1414 results about "Data compression" patented technology

An AI-enhanced distributed system for neural network-based data compression leverages reinforcement learning optimization and privacy-preserving computation across edge and central computing devices to autonomously optimize efficiency and quality. The system includes a lightweight compression subsystem at edge devices that applies privacy-preserving preprocessing and partially compresses input data before securely transmitting it to central computing devices. A reinforcement learning agent continuously monitors system performance and automatically optimizes compression parameters, model selection, and task allocation based on multi-objective rewards. The central compression subsystem processes data using AI-optimized parameters and temporal modeling components. The system incorporates hardware detection capabilities that automatically select optimal compression models based on available processing resources and implements homomorphic encryption for computation on encrypted data while coordinating federated learning across distributed devices. This AI-enhanced distributed approach improves bandwidth efficiency, energy consumption, and adaptability while ensuring data privacy and security.

The invention discloses a time sequence data management method of an edge computing gateway, which relates to the technical field of edge computing and industrial Internet of Things, and comprises the following steps of: respectively recording a communication bandwidth occupancy rate, a buffer area residual rate and a scheduling thread occupancy rate of the edge computing gateway in a preset fixed time period; and constructing a resource use original data matrix covering all time points in the fixed time period. According to the method, by periodically monitoring the resource use state and fusing the high-priority task scheduling performance, the scheduling resource abnormal occupancy index is dynamically generated, and intelligent sensing and scheduling optimization of the edge computing gateway on the resource pressure are achieved. When the abnormal index is increased, the system automatically triggers buffer area redistribution and low-optimal task data compression, data writing and scheduling real-time performance of key tasks are guaranteed preferentially, the problems of task starvation and data loss are effectively avoided, and the stability and the response capability of the system in a high-pressure environment are improved.

The invention discloses a double-rocker-arm derrick monitoring system based on multi-sensor data fusion, and particularly relates to the field of monitoring, which comprises a sensor module, a data preprocessing module, a data fusion analysis module, a state evaluation module and a visual terminal module, parameters of the double-rocker-arm derrick are monitored in real time through the sensor array, multi-source data synchronization and feature extraction are achieved in combination with the data preprocessing module, multi-modal data fusion is conducted through the improved D-S evidence theory, and the structure health index, the risk level and the fault probability are output; the state evaluation module generates three-level early warning signals based on a dynamic threshold model, historical data is compressed and stored and supports cloud synchronization, and the visual terminal renders a three-dimensional digital twinborn model through Unity 3D, dynamically displays postures, deformation fields and environmental factors, provides an interactive evaluation report and AR early warning annotation, and realizes whole-process real-time monitoring and intelligent decision support.

The invention relates to the technical field of data compression, and particularly discloses a method for realizing data compression in an RAID card and an RAID control chip, and the method comprises the following steps: S1, receiving a plurality of IO writing commands issued by a host, and obtaining the logic block address and length of each IO; s2, executing a merging operation on the plurality of IOs to generate a merged IO block; s3, performing a data compression operation on the merged IO block through a data compression engine to obtain compressed data; s4, establishing a mapping relation from a logic block address to a physical block address of the compressed data, and storing the mapping relation in a logic-to-physical mapping table; s5, the compressed data are written into a solid state disk through an RAID engine, and meanwhile, logic-to-physical mapping table metadata are stored persistently; s6, sending a recovery command or a zero-writing command to the solid state disk recovery space for the address space which is not used after compression; the problem that an existing SSD compression scheme is high in power consumption is solved, reliability is better, original user data content is closer, and the obtained compression effect is better.

The invention discloses a multi-source information fusion-based dynamic cooperative regulation and control method for a transmitting-end power grid energy storage station, and relates to the field of power grid energy storage regulation and control. The method comprises the following steps: compressing global heterogeneous data, and extracting a low-dimensional critical feature flow; constructing a dynamic coupling potential energy field, and quantifying gradient intensity to capture recessive instability; generating a layered fractal regulation strategy, resolving conflicts and outputting an instruction and a residual error; constructing a topological phase change trigger network, and triggering regulation and control through spectrum gap jump; causal tracing and model evolution are carried out, and parameters are optimized to form a closed loop. According to the invention, through fractal cooperation, topological response and evolution closed loop, regulation and control collaboration, instability response speed and system adaptability are improved, and safe and stable operation of a power grid is guaranteed.

