Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2343 results about "Memory bank" patented technology

A memory bank is a logical unit of storage in electronics, which is hardware-dependent. In a computer, the memory bank may be determined by the memory controller along with physical organization of the hardware memory slots. In a typical synchronous dynamic random-access memory (SDRAM) or double data rate synchronous dynamic random-access memory (DDR SDRAM), a bank consists of multiple rows and columns of storage units, and is usually spread out across several chips. In a single read or write operation, only one bank is accessed, therefore the number of bits in a column or a row, per bank and per chip, equals the memory bus width in bits (single channel). The size of a bank is further determined by the number of bits in a column and a row, per chip, multiplied by the number of chips in a bank.

Memory storing metadata and memory system

A memory may include a data transmission / reception circuit and a memory bank including a plurality of cell arrays. When a metadata mode is activated, data and metadata received through the data transmission / reception circuit may be distributed to and stored in the plurality of cell arrays. When the metadata mode is deactivated, the data received through the data transmission / reception circuit may be distributed to and stored in cell arrays except one or more no-access cell arrays, among the plurality of cell arrays.
Owner:SK HYNIX INC

Domain generalization method and system based on CLIP model semantic information extraction and target alignment

The invention discloses a domain generalization method and system based on CLIP model semantic information extraction and target alignment. The method comprises the steps that a detection image is input to a student model, and image features and classification prediction are obtained; and inputting the image and the text into a teacher model to obtain image and text features and classification prediction, comparing the prediction of the two models, and calculating the prediction similarity loss. Meanwhile, image features of the student model and text features of the teacher model are compared to obtain semantic loss, the semantic loss is optimized into spatial consistency loss, relative positions represented by the text features are utilized, and the loss of the spatial consistency loss, the relative positions represented by the text features and the loss of the spatial consistency loss are combined to train a feature encoder of the student model so as to extract semantic information. During testing, a memory bank is used for updating the classifier, and target domain alignment is promoted. A detection image passes through an optimization encoder and an alignment classifier to obtain a classification result, the whole process is compact and efficient, and the performance of the model in a target domain is remarkably improved; and through semantic information extraction alignment in a training stage and target alignment in a test stage, better domain generalization performance is realized.
Owner:XI AN JIAOTONG UNIV

Buffering of neural network inputs and outputs

Some embodiments provide a method for executing a neural network. The method writes a first input to a first set of physical memory banks in a unified memory shared by an input processing circuit and a neural network inference circuit that executes the neural network. While the neural network inference circuit is executing the network a first time to generate a first output for the first input, the method writes a second input to a second set of physical memory banks in the unified memory. The neural network inference circuit executes a same set of instructions to read the first input from the first set of memory banks in order to execute the network the first time and to read the second input from the second set of memory banks in order to execute the network a second time to generate a second output for the second input.
Owner:AMAZON COM SERVICES LLC

PCB defect detection method based on coordinate attention mechanism

The invention relates to the technical field of PCB defect detection, and discloses a PCB defect detection method based on a coordinate attention mechanism, and the method comprises the steps: obtaining a positive sample data set; inputting the positive sample data set into a defect detection model, and outputting a plurality of local neighborhood feature sets; repeated items are screened from the multiple local neighborhood feature sets, and the screened local neighborhood feature sets are obtained and stored in a memory bank; inputting a to-be-detected PCB picture into the defect detection model, and outputting a plurality of local feature sets; acquiring a first local neighborhood feature set closest to each local feature set from a memory bank; calculating a local anomaly score according to each local feature set and the corresponding first local neighborhood feature set; acquiring a global abnormal score graph based on all the local abnormal scores; and determining an abnormal region according to the global abnormal score graph and an abnormal threshold value, and segmenting the abnormal region to complete detection. According to the invention, the PCB defect detection accuracy and the defect segmentation precision can be improved.
Owner:GUANGDONG UNIV OF TECH +1

Memory matching industrial defect detection method based on adaptive feature fusion

The invention relates to the technical field of industrial defect detection, and discloses a memory matching industrial defect detection method based on adaptive feature fusion, and the method comprises the steps: generating a plurality of unknown defect samples through an enhanced image-level defect simulation strategy, and helping a model to effectively distinguish a normal mode from an abnormal mode; the method comprises the following steps: extracting multi-scale features of a to-be-detected sample image, a normal sample image and a defect sample image, designing an adaptive hierarchical memory bank architecture, embedding the multi-scale features into a grid memory bank in a layered manner, further improving the reasoning speed through an adaptive core set sampling strategy, and combining multi-scale feature fusion and a defect positioning optimization technology to obtain a defect positioning algorithm. And the difference between the multi-scale features and the normal mode is fully utilized, so that the accuracy of defect detection and positioning is remarkably improved. Compared with the prior art, the defect detection precision and the positioning accuracy can be improved, and meanwhile, the real-time detection requirement can be met.
Owner:SUQIAN COLLEGE

