453 results about "Feed forward network" patented technology

The invention provides a service prediction method and device based on a time sequence model, equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of historical time sequence data, and obtaining a training data set; performing fast Fourier transform on the training data set to obtain frequency domain data and frequency component intensity; extracting a plurality of main frequency components and corresponding period values from the frequency domain data, and determining a plurality of two-dimensional feature tensors according to the period values and the training data set; constructing L layers of time blocks including feature mapping, an attention mechanism and a feedforward network according to the two-dimensional feature tensor, and establishing residual connection between adjacent time blocks to obtain a time sequence model to be trained; performing feature extraction on each two-dimensional feature tensor by applying a multi-branch convolutional network to obtain a one-dimensional representation vector, and performing weighted fusion on the one-dimensional representation vector according to the frequency component intensity to obtain a fusion feature; and training the to-be-trained time sequence model through the fusion features, and outputting an analysis report of historical time sequence data.

The invention provides a complex scene-oriented AI large model lightweight deployment method, and relates to the technical field of edge computing, and the method comprises the steps: carrying out the structured pruning of a pre-trained Transform network based on the attention head importance score, carrying out the dynamic sparsification of the activation state of a feedforward network according to the input tensor entropy value, employing the dynamic mixing precision quantization, and carrying out the reconstruction of an AI large model. Obtaining network parameters after pruning quantization; deploying the pruned and quantized network parameters to an edge computing device, distributing a feature extraction operator to a neural network processor through a heterogeneous computing scheduler, and unloading a classification operator to a multi-core central processing unit; and managing an on-chip memory in combination with a virtual memory paging mechanism, realizing zero-copy data transmission by utilizing a direct memory access controller, and outputting a reasoning result tensor. According to the method, efficient and reliable operation of the large model at the resource-constrained edge node is realized.

The invention relates to an innovative embedded reconstructed text-image alignment style migration method, which comprises the following steps of: constructing a basic framework based on a diffusion model, and adding noise through a forward process and denoising to learn image style characteristics. And extracting style embedding from the artwork data set by utilizing perceptron attention and a feedforward network. Text embedding is generated through a text encoder, and guidance is provided for style migration. A cross attention mechanism is adopted to fuse style embedding and text embedding, multi-modal embedding is generated, and interaction of text and image information is optimized. And fusing multi-modal embedding and image embedding through linear interpolation, splicing with text embedding to form complete prompt embedding, and integrating the prompt embedding into a diffusion model to generate a style image matched with text description. According to the method, the quality and diversity of artistic image style migration are remarkably improved, the method has wide application potential in the field of artistic creation and design, rich and diversified stylized visual achievements can be provided, and the requirements of multiple creation scenes are met.

The invention provides an end-side multi-modal large model accelerated reasoning method and system, and the method comprises the steps: carrying out the two-stage screening and rearrangement of visual tokens based on the CLS attention and text-to-visual attention in a visual encoder and pre-filling stage, and constructing a sparse attention and sparse key value cache; in a decoding stage, an important neuron set is judged according to activation gating or historical statistics, only a corresponding feedforward network weight is pulled and calculated, missed weights are loaded on demand through asynchronous I / O, and hot neurons are maintained in a high-speed memory to utilize model sparsity, so that video memory / memory occupancy and calculation overhead are remarkably reduced on an end side; throughput and time delay performance are improved. According to the method, the internal memory and computing resources required by reasoning of the multi-modal large language model are reduced from two dimensions by utilizing the endogenous sparsity of the end-side large language model in input and the model, so that a higher reasoning speed is achieved by utilizing fewer resources on the premise of keeping the size of the model unchanged, and the performance of the whole system is improved.

