490 results about "Eigenvector computation" patented technology

The invention discloses an international propagation effect accurate evaluation method and system based on a large language model, and relates to the field of international propagation effect evaluation, and the method comprises the steps: obtaining a behavior log data set of a user, and dividing the user to a preset life cycle stage; extracting an interest label set of the user in a continuous time window, calculating a weight change rate of the same semantic keyword, and generating a user interest drift trend feature; extracting a propagation content feature vector of the to-be-evaluated propagation content, and calculating a basic matching degree with the interest label set; dynamically correcting the basic matching degree in combination with the life cycle stage and interest drift trend characteristics to obtain a final matching degree; extracting a path mode feature vector of the user, performing parameter matching with a propagation path mode library, and determining a propagation effect evaluation level; dividing the users into user groups according to the propagation effect evaluation levels, and implementing an intervention strategy on the user groups; according to the invention, refined grading evaluation of the propagation effect can be realized.

The invention relates to the technical field of isolator service life prediction, and discloses an isolator remaining service life prediction method based on deep learning. The method comprises the following steps: acquiring a vibration signal and a temperature signal when the isolator operates, and constructing a multi-dimensional sensor sequence; dividing a plurality of sub-sequence units containing a fixed time window; extracting time domain and frequency domain features of each sub-sequence unit, and generating a fusion feature vector; calculating statistical distribution characteristics and variation trend characteristics of key indexes in the vector, and outputting a health state index; through a bidirectional recurrent neural network model containing an attention mechanism, taking the health state index and the historical degradation data as input, processing a time sequence dependency relationship through multi-layer residual error connection, and generating a residual service life prediction value; and updating the multi-dimensional sensor sequence according to the real-time sensor signal, and dynamically correcting the predicted value. According to the method, multi-dimensional data are integrated, degradation characteristics are deeply mined, and the accuracy and adaptability of prediction of the remaining service life of the isolator can be improved.

The invention provides a cross-park enterprise data collaborative analysis method based on federated learning, and relates to the technical field of distributed machine learning and data security, and the method comprises the steps that a central server distributes an initial global model and configuration parameters to each park node; the nodes execute local data feature alignment to generate standardized feature vectors; calculating dynamic collaborative factors of local data and global distribution; adjusting a training strategy based on the collaborative factors and updating model parameters; collecting model updating through an encrypted channel, and screening effective updating by adopting a dynamic aggregation offset threshold value; performing weighted aggregation to generate a new global model; and terminating the process when the cross-park convergence condition is met or the maximum round is reached. According to the method, heterogeneous data differences are eliminated through a dynamic feature alignment mechanism, dual-channel collaborative evaluation and adaptive security protection are combined, multi-park collaborative modeling efficiency and robustness are remarkably improved on the premise of guaranteeing data sovereignty, and the problems of feature space splitting, weak attack protection and node contribution imbalance are solved.

The invention relates to an intelligent interview scoring system capable of explaining decisions based on a large language model, and the system comprises a multi-mode resume analysis and feature coding unit, a resume feature adaptive matching unit, an interactive scoring and knowledge enhancement unit, and an answer quality evaluation unit. Text, image and audio features are extracted through a cross-modal attention mechanism of a multi-modal large language model, resume features are encoded into dynamic word vectors, and entity-level feature vectors are extracted; the post description text is encoded into a demand feature vector by a resume feature adaptive matching unit; calculating semantic similarity between the resume entity feature vector and the demand feature vector; the interactive scoring and knowledge enhancement unit dynamically retrieves knowledge fragments to generate a preliminary evaluation report containing a scoring basis; and the answer quality evaluation unit fuses the information density, the fluency and the integrating degree to generate a final score. And the whole-process intelligence from demand analysis to final decision making is realized.

The invention relates to the technical field of lithium ore conveying, and discloses a lithium ore hopper energy-saving conveying system based on intelligent self-adaptive control. The system comprises a data acquisition module, a self-adaptive control module, an energy-saving optimization module and an execution adjustment module. The data acquisition module acquires multi-dimensional operation data of the lithium ore hopper through a distributed sensor network, and a hopper conveying state database is constructed after standardization processing; the adaptive control module performs dynamic feature extraction on the database, generates a real-time control parameter matrix, establishes an association rule graph of each parameter, and constructs an intelligent adjustment decision model based on the association rule graph; an energy-saving optimization module extracts a key energy consumption feature vector from the real-time control parameter matrix, calculates an energy consumption influence coefficient of each operation parameter, and screens out an optimal energy-saving control sequence in combination with an intelligent adjustment decision model; and the execution adjustment module drives an execution mechanism according to the optimal energy-saving control sequence, and self-adaptive adjustment of hopper conveying parameters is completed.

