6063results about How to "Easy to integrate" patented technology

The invention provides a vehicle collision risk early warning method, system and device and a medium, and belongs to the technical field of vehicle safety control. The method comprises the steps that surrounding environment information of a vehicle is collected in real time through a vehicle built-in sensor and a GPS module; a multi-sensor fusion device technology is used to carry out comprehensive processing on surrounding environment information of a vehicle, and an environment perception model is generated after data integration; based on the environment perception model, target identification is carried out by using a computer vision technology based on a convolutional neural network so as to identify travelers, vehicles, traffic signs and obstacles; performing behavior prediction based on a deep learning model to predict a behavior track of a front vehicle or pedestrian; evaluating a potential collision risk in the current scene in combination with the target recognition result and the behavior prediction result; when a potential collision risk is detected, an early warning signal is sent to a driver, and when the driver does not take corresponding measures, active safety measures are automatically triggered to avoid collision or reduce accident damage.

The invention discloses an unmanned ship multi-mode perception and decision support method and system based on fuzzy logic and a rule engine, and the method comprises the steps: obtaining multi-source sensor data, carrying out the standardization processing, calculating a dynamic weight coefficient based on information entropy, and carrying out the data fusion; mapping the fusion data to a feature space, analyzing feature correlation, and evaluating an environmental threat degree; performing fuzzy partitioning on the feature space and generating an initial rule, and optimizing a rule set through information gain; a fuzzy inference system is constructed and cooperatively operated with a rule engine, and collaborative decision parameters are optimized; and performing multi-level risk assessment and generating a level decision, and optimizing a decision instruction through reinforcement learning. According to the method, the sensing accuracy and decision reliability of the unmanned ship in a complex sea condition environment are improved through multi-modal data adaptive fusion and collaborative decision of the fuzzy logic and the rule engine, and the method has good engineering application value.

The invention relates to the technical field of sleep aiding, in particular to a method and a system for extracting feature information of a sleep state monitoring model. The method comprises the following steps: carrying out multi-mode physiological signal acquisition on a detected object to obtain original sleep monitoring data; performing noise removal and signal enhancement processing on the original sleep monitoring data, and performing signal segmentation to obtain multi-channel sleep signal fragment data; performing feature extraction based on electroencephalogram, eye movement diagram, electromyogram, electrocardiogram and accelerometer signals on the multi-channel sleep signal fragment data to obtain multi-dimensional feature data; and performing ultrasonic feature and acoustic feature extraction on the multichannel sleep signal fragment data to generate acoustic feature data. According to the method, dynamic modeling and trend prediction are carried out on the conversion process of the sleep state, potential sleep disorder events can be accurately recognized, influence evaluation is carried out on the potential sleep disorder events through deep learning, and support is provided for personalized sleep diagnosis.

The invention relates to a traffic flow prediction optimization method based on an intelligent optimization algorithm, which is applied to the technical field of traffic flow prediction. The system comprises a multi-modal data acquisition and fusion module, a hybrid deep learning prediction module, an intelligent parameter optimization module, an integrated learning module, a multi-scale error correction module, a prediction result analysis and visualization module, a distributed learning and privacy protection module and the like. Wherein the hybrid deep learning prediction module adopts an attention mechanism to fuse models such as CNN, Transform and LSTM, and introduces an adaptive error correction mechanism, so that the prediction precision is remarkably improved; the intelligent parameter optimization module accelerates the model search efficiency by using technologies such as quantum computing and swarm intelligence optimization; the integrated learning module and the adversarial training strategy enhance the robustness and generalization of the model; and the multi-scale error correction module adopts a time sequence decomposition and self-adaptive online learning method to improve the accuracy of long-term and short-term prediction.

The invention discloses an emotion-enhanced digital human driving and presenting system and method, and belongs to the technical field of computers.The system comprises an audio decoupling module, a potential diffusion model module, a human motion prior module, a training module and a rendered image generation module; predicting and reconstructing the facial expression and gesture action sequence to obtain a final action sequence; and generating a neural rendering image based on the final action sequence. According to the method, through voice input, emotion and style features in voice are captured, a cross attention feature fusion mechanism is introduced to enhance expression of emotion and personal style features, a voice-driven gesture generation task is expanded to a facial expression and gesture action synchronous generation task, the integrity of generated digital human actions is realized, and the user experience is improved. The emotional expressive force of facial expressions and gestures of the digital human is greatly improved.

