239 results about "Adaptive compression" patented technology

The invention relates to the technical field of computer vision and image recognition, in particular to an image recognition method based on edge computing, which comprises the following steps: dynamically capturing an original image through a plurality of edge nodes, rejecting redundant regions through a multi-modal perception triggering mechanism, and establishing a cooperative processing group. Illumination equalization, noise filtering and resolution self-adaptive compression tasks are distributed according to dynamic role election, a standardized preprocessed image is generated, a lightweight convolutional neural network is operated in parallel to extract a dual-channel feature vector, and after entropy coding lossless compression and equipment identity tag and time sequence stamp attachment, the dual-channel feature vector is transmitted to a cloud end by adopting a lightweight encryption protocol. The cloud end analyzes the data packet, reconstructs a feature topological graph based on space-time relevance, loads a depth residual error recognition model to execute feature fusion and classification decision, feeds back and updates the weight of an edge node model, solves the problems of low collaborative efficiency and feature distortion, and improves the efficiency and precision of image recognition.

A system and method for processing genomic data using dynamic latent manifolds that transforms multi-modal genomic datasets into geometric representations within a curved manifold space. The system receives genomic datasets including DNA sequences, genetic variants, and expression data, then extracts biological features and assesses importance using trained neural networks. Manifold curvature values are computed based on biological significance, and genomic data is embedded as geometric structures where semantic relationships are represented through distance and curvature properties. The system generates compression pressure fields that influence processing decisions and computes optimal geodesic paths through the manifold to minimize cognitive action functionals. Adaptive compression rates are determined for different genomic regions based on geometric properties and biological importance. The manifold structure evolves through use, strengthening frequently accessed pathways while applying thermodynamic decay to unused concepts. The system supports hierarchical organization across biological scales, reversible navigation, and federated learning capabilities that enable privacy-preserving collaboration.

The invention relates to the technical field of data compression, in particular to an intelligent data compression method and system based on multi-protocol heterogeneous equipment interconnection. The method comprises the following steps: when it is detected that a new heterogeneous device applies to join a network, carrying out communication protocol real-time analysis and protocol conversion adaptation to obtain a heterogeneous device adaptation protocol; carrying out multi-device data stream receiving according to a heterogeneous device adaptation protocol, and generating data streams of a plurality of time windows; adaptive coding and multi-level compression are carried out on the data streams of the multiple time windows, and a multi-device adaptive compression mechanism is constructed; identifying compression load characteristics of each heterogeneous device, and performing dynamic task allocation to obtain an intelligent task allocation strategy; and driving real-time data intelligent compression operation based on an intelligent task allocation strategy and a multi-device adaptive compression mechanism. According to the invention, efficient and adaptive data compression of different devices is realized, and the data transmission efficiency and quality are improved.

The invention discloses a time synchronization method suitable for a satellite communication system, and the method comprises the steps: analyzing a forward broadcast signal, and obtaining the reference time of a network clock; constructing a geometric prediction handle based on satellite orbit data, and predicting one-way propagation time delay between a terminal and a satellite by using the geometric prediction handle; estimating the processing delay of the terminal according to the symbol rate and the equipment working condition of the terminal and the delay calibration data; fusing the network clock reference time with the processing delay estimate to synthesize a terminal local time; and the sending time of the return link is calculated based on the local time and the propagation delay prediction. According to the method, the synchronization precision can be improved to a microsecond level, the convergence speed in a dynamic scene is accelerated, adaptive compression of the guard interval is supported, and the stability and spectrum efficiency of a satellite communication system are effectively improved.

The invention discloses a customized production-oriented edge node lightweight AI model adaptive compression method, which belongs to the technical field of intelligent manufacturing and edge computing, and comprises the following steps of: dynamically integrating compression strategies such as pruning, quantification and knowledge distillation by analyzing demand constraints and edge node hardware resources of customized production tasks; constructing an adaptive decision engine by utilizing reinforcement learning and Bayesian optimization, and generating an optimal compression scheme; in the deployment stage, compression parameters are dynamically adjusted through real-time monitoring and a closed-loop feedback mechanism, and the balance of model precision, reasoning efficiency and resource occupation is achieved. According to the method, the adaptability of the model in a heterogeneous edge environment can be remarkably improved, the deployment cost is reduced, and the small-batch and multi-task quick response requirement in a customized production scene is met.

