957 results about "Linear transform" patented technology

The invention relates to the technical field of data encryption, and discloses a data encryption protection system and method for intelligent controller hardware, and the method comprises the steps: generating a random confusion factor based on a real-time operation state through constructing a dynamic confusion algorithm, and carrying out the nonlinear transformation of original data; implementing a fragment encryption strategy, dividing fragments according to data sensitivity levels, and adopting a heterogeneous encryption algorithm; generating a dynamic binding key in combination with the environment parameters and the hardware unique identifier; hardware-level integrity check is executed, and data and hardware are verified through cyclic redundancy check codes and hardware fingerprints; establishing a self-adaptive key updating mechanism; performing multi-layer defense linkage; and implementing anti-side channel protection, and constructing a security audit log. According to the method, the hardware data security of the intelligent controller is comprehensively guaranteed, various security threats are effectively resisted, and the data confidentiality, integrity and availability are improved.

The invention relates to the technical field of voice processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a voice feature processing method, device, equipment and medium. Performing time resolution analysis based on the fused Mel band energy to generate a multi-scale Mel spectrum amplitude value, and performing nonlinear transformation on the multi-scale Mel spectrum amplitude value according to the noise intensity parameter to generate a noise suppression Mel component; and generating a perception weighting coefficient according to an auditory perception model, and executing frequency domain energy adjustment on the noise suppression Mel component to generate Mel spectrum representation. On the basis of frequency resolution self-adaption, time resolution dynamic adjustment and auditory perception modeling, nonlinear transformation and perception weighting processing are applied to the multi-scale Mel spectrum amplitude value, the influence of noise interference on voice features can be effectively reduced, and the key information retention capacity of voice signals is enhanced.

The invention provides a power load long time sequence prediction method and a related device, and relates to the technical field of power load prediction. The method comprises the steps of collecting power load time sequence data; preprocessing the power load time sequence data; decomposing the preprocessed power load time sequence data into a seasonal component and a trend component through a mobile decomposition method; inputting the trend components into a trend clustering enhancement network, performing channel clustering on the trend components through a K-means clustering algorithm, applying independent linear transformation to each clustering group, and extracting long-term trend features; inputting the seasonal components into a seasonal causal attention network, and extracting short-term seasonal features through a causal mask mechanism and a multi-head attention mechanism; fusing the long-term trend features and the short-term seasonal features to generate fused features; and inputting the fusion features into a decoder, and outputting a power load prediction result through a full connection layer. The change trend of the power load data is fully considered, and the prediction precision of the power load long sequence is improved.

The invention discloses an electric power system short-term load prediction method based on TCN-BIGRU-CBAM, and the method comprises the steps: obtaining a standard load time series data set as input data, and carrying out the preprocessing of the input data; establishing a time convolutional network TCN model, and extracting a long-term dependency relationship in the time sequence; establishing a two-way gating cycle unit network BIGRU, and outputting two-way time characteristics; constructing a convolutional block attention module (CBAM), and obtaining a four-dimensional feature map subjected to channel and space attention enhancement; and establishing a full connection layer, mapping the time sequence characteristics to a scalar through linear transformation, and outputting a power load prediction value of a target time step. According to the method, the problems of information loss, difficulty in high-dimensional feature extraction and the like of a traditional short-term load prediction model in complex time sequence modeling are effectively solved, the precision and the stability of short-term load prediction are remarkably improved, and the method has relatively high practical value and popularization potential.

The embodiment of the invention provides a multi-modal knowledge graph construction method in cross-media retrieval. The method comprises the steps that extracted multi-modal features are mapped to a multi-modal feature space through a linear transformation layer; in the multi-modal feature space, the intra-modal attention weight of each modal feature is calculated according to a self-attention mechanism, the cross-modal attention weight of different modal features is calculated according to a cross attention mechanism, the two weights are fused to obtain a final fusion weight, each modal feature is weighted and input into a graph attention network, and the multi-modal feature is obtained. Obtaining a multi-modal fusion graph structure; performing semantic analysis on each modal feature, matching with a preset multi-modal semantic knowledge base, determining potential semantic association, performing semantic alignment on the multi-modal fusion graph structure according to a preset graph matching algorithm and the potential semantic association to obtain a multi-modal knowledge graph, performing cross-modal data retrieval according to the multi-modal knowledge graph, and performing cross-modal data retrieval according to the multi-modal knowledge graph. The multi-modal data cross-media retrieval method and device can improve the efficiency and accuracy of multi-modal data cross-media retrieval.

