37results about How to "Reduce computing latency" patented technology

The invention discloses a low-illumination image enhancement algorithm based on deep convolution, which is suitable for the field of image processing, and the core of the algorithm lies in an efficient noise reduction process and accurate decomposition of an illumination image and a reflection image. Comprising the following steps that firstly, a channel noise reduction module works cooperatively through multiple noise reduction strategies, noise in an image is effectively removed, and a foundation is laid for follow-up processing; then, the illumination image decomposition network and the reflection image decomposition network accurately separate the brightness information, texture and color information of the image based on a deep learning structure. And finally, by ingeniously fusing the illumination image and the reflection image, reconstructing a high-quality enhanced image, remarkably improving the brightness, contrast and details of the image, and meanwhile, retaining the natural color of the image. The algorithm has the advantages of being high in noise reduction capacity, accurate in illumination image decomposition, efficient in reflection image decomposition, good in enhancement effect and the like, and an effective and practical solution is provided for image enhancement under the low-illumination condition.

The invention provides a method and system for carrying out DOA estimation by using an antenna array in a partition mode, and the method comprises the steps: 1, dividing the whole antenna array into a plurality of sub-arrays, and enabling each sub-array to independently receive a signal; 2, each sub-array independently collects the received signals, and corresponding filtering and noise reduction preprocessing is carried out; 3, performing independent direction estimation on the signal of each sub-array by using a MUSIC algorithm to obtain a plurality of preliminary DOA values; and step 4, performing comprehensive processing on the DOA preliminary estimation result of each sub-array through a weighted average or joint optimization fusion algorithm to obtain a final DOA estimation value. According to the method, through partition use of the antenna array, the calculation amount of angle estimation of the antenna array can be effectively reduced, so that the real-time performance of DOA estimation is improved, and the positioning precision and the anti-interference capability can be improved by fusing estimation results of a plurality of sub-arrays.

The invention relates to an agent brain-like SLAM (Simultaneous Localization and Mapping) and end-side environment exploration method and system, belongs to three-dimensional scene construction and artificial intelligence detection and identification, and solves the problems of low precision, high computing resource consumption, inaccurate target sound source positioning and insufficient visualization effect during end-side environment exploration in the existing map construction process. Comprising the following steps: acquiring IMU data, a camera image, DVS event sequence data and a sound source signal around an intelligent agent; characterizing the DVS event sequence data into a normalized voxel grid through frequency coding, then extracting features, fusing the features with the features of the camera image to obtain fused features, and obtaining the pose of the intelligent agent based on the fused features and IMU (Inertial Measurement Unit) data; constructing a cognitive map by using a spatial position characterization mechanism based on grid cell coding in combination with a camera image and DVS data after voxel grid normalization on the basis of the pose of the intelligent agent; and inputting a sound source signal into the trained sound listening and position distinguishing model to obtain azimuth information of a sound source relative to the intelligent agent in the cognitive map.

The invention discloses a large model reasoning hardware accelerator based on data flow execution, and belongs to the technical field of large model reasoning hardware acceleration. Each node comprises a linear calculation kernel used for sequentially completing query / key / value projection and attention output projection in multi-head attention calculation, dimension raising projection and dimension reduction projection calculation in a feedforward neural network layer, and inverse quantization operation after each projection is output; the multi-head attention calculation kernel is used for completing loading and quantization of query / key / value vectors, multi-head division and cache management, attention score calculation, Softmax normalization, context vector generation and KV cache updating; the RLA kernel is used for completing residual addition, layer normalization, quantization / inverse quantization and nonlinear activation calculation of each layer; the three cores in the same node are located in the same SLR area, and data transmission is carried out through a hardware queue and an HLS blocking mechanism. According to the invention, high hardware utilization rate and low-delay reasoning can be realized.

The invention relates to a gastrointestinal tract transport track acquisition system, which comprises a wearable positioning device provided with a magnetic sensor array of at least two magnetic sensors; a single administrable positioning marker comprising a magnetic substance and capable of moving within the gastrointestinal tract; m is greater than or equal to 1, and each auxiliary positioning marker comprises a magnetic substance and is used for being arranged at a fixed position of a human body; and a terminal device. The magnetic sensor can collect the magnetic field intensity of the wearable positioning marker and the auxiliary positioning marker through magnetic induction, and the terminal equipment receives the magnetic field intensity data to determine the real-time position of the positioning marker in the gastrointestinal tract of the human body. Wherein the terminal equipment calculates the position direction parameters of the administrable positioning marker and the auxiliary positioning marker according to the received magnetic field intensity data, corrects the position direction parameters of the administrable positioning marker by adopting a motion artifact interference elimination method, and determines the real-time position of the positioning marker in the gastrointestinal tract of the human body.

