2423 results about "Parallel processing" patented technology

A parallel processing unit comprises a plurality of processors each being coupled to a memory access hardware circuitry. Each memory access hardware circuitry is configured to receive, from the coupled processor, a memory access request specifying a coordinate of a multidimensional data structure, wherein the memory access hardware circuit is one of a plurality of memory access circuitry each coupled to a respective one of the processors; and, in response to the memory access request, translate the coordinate of the multidimensional data structure into plural memory addresses for the multidimensional data structure and using the plural memory addresses, asynchronously transfer at least a portion of the multidimensional data structure for processing by at least the coupled processor. The memory locations may be in the shared memory of the coupled processor and / or an external memory.

The invention relates to the field of power data management, and discloses a power big data adaptive management method and system fused with spatial-temporal feature mapping, and the method comprises the steps: obtaining a real-time operation data flow from a multi-source power terminal, and constructing an original power data set with a time sequence label and a device identifier; the method comprises the following steps: dividing an original power data set into parallel processing units based on a storage-while-computing architecture, performing dynamic index updating by adopting an event-driven index mapping rule, and constructing a multi-dimensional data index cache system with real-time responsiveness; identifying a key abnormal trajectory through a time-varying feature nesting mechanism, and performing hierarchical measurement and entropy disturbance analysis on a data fluctuation degree in the key abnormal trajectory by using a streaming feature aggregation network; identifying potential security risk nodes in combination with the structure matching degree between the historical abnormal event evolution graph and the key abnormal trajectory; and generating a multi-level response instruction chain based on the risk assessment result. The method has the advantage of improving the operation safety of the power grid.

A new transaction barrier synchronization primitive enables executing threads and asynchronous transactions to synchronize across parallel processors. The asynchronous transactions may include transactions resulting from, for example, hardware data movement units such as direct memory units, etc. A hardware synchronization circuit may provide for the synchronization primitive to be stored in a cache memory so that barrier operations may be accelerated by the circuit. A new wait mechanism reduces software overhead associated with waiting on a barrier.

The invention discloses a multi-mode fusion product document and source code association retrieval method based on a knowledge graph, and relates to the technical field of software engineering and artificial intelligence. The method comprises the steps that source codes are preprocessed, and code structure information and business semantics are mapped in combination with a predefined business term dictionary; performing controlled induction on a code file and a product document by utilizing a large model, extracting business terms, logic intentions and a subject relationship, fusing with original codes, and establishing a vector retrieval index system; further analyzing a code structure by using an abstract syntax tree, and extracting an entity and a calling relationship; semantic enhancement and relation normalization are performed in combination with the large model, entities and relations are stored in a graph database, and a knowledge graph is formed; and performing parallel processing on user query based on a full-text retrieval index, a vector retrieval index system and a knowledge graph, and finally generating a product concept. According to the method, the retrieval speed, the semantic depth and the logical reasoning ability can be considered at the same time, and the retrieval accuracy is improved.

The invention discloses a 10KV station electric control system of a convertor station adopting selecting 2 from 3 logic. Two PS830 boards are added, three PS830 boards are utilized to concurrently process and jointly realize a spare power automatic switching function and an operation interlocking logic function; the selecting 2 from 3 logic is added in PS853 programs of an ASI host machine and a switching value output board, i.e. the electric control system can be exported when at least two of three integrated circuit boards sends out same instructions. The damage of any one of the three PS830 boards can not lead to switch fault trip or refusing trip, the 10KV control system can be ensured to run safely and stably without being influenced by the faults of single element. The electric control system has the advantages of convenient use, safety and the like.

The invention relates to the technical field of intelligent diagnosis of power equipment, and provides a multi-mode fusion extra-high voltage converter transformer fault diagnosis method and system, and the method comprises the steps: collecting a multi-mode signal from a sensor of an extra-high voltage converter transformer, and classifying the signal into a plurality of modes; performing intra-modal feature reinforcement learning on the multi-modal data by adopting a SimCLR framework to obtain a discriminative representation feature vector zm of each modal; inputting the zm into a Transform branch encoder of a corresponding mode, and obtaining context feature vector enhancement representation hm of each mode; mapping the hm of different modalities to the same dimension in a unified manner, and performing weighted attention fusion to obtain feature vectors zf of all modalities after fusion; and inputting a multi-layer perceptron classifier (MLP) to obtain a fault category prediction result of the extra-high voltage converter transformer. According to the method, the multi-mode signals are processed and fused in parallel, and the fault recognition capability of the model on the extra-high voltage converter transformer in the complex operation state is improved.