The invention provides a communication segmentation learning system and method for adaptive channel compression, and a medium, and relates to the technical field of segmentation learning and communication compression. The system comprises a plurality of clients, a server side and a channel compression device arranged between the clients and the server side, the channel compression device comprises a channel sensitivity modeling module, a rate distortion adaptive compression module and a cross-client fair coordination module. In a channel sensitivity modeling module, channel importance is dynamically evaluated through intermediate layer activation value fusion; differentiated quantization and compression strategies are designed on the basis of sensitivity scores in a rate-distortion self-adaptive compression module, so that key information is reserved while communication overhead is reduced; and meanwhile, the cross-client fair coordination module realizes balanced distribution of communication resources among multiple clients through a fairness regularization and dual optimization mechanism, so that the influence of excessive compression on global convergence is avoided. According to the method, the communication efficiency and the training stability of segmentation learning in a complex heterogeneous environment are remarkably improved.

The invention relates to the technical field of artificial intelligence and big language model reasoning optimization, and discloses a big language model-oriented adaptive KV cache compression method and system, and the method comprises the steps: constructing a lexical element importance measurement mechanism; analyzing an attention head distribution structure in large language model reasoning, and constructing a plurality of pruning strategies; based on a lexical element importance measurement mechanism and the attention head distribution structure, designing a self-adaptive key value cache compression hybrid strategy set based on a pruning strategy; constructing a static self-adaptive key value cache compression method, and automatically distributing a key value cache compression strategy in a pre-filling stage of large language model reasoning; and in a decoding stage, performing adaptive compression on the key value cache based on the allocated key value cache compression strategy. According to the method, the key value cache can be efficiently compressed on the premise of not depending on explicit attention score calculation, a system-level reasoning optimization framework is compatible, the generation performance is kept, meanwhile, the video memory consumption is remarkably reduced, and the long context reasoning capability is enhanced.

The invention provides a multi-database automatic synchronization method under an AI platform, and belongs to the technical field of database automatic synchronization. The captured change records are converted into synchronous messages in a unified format, the synchronous messages are input into an intelligent scheduling optimization model for dependency analysis and transaction reordering based on dynamic programming, data conversion rules are dynamically generated according to mode version differences, and data consistency is verified through a Merkle tree hierarchical structure; the multi-stage self-adaptive compression transmission and data writing are completed after the target node executes conflict detection and circular dependency processing, and finally the final consistency among the multiple databases is guaranteed through a periodic full-amount account checking task, so that the technical problem of synchronization performance bottleneck caused by low transaction scheduling efficiency in the automatic synchronization process of the multiple databases is solved.

A collaborative transformation matrix learning system extends adaptive compression and encryption architectures through federated, privacy-preserving optimization. Each node analyzes local data distributions to generate anonymized distribution profiles using differential-privacy mechanisms, securely exchanging profiles and validated transformation matrices across a collaborative network. A trust and validation engine verifies mathematical properties and evaluates claimed performance metrics. Validated matrices are integrated into local optimization when trust and performance thresholds are satisfied. The system employs secure multi-party computation, homomorphic encryption, and conflict-resolution logic to ensure integrity of shared insights while preventing exposure of sensitive information. By combining collective learning with local adaptation, the invention accelerates convergence to optimal matrix configurations, mitigates cold-start inefficiencies, and improves compression-encryption efficiency and cryptographic strength across distributed deployments.

The invention discloses a memory management method and related equipment, and relates to the technical field of data storage, the method comprises the following steps: based on access information of memory pages of a target operating system, determining a dynamic popularity score of each memory page; on the basis of the current memory pressure level and the dynamic popularity score of the target operating system, executing a corresponding hierarchical data migration strategy so as to migrate different memory pages to the corresponding main Swap storage space or auxiliary Swap storage space; adjusting a compression algorithm applied to the auxiliary Swap storage space based on the current central processing unit utilization rate of the target operating system; and detecting real-time states of the main Swap storage space, the auxiliary Swap storage space and the physical memory, and adjusting a hierarchical data migration strategy and a compression algorithm based on a detection result. Through dynamic popularity perception, hierarchical data migration, adaptive compression regulation and cross-layer collaborative optimization, the memory utilization rate, the exchange efficiency and the overall system stability can be improved under different system loads.

