377 results about "Context modelling" patented technology

The invention discloses an intelligent programming auxiliary method and system based on a multi-modal AI language model, and belongs to the technical field of programming auxiliary tools. The method comprises the following steps: a multi-modal input processing stage; a dynamic context modeling stage; a hierarchical semantic analysis stage; in the code generation stage, codes are generated in two stages by adopting a Codex-Plus large model; the reinforcement learning driven code optimization stage is used for carrying out multi-objective optimization and reward function design on the codes generated in the code generation stage; a multi-dimensional feedback stage; an interaction and visualization stage; code semantic deep analysis, dynamic context sensing, multi-target optimization generation and real-time interactive feedback are realized by fusing code texts, natural language description, developer behavior data and a domain knowledge graph, and programming efficiency and code quality can be remarkably improved.

The invention relates to the technical field of intelligent retrieval and matching, in particular to a property intelligent retrieval and matching system based on a knowledge graph. The method comprises the following steps: a data acquisition and processing unit acquires property right data and preprocesses the property right data; the knowledge modeling and graph construction unit constructs the preprocessed property right data into a knowledge graph based on entity extraction, relation extraction and attribute labeling; the retrieval analysis and semantic understanding unit is used for receiving a retrieval request input by a user, converting the retrieval request into a structured retrieval statement matched with the knowledge graph based on a dynamic multi-hop reasoning intention path discovery scheme, and analyzing a retrieval intention of the retrieval request through a context modeling and semantic disambiguation method. According to the method, a semantic understanding mechanism combining a dynamic multi-hop reasoning intention path discovery scheme with context modeling and semantic disambiguation is introduced, so that a complex retrieval request input by a user in a natural language form can be accurately analyzed.

The invention discloses a multi-level feature fusion and time sequence modeling combined lithium battery life prediction method, and relates to the technical field of lithium ion battery health management and life prediction. The method comprises the steps of receiving time sequence observation data in a battery operation process, inputting the time sequence observation data into a pre-constructed local feature extraction model, and introducing a one-dimensional convolutional neural network into the local feature extraction model to perform feature extraction on the time sequence observation data to obtain local feature representation. According to the method, three structures of local feature extraction, global context modeling and bidirectional time sequence modeling are fused, and the battery degradation modeling capability and prediction precision are effectively improved. The TFN adopts an end-to-end architecture design, has good feature perception capability and time-dependent modeling capability, and can adapt to various degradation modes and complex time sequence environments. The method is suitable for life evaluation and health state monitoring in an intelligent battery management system, and has relatively high practical value and popularization prospect.

The invention relates to the technical field of project risk management, in particular to a project risk monitoring method and system based on a large language model, and aims to guide a language model to complete risk identification in a professional context by analyzing a natural language supervision request of a user, identifying a task field, matching a corresponding knowledge graph and a rule base, generating a reasoning configuration set and guiding the language model to complete risk identification in a professional context. Through a multi-modal fusion mechanism, unstructured data such as contract texts, drawing images and progress logs are coded in a unified mode, context modeling and rule reasoning of cross-modal information are achieved in combination with a large language model guided by a strategy, hidden risks needing image-text linkage judgment are effectively recognized, the analysis capacity for complex semantic association is improved, and the method is suitable for large-scale popularization and application. And furthermore, through a reinforcement learning mechanism, a supervision sample is constructed according to user feedback, a reward signal is generated, language model strategy parameters are optimized in real time, and continuous evolution and self-adaptive updating of a risk monitoring model are realized.

The invention discloses a low-code development automatic generation method based on a large language model, which comprises the following steps: collecting natural language description information input by a user, and preprocessing; inputting the standardized demand corpus set into a large language model, and executing semantic understanding and context modeling; matching the low-code component library based on the structured semantic representation to generate component assembly description information; generating and verifying an engineering skeleton according to the assembly description information, and outputting an executable low-code application initial version; running the executable low-code application initial version, and monitoring and analyzing execution difference to generate an increment adjustment instruction; and inputting the increment adjustment instruction into the large language model, performing reconstruction and adaptive optimization, and outputting an executable low-code application final version. According to the method, large language model semantic understanding and adaptive optimization technologies are fused, automatic generation and continuous optimization of low-code applications are realized, and the method has the advantages of intelligence, high precision and engineering reliability.