The invention provides a multi-modal digital twinborn scene building method and device based on image semantic fusion, and relates to the technical field of data processing and digital twinborn scenes. The method comprises the steps of obtaining an image data set and a text data set of a building construction site, and performing preprocessing; inputting the preprocessed image data set and text data set into a natural language processing model to obtain semantic description auxiliary data; inputting the preprocessed image data set into a target detection algorithm to obtain target extraction image data containing a target detection frame; fusing the output results of the two targets to obtain a fusion box of each target; then, a perspective projection algorithm is adopted to calculate a coordinate position corresponding to each target in the BIM, and three-dimensional world coordinates are obtained; and inputting the three-dimensional world coordinates into the BIM by adopting Dynamo to realize the building and real-time updating of the multi-modal digital twinborn scene. According to the method, the accuracy and robustness of scene recognition are remarkably improved, and the defects of a traditional method in the aspect of multi-modal data processing are overcome.

The invention discloses an enterprise-level knowledge management system based on a large language model. The enterprise-level knowledge management system comprises a knowledge storage module, a knowledge analysis module and a knowledge application module, the knowledge storage module is responsible for managing and storing knowledge from different sources, supporting uploading, updating, deleting and sharing of electronic documents and multimedia documents, and is provided with authority control; the knowledge analysis module is used for carrying out deep understanding and structured processing on text and multimedia contents through a special analyzer by utilizing an advanced large language model technology; the knowledge application module provides intelligent retrieval and intelligent question and answer functions and supports advanced applications such as behavior portrait analysis and standard process supervision. According to the method and the system, the acquisition, understanding and application efficiency of enterprise knowledge is remarkably improved by fusing a large language model technology and a traditional knowledge management method, an intelligent, automatic and safe knowledge management solution is provided for an enterprise, and value mining and innovative application of enterprise knowledge assets are effectively promoted.

The invention relates to the field of drug-target affinity prediction, in particular to a drug-target affinity prediction method based on a multi-scale mixed attention network. According to the method, global residue characteristics can be learned by protein pocket residues by utilizing a self-attention mechanism, so that the global characteristics of the protein are learned. In addition, a cross-modal feature fusion mechanism is utilized, protein and drug structural features are enhanced in sequence features, cross-modal feature fusion in entities is enhanced, meanwhile, a cross-entity interaction module is utilized to recognize key atoms of drug molecules or key residues of protein, and therefore the overall performance of the model is improved. Finally, multi-level protein feature extraction is further introduced to further extract protein features.

The invention discloses a target detection method and device based on cross attention multi-scale fusion and a medium, and relates to the field of target detection, and the method comprises the steps: obtaining a visible light image and an infrared image of a to-be-detected target, and carrying out the target detection through employing a trained cross attention multi-scale fusion detection network; wherein the cross attention multi-scale fusion detection network comprises a backbone network, a background sensing module, a cross attention fusion module and a detection head; the backbone network is used for extracting features of different scales; the background sensing module is used for predicting illumination and contrast; the cross attention fusion module is used for performing cross fusion on the features extracted by the backbone network by adopting differential attention and homogeneous attention according to the illumination and contrast predicted by the background sensing module to obtain a multi-modal fusion feature map; and the detection head is used for determining the position and category of the to-be-detected target according to the multi-modal fusion feature map. According to the invention, the accuracy of target detection is improved.

The invention discloses an Internet of Things equipment access protocol component development method, which is used for quickly developing an Internet of Things equipment access protocol analysis and processing component at an Internet of Things platform side, and comprises the following steps: S1, constructing a protocol analysis and processing general framework according to the protocol analysis and processing component of an Internet of Things platform; s2, abstracting a specific logic processing part of a protocol in the general framework into a method / function interface; s3, constructing a protocol expert AI knowledge base for data learning; s4, constructing an AI large model and a multi-agent processing flow, selecting a specified large model, configuring related parameters, extracting required parameter extraction / coding logic, and generating an interface implementation code; s5, integrating each generated interface implementation code with the universal framework; and S6, testing, adjusting and optimizing the integrated access protocol analysis and processing component. According to the method, the unified development template can be provided, so that the development technical threshold is reduced, and the development efficiency is greatly improved.

