49 results about "Resource reallocation" patented technology

An energy-conscious workflow planning system based on LLM with dynamic resource allocation, consisting of: a workflow input interface configured to receive workflow-directed acyclic graphs (DAGs), energy budget constraints, system performance constraints, and natural language requests from human operators; a large language model (LLM) logic module connected to the workflow input interface and configured to analyze the workflow specifications and system constraints in natural language, generate energy-conscious planning recommendations based on the analyzed workflow specifications, and provide explainable planning rationales in natural language; a reinforcement learning-based scheduling unit connected to the LLM reasoning module and configured to: receive scheduling recommendations from the LLM reasoning agent, fine-tune task-resource assignments by dynamically adapting to runtime variations, and perform online resource redistribution under runtime variability; an energy monitoring unit configured to: continuously monitor CPU and GPU utilization in heterogeneous clusters, track power consumption and thermal limits per node, and generate energy profiles for system components; a multi-objective optimization engine configured to: perform a Pareto-optimal scheduling analysis that balances energy consumption, lead time and reliability, apply statistical and AI-supported trade-off analyses and ensure optimal resource allocation based on Pareto frontier analysis; a dynamic resource allocation unit configured to: use predictive models that incorporate LLM inferences and feedback from reinforcement learning, reassign tasks between nodes and clusters while minimizing energy consumption and improving system throughput based on the predictive models; a performance optimization module configured to optimize scheduling decisions using multi-criteria optimization analysis; and a user interface that allows human operators to override and refine planning strategies in real time based on verifiable planning reasons.

The invention relates to the technical field of project management, and particularly discloses a project management method and system based on an AI large model technology, and the method comprises the steps: collecting multi-dimensional project execution data, carrying out the data cleaning and feature coupling analysis of the multi-dimensional project execution data, and generating a normalized project feature tensor; inputting the task delay risk into a pre-trained time sequence prediction large model, and outputting a task delay risk probability distribution matrix; carrying out risk level label mapping based on the task delay risk probability distribution matrix, and generating a multi-level risk early warning signal; and in response to the risk event exceeding the preset threshold in the multi-level risk early warning signal, a resource redistribution scheme is generated, and a project manager not only can monitor the project progress in real time, but also can quickly adjust resource configuration when the risk occurs, thereby realizing dynamic management. The intelligent project management mode based on data driving not only improves transparency and controllability of the project, but also provides powerful technical support for successful implementation of the project.

The invention relates to the technical field of port scheduling, in particular to a port loading and unloading equipment dynamic regulation and control method and system based on a working road, and the method comprises the following steps: obtaining the real-time state data of port loading and unloading equipment in the working road, and obtaining the cooperative state index of the working road; deducing a task operation chain of the operation path in combination with an operation environment factor to obtain a dynamic time flow; obtaining an efficiency prediction index of the job path, and generating a resource allocation regulation and control strategy by constructing a global resource reallocation model; converting the resource allocation regulation and control strategy into an equipment regulation and control instruction set for optimization to obtain a final regulation and control instruction sequence; and executing the final regulation and control instruction sequence, obtaining a regulation and control effect evaluation result, correcting the global resource redistribution model, and realizing dynamic regulation and control of the port handling equipment. The active regulation and control of the port loading and unloading equipment are realized, and the operation efficiency, the adaptability and the intelligent level of the equipment are effectively improved.

The invention discloses a digital twin-driven intelligent construction site resource dynamic scheduling system and method, and belongs to the technical field of building construction management, and the system comprises a four-dimensional resource topology construction module which constructs a four-dimensional topological graph of construction resources based on UWB and RFID technologies; the mixed engine scheduling module adopts a mixed integer programming engine to generate a reference scheduling scheme in an initial stage, and adopts a reinforcement learning optimization engine to perform dynamic adjustment in an execution stage; the conflict prediction network module is used for establishing a conflict prediction model based on historical data and triggering a resource redistribution mechanism; the virtual interaction visualization module displays a scheduling scheme in a virtual reality environment and supports manual intervention, depth relation modeling, double-engine collaborative optimization and active conflict prevention of construction resources are achieved, the resource utilization rate is increased by 35% or above, the construction period is shortened by 15% or above, and conflict events are reduced by 50% or above.