The invention relates to the technical field of intelligent monitoring, in particular to a multi-thread low-power-consumption intelligent monitoring system based on an AI processor. The method has the advantages that aiming at the problems of unbalanced computing power and power consumption, high multi-task processing delay and strong hardware dependence in the prior art, the NPU module of the RK3588 processor is combined with the INT8 quantitative model, so that the power consumption is lower than 10W under the 6TOPS computing power; a dynamic multi-thread scheduling mechanism is designed, parallel processing of more than eight paths of video streams is supported through binding of a priority queue and an NPU core, and end-to-end delay is compressed to be within 200 ms; a zero-copy video stream architecture is constructed, data transfer is eliminated through memory mapping, and preprocessing time consumption is reduced by 90%; an energy efficiency control module is integrated, the NPU voltage frequency is dynamically adjusted according to the load, and the energy efficiency ratio reaches 0.83 TOPS / W; space-time alignment of multi-model reasoning results is realized by adopting a frame ID synchronization technology, and the mismatching rate is lower than 0.1%.

The invention discloses a traffic image labeling method and device based on a D-S evidence theory and a medium, and relates to the technical field of image labeling. According to the method, two different types of real-time models are simultaneously utilized to process the same image in parallel, and two uncertainty detection results of the same image are obtained; a KM algorithm is utilized to match targets in two uncertainty detection results, then a prior credibility score is utilized to reduce a conflict coefficient, and two different types of small model prediction results are combined through an uncertainty theory. According to the traffic image labeling method and device based on the D-S evidence theory and the medium, the strong generalization ability of the open set model is utilized to make up for the defects of a closed set model, the use of a large model to improve the hardware dependence is avoided, the precision problem of a single small model is made up under the condition that the efficiency is ensured, and the iteration duration of the model is shortened.

The invention relates to the technical field of computer information processing, and discloses a high-fidelity terrain surface interpolation method and system for large-scale point cloud data, and the method comprises the steps: carrying out the multi-level cleaning of original point cloud data, and generating a cleaned point cloud data set; performing adaptive tile grid division based on the cleaned data to generate a tile set covering the target area; in each tile, taking the to-be-interpolated grid point as a query point, constructing and optimizing a local Gaussian process model, and obtaining a real elevation predicted value of the query point; processing all query points in the tiles in parallel to obtain a tile elevation interpolation result set; performing weighted average on each tile result to generate a global seamless terrain surface; according to the method, the problems of poor expandability and surface discontinuity caused by local interpolation in large-scale point cloud data processing are effectively solved, and high-precision and high-fidelity terrain surface construction is realized.

The invention discloses an electric power communication analysis system and method based on big data, and the method comprises the steps: collecting multi-source heterogeneous data, carrying out the sensitivity grading, and generating labels; gathering the data to a big data platform, and completing storage, partitioning and index construction; an asynchronous main control chain mechanism is constructed, high-optimal data is dispatched for rapid anomaly judgment, and other data is processed in parallel; performing desensitization mapping on the high-sensitivity data to generate a short-time mapping bill and performing desensitization analysis; issuing a local task for the low-confidence exception, collecting backflow data, and verifying and determining a high-risk event; restoring the sensitive data in the authorization window, and destroying the bill and the secret key after abnormity analysis is completed; and triggering network regulation based on an analysis result, and recording the whole process to an audit log. By introducing an asynchronous scheduling and reversible desensitization mechanism, high-efficiency anomaly analysis and whole-process traceability of the electric power communication big data on the premise of ensuring safety and compliance are realized.