An assessment apparatus and method for objective pain assessment are provided, wherein the apparatus includes a processor comprising a frequency-domain transformation module, a frequency-band segmentation module, a first assessment submodule, and a second assessment submodule. The frequency-domain transformation module generates a global time-frequency feature matrix, which is segmented by the frequency-band segmentation module in a frequency domain into five frequency bands associated with pain perception. The first assessment submodule extracts last time step features and an adjacency matrix from the time-frequency feature matrix and generates a first feature vector representing global association patterns among electrodes used for acquiring EEG signals. The second assessment submodule generates a second feature vector with local spatiotemporal dynamic features of EEG signals, concatenates it with the first feature vector to form a fused feature vector, computes its class probability distribution, normalizes it, and generates an objective pain quantification indicator corresponding to the EEG signals.

The invention relates to the technical field of power system fault diagnosis, and discloses a distribution network line fault detection data processing method, system and device and a medium, and the method comprises the steps: obtaining load data of a target distribution line detection point, and carrying out the first preprocessing of the load data, and obtaining a fusion feature vector; performing second optimization operation on the fusion feature vector to obtain an optimized fusion feature vector; calculating a potential feature matrix according to the optimized fusion feature vector, and mapping the potential feature matrix to a low-dimensional space to obtain a low-dimensional sample set; presetting an adaptive label propagation algorithm, and performing fault category judgment on the low-dimensional sample set based on the adaptive label propagation algorithm; and storing a judgment result in a relational database. The problems that feature extraction is not accurate in a high-noise environment, and a classification model is insufficient in new fault expansion capacity are effectively solved, and fault signal processing robustness is improved.

The invention belongs to the technical field of production monitoring systems, and discloses a numerical control machine tool dynamic fault diagnosis method and system. The method comprises the following steps: generating a global time reference signal through a main shaft encoder and a clock synchronization protocol; the method comprises the following steps: collecting vibration data of a main shaft bearing in each unit time, current data of an electric cabinet and process parameters, and generating a preprocessed data sequence through transmission delay compensation and multi-rate frequency raising processing; inputting the vibration data and the current data into a preset mechanical-electrical transfer function model, and calculating a time delay parameter; performing phase alignment on the preprocessed data sequence based on the time delay parameter to generate an aligned data sequence; inputting the aligned data sequence into a time sequence neural network, and outputting a fusion feature vector; calculating a cross correlation coefficient of the fusion feature vector, and generating a fault diagnosis result based on a preset cross correlation threshold value; the problem of failure of fault feature extraction caused by data asynchronization in the prior art is solved.

The invention discloses a feed online production intelligent monitoring method and system based on data analysis, and relates to the technical field of intelligent monitoring, original data RAW is collected and preprocessed to obtain an operation feature vector VPS, and a data foundation is laid for accurate analysis. Based on the operation feature vector VPS and a historical database HIS, a predicted quality feature vector VPQ containing specific indexes such as starch gelatinization degree Ysg is generated in real time, a comprehensive feed quality index SIFQ is calculated, a decision signal Sig is generated, multi-dimensional overall evaluation of product quality is achieved, and a clear basis is provided for regulation and control. And when the decision signal Sig indicates that the quality does not reach the standard, an adjustment instruction AIR is generated, and scientific and efficient process adjustment is ensured. And adjusting equipment according to an adjustment instruction AIR, continuously monitoring and updating a historical database HIS, and based on this, carrying out iterative optimization on an inherent coefficient set SCA, endowing the system with self-learning and continuous improvement capabilities, and ensuring long-term adaptability of the model and stable production optimization.

The invention provides a medicine raw material label consistency comparison method, system and device and a medium, and belongs to the technical field of medicine raw material label identification. The edge server searches a local template library according to the template index based on the comparison picture, and obtains a template tag picture and a feature vector file; extracting a feature vector of a comparison label picture by using a reconstructed Resnet18 network, calculating the similarity between the feature vector of the template label picture and the feature vector of the comparison label picture, and obtaining a label consistency result of the template picture and the comparison picture; and carrying out result visualization display on the label consistency result. Through a traditional image processing algorithm and a deep learning network feature extraction technology, the verification workload is reduced, and the verification efficiency is improved. The feature vectors are extracted by using the reconstructed Resnet18 network, and the consistency of the tag styles can be accurately judged in combination with an SIFT key point matching algorithm.