The invention discloses a multi-scale context enhancement small target detection method based on an improved RT-DETR (Reverse Transcription DET Rate). The method comprises the following steps: preprocessing unmanned aerial vehicle image data, and then constructing an improved RT-DETR model; the core is that a CSP-GFCG feature extraction module is used for modulating a feature map through frequency domain transform (DFT / IDFT) and a learnable global filter by using GFNet to realize global context modeling; and then the processed features are input into a ConvGLU module, and local features are enhanced in combination with depth separable convolution and a gating linear unit. GFNet and ConvGLU cooperate with each other, and challenge is effectively reserved for scale change and details in small target detection. The method aims at optimizing a feature extraction mechanism, reducing redundancy and improving the detection performance of a small target under a complex background. Meanwhile, the calculation efficiency is improved, the resource consumption is reduced, and the problem of missing detection of small targets is effectively solved.

The invention relates to a method for obtaining a hint injection attack test case for a large language model, which combines a conditional variation auto-encoder cVAE and a Markov chain, and obtains a large language model test case through data generation and context modeling, gradual exposure of malicious instructions and simulation of multiple rounds of dialogue attacks in reality. Realizing multiple rounds of dialogue attacks on the large language model, and challenging the defense capability of the large language model; the design scheme introduces a concealment technology, role play attack, state transition and other technologies, improves the complexity and concealment of attacks, has the core advantages of automation, higher concealment, wide coverage, batch testing and the like, can evaluate the security defense capability of the large language model more truly and comprehensively, and improves the security defense capability of the large language model. The defects of an existing defense mechanism are found, and research on multi-round prompt injection attacks and improvement of a security defense mechanism are promoted.

The invention discloses a pathological feature recognition and negative elimination method based on microscopic imaging. The method comprises the following steps: S1, collecting a pathological section image and digitally generating original microscopic image data; s2, preprocessing the original microscopic image; s3, constructing a pathological image recognition network fusing converter coding and a gating dynamic receptive field mechanism, and outputting pathological feature vectors; s4, performing context modeling through an attention guidance and category perception decoder, and outputting an image classification result; s5, constructing a discriminant boundary separation model based on positive and negative sample embedding, and performing negative exclusion judgment; s6, performing confidence coefficient weighted evaluation in combination with the uncertainty and the boundary distance, setting a dynamic threshold value, and screening out low-credibility samples; and S7, coding the classification result and the negative label into structured data, and sending the structured data to a diagnosis auxiliary system. According to the method, multi-scale modeling and a negative screening mechanism are fused, and intelligent recognition and credible diagnosis output of the pathological image are realized.

The invention discloses a multi-modal data sensitivity grading method and system based on semantic risk map diffusion perception, and belongs to the technical field of artificial intelligence security and information content identification. Aiming at the problems of weak cross-modal linkage capability, insufficient context modeling, poor interpretability and the like of the existing multi-modal sensitivity identification method, the method realizes multi-modal fragment association by constructing a semantic risk unit, utilizes a semantic risk graph to model a cross-modal cooperative relationship, and adopts a thermal diffusion mechanism to simulate a risk propagation process, so that the method has the advantages of high sensitivity and high reliability. And finally, generating a structured interpretation path through the sensitive tag atlas. According to the method, high-precision multi-mode sensitive information identification and traceable grading judgment are realized, and the method is suitable for automatic compliance review of AIGC generation content.