The invention relates to the technical field of data recording, in particular to a data recording system for an automatic driving vehicle, and the system comprises a multi-source signal synchronization module, a behavior stage recognition module, a track abnormity elimination module, a dynamic compression adjustment module and a segmented index marking module. According to the method, a unified time alignment mechanism is constructed in a signal synchronization processing link, a strict corresponding relation between acquisition sequences is ensured, key time sequence characteristics of driving behavior switching are extracted by adopting a multi-behavior parameter comprehensive judgment method, segmented expression of a complex driving process is realized, and the accuracy of driving behavior switching is improved. According to track anomaly identification, through collaborative screening of inertial data and a positioning track, abnormal fragments which do not conform to physical rules are effectively eliminated, data compression dynamically sets interval length according to a parameter combined fluctuation trend, the fidelity of a key period is remarkably improved, non-key data redundancy is inhibited, and after a segmented index structure is established, the data compression efficiency is improved. And the data retrieval process is clearer.

A correlation-aware adaptive codebook compaction system for multi-modal data compression that preserves cross-modal relationships while providing enhanced reconstruction quality. The system analyzes temporal and spatial relationships between different data modalities to generate correlation maps that guide compression decisions. A virtual management layer performs stream characterization and adaptive routing, while a processing pipeline implements primary codebook compression with mismatch handling for novel data blocks. High-entropy data segments receive pre-compression processing before codebook compression. Sequential registration data is processed through matrix factorization and dedicated matrix codebooks. The system continuously monitors data distribution characteristics and automatically retrains codebooks when drift thresholds are exceeded. A neural upsampling subsystem uses correlation information to guide cross-modal enhancement processes through modality-specific networks and attention mechanisms. The unified output includes compressed data streams, correlation maps, synchronization metadata, neural model parameters, and updated codebooks, enabling synchronized reconstruction with preserved cross-modal relationships and enhanced quality through correlation-guided neural upsampling.

The invention provides an unstructured data compression method and device, equipment and a storage medium, and the method comprises the steps: carrying out the feature extraction and clustering processing of a to-be-compressed unstructured data set, and obtaining a data segment clustering group; performing semantic region segmentation processing on each data fragment in the data fragment clustering group to obtain a semantic important region and a semantic non-important region; performing differential coding processing on the semantic non-important regions in the same clustering group to obtain differential coding data; and performing high-quality compression processing on the semantic important regions in the same clustering group, and performing merging processing on the compressed important semantic data and the difference coding data to obtain an unstructured data compression result. According to the method, semantic region segmentation and differential compression processing are performed on the unstructured data, so that the data compression efficiency can be effectively improved on the premise of ensuring the quality of important information, and an efficient solution is provided for storage and transmission of large-scale unstructured data.

A federated system and method for data compression optimization in distributed device networks. The system comprises multiple edge devices that analyze local data patterns to generate device characteristic profiles while performing local compression optimization and maintaining data privacy. Edge devices contribute to collaborative learning by generating privacy-preserved updates without transmitting raw data. A central coordination system aggregates encrypted contributions using secure multi-party computation protocols, identifies device groups based on data pattern similarities, and generates optimized compression parameters for each group. The system coordinates collaborative training of data reconstruction models across device groups and deploys group-optimized reconstruction capabilities. Device grouping is performed by calculating similarity scores between device characteristic profiles and clustering devices with scores above predetermined thresholds. The system dynamically adapts compression and reconstruction parameters through federated learning while preserving individual device data privacy, enabling efficient data compression and near-lossless recovery across heterogeneous Internet-of-Things networks.

