1458results about How to "Easy to deploy" patented technology

The invention belongs to the technical field of image classification neural networks, and discloses a lightweight image classification neural network architecture system based on knowledge distillation. The invention provides a lightweight image classification neural network architecture system based on knowledge distillation. The lightweight image classification neural network architecture system comprises a data set preprocessing module, a teacher model preprocessing module, a subnet model construction module, a personalized training module, a real loss calculation module, a distillation loss calculation module, a total loss calculation module and a student model construction module. The invention provides a lightweight neural network architecture system based on knowledge distillation, and designs a brand new training mode by using the superiority of knowledge distillation for teacher model weight extraction: the knowledge distillation of teacher and student models is combined with a deep compression method; the system for constructing the lightweight network can be used for training various complex image classification neural networks so as to improve the network performance.

The invention discloses a construction progress detection system and method based on three-dimensional model and field data fusion, and relates to the technical field of power grid construction engineering. The system comprises a data acquisition module, a data preprocessing module, a data matching module, a data fusion module, a progress detection module and a feedback module, the data matching module matches point cloud data with a panoramic image, a clonal selection algorithm is applied to optimize matching parameters, and on-site three-dimensional basic data is constructed; the data fusion module performs deep fusion on the BIM model and on-site three-dimensional basic data, and constructs a three-dimensional fusion model for construction progress detection by using a GeoBIM technology; and the progress detection module compares the real-time acquired panoramic image of the construction site with the three-dimensional fusion model frame by frame, and automatically detects the construction progress, so that efficient acquisition, accurate processing and real-time monitoring of construction site data are realized, and the efficiency and decision ability of construction management are remarkably improved through automatic progress detection and real-time feedback.

The invention discloses a retrieval method and system for efficiently collecting global accurate potential customer information, and the method comprises the steps: collecting and preprocessing multi-source heterogeneous data from an e-commerce platform, social media, an enterprise official website, exhibition information, an industry database and customs; generating standardized data through spatio-temporal feature extraction and multi-dimensional credibility evaluation; establishing a dynamic topological structure by adopting a characteristic decomposition reconstruction and value network construction method; based on adaptive classification and multi-dimensional trend analysis, customer value prediction and accurate recommendation are realized; and through system quality evaluation and feedback optimization, dynamic updating and optimized display of the result are realized. According to the method, the accuracy and timeliness of customer information retrieval can be effectively improved, the information redundancy is reduced, and the reliability of the recommendation effect is improved.

The invention discloses an ROV positioning navigation system based on vision inertial navigation fusion and pose correction, which comprises an inertial measurement value and image preprocessing module loaded on an ROV, the inertial measurement value and image preprocessing module is connected with a vision and inertial navigation data fusion module through a wire, and the vision and inertial navigation data fusion module is connected with a pose correction module. The invention also discloses a positioning navigation method of the ROV positioning navigation system based on visual inertial navigation fusion and pose correction. According to the method, the inertial data provided by the IMU and the environment characteristic information captured by the visual sensor are fused, high-precision estimation of the position and attitude of the ROV can be realized, the sensor data are optimally fused by using the MSCKF algorithm, the influence of the error of a single sensor on the positioning result is reduced, and the positioning precision and reliability of underwater operation are remarkably improved.

The invention relates to the field of degradation trend evaluation of rotary machinery, in particular to a motor abnormity identification method fusing low-frequency characteristics and an auto-encoder, and the method comprises the following steps: S1, collecting a vibration signal of target motor equipment; s2, data preprocessing; s3, building an auto-encoder network model; s4, training an auto-encoder network model; s5, calculating an equipment anomaly detection threshold value index; and S6, deploying applications. According to the method, vibration signal low-frequency feature mapping of the healthy operation state of the motor is self-learned through the self-encoder, the mean square error of the reconstructed feature and the original low-frequency feature is tracked, and the statistical abnormality trigger threshold value is calculated, so that feature information loss caused by direct extraction of a vibration signal monitoring index is avoided; extraction of original vibration low-frequency signal features is enhanced, the abnormal state of the motor is estimated in advance, and early warning and operation and maintenance of early degradation of the motor are achieved.

