366 results about "Attention model" patented technology

The invention relates to a dexterous hand multi-mode motion trail prediction model generation method and a related device, which are used for a dexterous hand simulation grabbing process, and the method comprises the following steps: generating a motion trail of a dexterous hand according to initial position information of the dexterous hand and end position information of a target object; based on the plurality of motion track points, a multi-modal data set of motion of the dexterous hand in the motion track is obtained, and the multi-modal data set comprises environment image data, first multi-modal data and second multi-modal data; performing multi-modal feature fusion on the environment image data, the first multi-modal data and the second multi-modal data to obtain an input sequence; and based on a preset sparse self-attention mechanism, inputting the input sequence into a to-be-trained self-attention model for training to obtain a motion track prediction model. According to the scheme provided by the invention, the real-time performance and the accuracy of the motion trail prediction of the dexterous hand can be improved through the fusion of the multi-modal data, and the grabbing success rate of the dexterous hand is improved.

The invention relates to a cultural scenic spot people flow prediction and scheduling method based on machine learning, and belongs to the field of scenic spot management. 2, constructing and training a mixed attention model, wherein the constructed mixed attention model comprises a spatial-temporal feature extraction module and a mixed attention mechanism module; step 3, people flow prediction and result output: inputting real-time data into the trained mixed attention model to carry out people flow prediction, and outputting a future time period passenger flow volume value; a quantile regression technology is combined to output a confidence interval of the passenger flow volume; step 4, scheduling strategy implementation: constructing a dynamic thermodynamic diagram based on a prediction result, and marking crowd density levels of different areas in the thermodynamic diagram; early warning information is pushed in real time, and touring suggestions are sent to tourists in advance.

The invention belongs to the related technical field of image processing, and discloses a texture surface defect generation method and system based on a mask perception image redrawing network, and the method comprises the steps: (1) obtaining a low-frequency structure feature based on a defect sample image of a to-be-processed product category, a binary mask for marking a defect position, and a convolutional coding module; (2) a context sliding window attention modeling module carries out long-range dependence modeling on the feature sequence, and attention calculation is carried out between effective feature marks to obtain high-frequency detail features; (3) inputting the low-frequency structural features and the high-frequency detail features into a collaborative feature fusion module for fusion to obtain fusion features; (4) a style modulation decoding module performs up-sampling on the fusion features based on the comprehensive style tensor; and (5) generating a defect image based on the trained generator network model, the defect-free sample image of the to-be-processed product category and a user-defined defect mask. According to the invention, the authenticity of defect generation is improved.

The invention provides a data center interconnection link fault self-healing and path switching method, which comprises the following steps of: acquiring multi-dimensional link performance monitoring data, establishing a standardized time sequence database, realizing link health degree multi-index trend prediction by combining an LSTM-Attention model, and determining the link health degree according to the LSTM-Attention model. Risk-aware dynamic path selection and switching for multiple business scenes are realized by combining business service sensitivity modeling, path inherent stability quantification, nonlinear adaptive switching criteria and a debounce switching process, the response accuracy and the business adaptation degree of path switching are improved, false triggering and service interruption risks can be remarkably reduced, and the path switching efficiency is improved. And the high availability and robustness of routing in a complex network environment are enhanced.

The invention discloses a power consumption time sequence prediction method and system based on a self-attention mechanism, a medium and a processor, and relates to the technical field of power consumption time sequence prediction. The method comprises the steps of obtaining original data, preprocessing the original data, dividing the original data into a training input set and a label set, extracting time and power unit features through convolution operation, calculating and fusing the features through double attention, obtaining a prediction value through convolution operation, optimizing model parameters, and finally predicting a future power consumption value based on an optimization model. The system comprises a preparation module, a first operation module, a fusion module, a second operation module and a prediction module. A computer readable storage medium and a processor store and run programs for executing the method, respectively. According to the method, the nonlinear features and the long-term dependency relationship of the data are effectively captured through a self-attention mechanism, the feature extraction capability is improved through a double attention model, and the prediction precision is improved.

