246 results about "Adaptive encoding" patented technology

The invention discloses a low-delay adaptive wireless audio transmission method, and relates to the technical field of audio data transmission. The invention relates to a low-delay self-adaptive wireless audio transmission method, which comprises the steps of audio signal acquisition and coding, priority scheduling and time slot allocation, wireless channel transmission and interference resistance, congestion control algorithm optimization, decoding and reconstruction of a receiving end, and dynamic buffer management and delay optimization. According to the method, low-delay transmission of audio signals is ensured through a plurality of technologies such as priority scheduling, time slot allocation, dynamic buffer management and adaptive coding, the stability of audio transmission is remarkably improved by combining congestion control, forward error correction (FEC) and adaptive interference elimination technologies, and even in a complex wireless environment, the stability of the audio transmission is greatly improved. And the audio signal can keep high quality, and the transmission stability is ensured by quickly responding to channel change, eliminating interference, correcting errors, reducing packet loss and retransmission.

The invention provides a fragment data cross-modal label generation system and method based on deep transfer learning. The method comprises the following steps: extracting first high-dimensional feature vectors in different modes; mapping the first high-dimensional feature vectors of different modals into the same semantic space through a cross-modal comparison loss function to realize multi-modal alignment and fusion to obtain second high-dimensional feature vectors; labeling semantic tags corresponding to the second high-dimensional feature vectors based on the fragmented data components by adopting a small sample transfer learning algorithm; a multi-channel Hash encoder is adopted, a self-adaptive encoding strategy is called according to different modal data combinations, and the second high-dimensional feature vector is encoded into a multi-channel binary Hash code; in combination with an incremental graph neural network, the binary hash codes and the corresponding semantic tags are dynamically expanded into the historical knowledge graph; matched fine-grained tags are established for semantic differentiation features of different entity combinations in the target knowledge graph, and a cross-modal tag tree is obtained by combining three-matrix hierarchical construction.

The invention discloses a super-resolution image reconstruction method, system and device based on dynamic frequency domain adaptive coding and contrast constraint optimization, and a medium. The method comprises the following steps: creating an original training data set; image data features and application scenes are considered, and feature extraction is performed on image data by adopting a modular design method; in combination with discrete cosine transform and inverse transform thereof, adaptive transform coding is carried out on different frequency components in the image features through a dynamic weight adjustment mechanism; the U-Net and Transform architectures are combined, isotropic design is optimized, a diffusion model and a feature fusion and reconstruction technology are applied, and diffusion process reconstruction is achieved; by introducing a contrast loss function, contrast learning is carried out between images with different resolutions, and the feature learning ability is enhanced. The image reconstruction method is more intelligent and efficient, and can effectively deal with frequency feature recovery and detail reconstruction problems in a complex image scene.

The invention provides an erasure code compatible read-write method and system based on a bidirectional data access agency, and relates to the technical field of distributed storage, and the method comprises the steps: employing multi-agent reinforcement learning to construct a heterogeneous resource portrait and optimize task allocation, combining a space-time graph convolutional network and a federated learning framework to construct a data format conversion model, and constructing an erasure code compatible read-write model; data features are analyzed through an encoder based on an attention mechanism, a fragmentation strategy is generated, self-adaptive encoding is achieved through a capsule neural network, data integrity verification and repairing are conducted through a double-layer space attention network and a graph attention network, the data access efficiency of a heterogeneous storage system is improved, data format compatibility is enhanced, and the data access efficiency is improved. And the data integrity is ensured.

The invention discloses a semantic communication method for adaptive coding of a semantic source channel under a parallel channel. The method comprises the following steps: S1, constructing a communication model for adaptive coding of the semantic source channel under the parallel channel; s2, at a sending end, encoding semantic information source samples in (X, S), distributing bit streams after encoding each semantic information source sample to an independent channel for transmission, and adopting K channel encoders with different channel rates to protect respective bit streams so as to resist channel errors; s3, at a receiving end, decoding the received signals by using K channel decoders, combining the received signals into a single serial flow, and decoding the single serial flow by using a semantic source decoder based on a deep neural network; s4, determining a source rate and prior information under any given deep neural network model; and S5, constructing an optimization problem, and performing joint optimization of the deep neural network parameter phi and the resource allocation variable # imgabs0 #. According to the invention, resource allocation optimization in a parallel Gaussian channel scene is realized.