The invention discloses a production line aluminum alloy ingot surface defect detection method, device and system and a storage medium. The method comprises the steps that an aluminum alloy ingot surface defect image data set is collected; selecting YOLOv5 as a detection model, and optimizing the initial anchor frame for an application scene by using a K-means + + algorithm; carrying out accelerated reasoning improvement on the YOLOv5 detection model, and meanwhile, fusing an attention mechanism to dynamically detect a head Dyhead; a Mixup and Mosaic data enhancement algorithm is adopted to enhance the data set, an improved YOLOv5 detection model is trained, and a Focal loss function and non-maximum suppression are introduced during training; and detecting the surface defect image of the aluminum alloy ingot by using the trained model to obtain the type confidence coefficient and position information of the defect in the image. With the adoption of the technical scheme, the types and positions of the defects can be quickly detected, so that the requirement of quick and accurate detection of an aluminum alloy ingot production line is met.

The invention discloses a roadway deformation real-time detection method and system based on binocular vision, and the method comprises the steps: firstly, installing and debugging a mining industrial binocular camera, and training an anchor rod end target detection algorithm; then real-time acquisition and preprocessing of images are carried out, and environmental noise is removed by using a self-adaptive median filter; and based on the preprocessed image, identifying and positioning the end of the anchor rod by using a trained target detection algorithm. A binocular vision technology is utilized to calculate three-dimensional coordinates of the end of the anchor rod, and feature matching and parallax calculation between images are carried out. And finally, comparing the three-dimensional coordinates of the ends of the anchor rods at different time points, and inputting the three-dimensional coordinates into a roadway deformation calculation module to obtain a deformation result of the roadway so as to realize real-time deformation monitoring and early warning of the roadway.

The invention relates to the technical field of voice recognition, in particular to a mixed recognition processing method and device, equipment and a medium, and the method comprises the steps: recognizing command word data based on a command word recognition model, selecting command word data with an error rate lower than a preset range, generating a corresponding phoneme embedding representation, and forming a phoneme embedding dictionary; determining a mixed recognition command word corresponding to the current command word, and generating a mixed recognition list; identifying an audio embedding sequence corresponding to the current command word; obtaining a phoneme embedding sequence of each mixed recognition command word in the mixed recognition list based on a phoneme embedding dictionary; and calculating the similarity between an audio embedding sequence and each phoneme embedding sequence to obtain an identification result. The method and the device can improve recognition accuracy and reduce mixed recognition of command words.

The invention provides a multi-degraded image restoration method based on self-adaptive prompt. The method comprises a two-stage hidden space diffusion model, and various degraded images can be flexibly processed. Specifically, the model generates a degradation cue by learning the difference between a degraded image and a clean image, and encodes the cue information in a hidden space. In the first stage, a degradation prompt is obtained through a degradation adaptive prompt learning mechanism as a key feature for guiding the diffusion model in the second stage to carry out image restoration. Finally, prompt information is integrated into a Fourier transform restoration network, and accurate restoration of different types of degraded images can be realized. The method not only improves the accuracy of image restoration, but also significantly reduces the calculation complexity, and is suitable for image restoration tasks in various real world scenes, including denoising, deblurring, defogging, rain removing, snow removing, raindrop removing and low illumination enhancement.

The invention discloses a waterworks double-coagulant accurate prediction method based on automatic machine learning, and the method comprises the steps: firstly obtaining the water quality data of a waterworks, the agent dosage data of two coagulants, and other basic data, and carrying out the preprocessing of the data; an automatic machine learning method is adopted, and a tap water double-coagulant dosage prediction model under the production condition is built; the model is optimized according to an actual effluent target value, and accurate prediction of the dosage of the two coagulants is realized by using the optimal model. According to the invention, accurate calculation and intelligent regulation and control of the dosage of the coagulant in the waterworks are realized, and the predictive capability of the double coagulant is particularly emphasized, so that the innovation point ensures that the effluent quality reaches the drinking water standard, meanwhile, the dependence on manpower is remarkably reduced, the operation cost and the medicament cost of the waterworks are saved, and the economic benefit is increased. And double improvement of economic benefits and environmental benefits is realized.

