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

1172 results about "Data dependence" patented technology

Health state assessment method for equipment based on knowledge graph attention network

Disclosed in the present invention is a health state assessment method for equipment based on a knowledge graph attention network, includes: steps: 1) constructing a graph data model which can comprehensively reflect change of a health state of the equipment by deeply integrating association relationships of equipment components, monitoring data dependence relationships and priori information, etc. by means of a knowledge graph and by combining with domain priori knowledge; 2) extracting feature information of the health state knowledge graph by using a graph attention network, and obtaining a target node vector representation which accurately reflects the health state of the equipment by means of learning; and 3) making a health state representation vector of the equipment pass through a fully connected layer to obtain a health state classification prediction probability, and performing training to reducing a loss value relative to a true label, thereby obtaining a health state assessment result.
Owner:ZHEJIANG UNIV OF TECH

Virtual power plant control method, system and equipment based on neural network

The invention relates to the field of power plant control, discloses a virtual power plant control method, system and equipment based on a neural network, and is used for solving the core problems of high data dependence, low topology safety and difficulty in multi-scale collaboration in traditional virtual power plant control. According to the virtual power plant control method based on the neural network, a correction instruction set, a joint estimation value and a topology constraint matrix are input into a neural network controller, and a cooperative control signal is output through singular perturbation decoupling of a fast-varying subsystem and a slow-varying subsystem. And the cooperative control signal is issued to the distributed power supply inverter, the energy storage converter and the intelligent switch, and meanwhile, an execution result is monitored in real time and fed back to the phase space reconstruction module, so that closed-loop control is formed. By constructing the Lyapunov candidate function and calculating the virtual damping coefficient, the transient stability, real-time persistent homologous analysis and topology self-healing instruction generation of the system are enhanced, and the self-healing capability and the fault-resistant capability of the system are improved.
Owner:SHENZHEN ENERGY BRIGHT POWER CO LTD

Link reliability tracking and optimizing method combined with real-time monitoring

The invention discloses a link reliability tracking and optimizing method combined with real-time monitoring, and relates to the technical field of data transmission. Comprising the following steps: constructing a topological graph of a full link based on component information and a data flow relationship of a data medium station, and deploying a data acquisition probe to acquire link data in real time; a potential fault or an abnormal link is automatically identified; based on the data map, sorting the data dependency relationship of the upstream and downstream of the link, recording the relevance and dependency path of each component, and forming an accurate link blood relationship map; link abnormal conditions are captured and backtracked, log information is summarized in a unified mode, and centralized analysis and problem positioning are carried out; and on the basis of operation historical data of the link, according to the time sequence prediction model, identifying a bottleneck and a high-risk area in the link, dynamically adjusting a transmission strategy of the link, and optimizing load balance and a link priority of a station in the data in real time. According to the invention, the influence on the service when the fault occurs is reduced, and the abnormal problem positioning efficiency is improved.
Owner:STATE GRID ANHUI ELECTRIC POWER CO LTD +1

Large and small model collaborative target detection and recognition method based on thinking chain

The invention belongs to the technical field of target detection and recognition, and particularly relates to a thinking chain-based large and small model collaborative target detection and recognition method. According to the method, the small model is responsible for most of easy-to-detect targets, the calculation pressure of the large model is reduced, the large model is responsible for suspected samples, vision and language multi-mode reasoning is combined, the overall false detection rate and the omission ratio are both reduced, confidence evaluation is conducted through the joint probability, automatic screening and manual rechecking of uncertain results are achieved, the reliability of key results is guaranteed, and the method is suitable for large-scale popularization and application. According to the'pseudo thinking chain + pseudo label 'method, by means of reasoning and labels generated by the model, data dependence on manual labeling is reduced, only low-confidence samples are manually confirmed, the human intervention range is narrowed, the human cost is remarkably saved, and semantic information with finer granularity is provided for the model by introducing phrase-level feature descriptors. And the identification capability of complex target attributes and states is improved.
Owner:NANJING NANZI INFORMATION TECH