The invention discloses a weak network environment video compression method based on deep learning, and relates to the technical field of video compression, and the method comprises the following steps: 1, carrying out the feature extraction of video content through a deep learning model; 2, dynamically adjusting video compression parameters according to the extracted features and real-time network conditions; step 3, compressing the video by using a self-adaptive coding strategy; according to the video compression method based on deep learning, the video compression efficiency and adaptability in a weak network environment are remarkably improved, the video content is subjected to feature extraction by using the deep learning model, key information in the video can be intelligently identified, such as a motion vector, texture complexity and scene change, and the video compression efficiency and adaptability are improved. Therefore, a more accurate compression strategy is realized, the compression ratio of the video data is optimized, and the smoothness and the stability of video playing are ensured to be kept under variable network conditions.

The invention discloses a wireless public network communication data transmission system based on multiple central stations, which relates to the technical field of data transmission and comprises a load sensing and balancing module, a path reconstruction module, a self-adaptive coding modulation module and a safety tunnel management module. The load sensing module realizes load balancing and stable transmission by monitoring indexes of a central station in real time and performing dynamic migration connection; the path reconstruction module adjusts and optimizes path parameters by using federal learning, dynamically adjusts a transmission path and optimizes path quality; the adaptive coding modulation module dynamically adjusts a modulation scheme according to channel conditions, generates a pre-coding matrix in combination with environment information, and improves the transmission efficiency; the security tunnel module adopts a plurality of encryption technologies and dynamic port hopping mechanisms to ensure the security of data transmission; according to the invention, the load balancing capability, the transmission efficiency and the security of the system are effectively improved, and the method is suitable for a complex and changeable wireless public network environment.

The invention discloses an HPLCamp (High Performance Liquid Chromatography) based on deep learning. The invention discloses an HRF dual-mode communication adaptive coding modulation and anti-noise method. The method comprises the following steps: acquiring an optical radio frequency signal amplitude-phase change rate and synchronously sampling and normalizing; calculating a node amplitude-phase residual error to generate a nonlinear mapping coefficient; monitoring coherent change to solve a drift trend, adjusting a modulation coding optimization scheme, compensating distortion and outputting an anti-noise result. According to the method, the instantaneous amplitude and phase of the optical radio frequency dual-mode signal are extracted, a multi-dimensional amplitude-phase characteristic matrix is formed in combination with time domain synchronization and a normalization template, differential residual modeling and nonlinear mapping coefficient calculation are carried out between impedance nodes, and dynamic compensation of amplitude-phase mismatch and envelope offset is achieved. A drift trend quantity is generated based on coherent offset parameter differentiation, feedback is provided for modulation format and coding strategy optimization, amplitude equalization and phase correction are completed, the signal synchronization degree and amplitude-phase consistency are improved, and the steady-state response and anti-disturbance performance of a transmission link are enhanced.

The invention relates to the technical field of audio coding and decoding, and discloses an audio coding and decoding method and system, and the method comprises the steps: carrying out the time domain analysis and frequency domain analysis of an audio input signal of a Bluetooth earphone, and generating an audio feature matrix; performing feature extraction and fusion processing to generate a target feature vector containing frequency band energy distribution and user preference information; inputting the target feature vector into a preset neural network model for dynamic parameter calculation, and generating an adaptive coding matrix; performing layered division on the audio input signal according to the adaptive coding matrix to obtain basic tone quality layer data and enhanced tone quality layer data; and encoding the basic tone quality layer data and the enhanced tone quality layer data through a heterogeneous computing unit to generate a target encoded data stream, and the method realizes double optimization of audio processing precision and processing time.

A method for processing a media stream includes: determining a cloud application and an interaction room created in the cloud application, and obtaining, during running of the cloud application, media-stream processing capability information of terminals joining the interaction room for interaction; performing adaptive encoding on media data in the interaction room based on the media-stream processing capability information, to obtain at least one type of media stream for the terminals in the interaction room, a media-stream parameter of the at least one type of media stream matching the media-stream processing capability information; determining a media stream matching a subset of the terminals in the interaction room, the media stream being selected from the at least one type of media stream based on media-stream processing capability information of the subset of the terminals; and delivering the media stream to the subset of the terminals in the interaction room.

