152results about How to "Efficient deployment" patented technology

The invention discloses a lightweight semantic segmentation network and method for power grid inspection, and the method comprises the steps: employing an encoder-decoder architecture, inputting original data into a lightweight MobileNet v2 backbone network for feature extraction at an encoder part, inputting an obtained feature map into a lightweight large-scale ASPP module, and carrying out the feature extraction; further performing multi-scale feature extraction on the high-dimensional feature map; and in the decoder part, high-dimensional features and low-dimensional features obtained by the backbone network are respectively input into a cross attention wavelet fusion module, after an obtained feature map is fused with the output of a decoder, the feature map is recovered to the size of original data through down-sampling operation by a full-dimensional dynamic convolution post-processing module, and a final prediction mask is obtained. According to the invention, by optimizing a coding and decoding structure, the receptive field of the model and the modeling capability of a narrow and long target are improved, the balance between the precision and the complexity can be effectively realized, and the method is suitable for an unmanned aerial vehicle inspection system with limited resources.

The invention discloses an unmanned aerial vehicle airport multi-target constraint planning and site selection method and system and electronic equipment. The planning and site selection method comprises the following steps: S1, obtaining geographic information of a target site selection area; s2, determining performance parameters of the unmanned aerial vehicle, and obtaining a flight coverage range of the unmanned aerial vehicle in combination with geographic information; s3, constructing a dynamic task point model, and determining an unmanned aerial vehicle task point set through the dynamic task point model; s4, obtaining an optimization target of airport site selection, establishing a target function according to the optimization target, constructing a site selection optimization model through the target function, and setting constraint conditions for the site selection optimization model; and S5, performing multi-target optimization calculation based on the site selection optimization model by adopting a heuristic algorithm to obtain a target layout of the unmanned aerial vehicle airport. According to the technical scheme disclosed by the invention, the navigation path can be precisely planned, the accurate navigation of the unmanned aerial vehicle in a communication limited or silent environment is realized, and the navigation reliability and the operation capability of the unmanned aerial vehicle are improved.

The invention belongs to the technical field of bridge damage identification, and relates to a bridge structure intelligent damage identification method based on a physical information neural network, which comprises the following steps: 1, acquiring spatial relation data of a bridge structure, 2, acquiring real-time data, 3, preprocessing the data after the data is acquired, 4, performing hyper-parameter adjustment, 5, constructing a model, 6, carrying out model training and evaluation; 7, carrying out early warning and repairing scheme matching; the health state of the bridge can be monitored in real time, data support can be provided for future maintenance and repair, the safety of the bridge is improved, and the service life of the bridge is prolonged; therefore, a novel efficient tool is provided for bridge health monitoring and damage assessment through a unique data and physical driving method, an efficient and intelligent bridge monitoring and assessment system is constructed, and the safety and maintenance efficiency of the bridge are improved.

The invention provides a coal gangue multi-scale detection method and system based on a YOLOv8 network, and the method comprises the steps: enabling a CBAM attention mechanism to be embedded in a whole network core module C2f, and improving the small target detection capability; secondly, a fast spatial pyramid pooling module is adopted in the backbone network, more front and back features are fused, interaction of feature information is enhanced, and the multi-scale detection capability is further improved; then, through a bidirectional feature fusion module with more jump connections, the multi-scale detection capability is increased, and small target features are prevented from being lost due to network depth; and finally, convolution blocks used for feature fusion in the detection head are combined for weight reduction, regression loss is set as EIoULoss, and errors caused by the fact that the length-width ratio of a prediction frame is consistent with that of a real frame are avoided. By means of the target network model, coal gangue with the size fraction ranging from 6 mm to 50 mm can be effectively detected, cross-size-fraction detection is achieved, and the target network model can be effectively deployed in coal gangue separation equipment.

The invention provides a large model segmentation and deployment method and device based on cloud edge end collaboration and a medium, and the method comprises the steps: giving a pre-trained large model as input, and evaluating the performance and resource consumption conditions of the large model during cloud edge end deployment; determining a segmentation point of the large model according to a performance evaluation result and a resource consumption condition; decomposing the large model into a plurality of sub-models according to the segmentation points; deploying each sub-model at a cloud end and an edge end; and establishing a cloud side end cooperative work mechanism, so that the sub-models cooperatively work at the cloud side and the edge side. The method can reduce the demand for computing resources and improve the response speed while ensuring the model performance, and is suitable for the demand in the field of intelligent manufacturing.

