762 results about "Data scheduling" patented technology

The invention discloses an industrial equipment real-time monitoring system based on edge computing, and the system comprises the following steps: collecting, processing and analyzing the operation data of industrial equipment through distributed edge computing nodes, constructing a node cooperation mechanism, and completing the processing of the data; the dynamic data scheduling module is used for dynamically optimizing a data transmission path and task allocation according to node performance; the intelligent model dynamic migration module is used for adjusting lightweight model deployment in combination with node resource conditions; the multi-modal fault sensing module is used for extracting and analyzing multi-modal features by using a cross-node collaborative algorithm; the edge node self-adaptive management module is used for adjusting node operation parameters in real time and repairing an abnormal state; and the equipment relevance reasoning module is used for constructing an equipment relevance model through a graph calculation method and generating a real-time relevance graph. According to the method, efficient monitoring and anomaly detection of industrial equipment are realized through resource optimization and intelligent analysis of collaborative edge computing nodes.

The invention relates to the technical field of data processing, and discloses a comprehensive dispatching system for a digital intelligent water service pipe network. Comprising a processing module, a layering module, an identification module, a scheduling module, an analysis module and an evaluation module which are connected in sequence. The processing module preprocesses the pipe network data and constructs a dynamic boundary area; the layering module generates operation parameters according to function classification; the identification module analyzes equipment fault features to obtain state data; the scheduling module formulates a preliminary scheme according to a time-sharing rule; the analysis module performs multi-target processing based on the dynamic weight to generate a scheduling instruction; and the evaluation module evaluates pressure, flow and water quality indexes to form a target strategy. The operation efficiency of the water supply network is improved.

The invention provides a continuous casting quality control method based on a meta-cognitive coordination architecture agent cluster, and relates to the technical field of ferrous metallurgy intelligent manufacturing. The continuous casting quality control method comprises the steps of data input and standardization, center coordination and intelligent agent cluster operation and maintenance. In the central coordination process, the meta-cognitive coordination agent serves as a core to coordinate six kinds of functional agents including a semantic analysis agent, a data perception agent, a defect prediction agent, a root cause analysis agent, a process optimization agent and a digital twinborn agent, and task scheduling and state monitoring of the whole system are achieved. Three key functions of task decomposition, data scheduling and closed-loop management and control are completed; in the closed-loop management and control step, risk early warning, defect prediction, root cause analysis, process optimization and digital twinborn verification and feedback are carried out for continuous casting quality. Compared with a traditional scheme, optimization is carried out in the aspects of whole process, multiple modes, intelligence, collaboration and the like, the management efficiency is improved, and economic benefits can also be increased.

The invention discloses a vehicle-mounted edge gridding data scheduling system based on combination of a block chain and load balancing. The vehicle-mounted edge gridding data scheduling system comprises a dynamic resource allocation module, an intelligent scheduling module, a data management module and a data security and privacy protection module, the system provided by the invention can dynamically adjust the allocation of calculation and storage resources, and performs data scheduling according to real-time traffic and vehicle state information, thereby realizing efficient vehicle-mounted edge calculation.

The invention provides a key value cache data scheduling method and device and a large model reasoning method and device, and relates to the technical field of artificial intelligence. The method comprises the following steps: predicting target key value cache data required by a large model for reasoning a subsequent token by utilizing a prediction model; the subsequent tokens refer to tokens which are not reasoned by the large model; judging whether the target key value cache data needs to be scheduled or not; if scheduling is needed, generating a scheduling strategy; obtaining target key value cache data from the first storage space according to a scheduling strategy, and storing the target key value cache data to a second storage space; wherein the target key value cache data is used for enabling the large model to infer subsequent tokens. According to the method and the device, frequent access to the first storage space is reduced, and only the required target key value cache data is transmitted every time instead of full-amount key value cache data, so that occupation of bandwidth resources caused by transmission of the key value cache data is reduced.