The invention discloses a shift change information intelligent complementation and error early warning system based on a large language model, which belongs to the technical field of medical information processing and comprises a terminal acquisition module, an intelligent distribution complementation module and an early warning control module. Structure and semantic fingerprints are generated for the data table, a shift exchange asset meta model is constructed through fusion similarity clustering merging, and a semantic enhancement model is generated in combination with medical shift exchange specifications to complete information field completion; the intelligent distribution and completion module configures an optimal path with the minimum comprehensive overhead for the acquisition module by relying on a regional dynamic shift information network formed by double sub-networks; the early warning control module is combined with a large language model semantic analysis and rule engine, monitors an acquisition track and identifies information abnormity to execute error early warning, and an early warning result is fed back to the intelligent distribution complementation module, so that dynamic adjustment of an optimal path is realized, and the integrity, accuracy and acquisition efficiency of medical shift information are improved.

The embodiment of the invention discloses an information generation method and device based on a transition index and electronic equipment. A specific embodiment of the method comprises the steps of obtaining a business index information set for a target virtual article; for the service index information, executing the following first processing steps: according to the service index information, performing transition index decomposition on a service index corresponding to the service index information; performing real-time index value updating on the transition index corresponding to each piece of transition index information in the transition index information group; according to the path diagram and the obtained updated transition index information group set, performing real-time restoration on the index value of the business index corresponding to the path diagram; and according to the updated business index information set, generating real-time article information for the target virtual article. According to the embodiment, the problem that index calculation cannot be carried out timely and accurately due to calculation bottleneck is effectively solved.

The present application discloses an acceleration device for deep learning and a computing device for deep learning. The acceleration device for deep learning includes: a data buffer, a computing module connected to the data buffer; the data buffer is used to cache the intermediate computing results of the network layer of the vocoder neural network; the computing module is used to obtain the intermediate computing results of the first network layer of the vocoder neural network from the data buffer according to the received control instructions, and send the intermediate computing results of the first network layer to the data buffer. The acceleration device for deep learning provided by the present application improves the processing efficiency of the vocoder neural network.

The application discloses a kind of robot dexterous operation systems, methods, equipment and media for transparent object, belong to robot dexterous operation and three-dimensional perception field, system includes: point cloud data construction module, can be constructed and noisy to obtain noisy hand-object interaction point cloud by physical simulation;Point cloud feature extraction module can extract high-dimensional latent features from noisy hand-object interaction point cloud;Query prediction module can infer object shape and pose by query point generation and decoder decoding;Perception coding module can extract features from global point cloud, hand-object interaction point cloud and tactile information to obtain multi-source perception features;Multi-modal feature fusion module can realize feature integration through self-attention mechanism and cross-attention mechanism calculation, and output fusion features;Action generation strategy module can generate differentiated action instructions for robot arm and dexterous hand based on fusion features.The system can achieve higher adaptability and stronger generalization capability in transparent object operation task.

The application relates to the technical field of laser precision machining, in particular to an optical coherence tomography real-time feedback control system based on neuromorphic computing, which comprises an optical coherence tomography device and a processing module; the optical coherence tomography device comprises a collecting module and an executing module; the collecting module is used for collecting an analog voltage signal corresponding to an original optical interference signal of a biological tissue; the processing module is used for converting the analog voltage signal into a digital signal stream, inputting the digital signal stream into a neural network model, outputting a target depth position index from the neural network model, and generating a control signal according to the target depth position index; and the executing module is used for controlling the energy output of a surgical laser guided by the optical coherence tomography according to the control signal, simulating a reflex arc mechanism of a biological nervous system, constructing a bionic optical reflex arc architecture, and being low in calculation delay and small in computing power consumption. Therefore, the problems that related technologies cannot match microsecond laser pulses and cannot realize precise control are solved.