The invention discloses a method for aggregating ocean buoy data, which comprises the following steps of: establishing a space-time correlation model according to the spatial distribution density of buoy clusters and the dynamic characteristics of an ocean environment, and adaptively dividing buoy groups with a data compression cooperative relationship; performing a data-related compression operation within the buoy group; constructing a transmission priority dynamic sorting engine, and calculating a dynamic weight coefficient; performing hierarchical packaging processing on the differential coding data, distributing enhanced forward error correction coding resources for high-priority data, and reserving redundant transmission time slots; the method comprises the following steps: receiving a hierarchical data packet through a low-orbit satellite and executing on-satellite preprocessing, reconstructing an original data stream by using a distributed decoder, and meanwhile, fusing multi-dimensional space-time related data to generate an aggregated data product; and finally, the aggregated data product is transmitted to a ground data center through a satellite downlink. According to the invention, uplink data volume is reduced, disaster monitoring timeliness is improved, ground station processing load is reduced, and system environment adaptability is enhanced.

The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. A method performed by a terminal in a wireless communication system is provided. The method includes identifying whether a packet data convergence protocol (PDCP) entity is suspended in case that the PDCP entity re-establishment is requested from an upper layer, identifying whether an indicator is configured for indicating that an uplink data compression (UDC) is continuously used and a PDCP service data unit (SDU) is compressed, for an acknowledged mode (AM) data radio bearer (DRB) whose the PDCP entity is not suspended, and submitting the PDCP SDU, in case that the indicator is configured for indicating that the UDC is continuously used and the PDCP SDU is compressed.

The invention provides a sea area digital twinning method and system based on buoy and station data fusion, belongs to the related technical field of sea area digital twinning, and establishes a data quality evaluation mechanism and a similarity data compression mechanism by constructing a multi-source heterogeneous ocean data acquisition system. Intelligent fusion processing of buoy data and station data is achieved, and the problem that in the prior art, the data fusion precision is low is solved; through the self-organizing growth network structure of the ocean dynamic response enhancement model, neuron connection can be automatically adjusted according to the spatial-temporal variation degree of training data, an optimal topological structure is formed, and the defect that a traditional fixed parameter model cannot adaptively process a complex ocean environment is effectively overcome; by establishing a dynamic parameter adjustment mechanism and a multi-algorithm adaptive switching strategy, the most suitable prediction algorithm is automatically selected according to the correlation characteristics of the ocean data sequence, and high-precision digital reproduction of the complex ocean environment is realized.

The invention discloses an ultra-low illumination-oriented SPAD active imaging data compression method, which comprises the following steps of: performing wavelet decomposition on histogram data of a single pixel in a time-frequency domain based on wavelet transform to obtain low-frequency data of each pixel after wavelet decomposition; by taking each pixel as a center, performing non-maximum suppression and data enhancement on the low-frequency data after the wavelet decomposition of the current pixel by using adjacent pixels to obtain processed compressed data; customizing different Gaussian kernel parameters for each pixel according to the possibility that each pixel is located at the boundary, and performing Gaussian filtering on the processed compressed data of each pixel to obtain filtered data; and performing depth estimation on the filtered data to obtain a final depth image. According to the method, the depth reconstruction performance of the laser pulse can be improved by utilizing the multi-resolution characteristic of wavelet transform, the space-time correlation of signal photons and the smoothness of Gaussian filtering.

The invention provides a dam safety monitoring system lightweight construction method and device, and the method comprises the steps: deploying a protocol conversion gateway, carrying out the protocol analysis and data standardization processing of an existing heterogeneous sensor, generating data in a unified format, and supporting the network disconnection caching and automatic supplementary transmission; deploying a data processing module on a local server or an industrial personal computer based on an edge computing architecture, performing feature extraction and multi-scale fusion analysis on acquired data, and performing data compression by adopting an improved revolving door algorithm; constructing a lightweight anomaly detection model, training by using historical data to generate a normal mode template library, calculating a dynamic time warping distance between new data and a template in real time, and triggering early warning when the distance of a plurality of continuous cycles exceeds a preset threshold value; the sampling frequency of the sensor is dynamically adjusted according to the real-time data analysis result, key parameters are collected in a high-frequency mode, non-key parameters are collected in a low-frequency or intermittent mode according to the change rate prediction result, and therefore the system resource use efficiency is optimized.