The invention discloses an obstacle detection method for a visual impaired group guiding waistcoat system based on improved YOLOv11, and the method comprises the steps: 1, obtaining an obstacle data set, and completing the marking work of the data set; 2, a backbone network of the YOLOv11 is replaced by a ShuffleNetV2 (ShuffleNetV2); thirdly, a lightweight detection head is redesigned, and subsequent deployment is facilitated; 4, completing the training of the improved YOLOv11 model by using the data set; 5, deploying the improved YOLOv11 detection model into embedded hardware equipment for sensing; and 6, performing model reasoning to realize real-time obstacle detection of the camera on the waistcoat. According to the invention, the real-time performance and accuracy of obstacle detection on the waistcoat can be ensured, a reliable basis is provided for guiding a visual impaired group to make an obstacle avoidance decision, and the travel safety of the visual impaired group is ensured.

The invention discloses a reconfigurable systolic array tensor IP core based on an FPGA. The architecture comprises a core controller, a shift distributor, a data processing array and a four-stage data cache. The tensor core can adapt to general tensor multiplication and addition operations in Prefill and Decode stages of the generative neural network at the same time through reconfigurable design. The core controller receives the tensor multiplication instruction and the configuration information and decouples the tensor multiplication instruction and the configuration information according to a data stream to generate a plurality of block tensor multiplication instructions. The shift distributor decodes a block tensor multiplication instruction, decoded mode information controls data communication between a first-level cache and a second-level cache (Distrided RAM and Bram), a control signal of a data processing array is generated, and the control signal enters the array together with data to flow. And the data processing array is connected with different secondary BRAM caches according to the received configuration information and is used for processing data in a bubble-free pulsating flow manner. The four-stage data cache realizes the multi-stage pinpong operation of the loading of the operation data of the tensor operation core, and realizes the multi-stage pipeline design of the data from the off-chip HBM to the on-chip URAM, from the URAM to the BRAM and from the BRAM to the operation unit. Aiming at a single-user edge end generation type network reasoning task, a core controller generates a data processing unit mode configuration signal in a fine-grained (tensor element level) manner, and the data processing unit mode configuration signal is transmitted by a shift distributor and flows in parallel with operation data, so that the mode configuration efficiency and the hardware resource utilization rate are greatly improved, the problem of high fan-out caused by broadcast control is reduced, and the user experience is improved. A control flow is designed by means of the structural characteristics of the systolic array, and a complex control algorithm is realized with low resource occupation.

The invention discloses an AI algorithm optimization method and system based on a deep learning technology, and relates to the technical field of deep learning model optimization, and the method comprises the steps: carrying out the preprocessing of a data set, carrying out the normalization and standardization processing, and dividing the data set into a training set, a verification set and a test set; a self-attention mechanism is introduced into a convolutional layer of the ResNet-18 deep learning model, and the weight of each channel is dynamically adjusted by calculating a self-similarity matrix of a feature map; training the model by using the training set data, and dynamically adjusting the model learning rate in the training process; an optimal hyper-parameter combination is automatically searched through a hyper-parameter tuning method; the number of model parameters and the calculation amount are reduced through a static quantification method; exporting and deploying the model, importing the test set, and testing the performance of the model; according to the method, a self-attention mechanism is introduced into the convolutional layer of the ResNet-18 model, the weight of each channel is dynamically adjusted, the attention of the model to important features is enhanced, and the feature extraction precision is improved.

The invention provides an image classification method and device based on a student model, equipment and a medium, and relates to the technical field of knowledge distillation, and the method comprises the steps: obtaining a to-be-classified image; inputting the to-be-classified image into a target student model to obtain a category corresponding to the to-be-classified image; inputting the initial image set into a trained teacher model and a preset initial student model, and obtaining a teacher model imbalance category probability and a student model imbalance category probability; inputting the mixed image set into a trained teacher model and a preset initial student model, and obtaining a teacher model imbalance category probability and a student model imbalance category probability; determining a corresponding loss; according to the loss, performing back propagation to update student model parameters so as to obtain a target student model; when the image is classified, the resource computing power required by computer hardware can be reduced, the response speed of a computer is improved, and the phenomenon of computer jamming is avoided.