The invention relates to the technical field of information security management, in particular to a multi-modal data dynamic desensitization method and system based on machine learning, multi-modal features such as texts, images and time sequences are jointly extracted through CNN-Transform-LSTM, 1-5 sensitive levels are evaluated by adopting a cross-modal attention model, a self-adaptive desensitization strategy is generated through an improved MOEA / D-DE algorithm, and the dynamic desensitization of the multi-modal data is realized. And realizing cross-modal collaborative desensitization by combining GNN. The system dynamically adjusts parameters through TD3 reinforcement learning, the response delay is less than or equal to 100ms, the Bi-LSTM-AE model evaluates privacy and utility in real time, and the block chain evidence storage whole process is realized. The method solves the problems of precision and utility imbalance, poor dynamic adaptability and insufficient multi-mode collaboration in the traditional technology, and is suitable for the fields of finance, medical treatment and the like.

The invention relates to a GIS (Gas Insulated Switchgear) equipment mechanical defect diagnosis method based on a Gramb angle field and a dual-channel PCNN-Attention neural network, and belongs to the technical field of gas insulated switchgear mechanical vibration defect diagnosis. The method solves the problems that traditional diagnosis depends on artificial feature extraction, so that subjectivity is high, information mining is insufficient, and defect severity evaluation is missing. According to the technical scheme, the method comprises the steps that a one-dimensional vibration signal is converted into a GASF two-dimensional image and a GADF two-dimensional image through a GASF field so as to completely reserve time sequence topological features; carrying out data enhancement by adopting an image geometric transformation technology so as to improve the generalization ability of the model; and a dual-channel PCNN-Attention model is constructed, and synchronous intelligent identification of defect types and severity is realized through parallel feature extraction and dynamic weight optimization of an attention mechanism. According to the method, the diagnosis accuracy, reliability and adaptive capacity are improved, and support is provided for equipment state operation and maintenance.

The invention relates to the field of forged image detection, and provides a forged image detection method and device, a medium and a product, and the method comprises the steps: dividing an input image into a plurality of local regions, and constructing a region dependence graph of the local regions; extracting local style features from the region dependence graph by using a local network model; extracting global style features of the input image by using the global network model; performing attention fusion on the local style features and the global style features by using an attention model to obtain a fusion vector; performing image forgery detection on the fusion vector by using a classifier; wherein the local network model, the global network model, the attention model and the classifier are optimized through training. According to the invention, high identification accuracy and robustness can be maintained in detection scenes of scarce samples, local detail forgery and cross-domain forgery.

The invention provides a product recommendation method and device, electronic equipment, a medium and a program product, and can be applied to the technical field of artificial intelligence, the technical field of big data, the technical field of block chains and the technical field of privacy computing. The method comprises the following steps: acquiring structured data and unstructured data of a target user; extracting preference features based on the unstructured data, and obtaining a time sequence preference portrait by using a time sequence attention model; obtaining a target user portrait based on the time sequence preference portrait and the structured data; obtaining a multi-dimensional sequential relation graph, and reasoning the multi-dimensional sequential relation graph by using a graph neural network to obtain relation representation; executing collaborative filtering scoring based on the target user portrait and the relationship representation, and generating an intermediate product score; taking the generated intermediate product score as an input, and outputting a candidate product score based on a recommendation optimization function containing a space-time weight; and performing product recommendation based on the candidate product scores.

The invention provides a model training method for a transverse mixed attention mechanism, a medium, equipment and a program product, and the method comprises the steps: obtaining a data set containing a plurality of sample sequences, each sample sequence in the data set being formed by arranging a plurality of Token sequences obtained through word segmentation; constructing a to-be-trained model based on the pre-trained full attention model, and adding newly added parameters for linear attention calculation; in the same transverse mixed attention layer, executing total attention calculation on a Token set in a preset total attention calculation range, executing linear attention calculation on all Tokens, and fusing results of the total attention calculation and the linear attention calculation to obtain transverse mixed attention output used for forward reasoning and loss calculation; and based on the output and prediction result, only updating the newly added parameters to optimize the to-be-trained model until the to-be-trained model converges. According to the method, the calculation complexity and video memory occupation of long text sequence processing are reduced, and the reasoning speed and the resource utilization rate are improved.

The invention relates to the technical field of user portrait information processing, and particularly provides a user real-time portrait updating method and system, and the method comprises the steps: collecting a time sequence interaction track sequence generated by a user in a current interaction scene in real time, and constructing a heterogeneous behavior data flow based on a cross-modal behavior synchronous collection technology; detecting the deviation degree of the historical behavior sequence in the unified feature space, and generating a conflict state mode label; analyzing a behavior evolution path by applying a time sequence self-attention model, and outputting multi-intention probability distribution; dynamically adjusting a confidence coefficient threshold value based on a conflict state and filtering out a noise portrait label; and triggering cross-modal joint recoding and intention re-reasoning for a prediction deviation time period, and locally updating the portrait through a feedback closed loop. Static portrait updating lag limitation is broken through, second-level intention tracking and dynamic behavior mode capturing are achieved, and portrait adaptability and storage efficiency in a high-noise scene are remarkably improved.