Secure over the air flashing for dual bank memories

Described techniques provide addressing schemes that account for address differences between active and inactive memory banks in dual bank memory architectures used in software over the air (SOTA) updates implemented using address swapping between the dual memory banks, including providing address translations where needed to obtain one standard addressing scheme for purposes of SOTA updates. A timing and implementation of authentication and booting techniques may ensure that signature authentication and boot processes use correct memory addresses across the dual memory banks to enable updates of both an application and a bootloader to occur. Swapping techniques are described that enable robust, secure swapping between the banks, and that enable SOTA updates to hardware security manager (HSM) software, while ensuring use of such HSM software in dual bank scenarios.
Owner:ATIEVA INC(US)

Apparatuses and methods for row hammer counter mat

Apparatuses and methods for row hammer counter mat. A memory array may have a number of memory mats and a counter memory mat. The counter mat stores count values, each of which is associated with a row in one of the other memory mats. When a row is accessed, the count value is read out, changed, and written back to the counter mat. In some embodiments, the count value may be processed within access logic of the counter mat, and a row hammer flag may be provided to the bank logic. In some embodiments, the counter mat may have a folded architecture where each sense amplifier is coupled to multiple bit lines in the counter mat. The count value may be used to determine if the accessed row is an aggressor so that its victims can be refreshed as part of a targeted refresh.
Owner:MICRON TECHNOLOGY INC

System and method for improving driving credibility based on multi-modal intelligent interaction

The invention belongs to the technical field of automatic driving, and particularly relates to a system and method for improving driving credibility based on multi-modal intelligent interaction, and the method comprises the steps: collecting behavior data, physiological signals and eye movement feature data of a driver under driving in various man-machine interaction combination mode scenes, and carrying out the preprocessing and feature extraction; inputting the initial data set into a pre-training model for fine tuning training to obtain a large model for credibility prediction and intelligent interaction recommendation; updating the large model in real time based on a feedback mechanism of a memory bank, and generating a credibility prediction result and a recommendation interaction mode; and judging whether the result meets the requirement of improving the credibility or not, and outputting an optimal man-machine interaction mode to the man-machine interaction module. The problems that in the prior art, a man-machine interaction system is low in intelligent level, and it is difficult to flexibly adjust the interaction mode according to the driver trust degree change are solved.
Owner:HANGZHOU DIANZI UNIV

Industrial image anomaly detection method based on deep learning

The invention discloses an industrial image anomaly detection method based on deep learning, and particularly relates to the technical field of industrial visual detection. The problems of high false alarm rate, fuzzy fine defect positioning, insufficient real-time response capability, difficulty in model increment updating and the like caused by data distribution drift in an industrial scene are solved. According to the method, robust features are extracted through a multi-scale feature fusion auto-encoder, and a dynamic memory bank is constructed to update a normal sample prototype online; a dual-path detection mechanism is adopted to cooperate with a pixel-level reconstruction error and attention weighted feature matching deviation; efficient edge reasoning is realized in combination with block parallel processing and model compiling optimization; and designing an elastic incremental learning framework to prevent disastrous forgetting. And finally, false alarms caused by environmental changes are reduced, accurate positioning of pixel-level defects is realized, millisecond-level detection requirements of high-resolution images are met, safe and efficient model online evolution is supported, and adaptability and reliability of an industrial quality inspection system are comprehensively improved.
Owner:SHANXI UNIV

Computer memory bank fault prediction method and system based on deep learning

The invention discloses a computer memory bank fault prediction method and system based on deep learning, and relates to the technical field of computer hardware fault diagnosis, and the system comprises a multi-source time sequence data collection module which is used for obtaining memory bank operation state data in real time; the dynamic feature enhancement module is based on a composite architecture of a generative adversarial network and transfer learning, comprises a fault mode generator, and generates synthetic data consistent with real fault distribution by using an LSTM network; aligning feature spaces of different hardware platforms through a maximum mean difference loss function; the multi-modal fusion deep learning model comprises a space-time convolutional network, a graph attention network and an adaptive weight adjustment mechanism; and the fault early warning analysis module is used for analyzing a fault probability predicted value, an interpretable thermodynamic diagram and a maintenance suggestion. According to the invention, passive maintenance is changed into active prevention and control, and preposition and precision of fault management are realized through dual mechanisms of long-term trend prediction and short-term risk early warning.
Owner:BENGBU JINSE INFORMATION TECHNOLOGY CO LTD