The embodiment of the invention provides a network state sensing and adaptive coding control method and device, equipment and a computer readable storage medium. The method comprises the following steps: acquiring network index data; inputting the network index data into a trained target AI model to generate a network prediction result; executing a target regulation and control operation according to the target network prediction result; the target regulation and control operation comprises an FEC proportion regulation and control operation, a video parameter regulation and control operation and / or an ICE path switching operation. In this way, higher-quality, more stable and more intelligent real-time audio and video communication can be realized in a complex public network environment.

The invention discloses an enterprise intelligent compliance auditing method based on data driving. The method comprises the following steps: S1, automatically collecting auditing data of various heterogeneous data sources in an enterprise in real time through a cross-domain data access interface; s2, performing feature automatic identification and standardization processing on the audit data by adopting a semantic adaptive coding method; s3, a cross-domain collaborative characterization model is constructed by extracting and fusing shared features through a sub-domain multi-expert structure; s4, generating a visual feature heat map by using a hierarchical attention mechanism of the model, and outputting an anomaly detection result; s5, extracting long and short period correlation mode features, inputting the features into a contrast learning framework, and outputting an abnormal risk score; s6, constructing a dynamic enterprise compliance risk knowledge graph; s7, strategy training is carried out, and risk rating is output; and S8, generating an audit report according to the risk rating. According to the invention, efficient and accurate enterprise compliance risk identification and audit decision support are realized.

The invention relates to the technical field of body intelligence, and discloses a body intelligence-oriented sensing active control method and system, and the method comprises the steps: obtaining multi-modal sensing data, and determining a feature extraction unit and a control center node based on a heterogeneous data fusion framework; selecting a target coding module according to the spatial-temporal correlation index of the adaptive coding module, and generating a feature fusion path; determining a signal synchronization moment by combining the dynamic response delay and the sub-layer coupling degree, and marking a real-time fusion topological graph; and detecting a signal phase conflict, and planning a multi-modal control instruction based on a conflict result. The technology also relates to perception mode priority grading, feature fusion path dynamic generation, spectrum interference detection, path re-planning and the like. Microsecond-level time-space stamp marking and modal feature decoupling are realized through a distributed heterogeneous sensor array. According to the invention, the multi-modal data fusion precision, the signal synchronization control and the multi-modal coordination decision ability are improved, and the environmental adaptability and robustness of the intelligent system are enhanced.

The invention proposes a transmitter arranged to transmit a sequence of physical layer frames at a physical layer symbol rate, said sequence being filtered with a transmit filter, and comprising adaptive coding and modulation means arranged to determine a modulation and coding for transmitting data, whereby the transmitter maps the data in frames using said modulation and coding and inserts encoded and modulated data frames into the sequence. The transmitter further inserts prior to said filtering with the transmit filter, fill frames modulated (and encoded) with a first fill modulation (and coding), said first fill modulation (and coding) selected from a set of fill modulations (and codings) comprising at least one fill modulation (and coding) with a modulation order higher than QPSK.

The invention provides a multi-source data convolution fusion TBM electric drive system fault diagnosis method, and relates to the technical field of TBM electric drive control. The method comprises the following steps of: filtering and denoising operation data of an electric drive system by using variational mode decomposition (VMD), extracting time domain features, and constructing a multi-mode fusion data set; secondly, extracting short-term, medium-term and long-term time sequence features in parallel through a residual causal convolutional network, and enhancing key features by using a convolutional block attention module (CBAM) to highlight early weak fault signals; furthermore, working condition parameters are embedded into a feature space by adopting working condition adaptive coding, and cross-working-condition feature consistency constraint is realized based on a maximum mean difference (MMD) criterion. According to the method, the weak fault identification capability and the cross-working-condition diagnosis generalization performance are effectively improved, and the TBM operation stability and the tunnel construction safety are guaranteed.