The invention belongs to the technical field of data analysis and processing, and particularly relates to an equipment state monitoring method based on a time sequence synchronous compression mechanism, and the method comprises the steps: 1, a monitoring terminal collects vibration type, acoustic type and acceleration type signals on a unified time baseline of Beidou time service signals, and registers a second sequence number and a frame sequence number in a unified fragment index table; 2, inputting an original time sequence data packet, constructing a phase grid frame by a phase locking ring according to a reference phase rail, extracting road-level flag event bits frame by frame, and fusing the road-level flag event bits into frame-level flag event bits; and step 3, outputting an equipment state label according to a mutual exclusion priority rule only on the basis of the synchronous compression time sequence packet and the coupling mark, the mode instruction and the abnormal fragment mark in the unified fragment index table in the identification window. The method is obviously superior to the prior art in the aspects of time sequence alignment precision, pattern recognition certainty, data compression efficiency and health state judgment reliability.

The techniques disclosed herein provide a system for condensing large log files to enable interoperability with transformer-based large language models in automated failure analysis. In various contexts such as enterprise cloud services, log files can be large oftentimes containing millions of lexical units that can incur significant processing time and resource consumption. As such, the disclosed techniques provide a system for producing a directional knowledge graph representing a condensed form of a log file for automated failure analysis. Firstly, the log file is preprocessed to filter information that is irrelevant to the failure that previously occurred. The filtered lexical units are then used to generate a directional knowledge graph comprising a plurality of vertices which correspond to individual lexical units, and which are connected by edges representing the semantic connection between the lexical units. In this way, the directional knowledge graph significantly reduces processing times and improves resource consumption.

A system and method for latent geodesic traversal across multi-axis hyperspaces for real-time video reconstruction and augmentation. Spatiotemporal video data are compressed into navigable latent representations using hierarchical and Lorentzian autoencoders that preserve geometric and temporal structure. A geodesic traversal engine computes paths across spatial, temporal, spectral, and semantic axes, guided by symbolic anchors and spatiotemporal routing protocols. A correlation network restores fine detail, while an augmentation generator synthesizes additional or counterfactual content to enable infinite zoom, continuous multi-scale exploration, and temporally coherent augmentation. A strategy caching system preserves successful traversal patterns for reuse, supporting persistent learning and adaptive real-time performance.

The invention discloses a multi-dimensional time sequence data compression and rapid retrieval method and system, and relates to the technical field of large data compression retrieval. The multi-dimensional time sequence data compression and rapid retrieval method comprises the following steps: S1, collecting and preprocessing multi-source data in a monitoring abstract video stream, and constructing a standardized time sequence behavior data set; s2, analyzing behavior characteristics of frame segments in the sliding window, and dynamically adjusting anchor point labeling and compression strategies; s3, evaluating the coverage integrity of anchor point information in a compression section, and driving generation of an index path; s4, comprehensively evaluating the path behavior association strength and dynamically adjusting a loading decision; and S5, verifying the matching integrity of the behavior anchor point field and the jump pointer, and guaranteeing the localizability and jump stability of the event in the compression structure. The problems that in an intelligent monitoring scheme, video abstract compression is not bound with behavior semantics, a fine-grained positioning mechanism based on behavior labels is lacked, and key action segments cannot be directly positioned during user playback are solved.

The invention discloses a voice data compression and index storage method based on a voiceprint template, and relates to the technical field of voice compression processing. The voice data compression and index storage method based on the voiceprint template comprises the following steps: S1, collecting and preprocessing acoustic state data, coded data and edge synchronization data, and constructing a standardized voice input data set; s2, evaluating the individual sound channel difference degree, and stripping non-universal components highly related to individuals in the voice; s3, analyzing the audio compression content, and constructing a structured total compression amount; s4, performing joint evaluation on real-time transmission regulation and control requirements of the compressed data, and dynamically adjusting an uploading priority and a continuous transmission strategy; and S5, constructing a multi-dimensional reverse index system at the cloud. The problems that for a high-noise far-field pickup scene, an existing compression method does not consider that individual sound channel characteristics are stripped from original signals, so that compression redundancy is high, and retrieval interference is large are solved.