The invention relates to the technical field of text feature fusion, in particular to an adaptive text guide fiber bundle feature fusion method and system based on a large language model. The method comprises the steps of performing multi-scale potential attention fusion based on features after fiber bundle feature fusion, including potential multi-scale feature embedding, inter-scale attention modeling, multi-scale fusion and residual enhancement, and attention regularization and scale consistency constraint; performing pseudo token sequence generation and aggregation based on features after multi-scale potential attention fusion, including pseudo token embedding representation, token serialization and slice mapping, semantic consistency and context modeling, and sequence aggregation and decodable interface generation; and processing the multi-modal fusion features subjected to pseudo token sequence generation and aggregation by using a large language model to generate natural language output. The invention provides an adaptive text-guided fiber bundle feature fusion method based on a large language model, which realizes efficient collaboration and semantic interpretable fusion of multi-modal information.

The invention discloses an unmanned platform electromechanical system fault early warning method based on a Transform-BiGRU cross attention mechanism, and belongs to the technical field of fault early warning. The method comprises the following steps: acquiring parameters, and performing time sequence alignment and key feature screening; secondly, designing a parallelization spatio-temporal feature extraction framework: on one hand, capturing a long time sequence dependency relationship through a multi-layer Transform encoder, on the other hand, realizing bidirectional context modeling of a sequence by adopting a bidirectional gating circulation unit, and introducing an interpretable global attention mechanism to perform feature weight dynamic allocation on a BiGRU hidden layer state; and a cross attention feature fusion module is constructed for a Transform and BIGRU fusion problem, and cooperative characterization of a time sequence dynamic feature and a space correlation feature is realized through interactive attention calculation of a spatial-temporal feature tensor. By means of the method, advanced early warning from diesel engine lubricating oil pressure abnormity to whole ship electric power system cascade faults is achieved.

The invention discloses a code vulnerability detection method based on multi-dimensional feature fusion and edge semantic enhancement, and the method comprises the steps: carrying out AST sub-tree structure compression based on a sub-tree folding rule on the basis of retaining an AST high-level grammar framework, fusing a PDG data flow and control flow dependency relationship, and constructing a lightweight program semantic graph; extracting node multi-dimensional features from the program semantic graph, extracting program-level global features in combination with an edge semantic enhancement mechanism, and performing vectorization representation; and inputting the program semantic graph features into a full connection layer, identifying potential vulnerabilities and outputting a detection result. According to the scheme, a context modeling mechanism based on a scope path is introduced, a semantic subtree, a grammar structure and scope information are combined, multi-dimensional features are extracted, multi-dimensional information fusion is realized through a dynamic attention mechanism, local and global feature splitting is prevented, and the edge semantic enhancement module is constructed to realize multi-dimensional information fusion. And the distinguishing capability and the feature expression capability of the model on heterogeneous edges are improved.

The invention discloses a dense small target detection method for an unmanned aerial vehicle aerial photography scene, and belongs to the technical field of computer vision and target detection. In order to solve the problems of small target scale dynamic change and feature expression weakening caused by flight height change, imaging resolution difference and scene complexity in aerial photography of an unmanned aerial vehicle, the invention provides a detection framework fusing an attention scale selection (AGSS) module and a dynamic local self-attention (DPSA) module. The method specifically comprises the following improvements: (1) an AGSS module enhances the significance and discrimination ability of small targets in multi-scale features through global context modeling and a dynamic weight distribution mechanism; and (2) a DPSA module introduces a sparse selection mechanism in a channel dimension, and focuses computing resources on a channel sensitive to a small target, so that efficient and lightweight attention modeling is realized. The above modules cooperate with each other, so that high reasoning efficiency is maintained, and small target detection precision and robustness in a complex background, low illumination and dense target scene are significantly improved. Experimental results show that on typical unmanned aerial vehicle aerial photography data sets such as VisDrone-DET2019 and the like, the method is superior to an existing mainstream method in multiple indexes such as the average precision (mAP), the accuracy rate and the recall rate, especially has obvious advantages in the aspects of integrity and stability of small target detection, and has good practical application value and popularization prospects.