The invention provides a Zip-MoE model grouping hybrid expert layer-based Chinese and English speech recognition method and system, a Zip-MoE model comprises six encoder blocks, a Bypass module is included between every two encoder blocks, and the weights of the output of the previous encoder block and the output of the current encoder block are learned; the first three encoder blocks are of a standard Zipform structure; the last three encoder blocks adopt a Zipform-MoE structure containing a grouped hybrid expert layer, and the grouped hybrid expert layer is used for replacing the last feed-forward network of the Zipform structure; the grouping mixed expert layer comprises a Chinese expert group, an English expert group and a language router, and each expert group is composed of a plurality of expert networks and is provided with an unsupervised router. The problem of language confusion is relieved, different time delay streaming scenes can be adapted, the number of experts is flexibly expanded, pre-training is not needed, and the Chinese and English recognition efficiency is greatly improved.

The invention discloses a multi-mode electroencephalogram analysis model construction method and an online processing method and system. According to the method, multi-modal physiological signals such as electroencephalogram, electrocardio, skin electrical activity and eye movement are collected, and an integrated multi-modal signal collection device is used for preprocessing and feature extraction. A modal expert system based on an adaptive Transform architecture is adopted to replace a standard feed-forward network so as to enhance the feature processing capability. By means of the method, the features can be complemented under the condition of mode or data missing, the robustness, real-time performance and accuracy of the brain-computer interface technology in multi-mode data processing are improved, and the method is particularly suitable for the fields of emotion recognition, cognitive load monitoring, neural rehabilitation and the like.

The invention discloses a low-light image denoising method based on a local-global interactive Transform, and the method is characterized in that the method comprises the following steps: 1, carrying out the denoising of a low-light image; the method comprises the following steps: step 1, constructing an overall structure of LGIT for recovering a given degraded image; 2, a Top-N Patches selection module is used for selecting N patches most related to the target patch and providing feature input for subsequent modules; step 3, the Patch selects an attention Transform module, and the Transform module is used for carrying out global feature aggregation based on the information of Top-N Patches; and step 4, mixing the double-gate feed-forward network MDGFF for further processing the features output by the PSATB and generating a final de-noised image. According to the method, the self-attention inside the patch and between the patches is effectively calculated on different scales, and accurate removal and detail recovery of low-light image noise are realized.

The invention is applicable to the technical field of artificial intelligence, and provides a cross-modal retrieval method and device, electronic equipment and a storage medium, and the method comprises the following steps: encoding an image modal through an image encoder, encoding a text modal through a text encoder, and generating a vector representation of a high-dimensional space; inputting the vector of the image mode and the vector of the text mode into the same shared self-attention layer for alignment, and extracting features through respective feedforward network layers; performing cross-modal cross fusion processing on the vector of the image modal and the vector of the text modal through a cross attention mechanism to obtain a cross-modal representation vector of the image modal and a cross-modal representation vector of the text modal; and based on the cross-modal representation vector of the image modality and the cross-modal representation vector of the text modality, outputting the similarity of the image modality and the text modality. According to the method, the cross-modal retrieval precision can be improved.

The invention provides an image recognition and classification method, system and device and a medium, and belongs to the field of image model optimization. The method comprises the following steps: acquiring a to-be-processed image, and carrying out normalization and zooming processing on the image to generate a target image; performing block processing and vectorization processing on the target image to generate a plurality of image blocks containing one-dimensional vectors as initial feature vectors; inputting the initial feature vector into a hybrid expert module, and calculating a routing weight of an expert network through a gating mechanism; activating the expert network for processing the data by adopting a sparse activation mechanism based on the calculated routing weight; outputting a feature vector according to the initial feature vector by using the MoE layer based on the activated expert network; and performing aggregation processing on the feature vectors through a multi-head self-attention mechanism and a feedforward network, and generating a classification result of the to-be-processed image by using a classifier. The invention provides an efficient, flexible and excellent-performance solution for the field of image recognition and classification.