The invention discloses a query acceleration system of a column storage database and a self-adaptive index construction method, and the system comprises a data compression module which is used for compressing data of the column storage database; the input end of the parallel processing module is electrically connected with the output end of the data compression module; the input end of the query load analysis module is electrically connected with the output end of the parallel processing module; the input end of the self-adaptive index module is electrically connected with the output end of the query load analysis module and the output end of the parallel processing module; and the input end of the machine learning prediction module is electrically connected with the output end of the query load analysis module. The system comprises a data compression module and the like, through multi-module cooperation and a five-step index construction method, the static index problem is solved, and the park monitoring data query efficiency and the system adaptability are improved.

The invention discloses a compression method and device for generic semiconductor industry operation and maintenance data, electronic equipment and a medium, and relates to the technical field of data compression. The method comprises the following steps: acquiring to-be-compressed generic semiconductor industrial operation and maintenance data; identifying the time sequence of the generic semiconductor industrial operation and maintenance data to be compressed, and judging whether the generic semiconductor industrial operation and maintenance data is time sequence data or not according to the time sequence; and if the to-be-compressed generic semiconductor industrial operation and maintenance data is time series data, splitting the to-be-compressed generic semiconductor industrial operation and maintenance data into a time data set and a feature data set, and compressing the time data set and the feature data set respectively. According to the compression method, different compression strategies are adopted for different types of data, the compression efficiency of the data is improved, and the balance between the compression rate and the calculation efficiency is optimized.

The embodiment of the invention relates to the technical field of artificial intelligence, in particular to a data compression method and electronic equipment. According to the method, the memory space occupied by kv cache data can be reduced, and the memory wall problem is relieved. The method comprises the following steps: determining a first key tensor and a first value tensor as to-be-compressed data objects; the first key tensor comprises m first key vectors corresponding to the m tokens; the first value tensor comprises m first value vectors corresponding to the m tokens; m is a positive integer; compressing the first key tensor and the first value tensor to obtain a second key tensor and a second value tensor; the second key tensor comprises n second key vectors; the second value tensor comprises n second value vectors; n is a positive integer and is less than m; wherein the dimension of a single first key vector is the same as that of a single second key vector; the dimension of the single first value vector is the same as that of the single second value vector.

The invention relates to the technical field of data monitoring analysis, in particular to a carbon emission data monitoring analysis system and method.The carbon emission data monitoring analysis system comprises a source point extraction module, an on-chain confirmation module, an access frequency sorting module, a block positioning adjustment module and an integration module; and confirming a record on a certificate broadcast verification construction chain, sorting access frequency calculation intensity sorting numbers, positioning and adjusting a link to draw a deployment atlas, and collecting concentration frequency integration fluctuation to establish an archive set. According to the method, a unique compressed tracking code is generated based on time and structure identification, node comparison consistency is written into a linked list, access frequency constructs intensity sorting division areas, paths are adjusted, time sequence fluctuation sections are extracted and classified into sets, a filing structure is formed in combination with labels, and the method is suitable for trend arrangement and continuous calling of carbon emission monitoring. And the data reading efficiency and the retrieval continuity are improved.

The invention provides a data compression sampling method and device, and the method comprises the steps: obtaining an original collection signal through data collection equipment, and storing the original collection signal to a target region; processing the original acquisition signal in the target area by using a deterministic measurement matrix and a sparse transformation matrix in response to the condition that the data volume of the target area reaches a preset value to obtain a processing result; and transmitting the processing result to target equipment. Through the deterministic measurement matrix and the sparse transformation matrix, linear mapping and instant data stream compression are carried out on the sampled original acquisition signals, the data transmission amount is significantly reduced, real-time signal processing and interaction in a resource-constrained environment are supported, and the method has small limitation on a hardware environment, has good transportability and deployment flexibility, and is suitable for large-scale popularization and application. The method is suitable for various system application requirements, so that efficient data compression sampling is realized.