The application relates to the technical field of network communication, and discloses a network self-healing device based on node state data, which aims to improve the stability and self-healing ability of network communication. By monitoring the network state in real time, combining the extended Kalman filtering algorithm to perform state estimation and filtering, and combining the ant colony algorithm and the simulated annealing algorithm to perform fault prediction, path selection and resource allocation, the potential fault can be predicted and quickly recovered. The device comprises five modules of state monitoring, state estimation and filtering, fault prediction and prevention, fault recovery and resource reallocation, forms a closed-loop optimization mechanism, and is especially suitable for complex large network environments, such as data center networks.

The invention discloses a multi-disciplinary simulation task intelligent planning method based on a knowledge graph, and relates to the technical field of intelligent scheduling, and the method comprises the steps: constructing a preliminary knowledge graph comprising multi-disciplinary task description, resource limitation and execution dependence, analyzing historical task data through a pre-trained deep learning model, and obtaining a multi-disciplinary simulation task planning model; dynamically adjusting the preliminary knowledge graph through adaptive learning, and outputting an adaptive knowledge graph; carrying out resource redistribution optimization according to the updated task scheduling strategy, continuing to execute the task, starting monitoring, and collecting task progress and resource data as a new feedback data stream; the resource reallocation and the new feedback data stream are fed back to the adaptive knowledge graph, and multidisciplinary task description, resource limitation and execution dependency are updated through reasoning to generate a final optimization task execution sequence; the synchronous suppression of waiting time and resource contention is realized, the average utilization rate of resources and the time sequence stability are improved, and the adaptive adjustment capability of operation disturbance is formed.

The application relates to the computer technical field and provides a resource recommendation method, which comprises the following steps: selecting a first quantity of to-be-recommended resources; distributing the to-be-recommended resources to corresponding recommendation positions for recommendation and starting to calculate a first recommendation duration; determining to-be-recommended resources that have completed recommendation as target resources; determining a unit-time exposure income value corresponding to each target resource; sequencing each target resource based on the income value to obtain a first sequence; and in the case that the first recommendation duration reaches a first duration threshold, re-distributing the recommendation positions of each target resource based on the first sequence, starting to calculate the first recommendation duration again, and repeatedly executing the step of determining the target resources, so that the problem that the promotion effect is poor when information is put in based on user types can be solved; since the recommendation positions are distributed to the target resources based on the unit-time exposure income, the promotion effect can be improved. In addition, an electronic device and a storage medium are also provided.

The invention relates to the technical field of industrial internet-of-things automatic control, and discloses an actuator internet-of-things multi-protocol adaptation system and method.The method comprises the steps that a protocol module constructs a state machine model for each protocol adapter, cross-protocol state collaboration and abnormal event release are achieved through tense logic rule verification, and a resource module receives abnormal events and sends the abnormal events to a server; the method comprises the following steps: dynamically updating a global resource constraint graph, analyzing an optimal resource reallocation scheme and an atomic task sequence, deconstructing the task sequence into a pi-calculation concurrent process network by applying a reconstruction module, recombining the process network and mapping the recombined process network into a cross-protocol instruction set to drive an executor, and finally, executing the Pi-calculation concurrent process network. Full-link adaptation from protocol layer state consistency guarantee and resource layer dynamic optimization scheduling to application layer process flexible reconstruction is realized, and the reliability and response efficiency of a multi-protocol actuator system in a complex industrial environment are improved.

Embodiments of the present application provide a method of distributed resource management, apparatus, and system, a device, and a non-transitory readable storage medium, which relate to the field of computer technologies. The method includes: in response to receiving a power-on instruction, controlling a switch, a target device, and a target computing unit to power on synchronously; in response to receiving a reset instruction, performing a reset operation on a to-be-reset device indicated by the reset instruction, wherein the to-be-reset device includes at least one of the target devices, the target computing units, and the switch; and performing resource scheduling on target resources in the plurality of resource pools based on a resource scheduling request, wherein the resource scheduling includes resource reset and resource allocation. In this way, the distributed resource management system may achieve resetting of the entire system or device, supports both resource reset and resource reallocation during the resource scheduling process, provides a more efficient and flexible resource management architecture, achieves lifecycle management of pooled resources, and improves the practicability and flexibility of resource management.