The present application relates to a kind of marine diffusible matter concentration field prediction method, system and equipment, belong to marine environment monitoring technical field.It includes: respectively deploying acoustic sensor node cluster to each sub-region of diffusible matter distribution, and constructs multiple NG-RC module;The acoustic sensor node in each acoustic sensor node cluster is divided into prediction and observation sensor node, and corresponding original observation sequence is obtained;Input vector is obtained according to original observation sequence, the vector is input into NG-RC module, and the local concentration prediction result of each sub-region is obtained;Cross-regional association information fusion is carried out to each NG-RC module, and according to local concentration prediction result, the global prediction result of each sub-region is obtained;According to the spatial position of each sub-region, the global prediction result of each sub-region is spliced, and the prediction concentration value of corresponding time whole region is obtained.The present application improves timing prediction ability and improves prediction precision, and enhances the adaptability to complex environment.

The invention discloses a high-definition rendering method and system of a liquid circulation processing configuration, the high-definition rendering system of the liquid circulation processing configuration comprises a client and a cloud server, the client is used for obtaining eye movement data of a user and sending a request to the cloud server; the cloud server comprises an API gateway which is used for obtaining eye movement data and requests from the client, distributing the requests and the eye movement data to corresponding service modules and then returning processing results to the client; the fluid dynamic calculation module is used for performing fluid dynamic simulation on the liquid according to the request information to obtain a fluid dynamic calculation result; and the image rendering module is used for receiving a fluid dynamics calculation result. According to the method, simulation and rendering of liquid fluid dynamics are carried out through the cloud high-performance GPU, a WebGL technology is combined, a high-definition rendering effect can be presented at a client with lower hardware burden, user behaviors and a region of interest can be predicted through the prediction model, rendering in advance is realized, and distribution of rendering resources is optimized.

The application discloses a kind of adaptive optics real-time controller hardware architecture based on multi-core CPU and GPU.Shack-Hartmann wavefront sensor sub-aperture slope calculation, wavefront recovery and wavefront control are completed in parallel by multi-core CPU and GPU using the real-time controller hardware architecture.The application uses general multi-core CPU and GPU as computing platform, after receiving image data in multi-core CPU, part of sub-aperture image data is transmitted to GPU by PCIE bus using a CPU core, and wavefront calculation task of the part of sub-aperture is completed by GPU;At the same time, the remaining CPU core is used to complete the remaining sub-aperture wavefront calculation task in parallel, to reduce the purpose of real-time controller calculation delay.The application uses multi-core CPU and GPU in parallel to complete wavefront calculation task, to reduce the effect of adaptive optics real-time controller calculation delay, to meet the real-time requirement of adaptive optics system to real-time controller, especially suitable for next-generation large-aperture ground-based telescope adaptive optics system real-time control.

The application discloses a kind of adaptive non-sine orthogonal conversion method and storage medium, it is related to digital signal processing field.The steps of the method include: the data to be converted into digital matrix;Digital matrix is processed;Conversion processing includes: adjacent data pairing is operated by butterfly addition and subtraction, and primary conversion data is obtained;The data pairing mode corresponding to the type of non-sine orthogonal conversion required is determined, and the primary conversion data is paired and operated by butterfly addition and subtraction according to the data pairing mode, and multi-stage conversion data is obtained.The application is processed by butterfly addition and subtraction and multi-stage processing flow This parallel processing mode greatly reduces the calculation delay of single conversion, can easily cope with the real-time processing demand of high-resolution, high-frame-rate image data, especially suitable for security monitoring, industrial detection and other time-sensitive scenes.

Embodiments of the present application provide a request processing method and device, electronic equipment and computer readable storage medium, and relate to the technical field of computers. The method comprises: determining a response end for responding to the display request according to the number of target electronic labels requested in the display request and / or the estimated response time of the central cloud server responding to the display request; and responding to the display request based on the response end. In this way, the display requirement of the electronic labels in the actual scene and the data processing capability of the central cloud server can be flexibly determined to respond to the display request by the central cloud server and / or the edge cloud server, thereby relieving the processing pressure of the central cloud server, reducing the network bandwidth occupation, and reducing the calculation delay.