The invention relates to the technical field of intelligent traffic systems, in particular to a highway network global traffic flow prediction method, device and equipment, and the method comprises the steps: constructing an initial feature sequence based on the multi-source data of an ETC portal system; inputting the data into a multi-head attention model driven by a query mechanism, and outputting a spatial dependency relationship between ETC door frame nodes; inputting the spatial dependency relationship into an extraction fusion model fusing a causal convolutional network and a selective state space network, extracting short-term time sequence features through the causal convolutional network, modeling long-term time sequence features through the selective state space network, and fusing the long-term time sequence features into fused time sequence features; and a global traffic flow prediction result is generated based on the fusion time sequence features, so that the problems of high traffic flow prediction cost, data coverage missing and the like in related technologies are solved.

The invention relates to an external parameter online calibration method for a laser radar and a camera in a cross-country environment, and the method comprises the steps: constructing an external parameter calibration network MLLANet based on a Mama-like linear attention model, taking a camera RGB image and a laser radar initial depth map as input, extracting multi-scale features through multistage convolution and a Mama-like attention module in sequence, and carrying out the multi-scale feature extraction; and feature matching is realized through multi-resolution feature fusion and cost volume construction, and translation and rotation parameters are respectively predicted by a global regression layer. According to the network, regression loss and depth map loss based on Huber are introduced into a loss function part, and a mixed loss system is constructed, so that training robustness is enhanced, and the influence of point cloud outliers is inhibited. And gradually reducing the external parameter search range through multi-stage iterative optimization, and finally realizing high-precision estimation of the six-degree-of-freedom external parameters. The method does not need a manual calibration board, can still keep high precision and real-time performance in a cross-country unstructured environment, and can be widely applied to environment perception and autonomous navigation tasks of an unmanned system.

The invention provides a vehicle path planning method and system based on a dynamic attention model, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining instance data containing warehouse nodes, client nodes and vehicle capacity information; a dynamic encoder-decoder architecture model is constructed, and an encoder recalculates feature embedding of unaccessed nodes every time a vehicle returns to a warehouse based on a graph attention network so as to respond to dynamic changes of instance states in the path construction process; the decoder selects a next node to be accessed according to the current path state, residual node embedding and vehicle real-time capacity; a REINFORCE algorithm is adopted to take the minimum path length as a target training model, and a greedy strategy baseline is introduced to reduce variance; and finally, the initial path is optimized by combining the local search of the 2OPT, and a final planning scheme is output. According to the method, the problem that a traditional attention model cannot adapt to a dynamic environment due to fixed node embedding is effectively solved, the total cost of a path is reduced, and good generalization and expandability are achieved.

The invention discloses a step-type landslide-oriented multi-source fusion deep learning deformation intelligent prediction method, and belongs to the technical field of geological disaster monitoring and early warning, and the method comprises the following steps: S1, constructing and preprocessing a landslide data set of a research region; s2, decomposing displacement data based on a CEEMDAN algorithm; s3, screening key influence factors through grey correlation analysis; s4, constructing a TCN-Attention model to respectively predict a trend term and a period term; and S5, superposing prediction results and carrying out precision evaluation. According to the multi-source fusion deep learning deformation intelligent prediction method for the step-type landslide, the problems of modal aliasing and energy loss of a traditional method are reduced, and the signal decomposition effect is optimized; and the long-term deformation trend is accurately captured, the displacement abrupt change point is identified, and the prediction precision is improved.

The invention relates to an AI dynamic repayment behavior monitoring and early warning method and system, and belongs to the field of financial risk control and artificial intelligence. Multi-dimensional time sequence features are constructed by fusing repayment behaviors, home decoration progress and text interaction information, dynamic risk prediction is realized by using an LSTM-attention model, grading early warning is triggered in combination with a home decoration stage adaptive threshold, a scenarized intervention strategy is generated according to a risk grade, intervention feedback is used for optimization of the model and the threshold, and the risk prediction efficiency is improved. And a closed-loop mechanism of post-loan risk identification and intervention is formed. According to the invention, real-time risk monitoring and accurate intervention of the home decoration staged loan can be realized, and the early warning accuracy and the post-loan management efficiency are effectively improved.