The invention discloses a high-resolution and low-delay audio and video transmission method and system, which realize high-quality and low-delay remote audio and video transmission by dynamically negotiating transmission resolution and self-adaptive compression coding. The method comprises the following steps: constructing a resolution negotiation matrix through extended display identification data based on receiving end equipment, and determining an optimal transmission resolution parameter; the compression ratio is dynamically adjusted in combination with network bandwidth fluctuation, a compressed data stream is generated by adopting inter-frame prediction coding, and the anti-interference capability is enhanced through forward error correction and time division multiplexing packaging; and finally, the differential signal pair is transmitted to a receiving end to be decoded and restored into a standard audio and video signal. According to the method, the transmission delay is remarkably reduced while the high-resolution image quality is ensured, the method effectively adapts to a complex network environment, the transmission distance and stability are considered, and the method is suitable for application scenes such as remote conferences and real-time monitoring which have high real-time requirements.

The invention relates to the field of multi-modal neural network model compression, and particularly discloses a multi-modal model compression and distillation method and system based on causal reasoning, and the method comprises the steps: constructing a comprehensive causal discovery module, identifying a causal dependency relationship among the multi-modal features through information theory measurement, Granger causal analysis and intervention-based verification; executing an adaptive compression engine, and performing pruning, mixing precision quantification and low-rank decomposition based on a causal relationship; a cross-modal distiller is applied, and multiple loss function combinations are adopted to maintain the relationship between modals; and implementing a dynamic optimizer to carry out hardware perception and context-sensitive reasoning optimization. According to the method, the compression decision is guided through causal reasoning, the high compression rate is achieved while the key causal path is kept, and the deployment problem of the multi-modal model in the resource-constrained environment is effectively solved.

The invention discloses a rotary steerable drilling trajectory prediction method based on deep learning and knowledge distillation, and belongs to the technical field of drilling trajectory prediction, and the method comprises the following steps: collecting rotary steerable drilling site ground data and while-drilling well logging data, and carrying out data preprocessing; constructing a teacher model and training; the teacher model comprises a well drilling feature enhancement module and a sequence change prediction module; a teaching assistant model is constructed and trained, and the teacher model is assisted to carry out multi-interlayer data adaptive compression; a composite knowledge distillation framework and a student model are built, the student model is trained, and the trained student model is a lightweight borehole trajectory prediction model; during field application, ground data and logging-while-drilling data are preprocessed and then sent into the lightweight well track prediction model, a well track prediction value in the rotary steering drilling process is obtained, and therefore drilling operation parameters are adjusted in time according to a prediction result. According to the method, high-precision and light-weight well track prediction is realized.

The invention belongs to the technical field of petroleum and natural gas engineering, and particularly relates to a logging data intelligent inversion method fusing an attention mechanism and a convolutional neural network, and the method comprises the steps: S100, selecting a borehole which is subjected to well drilling and logging as a research well, and obtaining the drilling, logging and logging data of the research well; s200, constructing a unified depth reference of well drilling, well logging and well logging data, and improving the resolution of the well drilling and well logging data by adopting an interpolation method; s300, constructing an attention mechanism module based on a multi-scale adaptive compression excitation network, and improving the modeling capability through triple mechanisms of multi-scale feature perception, adaptive compression proportion adjustment and residual enhancement attention weight; s400, constructing a feature extraction and regression prediction network based on a one-dimensional convolutional neural network; s500, supervised learning training is carried out on the inversion model until comprehensive evaluation index requirements are met; and S600, intelligent prediction and inversion of the logging curve are carried out by using the trained model. According to the invention, intelligent and efficient inversion of the logging data by using the low-cost drilling and logging data is realized.

The invention provides an edge-collaborative point cloud data modeling and building design collaborative management method and system, electronic equipment and a storage medium, and relates to the technical field of edge computation.The method comprises the steps that city multi-source point cloud data is collected through a mobile scanning device, and time-space reference synchronization is conducted through an edge node dynamic transmission channel to generate a unified data set; detecting terrain contour features based on the environment sudden change index, triggering to re-collect updated data and generating scene constraint parameters; density self-adaptive compression is executed, a compression data set with adjustable partition precision is generated in combination with vegetation and temporary building distribution, and spatial topological features are extracted; inputting a building rule base to start distributed collaborative optimization to generate a design model; the model boundary is compared with the topographic change, the space conflict is solved through geometric structure adjustment, the closed-loop cooperative management adaptive to the environment contour is realized, the closed-loop cooperative control of the building design and the actual topographic data can be realized, and the space conflict is effectively avoided.