Intelligent cooling system and method of centerless grinding machine for difficult-to-machine materials

The invention relates to the technical field of industrial control, in particular to an intelligent centerless grinding machine cooling system and method for difficult-to-machine materials, and the system comprises a multi-source sensing unit, an edge calculation module, a decision center module, a precise execution module and a digital immune memory bank; compared with the defects that in the prior art, monitoring depends on a single temperature sensor, thermal field sensing is incomplete, thermal damage early warning lags behind and the like, according to the scheme, grinding power frequency spectrum, acoustic emission signals, triaxial vibration and coolant mass spectrum data are collected in real time through a multi-source sensing unit, and a micron-sized temperature field is reconstructed in combination with an edge end space-time diagram convolutional network; full-dimensional monitoring of the grinding thermal-mechanical coupling effect is achieved, and thermal anomaly recognition sensitivity and early warning timeliness are remarkably improved.
Owner:WUXI JIANHE NUMERICAL CONTROL MACHINE TOOL

Quality management and control system for fabricated decoration construction

The invention discloses a quality management and control system for fabricated decoration construction, and the system comprises a sensing layer which constructs a multi-modal data collection network, carries out the three-dimensional real-time data synchronous collection through combining logistics API docking and an OCR recognition system, and constructs a construction process digital twin bottom plate; in the edge calculation layer, an edge node carries out lightweight processing on the original data; the cognitive layer is used for calling a Prolog rule through a process knowledge graph engine to reasone the feature snapshots, carrying out defect instant diagnosis and dynamic constraint propagation, outputting a root cause path with probability weight through three-stage verification, and quantifying intervention influence; the decision-making layer is used for constructing a dynamic prediction model based on a bidirectional LSTM and an attention mechanism, automatically activating a compensation mode when key interference is detected in combination with an anti-fact memory bank and a case-based reasoning compensator, and generating an alternative scheme of optimal cost / optimal construction period / comprehensive balance through a multi-target optimizer; and in the application layer, a Unity engine is utilized to develop the digital twinborn billboard.
Owner:TAIZHOU UNIV

Personalized memory auxiliary interaction method based on mental cognition mechanism

The invention discloses a personalized memory auxiliary interaction method based on a mental cognition mechanism, and particularly relates to the field of agent interaction. Comprising the following steps: determining a desire type and a personal role abstract of an input text, and taking the desire type and the personal role abstract as semantic memory; taking the current input text as scene memory, summarizing all the input texts in the dialogue date at the end of the current dialogue date to obtain a daily event abstract, and taking the daily event abstract as abstract memory; performing similarity retrieval in a memory bank according to the current input text to obtain related historical semantic memory, historical scene memory and historical abstract memory, and taking the retrieval result as working memory; and generating a response text according to the working memory, and performing interaction. The role and personality characteristics of the user can be deeply understood and memorized, personalized response can be generated, and historical dialogues can be effectively associated.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Memory access instruction processing method and processor

The invention provides a memory access instruction processing method and a processor, and relates to the technical field of data processing, and the method comprises the following steps: splitting a target vector memory access instruction into a plurality of target vector memory access micro-operations based on a memory access width, combining the target scalar memory access instruction with at least one unexecuted scalar memory access instruction into a target scalar memory access micro-operation; executing each target vector memory access micro-operation, and / or executing a target scalar memory access micro-operation; the memory access width is determined based on a number of data cache banks in a data cache in the processor and a bit width of the data cache banks. According to the memory access instruction processing method and the processor provided by the invention, resources can be more reasonably allocated for vector memory access and scalar memory access during data memory access through splitting of the vector memory access instruction and merging of the scalar memory access instruction, and maximum resource sharing of the vector memory access and the scalar memory access is realized.
Owner:BEIJING VCORE TECH CO LTD

Defect classification and segmentation method and system based on unsupervised and weak supervised combination