The invention discloses a self-adaptive scene perception small target detection system, and the system comprises a scene perception and analysis module which is used for extracting scene features and calculating scene complexity; the multi-level feature extraction and reconstruction module is used for enhancing discriminative features in the scene features; the adaptive modal fusion module is used for dynamically generating a fusion weight for the enhanced scene features so as to perform feature fusion and iterative optimization; the spatio-temporal context modeling module is used for calculating a time sequence consistency constraint and a target appearance similarity, predicting a target motion track by using Kalman filtering, and establishing a spatial relation graph model; the detection strategy self-adaptive adjustment module is used for adjusting detection parameters of the spatial relation graph model so as to select an optimal detection strategy combination; and the edge calculation optimization module is used for constructing a knowledge distillation compression model so as to compress the spatial relation graph model. The method is high in environmental adaptability, can automatically adapt to different conditions, stably works around the clock, and is high in small target detection capability.

The invention belongs to the technical field of operation and maintenance of edge computing equipment in an industrial scene, and particularly relates to an edge computing terminal information query method based on LLM and MCP protocols and an intelligent agent. According to the method, a free question and answer mode and a timed query mode are supported at the same time, the free question and answer mode meets the temporary and interactive information acquisition requirement of a user, and the timed query mode is suitable for periodic and automatic index acquisition and monitoring, so that two scenes of real-time query and long-term operation and maintenance are considered, semantic analysis and context modeling are performed on a natural language request through LLM, and the query efficiency is improved. According to the method, the multi-target requirements and implicit intentions of the user can be understood, the mood, specialty and context consistency can be adjusted when the natural language answer is generated, the user experience is remarkably improved, bidirectional authentication and communication encryption of the client side and the server side are achieved by combining the MCP with the encryption token, and the safety of the query process and the reliability of result data are ensured.

The invention provides an automatic consumption tag analysis system and method based on multi-agent collaboration, and the system comprises a data processing agent which is used for collecting data from a social media platform and carrying out the data preprocessing; the label identification intelligent agent is used for extracting consumption labels of different dimensions from the preprocessed data; the sentiment analysis agent is used for carrying out context modeling and sentiment tendency recognition and binding the recognized sentiment tendency to the corresponding consumption label; the label normalization agent is used for performing clustering and normalization processing on all consumption labels bound with emotional tendencies to generate a structured multi-layer label atlas; the central scheduling agent is used for scheduling other agents, generating a label analysis result by using the multi-layer label atlas and sending the label analysis result to the user; according to the invention, based on a multi-agent architecture, structured analysis is carried out on user tags, behavior attributes and consumption intentions in social media contents, so that high-precision and high-efficiency intelligent consumption insight is realized.

The invention provides a geometric parameter measurement method based on underwater structure crack pixel-level semantic segmentation, and the method comprises the steps: constructing a multi-level feature extraction network based on ResNet-34, providing a structured feature pyramid for the subsequent context modeling and interference suppression, modeling illumination distribution features through a multi-head self-attention mechanism, and carrying out the modeling of the illumination distribution features through a multi-head self-attention mechanism. Regional scattering noise is extracted in combination with a cavity convolution pyramid, an environment context tensor is generated through fusion, a learnable gating mechanism is introduced for a decoding stage, dynamic modulation of jump connection characteristics and interference area response suppression are achieved, in addition, an edge perception auxiliary loss function is adopted, topological continuity of crack edges is enhanced, and finally, the method is applied to the field of jump connection. High-precision pixel-level segmentation of the underwater crack area can be realized without prior illumination correction, and the detection robustness and segmentation integrity in a complex environment are improved.

The invention provides an underwater image enhancement system and method based on multi-head transposition space attention, belongs to the technical field of underwater image enhancement based on computer vision, provides multi-head transposition space attention, and effectively combines multi-head transposition self-attention and space attention. According to the multi-head transposition self-attention, multi-head attention and transposition operation advantages are combined, so that the model is remarkably improved in the aspects of capturing a complex dependency relationship, enhancing context modeling, improving parallel computing efficiency and the like, meanwhile, space attention is fused, the weight of each position of a feature map is dynamically adjusted, and the multi-head transposition self-attention can be better focused on a key area. Wherein a feature extraction sub-module is added to further extract the features of the input image, so that the feature representation of the image can be refined, and the feature representation capability of the model is improved. And an adaptive instance normalization module of image style migration is applied to image enhancement, so that probability adaptation of the model is formed, and the image enhancement effect is further improved.