The invention discloses a method and equipment for compressing multi-dimensional data based on column storage and self-adaption, and the method comprises the steps: recombining original multi-dimensional data into a column data set structure, and organizing data block storage for the column data set structure according to a hierarchical structure; each data block stores observation grid data of a single variable of multi-dimensional data at a certain moment so as to support column type storage and self-adaptive compression; and carrying out real-time statistical analysis on characteristics or parameters of variables in the data blocks, and dynamically selecting and configuring a filter and parameters thereof to compress the multi-dimensional data. The data of the same variable are stored together through column storage, so that the data access efficiency is greatly improved, especially during variable-level analysis. Meanwhile, the self-adaptive compression technology can dynamically select a compression mode according to the distribution characteristics of the data, so that the compression rate of the data is effectively improved, and the occupied storage space is reduced. The processing speed of the meteorological grid point data can be obviously improved, and the storage cost is reduced.

The invention provides an intelligent inspection system based on AI image recognition. The intelligent inspection system based on AI image recognition comprises a multi-source image acquisition module for performing distributed and continuous image acquisition on an area to be inspected through a positioning camera device; the edge preprocessing and high-speed transmission module is used for performing noise suppression, resolution self-adaptive compression and target coarse positioning on the image; and the multi-modal self-adaptive defect identification module is used for carrying out cross-modal cross attention fusion on the optical image and the infrared image by adopting a double-branch backbone network consisting of a deformable convolution residual branch and a Swi n converter global branch. According to the intelligent inspection system based on AI image recognition, a visual decision basis is provided for operation and maintenance personnel, and automatic and precise path scheduling is realized, so that the inspection efficiency, coverage and decision support capability are comprehensively improved.

The invention discloses a parallelizable self-adaptive matrix lossless compression method, which comprises the following steps of: partitioning a first matrix with a larger scale into second matrixes with smaller scales, distributing a splitting process for the second matrixes, splitting all the second matrixes into a plurality of bit matrixes in parallel by the splitting process, and distributing compression threads for the bit matrixes. And adaptively selecting an optimal compression strategy from the compression strategy set by the compression thread, and finally, completing compression of all bit matrixes by the compression thread according to the determined compression strategy in parallel to form a compression matrix and a flag array as final compression data of the first matrix. Through compression process grading and step-by-step parallelization, the memory overhead in the compression process is effectively reduced, the compression speed is improved, an optimal compression strategy is selected through trial compression, self-adaptive compression is achieved, the data compression rate is effectively improved, and lossless compression of data is achieved by constructing a flag array.

The invention discloses a secure cloud workstation and a resource scheduling method suitable for a high-altitude weak network environment, and the secure cloud workstation comprises a virtualization management platform which is used for carrying out the virtualization processing of core computing components of a plurality of servers contained in a back-end server cluster, and forms a plurality of virtual hosts; the front-end thin client only reserves display and input functions, establishes connection with the virtualization management platform, receives a virtual host human-computer interface pushed by any virtual host in the virtualization computing resource pool, and feeds back a user operation instruction to the virtualization management platform; the transmission protocol optimization module is used for integrating graph, input and audio data transmission channels, monitoring the network bandwidth and the delay state of a high-altitude area in real time by adopting a self-adaptive compression algorithm, and dynamically adjusting the transmission image quality and the frame rate of a virtual host human-computer interface; and the resource scheduling module is used for automatically allocating computing resources to the plurality of virtual hosts based on the load data of the virtualization management platform so as to realize cross-server load balancing.

The invention relates to a GPU-based adaptive compressed data direct query method, system and device and a medium, and the method comprises the steps: carrying out the data compression of input column data through employing an adaptive compression strategy, and obtaining a block-level structure suitable for GPU storage and calculation; loading the compressed data into a GPU memory, and performing Tile-level memory management by taking Tile as a basic scheduling unit; and according to the received query statement, executing direct query of the compressed data on the Tile level through the GPU, and outputting a query result. By designing a Tile-level direct query framework, a hardware-aware memory management and control flow coordination mechanism and a self-adaptive compression strategy, high-performance query execution is realized without decompression, and the computing potential of the GPU is fully released. The method can be widely applied to the technical field of big data processing.