Bearing fault diagnosis method based on fusion of improved capsule network and zero sample learning

The invention discloses a bearing fault diagnosis method based on fusion of an improved capsule network and zero sample learning, and relates to the technical field of state monitoring and fault diagnosis of electromechanical equipment, and the method comprises the following steps: collecting a multi-mode signal during the operation of a bearing, employing an improved wavelet threshold denoising algorithm for the multi-mode signal to eliminate environmental noise, and then employing a zero sample learning algorithm for the multi-mode signal; according to the method, the improved wavelet threshold de-noising algorithm and the WPD and VMD fusion decomposition algorithm are adopted to extract the time-frequency domain mixed features as sample data, and the GAN is combined to expand the bearing sample data, so that the data dependence of traditional deep learning is broken through, the time-frequency domain mixed features are extracted through the improved wavelet threshold de-noising algorithm and the WPD and VMD fusion decomposition algorithm, and the time-frequency domain mixed features are extracted through the improved wavelet threshold de-noising algorithm and the WPD and VMD fusion decomposition algorithm. Small sample data learning is realized, and by training a pyramid capsule network and optimizing a cross entropy loss function and combining cross-modal joint optimization and a zero sample inference engine, the diagnosis accuracy of known faults is greatly improved, and unknown fault types can be effectively inferred.
Owner:SUZHOU FURUITE DIGITAL INTELLIGENT TECHNOLOGY CO LTD

Unmanned aerial vehicle image small target detection method based on dynamic filtering and adaptive sparse Transform

The invention discloses an unmanned aerial vehicle image small target detection method based on dynamic filtering and an adaptive sparse Transform. According to the method, an end-to-end target detection framework is adopted, a dynamic filtering module is introduced into a backbone network, global feature interaction is achieved through data-dependent frequency domain operation, and linear calculation complexity is maintained. For feature interaction in a scale, an adaptive sparse Transform module is introduced to enhance the capability of focusing key information on high semantic hierarchy features of a model, and noise interference and feature redundancy are effectively suppressed at the same time. Through the combination of dynamic filtering and adaptive sparse Transform, the model can extract image foreground information more effectively on the premise of not significantly increasing the calculation burden, and the problem that a traditional target detection model is susceptible to complex background interference is significantly relieved.
Owner:GUILIN UNIV OF ELECTRONIC TECH

GPU heterogeneous computing resource allocation method and system based on task scheduling

The invention provides a GPU heterogeneous computing resource allocation method and system based on task scheduling, and the method comprises the steps: carrying out the feature analysis of a to-be-scheduled task, so as to extract the calculation intensity, video memory demands, inter-task data dependence and historical execution data of the to-be-scheduled task, and obtaining a task feature vector; constructing a performance model of heterogeneous GPU resources to predict execution efficiency and resource consumption of the GPU under the target task based on hardware performance parameters and running states of the GPU; and matching the to-be-scheduled task with the GPU resources according to the task feature vector and the performance model of the heterogeneous GPU resources. Through task feature analysis and GPU resource performance modeling, the adaptive relation between tasks and GPU resources can be deeply mined, to-be-scheduled tasks are accurately allocated to the most appropriate GPU, the resource utilization rate is greatly increased, the task execution sequence and resource allocation are dynamically planned, and the task execution time is effectively shortened.
Owner:HEFEI SUMICROELECTRONICS TECH CO LTD

Operator parallel processing method, electronic equipment, storage medium and program product