The invention discloses a production line operation monitoring system based on a digital twin technology, and the system comprises a data collection module which is used for collecting the data of each task in a production line; the scheduling unit construction module is used for mapping each task instance in the virtual task relationship into a cat-shaped scheduling unit and initializing a role field based on a preset threshold value; the scheduling game engine module is used for executing a combat cat algorithm on the game model and generating a scheduling scheme set comprising a plurality of candidate scheduling schemes; the simulation evaluation module is used for executing simulation evaluation on each candidate scheduling scheme in the digital twin environment to obtain a corresponding task completion rate, a resource utilization rate and a system load balance degree; and the strategy management module is used for sorting the candidate scheduling schemes according to the simulation evaluation result and screening the current optimal scheduling scheme. According to the invention, intelligent production task scheduling, real-time response and strategy adaptive optimization are realized.

The invention provides a ship comprehensive energy efficiency improvement platform and a data management and application method thereof, and belongs to the technical field of ship comprehensive energy efficiency optimization and big data. The ship comprehensive energy efficiency improvement platform comprises a ship end, a cloud end and a shore end, wherein the ship end realizes equipment data acquisition, edge processing and scheduling through a data acquisition module, an edge calculation module and a data scheduling module; the cloud end completes data aggregation, isolation and distributed storage through the data aggregation module, the data isolation module and the distributed storage module; and the shore end realizes data standard management, algorithm version control and micro-service business application through the data center layer, the algorithm center layer and the business center layer. The ship energy efficiency comprehensive improvement platform provides comprehensive management and optimization for various energy-saving devices and various ship energy efficiency improvement software, and optimization and improvement of ship comprehensive energy efficiency are achieved.

The invention relates to a smart campus data management method and system. Comprising the following steps: modeling by adopting semantic consistency-oriented data behaviors; abstracting all system data as behavior event units; uniformly converting modeling results into semantic vectors, and writing the semantic vectors into a campus semantic behavior database; establishing an event standardization rule base; constructing a dynamic data flow scheduling engine by adopting a behavior link diagram; constructing a behavior path map according to the behavior event nodes, and extracting a high-frequency behavior link; a graph search algorithm is introduced to calculate a data scheduling path; a polymorphic perception and difference recognition mechanism of heterogeneous behavior states is adopted; capturing the deviation between the actual behavior event and the expected behavior link; constructing a behavior state comparison model, and identifying a potential abnormal state or a strategy failure risk; adopting a self-adaptive optimization and feedback updating mechanism of a strategy evolution graph; introducing a reinforcement learning algorithm, and carrying out strategy scoring and value return calculation on the strategy map; and adjusting and optimizing link parameters and resource scheduling logic, and notifying rhythm.

Embodiments of the present invention relate to the fields of large model techniques and big data. Disclosed are a data scheduling method, a system, and an electronic device. The method comprises: in a performance feature set of a performance prediction model, determining a target performance feature matched with a scheduling strategy of a model to be trained, wherein the performance prediction model is matched with the model type of the model to be trained, the model type is used for representing a data architecture of the model to be trained, and the scheduling strategy is used for at least representing a rule required to be satisfied during training of the model to be trained; and identifying from among different training strategies a target training strategy corresponding to the target performance feature, and identifying from among different training resources a target training resource corresponding to the target performance feature; and configuring the identified target training strategy to the model to be trained, and allocating the identified target training resource to the model to be trained.

The invention provides a resource intelligent bus and task parallel hydrogen energy data scheduling optimization method and system, relates to the technical field of energy, and aims to solve the problems of resource heterogeneity, lack of real-time performance and dynamic adjustment, insufficient energy efficiency optimization, poor adaptability to abnormal working conditions and the like in the prior art. According to the method, a resource intelligent bus architecture is constructed, and the resource intelligent bus architecture comprises a resource virtualization encapsulation layer, a resource state sensing layer and a global prediction and scheduling layer; in the resource state sensing layer, performing multi-granularity task decomposition on hydrogen energy business requirements, and establishing an inter-task dependency relationship model by adopting a directed acyclic graph; in the global prediction and scheduling layer, a multi-objective optimization model is constructed based on a dependency relationship between resource states and tasks, and resources and tasks are dynamically matched according to an optimal solution of the model; and dynamically scheduling the resources according to a matching result of the resources and the tasks. The problems in the prior art are solved, and the hydrogen energy data scheduling optimization performance is improved.