The invention discloses a defect classification and segmentation method and system based on unsupervised and weak supervised combination, and the method comprises the steps: employing a training data set only containing a defect-free sample, extracting the feature representation of the defect-free sample through a feature extractor, and storing the feature representation in a feature memory library; comparing the mixed data set without labels including defect and defect-free samples with the features in the feature memory bank to determine false classification labels; designing a class activation graph-based weak supervision network for extracting features in the image, a semantic segmentation network and a loss function thereof, and training the semantic segmentation network by using a training data set of a defect-free sample and pseudo-classification label data; according to the method, the advantages of weak supervision and unsupervised learning algorithms are combined, and efficient defect detection and positioning can be realized.
Owner:HARBIN INSTITUTE OF TECHNOLOGY (SHENZHEN) (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)

Memory mechanism-based information processing method, electronic device and storage medium

Provided in the present disclosure are a memory mechanism-based information processing method, an electronic device and a storage medium. The method comprises: acquiring information to be processed corresponding to a target user; searching in memory banks corresponding to the target user for knowledge related to said information, so as to use the searched knowledge to obtain a processing result corresponding to said information, the memory banks comprising a long-term memory bank and a short-term memory bank; if the used knowledge is knowledge in the short-term memory bank, recording a use behavior for the knowledge, the short-term memory bank being used for temporarily storing knowledge related to the target user, and when a use behavior corresponding to any knowledge in the short-term memory bank meets a preset condition, storing the knowledge meeting the preset condition into the long-term memory bank. The present disclosure can achieve hierarchical storage of memory, and simulate the memory mechanism of the real world to process information to be processed of users, thus improving the effect of interacting with the users, and improving the user experience.
Owner:ALIBABA (CHINA) CO LTD

Distributing staged sampled signals and conveying over electromagnetic pathways

In a transmitter there is a distributor and assembly bank into which a predetermined quantity of an input payload from a source is repeatedly written according to a first distributor permutation to create as many input vectors as there are electromagnetic propagation pathways. A staging bank exists into which each input vector available from the assembly bank are repeatedly written according to a second distributor permutation. A presentation bank exists into which each input vector available from the staging bank are repeatedly written according to a third distributor permutation. One or more encoders repeatedly encode input vectors from the presentation bank; there being as many encoders as electromagnetic propagation pathways, and each encoder makes available each encoded ordered series of output levels for communication over the pathways. The banks and encoders are in up to four timing domains. A corresponding receiver, decoder, and reception, staging and disassembly banks and a sink are at the end of the pathways.
Owner:HYPHY USA INC

Long-term video understanding system based on adaptive sparse memory and language model

The invention provides a long-term video understanding system based on adaptive sparse memory and a language model. The long-term video understanding system comprises a visual encoder used for extracting visual features from a long video; the memory bank module is used for storing and retrieving visual features of historical video contents; and the sparse adaptive module is used for dynamically managing the memory bank module, and the memory bank module interacts with the multi-modal large language model by querying a converter Q-Former and is used for incrementally processing video data and mapping visual features to a language space. By introducing an adaptive sparse memory mechanism, a long-term video sequence can be effectively processed, redundant features can be dynamically compressed, and key information can be reserved, so that efficient analysis of a long video is realized; compared with the prior art, the method has high accuracy in multiple tasks, and can dynamically manage the memory bank and reduce processing of redundant features through a sparse adaptive mechanism, so that the calculation overhead is reduced, and the overall efficiency of the system is improved.
Owner:JINAN UNIVERSITY

Open vocabulary task guiding grabbing method and device, medium and program product

The invention provides an open vocabulary task guiding grabbing method and device, a medium and a program product. The open vocabulary task guiding grabbing method comprises the steps that a user language instruction and a complex scene image are input into a preset visual language model; identifying a target task corresponding to the user language instruction through a preset visual language model, matching a target object associated with the target task in the complex scene image, and determining an optimal grabbing component of the target object based on a plurality of functional components of the target object; constructing a plurality of capture candidate schemes by adopting the optimal capture component and the complex scene image; and performing optimization solution on each grabbing candidate scheme to determine the optimal grabbing pose, so as to solve the problem that the existing method is poor in effect when dealing with an unseen object and a new task in a scene with open vocabularies due to the limited scale of an operability memory bank in the related technology. The invention aims at solving the problem that the existing method is poor in effect when dealing with the unseen object and the new task in the scene with the open vocabularies.
Owner:BEIJING ACAD OF ARTIFICIAL INTELLLIGENCE