The invention discloses a multi-modal data fusion financial service information processing method and system, and the method comprises the steps: S1, collecting enterprise text data and enterprise table data, and carrying out the preprocessing, and obtaining cleaned text data and cleaned table data; s2, calculating an enhanced text embedding vector, extracting a semantic representation feature vector, decoding a text triple set, and generating a text semantic vector; s3, calculating a standardized field set and a row-level entity primary key, outputting an exception risk vector, and then calculating a table exception mark and a table semantic vector; s4, calculating an entity alignment gate, and calculating an entity alignment feature vector; calculating an entity matching degree score, and finally calculating a cross-modal conflict mark; and S5, calculating a cross-modal fusion vector through the multi-layer perceptron, and then calculating a knowledge representation vector. According to the method, the problem of low entity alignment precision caused by data structure difference, field semantic conflict and insufficient entity recognition precision of a traditional method can be solved.

The invention discloses an intelligent stereoscopic warehouse goods allocation control method and device and a computer program product, and the method comprises the steps: collecting the multi-source data of goods and goods allocation, and extracting the feature vectors of the goods and goods allocation; the adaptation degree of the goods and the goods allocation is calculated, and the dispatching priority is determined through a preset model in combination with goods characteristics; on the basis of the priority and the adaptation degree, combining the dynamic volume demand of the goods, the carrying path parameters and the goods aggregation degree, performing global optimization by utilizing a preset space group effect function, and determining the optimal target goods allocation of each goods; and calculating the spatial deviation degree between the current position of the goods and the optimal target goods allocation, judging and adjusting urgency in combination with timeliness, and dynamically planning a path to realize self-adaptive allocation of the goods allocation. According to the invention, accurate adaptation of the goods and the goods locations is realized, the warehouse resource utilization efficiency and scheduling rationality are improved, the robustness of the system in a complex scene is enhanced, and the method is suitable for efficient operation of a high-density and automatic stereoscopic warehouse.

The invention discloses a task processing method and device based on a dynamic LoRA network, computer equipment and a storage medium, and the method comprises the steps: receiving a task processing text, recognizing a feature vector of the task processing text, and enabling the feature vector to at least indicate the semantic and context features of the task processing text; calculating correlation with a plurality of to-be-selected LoRA networks according to the feature vector of the task processing text; determining an activation probability of each to-be-selected LoRA network according to the correlation, and determining a to-be-activated target LoRA network according to the activation probability based on a pre-configured gating network; fusing the target LoRA network into a basic model to obtain a fusion model; and performing task processing based on the semantic and context features of the task processing text by using a fusion model so as to load the target LoRA network and then output a processing result of the task processing text. By dynamically accessing the LoRA network, the accuracy and efficiency of task processing are improved.

The invention discloses an intelligent retrieval enhanced text creation method and device and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: constructing a multi-dimensional feature knowledge base, and setting configuration information; receiving a query condition, and determining an input text according to the query condition; performing feature vectorization on the input text based on the multi-dimensional feature knowledge base to obtain a feature vector; calculating a target similarity between the feature vectors; dynamically adjusting the weight of the input text based on the configuration information to obtain an adjusted weight, and fusing and calculating a target similarity score based on the adjusted weight and the target similarity; screening a text fragment higher than a matching threshold in the configuration information through the target similarity score as a creation reference; the preset cue word template and the creation reference are input into the large language model, text creation is performed through the large language model, a dynamic weight adjustment mechanism is designed, intelligent similarity calculation is realized, and the quality and availability of text creation content are improved.

The invention provides a weak supervision video anomaly detection method and system based on potential energy field damping dynamics. The method comprises the following steps: inputting a video into an anomaly detection model to obtain an original video feature sequence; calculating fluctuation potential energy by using the original video feature sequence and further obtaining a global inertia proxy vector; calculating interaction potential energy through the global inertia proxy vector and the original video feature vector; nonlinear self-adaptive damping force is generated through interaction potential energy; applying a nonlinear adaptive damping force to the original video feature vector to obtain a purified dynamic feature vector; constructing a loss function by using the purified dynamic feature vector, and training the model to obtain an optimized model; and inputting the video into the optimized model to obtain a final frame-level anomaly detection result. According to the method, anomaly detection is reconstructed from a classification problem to a signal decoupling and energy dissipation problem in a physical system, and the physical nature of a depolarization mechanism is explained from the theoretical level.