The invention, which relates to the technical field of marine transportation data analysis, discloses a block chain-based marine transportation data periodic acquisition and scheduling system comprising a data scheduling management center, the data scheduling management center being in communication connection with a data acquisition module, a request management module, a scheduling optimization module and a cross-chain interaction module, the modules are in electric signal connection; the data acquisition module is used for collecting and preprocessing sea transportation data from a plurality of data sources, and performing distributed storage of the sea transportation data in combination with a block chain technology. The block chain side chain and fragment technology is adopted, sea transportation data processing is dispersed to different side chains and fragments, the load of a main chain is effectively reduced, the throughput of the system is improved, meanwhile, the application of a hierarchical consensus mechanism carries out hierarchical processing on the consensus process, consensus delay is reduced, and the system performance is improved. The hierarchical processing mode not only balances the security and the efficiency, but also significantly reduces the system bottleneck and transaction confirmation delay during multi-user concurrent requests.

The invention discloses an AI data scheduling distribution system and method based on cloud computing, and relates to the technical field of intelligent cloud computing, and the system comprises an AI data collection module, a feature extraction module, a decision parameter generation module, a scheduling distribution module and a visual feedback module. The AI data acquisition module acquires equipment video data and temperature data, the feature extraction module extracts video temperature features, the decision parameter generation module outputs equipment vibration intensity and temperature rise rate, and the scheduling distribution module calculates equipment shutdown probability and node load score and triggers a shutdown instruction and a task migration decision. And the visual feedback module maps the equipment health state and node load distribution, and optimizes the feature weight. Through multi-modal data fusion and a closed-loop feedback mechanism, accurate early warning of equipment abnormity and dynamic optimal allocation of resources are realized, visual decision assistance and adaptive weight adjustment are combined, equipment safety and cluster load balancing efficiency in a cloud computing environment are improved, and manual intervention requirements and operation and maintenance cost are reduced.

The invention belongs to the field of airborne electromechanics, and discloses a hydraulic mechanism heterogeneous control method and system.The method comprises the steps that hydraulic systems are divided into two groups, and on-board state signals, flight control system state signals and first hydraulic pressure and second hydraulic pressure of sub hydraulic systems are collected; giving an on-board state threshold value, a low-pressure threshold value, a hydraulic safety threshold value and a sub-hydraulic system relation table; starting and stopping automatic control is conducted on the electric pumps in the first group through the established first control logic architecture according to the data; and the electric pumps in the second group are automatically controlled to start and stop by adopting the constructed second control logic architecture through the data. The system comprises a grouping module, a control logic construction module and two control units, wherein each control unit comprises an acquisition module, a data scheduling module, a staggered starting module, an anti-overvoltage protection module and an anti-error working module. All the electric pumps are controlled through two heterogeneous logic architectures, and the control precision and safety are improved.

The invention relates to the technical field of e-commerce, in particular to an e-commerce data processing method and system.The e-commerce data processing method comprises the following steps that based on user search data, the similarity between keywords and commodity titles is recognized, stable behavior fragments are extracted to generate a matching relation set, keyword sorting is optimized to form a semantic triggering sequence, and the matching relation set is extracted; and analyzing behavior chain identification jump nodes to extract switching points, reconstructing partition frequency output acquisition priorities, and aggregating regional active data streams. According to the method, the matching relation is constructed through the similarity of the keywords and the commodity titles, the semantic logic of the search path is enhanced, the user intention recognition precision is improved, the keyword sorting is optimized by analyzing the click sequence and frequency, the path turning point extraction capability is improved, and the attention is guided to be dynamically adjusted through the commodity partition click change; regional data streams are classified and aggregated according to active time periods, refined recommendation and efficient data scheduling are realized, and the accuracy and personalization of e-commerce data processing are enhanced.

Various solutions for improvement of network energy saving with user equipment data scheduling are described. An apparatus may receive a system information block (SIB) from a network node of a wireless network. The SIB indicates at least one cell-specific discontinuous reception (DRX) parameter set. The apparatus may determine one of the at least one cell-specific DRX parameter set based on the SIB. The apparatus may apply the one of the at least one cell-specific DRX parameter set to a DRX procedure.