The invention belongs to the technical field of robot obstacle avoidance, and particularly relates to a double-arm collision detection and obstacle avoidance path planning method based on an improved artificial potential field method.The method comprises the steps that a three-dimensional model of double mechanical arms is obtained; the working space and environment obstacle information of the double mechanical arms is initialized; respectively calculating the repulsive force distance between each joint sphere and each connecting rod cylinder of the double mechanical arms and the obstacle; a mechanical arm performing path planning is defined as a main arm, the other mechanical arm is defined as a slave arm, positions of joints and connecting rod centers of the slave arm are calculated according to joint angles of the slave arm, a repulsive force field is set, meanwhile, the repulsive force field is set at a center point of an obstacle, and a gravitational field is set at a target point of the main arm; generating a track by using an improved artificial potential field method and updating the tail end position of the current main arm; and whether the tail end of the mechanical arm reaches the target point or not is judged, and if not, execution is repeated till the mechanical arm reaches the target point. According to the method, the calculation amount in a complex environment is reduced, and the planning efficiency and the safety of robot operation are improved.

The invention provides a power station photovoltaic module defect detection method and device based on unsupervised learning. The method comprises the steps that firstly, a thermal imaging image to be detected and a visible light image in a target area provided with a photovoltaic module are collected; cutting a thermal imaging photovoltaic module image from the thermal imaging image, and cutting a visible light photovoltaic module image from the visible light image; afterwards, a teacher network model and a visible light photovoltaic student network model in the photovoltaic defect detection model are used for processing the visible light photovoltaic module image, and position information of the visible light abnormal photovoltaic module is determined and returned; and the teacher network model and the thermal imaging photovoltaic student network model in the photovoltaic defect detection model are used to process the thermal imaging photovoltaic module image, and the position information of the thermal imaging abnormal photovoltaic module is determined and returned. Wherein the photovoltaic defect detection model is obtained by training in a label-free supervision mode.

The invention discloses a time-frequency domain cooperative industrial Internet of Things anomaly detection method under a full MLP lightweight architecture, and the method only employs four parallel two-layer MLP networks to construct a lightweight full MLP architecture with high timeliness and low resource consumption, and guarantees that the lightweight full MLP architecture can be flexibly applied in an industrial scene with limited resources. According to the architecture, a double-branch reconstruction learning process is constructed from two angles of'local to global 'and'global to local'; in order to further improve the accuracy, the reconstruction learning process of each branch utilizes two two-layer MLP networks to carry out reconstruction learning in a time domain and a frequency domain respectively, and the time domain and the frequency domain are aligned by utilizing reconstruction consistency, so that the feature capture capability of the full MLP architecture is improved; and finally, designing an anomaly scoring scheme based on a time-frequency reconstruction error, fusing the time-frequency domain reconstruction error obtained in double-branch reconstruction learning by using different weights, thereby generating a final anomaly score for each timestamp, and further judging whether the timestamp is abnormal or not.

The invention discloses a monitoring video target detection method based on multi-frame high-frequency difference enhancement, and the method comprises the following steps: 1, firstly, selecting a series of monitoring videos, carrying out the segmentation and frame extraction of the monitoring videos, and sampling one frame every ten frames as a training set, carrying out data preprocessing and enhancement operation on the input continuous image frames; and 2, constructing a multi-frame image reconstruction module to reconstruct an image according to the low-layer feature maps of the current frame and the reference frame, and optimizing parameters of the reconstruction module by calculating mean square error (MSE) loss between the original image and the reconstructed image. According to the monitoring video target detection method based on multi-frame high-frequency difference enhancement, a continuous frame high-frequency difference chart and a self-adaptive fusion enhancement feature strategy are ingeniously combined, high-frequency motion features are extracted and fused through reconstruction of continuous frames, and a powerful target detection framework is constructed; the target detection performance in the monitoring video can be obviously improved.

The invention discloses a power distribution network scene low-voltage electric quantity internet-of-things monitoring device and method, and the device comprises a sensing layer, a network layer and an application layer, the sensing layer comprises a plurality of electric quantity collection terminal nodes, and each electric quantity collection terminal node comprises a current transformer, a voltage transformer, a metering chip, a first Bluetooth Mesh communication module and a first power module. And the metering chip converts analog signals acquired by the current transformer and the voltage transformer into digital signals and calculates to obtain voltage, current, power, electric quantity, frequency and other electric quantity parameters. According to the invention, automatic acquisition, wireless transmission, remote monitoring, intelligent analysis and visual display of the electric quantity data of the low-voltage side of the power distribution network can be realized; and meanwhile, an early warning effect can be achieved, early warning can be given out for possible faults of the line, the manual field patrol intensity is reduced, and an Internet of Things solution which is low in cost, high in efficiency, easy to deploy and wide in coverage is provided for low-voltage electric quantity monitoring of the power distribution network.