The invention discloses an adaptive evaluation method for the health degree of an electrolytic cell, and the method comprises the following steps: collecting the multi-dimensional operation parameters of the electrolytic cell in real time, and carrying out the preprocessing of the collected time series data, so as to construct a training sample with a time window; extracting a multi-scale time sequence feature from the training sample to form a feature vector; inputting the feature vector into a weight adjustment network, and outputting a dynamic weight vector; weighting the feature vector by using the dynamic weight vector to generate a weighted feature vector; inputting the weighted feature vector into a performance prediction model, and outputting a short-term performance prediction value of the electrolytic cell at a future moment; after the corresponding real performance value is obtained, calculating a prediction error of the short-term performance prediction value, and constructing a reinforcement learning reward signal based on the prediction error; updating a strategy of the weight adjustment network through a reinforcement learning algorithm by utilizing a reward signal, thereby optimizing dynamic weight vector generation at a subsequent moment; based on the dynamic weight vector and the feature vector at the current moment, a comprehensive health degree index of the electrolytic bath is obtained through calculation; according to the method, main factors influencing the equipment health degree in different stages are intuitively revealed, and a basis is provided for operation and maintenance decision making.

The invention relates to the technical field of aging detection, and discloses an inverter aging detection method and device based on multi-source data analysis, and the method comprises the steps: carrying out the multi-dimensional data set and synchronizing a timestamp, and obtaining a fusion data set; segmenting the fusion data set to calculate fluctuation amplitude, and when the fluctuation amplitude exceeds a threshold value, marking as an abnormal time period to generate a multi-dimensional feature vector; calculating a feature slope distribution weight, obtaining a weighted feature vector, calculating the similarity between the weighted feature vector and the feature pattern library, matching patterns of which the similarity is greater than a preset threshold value, extracting historical multi-dimensional feature vectors, and calculating parameters to obtain a mathematical description result; parameters in the mathematical description result are updated according to the feature vectors, and an early warning threshold value and a fault threshold value are calculated; when the feature slope in the weighted feature vector is greater than an early warning threshold but less than a fault threshold, generating an early warning signal; calculating a comprehensive health degree score distinguishing grade; and generating maintenance guidance information according to the health state level, and completing inverter detection. The method can solve the problem of resource waste.

The invention discloses a multi-dimensional training method and device for a support vector machine, electronic equipment and a computer readable storage medium, and the method comprises the steps: carrying out the discretization of a training sample data set, and obtaining a discretized data set, the discretized data set comprises a plurality of different attributes, and each attribute corresponds to a plurality of feature vectors; calculating a classification contribution parameter of each attribute feature vector to obtain a plurality of classification contribution parameters; performing data mapping on the plurality of classification contribution degrees by using a kernel function to obtain a target function; and optimizing and training the objective function by using a gradient descent algorithm to obtain a support vector machine model. According to the method, different dimension data are mapped through the kernel function, the data gain weight can be determined, the linear separable effect of the mapped dimension data can be improved, and then the classification and analysis capability of the SVM can be improved.

The invention discloses a multilingual work order processing method and device based on a dynamic LoRA network, computer equipment and a storage medium, and the method comprises the steps: receiving multilingual voice input, and converting the voice input into a source language text in real time; identifying a feature vector of the source language text; calculating the correlation with a plurality of LoRA networks to be selected according to the feature vectors; determining an activation probability of each to-be-selected LoRA network based on the correlation, and dynamically activating a target LoRA network through a pre-configured gating network according to the activation probability; fusing the target LoRA network into a basic large language model to generate a fusion model; and performing cross-language translation and work order content generation on the source language text by using the fusion model, and outputting a standard work order of a target language so as to distribute the work order to a corresponding processing module according to the work order content. By dynamically activating the proper LoRA network, the efficiency and accuracy of multilingual work order processing are improved.

The invention provides a multi-modal feature vector fused vehicle cross-lens ReID matching method and system, and relates to the technical field of vehicle identification, and the method comprises the steps: collecting a vehicle image through a camera, and extracting triple features, including a bottom-layer visual feature, a middle-layer semantic feature and a high-layer character feature; in combination with vehicle space-time metadata at adjacent acquisition cameras, generating space-time trajectory feature vectors, and capturing a time sequence rule of a vehicle driving path; the missing features are complemented by adopting an AI generation technology, and the complementation precision is optimized through adaptive learning; inputting the triple feature, the time sequence rule and the complementation feature into a Transform fusion network to generate a fusion feature vector; calculating the cosine similarity of the to-be-matched vehicle according to the fusion feature vector, and carrying out cross-border head matching; according to the method, the problem of insufficient distinction degree of single-modal features is solved, the track feature vector is generated by combining the space-time metadata of the camera, the driving time sequence rule of the vehicle between different lenses is captured, and the space-time constraint of cross-scene matching is enhanced.