Apparatuses and methods for access based targeted refresh operations

Apparatuses, systems, and methods for access based targeted refresh operations. A memory bank has a first sub-bank and a second sub-bank. A refresh control circuit detects an aggressor in one of the sub-banks. Responsive to an access in the other sub-bank, the refresh control circuit performs a targeted refresh operation based on the sub-bank based on the aggressor address.
Owner:MICRON TECHNOLOGY INC

Task planning method and system for robot

The invention relates to the technical field of robots, and discloses a task planning method and system for a robot, and the method comprises the steps: obtaining a user instruction; based on the large language model and the semantic coding model, retrieving in a memory bank to obtain environment perception information related to the user instruction; inputting a first cue word determined based on the user instruction and the environment perception information into the large language model, and generating an overall action sequence corresponding to the user instruction; and for each sub-action in the whole action sequence, determining a second cue word, inputting the second cue word into the large language model, and generating a detailed action plan corresponding to the current sub-action until each sub-action in the whole action sequence is traversed. According to the method, the natural language or unstructured instruction can be received, the intention of the user can be understood, and the executable overall action sequence and the detailed action plan of each sub-action in the sequence are generated, so that the task issued by the user is completed, it is ensured that the robot can execute the task, and the accuracy and efficiency of task execution are improved.
Owner:CHENGDU HUMANOID ROBOT INNOVATION CENT CO LTD

Voltage regulators with shared decoupling capacitor for memory devices

A circuit includes a memory macro comprising a plurality of memory banks. The circuit includes a first voltage regulator configured to provide a first operation voltage to the memory macro at a first output node. The circuit includes a second voltage regulator configured to provide a second operation voltage to the memory macro at a second output node. The second operation voltage is substantially higher than the first operation voltage. The circuit includes a decoupling capacitor configured to be alternately shared by the first voltage regulator when the memory macro receives the first operation voltage, and by the second voltage regulator when the memory macro receives the second operation voltage.
Owner:TAIWAN SEMICONDUCTOR MANUFACTURING CO LTD

Near proximity search-based few-sample visual defect detection method

The invention discloses a few-sample visual defect detection method based on approximate proximity search, and belongs to the technical field of industrial intellectualization. The system mainly comprises an image acquisition module, a feature extraction module, a memory bank construction module, a feature compression module, an approximate nearest neighbor search module and an anomaly detection and result output module. The feature extraction module is used for performing feature extraction on the collected image; the feature compression module is used for reducing the feature data volume and reducing the internal memory and calculation burden; the memory bank construction module is mainly operated during system initialization or model training and is used for constructing a feature memory bank of normal samples; the approximate nearest neighbor search module is responsible for quickly finding normal sample features closest to the input features in the memory bank; and the anomaly detection and result output module is used for converting distance information obtained by neighbor search into anomaly. According to the few-sample visual defect detection method based on the approximate proximity search, the effect of few-sample anomaly detection is achieved.
Owner:上海仰羿自动化工程有限公司 +1

Distribution network line facility defect detection method based on line magnetic field variable characteristics

The invention discloses a distribution network line facility defect detection method based on line magnetic field variable characteristics, and relates to the technical field of magnetic variable measurement. According to the method, high-precision spatio-temporal data are obtained through multi-point synchronous non-contact magnetic field sensing, codes are efficiently preprocessed through self-adaptive voxel division and bytes, and the detection accuracy of the distribution network line facility defects is improved; and the line topology information is deeply fused to Token for representation. A pre-trained large language model is combined with low-rank adaptation (LoRA), sliding window attention and an external memory bank for efficient reasoning, and understanding of long sequences and topological association is enhanced. Characterization quality is improved through mixed mask self-supervised learning, and multi-task (classification, positioning and scoring) output is optimized by adopting uncertainty weighted loss. And privacy protection federal training is supported. And finally, an interpretable diagnosis report is generated, and an alarm and work order process is automatically performed. The accuracy, efficiency, intelligent level and automation degree of distribution network fault detection are remarkably improved, and safe and reliable operation of a power grid is guaranteed.
Owner:KUNMING NENGREI TECH CO LTD

Cyclic feedback scheduling cooperation method based on agent and cloud computing power service