The invention discloses a remote sensing image change detection method and system based on Transform and graph semantic guidance in the technical field of image processing. In an overall framework, a CNN (Convolutional Neural Network) and a Transform multilayer are connected in series and in parallel, a novel graph semantic module (GSM) is also constructed, and the purpose is to guide the network to carry out more detailed feature extraction through graph semantic features. In the module, each channel of a feature map is regarded as a feature vertex, an adjacent matrix is used for representing the relationship between the channels, and the capturing capability of the model on the long-distance dependency relationship is enhanced through multi-hop neighbor aggregation, so that the map semantic features with richer information are obtained. The graph semantic features are used for guiding trunk features extracted by the network in a subsequent Semantic Fusion Transform Module (SFTM), and the graph semantic features and the trunk features are interactively updated in a self-adaptive mode. Wherein the SFTM is mainly composed of cross attention used for completing information exchange, a local information compensation layer used for supplementing local information loss and an enhanced feedforward network used for optimizing input. According to the method, the performance of the network can be improved, and the change detection precision is improved.

The invention discloses a medical image classification method and system based on multi-scale spatial state modeling, and the method comprises the steps: firstly dividing an input medical image into a plurality of non-overlapping image blocks, and mapping the non-overlapping image blocks to a feature space through a learnable linear projection layer to obtain an initial feature map; then, multiple layers of stacked MS-SMamba blocks are used for carrying out layer-by-layer feature extraction, each MS-SMamba block comprises a main branch, an auxiliary branch, a dynamic gating fusion network, a residual error connection unit and a feedforward network, and long-range dependency relation capture and multi-scale feature fusion are achieved; and finally, processing the last-layer output feature map through a global feature aggregation and classification module, generating a global feature vector, and outputting a classification result. According to the method, the capturing capability of complex pathological features in the medical image is improved, the calculation efficiency and clinical applicability are improved, and the method is suitable for scenes such as disease screening and auxiliary decision making in medical image diagnosis.

The invention provides a remote sensing image super-resolution reconstruction method and system based on residual hierarchical Transform, and relates to the technical field of digital image processing, and the method comprises the following steps: obtaining a low-resolution image; performing shallow feature extraction on the input low-resolution image through convolutional layer operation to obtain a shallow feature image; secondly, on the basis of the design concept that residual blocks are nested in residual groups, a multi-scale feature calibration mechanism, a Transform space-channel attention mechanism based on a hierarchical window and a space-gate feed-forward network are combined, and a depth feature image is obtained; and finally, performing fusion and up-sampling on the shallow feature image and the depth feature image through convolution and sub-pixel convolution operation to obtain a final remote sensing image super-resolution reconstruction result. By means of the scheme, the remote dependency relationship in the remote sensing image can be effectively modeled, the feature extraction capacity can be improved, and the problem that large-scale window self-attention calculation is high in complexity in a Transform mechanism can be solved.

The invention discloses a road defect detection method based on an improved RT-DETR-R18 model. A backbone network adopts a CSPNet architecture. According to the invention, innovative improvement is carried out on an original C2f module, and Bottleneck in the original C2f module is replaced by DynamicIncMixerBlock to form a C2fDCMB module. The DynamicIncMixerBlock is characterized in that a DynamicIncMixerBlock is fused with a DynamicInceptionMixer component and a ConvolutionalGLU component, and the DynamicIncMixerBlock and the ConvolutionalGLU component are fused with each other. A dynamic Inception deep convolution structure is adopted by the DynamicInception Mixer, and features of different scales and directions are adaptively captured through dynamic kernel weight distribution; according to the method, AIFI (intra-scale feature interaction) in a high-efficiency hybrid encoder is improved, a module is combined with an EfficentAdditiveAttach and a feedforward network structure to form TransformerEncoder LayerEfficentAdditiveAttach, a RepC3 module is replaced by a RetBlockC3 module in a cross-scale feature fusion module (CCFM) through a multi-head attention mechanism and a nonlinear activation function, the RetBlockC3 is improved based on the RepC3, RetBlock and RelPos2d are introduced, and the RetBlock and RelPos2d are introduced into the RetBlockC3 module to form a multi-scale feature fusion module. According to the method, the accuracy, recall rate and detection speed of road defect detection are obviously superior to those of a traditional detection model, and a more accurate and efficient technical solution is provided for maintenance of road infrastructures and traffic safety guarantee.