The invention relates to the technical field of hydrological monitoring and computer vision, in particular to a hydrological station flow monitoring system and method based on deep learning, and the method comprises the steps: synchronously collecting the water level time sequence data of a river section and a video key frame flow containing water surface texture; converting the water level time sequence data into a corresponding water passing area numerical value and a hydraulic radius numerical value; outputting a flow state feature vector representing the dispersion degree of the water surface flow velocity; outputting a physical parameter vector changing along with time; calculating a moving average value of the river course roughness coefficient in a preset time window; judging whether the moving average value is greater than a preset siltation alarm threshold value or not; if the judgment result is yes, generating a river deposition early warning data packet and sending the data packet to a remote monitoring terminal; otherwise, generating a state log of normal operation of the river channel and storing the state log into the local database; the limit that a traditional flowmeter can only output numerical values is broken through, and a key diagnosis basis is provided for operation and maintenance and flood control decision making of a hydrological station.

The invention discloses an auto-regression and mask diffusion double-normal-form fusion language model hardware acceleration system based on an FPGA (Field Programmable Gate Array), and relates to the field of FPGA and machine learning. The invention provides a model core calculation process-oriented hardware acceleration architecture by aiming at a language model fusing double normal forms of an autoregression model and a mask diffusion model and adopting the characteristics of revising an attention mechanism and parallel generation of a KV cache. The method disclosed by the invention is implemented by taking an Eso-LMs (Esolic Language Models) model as an example. The system comprises a layer normalization and adaptive layer normalization modulation module, a QKV projection module, a rotation position coding application module, a KV cache management module, a multi-head attention calculation module, an output projection and residual connection module and a multi-layer perceptron module. By optimizing the calculation sequence and the data flow of each module in the model calculation process and adopting the pipeline parallel and resource reuse technology, the efficient reasoning acceleration of the language model fusing the autoregression and mask diffusion double normal forms on the FPGA platform is realized, and the model reasoning speed is obviously improved. According to the system, the advantage of FPGA customizable hardware acceleration is fully exerted, the utilization efficiency of hardware resources is improved, data pipeline blockage is eliminated, calculation delay and storage overhead are reduced by reconstructing the data flow direction and constructing a whole-process pipeline processing architecture, and the system is suitable for the deployment requirement of an edge calculation scene.

The invention provides a double-peak-value current control strategy of a four-switch Buck-Boost converter, belongs to the technical field of converter control, and solves the problems that an existing control algorithm is relatively large in delay during high-frequency real-time calculation, and the control method still needs to switch algorithms under light-load and heavy-load conditions. Comprising the following steps: dividing a switching period into four stages: an energy storage stage D-A, a direct connection stage A-B, an energy release stage B-C and a clamping stage C-D according to on and off states of a switching tube of the FSBB converter; a voltage regulator is introduced to the point B to output Vc1, so that the point B is related to the point A, and the FSBB is limited to control the degree of freedom; and the specific value information of the input voltage and the output voltage is detected, the inductive current working state of the FSBB in the step-up / step-down state is determined according to the magnitude relation of the input voltage and the output voltage, and a control logic circuit is constructed to complete double-peak current control.

The application discloses an intelligent agent real-time decision-making method and system based on Riemannian manifold and a medium, and relates to the technical field of artificial intelligence. The method is executed by an intelligent decision-making system, and comprises the following steps: constructing a behavior transition graph according to a historical trajectory data set; mapping an attention matrix generated by a large language model in a decision-making task to a symmetric positive definite matrix manifold for representation; embedding the behavior transition graph into a hyperbolic Riemannian space for representation; learning a geometric alignment mapping from the symmetric positive definite matrix manifold and the hyperbolic Riemannian space to a common metric space by optimizing an objective loss function; in the reasoning stage, obtaining current environment observation data, inputting the large language model, obtaining corresponding attention representation, and mapping the attention representation to the common metric space to obtain a query vector; and taking an action corresponding to an action node with a geometric distance lower than a preset threshold as a control instruction. In this way, the decision-making calculation overhead can be significantly reduced, and the cross-scene generalization capability and decision-making interpretability can be improved.