The invention discloses a self-adaptive underwater single-pixel imaging technology based on Fourier modulation, belongs to the technical field of computational optical imaging, is used for ocean detection and improvement of ocean surveillance and defense efficiency, and adopts a self-designed LED array to replace an expensive DMD and a four-quadrant detector composed of common photodiodes to replace an expensive barrel detector. And high-speed illumination and parallel acceptance are realized while the cost is greatly reduced. The technical route comprises a high-speed underwater single-pixel imaging device, a high-speed Fourier single-pixel imaging algorithm and an adaptive sampling strategy based on Fourier single-pixel imaging. The high-speed single-pixel imaging device comprises a self-designed LED array light modulation module, a converging lens module and a receiving module. The high-speed Fourier single-pixel imaging algorithm comprises a binarization algorithm based on error diffusion and an algorithm based on adaptive compressed sensing. According to the innovative self-adaptive sampling strategy based on Fourier single-pixel imaging, a specific sampling path is generated by fusing circular sampling and random sampling according to the characteristics of an image in a Fourier spectrum, so that Fourier coefficients which have great influence on image quality are acquired as much as possible under water with low sampling rate and high turbidity, and the image quality is improved. Therefore, the high-efficiency imaging of the underwater target object is realized, and the imaging speed and quality are both considered.

The invention relates to the field of internet search service, and discloses a big data-based investment attraction clue analysis system, which comprises a query analysis unit, a query analysis unit, a query analysis unit, a query analysis unit and a query analysis unit, wherein the query analysis unit calls an event sequence template for defining a meta event type and a standard relative time window constraint interval; the distributed retrieval and aggregation unit is used for retrieving and aggregating meta event types to entity objects; the sequential logic verification unit is used for counting the global document frequency of the meta event, reversely mapping the global document frequency to generate a zoom coefficient, dynamically correcting a time window, and judging that only an entity object in a dynamic verification interval after correction is passed; the object sorting unit generates sorting scores according to template matching integrity, and by constructing a density and window reverse coupling mechanism, the sequential logic boundary is adaptively compressed in a high background noise environment, and the retrieval signal-to-noise ratio and the logic confidence coefficient are maintained.

A large ship safety supervision system, configured to realize shipmen monitoring and ship safety supervision, wherein shipmen monitoring comprising monitoring of real time positions of shipmen in cabins and shipmen health data, and ship safety supervision comprises oceanic condition warning, on board devices running condition monitoring, ship navigation / construction monitoring and ship remote guidance. Data transmission in between ships and shores is realized by the hybrid self-adaptive compression technology based on model classification and the data transmission link intelligent selection technology based on fuzzy neural network creatively, in the meanwhile, real time safety management and supervision and ship remote work analysis and guidance can be realized.

The invention relates to the technical field of package detection, and discloses a non-abandoned wine product package box compression resistance detection method and system based on a sensor. According to the method, surface pressure distribution data and internal stress waveforms of a packaging box are collected through a sensor network, and a multi-modal sensing data flow is generated. A three-dimensional digital twinning model of the packaging box is constructed based on the data flow, and material elastic parameters and structural constraint conditions are initialized; and carrying out compression resistance prediction training on the model to generate an adaptive compression resistance prediction model, and outputting a deformation simulation sequence in a virtual pressure environment. Real-time sensor data and a simulation sequence are dynamically compared to calculate a deformation error coefficient, so that a trigger threshold value of a pressure detection device is adjusted, and a compression resistance detection cycle is started. Multi-source data are fused in the circulation process for spatio-temporal feature analysis, and the overall compressive strength of the packaging box is evaluated. According to the invention, accurate prediction and dynamic detection of the compression resistance of the packaging box are realized.

The invention discloses a streaming data compression and time sequence prediction integrated method for a geothermal monitoring platform, and relates to the technical field of industrial data processing. The method comprises the following steps of: 1, acquiring various original heterogeneous sensing protocol data from a plurality of wellheads and a plurality of layers of sensor arrays in real time on a wellhead gateway side of a geothermal monitoring platform; 2, calling a well layer wavelet domain self-adaptive compression encoder through a well site edge end processor, and performing real-time compression on the structured geothermal flow data; and 3, in a well site edge end processor, performing wavelet dynamic system coding on the multi-scale wavelet coefficient of the well layer wavelet domain compressed code stream, and outputting a temperature prediction sequence, a pressure prediction sequence and a flow velocity prediction sequence of multiple time steps in the future.