The embodiment of the invention discloses a large-scale competition medical resource scheduling guarantee method and system, a medium and a product. The method comprises the following steps: determining a plurality of initial medical points and first deployment positions of the plurality of initial medical points based on geographic data of a target track so as to obtain a rescue service radius of each initial medical point, and screening available medical points from the plurality of initial medical points based on the rescue service radiuses; dividing the target track into a plurality of track partitions based on a second deployment position of the available medical point, obtaining a demand level of the track partitions, and performing medical resource deployment according to the second deployment position and the demand level; when the participant has a safety risk, acquiring an optimal rescue route based on a third deployment position of the recently available medical point and the staying position of the participant; and according to the optimal rescue route, rescuing the participant by adopting the recent available medical point. According to the method, the utilization efficiency of medical resources can be improved, and meanwhile, the safety guarantee capability of a large competition is effectively enhanced.

The invention discloses an infrared expressway foreign matter detection method based on a Mama framework, and the method comprises the steps: continuously carrying out the data collection of expressway scenes under different illumination conditions and different weather conditions through an infrared sensor, obtaining infrared image data, carrying out the preprocessing of the infrared image data through data augmentation, generating training data, and carrying out the detection of foreign matter in an expressway. Dividing the training data into a training set, a test set and a verification set in proportion; constructing a detection network based on a Mama framework, wherein the detection network comprises a student network and a teacher network; training the teacher network through back propagation based on the training set; training a student network based on the result of the teacher network and the real data to obtain a target detection network; and inputting a to-be-identified image into the target detection network to obtain a detection result. According to the invention, the method achieves the quick and accurate recognition of potential risks, guarantees the high detection precision through the combination of the infrared imaging technology and the powerful processing capability of a Mama frame, achieves the real-time response to foreign body threats, and remarkably improves the efficiency and safety of expressway monitoring.

The invention belongs to the technical field of cloud computing, and discloses a lightweight multi-domain hyper-fusion platform construction method compatible with heterogeneous hardware resources, which adopts a lightweight hyper-fusion platform architecture compatible with the heterogeneous hardware resources, converts physical resources into virtual resources on a virtual machine based on a KVM (Kernel-based Virtual Machine), shields the difference of underlying hardware, and improves the performance of the platform. According to the method, heterogeneous storage resources are integrated based on Ceph, and storage devices of different manufacturers are integrated into a unified storage pool through a distributed storage technology without being limited by types of bottom hardware devices. Through the SDN technology, the OpenStack network service can decouple a network control plane and hardware, and unified management of different network devices is realized. Through a virtualization technology and an automatic management tool, a simplified elastic expansion solution is provided, and changes of resource demands are easily coped with.

The invention discloses a multi-task large language model service system based on quantification. The system comprises a dynamic multi-task quantification module and a multi-task request scheduling module, wherein the dynamic multi-task quantification module is used for performing initial multi-task joint quantification and deployment on a deployed model, and when a subsequent new task needs to be introduced, the dynamic multi-task quantification module is also responsible for performing re-quantification on the model; the request pool is used for caching requests sent by various clients and giving the requests to the subsequent multi-task request scheduling module; the multi-task request scheduling module schedules and arranges requests of multiple tasks; whenever a multi-task request scheduling module gives a group of inputs similar to an existing service system, the inputs are sent to a reasoning process to be processed, predicted values corresponding to the outputs are obtained and decoded, and lexical elements obtained through decoding are output in a streaming mode and returned to the scheduling module to wait for next round of scheduling. The method has the advantages of higher availability, better expandability and better user experience.

The invention discloses a road surface disaster detection method and system, electronic equipment and a storage medium, and relates to the technical field of intelligent traffic management and computer vision, and the method comprises the steps: collecting image data containing a plurality of road surface disaster types, carrying out the data marking in each image data, and carrying out the data marking; a data sample is constructed through each piece of image data subjected to data annotation; training the improved YOLOv10 model by using the data sample until a loss function of the improved model reaches a preset end condition, and determining the improved model of which the loss function reaches the preset end condition as a disaster detection model; acquiring a to-be-detected image of a to-be-detected road surface, and inputting the to-be-detected image into the disaster detection model for processing to obtain a disaster detection result of the to-be-detected road surface, the disaster detection result including a disaster type and a disaster position; by combining the deep learning technology and optimization algorithm design, the problem that the existing method is insufficient in detection precision, robustness and applicability is solved.