The invention relates to the technical field of artificial intelligence, and provides an operator parallel processing method, electronic equipment, a storage medium and a program product, and the method comprises the steps: determining a step of data dependence based on each processing step of a first operator and a second operator; and performing parallel execution on each processing step of the first operator and the second operator by applying a synchronization strategy and a segmentation strategy based on the plurality of cooperative thread bundles. According to the method, the parallel fusion processing of operators is realized through the steps of determining data dependence, segmenting the data, realizing parallel execution by utilizing the cooperative thread bundle, inserting synchronization between the data dependence steps and the like, the calculation performance is remarkably improved, and meanwhile, the data blocks after segmentation are multiplexed, so that the data processing efficiency is improved. The data dependence in the operators and between the operators can be reduced, and the overhead of data reading, instruction synchronization and the like can be reduced.
Owner:SHANGHAI BIREN TECH CO LTD

Resource scheduling control method and system for big data server

The invention provides a resource scheduling control method and system for a big data server, and the method comprises the steps: constructing a multi-dimensional resource portrait module, collecting the CPU, memory, network, storage I / O load and task queue length of each node in real time, and predicting a resource demand trend through a time sequence algorithm; extracting characteristics such as calculation intensity, data dependence, memory requirements, network transmission quantity and the like; adjusting the weight coefficients of the resource utilization rate, the task completion time and the energy consumption efficiency according to the system load and the historical effect; establishing a bipartite graph model by taking a resource trend as a node feature and a task vector as an edge feature, and calculating a matching score through graph convolution and a multi-objective optimization function; the scheduling scheme is synchronized by adopting a consistency algorithm; automatic rollback and reallocation are carried out when resources are detected to be insufficient; and optimizing a weight coefficient and a network parameter through reinforcement learning. Through the method, the system resource utilization rate can be improved, the task execution efficiency is improved, the overall scheduling effect stability is improved, and the system fault recovery time is shortened.
Owner:SHANGHAI HONGXING INFORMATION TECH CO LTD

Multi-platform fusion interaction method and system based on large touch screen

The invention provides a multi-platform fusion interaction method and system based on a large touch screen, and relates to the technical field of man-machine interaction, and the method comprises the steps: dividing a main control area and a cooperative display area, building a mapping relation between touch operation and a multi-platform interaction scene, recognizing a gesture intention through a neural network, and generating touch event data. After touch event data are received, a platform control instruction is generated according to the data dependency graph and the interaction rule base, a master control platform instruction is processed preferentially, and an execution result is synchronized to the cooperation platform or vice versa. And finally, establishing an inter-platform real-time data synchronization mechanism, transmitting data through a bidirectional data channel, dynamically adjusting a transmission strategy, and ensuring data consistency of each platform, thereby realizing efficient multi-platform fusion interaction, improving user experience and reducing system delay.
Owner:BEIJING ZHONGHE HUANGPU EDUCATION TECHNOLOGY CO LTD

Instruction execution method and device for artificial intelligence chip

The invention discloses an instruction execution method and device for an artificial intelligence chip, and relates to the technical field of artificial intelligence chips, and the method comprises the steps: carrying out the deep learning driven feature recognition and resource demand prediction of an input task, and generating a demand prediction report of the task for computing resources through the analysis of a computational graph and a data dependency relationship of the task; a computing unit and memory resources are intelligently scheduled, an optimal instruction execution path is dynamically selected, and meanwhile a caching strategy is optimized; automatically generating a micro instruction set corresponding to the task according to the computing resource demand, the computing characteristic and the intelligent scheduling result of the task; when multiple tasks are executed in parallel, the execution sequence of the multiple tasks is dynamically adjusted according to the calculation load and the resource sharing condition of the tasks, and resource allocation is optimized. According to the method, the computing resources and the memory bandwidth required by each task can be accurately predicted through the deep learning driving analysis of the task computing graph, so that the allocation of the computing resources is optimized.
Owner:BEIJING LEKAIWENYU TECHNOLOGY CO LTD

Graph neural network pre-training method and system based on community structure generality