The invention discloses an RGB data and event data fusion target tracking method based on visual Mama, relates to the technical field of computer vision, and solves the technical problem that efficient and accurate target tracking of RGB data and event data is difficult to realize. The method comprises the following steps: performing frame-level synchronization and conversion on an original RGB image of an RGB camera and an original event stream of an event camera to generate RGB input data and event input data; obtaining an RGB feature map and an event feature map through a feature extraction module of the Mamba network; performing linear transformation and deep convolution operation through an interaction module to obtain RGB features and event features; dynamically fusing the RGB features and the event features through a fusion module to obtain cross-modal fusion features; and the template features and the search features are aligned through an alignment module to generate an alignment feature graph, and target positioning and tracking are completed. According to the method, through efficient modal fusion and the state space model, the target tracking precision and robustness in a dynamic scene are remarkably improved.

The invention discloses a word embedding vector extraction method and system based on a large language model, and belongs to the field of natural language processing, and the word embedding vector extraction method based on the large language model comprises the following steps: S1, embedding a global context attention module, generating a Q / K / V vector through linear transformation, and calculating a global attention weight in a cross-position manner; s2, splicing coding features of adjacent layers, and performing gating fusion to generate a global context dynamic semantic state; s3, multi-head attention joint coding is carried out on the dynamic semantic state of the current layer and the global state; s4, performing average pooling to generate a global semantic vector, and calculating a dynamic attention weight; s5, performing weighted fusion on the dynamic weight and the global vector to generate an enhanced code; s6, outputting a final word vector by a GELU nonlinear transformation full-connection layer; the method has the beneficial effects that the global context semantic capture capability is enhanced, and the expression effect of the word embedding vector is improved.

The invention provides a cellular network flow space-time prediction method and system based on a hybrid neural network, and belongs to the technical field of intelligent communication. The method adopts a layered deep neural network architecture, and comprises a data embedding layer, a space-time coding layer, a feature fusion layer and an output layer. The data embedding layer maps a historical traffic sequence, cross-domain external data and metadata into high-dimensional features; the space-time coding layer is used for respectively fusing one-dimensional causal convolution and a Mama neural network to extract multi-scale time features and densely connecting convolution and a multi-head attention mechanism to capture multi-scale space features through time and space modeling branches; the feature fusion layer realizes adaptive weighted fusion of spatial-temporal features, cross-domain features and metadata features by using a gating fusion mechanism; and the output layer performs linear transformation on the fusion features to generate a final prediction result. According to the method, the spatial-temporal dynamic capture of the service traffic is accurate, the prediction curve is highly fit with the true value, and the accurate prediction of the multi-service traffic of the cellular network is realized.

A method and system for optimizing compute runtime and memory footprint of a linear transformation process are provided. The method includes determining a set of optimal rotation parameters, wherein the optimal rotation parameters provide an optimal tradeoff between runtime compute resources and a memory footprint for a runtime execution of the linear transformation process; initializing the linear transformation process to run a boosting technique with the determined set of optimal rotation parameters, wherein the boosting technique, when executed at runtime as part of the linear transformation process, performs at least one iteration that yields rotated ciphertexts, and wherein the at least one iteration is based on the determined set optimal rotation parameters and at least one key switching key (KSK); and loading the initialized linear transformation process to an internal memory of a hardware accelerator.

The invention discloses a dynamic feature retrieval generation and management method based on a cross attention mechanism, which belongs to the technical field of natural language processing, and comprises the following steps: step 1, converting knowledge base document fragments into atomic knowledge units, each atomic knowledge unit comprising question and answer pairs, codes as key value pairs, and adding dynamic priority weights; self-attention query is replaced with a double-channel query structure, one channel is used for cross attention, a cross attention query vector is generated through linear transformation, and key value pairs of atomic knowledge units are used; and step 3, training a cross attention adapter, freezing the weight of the language model, optimizing parameters of the adapter, and dynamically adjusting a loss function by using pre-judgment parameters based on input sequence context complexity. By means of the method, deep correlation description of user input and knowledge fragments can be achieved, semantic ambiguity is eliminated, knowledge injection and context information are balanced, distortion is avoided, and the strict requirement for semantic precision in the professional field is met.