The invention discloses a breast cancer axillary lymph node metastasis prediction method based on multi-instance learning. The breast cancer axillary lymph node metastasis prediction method is used for predicting the metastasis state of axillary lymph nodes through breast cancer pathological sections. Firstly, a data enhancement function containing various disturbance strategies is designed in a data enhancement part, and the adaptability of a model to small samples and variation data is improved; secondly, a ConvNeXt network is adopted to extract instance features in the image blocks, and a feature optimization structure based on a global attention mechanism, a feedforward enhancement module, multi-head attention pooling and a residual connection mechanism is designed on the basis, so that the global context modeling capability is enhanced, and the consistency and discrimination of feature representation are improved; in addition, an MS-AttnFusion architecture based on fusion of a Scattering2D two-dimensional wavelet scattering network and an attention mechanism is designed, and through multi-scale feature decomposition and key area adaptive enhancement, a packet-level feature vector with higher discrimination capability is generated; and finally, the classifier receives the packet-level feature vector as input, and outputs a prediction result of the axillary lymph node metastasis state.

The invention belongs to the field of photovoltaic panel hot plate image processing, and particularly relates to a photovoltaic panel defect detection method fusing multi-scale wavelets and a lightweight attention mechanism. According to the method, an RHDWT discrete wavelet transform module based on multi-scale decomposition is added in a model input stage to strengthen image edge and texture detail representation; a Mix Structure Block module is introduced into a backbone network of the YOLOv11, so that multi-scale features are fused, and the feature expression capability is improved; an LWGA lightweight global attention mechanism is introduced into a neural network connection layer to enhance the context modeling capability, and the detection effect on small target defects such as fine cracks and hot spots is improved. According to the model, through collaborative optimization in three aspects of input preprocessing, feature extraction and an attention mechanism, the precision and robustness of defect detection in a complex photovoltaic module infrared or visible light image are remarkably improved, and the model is suitable for scenes such as high-precision photovoltaic panel image detection and intelligent maintenance.

The invention discloses a texture perception state space modeling method for an image restoration task, and the method comprises the steps: 1, constructing a region selection mechanism based on texture complexity, and enabling the region selection mechanism to be used for distinguishing a flat region and a high-texture region in an image; 2, introducing a texture modulation mechanism, and performing explicit adjustment on a state transition matrix in the state space model; 3, enhancing the context modeling capability of the model through a multi-direction sensing module; and 4, by combining position embedding and a sequence modeling structure, the capability of the model in the aspects of image structure understanding and spatial information maintenance is improved. The method can effectively alleviate the problem of information loss when a traditional image restoration method processes texture details, improves the structure restoration capability of a complex region, gives consideration to the restoration quality and the calculation efficiency, is suitable for multiple image restoration scenes such as image super-resolution, image rain removal, low-light image enhancement and the like, and improves the image restoration efficiency. And the method has good engineering adaptability and actual deployment value.

The invention provides a lightweight medical image segmentation network (ABUNet) based on asymmetry and an implementation method thereof, and the method comprises the following steps: S1, in a coding stage, proposing a feature subtraction convolution block (FSCB), and implementing O (C2 / N)-level parameter compression (N is a group number) by using channel feature difference operation; in a lightweight scene, the FSCB can effectively reduce feature redundancy, directly highlights key features of a lesion area, and is superior to traditional feature operation based on addition and multiplication; s2, in a decoding stage, a feature addition convolution block (FACB) is designed, a multi-branch feature fusion mechanism is adopted, and the alignment precision of different feature representations is improved under the condition that the calculation cost is not increased; and S3, in a bridging stage, a multi-scale deep convolutional block (MSDB) is constructed, and the multi-scale context modeling capability of the model is remarkably enhanced by utilizing heterogeneous kernel parallel computing, so that more accurate lesion feature extraction is realized. And S4, in a network integration stage, an FSCB module is integrated into an encoder part of a U-shaped architecture, an FACB module is integrated into a decoder part, and an MSDB module is used for processing grouping characteristics in a bridging module to construct an asymmetric model ABUNet. The asymmetric architecture overcomes the limitation of symmetry of a traditional encoder-decoder, and effectively balances high segmentation precision and calculation efficiency.