The invention belongs to the field of fault diagnosis, and particularly relates to a main shaft bending common characteristic diagnosis system based on a stacking integration method, and the system comprises the following modules: a sensor module which is used for collecting a vibration signal of a main shaft in real time; the data acquisition and processing module is used for converting an analog signal into a digital signal and preprocessing the signal acquired by the sensor; the feature extraction module is used for extracting features from the preprocessed vibration signals; the machine learning diagnosis module analyzes and classifies the extracted features by using stack integration based on a plurality of trained machine learning models, and judges the health state of the main shaft; and the output module is used for outputting the diagnosis result and sending out an alarm signal when abnormality is detected. Real-time monitoring and automatic diagnosis of the main shaft bending fault are achieved, compared with a traditional method depending on expert experience and manual detection, the fault detection efficiency and accuracy can be greatly improved, and misjudgment and missed judgment risks caused by human factors are reduced.

The invention relates to the technical field of biological sewage treatment, in particular to a device and a method for improving the autotrophic nitrogen removal performance of an MABR (Membrane Ammonia Baffled Reactor). Coupling of partial nitrosation reaction and anaerobic ammonia oxidation reaction is completed; through a circular reaction zone and a membrane reaction zone in the reaction tank, nitrate nitrogen generated by anaerobic ammonia oxidation and excessive nitrite nitrogen during instability regulation are circularly removed, and the purpose of improving the total nitrogen removal effect of the reactor is achieved; a proper amount of a sodium nitrite solution is added at proper time, the concentration of free nitrous acid in a mixed solution of the reactor is increased, and the intermittent proportion of MABR intermittent aeration is synchronously regulated and controlled, so that the activity of nitrite oxidizing bacteria is synergistically inhibited by low dissolved oxygen and high free nitrous acid, and the unstable short-cut nitrification reaction is recovered again; the autotrophic nitrogen removal performance of the reactor is improved.

The invention discloses a multi-mode adaptive fusion navigation positioning method and system in a satellite navigation denial environment, the system adopts GNSS / IMU / visual sensors, and the method comprises the following steps: receiving data of the three sensors and completing modeling; initializing the three sensors; judging the strength of the GNSS signal by utilizing chi-square test; optimization variables are set, a residual matrix is constructed, and nonlinear optimization is carried out; setting a GNSS trust factor when the GNSS signal is weak or denial, and calculating a weight; and weighting and fusing sensor data, outputting optimal state estimation of the system, and realizing continuous navigation and positioning. According to the method, a self-adaptive weight adjustment mechanism is established, GNSS trust factors are introduced, and the weights of multi-sensor data are adjusted in a self-adaptive manner, so that the positioning difficulty under the conditions that the GNSS is subjected to deception interference, suppression interference, building blocking and the like can be overcome, and continuous navigation positioning of an unmanned system (such as a robot, an unmanned vehicle, an unmanned aerial vehicle, an unmanned ship, an unmanned underwater vehicle and the like) is realized.

The invention relates to the field of image segmentation, in particular to a multi-modal nuclear medicine image segmentation method and system and a storage medium. Comprising the steps that image type classification is carried out on multi-modal medical examination images, focus area positioning is carried out, and CT (computed tomography) focus images and PET (positron emission tomography) focus images are obtained respectively; carrying out lesion geometric mutation form prediction on the CT fault lesion image, and carrying out multi-modal image fusion boundary correction on the CT fault lesion image and the PET lesion image to obtain multi-modal lesion image fusion boundary correction data; according to the multi-modal lesion image fusion boundary correction data, performing multi-modal lesion region segmentation combination optimization on the CT image and the PET image to obtain a lesion region segmentation combination optimization strategy; and carrying out image segmentation model construction on the lesion region segmentation combination optimization strategy based on a strategy gradient algorithm to obtain a lesion image segmentation model. According to the method, the image segmentation technology is optimized, so that the image segmentation technology is more perfect.

The invention discloses a corrugated pipe inner wall multi-type flaw detection method based on deep learning, and the method comprises the following steps: S1, collecting an initial corrugated pipe inner wall image and corrugated pipe inner wall images in different illumination environments, and generating an original image; s2, preprocessing the original image to generate a preprocessed image; s3, extracting surface geometric overall features of the inner wall of the corrugated pipe from the preprocessed image through a pre-trained ResNet101 network; s4, inputting the preprocessed image and the surface geometric overall features into an improved StyleGAN3 network to generate an enhanced image; s5, inputting the enhanced image into the multi-scale adaptive deep network, and outputting a defect detection result; and S6, performing post-processing on the flaw detection result, and outputting a final flaw detection result. According to the method, deep learning and geometric characteristic embedding technologies are adopted, so that the defects of the inner wall of the corrugated pipe are accurately detected, and the method has the advantages of high precision, high robustness and comprehensive adaptability.