The invention relates to the technical field of artificial intelligence graph neural networks (GNN), in particular to a graph neural network pre-training method and system based on community structure generality. The pre-training method comprises the following steps: preprocessing an input graph to form a graph G (V, A) comprising a node set V and an edge set A; community structure detection is carried out on the graph G (V, A) to identify the community structure of the graph G (V, A), and a community is highly identified by adopting a modularity-based Louvain method or a label propagation LPA method; the invention provides a graph neural network pre-training method based on community structure generality. The problems that in the prior art, large-scale graph data processing efficiency is low, and dependence on labeled data is high can be effectively solved. Through preprocessing and community structure detection on an input graph, a modularity optimized Louvain method or a label propagation LPA method is adopted, and communities can be efficiently identified and divided, so that local and global structure information of the graph is reserved.
Owner:ANHUI UNIV

Industrial data online migration method, medium and system of productivity middle platform

The invention provides an industrial data online migration method, medium and system of a productivity middle platform, and belongs to the technical field of electrical digital data processing.The method comprises the steps that firstly, historical access records of an industrial data source are collected, and a deep neural network model comprising a multi-head attention layer, a time sequence feature extraction layer and a residual connection layer is constructed; and the prediction of the data change rate is realized. And based on a prediction result, dynamically calculating a data change rate demarcation point by utilizing an optimization equation set, and dividing a data table into different change frequency categories. And then constructing a data dependency relationship matrix, and determining a migration sequence by adopting an improved topological sorting algorithm. Batch migration, incremental migration and real-time synchronization mechanisms are adopted for different types of data, and model updating is triggered through real-time monitoring, so that dynamic optimization of a migration strategy is ensured. Finally, data consistency verification is carried out, migration accuracy is guaranteed, and the technical problem that the online migration efficiency of industrial data is low due to real-time dynamic change of the data change rate is solved.
Owner:BEIJING NANCAL RUIYUAN DIGITAL TECH CO LTD

Compliance verification method and device for medical process data

The invention discloses a compliance verification method and device for medical process data, and relates to the field of medical data, and the method comprises the steps: constructing a medical process knowledge graph, and defining the data dependence relation of clinical test, production and declaration stages; dynamically activating the rule subsets based on the current process stage, and calculating and loading association rules through dependency to form a composite rule set; converting the structured data, the medical image and the handwritten text into a unified vector space, calculating a cross-modal semantic consistency score, and resolving conflicts according to a preset priority or a cross-modal attention fusion mechanism; and when the flow stage is switched or the historical data is modified, full-link backtracking verification is triggered. The device comprises a process modeling module, a rule dynamic generation module, a multi-modal alignment module and a visual proof module. According to the invention, the compliance verification efficiency is greatly improved through the dynamic rule engine, and the supervision risk and operation cost caused by data defects of pharmaceutical enterprises are effectively reduced.
Owner:SHANGHAI PHARMA PHARMA TECH CONSULTING

Training / application method for representation learning model, and device and medium

Provided in the present application are a training / application method for a representation learning model, and a device and a medium. The training method comprises: extracting a plurality of source codes from an open-source repository, and on the basis of the plurality of source codes and a large language model, generating a training sample set, wherein each sample in the training sample set comprises assembly codes and natural language text; on the basis of an assembly code data set, performing pre-training to generate an assembly coder, and on the basis of a natural language data set, performing pre-training to generate a text coder; on the basis of the training sample set and a contrastive learning algorithm, performing alignment training on the assembly coder and the text coder, so as to obtain a code representation learning model and a natural language representation learning model which are semantically aligned; and on the basis of the code representation learning model and the natural language representation learning model, which are semantically aligned, constructing a representation learning model. The method of the present application significantly improves the generalization ability and accuracy of a representation learning model, and greatly reduces dependence of the model on samples and a large volume of tagged data.
Owner:TSINGHUA UNIVERSITY

Intelligent generation method and system for household pelvic floor muscle rehabilitation training scheme