The invention provides a fault detection method based on the combination of a Transform model of VMD and a BiGRU, and the method comprises the steps: firstly collecting voltage and current signals, and carrying out the preprocessing of the voltage and current signals; then, decomposing the preprocessed signal into a plurality of modal components by using VMD, and performing normalized coding to form a feature vector; the feature vectors are then input into a Transform model, deep features are extracted, and residual connection and layer normalization processing are carried out; the output of the Transform model is input into the BiGRU network, time sequence change characteristics are captured, and a characteristic vector with a fixed length is output; and finally, inputting the output of the BiGRU network into a softmax classifier, outputting probability distribution through linear transformation and a softmax function, and selecting a fault type with the maximum probability as a final result. And if the fault type is not a normal state, generating early warning information and giving an alarm. The method has the advantages of high-precision fault detection, strong robustness, strong adaptability and good real-time performance, and can effectively improve the accuracy and efficiency of fault diagnosis of the power system.

The invention discloses an acute pancreatitis complication assessment method based on artificial intelligence, and belongs to the technical field of medical information, and the method specifically comprises the steps: firstly, obtaining a clinical data set containing real-time clinical indexes and basic disease historical records; performing time sequence analysis on the historical records of the basic diseases, extracting long-term influence characteristics of the historical records of the basic diseases and generating basic disease influence factors; carrying out standardization processing on the real-time clinical indexes and the basic disease influence factors, and generating a comprehensive feature vector after calculating association weights among features; inputting the vector into a trained artificial intelligence evaluation model, and outputting a complication risk probability through layer-by-layer nonlinear transformation; and finally, mapping the risk probability value into a risk level, and integrating patient information to generate a structured risk assessment report. And an acute pancreatitis complication evaluation scheme integrating the acute stage index and the chronic basic disease influence is established.

Disclosed in the present invention is a deep learning-based power distribution network load prediction method, comprising: acquiring regional load data and renewable energy power generation data to form a data set, and preprocessing the data set to obtain a first data set; using a convolutional neural network to extract a time series feature in the first data set, and converting the time series feature into a data form of a deep learning model by means of an embedding layer to obtain one-dimensional time series data; performing fast Fourier transform on the one-dimensional time series data to obtain a frequency curve, extracting amplitude values on the frequency curve to calculate corresponding periods, and selecting the corresponding periods to slice the one-dimensional time series data and form same into two-dimensional matrixes; using a two-dimensional convolutional network to perform feature extraction, reshaping the two-dimensional matrixes that have undergone feature extraction into one-dimensional arrays, and performing adaptive fusion on the one-dimensional arrays to obtain a first time series feature; and inputting the first time series feature into a fully connected layer for weight calculation and linear transformation to obtain a power distribution network load prediction result, thereby improving the stability and reliability of electric power supply.

The invention discloses a model training method and device based on a reattention mechanism. In the scheme, an embedded vector sequence is input into a multi-head attention layer of a pre-training language model to extract global semantic features, and a global context vector is generated based on the global semantic features; based on a sparse Softmax function and the global context vector, a sparse gating network calculates dynamic weights corresponding to multiple attention heads, and constructs an attention weight vector; performing weighted fusion on the context vectors output by the attention heads and the corresponding attention weight vectors by a multi-head attention layer, and performing linear transformation on the fused context representation based on a fixed weight matrix to obtain a self-attention value; and adjusting parameters of the pre-training language model according to the self-attention value through a preset loss function to obtain a target pre-training language model. According to the method, the sparse gating mechanism is introduced to dynamically adjust the weight of the multiple attention heads, and the model prediction precision is remarkably improved.

The invention discloses an attention mechanism optimization method and device, a storage medium and a processor. In the scheme, rotation position coding is carried out on a Query vector and a Key vector which are obtained through linear transformation of an input sequence, and an original attention value is obtained; based on the relative distance of each position in the input sequence, constructing a bias item; the bias item comprises a sine bias item; and carrying out dynamic fusion on the original attention value and the offset item, and outputting an optimized attention value. Compared with the position coding technology in the prior art, the method has the obvious advantages that the performance of the model is obviously reduced when the model is used for processing the super-long sequence, and the extrapolation is insufficient.