The invention provides an array image demosaicing method based on dynamic convolution and adaptive coding, which relates to the technical field of image processing, and comprises the following steps: acquiring single-channel original image data and a corresponding color filtering array arrangement type identifier; converting the arrangement type identifier into a multi-dimensional physical feature vector, and inputting the multi-dimensional physical feature vector into a feature processor of a neural network model to generate a weighting coefficient vector; carrying out weighted combination on the plurality of special arrangement transformation matrixes through a weighting coefficient vector to obtain a transformation component, adding the transformation component and a basic convolution kernel parameter to obtain a dynamic convolution kernel parameter, and carrying out directional modulation on a specific spatial position of the dynamic convolution kernel parameter based on a direction weight component in a multi-dimensional physical feature vector; and performing convolution operation on the original image data by using the dynamic convolution kernel parameters, extracting multi-scale features, reconstructing image features, and outputting multi-channel color image data, so that the method can be adaptive to different color filter array types, and the demosaicing precision and generalization capability are improved.

The invention discloses a data full-link dynamic anti-interference optimization transmission method. The method comprises the following steps: S1, constructing a data transmission system architecture comprising a sending end, a transmission link and a receiving end; the sending end detects environment disturbance characteristics in real time, and the receiving end collects receiving signals containing background noise and link distortion; s2, designing a self-adaptive waveform coding strategy at a sending end; s3, performing active channel compensation on a transmission link; channel characteristics are extracted, and channel interference is counteracted in real time through pre-distortion waveform adjustment; s4, deploying an intelligent noise reduction decoding algorithm at a receiving end; a depth feature separation network is constructed, and link residual interference is filtered out by analyzing the time-frequency domain difference between a target signal and a noise component. Through a three-level anti-interference mechanism of adaptive coding of the sending end, active compensation of a transmission link and intelligent noise reduction of the receiving end, the problem that the transmission reliability of signals is reduced due to environment disturbance, channel distortion and noise pollution in a complex environment is solved.

Length-adapter input parameters for length-adaptive encoding include a data word length and a length-adapted codeword length, which are positive integers. Length-adapter output parameters include a primary data word length, a secondary data word length, a primary codeword length, and a secondary codeword length. A received data word is split according to splitter parameters into a primary data word based on the primary data word length and a secondary data word based on the secondary data word length. The primary data word is encoded in accordance with primary encoder parameters to generate a primary codeword from a primary code. The secondary data word is encoded in accordance with secondary encoder parameters to generate a secondary codeword from a secondary code. The primary and secondary codewords are combined in accordance with combiner parameters to generate a length-adapted codeword transmitted via a channel to a decoder.

The invention discloses a self-adaptive coding modulation method and system for relieving sun-borne interference in an ultra-dense low-orbit satellite network, and aims to improve the reliability and the spectrum utilization rate of satellite network communication. The method specifically comprises the following steps: modeling satellite-ground and inter-satellite communication links of the ultra-dense low-orbit satellite network, and modeling and calculating time generated by the sun and interference to the low-orbit satellite network; the ground station estimates and predicts the satellite-ground channel state, and returns the predicted SNR to the satellite; and according to the SNR returned by the ground station and the SNR generated by the sun, a deep reinforcement learning method is adopted to select a coding modulation scheme to perform downlink data transmission, and whether a lower satellite is selected to perform data unloading and then transmit the data to the ground station is determined. Simulation results show that the bit error rate of the ultra-dense low-orbit satellite network can be effectively reduced, the spectrum utilization rate can be remarkably improved, real-time response and efficient resistance to sun interference can be achieved, the satellite calculation load can be reduced, the comprehensive performance of the system can be improved, and the method has high practical application value.

A satellite adaptive modulation method based on deep reinforcement learning: 1) Perform initialization operations; initialize the state space, action space, and greedy parameter; 2) The signal receiving end on the ground receives the signal from the satellite downlink and extracts the pilot information in the current frame for signal-to-noise ratio (SNR) estimation. After the receiving end calculates the SNR estimation result, it is transmitted to the ground sending end through the ground feedback link; 3) The sending end translates the selected action into the corresponding modulation method and coding rate; 4) Determine whether the current iteration number is an integer multiple of the preset network update step number. If so, go to step 5) for network update; if not, update the SNR state and return to 2) to enter the next round of iteration; 5) Introduce the concept of a dual network and improve the learning effect and accelerate the convergence of the results by optimizing the structure of the neural network. 6) Update the SNR state, increment the greedy parameter, and return to 2) for the next round of iteration.