The invention belongs to the field of nuclear power engineering, and particularly relates to a nuclear power engineering drawing recognition method and system based on a visual language multi-modal large model, and the method comprises the following steps: obtaining a to-be-recognized nuclear power engineering drawing and a text input by a user, comparing the drawing information with a data set based on the multi-modal large model, and obtaining a recognition result; and verifying the logic consistency of the information on the drawing by using a multi-modal data fusion technology, and outputting a verification result and analyzing the information. Compared with the prior art, the challenges of complexity, accuracy and the like encountered by a traditional drawing recognition method in the nuclear power engineering field are solved; according to the scheme, an advanced multi-modal large model (visual language large model) is fused, nuclear power engineering drawings and related document data are combined, a hidden association mode is mined through organic combination of multi-modal data, the recognition and analysis effect is improved, and the limitation of traditional single-modal analysis is broken through.

The present invention discloses an infrared highway foreign body detection method based on Mamba architecture, comprising: continuously collecting data of highway scenes under different lighting conditions and different weather conditions through infrared sensors to obtain infrared image data, preprocessing the infrared image data through data augmentation to generate training data, and dividing the training data into training set, test set and verification set in proportion; constructing a detection network based on Mamba architecture, including a student network and a teacher network; training the teacher network through back propagation based on the training set; training the student network based on the results of the teacher network and real data to obtain a target detection network; inputting the image to be identified into the target detection network to obtain the detection result. Rapid and accurate identification of potential dangers is achieved, and the powerful processing capability of the infrared imaging technology and the Mamba framework is combined to ensure high detection accuracy, achieve real-time response to foreign body threats, and significantly improve the efficiency and safety of highway monitoring.

The invention relates to a multi-agent cooperation-based language model reasoning resource scheduling method and system, and the method achieves the intelligent simulation of multi-view iterative thinking in a complex reasoning task through the construction of a multi-agent system which is clear in division of labor and is provided with a special knowledge base. View limitation and decision deviation of a single model in long-sequence and multi-step reasoning are effectively overcome; depending on the fusion of the general capability of the large language model and the task special knowledge base, the professionality and accuracy of the reasoning result are improved. Meanwhile, the problems of resource waste, redundant calculation and unstable convergence caused by cognitive overload in the cooperation process are solved by combining multi-round dynamic cooperation with a convergence mechanism of cognitive load perception and a dynamic token number limitation and low-confidence branch pruning strategy; therefore, on the premise that the reasoning quality is guaranteed, the utilization efficiency of computing resources is remarkably optimized, peak value occupation is reduced, the overall reasoning time delay is shortened, and reliable technical support is provided for efficient and stable deployment of a large language model in a complex task.

The invention provides an Android cloud computing power cluster management method and system based on a Docker container, and the method comprises the following steps: firstly, installing a Docker environment on a target server, configuring a container environment supporting the operation of an Android virtual machine, deploying a management program on a main server, and building cross-server SSH connection; secondly, constructing or importing a Docker mirror image of the Android virtual machine, and distributing the Docker mirror image to a target server; the batch creation, destruction and resource limitation of the Android virtual machine container are realized through the Docker container management module; the centralized monitoring module collects and displays the operation states of the target server and the container in real time; the client interaction module realizes remote control, a user accesses the Android virtual machine by connecting a container port through an ADB interface, and configures a QoS priority to guarantee communication flow; abnormal early warning and log analysis functions are provided; according to the method, the Android virtual machine cluster is efficiently deployed and managed in a centralized manner, the resource utilization efficiency is improved, the management process is simplified, and the monitoring and early warning capabilities are enhanced.

The invention relates to the technical field of computer vision, lane line detection and automatic driving, provides a night lane line detection method and device based on decomposition convolution, and aims to improve the accuracy and stability of lane line detection under a night light condition. The method comprises the following steps: firstly, acquiring image data of various vehicles on a night traffic road, marking the data, and establishing a reference data set CULane-Night for night lane line detection; based on the data set, the invention provides a lane line detection model MDCR-Net, and the model comprises a specially designed encoder module (MDCRM) and an attention module (SPA). The MDCRM adopts a multi-scale decomposable convolution residual module, can effectively extract features of lane lines in a complex scene at night, and realizes lightweight design by reducing model parameters and calculation amount. The SPA module comprehensively considers lane information in the horizontal direction and the vertical direction through a strip-shaped pooling technology, so that the recognition capability of the model on the sheltered area is improved.