The invention discloses a lithium ion battery capacity inflection point prediction method and system based on a multi-parameter data fusion decision. The method comprises the following steps: collecting multi-parameter data of a lithium battery and preprocessing the multi-parameter data; constructing an inflection point prediction model based on deep learning, and extracting time sequence data characteristics of current, voltage and temperature; based on an attention-enhanced graph convolutional neural network AGCN, an attention mechanism is introduced into a graph convolutional neural network GCN to dynamically learn the association weight of a multi-parameter feature matrix, and multi-parameter data fusion features are obtained; dynamic decision making is carried out on the battery multi-parameter data fusion features, linear transformation is carried out on a dynamic decision making result to obtain a predicted value of an inflection point, and construction of an inflection point prediction model is completed; carrying out training optimization on the whole model, and predicting the residual cycle period of the battery to the inflection point; according to the method, inflection point high-precision prediction of any stage of the battery can be realized by depending on relatively short cycle period data.

The invention discloses a model reasoning method and device. The method comprises the following steps: preprocessing an input text to convert the input text into a semantic vector sequence; calculating a compression key and a compression value matrix corresponding to the semantic vector sequence through dimension reduction mapping and key-value mapping, and storing the compression key and the compression value matrix into a preset cache space; in response to the fact that the loop end condition is not met, the following steps are executed in a loop mode: based on the target semantic vector and first linear transformation of a compression key and a compression value matrix stored in a preset cache space, current attention representation is calculated; generating a new semantic vector based on the current attention representation and updating a semantic vector sequence; and through dimension reduction mapping and key-value mapping, calculating a compression key vector and a compression value vector corresponding to the new semantic vector, and updating a compression key matrix and a compression value matrix. According to the model reasoning method, the reasoning efficiency can be remarkably improved while the model reasoning effect and performance are ensured.

The invention provides a building identification method and system based on three-dimensional point cloud, and particularly relates to the technical field of computer vision and three-dimensional target identification, and the method comprises the steps: carrying out the undersampling, oversampling and data enhancement preprocessing of inputted building roof point cloud data, and carrying out the T-net network space alignment to output the aligned data. Then, an NEWPCT model is obtained by improving a PCT model, aligned data are input into the NEWPCT model, a point cloud feature matrix is generated through a linear coding layer, query, key and value matrixes are obtained through linear transformation, multi-head attention output is calculated by introducing an offset matrix, intermediate correlation features are obtained after splicing and fusion, and a global feature vector is generated through global maximum pooling; and finally, inputting the vector into a classifier, and outputting a building roof type, and the method solves the technical problems of geometric transformation sensitivity and local feature loss while improving the precision and robustness of three-dimensional point cloud building identification, thereby effectively improving the identification precision and robustness.

The invention provides a photovoltaic prediction method, which comprises the following steps: data preprocessing: aligning time sequences of historical power generation data and meteorological data through a time sequence warping strategy, constructing an equipment health index, and inputting the equipment health index into an input layer; designing a space-time embedding layer, and performing space-time coding on data transmitted by the input layer and all meteorological data branches; defining a neural network module, designing a local-global attention layer, designing a network layer, and injecting meteorological condition constraints through a physical regularization item; a joint attention fusion layer is designed, and key features are effectively integrated; an output layer is designed, and feature integration, linear transformation, activation function setting, physical regularization and final photovoltaic power prediction generation and output are completed; and offline prediction is realized through edge optimization. The invention provides a photovoltaic intelligent prediction method fusing time-space sparse attention and a time sequence neural network, and solves the problems of insufficient data isomerism, calculation efficiency, physical interpretability, dynamic environment adaptability and the like in the prior art.

The invention discloses a space image generation method and system based on visible light and thermal imaging, and relates to the technical field of image generation, and the method comprises the steps: obtaining thermal imaging image data, visible light gray data, depth map data and event camera data as collection data, and carrying out the coordinate system unification and space alignment; patch segmentation is carried out on the collected data, and position codes are added; according to the method, the global attention distribution is calculated by adopting ViT, so that each Patch can pay attention to all other Patches, it is ensured that the characteristics of cross-modal data are not only influenced by local neighborhoods, but the characteristics of the cross-modal data are combined with the information of the whole image, and a comprehensive characteristic matrix is calculated, so that the cross-modal data are obtained. The use of linear transformation can ensure that the final fusion feature comprises global information of ViT calculation, and the spatial attention weight obtained through calculation directly acts on the channel enhancement feature matrix, so that the expression of the spatial feature is further optimized.