The invention provides a magnetic particle imaging resolution improving method and system based on frequency domain information filtering, and relates to the technical field of magnetic particle imaging. Comprising the following steps: inputting original magnetic particle imaging data into a Transform model, and selectively filtering frequency domain information in the magnetic particle imaging data through a fusion frequency domain discrimination feedforward network module in an encoder to obtain the output of the encoder; inputting the output of the encoder into a bottleneck layer, aggregating global and local information through a multi-scale attention mechanism module, and then selectively filtering frequency domain information in the magnetic particle imaging data again to obtain the output of the bottleneck layer; inputting the output of the bottleneck layer into a decoder with the same structure as the bottleneck layer to obtain deep features; inputting the deep features into a convolutional layer to obtain a residual image; and calculating the sum of the original magnetic particle imaging data and the residual image to obtain a reconstructed image. According to the invention, the overall imaging resolution of the MPI image under the low-gradient field acquisition condition is improved.

The invention discloses a power transmission line insulator multi-modal multi-type defect detection method based on an MEWL-YOLO model. The method comprises the following steps: acquiring a multi-modal power transmission line data set; constructing an insulator multi-type defect detection model of the MEWL-YOLO model; the method specifically comprises the steps that on the basis of a YOLOv10n network framework, a multi-head attention mechanism and a gated convolution feedforward network are combined, a multi-head gated convolution feedforward network MGDB module is designed, and a C2K layer is optimized; a multi-scale efficient attention mechanism (EMA) is inserted into the Neck part of the YOLOv10n network; an Inner-Wise-MPDIOU loss function is adopted to replace a traditional loss function; a detection head in a YOLOv10n network is replaced by an LSCD lightweight detection head, and defect detection is carried out on the power transmission line insulator based on an insulator multi-type defect detection model of a constructed MEWL-YOLO model. According to the method, the MEWL-YOLO model is provided to realize defect detection of the multi-modal power transmission line insulator image, the detection effect of multi-modal and multi-type defects is improved, and the method has good practical application value.

The invention discloses a physical-data dual-drive retaining wall catastrophe robustness evaluation method, and relates to the technical field of structure catastrophe evaluation and computer science crossing. Aiming at the problems that an existing retaining wall catastrophe robustness evaluation method cannot correct physical model errors in real time and is insufficient in accuracy, the invention provides a retaining wall catastrophe process robustness evaluation method driven by fusion of a physical model and a neural network. The method comprises the following steps: 1, carrying out time discretization and parameter vectorization on retaining wall catastrophe monitoring parameters; 2, constructing a performance attenuation function based on the physical model; 3, updating an implicit damage state in combination with a neural network Cell module; 4, correcting an error through a feedforward network to obtain a total performance attenuation function; and 5, finally calculating a robustness index and outputting a corresponding robustness grade, thereby realizing quantitative evaluation of the retaining wall catastrophe robustness. Reliable quantitative support can be provided for retaining wall design optimization, operation monitoring and post-disaster recovery evaluation.

The invention discloses an adaptive TimeXer model photovoltaic power prediction method and system based on weather typing, and belongs to the technical field of photovoltaic power generation, and the method comprises the steps: dividing a historical photovoltaic power sequence into time patches, carrying out PatchEmbedded projection on the time patches to generate time stamps, and generating learnable global stamps; the method comprises the following steps: carrying out standardization processing on meteorological data, carrying out clustering to generate a weather classification label, converting the weather classification label into a discrete variable label, and carrying out Variate Embedded projection on the standardized continuous meteorological data to generate a continuous meteorological factor; performing endogenous self-attention calculation on learnable global marks, continuous meteorological factors and discrete variable marks to obtain attention weights among the time marks, aggregating the continuous meteorological factors and the discrete variable marks by using the attention weights among the time marks through cross attention processing, and inputting multi-scale feature marks into a feedforward network to obtain a multi-scale feature mark; and adjusting the frequency domain of the predicted value by using a Fourier mixing layer to obtain a final prediction result.