The invention relates to the technical field of engraving control, in particular to an engraving control method and system. The method comprises the following steps: acquiring a sculpture design planar graph, marking the shape outline of the sculpture design planar graph, and generating a three-dimensional sculpture model; thirdly, engraving requirement data are obtained, and the raw materials are classified into wood and stone; if wood raw materials are selected, temperature and humidity monitoring is carried out, the stress warping condition is analyzed, and compensation planning is carried out through linear regression. If stone raw materials are selected, internal cracks of the stone raw materials are analyzed through X-ray scanning, cutting fracture limit stress is recognized, and carving logic design is conducted based on the cutting fracture limit stress. And finally, in combination with wood compensation planning and stone carving logic, automatic carving control firmware is designed and uploaded to the cloud platform to execute the carving control method, and automatic precise carving is achieved. The engraving control technology is optimized, so that the engraving control technology is more perfect.

The invention relates to the technical field of distribution network power supply, and discloses a distribution network optimization method based on artificial intelligence, and the method comprises the steps: firstly, periodically obtaining the attribute information of each power supply area, and determining the first stability; secondly, collecting and analyzing different power supply data sequences of each transformer area, and generating first sample data; and then, extracting label data through the historical operation data for subsequent model training. On this basis, the first sample data, the label data and the first stability are utilized to train a prediction model; and finally, inputting second sample data of each power supply transformer area, which is acquired in real time, into the model so as to obtain the prediction stability of each transformer area. According to the method, through integration of data analysis and prediction modeling, the overall stability and reliability of the power distribution network are improved, optimal scheduling is achieved, energy loss is reduced, flexibility is improved, and technical support is provided for construction of the intelligent power distribution network.

The application discloses a mixed expert network-based optical flow estimation method and system, belonging to the field of computer vision and artificial intelligence. First, the input two frames of images are preprocessed, low-resolution features are extracted through a mixed expert feature extractor (MoEE) containing a sparse activation mechanism to reduce redundant calculation; then, dot product operation is performed on the low-resolution feature maps to construct a 4D correlation volume to capture pixel motion matching relationship; subsequently, a mixed expert updater (MoEU) is used to iteratively update the hidden state and regress the residual flow increment through a dynamic expert selection mechanism to optimize the optical flow accuracy; finally, a multi-scale upsampling module is used to reconstruct the high-resolution optical flow field to output the high-precision optical flow result. The algorithm realizes dynamic resource allocation through the MoE architecture, significantly reduces the calculation cost while ensuring the accuracy of optical flow estimation, and can adapt to resource-constrained scenarios such as automatic driving and unmanned aerial vehicles, and can balance efficient inference and flexible deployment.

The invention discloses a smart campus resource allocation management method and system based on big data, and belongs to the technical field of smart campus management. Receiving a reservation demand instruction of a user through a reservation medium, and uploading the reservation demand instruction to a resource data center to form a temporary resource data cluster; sorting the temporary resource data clusters according to a to-be-executed time sequence of the reservation demand instructions, setting an instruction sliding window, grouping the reservation demand instructions according to a scale value (namely the number of personnel of a user demand project) of the instruction sliding window in a sliding grouping manner, and performing first optimization of resource allocation; and after the first optimization, generating a secondary to-be-optimized object set, and performing secondary to-be-optimized executable evaluation by evaluating the executable degree of the reservation demand instruction fused into the secondary to-be-optimized object set, so as to complete the optimization process of resource allocation. In order to improve the quality of campus life, the resource allocation can be efficiently and accurately carried out according to the user demand, and the resource utilization rate and the user satisfaction are improved.

The embodiment of the invention provides an autonomous configuration method and system for fan control, and belongs to the technical field of wind turbine generator control. The method comprises the following steps: acquiring to-be-configured control flow information, and reading the corresponding to-be-configured information based on the format of the to-be-configured control flow information; compiling a corresponding control scheme based on the to-be-configured information to obtain a corresponding control program; executing corresponding control program configuration based on the to-be-upgraded wind turbine generator so as to configure the obtained control program to each target wind turbine generator; and controlling each target wind turbine generator based on the configured control program. According to the scheme, the complexity of control program development is reduced, low-threshold and high-efficiency control program configuration and execution are achieved, and the operation efficiency and maintenance convenience of a fan control system are improved.

The present disclosure provides an image processing method based on end-edge-cloud collaboration, which can be applied to the field of 5G technology. The method includes: in a cloud data center, according to a preset model cutting point, dividing a trained neural network model into a first part model and a second part model, and deploying the first part model and the second part model on a terminal device and an edge server respectively; in response to an image processing request sent by the terminal device to the cloud data center, the first part model performs preliminary processing on the image processing request to obtain an intermediate result, and the second part model performs secondary processing on the intermediate result to generate an inference result; the cloud data center queries the real-time information corresponding to the inference result, and returns the real-time information to the terminal device. The present disclosure also provides an image processing device, electronic device, storage medium and program product based on end-edge-cloud collaboration.