The invention discloses an LED large screen automatic repair and fault-tolerant display system and method, and relates to the technical field of LED display. The method comprises the steps that a sensor network and a high-definition camera collect data in real time; when an abnormal area is found, an intelligent diagnosis algorithm carries out comprehensive judgment according to sensor data and an image processing result, and the position and the type of a fault lamp bead are determined; starting an automatic repair process; redundant pixels are started to carry out hardware restoration; the dynamic reconstruction algorithm automatically adjusts the arrangement and brightness of redundant pixels, so that the redundant pixels replace fault lamp beads to participate in display; the system automatically adjusts the resolution and the display mode of the large screen according to the number and the distribution of the fault lamp beads. The problem that the display effect of an existing LED large screen is reduced when part of LED lamp beads are damaged is solved, it is ensured that the large screen can still maintain the good display effect under the fault condition through an innovative automatic repair and fault-tolerant mechanism, and the reliability of the system and the user experience are improved.

The invention discloses an image generation method and system based on diffusion model adaptive reasoning. The method comprises the following steps: constructing a next noise intensity prediction module TPM; improving an original diffusion model, and adding a TPM; the improved diffusion model is trained by using a reinforcement learning method, the whole denoising process is expanded for multiple times, the next time step is predicted in each iteration, an award is calculated according to the quality of a finally generated image and the number of steps, and TPM parameters are updated by using a PPO loss function; in the actual reasoning process, noise is randomly sampled from Gaussian noise and input into the trained diffusion model, the diffusion model is used for predicting a denoising result, meanwhile, the TPM is used for outputting distribution of time steps based on next denoising, and a distribution mode is used as the next time step used in actual reasoning; and when the predicted time step is smaller than a set threshold value, a final image generation result is obtained based on model output. According to the method, the image generation process can be dynamically adjusted, and a reasoning result with both efficiency and quality is realized.

The invention discloses a river pollution tracing method and system based on underground water quality pollution monitoring, and relates to the technical field of river pollution tracing. According to the river pollution tracing method based on underground water quality pollution monitoring, the real-time concentration value of each pollutant in underground water is obtained in real time and analyzed to obtain the underground water pollution real-time evaluation index; according to the method, a plurality of abnormal measurement points with abnormal concentration in a set area are identified, and the traceability position coordinate of each pollutant with abnormal concentration in underground water in a river is analyzed, so that the real-time evaluation index of underground water pollution can be continuously calculated by acquiring the pollutant concentration data of each measurement point in real time; and whether the pollutant concentration exceeds the preset range or not is judged in time, so that the defects of hysteresis and untimely data updating of traditional water quality monitoring are overcome, dynamic monitoring of the pollutant concentration can be realized, and quick response when the pollutant is abnormally increased is ensured.

The invention relates to a wheel type double-arm humanoid robot motion track planning and obstacle avoidance method. The method comprises the steps that a robot system is started for self-inspection; the first sensor obtains environment information and constructs a real-time three-dimensional point cloud obstacle information graph; the second sensor obtains chassis state information and mechanical arm state information; a target task is set, and a moving path of a chassis and a moving path of a mechanical arm are planned based on the state information of the target task; and the system controls the chassis to move according to the planned moving path through the cooperative control model, and the mechanical arm moves according to the planned moving track. Through construction and real-time updating of the real-time three-dimensional point cloud obstacle information graph, the robot can effectively recognize and avoid obstacles, the risk of collision with the surrounding environment is reduced, meanwhile, the robot can adapt to the dynamically changing environment, path planning is rapidly updated through the D * Lite algorithm, and the path planning efficiency is improved. And the path can be adjusted in time when the obstacle moves or a new obstacle appears.

The invention belongs to the technical field of computer vision, provides a real-time semantic perception system running on equipment, performs real-time instance segmentation and semantic mapping on a working environment, and provides a perception method based on lightweight real-time instance segmentation and semantic mapping. In the first part, firstly, a color image containing color and texture information is used for object classification and bounding box regression; cutting the original depth image into a depth image with an accurate geometric edge, and inputting the depth image into the truncation network to generate a mask of the instance; a second part: (1) calculating the attitude and size of a target object in the view of the camera through principal component analysis; (2) obtaining the category of the object in the view obtained by segmentation; (3) creating a point cloud of the depth image projection of the target object in a map; and then cross-frame tracking and fusion are carried out by using data association to realize the purpose of sensing. The method is mainly applied to automatic sensing occasions.