The invention discloses an environment gas leakage intelligent detection method based on big data analysis. The method comprises the following steps: collecting monitoring data and constructing a sensor network space-time diagram fused with meteorological conditions; predicting the background concentration of each node by using a sequence decomposition attention model; calculating a concentration residual error and constructing a space-time residual error map; extracting an abnormal feature vector through a physical information enhanced graph attention network; calculating an abnormal score in combination with the normal mode memory bank and generating a leakage source probability distribution diagram; when the conditions are met, calling a computational fluid dynamics model to simulate a theoretical concentration field; and determining a leakage event through spatial correlation analysis. According to the invention, the false alarm rate of gas leakage detection in an open environment is obviously reduced, and the leakage source positioning precision is improved.

The invention provides a multi-mode-based sensing intelligent road and bridge automatic inspection method and system, and is applied to the technical field of intelligent traffic. The method comprises the steps of collecting road and bridge visual images and geographic coordinate data, determining a preliminary damaged area and performing initial mapping, and obtaining an accurate positioning result through attention model optimization matching and iterative calibration; according to the scheme, the road and bridge defect positioning precision and inspection efficiency in a complex environment can be improved, and the problem of large positioning error in the prior art is solved.

The invention relates to a multi-modal power data retrieval method and device and a medium, and belongs to the technical field of data retrieval, and the method comprises the following steps: obtaining and preprocessing power data, inputting a text and an image into a multi-layer perceptron to obtain an initial feature vector, and outputting a text feature vector and an image feature vector through a routing capsule algorithm; mapping to a public space by adopting linear transformation to obtain a projection vector; and inputting the projection vector into the additive attention model, and outputting a fusion feature vector. And constructing a hash function, calculating an electric power data index based on the fused feature vector, and storing data with the same index into a corresponding hash table bucket. And obtaining a user query, calculating a query fusion feature vector and an index, calculating the similarity of the query fusion feature vector and the index with each power data fusion feature vector in the corresponding bucket, and returning R power data with the highest similarity score as a retrieval result. According to the method, multi-modal information is integrated, the importance is adjusted by using an attention mechanism, and the retrieval effect is effectively improved.

The invention provides a binocular stereo matching method and system, and the method comprises the steps: obtaining a left and right stereo image pair captured by a binocular camera, and carrying out the feature extraction and enhancement through a depth separable convolution basic network and an ECANet attention model; carrying out topological structure transformation by using a TopoAug feature enhancement strategy, constructing a topological consistency loss function and carrying out adaptive feature fusion; a large neighborhood search strategy and a hybrid node-destructor model are adopted to construct an initial cost body, and cost aggregation is carried out through capacity routing; and constructing an M uniform loss grid and a grid motion model to carry out parallax estimation, and obtaining a final parallax map through unsupervised consistency optimization. Through the technologies of lightweight network design, topology perception feature enhancement, hybrid node optimization cost body construction, unsupervised consistency optimization and the like, the calculation complexity is reduced while high precision is kept, and the method is particularly suitable for real-time monitoring scenes in resource-constrained environments such as substations and the like.

The invention discloses a joint blind denoising method and system based on self-heuristic learning and Bayesian reasoning, belongs to the field of computational imaging, and solves the problems that in the prior art, the mixed noise modeling capability is insufficient, the performance is degraded under the condition of low signal-to-noise ratio, the combination of uncertainty quantization and regularization is lacked, and the generalization capability is limited due to data dependence. Comprising the following steps: collecting an original image and preprocessing; generating a noise data pair; an enhanced residual attention U-Net model is constructed; a noise estimation sub-network is adopted to extract noise features, the noise features are fused with original image features, and the model is trained; adopting the trained model to carry out multiple times of forward propagation on the same input image to obtain multiple groups of denoising results; calculating a mean value and a standard deviation to obtain a de-noising prediction and uncertainty heat map; and training the trained model again based on the uncertainty heat map, optimizing network parameters, and obtaining a final denoising prediction result and uncertainty estimation thereof. The method is suitable for complex noise distribution processing scenes.