The application relates to a water quality change trend rapid prediction method based on multi-source data fusion and physical constraints, and specifically comprises the following steps: step 1: synchronously collecting data such as spectrum information, DO, COD, temperature and pH at key monitoring sites, constructing a water dynamics-water quality coupling equation, and simulating the space-time dynamic distribution of water quality parameters; step 2: outputting a water quality sensitive area through a water dynamics-water quality model, screening sensor layout points by combining information entropy evaluation and spatial clustering, realizing low-cost water quality sensor network deployment through a multi-objective optimization algorithm, and calculating a water body global water quality distribution map by adopting a spatial interpolation method; step 3: analyzing main pollution sources according to the synchronous collection of spectrum information at key monitoring sites, and adopting principal component analysis and an attention mechanism neural network; step 4: based on real-time optical characteristic value-DO data, combining a spatial topological network, a water quality gradient and a cross-region covariance to capture the spatial correlation of water quality parameters between different points, and constructing an optical characteristic value-DO-COD dynamic prediction model; combining pollution tracing and spectrum characteristic correction to correct the COD prediction value, adopting ensemble Kalman filtering to assimilate multi-source data, and improving the model accuracy.

This invention belongs to the field of industrial manufacturing technology, specifically providing a method and system for visual detection of industrial defects by decoupling defect features from imaging conditions. The method includes: collecting defect samples of industrial products under different operating conditions; wherein the defect samples include defect images and corresponding defect annotations; based on the defect samples, constructing a region-guided causal decoupling network model by combining a feature decoupling mechanism guided by defect regions and a causal invariance learning mechanism based on imaging simulation; performing multi-supervised loss joint optimization training on the causal decoupling network model to obtain a converged causal decoupling network model; and detecting defects in industrial products under target operating conditions based on the converged causal decoupling network model to obtain defect detection results. This invention can significantly improve the generalization and robustness of defect detection algorithms in complex industrial environments, enabling rapid and low-cost model transfer between different operating conditions.

This invention relates to a method and system for automated generation of TSN network configurations based on a reflective agent. The system comprises a network state perception and intent reflection module, a YANG model configuration parameter and structure decision module, and a YANG model intelligent generation module. The network state perception and intent reflection module is responsible for structurally perceiving network state and resource information. The YANG model configuration parameter and structure decision module integrates multi-source knowledge and contextual information, intelligently generating deployable TSN scheduling parameters and YANG configuration structures based on business needs. The YANG model intelligent generation module automatically generates the corresponding YANG configuration model based on the optimized results, performs syntax and semantic verification, and then distributes it to the target device, achieving automated deployment of network configurations. This invention significantly improves the intelligence level and deployment automation capability of TSN network configuration by introducing reflective reasoning and feedback optimization techniques.

The invention provides a multi-line vehicle intelligent scheduling method and system, equipment and a storage medium, and belongs to the technical field of intelligent vehicle scheduling, and the method comprises the steps: constructing a feature extraction network which is used for extracting a feature vector of first information; and constructing a vehicle selection network, wherein the vehicle selection network is used for selecting vehicles for scheduling. And constructing a simulation environment, wherein the simulation environment is used for simulating operation information of the vehicle. And constructing an intelligent agent based on the feature extraction network and the vehicle selection network. First information is generated based on the simulation environment, the intelligent agent is trained based on the first information and a reward function to obtain a reinforcement learning intelligent agent, the first information is historical operation information of the simulation vehicle, and the reward function is a reward value calculation function corresponding to the first information; and inputting second information into the reinforcement learning agent to obtain a target scheduling scheme, wherein the second information is multi-line vehicle information. According to the multi-line vehicle intelligent scheduling method and system, the equipment and the storage medium provided by the invention, the capability of coping with a complex vehicle scheduling problem can be improved.

The present application relates to the technical field of GPU computing optimization, and in particular to a sparse attention computing method, device and medium for GPU, wherein the method realizes the high efficiency of long context reasoning through the geometric perception sparse attention framework of ball hashing, and combines a large-scale parallel hashing optimization algorithm and a load adaptive computing kernel. Compared with the existing sparse attention methods based on heuristics or gradient learning, the present application realizes higher retrieval recall rate, lower preprocessing overhead and efficient hardware adaptation to irregular sparse patterns.