The invention belongs to the technical field of intelligent sensing, and relates to a micro-seismic monitoring method for a ground moving target in a sensitive area, which comprises the following steps: collecting five types of moving target seismic signals, and constructing a data set; preprocessing the data; constructing an interpretable convolution kernel based on a scalar wave field equation, and realizing adaptive extraction of key physical parameters and nonlinear dimensionality reduction of a high-dimensional feature space by embedding a partial differential operator to form compact feature representation with physical traceability; forward diffusion is adopted to carry out progressive Gaussian noise enhancement on the noisy features; designing a Transform architecture with a multi-head self-attention mechanism and position coding, capturing time-space correlation characteristics of vibration signals through context modeling, and realizing end-to-end mapping from physical characteristics to classification decision in combination with a multi-layer perceptron; and carrying out training and event decision making on the model, and outputting a decision classification result. According to the method, the identification accuracy of the seismic oscillation signal of the moving target can reach 95.2%, and the robustness is remarkably improved.

The invention discloses a broadcast ephemeris time sequence anomaly detection method based on multi-dimensional feature fusion, and the method comprises the steps: obtaining multi-dimensional broadcast ephemeris time sequence data, carrying out the anomaly scoring of the variable dimension of the multi-dimensional broadcast ephemeris time sequence data through employing an isolated forest and a relative quality algorithm, thereby completing the preliminary screening, recognizing potential abnormal data points, and carrying out the detection of the abnormal data points. Extra time sequence features are constructed; then, further deeply analyzing the data points based on the LSTM of a time pattern, and capturing complex spatial-temporal characteristics in the data through the strong context modeling capability and attention mechanism of the LSTM, thereby reducing the excessive sensitivity to a single data point and completing the construction and training of an anomaly detection model; and obtaining a predicted value of a previous moment based on the existing features and a trained anomaly detection model, and judging whether abnormal data exist in the multi-dimensional time series data based on the predicted value. According to the method, the limitation of processing long-period data is solved, and the accuracy and the stability of a detection result are remarkably improved.

The invention relates to an event camera target detection method based on sparse Mama, and the method comprises the steps: adaptively discarding no-event and noise marks based on time-space continuity evaluation, capturing a global dependency relationship in space and channel dimensions, and showing the optimal balance between accuracy and efficiency; an information-first local scanning strategy (IPL-Scan) is provided and is used for guiding the model to pay attention to marks with high information content in the scanning process, so that the space context modeling capability is improved; and a global channel interaction module (GCI) is designed to aggregate channel information from the perspective of global space, and global interaction is expanded to a 3D feature space, so that the global modeling capability is further improved.

The invention discloses a dynamic multi-scale convolution and cross-level attention feature fusion method and device, and relates to the technical field of image semantic segmentation. The basic strategy of the method comprises the following steps: receiving a feature map output by a decoder and a residual feature output by an encoder at the same level, carrying out dual calibration through channel attention and space attention, and adding a channel enhancement feature and a space enhancement feature to obtain a preliminary fusion feature; then, after cross-layer features and preliminary fusion features are introduced to be spliced in a channel dimension, a new feature map after dynamic fusion is output by means of dynamic multi-scale convolution, finally, local and global feature extraction is conducted on the new feature map, and fusion output is conducted after fine screening is conducted on the local and global features and the dynamic fusion features through a gating mechanism. Therefore, the cross-level feature fusion can be realized by taking the dynamic calculation as a means and the cross-level context as a link, the context modeling capability of the segmentation model is enhanced, and the capability of the image segmentation task is further improved.