The invention relates to a training method of a target detection model based on knowledge distillation, and belongs to the field of target detection. Comprising the following steps: constructing a training data set and a target detection model, and training the target detection model based on the training data set to output an inference graph; calculating a first loss function to obtain a trained target detection model, and taking the trained target detection model as a teacher model; simplifying parameters of the teacher model to obtain a student model; obtaining a second training data set based on the training data set, training the teacher model and the student model based on the second training data set, and respectively outputting prediction labels; and calculating a second loss function to obtain a trained student model as a trained target detection model. According to the method, the optimal distillation temperature and loss coefficient are obtained by adopting the differential mutation algorithm, and the trained target detection model is obtained by training the student model through knowledge distillation, so that the problem of low detection precision caused by the fact that the existing target detection model is trained by a small amount of samples is solved.

The invention discloses a large model deployment method and device for a heterogeneous platform, equipment and a program product, and relates to the technical field of artificial intelligence. A large model to be deployed is divided into a plurality of sub-models, and according to the operator type and the operator calculation amount contained in each sub-model, the operator support conditions of various types of chips on the heterogeneous platform are combined, so that the large model deployment efficiency is improved. The method comprises the following steps: determining a target chip to be deployed by each sub-model, determining a quantization strategy of each sub-model according to a quantization support condition of the target chip, quantifying the sub-model according to the quantization strategy, and generating a deployable sub-model from the quantized sub-model and the quantization strategy so as to be deployed into a corresponding target chip on a heterogeneous platform. And automatic deployment of a large model is realized. According to the method, the target chip to be deployed by the sub-model can be automatically selected in the large model deployment process, the quantization strategy can be automatically selected, and compared with a method of manually setting a deployment scheme, the deployment efficiency can be greatly improved, and the end-side deployment difficulty of the large model can be reduced.

The invention discloses a privacy protection-oriented personalized federal recommendation system and method, and relates to the field of federal recommendation systems. According to the method, an article preference embedding vector is constructed for each client, and a global article embedding orthogonal mapping matrix and a double-layer perceptron used for generating an article embedding mixed factor matrix are trained, so that the global article embedding matrix and the article preference embedding vector of a user are fused; a mixed article embedding matrix which is more personalized and finer in granularity is constructed for the client, and the mixed article embedding matrix is input into a personalized recommendation prediction perceptron constructed for the client to obtain a recommendation result, so that the final recommendation effect is improved; when the client side uploads data to the central server, local differential privacy encryption is carried out; according to the technical scheme, negative sampling is carried out on each client side, the positive samples and the negative samples are mixed and then jointly used for training, the training effect is improved, meanwhile, the server cannot distinguish the historical interaction situation between the client sides and the articles according to the update data uploaded by the client sides, and user privacy is protected.

The invention provides a wind power auxiliary frequency modulation optimization method based on system frequency trajectory optimization. The method comprises the steps that key operation parameters and frequency modulation parameters of a wind turbine generator and a traditional generator are collected respectively, a small signal analysis method is used for deducing a wind turbine generator power frequency transfer function considering working point deviation, and a system frequency response model containing the wind turbine generator and the traditional generator is established; based on the system frequency response model, constructing a discretized optimal system frequency trajectory optimization model by taking the lowest point of the maximized system frequency as a target function; and solving the discretized optimal system frequency trajectory optimization model by using a commercial solver to obtain an additional frequency modulation power signal, and applying the additional frequency modulation power signal as an additional control signal to virtual inertia control to obtain a system frequency optimal control effect. According to the method, the additional frequency modulation power can be obtained by considering accuracy and efficiency, the advantages of rapidness, flexibility and high plasticity of fan power adjustment are fully utilized, and the system frequency response dynamic characteristic is effectively improved.

The invention provides a zero sample image classification system and method, and the system comprises a teacher model and a student model which are the same in architecture, and each of the teacher model and the student model comprises a visual encoder, a semantic encoder, a visual-semantic alignment module and a zero sample classification module; a visual encoder of the teacher model is constructed in a manner of cascading a CNN (Convolutional Neural Network) and a Transform; selecting a BERT network as a semantic encoder of the teacher model; the visual-semantic alignment module is used for constructing a teacher model and a student model based on a cross-modal attention mechanism; a full connection layer is adopted as a zero sample classification module of the teacher model and the student model; a visual encoder of the student model is constructed by adopting a lightweight EnviroNet network; and a semantic encoder of the student model is constructed by adopting a Core-BER network. The method has the advantages that under zero sample setting, the high unseen category classification performance can be kept, meanwhile, the model complexity is reduced, and deployment on actual equipment is better facilitated.