The invention relates to an interaction method and device based on virtual reality, equipment and a medium. According to the method, firstly, state data of a user in a virtual reality environment is collected and preprocessed to generate a standardized data stream, and then the distance, orientation similarity and interaction frequency between the user and a virtual avatar are calculated based on the data so as to construct a situational social graph representing social relation strength. Meanwhile, an attention model representing attention weight is constructed by analyzing a fixation point and a head direction of a virtual avatar of the user, and then information priority is calculated through weighted summation of social relation strength and the attention weight by utilizing a situational social graph and the attention model; according to the method and the device, the priority of the user is obtained, the audio, visual and text information is dynamically filtered or enhanced according to the priority to generate the optimized information flow, and finally the information flow is presented in the virtual reality environment, so that the cognitive load of the user in a dense social scene is effectively reduced, and the social interaction efficiency and immersion are improved.

The invention provides an operation method of an attention mechanism in a chip, the chip, electronic equipment, a storage medium and a program product. In a forward stage of attention model training, forward calculation is performed on a query matrix, a key matrix and a value matrix in each thread of a calculation engine based on a first instruction pipeline to obtain a forward output matrix, in algorithm implementation, matrix multiplication is executed by calling a matrix multiplication unit through a first thread and a third thread, and a forward output matrix is obtained. The vector calculation is processed by a second thread calling vector calculation unit; in a reverse phase, performing reverse calculation on the query matrix, the key matrix, the value matrix and the output gradient matrix in each thread based on a second instruction pipeline to obtain a target gradient matrix; the matrix multiplication unit is called in the first thread and the third thread to execute matrix multiplication, the vector calculation unit is called in the second thread to execute vector calculation, and the data carrying unit is called in the idle first thread or the third thread to obtain all matrixes. According to the invention, the operation performance of the chip can be improved.

The invention relates to the technical field of machine learning, and discloses a mapping operator-based automatic generation method for a sub-mirror rough sketch, which comprises the following steps of: carrying out hierarchical analysis on a sub-mirror script text by adopting a power attention-Transform model; generating a visual composition scheme through a semantic visual mapping operator; wherein an improved Bezier curve method of a four-parameter Bernstein substrate is introduced into an action track, flexible reconstruction and key frame extraction of complex actions are realized, and picture colors, illumination and line styles can be adaptively adjusted by emotional style parameters to ensure that a narrative atmosphere is consistent with a director intention; and finally, rendering into a complete sub-mirror sketch sequence. According to the method, efficient, accurate and uniform-style sub-mirror sketch generation can be realized in film and television, animation and advertisement production, and creation efficiency and picture expressive force are remarkably improved.

The invention discloses a real-time well drilling lithology identification method fusing double attention and wavelet transform. The method comprises the steps that firstly, drilling parameters are collected and preprocessed, and a depth domain analysis matrix is formed through a sliding window; then carrying out wavelet transform, and extracting and filtering amplitude and phase characteristics; secondly, constructing a double-attention model, capturing time domain dependence by using self-attention, and fusing time-frequency features by using cross attention; after the fusion features are subjected to linear projection and layer normalization, a lithology classification result is output through a multi-layer perceptron; according to the method, through fusion of double attention and wavelet transformation, collaborative modeling of time domain and frequency domain features is achieved, the problems that long-range dependence modeling is weak, cross-domain fusion is difficult and the like in a traditional method are solved, lithology can be accurately recognized in real time, and the method is suitable for being used for a large-scale popularization and application. The method does not need to depend on expensive logging-while-drilling equipment, and has high practical value in petroleum drilling engineering.

The invention discloses a channel estimation method and device, a program product and a decoupling antenna array, and the method comprises the steps: obtaining initial channel estimation data based on signal transmission data and signal receiving data obtained by the decoupling antenna array; and constructing a channel tensor structure diagram, determining channel frequency domain data, and performing dimension fusion to obtain channel fusion data. And performing multi-layer attention fusion through a multi-layer attention model, and determining a fusion feature tensor of the antenna node in the channel tensor structure diagram. And based on the node feature tensor, accurately determining channel estimation data. According to the technical scheme provided by the invention, the channel estimation precision is effectively improved, the multi-dimensional feature information of the channel is fully mined, the complex spatial relationship between different antenna nodes is dynamically captured, the channel feature extraction accuracy is improved, the channel estimation process precision is remarkably improved, and the channel estimation efficiency is improved. Real and effective feedback information is provided for optimizing an antenna array hardware structure, and the communication quality and the user communication experience are improved.