The invention relates to the technical field of use of medical instruments, and discloses a household pelvic floor muscle rehabilitation training scheme intelligent generation method and system.In the rehabilitation training process, selection operation of a pelvic floor muscle dynamic model and a local scheme generation model is introduced, on one hand, the pelvic floor muscle dynamic model is used for elastic reaction simulation, and on the other hand, the pelvic floor muscle dynamic model is used for local scheme generation; on the other hand, a local scheme generation model matched with the real situation of the target training stage is selected, so that the real situation of the target training stage can be evaluated through the matched local scheme generation model; according to the accurate and credible local stage evaluation data and stage test data of the target training stage, a more matched targeted training scheme is obtained, accurate and high-quality data dependence is provided for adjusting a global rehabilitation training scheme, and the intelligent level of training scheme generation can be improved; therefore, the household rehabilitation training effect of pelvic floor muscles is effectively improved.
Owner:WOMEN S HOSPITAL ZHEJIANG UNIVERSITY SCHOOL OF MEDICINE

Method for scheduling workloads of data center in electricity market environment, and device

Provided in embodiments of the present disclosure are a method for scheduling workloads of a data center in an electricity market environment, and a device. In the embodiments of the present disclosure, a multi-stage random optimization solution that allows a data center to participate in a multi-level electricity market is provided. The types and data dependency relationship of workloads are taken into consideration, and a load scheduling model, in a time dimension, for the workloads is constructed; on the basis of electricity source information of the data center, a multi-stage electricity cost optimization model is constructed, so as to comprehensively consider the exogenic uncertainty of an electricity price and carbon emissions and the endogenic uncertainty of the workloads; on the basis of the multi-stage electricity cost optimization model, multi-stage optimization solving is performed on the load scheduling model, so as to obtain a load scheduling scheme and an electricity purchase strategy. Therefore, a more accurate and more reliable estimation is made concerning the electricity flexibility of the data center, such that the electricity cost of the data center can be reduced, support is provided for the reduction of carbon emissions, and the consumption of renewable energy sources is encouraged, thereby achieving the energy use flexibility of the data center in the multi-level electricity market environment.
Owner:ALIBABA CLOUD COMPUTING CO LTD

Data cable adaptive production method and system based on image analysis

The invention discloses a data cable self-adaptive production method and system based on image analysis, and the method specifically comprises the steps: synchronously collecting three-mode image data containing visible light, infrared light and polarization at a gas injection section, an extrusion section and a molding section of a data cable through a multispectral imaging unit; performing spatial alignment on the three-mode image data by adopting a sub-pixel registration algorithm to obtain standard image data; based on the standard image data, combined diagnosis is carried out on the cable gas injection structure, the insulation layer quality and the surface defect through a multi-task analysis engine, and a defect diagnosis result is obtained; and based on a defect diagnosis result, dynamically adjusting the traction speed, the extrusion temperature and the gas injection pressure by utilizing a fuzzy PID controller optimized by reinforcement learning to form online process parameter closed-loop control. The defects of single function, static detection, high data dependence and the like of a traditional data cable production detection method are effectively overcome, and a more efficient and intelligent solution is provided for data cable production.
Owner:DONGGUAN QINGFENG ELECTRIC MACHINERY

Highway-oriented full-process digital collaborative management system and method

The invention discloses a road-oriented full-process digital collaborative management system and method, particularly relates to the technical field of road data management, and is used for solving the problem of abnormal multi-role collaborative conflict recognition. According to the method, dynamic linkage management of task states and role behaviors in the whole highway design process is achieved by building the task-driven atlas and the multi-role scheduling model, and the dynamic linkage management of the task states and the role behaviors in the whole highway design process is achieved by extracting access behaviors, task records and data version states, calculating role collaborative offset and recognizing and controlling the write-in permission of task conflict nodes. A priority factor is constructed based on a stage index, data dependence and a time urgency degree, a nonlinear model is adopted to generate scores, automatic reconstruction of a scheduling sequence and data ownership is driven, role permission and a collaborative view are synchronously updated, a data access control closed loop based on task state evolution is formed, and a three-dimensional responsibility chain is constructed by whole-process behavior traces. The traceable management of collaborative operation is realized, and the intelligence of collaborative scheduling and the accuracy of data management are improved.
Owner:JIANGXI HIGHWAY RES & DESIGN INST CO LTD

