model, inputting newly collected data into the trained model, outputting a cracking prediction probability, and judging whether to carry out early warning or not. According to the method, online, real-time, intelligent and accurate prediction of the cracking risk of the circumferential prestressed steel bars of the concrete main tower can be realized, the monitoring false alarm rate is effectively reduced, and reliable technical support is provided for bridge operation maintenance and safety management and control.