The invention discloses an infrared and visible light image data association method based on multi-view clustering, graph construction is completed by aiming at obtained data of different data sources, nodes represent data entities, and edges represent similarities or relationships among the entities. By means of a graph convolution network, input multi-view data features and a structure graph are mapped step by step through a series of nonlinear transformation, and features in a feature graph are extracted. After feature representation of data is independently learned from each view angle, the features are fused to obtain global feature representation, and meanwhile, features of similar samples in other different view angles are integrated to learn a common space. In addition, the multi-view clustering is guided and compared by using the pseudo labels, so that the multi-view data is effectively processed, and the accuracy and efficiency of association are improved.

The invention discloses a cable fault detection method and system, and relates to the technical field of power system monitoring and fault diagnosis, and the method comprises the steps: obtaining cable signal data, carrying out the standardization processing, converting the cable signal data into a matrix, carrying out the parallel calculation of attention heads, carrying out the feature extraction of the cable signal data, and carrying out the splicing and linear transformation of the output of the attention heads, the method comprises the following steps of: obtaining fused feature representation, introducing position codes into a self-attention mechanism, processing the structure and dynamic change of a sequence by utilizing the position codes, detecting and analyzing cable fault signals by utilizing extracted feature information, optimizing model parameters through detection and training results, and distinguishing the fault signals from noise. According to the method, position coding and a multi-head self-attention mechanism are combined, so that the model not only can capture the long-range dependency relationship, but also can accurately locate the time sequence characteristics of fault occurrence, and the accuracy of fault detection is improved.

The invention provides a multi-modal data classification method and system, computer equipment and a storage medium, and the method comprises the steps: receiving multi-modal data through edge equipment, and carrying out the preprocessing of the multi-modal data; aligning to the same latitude through linear transformation or a projection layer; a comprehensive information representation vector is generated through fusion of an attention mechanism or a Transform architecture; quantifying the multi-modal large model, and deploying the multi-modal large model in edge equipment; sending the comprehensive information representation vector to a multi-modal large model for reasoning, and processing the comprehensive information representation vector through a multi-layer Transform architecture; and generating a classification result according to task requirements. According to the method, the real-time performance, the accuracy and the resource utilization efficiency of the system are improved through localized deployment on the edge equipment, sensitive data can be processed locally, data privacy and safety are guaranteed, cross-modal feature extraction and alignment are achieved, and the recognition capability in a complex scene is improved. Dependence on large-scale annotation data is reduced, and adaptability is improved.

The invention discloses a ship route planning method and system in a polar region sea ice environment and a program product. The ship route planning method comprises the steps of preprocessing satellite remote sensing radiation intensity data, performing image reconstruction of inter-ice water channel detection through an improved Vision Transform model, planning and visualizing a ship route and the like. The deep features of the image blocks are extracted through a Transformer encoder which comprises a multi-head self-attention mechanism and is processed by a multi-layer perceptron; and the Transform encoder firstly performs layer normalization on the input, and then performs multi-head attention mechanism and multiple linear transformation and regularization processing. And realizing path planning in an inter-ice water channel environment by fusing a dynamic planning cost function through a fast marching method. Compared with a traditional algorithm, the method has the advantages that the calculation precision is higher in the same scene, the calculation efficiency is greatly improved, and the planning result obtained after multiple costs are comprehensively considered is given instead of pursuing the shortest distance.

The invention belongs to the technical field of time series prediction, and particularly relates to a time series prediction method based on variable decomposition and convolution attention modeling. Firstly, variable decomposition is carried out on historical time sequence data of the electrical transformation temperature, decomposition of trend and seasonal components is carried out on the historical time sequence data by utilizing learnable one-dimensional convolution operation, and the problem that a traditional decomposition method is insufficient in flexibility is solved. In seasonal component modeling, simple and efficient linear transformation is adopted, and feature extraction is carried out by learning a periodic mode of seasonal change. And on the aspect of trend component modeling, a convolution attention structure is adopted to capture a nonlinear relationship in a long-term trend, and meanwhile, the calculation efficiency of the model is ensured. And finally, fusing the features of the seasonal component and the trend component, and further improving the prediction precision of the model through a residual learning module.