The invention provides a sewage treatment operation cloud platform based on Internet of Things and GIS, and the platform is characterized in that a data collection layer is used for obtaining user water consumption data and sewage pipe network data, and distributing all the data to each edge calculation node; the data storage layer is used for temporarily storing the data preprocessed by the edge computing node into a high-frequency storage chain, aggregating to obtain sewage pipe network comprehensive data, and permanently storing the sewage pipe network comprehensive data into a low-frequency storage chain; the data analysis layer is used for extracting sewage pipe network comprehensive data in the low-frequency storage chain, constructing a multi-dimensional dynamic GIS model by utilizing a GIS system, analyzing and predicting the multi-dimensional dynamic GIS model through a sewage treatment rectification analysis model, and generating a sewage treatment rectification plan of the sewage pipe network according to an analysis and prediction result; and the application service layer is used for acquiring all the sewage treatment and rectification plans and distributing all the sewage treatment and rectification plans to a management client held by a sewage pipe network manager. The sewage treatment device has the effect of efficiently and intelligently realizing sewage treatment.

The invention discloses an infrared and visible light image fusion method and system based on high and low frequency separation enhancement, and relates to the technical field of image processing. The method comprises the following steps: acquiring an infrared image and a visible light image to be fused; performing image fusion on the to-be-fused infrared image and the to-be-fused visible light image by using the image fusion network to obtain a fused image; wherein the image fusion step comprises the steps of extracting shallow layer features of an infrared image and a visible light image, processing the shallow layer features by using a feature separation algorithm to obtain high-frequency features and low-frequency features, performing feature enhancement on the high-frequency features by using a feature enhancement algorithm, and fusing the enhanced high-frequency features and low-frequency features to obtain a fused image. According to the method, the high and low frequency features are subjected to feature separation, the high frequency features are subjected to feature enhancement by using a self-attention mechanism, and then the features are subjected to cross fusion, so that important information such as texture details is highlighted, and the image fusion quality is improved.

The invention discloses an intelligent question answering system and method based on question decomposition and community semantic search. According to the method, firstly, a complex question is decomposed into a plurality of single-hop sub-questions through an original loop question decomposition technology, then information needed for answering each sub-question is obtained based on communities in a vector retrieval knowledge graph, and the sub-questions are answered by using a large language model. And finally, generating a final question and answer for the original complex question by combining the LLM with the answers of all the sub-questions. Compared with other methods in the industry, the method has the advantages that the information integration capability is remarkably improved, information fragmentation is avoided through community-level search and abstract generation, and high-quality and logically consistent answers are provided. When a complex query is processed, the effect of the method is superior to that of a general method in the industry and is improved by 29% at most; meanwhile, on the basis of ensuring a better question and answer effect, the efficiency is remarkably improved, and on the premise that the effect exceeds that of an existing optimal method GraphRAG, the token consumption is only 3.2% of that of the existing optimal method GraphRAG.

The invention discloses a road surface detection method based on artificial intelligence and a road inspection robot, and the method employs a self-designed RCDIT network model, proposes an implicit expression method and a multi-head cross attention mechanism in the network model, guarantees the expression integrity and continuity of image blocks, and improves the detection precision. Complex interaction of image blocks and position information can be effectively processed, and the integration capability and information relevance of the model to multi-modal data are enhanced. In addition, the introduced position feedforward network further improves the abstract ability of feature representation, and is helpful for more effectively processing complex features and improving the expressive force of the model. And the RCDIT network model is combined with the road detection robot, so that the crack defects of the road surface and the road can be accurately and quickly identified and segmented, and the reliability and the accuracy of detection are greatly improved. The road detection robot can work in a 24 / 7 all-weather mode and is not limited by time and environment, manpower resources are effectively saved, and continuous monitoring on the road surface can be achieved.

The invention discloses a dual-mode communication signal identification method based on deep learning, relates to the technical field of communication signal processing, and aims to solve the problems that a simple neural network structure is generally adopted in a traditional deep learning algorithm, the attention of a model to important features is insufficient, gradient disappearance is likely to occur and the like. The method comprises the following steps: S1, signal acquisition and preprocessing are carried out; s1.1, receiving a signal; receiving a dual-mode communication signal from the intelligent traffic communication system; in an intelligent traffic communication scene, communication signals come from vehicle networking communication among vehicles, communication between the vehicles and road infrastructures, communication between a traffic management center and traffic nodes and the like; s1.2, carrying out adaptive sampling; an advanced self-adaptive sampling technology is used for sampling; the technology dynamically adjusts the sampling frequency and the number of sampling points according to the characteristics of signals. The method has the advantage of improving the processing capability and the recognition precision of the model on complex features.