The invention provides an image deblurring method based on combination of a CNN (Convolutional Neural Network) and a Transform. According to the method, a training set, a verification set and a test set are prepared by using a public data set; in an encoder stage, inverse residual fast Fourier transform is adopted to extract features of an input blurred image, and a pixel attention feature fusion module is used. A channel modulation self-attention mechanism and a mixed scale feedforward network are introduced into the decoder part, global context modeling is achieved, and more information is obtained. In addition, a same-scale feature fusion module is also applied in the decoder, so that the hierarchical information of the image is learned and the feature representation is enriched. In the method, a small U-shaped network is used for multi-scale learning in the first layer of the decoder and in the feature enhancement network. And finally, combining the enhanced features with the original image to generate a clear deblurred image. According to the method, by optimizing model parameters and introducing multiple innovative mechanisms, the image deblurring effect and the generalization and robustness of the model are improved.

The invention discloses a double-branch pyramid attention time sequence prediction method, which belongs to the field of time sequence prediction, and comprises the following steps of: supplementing and standardizing input sequence deletion, and embedding and aligning time covariables; a horizontal branch coding time domain and a vertical branch coding variable are dynamically fused to obtain a unified feature; multi-scale representation is formed through multi-layer convolution down-sampling, and information interaction is completed through local-cross-scale mask attention. The result is subjected to pyramid residual normalization and feedforward network updating, a global context is generated through multilayer stacking, and a linear head outputs future multi-step prediction. The complexity of the method is O (L log L), long-range dependence and a fine-grained mode are captured at the same time, the method is remarkably superior to thirteen existing models on five data sets including ECL, Exchange and Trafic, and the method has the advantages of being high in precision, high in speed and easy to expand.

The invention discloses an oil-filled cable multi-leakage-point positioning method and system, and relates to the technical field of oil-filled cable leakage point localization, monitoring parameters and cable parameters of a to-be-detected oil-filled cable are acquired, state information of the to-be-detected oil-filled cable is determined according to the monitoring parameters, and when the state information is cable leakage, the to-be-detected oil-filled cable is detected. If yes, leakage point positioning is conducted on the oil-filled cable to be detected, a single leakage point position is obtained, a multi-leakage-point digital twinborn model is constructed by combining cable parameters, multi-leakage-point leakage working condition monitoring is conducted on the multi-leakage-point digital twinborn model through the monitoring parameters, and when the monitoring result is that the oil-filled cable leaks for the second time, the single leakage point position is obtained; if yes, the multi-leakage-point digital twinborn model, the monitoring parameters and a preset feedforward network model are adopted for leakage point positioning, a second leakage point position is obtained, the second leakage point position is adopted for updating the multi-leakage-point digital twinborn model, and the step of monitoring the multi-leakage-point leakage working condition of the multi-leakage-point digital twinborn model through the monitoring parameters is skipped to be executed. The technical problem that multiple leakage points cannot be positioned in the prior art is solved.

The invention provides a lightweight low-dose CT (Computed Tomography) (LDCT) image denoising method based on a Transform network, and belongs to the technical field of medical image processing. The method provided by the invention is called CT-Denomer, global context information in a CT image and local context details of complex space change can be captured, and a high-quality image is generated. A core of a framework of the CT-Denoimmer is a Transform module, and the CT-Denoimmer comprises two key components, namely a multi-head convolution transpose attention (MDTA) and a hybrid context feedforward network (MCFN). The MDTA module captures global context information in an image with linear computational complexity, while the MCFN module pays attention to multi-scale local static and dynamic context information through a series of enhanced context Transformer blocks (eCoT). Besides, an intelligent operation attention layer (OWALs) is introduced to cope with a complex and changing noise mode in the LDCT image, so that the network can optimize the denoising effect in diversified scenes. According to the method, the fine structure retention and noise suppression of the denoising result of the LDCT image reach advanced performance.