The invention provides a cyclic feedback scheduling collaboration method based on an intelligent agent and cloud computing power service. The method comprises the following steps: memory recall: the intelligent agent receives a task demand, accesses a memory library to obtain historical experience entries, performs memory matching and memory fusion, generates memory recall information, and outputs the memory recall information to the cloud computing power service; cloud task planning: a cloud big language model understands task demand intentions based on memory recall information, decomposes tasks and generates executable descriptions, and an agent generates a preliminary task plan and calls a proper tool; performing action observation: performing operation by the intelligent agent, acquiring feedback data in real time, comparing an actual result with an expected target adjustment strategy, selecting a more suitable tool, and performing repeated execution until a task is completed; summarizing and reflecting: generating task execution tracks, integrating into experience entries, and storing into a memory bank. According to the method, historical memory, dynamic feedback and cloud computing power are combined, and the autonomous decision-making ability, execution efficiency and accuracy of the intelligent agent in a complex task are remarkably improved.
Owner:BEIJING AEROSPACE WANYUAN TECH CO LTD +1

Time-varying graph neural network traffic flow prediction method based on dynamic memory bank

The invention provides a time-varying graph neural network traffic flow prediction method based on a dynamic memory bank, and belongs to the technical field of traffic prediction. The method adopts a layered deep neural network architecture, and comprises a data embedding layer, a space-time coding layer, a memory enhancement layer and a prediction output layer. The data embedding layer preprocesses a traffic flow sequence, associates a collaborative coding time sequence mode with a road network, and synchronously constructs a dynamic graph structure; the space-time coding layer is subjected to space-time stream decoupling extraction, a space branch models multi-scale space dependence through a time delay graph convolution module and a space Mama module, and a time branch extracts multi-granularity time features through a hierarchical time sequence sensing module and a time Mama module; the memory enhancement layer performs pattern matching and reconstruction on the space-time fusion features by means of a dynamic memory bank; and the prediction output layer generates a prediction result by taking the GCRN as a decoder. According to the method, the space-time dependence of the traffic situation is accurately captured, the prediction curve is highly fit with the true value, and the high-precision prediction of the traffic flow is realized.
Owner:CHINA UNIV OF PETROLEUM (EAST CHINA)

Multi-agent cooperative energy production demand generation method and system

The invention provides a multi-agent cooperative energy production demand generation method and system, and relates to the field of intelligent energy, and the method comprises the steps: collecting multi-modal data of a to-be-generated energy field, and carrying out the preprocessing; performing data analysis and information purification by utilizing a multi-modal information processing agent driven by a large model, taking an input energy production demand target as a cue word Prompt of the agent and taking the preprocessed multi-modal data as a memory bank of the agent, and generating energy production demand scheme items in a discrete token sequence form; automatically generating an energy production demand reference document based on the energy production demand scheme items through a large model-driven iterative dialogue between a session manager and an energy expert agent; according to the method, a generative multi-agent technology is introduced, the designed agents autonomously take actions according to information purification and answers of other agents, and energy production requirements are quickly and efficiently generated through own observation, reasoning and memory capabilities.
Owner:DAREWAY SOFTWARE

Apparatuses and methods for dynamically allocated aggressor detection

Apparatuses, systems, and methods for dynamically allocated aggressor detection. A memory may include an aggressor address storage structure which tracks access patterns to row addresses and their associated bank addresses. These may be used to determine if a row and bank address received as part of an access operation are an aggressor row and bank address. The aggressor row address may be used to generate a refresh address for a bank identified by the aggressor bank address. Since the aggressor storage structure tracks both row and bank addresses, its storage space may be dynamically allocated between banks based on access patterns to those banks.
Owner:MICRON TECHNOLOGY INC

Wind power plant cluster power prediction method

The invention discloses a wind power plant cluster power prediction method. The method comprises the following steps: step 1, embedding priori knowledge into a learning module; step 2, constructing a memory enhanced adaptive graph structure; step 3, an endogenous feature learning module; step 4, an exogenous feature learning module; 5, performing memory enhancement gating fusion on the MAGF; and step 6, outputting and predicting. According to the method, special learning modules are respectively constructed by decoupling endogenous power signals and exogenous meteorological factors, and a dynamic graph structure adaptive to a sample is retrieved by utilizing a meta-memory library, so that context sensing modeling of a complex space-time dependency relationship is realized. Meanwhile, a memory enhanced gating fusion mechanism (MAGF) is introduced, adaptive semantic alignment and fusion of double-flow features are realized, the precision and robustness of the model in multiple prediction time domains are remarkably improved, and more reliable technical support is provided for power grid dispatching and wind field operation.
Owner:CHANGAN UNIV