The invention relates to the field of voltage regulation and control, in particular to a real-time voltage regulation method for a new energy automobile. Initializing a power distribution network voltage measurement module, and collecting voltage data of each node of the power distribution network; setting a voltage deviation threshold value, and judging whether the voltage is in a normal range or not; collected voltage is compared with a set voltage deviation threshold value, a result obtained after preliminary voltage regulation of an on-load voltage regulation transformer is compared with the set voltage deviation threshold value, and a result obtained after cooperative voltage regulation of an electric vehicle charging pile is compared with the set voltage deviation threshold value. According to a comparison result, tap adjustment of an on-load voltage regulation transformer, cooperative voltage regulation of an electric vehicle charging pile and voltage regulation participated by a distributed photovoltaic system are carried out in sequence; and formulating an optimization strategy based on historical data and results of three times of voltage regulation. By means of cooperative voltage regulation, optimal control, intelligent management and the like, the voltage stability is effectively improved, and the adaptability and flexibility of the system are enhanced.

The invention provides an innovative apple tree fruit nutritional ingredient dynamic monitoring and precise management system, and aims to solve the problem that the change of fruit nutritional ingredients cannot be mastered in real time in traditional orchard management. The system integrates spectral data, environmental data and image data, and comprehensively reflects the change of fruit nutrients and the relationship between the change and environmental factors through multi-source data fusion analysis. According to the invention, a standardized model between spectral data and nutritional ingredients is established, and a deep learning algorithm is introduced to improve the accuracy and efficiency of image recognition. The system can analyze fruit nutrients and environmental parameters in real time, send early warning information and generate personalized fertilization and health management suggestions. In addition, the system adopts a modular and extensible design, and is convenient to customize and integrate. The orchard management accuracy and efficiency can be remarkably improved, the yield and quality of fruits can be improved, the production cost is reduced, and the economic benefits are increased.

The invention relates to the technical field of target tracking in computer vision, and particularly discloses a target tracking method based on a gated attention mechanism and a space-time memory network, which mainly comprises a feature extraction module, a gated attention mechanism feature fusion module, a space-time memory feature reading module and a double-branch prediction module. The method comprises the following steps: inputting a memory frame image and a current query frame image into a backbone network to extract features; fusing the enhanced memory frame image features and the query frame image features by adopting a gating attention mechanism; respectively predicting a target position frame and a segmentation mask result by using a double-branch detection module; and dynamically screening the memory frame template according to the confidence score and the time distance constraint. According to the method, fusion of memory frame image features and query frame image features is enhanced through a gating attention mechanism, space-time memory information is fully utilized, interference caused by conditions that a target is shielded for a long time and non-target similarity is high is effectively reduced, and accuracy and robustness of a tracking model are improved.

The invention relates to the technical field of medical image processing, and discloses a CyclGan-based multi-modal medical image elastic registration system, which comprises a multi-modal medical image data preprocessing module, a CyclGan-based elastic registration module, a CyclGan-based elastic registration module and a CyclGan-based elastic registration module, a module for training the CyclGan model on the basis of training strategies of medical image data of different modalities; a module for performing elastic transformation and resampling on the preprocessed medical image based on an output grid of the model; and a post-processing module is used for post-processing the deformed medical image. Through the above operations, automatic elastic registration between medical images of different modalities and fusion of medical images of different modalities after registration and alignment can be realized, a doctor is helped to obtain more comprehensive information and more accurately position a lesion area, and thus the accuracy and efficiency of diagnosis are improved.

The invention discloses a platform vehicle abnormal behavior intelligent analysis method based on deep learning. Accurate early warning is realized through multi-dimensional data acquisition and deep learning model construction. Firstly, platform passenger flow, road conditions, video monitoring and vehicle operation information are integrated, and a comprehensive data basis is provided for anomaly analysis. After the data is preprocessed, a graph neural network and an attention mechanism are utilized to perform preliminary fusion, and an AGCN adaptive graph convolutional network and a DTW dynamic time warping algorithm are introduced to optimize a fusion result, so that time sequence data are effectively aligned, and the feature extraction accuracy is improved. And then, a deep learning model is constructed to automatically identify abnormal behavior modes of the platform vehicles, such as illegal parking and passenger congestion. Early warning information is issued in real time, potential risks can be timely handled, and safe and efficient operation of a public transportation system is guaranteed. According to the scheme, the identification and early warning capability of the abnormal behavior of the station vehicle is enhanced, and powerful support is provided for bus safety management.