The invention discloses an intelligent data acquisition method and equipment based on a front-end monitoring SDK (Software Development Kit) and a medium, and relates to the technical field of front-end monitoring of Web applications. The method comprises the steps that when a Web application page is loaded, a front-end monitoring SDK script is introduced through an external file label, and preset data collection logic in the front-end monitoring SDK script is loaded; wherein the data acquisition logic comprises performance data acquisition logic, user behavior data acquisition logic and error log acquisition logic; when a Web application page runs, intelligent data acquisition is carried out through a preset idle time data scheduling mechanism in a front-end monitoring SDK script; the method comprises the following steps: determining to-be-uploaded data through a preset incremental data uploading mechanism in a front-end monitoring SDK script, and intelligently compressing the to-be-uploaded data; and dynamically selecting a data uploading strategy based on the real-time network condition so as to upload the compressed to-be-uploaded data to a data server.

The invention relates to the technical field of high-concurrency data processing, and discloses a storage and calculation integrated data scheduling system and method for a high-concurrency scene, and the system comprises a storage and calculation fusion architecture module, a distributed cache module, a dynamic fragmentation module, a parallel calculation module, a preloading module and a resource scheduling center. The method corresponds to the system. According to the method, by deeply fusing data storage and calculation and utilizing a distributed caching technology and a data preloading mechanism, I / O bottleneck is effectively reduced, dynamic data fragmentation and parallel calculation are supported, and the method is particularly suitable for large-scale data analysis scenes.

The invention discloses a hardware acceleration device for processing a dynamic graph convolutional neural network, and the device comprises an FPGA parallel acceleration system which comprises a plurality of acceleration modules used for processing different types of calculation tasks; the dynamic data flow control system is used for calling acceleration modules to carry out data calculation according to a data processing task of the dynamic graph convolutional neural network, and managing data transmission and states between the called acceleration modules; and the memory management and data scheduling system is used for distributing a memory space for the acceleration module and storing input data required when the data processing task is executed, an intermediate calculation result obtained when the data processing task is executed and output data obtained after the data processing task is executed. The invention provides a hardware acceleration scheme with low delay, high throughput and high energy efficiency ratio for the dynamic graph convolutional neural network.

The invention provides a structured data representation method, a structured data conversion method, a structured data scheduling method, a structured data conversion device, a structured data scheduling device, a structured data conversion system, a medium and electronic equipment. The representation method comprises the following steps: responding to an operation of dragging a module from a module library to a visual editing canvas by a user to form a node corresponding to the dragged module; responding to the operation that a user establishes visual connection between input ports and output ports of different nodes on the canvas to form edges, wherein the edges define a data flow and calculation dependency relationship between the nodes; a structured data representation of a machine-readable AI model structure is generated based on all the nodes on the canvas and user-configured parameters thereof, and a set of edges defining the edge interconnection relationship. According to the representation method, conversion from graphical representation to structured data of the artificial intelligence model is completed.

The invention belongs to the technical field of airborne electromechanical control, and discloses a redundancy automatic electric pump control method and system.The control method comprises the steps that airborne state signals, flight control system state signals and hydraulic pressure of each sub hydraulic system in a hydraulic system are collected in real time; and according to the onboard state signal, the flight control system state signal and the hydraulic pressure, an electric pump connected to each hydraulic sub-system is automatically controlled through electric pump control logic. The system comprises an acquisition module, a data scheduling module and a plurality of electric pump control modules, each electric pump control module is connected with an electric pump, and the output end of the acquisition module is connected with the input end of the data scheduling module. Automatic electric pump control logic is designed, energy consumption can be reduced by independently and accurately controlling each electric pump, single-point faults caused by failure of a control module are avoided, and flight safety is improved.

The invention relates to the technical field of medical data analysis, in particular to a kidney injury prediction system based on big data, which comprises a physiological data processing module, a fluctuation analysis construction module, a dynamic weight evaluation module, a cross-domain data scheduling module and a risk trend prediction module. According to the method, through timestamp standardization and continuous recombination of the acute kidney injury physiological data, the consistency of multi-source monitoring data in the time dimension is ensured, drifting and dislocation are eliminated, the time sequence integrity is improved, fluctuation points of serum creatinine and urine volume are extracted, sensitive time slices are recognized, and high-risk time point early warning is achieved; a rate change comparison mechanism is introduced, a physiological factor weight sequence is generated, factor influence evaluation is enhanced, uploading frequency and a time delay state are combined, high-reliability nodes are screened, data continuity and real-time performance are improved, index trend deviation is tracked, a mode label is generated, and timeliness and accuracy of renal function change prediction are improved.