The invention discloses a large model dynamic batch processing method based on sequence splicing. The method comprises the following steps: receiving input sequences of a plurality of users in a batch; converting the input sequence into a corresponding token sequence; carrying out heterogeneous splicing on all token sequences along a sequence length dimension to form a unified joint token; the spliced joint tokens pass through a normalization layer, standardization operation is executed on the joint tokens, and data distribution is unified; carrying out linear projection on the joint token through a shared linear transformation layer to generate a joint query vector, a joint key vector and a joint value vector, and splitting the joint query vector, the joint key vector and the joint value vector into sub-vector groups corresponding to each user; executing multi-head attention calculation to obtain attention output of the user; and carrying out linear transformation on the attention output, and inputting a transformed result into a shared MLP to carry out nonlinear feature extraction and enhancement so as to obtain a final output corresponding to each user. According to the method, the problems of efficiency bottleneck and resource consumption when a large model processes mass data are effectively solved.

The invention provides a coupling space-spectrum conversion operator transformer multi-physics field distribution prediction method and system, and the method comprises the steps: mapping the initial condition distribution of multi-physics field distribution to a potential space of a unified dimension through independent linear transformation, generating an initial potential feature vector, and carrying out the prediction of the initial potential feature vector; performing spatial expansion on the cross-field coupling state of the multi-physical field distribution in combination with the GRU, splicing the obtained current global cross-field coupling state and the current potential feature input, and obtaining the potential feature input of the next layer of the GRU through a space-spectrum conversion operator layer; and inputting the potential features of all the current physical field distribution and the global cross-field coupling state into a GRU unit, updating the cross-field coupling state including cross-physical field interaction, minimizing weighted error optimization parameters of a physical field distribution prediction result, inversely mapping the reconstructed final potential features to a target space, and generating the prediction result of the physical field distribution. The method has higher generalization ability, the modeling precision is improved, and the calculation complexity is reduced.

The invention provides an improved YOLOv8 underwater image target detection method, device, medium and program, a fine-grained feature extraction module is arranged to replace a C2f module on the basis of YOLOv8, the fine-grained feature extraction module comprises a visual state space model and a local feature extraction module which are arranged in parallel, feature distribution is adjusted through linear transformation in the visual state space model, and the local feature extraction module is used for extracting local features in the visual state space model. A multi-scale space context is extracted in combination with depth separable convolution and a SiLU activation function; in the local feature extraction module, detail information of a target is focused through a convolution kernel channel attention mechanism, and noise interference is suppressed; the two outputs are subjected to element-by-element addition fusion and then enter a multi-scale cross attention fusion module, local and global features of different scales are fused in the multi-scale cross attention fusion module through dynamic weighting, and fine-grained features are output. The improved YOLOv8 is used for underwater target detection, and the identification capability of a fuzzy target and a complex background in underwater image target detection can be remarkably improved.

The invention discloses a route planning method and system, and relates to the technical field of unmanned aerial vehicles, and the method comprises the steps: calculating a cross-modal attention weight based on a feature vector, combining the attention weight with the feature vector to obtain a weighted feature vector, calculating an attention score based on the weighted feature vector, generating an integrated feature based on the attention score through linear transformation, and carrying out the calculation of the integrated feature. And integrating the features and combining the communication topology, and inputting the features into a Transform architecture to generate 3D environment representation. A cross-modal attention mechanism is utilized, attention weight dynamic modulation feature vector contribution of each modal is calculated, the environmental perception accuracy in a complex environment is improved, feature vectors of neighbor unmanned aerial vehicles are aggregated through a distributed communication topology construction method in combination with a multi-head attention mechanism, and the multi-modal attention mechanism is established. The group stability is still kept when communication is interrupted or obstacles change, and the environmental adaptability, the cooperation efficiency and the navigation precision of the unmanned aerial vehicle group in a complex environment are improved.

The invention provides an urban traffic flow prediction method and system, and relates to the technical field of intelligent traffic systems, and the method comprises the steps: receiving traffic data, and carrying out the linear transformation processing through a full connection layer; the processed traffic data are input into multiple layers of time-space modules of the same structure for feature extraction, each layer of time-space module is composed of a time convolution module and a mixed time-varying graph module, and time features output by the time convolution module and spatial features output by the mixed time-varying graph module are spliced to form output of the time-space modules; parameterized learning is carried out on the mixed time-varying graph module; performing jump connection on the outputs of all the space-time modules to generate fused space-time features; and processing the fused spatial-temporal characteristics through a ReLU activation function, and transmitting a processing result to a full connection layer to obtain a final prediction result. According to the method, the urban traffic condition and the change trend can be accurately judged, and effective decision support is provided for urban planning and traffic management.