The invention provides a work plan and task management system, which belongs to the technical field of work plan tasks and comprises a portal layer, an application program interface gateway layer, a business service layer, a public service layer and a data layer. And the application program interface gateway layer realizes intelligent management of the interface through a self-adaptive division module, wherein the intelligent management comprises dependency analysis, granularity calculation, aggregation optimization and recombination execution. The business service layer focuses on work plans and task management, and realizes collaboration through flexible interface interaction. The public service layer provides basic support for user authentication, log recording, message queue, service registration, configuration management and the like. And the data layer adopts a diversified storage strategy, integrates a relational database, a cache database, a time sequence database and distributed file storage, and meets data processing requirements of different scenes. The problem that in the prior art, interface definition and calling relations between micro-services are difficult to manage in a self-adaptive mode is solved.

The invention discloses a vehicle-mounted large model deployment method based on mixed granularity knowledge distillation. The vehicle-mounted large model deployment method comprises the following steps: performing mask initialization on coarse particle and fine particle structures in a pre-trained large model; initializing low-rank matrixes, wherein the matrixes are used for replacing original weight parameters of the model for updating in the distillation training process; setting a model loss function including knowledge distillation loss and regularization loss; in the model training process, the parameters of the pre-training model are kept unchanged, and only the low-rank matrix and the mask parameters are updated; performing model evaluation after training is completed, and checking whether the model after knowledge distillation meets performance requirements or not; if the evaluation result is not satisfied, returning to the training step for further optimization; a low-rank matrix and mask parameters are fixed, and the parameters are fused into an original model according to masks. The model after knowledge distillation can obtain the capacity of a large model in a small size, and is more suitable for being deployed in a vehicle-mounted system with limited resources so as to provide efficient calculation performance.

The invention discloses a method and a device for detecting and positioning surface defects of a PCB (Printed Circuit Board). The method comprises the following steps: acquiring a reference image and a sample image of the PCB; processing the light and shade distribution of the sample image to obtain a sample image with uniform illumination; correcting a pixel difference between the sample image and the reference image to enable the reference image and the sample image to achieve pixel-level alignment; carrying out defect detection index calculation on the reference image and the sample image according to regions, and detecting and positioning defects. According to the method, the detection accuracy and efficiency are improved, the hardware cost and the calculation overhead are reduced, and deployment and implementation in the actual production and manufacturing process are easy; meanwhile, due to the high automation attribute, the detection reliability and the flexible adjustment capability, the method has wide application prospects and practical value.

The invention discloses a distributed RIS fast beam forming method based on quantum annealing. Comprising three parts: phase quantization of discrete units, quantization mapping of variables and quantum annealing solution. The distributed RIS-assisted communication system comprises at least two RISs which are deployed at proper positions to assist guiding of communication signals. The phase quantization of the RIS reflection unit is used for constructing discrete variables, so that the corresponding variables can conform to the topological structure of the quantum computer and are mapped to quantum bits. The quantization mapping of the variables is based on a series of operations of fractional programming and matrix transformation, and an original optimization problem is mapped to an unconstrained Hamiltonian, so that the quantization mapping can be deployed on a quantum computer for annealing solution. And evolving a target function formed by the superposition state of the quantum states of the combination of all possible solutions according to a Schrodinger equation to find a global optimal solution.

The invention relates to the technical field of crayfish quality rapid detection based on a neural network, in particular to a light-weight crayfish quality rapid detection method based on pattern recognition, which comprises the following steps: firstly, collecting crayfish photographing data, then screening qualified images based on manual work, marking each image, and finally, carrying out pattern recognition on the marked images; according to the method, the crayfish detection precision is further improved by using the improved YOLOv8 network, the network model is lightened, and the deployment is more convenient, so that the detection efficiency is improved, the labor cost of manual detection is reduced, the commercial processing and classification requirements of the crayfish are better met, the characteristic of simpleness of traditional crayfish classification is overcome, and the method is suitable for large-scale popularization and application. And the processing and grading requirements of the commercial crayfish are met.