A system for analyzing sports science data with integrated financial management, consisting of: a data acquisition module configured to ingest heterogeneous data streams from multiple sources, including digital advertising platforms, customer relationship management systems, ticket databases, sponsorship activation protocols, broadcast audience statistics, and point-of-sale systems for goods; a telemetry harmonization processing unit configured to encode temporal, categorical, and numerical marketing and engagement signals into structured tensors, correcting inconsistencies in sampling frequency and missing values; an attribution modeling processor comprising a neural sequence encoder selected from a bidirectional long-term-short-term memory network or a transformer-based attention model, coupled with a causal inference submodule that generates attribution scores by unraveling overlapping influences of concurrent marketing campaigns; an explainability controller configured to generate interpretable attribution outputs by applying Shapley value decomposition, local surrogate model explanations, counterfactual simulation, and temporal sensitivity analysis, with the outputs visualized for end users in real time; a financial simulation engine that is operationally coupled with the attribution modeling processor and configured to translate incremental marketing contribution signals into structured financial reports, including profit and loss statements, balance sheets, and cash flow forecasts, using stochastic financial models to predict key indicators under variable marketing scenarios; a secure audit logging module that includes a blockchain anchoring layer configured to record allocation decisions, explainability results, and financial simulation results in tamper-proof records to ensure traceability and compliance; and a machine interface device consisting of a processing unit, a storage unit, a visualization subsystem and an interaction console, displaying mapping, explainability and financial simulation results on interactive dashboards.

The invention discloses a mobile robot visual navigation method based on space-time attention and an asynchronous element variation strategy. The method comprises the following steps: S100, defining a state space and an action space of a visual navigation task; s200, hierarchical semantic information modeling and context vectors are introduced; s300, adopting a space-time adaptive convolution attention model, fusing causal expansion convolution and a time sequence adaptive multi-dimensional attention mechanism, and dynamically capturing long-term space-time dependence characteristics of the environment; s400, constructing an asynchronous meta-variation strategy algorithm, and modeling the uncertainty of navigation strategy parameters by combining an asynchronous parallelized strategy gradient updating and meta-variation inference method; s500, designing a multi-target reward function and training a navigation strategy; and S600, migrating the trained navigation strategy model to a real machine. The visual navigation method provided by the invention can effectively solve the defects of an existing navigation method in the aspects of processing long-term space-time dependence and generalization, and realizes efficient autonomous navigation of the mobile robot in an unknown complex environment.

The invention relates to the technical field of ship and ocean engineering, in particular to a global-local dependency cooperative expression ship rolling motion extremely-short-term forecasting method which comprises the steps that an Informer branch and BiGRU-GSA branch parallel architecture is constructed, an encoder of the Informer branch screens key query key pairs through a ProbSparse self-attention mechanism, and the sequence length is compressed through a self-attention distillation mechanism; the decoder adopts generative reasoning and single forward propagation to generate a complete prediction sequence; the BiGRU-GSA branch utilizes a multi-layer BiGRU network to simultaneously capture forward and backward time sequence dependence through a bidirectional gating unit, and extracts time domain fine-grained features; the GSA network constructs local representation of time sequence preference by using two-stage gating linear attention through a gating slot attention model; and the global features of the Informer branch and the local features of the BiGRU-GSA branch are spliced, feature fusion is realized through a full connection layer, a prediction result is generated, and collaborative expression of global-local dependence is realized. According to the invention, high-precision prediction can be carried out on the future motion state of the ship in an extremely short time.

The invention discloses a multi-modal sensor external parameter failure perception and online calibration method. The method comprises the steps of performing speed estimation and point cloud distortion correction on a three-dimensional scene moving target based on a space attention model and an unsupervised scene flow training framework; on the basis of distortion correction and data of a significant target estimation heat map, semantic feature extraction of a spatial moving target is performed through an attention heat map region, and multi-modal data feature matching of a laser radar and a camera is performed through consistency estimation between semantic information and a significant three-dimensional target pose; according to streaming data of an online scene, time-space and attention heat map information are fused, a factor graph optimization model is constructed by using multi-sensor external parameters, online tight coupling optimization is carried out, the external parameters are further accurately estimated, failure perception is carried out by using consistency discrimination of optimization convergence, and a closed loop is formed on a result. According to the method, aiming at an online calibration environment and based on a space attention mechanism, a multi-sensor high-precision fusion external parameter drift problem existing in large-scale road surveying and mapping is optimized, and a better solution is provided.