The invention discloses a market intelligence-oriented automatic data acquisition and decision support system, particularly relates to the technical field of artificial intelligence and information processing, and comprises a structure rendering module, a semantic extraction module, and a credible evaluation and execution feedback module. The system extracts structural anchor points through image rendering, generates semantic vectors in combination with context modeling, calculates a structural consistency index and a semantic validity index, outputs a five-level credibility level result through a fuzzy logic device, refreshes a collection task scheduling priority, and updates a pre-training language model based on semantic offset feedback. Self-iteration semantic generalization and efficient decision support under a cross-platform context are realized; according to the method, stable recognition of the webpage structure is achieved through structure rendering, multi-dimensional semantic feature generation is achieved by means of semantic extraction, the credibility level is output in combination with double-index evaluation and fuzzy logic, then collection scheduling and model self-adaptive updating are optimized, and the obtaining precision and decision reliability of market information data are effectively improved.

The invention relates to a traffic accident intelligent detection system and method based on a YOLOv12 improved architecture. The system comprises a YOLOv12 enhanced feature extraction network, a multi-scale detection head, a time sequence information fusion module, a real-time reasoning optimization engine and an intelligent decision fusion system, and realizes collaborative optimization of local feature enhancement and global context modeling by constructing six core technology modules and adopting collaborative learning of a C2f-Attention mechanism and deformable convolution. According to the method, a composite loss function special for traffic accidents is innovatively designed, and adaptive fusion of multi-scale features and difficult sample mining are realized through a multi-objective optimization mechanism of Enhanced Focus Loss, IoU-aware Loss and Severage-aware Loss. According to the method, the problems of low detection precision and false alarm and missing alarm caused by illumination variation, shielding and motion blur in a traffic monitoring scene are effectively solved, in the test of an AccidentsDesection YOLOv8 data set, the mAP at 0.5 reaches 91.27% and is improved by 8.6% compared with that of YOLOv8, the reasoning speed reaches 67 FPS, experimental results show that the system has excellent performance in the aspects of detection precision, real-time performance and model compression, and the method is suitable for popularization and application. The method achieves a remarkable effect in traffic accident intelligent identification, and has a remarkable technical effect and industrial application value.

The invention discloses an event causal relationship identification method based on iterative graph prompt learning, and belongs to the technical field of natural language processing. Comprising the following steps: constructing an initial definite causal graph; based on the initial definite causal graph, performing context modeling on a to-be-recognized text, extracting multi-path information of each event pair in the to-be-recognized text, and inputting the multi-path information into a generative language model to perform causal relationship generation to obtain an initial causal relationship result; based on the initial causal relationship result, adopting a graph structure constraint mechanism to carry out multiple rounds of iterative optimization on the initial definite causal graph, dynamically selecting an edge according to confidence, updating the initial definite causal graph, judging whether an iteration termination condition is met or not, and stopping iteration when the iteration termination condition is met to obtain an optimized definite causal graph; and obtaining an event causal relationship result of the to-be-identified text based on the optimized definite causal graph. According to the method, the event causal relationship identification accuracy is improved.

The invention discloses a metro dangerous goods terahertz detection method based on adaptive downsampling and a multi-dimensional attention mechanism. The metro dangerous goods terahertz detection method comprises the following steps: acquiring a terahertz image data set; building a deep learning network model, wherein the deep learning network model comprises a backbone feature extraction network, a check feature extraction network, a down-sampling module, a fusion channel and space attention module, a space attention module and a YoloHead detection head which are connected in sequence; performing dual-path processing on the input feature map through parallel pooling and convolution operation; in the fusion channel and space attention module, global context modeling is carried out on the feature map; in the space attention module, long-range context dependence is captured through a strip-shaped pooling layer; inputting the multi-scale feature map output by the check network into a YoloHead detection head, and outputting a target detection frame; a redundant detection frame is removed through a non-maximum suppression algorithm, and a detection result with the highest confidence coefficient is reserved.