The invention discloses an electric power material supply management and control system and a method thereof. The electric power material supply management and control system comprises a master control center, a sub-control center, a material warehouse, a mobile control terminal and a data processing platform. The electric power material supply management and control method comprises the following steps: S1, material demand prediction; s2, intelligent scheduling; s3, performing real-time monitoring; s4, risk assessment and early warning; and S5, emergency response is carried out. The electric power material supply management and control system and the method thereof can improve the material supply efficiency, enhance the decision support capability, make the decision more accurate and efficient, help to optimize resource configuration, improve the overall operation efficiency, improve the transparency and visualization of a supply chain, enhance risk management, guarantee the safe and stable operation of a power grid, improve the emergency response speed, and improve the power supply efficiency. The resource allocation is optimized, the inventory cost is reduced, the fund utilization efficiency is improved, the optimal allocation of resources is realized, and the electric power material requirements of each region can be better met.

The invention belongs to the technical field of power equipment, and particularly relates to a multi-modal deep learning edge computing platform for power equipment. The edge computing platform comprises a data acquisition module, a data fusion module, a dynamic model updating module, an edge computing optimization module, an intelligent alarm and prediction module, an upstream and downstream data link integration module, an edge device resource management module, a security enhancement module and a simulation and emulation module. And the data fusion module performs splicing, weighted fusion or PCA mathematical transformation on the features of different modalities in the feature extraction stage to form a comprehensive feature vector, and performs fusion according to model output results of different modalities in the model decision-making layer, including use of a voting mechanism, weighted scoring or logistic regression. According to the invention, by integrating a multi-modal deep learning technology and an edge computing architecture, comprehensive performance improvement and cost saving are brought to power equipment monitoring and management.

The invention discloses a logistics positioning navigation system and method based on visible light communication. The system comprises a visible light transceiving array used for controlling an LED lamp to emit visible light carrying coded information of position information and service information; the navigation service module is used for processing the visible light with the coding information; the signal processing module is used for detecting the visible light with the coding information, calculating the initial position of the target cargo and correcting the initial position based on the processed visible light; and the path planning module is used for receiving the information of the signal processing module, displaying the position information of the target goods and planning a navigation path. According to the invention, the efficiency and accuracy of logistics operation are improved.

The invention relates to a conveying device for box posture adjustment, which comprises a conveying mechanism, a recognition mechanism and a posture adjustment mechanism, and the conveying mechanism comprises a rack and a roller conveying line. And the roller conveying line is erected on the rack. The recognition mechanism comprises a first portal frame, a recognition assembly and a control assembly. The recognition assembly comprises a camera. And the camera is used for identifying target characteristics of each surface on the box body. The control assembly is in communication connection with the posture adjusting mechanism and used for judging the real-time posture of the box body according to the position of the target feature and controlling the posture adjusting mechanism to adjust the box body to the target posture according to the real-time posture. The posture adjusting mechanism comprises a second portal frame, an overturning assembly and a rotating assembly. The overturning assembly is used for overturning the box body. The rotating assembly is used for driving the box body to rotate. Compared with the prior art, the conveying device for adjusting the posture of the box can formulate different adjusting strategies according to the real-time posture of the box to adjust the box to the target posture, and is small in size and high in adaptability.

The invention relates to the technical field of unmanned aerial vehicle dispatching, in particular to a disaster area emergency unmanned aerial vehicle networking method based on reinforcement learning, which comprises the following steps: taking an unmanned aerial vehicle as an intelligent agent, and taking horizontal and vertical coordinates, speed, direction, residual energy consumption and user throughput of the unmanned aerial vehicle as an observation space of the unmanned aerial vehicle; taking the speed scheduling scheme and the bandwidth allocation scheme of the unmanned aerial vehicle as an action space of the unmanned aerial vehicle; introducing a graph attention mechanism to aggregate observation features of adjacent unmanned aerial vehicles; based on the aggregated observation features, bandwidth allocation actions and corresponding rewards of the unmanned aerial vehicle under each speed scheduling are obtained; and introducing a Jain's fair index to measure the fairness of the service quality of the unmanned aerial vehicle in the region, and optimizing the speed scheduling and bandwidth allocation of the unmanned aerial vehicle. Under the condition of limited resources, the communication bandwidth is reasonably allocated, and the service coverage rate of the affected user is maximized.