The invention relates to the technical field of data processing, and discloses a scheduling method and system for realizing cloud terminal call center data based on edge computing, and the method comprises the steps: carrying out the feature extraction of a data scheduling request, obtaining a feature descriptor, and calling request association data from a database of a cloud terminal call center; calculating the adaptation degree between the multimode integrated semantics and the edge computing nodes, and screening out data execution nodes corresponding to the request associated data from the edge computing nodes; calculating a channel noise ratio between the data scheduling equipment and the node server, and calculating a communication throughput rate between the data scheduling equipment and the node server; calculating the total load of task data when the request associated data is transmitted, and constructing a data transmission path between the data scheduling equipment and the node server; and executing scheduling processing on the request associated data by using the data scheduling equipment and the node server to obtain a scheduling result. The scheduling efficiency of the cloud terminal call center data can be improved.

Methods and systems are described for AI and / or ML model selection in a telecommunications network. One example embodiment includes obtaining a first set of one or more criteria for selecting between at least two AI / ML models; performing at least one measurement procedure to obtain one or more measurements; and using the obtained one or more measurements and the first set of one or more criteria to select between the at least two AI / ML models. A measurement procedure can comprise e.g. CSI, radio link procedure (RLP), positioning measurement, measurement related to cell change procedure etc. Certain described embodiments enhance measurement performance of the measurement (e.g., CQI) and correspondingly improve the outcome / performance of the procedure (e.g., data scheduling) using the measurement. This in turn reduces the overall processing in the UE, frees up at least part of the memory resources and reduces the UE power consumption.

The invention discloses a multi-agent collaborative application big data management system and method. The system comprises a data acquisition unit, a data preprocessing unit, a multi-agent collaborative processing unit, a data storage unit and a data scheduling unit. The data acquisition unit is used for acquiring multi-source heterogeneous original big data and transmitting the multi-source heterogeneous original big data to the data preprocessing unit; and the data preprocessing unit is used for executing preprocessing operation including de-duplication and format standardization on the original big data. The invention relates to the technical field of big data management. According to the multi-agent collaborative application big data management system and method, through a multi-agent collaborative algorithm, the system can realize a self-adaptive data classification and optimization strategy, a data processing mode is dynamically adjusted, the processing efficiency problem of a traditional static rule during data mode fluctuation is improved, and the data processing efficiency is improved. The system adopts a dynamic resource scheduling strategy based on a data access demand and a system load, efficiently distributes calculation and storage resources, and facilitates priority processing of high-priority tasks.

The invention discloses a hotel self-service equipment collaborative management system and method based on the Internet of Things, and relates to the technical field of hotel intelligent management, and the method comprises the steps: a sensing module monitors personnel distribution and behavior characteristics in an equipment operation radius in real time through a multi-source sensor network, and generates spatial state data; the scheduling engine module receives the spatial state data, divides a physical space into virtual grids, calculates a service pressure index and generates an equipment state control strategy; an equipment cooperation module responds to the equipment state control strategy, establishes an equipment cluster dynamic health baseline and executes cross-equipment micro-task scheduling and verification; and the user interaction module fuses the biological characteristics and the behavior data to generate a dynamic trust score, and controls equipment service activation. According to the invention, the problem of low efficiency caused by rigid spatial layout, uneven load and fault diffusion of hotel self-service equipment is solved, full-link collaborative optimization from a physical environment to digital resources is realized, the user experience is improved, and the operation and maintenance cost is reduced.