The embodiment of the invention discloses a dynamic computing power scheduling method and device based on deep learning and a medium, belongs to the technical field of cloud computing, and solves the problem that cloud computing resources are seriously wasted due to the fact that a cloud computing scheduling method in the prior art is prone to unbalanced resource allocation. Comprising the following steps: preprocessing acquired cloud computing data to generate a structured feature vector; wherein the cloud computing data at least comprises cloud node state data, computing task attributes and environment data; through a multi-head attention mechanism, task resource space-time correlation features corresponding to the structured feature vectors are extracted; the task resource space-time correlation features are input into a weight dynamic prediction module and a resource matching degree scoring module at the same time so as to carry out parallel processing of weight prediction and matching degree scoring calculation; and solving a multi-objective optimization function corresponding to computing power scheduling based on a parallel processing result, and generating a computing power scheduling instruction based on a solving result.

The invention discloses an electrocardiosignal preprocessing system and method based on filtering and deep learning, and relates to the field of electrocardiosignal data processing. The multi-stage adaptive filtering module comprises a baseline drift elimination unit, a power frequency interference suppression unit and a myoelectricity noise removal unit, and all the units are connected in sequence to form pipelined parallel processing; the deep learning fusion module is used for performing deep feature extraction and noise classification on the output signal and feeding back a classification result to the multi-stage adaptive filtering module; the signal quality evaluation module carries out quality evaluation on the electrocardiosignals subjected to multi-stage adaptive filtering and deep learning fusion and judges whether the signal quality is qualified or not; a feature enhancement and standardization module; the technical effects of improving the self-adaptability and robustness, improving the calculation efficiency of heart disease classification, the signal fidelity and the diagnosis reliability, and enhancing the signal quality evaluability and the self-adaptive ability are achieved.

The invention relates to the technical field of data information retrieval, and discloses an efficient batch privacy information retrieval method and system based on OCD and GPU optimizing.The efficient batch privacy information retrieval method comprises the steps that firstly, a server is initialized, a database is subjected to bucket division through a PBC encoding algorithm based on the client query number, the database subjected to bucket division is obtained, and when a user conducts information retrieval, the user can retrieve privacy information in a batch mode; the method comprises the following steps of: finding a sub-bucket position of a retrieval request in a server at a client by using a PBC scheduling algorithm, carrying out homomorphic encryption on the retrieval request in each sub-bucket, compressing all the retrieval requests by using an OCD to obtain a retrieval ciphertext, sending the retrieval ciphertext to the server, and sending the retrieval ciphertext to the server according to the retrieval ciphertext provided by the client. The retrieval result in the ciphertext form is obtained and returned to the client side, the client side decrypts the retrieval result in the ciphertext form, and the required retrieval result in the plaintext form is obtained. According to the method, the GPU is used for parallel processing, computing resources in a real scene can be fully utilized, and the computing efficiency of privacy information retrieval is remarkably improved.

The invention relates to the technical field of tunnel engineering monitoring and construction, and discloses a shield construction tunnel full deformation prediction method based on artificial intelligence. The method comprises the following steps: acquiring a geological sensing data stream, a construction operation data stream and a historical deformation case library; performing multi-modal data fusion on the geological sensing data flow and the construction operation data flow to generate a construction environment map with consistent time and space; searching a case sequence matched with the current construction environment map from a historical deformation case library, performing feature significance evaluation through the case sequence, and identifying a dominant feature group of full deformation prediction; constructing an algorithm preferential engine based on the dominant feature group; activating an algorithm preferential engine to perform parallel processing on the construction environment map, and generating an adaptability measurement set of each algorithm; integrating the adaptability measurement set and real-time construction limiting conditions, and selecting an optimal prediction algorithm by adopting a trade-off decision-making mechanism; and generating a full deformation prediction model, and integrating the model to a shield construction monitoring platform.

The invention discloses a spectrum-space depth fusion hyperspectral image classification method oriented to a small sample condition, and the method comprises the steps: firstly carrying out the multi-scale hole convolution processing of input hyperspectral data through a range attention convolution SAC module, and extracting the multi-scale context features; then, a spatial normalization attention SNA mechanism is utilized to carry out adaptive weighting adjustment of spatial dimensions on the feature map, and spatial feature representation of the key area is enhanced; the method comprises the following steps: constructing a lightweight hybrid expert model LMOE, carrying out parallel processing and gating weighting through a multi-path expert network, carrying out efficient refining and mapping on features, finally fusing processed spectral features and spatial features, and carrying out pixel-level prediction through a classifier to obtain a terrain classification result map of a hyperspectral image. The method solves the problems that in the prior art, overfitting is prone to occurring under the small sample condition, the spectrum-space collaborative modeling capacity is insufficient, the long-range dependence obtaining efficiency is low, and the recognition precision is reduced under the class imbalance scene.