The invention discloses a privatized large model construction method and system based on generative artificial intelligence, and relates to the technical field of privatized large models, and the method comprises the steps: obtaining a data source through an enterprise internal system or a financial database, carrying out the data preprocessing, and building a privatized large model. Feedforward network parameters are adjusted and optimized based on an ecological niche dynamic optimization algorithm, and a network training process is optimized based on a self-encoding neural network algorithm of unbalanced dynamic optimization. According to the method, the problem that a traditional optimization algorithm is likely to fall into local optimum in high-dimensional financial data is effectively solved, rapid changes and complex characteristics of data in the financial market can be better dealt with, the robustness of the model in the face of abnormal values, noise and extreme events in the financial data is improved, and the stability and prediction accuracy of the model are enhanced.

The invention provides a hierarchical hybrid structured compression method and device for a large language model, and relates to the technical field of artificial intelligence, and the method comprises the steps: determining the compression ratio of each layer of a target model based on the importance degree of each layer of the target model; based on the compression ratio of each layer, compressing the target model to obtain a compressed model; wherein the compression of the target model comprises the following steps: for a current processing layer, calculating a two-norm of an input activation value corresponding to each weight of the current processing layer on a calibration data set to obtain a characteristic norm; under the condition that the current processing layer is the multi-head attention sub-layer, performing weighted low-rank decomposition and differential singular value distribution processing on the current processing layer based on the characteristic norm of the current processing layer and the compression ratio of each layer; and under the condition that the current processing layer is the feedforward network sub-layer, performing channel pruning and compensation processing on the current processing layer based on the characteristic norm of the current processing layer and the compression ratio of each layer. Therefore, the compression ratio and the performance balance of the LLM are realized.

The invention relates to a complex medium inversion imaging method and system guided by a physical information neural network, and the method comprises the steps: constructing a two-dimensional grid model of a block structure with different medium distributions, obtaining out-of-plane displacement data at grid points through staggered grid finite difference, and forming a wave field full-waveform data set; constructing a physical information neural network, wherein the physical information neural network comprises a first feed-forward network for modeling a mapping relation of a displacement field of the sample, a second feed-forward network for modeling a velocity field of the sample, and a residual network; based on the wave field full-waveform data set, training a physical information neural network by taking minimization of compound loss as a target; and taking the space-time coordinates of the sample as input, and utilizing the trained physical information neural network to obtain predicted displacement and sound velocity of the corresponding position of the space-time coordinates, so as to realize inversion imaging of sound velocity medium distribution. According to the method, the ultrasonic propagation model of the complex medium can be quickly and accurately established under the condition that a small amount of marked data is used.

The invention relates to a Chinese grammar error correction method and system based on large model fine tuning. According to the method, a Qwen2-7B model is used for generating an error correction instruction data set; screening the instruction data set according to complexity, quality and diversity; performing supervised fine tuning on the Qwen2-7B model by adopting an LORA method, and emphatically optimizing a self-attention layer and a feedforward network layer so as to enhance the processing capability of the model on long-distance dependence and context information; then, a Qwen2-72B model is used for scoring the error correction data set, preference tags are generated, and the Qwen2-7B model is further optimized by using the tags, so that the response quality of the Qwen2-7B model is improved; a direct preference optimization method is used, a preference data set is combined to train the model, and parameters are adjusted to minimize a loss function, so that the tendency of the model to preference response is enhanced. According to the method, the accuracy of Chinese grammar error correction is effectively improved through a multi-level optimization strategy.

A processor-implemented method for converting a trained language model into a language model in an architecture of mixture of experts (MoE), and a computing device using the same is provided. The method for converting a trained language model into a language model in an architecture of mixture of experts using a computing device according to an embodiment of the disclosure may include dividing a plurality of layers included in a target language model and extracting a feed-forward network (FFN) included in each of the plurality of layers, generating an MoE block of the MoE language model, which corresponds to the feed-forward network, generating an input tensor, comparing output tensors between the feed-forward network and the MoE block for the input tensor to obtain a first loss, and updating a weight of the MoE block, based on the first loss.