The invention relates to the technical field of new energy power system instability risk assessment, in particular to a new energy power system frequency instability risk assessment method based on a heterogeneous graph attention network. The method comprises the following steps: constructing a wind power-photovoltaic heterogeneous graph model according to a power grid topology; performing combined sampling on different operation modes and anticipated disturbances, and determining corresponding input feature vectors; calculating a frequency stability index value label of the sample set; expanding the training set through an active learning iteration process, and carrying out model training; and inputting the collected operation data into the trained heterogeneous graph attention model, outputting a frequency stability index value, and evaluating the system frequency instability risk in combination with the risk matrix. By adopting the frequency instability risk assessment method for the new energy power system based on the heterogeneous graph attention network, the problem of low efficiency of risk assessment in a high-dimensional uncertain scene is solved, and the heterogeneous graph attention network can reflect the influence of different types of devices at different positions and disturbance types on the dynamic frequency of the system; and the accuracy of frequency instability risk assessment is improved.

The invention provides a network security malicious code binary search method and system, and relates to the technical field of data processing, and the method comprises the steps: calculating the multi-dimensional structural similarity between a to-be-detected binary file and each standard binary reference file based on a function level control flow semantic feature vector; determining a finally matched standard binary reference file according to the multi-dimensional structural similarity; performing fine-grained difference analysis on the binary file to be detected and the finally matched standard binary reference file to obtain a fine-grained difference analysis result; and on the basis of a fine-grained difference analysis result, in combination with sensitive data operation behavior feature detection, judging whether the to-be-detected binary file is a maliciously tampered version, and positioning a malicious code injection point. According to the method, the defects that in the prior art, dependence on fixed features is too high, and compilation optimization is sensitive are overcome.

The invention relates to the technical field of artificial intelligence, can be applied to business system platforms of medical health, financial science and technology and the like, and discloses a multi-agent cooperation method based on meta reinforcement learning, which comprises the following steps: constructing a task feature vector according to acquired multi-source information data; calculating a task difference degree between the new task and the training task according to the task feature vector; constructing a meta-training model through the task difference degree; performing double-loop training on the meta-training model according to the sampling task to obtain an optimal meta-parameter; taking the optimal meta-parameter as an initial parameter of a new task, updating a task difference degree between the new task and the training task according to the initial parameter, determining a fine tuning learning rate according to the updated task difference degree, and performing fine tuning processing on the meta-training model by using the fine tuning learning rate; environment data of preset time are obtained, the environment data are input into the meta-training model after fine tuning processing, the action distribution probability is obtained, specific actions are determined according to the action distribution probability, and the multiple agents are made to execute the specific actions.

The invention discloses an intelligent coordination method and system for personalized driving behavior habits, and relates to the technical field of intelligent traffic, and the method comprises the steps: collecting multi-modal driving data, carrying out the preprocessing, generating a structured multi-modal data set, the multi-modal driving data comprises vehicle operation data, environment perception data, driver biological characteristics and historical driving behavior logs; constructing a hierarchical feature extraction network based on the structured multi-modal data set, and performing feature interaction in combination with a space-time separated dual-channel structure gating mechanism to generate a dynamic driving feature vector; and based on the dynamic driving feature vector, calculating a safety index, a compliance index and a stability index, dynamically adjusting and generating a credibility score through reinforcement learning, and constructing a three-level evaluation mechanism to judge a credibility level. According to the method, the capabilities of multi-modal data fusion and dynamic response are improved, and the personalized level and the real-time adaptive capability of driving evaluation are enhanced.

The invention discloses a method and a system for asynchronous execution of JavaScript at a server side, and relates to the technical field of computer software, the method comprises the following steps: constructing a multi-language runtime context pool on the server side based on GraalVM, and pre-compiling a script and a core class; when the script is loaded, asynchronous execution strategy parameters are injected into the corresponding isolation context; calculating the fragmentation number of the overall task submitted by the script, and carrying out overall task fragmentation; mapping the fragments to the corresponding isolation assembly lines according to the fragment execution categories, constructing feature vectors according to the fragments in the isolation assembly lines, calculating fragment priorities, and executing in sequence; after fragment execution is completed, execution time delay is collected, historical time delay prediction is updated, and when conditions are met, isolation retry is carried out, and compensation fragments are generated. Through pre-compilation, asynchronous execution strategy, adaptive fragmentation and priority scheduling, and compensation fragmentation generation, fault self-recovery and service continuity guarantee with low time delay response, high scheduling flexibility and controllability and automation are realized.