The application discloses an SNN hardware accelerator, belongs to the technical field of integrated circuits, and provides a hardware architecture for realizing an STDP+DFA algorithm, and realizes the calculation of each network layer of an SNN network based on a LIF neuron array; a plurality of activity counters corresponding to each neuron in the SNN network are arranged in the SNN hardware accelerator; the number of pulse firings of the corresponding neuron is recorded through the activity counter; when a network training request is received, the neuron with the number of pulse firings greater than a preset activity threshold is taken as an active neuron, the active neuron firing a pulse at a current time step t is taken as a neuron to be updated, and when the corresponding error signal is calculated, only the column vector under the column index corresponding to the neuron to be updated in the preset sparse matrix is multiplied by the corresponding error loss gradient vector, so that the SNN hardware accelerator with high precision can be realized with lower calculation resource consumption.

The invention relates to the technical field of electronic test and measurement, and particularly discloses a complex signal multi-objective optimization system and method based on a PXIe bus, the system comprises a system controller, a PXIe bus backboard and a functional hardware module, the functional hardware module comprises a signal acquisition module, a core processing module, a signal output module and an auxiliary module; the signal acquisition module is used for converting a complex analog signal into a complex digital signal; the core processing module is used for processing the complex digital signals according to the current configuration parameters and obtaining optimized configuration parameters through a multi-objective optimization algorithm; and the signal output module is used for converting the optimized configuration parameters into actual physical signals and then outputting the actual physical signals so as to drive subsequent execution equipment or serve as feedback signals. According to the invention, the high bandwidth, low delay and modularization characteristics of the PXIe bus are utilized, and a multi-objective optimization algorithm is combined to realize efficient acquisition, processing and optimization of complex signals, so that the real-time performance, precision and flexibility of signal processing are improved.

The invention relates to a business product actuarial calculation method based on a distributed parallel computing framework. The method comprises the following steps: submitting a newly added attribute value determination task to an attribute value determination task queue through a compilation type application program; the newly added attribute value determination task carries an attribute value determination model of the business product; under the condition that the number of the attribute value determination tasks in the execution process in the attribute value determination task queue is smaller than the number of the servers, an idle server is occupied through a compilation type application program; calling an interpretation type application program through a compiling type application program, determining a model point in the attribute value determination model, splitting the attribute value determination task in the attribute value determination task queue into a plurality of parallel subtasks according to the model point, and distributing the plurality of parallel subtasks to an idle server for parallel processing, and obtaining an attribute value determination result of the business product. By adopting the method, the business product attribute value determination efficiency can be improved, and the calculation delay is reduced.

This invention discloses a method for parallelizing and pipelining a nested multiplier, relating to the field of intelligent warehousing technology. Based on the nested multiplication concept, the multiplication operation is decomposed into a formula to obtain the squaring operation of the high-bit part and the difference of squares plus shift operation of the low-bit part. Based on the characteristic of 2ab in the multiplication formula, the intermediate values ​​required for high-bit calculation are obtained by querying a preset low-bit square value table through the low-bit results. For batch data, multiple sets of data are processed simultaneously through a parallel architecture. The overall calculation process is divided into multiple pipeline stages, and continuous calculation is achieved through stage cascading. The pipeline output results of each parallel computing unit are collected, verified, and integrated to output a complete set of multiplication results. This invention achieves breakthroughs in hardware resources, computational latency, and batch throughput through the collaborative design of nested recursive simplification, pipeline reuse, and parallel architecture, providing an efficient solution for high real-time and high-parallelism digital computing scenarios.

This invention provides a method for accelerating the compression of intelligent models on edge terminals, relating to the field of edge intelligence. Its key feature is that it includes: acquiring real-time operating status data of the edge terminal and feature information of the current input data, wherein the real-time operating status data includes computing resource load, memory occupancy, battery level, and device temperature. The advantages of this invention are: by sensing the device status and input complexity in real time, and utilizing reinforcement learning to dynamically generate an optimal strategy combination including pruning, hybrid quantization, and early termination mechanisms, this method overcomes the limitations of traditional static compression, achieving a dynamic balance between computing power, accuracy, and energy consumption. It not only significantly reduces inference latency and memory usage but also adaptively adjusts based on battery level and temperature, effectively solving the problems of difficult deployment, high heat generation, and short battery life of large models on resource-constrained edge devices, and greatly improving the real-time performance and stability of intelligent applications.