Hybrid content item chunking techniques for retrieval augmented generation (RAG) systems are disclosed. The techniques employ a dual approach, combining size-based and semantic chunking with layout-based chunking. The techniques analyze content for layout indicators, creating two sets of chunks that are then merged into a hybrid set. This hybrid set is loaded into a database for subsequent searches. The techniques offer several technical advantages, including improved handling of diverse document types, potential for parallel processing, and enhanced capture of both semantic meaning and structural layout. By maintaining size constraints and adapting to various formats, the techniques provide a more comprehensive representation of document content. The techniques overcome limitations of single-method approaches, potentially leading to more accurate information retrieval, improved context preservation, and enhanced RAG system performance across varied document types.

A neural-symbolic hybrid system for generating binary document formats directly from natural language input comprises a binary-aware hierarchical tokenizer operating across four levels (binary bytes, structural elements, semantic content, and concepts), a constraint satisfaction engine with 64 parallel processing cores for enforcing structural integrity and mathematical consistency, format-specific processors for Excel, PowerPoint, PDF, and CAD documents, and a formal verification system generating mathematical proofs of correctness. The system includes custom AI Document Generation Processor (AIDGP) silicon spanning 600 mm2 with specialized cores providing 500 TOPS processing power. Performance characteristics include 99.7% structural accuracy, 100% format compliance, 15.3 second average generation time for complex documents, and distributed capacity of 1,000,000 documents per hour. The system eliminates intermediate conversion steps while maintaining semantic preservation through hardware-accelerated constraint satisfaction and formal verification engines ensuring structural integrity, format compliance, and security through AES-256 encryption and automated regulatory compliance across 25+ international standards.

The invention relates to the technical field of intelligent diagnosis, and discloses a micro-grid fault diagnosis method and system based on data driving and unsupervised learning. The method comprises the following steps: collecting current, voltage, temperature and power data of a micro-grid and constructing a time sequence matrix; inputting a time sequence prediction network and a time sequence reconstruction network, and performing parallel processing to obtain a prediction error and a reconstruction error; carrying out weighted fusion on the two errors and constructing a two-dimensional error space to judge normal fluctuation and fault abnormity; and extracting a state variable to generate a dynamic threshold to judge a fault. The false alarm rate and the missing report rate of fault diagnosis are reduced.

The invention discloses an automatic auditing method and system based on ship-shore model matching fusion, and belongs to the technical field of data processing.The method comprises the steps that ship-shore matching related documents of a user are interacted, and the ship-shore matching related documents support multiple formats; activating a multi-model fusion processing module to perform preprocessing and multi-modal analysis on the ship-shore matching related document, extracting a text, a visual element and structured data, and generating a structured data object; a preset rule engine and the large language model are called to process the structured data object in parallel, the rule engine executes deterministic rule verification, and the large language model processes uncertainty semantic recognition determination; and fusing output results of the rule engine and the large language model to generate an audit result and a risk prompt. The problems that in the prior art, ship-shore matching auditing depends on labor, the efficiency is low, errors are large, multi-format documents are difficult to process through a single technology, rule and semantic coverage is incomplete, information fragmentation is caused, and auditing accuracy and efficiency are difficult to consider at the same time are solved.

The invention discloses a plant protection field literature information batch structured extraction method based on an AI large model, and belongs to the technical field of computer data processing and artificial intelligence application. According to the method, a PDF format literature is converted into a Markdown format text through a PDF literature self-adaptive preprocessing module and a Markdown conversion module; then, a double-strategy self-adaptive AI extraction module is adopted, different modes are adopted for processing according to a text length threshold value, and JSON data are extracted in combination with a JSON format data restoration strategy; then, the CPU intensive conversion task and the I / O intensive AI analysis task are processed in parallel through a two-stage parallel scheduling module, and a structured database file is generated through aggregation according to a predefined mapping rule through a multi-dimensional aggregation export module. According to the method, end-to-end automation from literature acquisition to structured data output is realized, and the problem of low extraction efficiency of manual literature reading information is solved.