The invention discloses a cross-satellite communication method for a high-dynamic terminal. The cross-satellite communication method comprises the following steps: a satellite carries out bidirectional communication with a terminal and a terminal control station; the satellite forwards terminal service information to the terminal control station, and forwards terminal control station preset information and signaling information to the terminal; according to the preset information and the signaling information, the terminal dynamically judges whether cross-satellite switching needs to be initiated or not; if cross-satellite switching needs to be carried out, the terminal changes parameters according to the content of the signaling information to realize communication with a target satellite, and the target satellite forwards terminal service information to a terminal control station; meanwhile, terminal state information is updated and sent to the terminal control station, and the whole cross-satellite communication process is completed. According to the invention, on the premise of ensuring continuous and reliable cross-satellite communication, the cross-satellite communication process is simplified, and a self-adaptive coding modulation mode is adopted in an uplink, so that cross-satellite rapid switching and efficient communication of the high-dynamic terminal in a satellite networking scene are realized.

The invention discloses a scene electromagnetic texture mapping method and system based on an autonomous mobile robot. The method comprises robot operation and development, radar sensor operation and DART implementation. The robot carries out data acquisition through a sensor and carries out data fusion and processing on the acquired information; the radar sensor operates to detect the surrounding environment through a signal transceiving mechanism, and the obtained signals are fused and processed; in the DART implementation step, visual results of different angles are provided through a visual angle synthesis technology and are finally output in a multi-visual-angle mode. Through a strong coupling mechanism of robot body motion control and radar scanning parameters, a personal error source is eliminated, high-precision motion control is realized based on a robot-radar cooperative control architecture, and based on a DART-NeRF hybrid modeling engine and a lightweight network architecture, model parameters are compressed through adaptive coding, and training and reasoning processes are accelerated.

The invention provides a control panel optimization method based on multi-task scheduling, which relates to the field of data processing, and adopts a self-adaptive coding technology to carry out characteristic analysis on each task in a task queue and dynamically distribute priority codes for each task; constructing a dynamic state matrix for the real-time data flow of the control panel by applying a dynamic matrix technology based on the priority coding; tensor decomposition is carried out, potential correlation features between tasks are extracted, and a decomposition result is input into a reinforcement learning model to generate a real-time scheduling strategy; and according to a scheduling execution result, reversely calculating a weight compensation coefficient, adjusting priority codes and state parameters in the dynamic state matrix, generating an updated scheduling strategy, and feeding back the updated scheduling strategy. Through continuous monitoring and dynamic updating of the data flow state, resource distribution in the task scheduling process is optimized, high-priority tasks are executed preferentially, and the response speed of the system and the accuracy of task execution are effectively improved.

The invention discloses a pneumatic actuator remote intelligent monitoring system based on the Internet of Things, and relates to the technical field of actuator control. Traditional, quantum and biosensors are used for data acquisition, adaptive coding is adopted, transmission is combined with quantum encryption and ultra-wideband, quantum machine learning and causal inference are analyzed and applied, and remote control comprises brain-computer, holographic and intelligent agent technologies; naked-eye 3D and AR are used for visualization, system management depends on a block chain and a quantum key, and a self-repairing function is achieved. The advanced technology is creatively applied, data are comprehensively collected, transmission safety is guaranteed, faults are accurately analyzed and predicted, convenient remote control and visual display are achieved, system safety and stability are improved, and efficient operation of the pneumatic actuator is powerfully guaranteed.

The invention provides an LDPC (Low Density Parity Check) optimization method based on dynamic parameter adaptive coding and a Tanner graph neural network. The method comprises the following steps: acquiring a data set through a channel sensing module; the data set comprises channel state information, bit error rate statistics and QoS (Quality of Service) demand information; the collected data set is preprocessed; dividing the preprocessed data set according to a preset proportion; constructing an LSTM (Long Short Term Memory) prediction model; training and optimizing the LSTM prediction model by using the training set based on the loss function, and storing an optimal model; inputting the test set into the optimal model to predict the coding parameters of the channel transmission to obtain a prediction result of the adaptive coding parameters of the channel transmission; the method comprises the following steps: establishing an LDPC encoder and a Tanner-GNN decoder; building a joint optimization controller; the joint optimization controller is used for dynamically adjusting coding parameters through the LSTM prediction model and receiving the bit error rate BER counted by the Tanner-GNN decoder, the technical limitation of traditional coding and decoding separation optimization is broken through, and the performance of the LDPC code in a complex channel environment is remarkably improved.