The application is specifically an optimization method of an air unmanned aerial vehicle communication network based on AI, relates to the technical field of communication networks, and comprises intelligent sensing and data processing, an AI decision and optimization core, communication and task collaborative management, and resource and energy consumption optimization.In the application, a laser radar scans a canyon terrain in real time, a cutoff frequency is calculated in combination with a rectangular waveguide model, a transverse electric wave transmission mode is dynamically adjusted, terrain changes are predicted in advance and mode switching is triggered, a buffer interval and a rollback mechanism are matched, and signal interruption caused by a terrain-induced multipath trap can be avoided; when a canyon width suddenly changes, mode switching is started in advance, parameter updating is completed before the unmanned aerial vehicle reaches a critical area, the risk of communication interruption is reduced, the rollback mechanism can correct erroneous switching, and link continuity is ensured.

This invention belongs to the field of high-precision position detection technology, and particularly relates to an absolute grating position calculation method based on an adaptive error-correcting sliding window. A photodetector array, in conjunction with an error-correcting sliding window, collects photoelectric signals of symbols, converting them into a symbol amplitude sequence. Abnormal erased symbols are identified through symbol confidence levels. If erased symbols are found, the window length is gradually expanded, and the process is repeated iteratively until a qualified target error-correcting sliding window is obtained. After removing erased symbols within the target error-correcting sliding window, grating position calculation is performed. After detecting a single acquisition position, the process is repeated for subsequent acquisition positions until the task is completed. This invention relies on adaptive iteration of the window to achieve signal error correction, reducing the interference of bad symbols on the calculation results and effectively improving the overall performance of grating position detection.

This invention discloses an FPV unmanned aerial vehicle (UAV) identification method and apparatus based on analog image transmission signals. The method includes: S1, setting acquisition parameter information, including acquisition center frequency and acquisition bandwidth; S2, acquiring spatial electromagnetic wave signals based on the acquisition parameter information to obtain an acquisition signal; S3, performing identification processing on the acquisition signal to obtain an identification signal.

The application relates to the technical field of artificial intelligence security, and provides an agent runtime security control method and device, which comprises the following steps: maintaining a structured security state digest containing a historical interaction compressed representation and not containing complete plaintext during the running of an agent; in response to a current interaction request, performing security reflection based on the digest and a loaded dynamic defense strategy, and outputting a security disposal decision; when a preset security anomaly triggering condition is met, marking an accident candidate session; extracting a generalization risk feature based on the interaction track of the accident candidate session, performing desensitization processing, and generating a dynamic defense strategy for subsequent session loading. The application realizes the structured precipitation and lightweight runtime security reflection of defense knowledge, and supports the closed-loop self-evolution of security capability.

The invention relates to the technical field of computing resource allocation, and discloses a satellite-assisted multi-unmanned aerial vehicle computing unloading method and device and a program product, and the method comprises the steps: obtaining a state sample set generated by interaction between each unmanned aerial vehicle and a satellite mobile edge computing network and stored in an experience playback buffer area; judging whether the number of state samples in each state sample set is greater than or equal to a preset batch size; and when the number of the state samples in the state sample set is greater than or equal to a preset batch size, updating the initial calculation unloading strategy of each unmanned aerial vehicle by using a near-end strategy optimization algorithm until the satellite mobile edge computing network is in a stable state, and obtaining an optimal calculation unloading strategy of the unmanned aerial vehicle, according to the invention, low energy consumption and low calculation delay of the unmanned aerial vehicles are ensured in a high-dynamic network environment, and conflicts among the unmanned aerial vehicles when the unmanned aerial vehicles acquire calculation resources are reduced.

The invention discloses a topological link sensing task collaborative unloading method for a V2V and V2I combined system. A delay minimization problem of sequential subtasks in a V2I and V2V combined system model is expressed as a path optimization problem and modeled as a Markov decision process, an action selected by an optimal unloading scheme under a time window is obtained, a task execution process is further obtained, the task execution process is divided into the time window, and the time window of the task execution process is obtained. Calculating the task calculation amount in each time window under the current pulse parameter, and then carrying out Gaussian fitting on the task calculation amount to obtain a Gaussian curve; and fitting Gaussian curve parameters, and predicting the time window task calculation amount under other pulse parameters. By combining the TLCO and the STW, the method achieves the efficient prediction of the calculation workload of the V2V and V2I systems on different time slices, can provide an optimization basis for an unloading decision, and reduces the calculation delay and communication overhead.