A system for encoding and compressing images and textures to a bitstream as an executable program of computer instructions operable on pixel space, permitting the Encoder to arbitrarily determine the order, location and method used for reconstructing the components of an image at the decoder. The bitstream is typically further compressed by an Adaptive Entropy Compressor. Bitstream execution reconstructs the image directly to pixel space. Memory management and parallel processing controls may be embedded in the bitstream. The system is optimised for AI processing of images with a universally interpretable construction format that enables machines and humans to understand precisely how the image was created and can be reconstructed. Dual bitstreams may be combined at the decoder for securely embedding customised content (e.g., advertising) at the edge.

The invention discloses a multi-motor parallel control system and method based on an FPGA, and belongs to the technical field of multi-motor parallel control. The FPGA module is in communication connection with the control processing unit, and the FPGA module is internally provided with a global synchronous triggering unit used for generating a periodic synchronous triggering signal; the number of the position acquisition sub-modules corresponds to that of the motors, and each position acquisition sub-module comprises a position counter and a hardware latch register, wherein the position counter is used for carrying out counting and direction decoding on encoder pulses in real time; wherein the global synchronous triggering unit is connected with all the position acquisition sub-modules. According to the multi-motor synchronous control system, the position and other state signals of the multiple motors are collected at the same time through the parallel processing capacity of FPGA hardware, real-time control is achieved in combination with the control processing unit, and therefore the multi-motor synchronous control precision is improved, and the response speed is increased.

The invention relates to the technical field of streaming computing, and provides a real-time service computing system based on a dynamic rule engine, which comprises a rule management module and a streaming computing engine, the rule management module is used for providing visual configuration and release functions of service rules and performing versioning storage on the released service rules; the streaming computation engine comprises a rule synchronization unit and a plurality of parallel processing units; the rule synchronization unit is used for acquiring service rules from the rule management module and distributing the acquired service rules to each parallel processing unit based on a broadcast mechanism; and each parallel processing unit is used for receiving the business event flow and performing real-time rule matching on the business event flow according to the received business rule so as to output a decision result. According to the system, complete decoupling of business rule configuration and execution is realized, and the problem that rule updating in a traditional business system needs shutdown deployment is effectively solved.

The invention relates to the technical field of environment regulation and control, and discloses a multi-parameter environment closed-loop regulation and control method and system based on an FPGA, and the method comprises the steps: unifying monitoring data to a same space coordinate system through the FPGA according to the monitoring data collected by a sensor network disposed in an environment, analyzing the coupling relation between different parameter data, and obtaining fusion data; based on the fusion data, analyzing the environment crop state through a preset crop state recognition model, simulating the influence condition of different parameter adjustment processes on the crop state, and generating a first control instruction set; analyzing the degree of deviation between the environmental parameters in the fused data and a preset target value, calculating the priority of each control instruction in the first control instruction set, and merging and optimizing the control instructions; the environmental parameters are corrected; according to the application, the regulation and control efficiency can be improved, the environmental disturbance and the crop demand change can be quickly responded through FPGA parallel processing, and the environmental regulation and control efficiency and the regulation and control effect are improved.

The invention provides a CycleGAN-based brain blood oxygen signal enhancement method and system, and the method comprises the steps: building a mapping relation between a wearable device and a clinical-level device, enabling the wearable device and the clinical-level device to synchronously collect a brain blood oxygen signal, carrying out the preprocessing, and constructing a training data set; carrying out secondary preprocessing on the brain blood oxygen signal by adopting a cascade noise reduction module; the method comprises the following steps: constructing a CycleGAN network architecture by adopting a bidirectional generator network and a discriminator network, and obtaining an fNIRS-CycleGAN network model by optimizing parameters of the network architecture and training; different frequency band components of the brain blood oxygen signals are processed in parallel through convolution kernels of different scales by adopting a multi-round iterative optimization mechanism and a multi-scale multi-iteration optimization strategy through a network model; and evaluating the enhancement effect of the brain blood oxygen signal by using the quantitative index. According to the invention, intelligent conversion from a low-quality wearable device signal to a clinical-grade high-quality signal is realized.