Fixed function shared accelerator

Systems and methods for generating fixed function shared accelerators (FFSAs) implement and / or comprise operations of receiving source code, the source code indicating a plurality of workloads to be performed by an electronic circuit; generating a plurality of abstract syntax trees (ASTs) based on the source code, wherein respective ones of the plurality of ASTs include a plurality of nodes corresponding to function instructions; generating a plurality of fingerprinting vectors corresponding to the plurality of ASTs, wherein respective ones of the plurality of fingerprinting vectors encode at least one of a number of nodes, a number of edges, a density, a computation intensity, an operands percentage, a control, or a data dependency; and providing the plurality of fingerprinting vectors to a machine learning (ML) model, wherein the ML model is configured to predict similarities between different ones of the plurality of workloads and to output at least one candidate FFSA.
Owner:TRUSTEES OF TUFTS COLLEGE

Lithium battery thermal runaway control and safety response strategy system

The invention discloses a lithium battery thermal runaway control and safety response strategy system, which realizes the real-time monitoring and prediction of the internal temperature and voltage state of a battery through thermal-electric coupling modeling and multi-sensing data fusion, and realizes the real-time monitoring and prediction of the internal temperature and voltage state of the battery based on a model prediction control and threshold enhancement strategy. And triggering graded safety response in the early stage of thermal runaway. The system adopts a multi-stage response mechanism including measures of primary early warning, active cooling intervention, emergency power-off fire extinguishing and the like, a gas suppression path and cooling mode switching function is designed, and heat diffusion and spreading and toxic gas harm are effectively suppressed. Compared with a method depending on complex digital twinning or deep learning, the method is simple in structure, rapid in response and low in data dependence, has good system stability and engineering applicability, and can be widely applied to the field of lithium battery safety management of electric vehicle battery packs, energy storage power stations and the like.
Owner:ANHUI ZHONGJI INVESTMENT NEW ENERGY CO LTD

Unsupervised wind power equipment blade fault detection method based on phase perception parallel attention mechanism

The invention relates to a wind power equipment blade fault detection technology, discloses an unsupervised wind power equipment blade fault detection method based on a phase perception parallel attention mechanism, and solves the problems that an existing wind power equipment blade fault detection method is high in dependence on labeled data, insufficient in generalization ability under strong noise and variable working conditions and high in fault detection efficiency. And a weak transient fault signal and a dynamic change characteristic are difficult to capture robustly. According to the scheme of the invention, the method comprises the steps: collecting a blade operation audio signal, and extracting a dual-channel time-frequency feature containing an amplitude spectrum and a phase spectrum through improved short-time Fourier transform; a deep adversarial auto-encoder is constructed by using an encoder containing a phase perception parallel attention module, a decoder and an auxiliary encoder, and normal working condition feature distribution is learned by reconstructing an error loss, potential representation consistency loss, adversarial loss and phase consistency loss optimization model during off-line training; in the reasoning stage, the fault is judged based on the feature distance score and the reconstruction error score.
Owner:CHINA HYDROELECTRIC ENGINEERING CONSULTING GROUP CHENGDU RESEARCH HYDROELECTRIC INVESTIGATION DESIGN AND INSTITUTE

BERT and self-supervised learning-based small sample city scene image analysis method