The invention belongs to the technical field of video time sequence positioning, and discloses a video time sequence positioning method and system based on a large model, and the method comprises the steps: obtaining original video data and a query statement, and compressing the original video data into a fixed number of frames; extracting image features of each frame, and mapping the image features to a semantic embedding space compatible with the large language model frame by frame to obtain continuous video representation; extracting text features of the query statement, and sequentially splicing the continuous video representation and the text features to obtain an image text pair; inserting a visual prompt at the front end of the image text pair to obtain a visual description sequence, inputting the visual description sequence into the large language model to perform time sequence positioning prediction on the visual description sequence, and outputting a video data positioning result; and defining a loss function, training the video time sequence positioning model, and performing video time sequence positioning by using the trained video time sequence positioning model. According to the method, the large model can be guided to be more accurate during semantic understanding and positioning of the video clip.

Certain aspects of the present disclosure provide data compression and channel coding techniques for variable length payloads. A method performed at a wireless node may include obtaining a payload for transmission, compressing the payload using a variable length compression technique to obtain a compressed payload having compressed payload bits of a first length, adding padding bits to the compressed payload to obtain a padded compressed payload. The padded compressed payload comprises information bits including the compressed payload bits and the padding bits. The method further includes encoding the padded compressed payload and outputting the encoded padded compressed payload.

A Large Codeword Model (LCM) with a latent transformer core is a deep learning architecture that operates on discrete, compressed representations of data called codewords. The latent transformer core incorporates a Variational Autoencoder (VAE) which allows for the removal of the embedding and positional encoding layers from the Transformer. Input data is compressed into a latent space representation using the VAE encoder, which is then processed by the Transformer. The VAE decoder generates outputs based on the processed latent vectors. This approach enables efficient handling of diverse data types beyond language, including time series, images, and audio.

The invention relates to the technical field of edge computing, and provides an edge data acquisition and processing device for a power plant unit, which comprises a data receiving module, an edge processing module, a data compression module and a communication module, the data receiving module is used for receiving data input by the access equipment and carrying out frame decoding processing on the data input by the access equipment to obtain data after frame decoding; the edge processing module is used for calculating and analyzing the deframed data to obtain preprocessed data; the data compression module is used for performing data compression processing on the preprocessed data to obtain compressed data; and the communication module is used for transmitting the compressed data to a preset target system. The efficient edge calculation and data compression mechanism not only improves the real-time performance and accuracy of data processing, but also enhances the adaptability of the system to the constantly changing operating environment and technical upgrading requirements of the power plant unit, and provides powerful support for safe operation and stability of the power plant unit.

The embodiments of the present application relate to the technical field of artificial intelligence, and in particular relate to a data compression method and an electronic device. The method can reduce the memory space occupied by kv cache data, thereby alleviating a memory wall problem. The method comprises: determining a first key tensor and a first value tensor to be data objects to be compressed, wherein the first key tensor comprises m first key vectors corresponding to m tokens, the first value tensor comprises m first value vectors corresponding to the m tokens, and m is a positive integer; and compressing the first key tensor and the first value tensor, so as to obtain a second key tensor and a second value tensor, wherein the second key tensor comprises n second key vectors, the second value tensor comprises n second value vectors, n is a positive integer, and n＜m; and the dimension of a single first key vector is the same as the dimension of a single second key vector, and the dimension of a single first value vector is the same as the dimension of a single second value vector.

According to the ring main unit with the intelligent online partial discharge detection system provided by the invention, the problem of multisource data asynchronization is solved through a four-dimensional space-time synchronous acquisition mechanism, so that the time alignment error of ultrahigh frequency and ultrasonic signals is lower, and the positioning precision is higher; the edge computing unit is used for executing adaptive filtering and pulse extraction, so that the effective data compression rate is greatly increased, the bandwidth requirement is reduced, and quick response within 3 seconds is realized; cross-modal coupling factor quantification electromagnetic-acoustic emission correlation characteristics are innovatively proposed, the contribution degree of a sensor is adaptively adjusted in combination with a dynamic weight distribution strategy, and high discharge type recognition accuracy is still kept in a strong electromagnetic interference environment; the space-time heterogeneous data is cooperatively processed through the two-channel deep learning model, the composite discharge mode is effectively identified, and the false alarm rate is lower compared with a traditional method; in addition, the system automatically and incrementally trains the model per week, continuously adapts to signal attenuation caused by equipment aging, and prolongs the effective monitoring life by more than three times.