The invention provides a large language model training method based on a time-space tensor division strategy, and the method comprises the steps: employing a time-space collaborative tensor division strategy to divide tensor operation to a plurality of calculation devices in a time dimension and a space dimension, and enabling the calculation devices to carry out the parallel processing, each computing device only caches matrix data required by the current computing step, complete tensors or redundant copies do not need to be reserved, the problem of repeated storage of data such as activation values and weights in traditional tensor parallel is fundamentally solved, video memory occupation is greatly reduced, and the problem of redundant storage of the tensors is solved; point-to-point data transmission replaces set communication, efficient folding of communication and calculation delay is achieved, communication overhead and video memory occupation in the training process are remarkably reduced, the parallel efficiency and resource utilization rate of large language model training are remarkably improved on the premise that training precision is guaranteed, and the method is suitable for large language model training. And a brand new solution is provided for efficient training of a large language model.

The invention relates to the technical field of power distribution equipment, and discloses a centralized station terminal which comprises a main control module, an FPGA module, a remote control bus driving circuit, a remote signaling bus driving circuit, a plurality of remote control expansion circuits, a plurality of remote signaling expansion circuits and a plurality of telemetering expansion circuits. Wherein the main control module is provided with a PCIe interface, the FPGA module is connected with the main control module through a PCIe bus, and the remote control bus driving circuit and the remote signaling bus driving circuit are both electrically connected with the FPGA module. And the plurality of remote control expansion circuits are electrically connected with the remote control bus driving circuit and are used for outputting remote control signals. And the plurality of remote signaling expansion circuits are electrically connected with the remote signaling bus driving circuit and are used for receiving the remote signaling signals. And the plurality of telemetering expansion circuits are directly and electrically connected with the FPGA module and are used for receiving telemetering signals. According to the centralized station terminal, the FPGA module can process the telemetering signals received by the multiple telemetering expansion circuits in parallel, and transmits the collected data to the main control module through the PCIe bus at a high speed, so that the equipment data collection efficiency is improved.

According to the high-computing-power special processor architecture for the big data file and the processing method, a data preprocessing unit receives an original big data file and formats and cleans the original big data file, and a special acceleration computing chip executes a computing-intensive task and avoids the floating-point number precision problem; the parallel processing unit realizes parallel data processing through a MapReduce programming model, the cache storage architecture adopts a multi-level cache system and an LRU cache elimination algorithm to store an intermediate result, and the instruction set optimization module performs parallel operation on isomorphic continuous storage data. The method can be widely applied to multiple fields of data analysis, machine learning, high-performance calculation and the like, and has great significance in improving the data processing capacity in the big data era.

The invention provides an electric energy quality on-line monitoring device and a cloud platform cooperation system, and relates to the technical field of electric energy quality management, and the device comprises a signal collection unit which obtains three-phase voltage and current signals in parallel through a Rogowski coil and a capacitive voltage divider; the event detection unit is used for synchronously executing harmonic spectrum analysis and transient event capture by adopting a parallel processing architecture realized by an FPGA (Field Programmable Gate Array); the edge processing unit is connected with the event detection unit, and is configured to encode the transient event features into a Gramer angle field image and compress steady state data into feature vectors; the multimode communication unit comprises a 4G / 5G wireless module and an optical fiber Ethernet interface; and the strategy execution interface outputs a treatment instruction to the compensation device through the D / A converter and the current loop. Through collaborative innovation of the device and the cloud platform, the power quality monitoring and treatment efficiency is remarkably improved.

The invention discloses a multi-modal AI-based contract online analysis optimization system and method, and relates to the field of contract analysis, and the method comprises the steps: obtaining a to-be-analyzed contract file, and carrying out the standardization processing of the to-be-analyzed contract file; dividing the content features of the contract file into text content features, visual layout features and logic structure features, and synchronously extracting the features; dynamically generating an analysis process path through a lightweight decision tree model, and selecting an optimal analysis engine combination; calling at least three analysis engines for parallel processing based on multi-engine collaborative analysis; correcting a conflict analysis result generated by the parallel processing analysis engine based on an attention mechanism to generate a final analysis result; and recording the accuracy rate and time consumption index of each analysis, and dynamically adjusting an analysis process generation strategy through reinforcement learning. The method has the advantages that the text, visual and logic features in the contract are extracted based on the multi-modal AI technology, and the accuracy and efficiency of contract analysis are improved through multi-engine collaborative analysis and attention mechanism correction.