The application relates to the field of multi-modal neural network model compression, and specifically discloses a multi-modal model compression and distillation method and system based on causal reasoning, which comprises the following steps: constructing a comprehensive causal discovery module to identify the causal dependence relationship among multi-modal features through information theory measurement, Granger causality analysis and intervention-based verification; performing an adaptive compression engine to perform pruning, mixed precision quantization and low-rank decomposition based on the causal relationship; applying a cross-modal distiller to maintain the relationship among modes by using a variety of loss function combinations; and implementing a dynamic optimizer to perform hardware perception and context-sensitive reasoning optimization. The application guides the compression decision through causal reasoning, realizes high compression rate while maintaining key causal paths, and effectively solves the deployment problem of multi-modal models in a resource-limited environment.

The invention discloses a document visual compression and retrieval method and device, equipment and a storage medium, and relates to the technical field of computers, the method comprises the following steps: obtaining a to-be-processed document page image, segmenting the image into a plurality of image blocks, and determining the structure category and the structure importance score of each image block; obtaining a plurality of structure regions based on structure category and spatial position aggregation, and distributing a preset number of compression tokens for each region in combination with structure category weights and importance scores; generating structure anchor point tokens corresponding to the regions by the compressed tokens to form a set; receiving a query request, converting the query request into a query vector, and performing retrieval in the anchor point token set to obtain a target structure region; and performing local decoding reconstruction based on the compressed token of the target region, and outputting a region image or a structure mask. According to the method, through structure-guided self-adaptive compression and fine-grained retrieval, the long document processing efficiency is greatly improved, and the compression effect and the retrieval accuracy are both considered.

The invention discloses a video code rate dynamic allocation compression method based on content complexity prediction, which comprises the following steps of: S1, acquiring a video frame sequence, and preprocessing; s2, inputting the frame-level feature tensor into a gated residual convolutional network, and outputting a complexity prediction sequence; s3, constructing a frame priority queue, and calculating the complexity jump amplitude between adjacent frames; s4, a compression area is divided, and a corresponding code rate resource scale factor is allocated; s5, configuring a reference frame structure, a prediction interval and an initial quantization step size for each compression region, and calculating a region target bit number; s6, distributing regional bits to each frame in a compression coding process, and dynamically adjusting a frame-level quantization parameter and an entropy coding strategy; and S7, after compression is completed, reversely updating convolution prediction network parameters through bit distribution errors. According to the invention, fine code rate dynamic allocation and adaptive compression control based on content complexity are realized, and the video compression quality and bit utilization efficiency are effectively improved.

The invention discloses an electric vehicle charging load prediction method based on an optimized fuzzy neural network, and the method comprises the steps: obtaining a plurality of historical load data of an electric vehicle, and processing all historical load data to generate a multi-dimensional feature data set; dividing an input feature space for the multi-dimensional feature data set based on an improved fuzzy clustering algorithm to obtain a clustering result and an activation intensity-contribution degree two-dimensional evaluation index; iteratively optimizing FNN parameters based on an improved adaptive differential evolution algorithm; constructing a rule contribution degree analysis model based on an orthogonal experimental design, setting a quantitative truncation threshold with the cumulative interpretation degree greater than or equal to 85%, and realizing self-adaptive compression of the scale of the rule base; an activation intensity threshold value dynamic calculation method is used, low-efficiency rules are automatically identified through sliding window statistics, and rule pruning is achieved; and outputting a load prediction result, and applying non-negativity and peak constraint to a prediction value.

The invention discloses a video inter-frame redundancy adaptive compression method based on a space-time perception graph neural network, and the method comprises the following steps: S1, obtaining continuous frame image data of a to-be-compressed video, carrying out the preprocessing, and constructing a frame sequence feature tensor; s2, extracting region candidate blocks in each frame of image, and constructing an inter-frame adjacency graph; s3, combining the motion vector and the local gradient features to construct a space-time perception feature map structure; s4, executing graph convolution calculation, and outputting a redundant feature score value; s5, setting a compression threshold, and generating an inter-frame redundancy mask; s6, performing variable bit rate quantization compression and reference frame reconstruction compression on the region candidate blocks with different redundancies to generate compressed frame data; according to the method, the space-time perception graph neural network is introduced, so that accurate recognition and adaptive compression of the redundant region between the video frames are realized, and the compression efficiency and the image restoration quality are remarkably improved.