The present invention relates to the field of data processing, and more specifically, to a text knowledge base classification management method based on a large language model. The method comprises: obtaining a text dataset containing a plurality of text samples; obtaining a pre-acquired large language model, inputting the text samples in the text dataset into the large language model in batches, iteratively updating the network parameters of the large language model to complete classification training of the large language model, thereby implementing text knowledge base classification processing; after any batch of text samples are input, calculating the interference level, obtaining a difference feature vector, calculating the information distinguishing attention credibility based on the difference feature vector, calculating the learning rate based on the interference level and the information distinguishing attention credibility; and updating the network parameters based on the learning rate. This improves the text classification accuracy of the large language model.

The invention discloses an image training data optimization method and system based on dynamic distillation, and belongs to the technical field of image processing, and the method specifically comprises the steps: dynamically dividing an input image into non-uniform grids according to an image region feature entropy value; constructing a teacher model and a student model, inputting a non-uniform grid image, extracting a feature vector of each grid node, and calculating a feature difference degree; dynamically generating a distillation temperature coefficient based on the characteristic difference degree, and reconstructing a distillation loss function to obtain an optimized loss value; calculating a loss curvature by using the loss value, screening difficult samples and easy samples, and respectively implementing dual-stage enhancement and feature disturbance enhancement; the feature migration rate is calculated based on the enhanced sample set and the feature vector, the teacher model intermediate layer feature weight is dynamically adjusted and fed back to the model training link, and the knowledge distillation effect is improved.

The invention provides a value-oriented content analysis and intervention method in ideological and political education, and belongs to the technical field of education and teaching. A pre-trained multi-modal value understanding model is combined with a recurrent neural network to extract dominant value features and capture context dependence, implicit value expressions are recognized through an attention mechanism and comparative learning, and a tendency index is generated based on the similarity between feature vector calculation and core value. A reinforcement learning training content intervention agent is utilized to generate an education intervention strategy, and finally anti-fact reasoning is adopted to evaluate different intervention strategy effects and optimize an intervention scheme, so that a complete technical closed loop from content analysis to intervention implementation to effect evaluation is formed. The technical problem that the implicit value in the ideological and political education content is difficult to quantify to accurately identify and implement effective intervention is solved.

The invention discloses a chromatographic data optimization processing method for a liquid chromatograph, and relates to the technical field, and the method comprises the following steps: collecting an original signal flow, carrying out preliminary peak detection, and generating an original peak list; extracting modal exclusive characteristics of each chromatographic peak; converting the modal exclusive features into a unified multi-dimensional semantic feature vector; calculating a time interval weight, and calculating a semantic relevancy weight based on the multi-dimensional semantic feature vector; correcting the time interval weight, generating a network edge weight, and constructing a peak correlation topology network by taking the multi-dimensional semantic feature vector as a node; identifying node clusters connected with high edge weights, and aggregating the node clusters into candidate compound entities; tracking a node signal intensity change track, and adding a conflict mark; conflict resolution arbitration is carried out on the candidate compound entities with the added conflict marks, dominant detector evidence is output, and an analysis report is generated. According to the method, the problems of poor data collaboration of multiple detectors, inaccurate peak identification and association and isolated data processing flow are effectively solved.

The invention provides an artificial intelligence-based engineering safety assessment method and system, and belongs to the technical field of engineering structure health monitoring. The method comprises the following steps: acquiring physical parameter time sequence data of an engineering structure through a distributed sensor network, synchronously acquiring surface visual data, and processing the data; inputting the processed data into a multi-modal artificial intelligence analysis model; processing time sequence data by an improved Mogrimer LSTM network through four-round iterative optimization and a sensor health sensing mechanism, and realizing damage positioning, classification and crack width quantification by an improved YOLOv8 network through a coordinate attention module and a decoupling detection head; fusing the time sequence and the visual features through a cross-modal attention mechanism, and generating a risk part feature vector; and calculating a safety risk index based on the risk part feature vector, and outputting a three-level risk level and a structured report. According to the method, multi-source data are fused, and the precision and real-time performance of engineering safety assessment are remarkably improved.