The invention discloses an oil and gas exploitation stratum rapid prediction method and device, a storage medium and equipment, and belongs to the technical field of oil and gas field development. Comprises: constructing a data set; the data set comprises logging parameters of multiple wells in the target work area; constructing a deep learning model; the deep learning model comprises an encoder and a decoder, the encoder comprises a set number of encoder layers, and each encoder layer comprises a multi-head self-attention sub-layer and a full-connection feedforward network sub-layer; the decoder comprises a set number of decoder layers, and each decoder layer comprises a mask multi-head self-attention sub-layer, a multi-head self-attention sub-layer and a full-connection feedforward network sub-layer; training the constructed deep learning model through the data set, and iteratively updating parameters to obtain optimal model parameters; and obtaining logging parameters of a to-be-logged well and inputting the logging parameters into the trained deep learning model to obtain a stratum prediction result. The method has the advantages of higher prediction precision, higher prediction speed and higher applicability.

The invention relates to the field of well drilling anomaly detection, and discloses a well drilling abnormal vibration working condition detection method, device, equipment and medium, which can be realized by using a trained abnormal vibration working condition detection model, and the model comprises a multi-head self-attention layer, a feedforward network layer and a full connection layer. According to the invention, the multi-modal vibration data can be collected in the drilling operation, the multi-modal vibration data is input into the trained abnormal vibration condition detection model, and the multi-head self-attention layer efficiently captures the potential long-range dependency relationship among different modal vibration data in the multi-modal vibration data through a self-attention mechanism. And generating a multi-modal feature vector, and performing label detection by the feed-forward network layer and the full-connection layer according to the multi-modal feature vector output by the multi-head self-attention layer, thereby realizing detection of the abnormal vibration working condition of the drilling well and obtaining an abnormal vibration working condition detection result. The method can enrich the detection means of the abnormal vibration working condition in the drilling operation, and effectively improves the detection accuracy of the abnormal vibration working condition.

The invention discloses a feature hierarchical attention fusion and dynamic optimization method for single-stage target detection, and relates to the technical field of computer vision. The method comprises the steps of collecting image data, preprocessing an image and dividing the image into a training set, a test set and a verification set; the HAF-DRFPN neck network uses dynamic up-sampling single pixel point sampling to recover the feature resolution; feature extraction is optimized by using a gating residual mechanism and depth separable convolution; a feature refining feed-forward network is introduced through multi-layer perception generation weight, and feature expression is enhanced; respectively capturing and fusing superficial details and deep semantic information by utilizing channel and space attention and cross attention; a multi-branch dynamic sampling stacking framework is adopted, and cross-scale features are adaptively fused and optimized; multi-module cooperative processing is carried out on the whole architecture, and multi-scale features with higher discrimination are provided for the detection head; according to the method, the YOLO12 trunk and the detection head are connected with the HAF-DRFPN to form the model HAF-DRNet suitable for target detection, so that the flexibility and accuracy of single-stage target detection are improved.

The invention relates to a GAI-BRI-based air pollutant concentration interpolation prediction method and device and a medium, and the method comprises the steps: carrying out the interpolation prediction of the concentration of air pollutants according to the extracted air pollutant concentration, meteorological data and satellite data of a plurality of distribution sites in a given region within a given time range; constructing an air pollutant concentration diagram for describing pollutant conditions in a given time range and a given area range; inputting the numerical value of the air pollutant concentration diagram into a GAT-BRI prediction model to obtain an air pollutant concentration interpolation prediction result in a period of time in the future; wherein the GAT-BRI prediction model comprises a graph attention network GAT which is arranged at a bottom layer and is used for extracting spatial features from an air pollutant concentration graph, and a bidirectional cyclic interpolation network BRI which is arranged at a middle layer and is used for extracting time sequence features from the spatial features output by the graph attention network; and the feed-forward network is arranged at a high layer and is used for outputting an interpolation prediction result. Compared with the prior art, the method has the advantages that the spatial dependence and time dependence relationship among multiple cities can be fully mined, and the prediction accuracy is high.