The invention belongs to the technical field of computer vision and natural language processing, and discloses a small sample city scene image analysis method based on BERT and self-supervised learning. Potential information of unlabeled urban environment image data is fully mined in combination with self-supervised learning, and multi-modal features of urban environment images and description texts are integrated by using a cross-modal semantic enhancement mechanism, so that accurate diagnosis of small sample urban environment images is realized. According to the method, the generalization ability of the model in a small sample scene is improved, the diagnosis efficiency and accuracy of an existing method in a complex analysis scene are remarkably improved, and the defects that in the prior art, data dependence is high, the requirement for hardware resources is high, and cross-modal information utilization is insufficient are overcome.
Owner:NORTHEASTERN UNIV CHINA

Yaw static and dynamic error self-adaption method based on big data back test

The invention relates to the technical field of wind power generation. The invention provides a yaw static and dynamic error adaptive method based on big data backtesting, which comprises the following steps of: constructing a multi-dimensional feature vector through multi-source data fusion data, and establishing a dynamic feature data set; based on the dynamic characteristic data set, a space-time diagram convolutional network is adopted to establish a wind power plant dynamic error prediction model, and space-time evolution rules of wind shear, turbulent flow and wake flow effects are captured; constructing a variational self-coding reference model based on historical full wind speed section data, calculating a residual error between a current working condition and the variational self-coding reference model in real time, and taking the residual error as a static error prediction value; performing adaptive weight fusion on the static error prediction value and the dynamic error prediction value to obtain a fusion error; and the fusion error is converted into the yaw angle correction amount, and the wind facing action is executed. The problems that an existing yaw error recognition technology is high in data dependence, lack of dynamic analysis, poor in model adaptability and difficult in complex wind field processing are solved.
Owner:HUANENG DINGBIAN NEW ENERGY POWER GENERATION CO LTD +1

Unsupervised semi-pairing cross-modal retrieval method and system based on deep learning

The invention discloses an unsupervised semi-pairing cross-modal retrieval method and system based on deep learning, relates to the field of artificial intelligence, and is used for solving the problems of annotation data dependence, asymmetric semantic association and high-dimensional storage efficiency. According to the method, a double-branch visual encoder and a dynamic prompt text encoder are combined, dynamic weighting of visual-text features is achieved through gating cross attention, and modal redundancy interference is restrained. An enhancement strategy is generated through low-frequency semantic guidance, and the long-tail word coverage rate is increased; a dual-stage quantitative hierarchical index is constructed, coarse-grained clustering and fine-grained product quantitative compression feature storage is adopted, and million-level data real-time retrieval is supported. A degradation aware increment maintenance mechanism monitors data distribution offset through a KL divergence threshold, and triggers index reconstruction to maintain long-term update precision. According to the method, limitation of a traditional strong pairing model is broken through, cross-modal sensitive content second-level positioning is achieved, asymmetric semantic alignment is effectively solved, and retrieval efficiency is improved.
Owner:SHENZHEN KESHU INTELLIGENT TECHNOLOGY CO LTD

Multi-type database performance optimization and operation and maintenance management method and system

The invention relates to the technical field of databases, and discloses a multi-type database performance optimization and operation and maintenance management method and system.The multi-type database performance optimization and operation and maintenance management method comprises the steps that real-time performance indexes of a heterogeneous database cluster are collected, and a noise reduction data set is obtained; generating a cross-library performance coupling degree matrix through the resource competition coupling degree and the data dependence coupling degree; constructing a coupling relation graph; identifying a bottleneck node set based on the coupling relation graph and the abnormal level; generating an optimization strategy; and performing strategy conflict identification according to the optimization strategy, generating a processing strategy, and executing the processing strategy optimization strategy. Through the improved weighting centrality algorithm, the core bottleneck node which has the greatest influence on the whole cluster is accurately identified, a differential optimization strategy is adopted according to the database type, a perfect strategy conflict detection and avoidance mechanism is established, mutual interference in the optimization process is effectively prevented, the optimization success rate is improved, and the optimization efficiency is improved. And the optimization time is shortened.
Owner:NANJING TORTOISE & HARE RACE SOFTWARE RES INST CO LTD

Data dependency relationship confirmation method and device, equipment and medium