A communication system includes a transmitter and one or more receivers. The transmitter is arranged to transmit a sequence of physical layer frames at a physical layer symbol rate. An adaptive coding and modulation optimization means are arranged to determine a first modulation and coding for transmitting per receiver of one or more receivers. The transmitter further inserts fill frames modulated (with a first fill modulation) prior to filtering with the transmit filter. The first fill modulation is selected from a set of fill modulations with at least one modulation with a modulation order higher than QPSK. The communication system includes link quality detection, which means to determine a metric of the communication link quality from a version of physical layer frames at the receive side. The physical layer frames include the fill frames and convey the link quality metric to the adaptive optimization means.

The invention discloses an AI-based motion subject tracking and streaming media optimization live broadcast system, and particularly relates to the technical field of motion subject tracking and streaming media optimization, AI-driven motion subject detection and tracking and streaming media coding adaptive control are closely fused, and code rate fluctuation of a coding end and bandwidth change of a network end are sensed in real time, so that the accuracy of the motion subject tracking and streaming media optimization live broadcast system is improved. A continuous and explainable live broadcast jitter risk analysis index is constructed, potential image quality jitter and delay risks are identified in advance through fusion of causal rule scoring and time sequence prediction, and the live broadcast jitter risk analysis index is directly mapped into an adaptive coding and transmission adjustment instruction. Priority guarantee, code rate distribution smoothing and delay control optimization of a key area are realized, the definition and playing smoothness of a live broadcast picture are remarkably improved, and sudden jitter and jamming phenomena are reduced.

The invention discloses a ship-shore video transmission system and method, and relates to the technical field of ship communication. The ship-shore video transmission system comprises a user side, a ship side and a shore side, the ship end comprises a client and a self-adaptive video coding module; the shore end comprises a server; the server is used for acquiring a playing instruction of a ship-end target camera and sending a transmission instruction of a current video stream of the ship-end target camera to the client; the client is used for receiving a transmission instruction of a current video stream of a ship end target camera and calling the self-adaptive video coding module; and the adaptive video coding module is used for adaptively coding the current video stream of the ship end target camera to obtain a target video stream, and transmitting the target video stream to the shore end and the user end. Therefore, by arranging the adaptive video coding module, adaptive coding adjustment can be performed on the current video stream of the ship-end target camera, so that delay can be reduced, and stability and reliability of ship-shore video transmission can be improved.

The invention relates to the field of hybrid coding of video engines, and provides a hybrid coding processing method, system and equipment based on a video engine, which comprises the step of intelligently switching an H.265 inter-frame predictive coding mode and an MJPEG (Multijoint Joint Photographic Experts Group) intra-frame compression coding mode by dynamically monitoring the proportion of a motion area in a video picture. When a scene is static, discrete cosine transform is adopted to compress space redundancy, motion vector compensation is started to eliminate time redundancy when motion is violent, and meanwhile, key frames are doubly screened by using pixel difference analysis and a perceptual hash algorithm, and repeated frames of visual redundancy are eliminated. And finally, space-time association is established for the optimized double-code-stream data through a timestamp index system, and efficient storage and accurate reconstruction of the mixed code stream are realized. The problems that the coding efficiency is low, no self-adaptive coding mode exists, redundant frames are not optimized, and code stream management is insufficient are solved.

The invention provides an on-site video return coding method and system, and the method comprises the steps: collecting a video stream of an on-site scene, judging whether a current video frame in the video stream responds to a scene switching video frame or not, and marking the current video frame as a key frame when the current video frame responds to the scene switching video frame; after the current video frame is identified as a key frame, visual saliency analysis is performed on the key frame, and an entropy weight matrix representing regional information importance distribution in the key frame is constructed according to a visual saliency analysis result and texture information entropies of different blocks in the key frame; adjusting code rate allocation weights of different blocks in the key frame according to the entropy weight matrix and a code rate regulation and control strategy of the key frame to obtain adaptive coding configuration adaptive to content characteristics of the key frame; and performing optimization coding on the key frame through adaptive coding configuration to obtain a target code stream in response to a field video return demand. By adopting the scheme of the invention, the dynamic differential coding of the key video frame in a complex scene can be realized.