The invention discloses a data scheduling and control method based on mainboard memory straight-through, and relates to the technical field of computer hardware, the method comprises the following steps: pre-allocating a straight-through memory area for mounting equipment in a firmware initialization stage, establishing a mapping relation between equipment identification and a physical address of an exclusive memory segment, and through address translation and access control rules of a firmware layer, the device bypasses a system cache level and accesses the exclusive memory segment in a direct memory access mode. Constructing a firmware scheduling table based on the mapping relation to manage access requests of all devices, monitoring transmission delay in real time, and dynamically adjusting priority weight and bandwidth allocation in the scheduling table according to a monitoring result; and sequencing the requests according to the updated scheduling table to complete scheduling and control of the memory access behavior of the equipment. According to the method and the device, the delay bottleneck caused by multi-level copying and firmware scheduling lag in mainboard data forwarding is effectively solved.

The invention discloses a virtual power plant resource scheduling strategy optimization system, a virtual power plant resource scheduling strategy optimization method and a medium, mainly relates to the technical field of virtual power plants, and is used for solving the problems that an existing virtual power plant lacks systematic scheduling of resource scheduling control instructions, and when project data changes greatly, the scheduling control instructions cannot be systematically scheduled. The problem that an existing scheduling scheme cannot effectively fit new project data is solved. Comprising an aggregation resource information acquisition module used for acquiring device data of a source network load storage device corresponding to a power user and issuing a device control instruction to the source network load storage device; the scheduling control strategy selection module is used for determining a corresponding scheduling control strategy and prediction equipment data from the control strategy database; the scheduling control instruction execution module is used for issuing a scheduling instruction associated with the scheduling control strategy to the corresponding source network load storage equipment; and the scheduling control strategy optimization module is used for generating an equipment control instruction when the real-time equipment data is inconsistent with the predicted equipment data, and issuing the equipment control instruction to the corresponding source network load storage equipment.

The invention provides a graphical programming education system, which comprises a database used for storing coding information and drawing data; the scheduler is connected with the database and used for managing data flow between the database and the interpreter; the interpreter is connected with the scheduler and is used for analyzing the coding information and generating a task in an intermediate representation form which can be understood by the system; the judgment module is connected with the interpreter and is used for carrying out logic judgment on the task and providing a control signal for the operation module; the operation module is connected with the judgment module and is used for executing the task according to the control signal and transmitting the output to the output module; and the output module is used for displaying the result transmitted by the operation module. The system is used for realizing bidirectional mapping and real-time synchronization between the coded information and the graphical representation, and realizing dynamic visualization of the coded information logic based on the data flow.

The invention relates to the technical field of deep learning, and discloses a fine-grained pipeline scheduling method and device based on cluster node memory difference perception. The method comprises the following steps: estimating the ratio of the peak memory occupancy to the memory capacity of each GPU node, comparing the ratio with a preset threshold value, and selecting a re-calculation strategy and a back propagation segmentation strategy: by taking minimization of the end-to-end training time of a model as a target, scheduling and modeling micro-batch data as a flow shop problem, analyzing the dependency constraint of each flow line stage, and calculating the flow shop problem; comprising forward-back propagation sequence dependence, stage dependence, operation dependence and memory limitation, and generating a micro-batch operation sequence scheduling scheme meeting the memory capacity limitation; according to the scheduling scheme, an execution sequence queue is created by executing sorting, and the execution time sequence of calculation blocks, communication blocks and re-calculation operation is dynamically coordinated. According to the method, the GPU equipment utilization rate can be remarkably improved, and the end-to-end training completion time of the model is shortened.

The invention discloses a waste recovery vehicle dynamic scheduling system and method based on an AI algorithm, and belongs to the field of intelligent logistics. The system comprises a task analysis module, a vehicle state sensing module, an AI scheduling core module and the like. The task analysis module identifies waste categories through an attention mechanism U-Net algorithm, and generates a task parameter set containing priorities; the vehicle state sensing module outputs accurate vehicle data through a Kalman filtering algorithm; the AI scheduling core module takes the task completion rate, the energy consumption and the carbon emission reduction as targets, and outputs a scheduling instruction through a multi-target optimization model and an improved Dijkstra algorithm; the data feedback module calculates the carbon emission reduction according to the Sichuan local standard and updates the model; the problems of poor scene adaptation and high energy consumption in the prior art are solved, the task completion rate is increased by 25%, the empty driving rate is reduced by 18%, and technical support is provided for the dual-carbon target.