The invention relates to the technical field of big data and the field of financial science and technology, and discloses a data dependency relationship confirmation method, which comprises the following steps of: importing metadata information containing a field name, a data table name and data source information into a data processing module to obtain a target field name, and retrieving a target field in the metadata information by utilizing the data processing module to confirm a data dependency relationship. Determining an upstream data source and a downstream data destination of the target field; generating upstream and downstream data link diagrams of the target field, wherein the upstream and downstream data link diagrams are used for identifying a flow relation of data, a data generator and processing logic; and analyzing a dependency relationship between the target field and the upstream and downstream fields based on the link diagram, and further determining a data table on which the target field depends and owner information of the data table. According to the method, through automatic analysis and link diagram generation, the original complex process needing manual query and processing is simplified, the data dependency relationship is clearer, the communication cost and query time of developers are reduced, and the data use accuracy and processing efficiency are effectively improved.
Owner:PING AN BANK CO LTD

Method for converting C + + code into CUDA-C code

The invention relates to the technical field of computers, and discloses a method for converting a C + + code into a CUDA-C code, and the method comprises the steps: receiving a C + + source code, carrying out lexical analysis and grammatical analysis, generating an abstract syntax tree, and carrying out semantic analysis to ensure that the source code is correct semantically; analyzing the abstract syntax tree, identifying a data dependency relationship among the calculation tasks, and determining loop statements and conditional statements in the source code; and converting a loop statement and a conditional statement in the source code into a kernel function, a thread block and a thread management code corresponding to the CUDA, and further generating a corresponding compilable source file. According to the method, the abstract syntax tree of the C + + code is analyzed, the parallelism in the abstract syntax tree is analyzed, the code is optimized, the CUDA-C efficient code is generated, then efficient automatic conversion of the code is achieved, and the method has great significance in accelerating program performance and shortening the development period.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

Improved YOLOv8 fish image recognition method based on transfer learning

The invention discloses an improved YOLOv8 fish image recognition method based on transfer learning, and the method comprises the following steps: collecting a fish image data set, and carrying out the preprocessing of the data set; correspondingly marking category names on the fish image data set according to fish categories, and dividing the fish image data set into a training set, a verification set and a test set in proportion; a standard YOLOv8 model is improved; all fish images in the ImageNet data set are adopted to pre-train the improved YOLOv8 model, and obtained weight parameters are migrated to the model; performing optimization parameter training on the improved YOLOv8 model after transfer learning by using the training set and the verification set; and performing target detection on the test set through the optimized improved YOLOv8 model, and outputting a fish identification result. According to the method, the feature extraction and recognition precision is effectively improved, the computing resource demand is reduced, and the robustness and adaptability of the model are enhanced; according to the method, the learning efficiency and the recognition precision of the model are remarkably improved, data dependence is reduced, and the model has high generalization ability.
Owner:SHAOXING CAOEJIANG DAZHA INVESTMENT DEV CO LTD +2

Hardware computing resource allocation method, hardware computing resource and electronic equipment

The invention discloses a hardware computing resource allocation method, hardware computing resources and electronic equipment. The hardware computing resource allocation method comprises the following steps: acquiring a data shape of an input tensor of an operator for a model computing task; acquiring hardware parameters of the hardware computing resources; according to the hardware parameters and the data shape, a resource allocation scheme of the operator is determined, and the resource allocation scheme indicates a segmentation mode of the input tensor on multiple dimensions of the input tensor and an allocation mode of allocating the input tensor to hardware computing resources for processing according to the segmentation mode; segmenting the input tensor according to the resource allocation scheme, and sending each segmented tensor to a corresponding computing resource to execute a model computing task; wherein the elements, belonging to the same row, in the input tensor have data dependence during model calculation, and in the resource allocation scheme, the elements in the same row perform a model calculation task in the same calculation unit.
Owner:广州壁仞智能科技有限公司 +1