The invention relates to the technical field of big data processing, and discloses an intelligent data processing method and system based on distributed transactions, and the method comprises the steps: obtaining a dynamic change index, carrying out the clustering and frequency analysis according to the dynamic change index, determining a transaction coordinator candidate set, and carrying out the clustering and frequency analysis according to the transaction coordinator candidate set. Performing responsivity analysis and load correction to obtain a consistency risk level, performing weight correction and resource redistribution according to the consistency risk level to obtain a load balance distribution vector, performing high-frequency interaction node positioning according to the load balance distribution vector to obtain a mapping priority sequence, and performing high-frequency interaction node positioning according to the mapping priority sequence to obtain a high-frequency interaction node. And carrying out transaction coordinator optimization to obtain a final coordinator, and carrying out efficiency monitoring and dynamic index updating according to the final coordinator to obtain a data distribution rule. The method can dynamically adapt to data distribution changes under high concurrency.

This invention belongs to the field of artificial intelligence technology and discloses a resource allocation method, apparatus, device, and storage medium. The allocation method includes: invoking a target business rule set and a target machine learning model that match the description information; generating a first initial allocation scheme based on rules and a second initial allocation scheme based on the model for the items to be allocated based on the target business rule set and the target machine learning model; generating a root cause diagnosis report when the difference between the first initial allocation scheme and the second initial allocation scheme exceeds a preset threshold; constructing a rule parameter optimization space based on the root cause diagnosis report; and searching for target rule parameters within the rule parameter optimization space that give the preset objective function an optimal solution, generating a final allocation scheme for the items to be allocated corresponding to the rule parameter optimization suggestions. This invention can be applied to business management systems in fintech, healthcare, and other fields, solving the technical problem of inaccurate resource reallocation.

The application discloses a kind of blockchain edge computing resource collaborative scheduling systems of Internet of Things equipment, it is related to Internet of Things technical field, including equipment edge networking module, for deploying edge node in the dense area of Internet of Things equipment, and edge node is accessed blockchain network;Resource state initialization module, for after Internet of Things equipment generates task, task information is sent to edge node layer;Intelligent task allocation module, for after edge node receives task, root calculates optimal task allocation scheme, and according to optimal task allocation scheme, task is allocated to edge node and is handled;Dynamic resource adjustment module, for real-time monitoring the resource load condition of edge node, when resource load is not balanced, according to dynamic resource self-adapting adjustment strategy, resource is re-allocated, and system stable operation is realized. Realize the efficient collaborative scheduling and safe and reliable management of edge computing resource between Internet of Things equipment.

The present application belongs to the technical field of data processing, and specifically discloses a human resource allocation method and device for elevator maintenance, an electronic device, a medium and a program product. The method comprises the following steps: detecting a temporary redeployment event of personnel and recording key information, constructing and updating a task-personnel dependency graph containing task nodes, personnel nodes, time sequence edges, cooperation edges and the like; propagating delay from an event source node to determine an affected task set, evaluating a task impact weight based on urgency, default cost and other parameters, and extracting high-weight tasks; taking the event source as the center, combining multi-dimensional threshold to extract a local optimization domain and freeze the allocation outside the domain, inputting the information in the domain into a large model to generate a candidate strategy, and finally screening an optimal scheme based on constraint conditions and objective functions. The present application realizes efficient human resource reallocation under local minimum disturbance, reduces delay cost and default risk, and improves the utilization rate of human resources.

The application discloses a logistics cost management method and system based on shared storage resources, comprising the following steps: step one: collecting original actual operation data of each warehouse in the shared storage platform, and performing time alignment and correction processing; step two: establishing a shared storage resource network diagram; step three: obtaining multiple complete cost occurrence paths, calculating various logistics costs, and obtaining a logistics cost set; step four: inputting the shared storage resource network diagram and the logistics cost set into an improved Graphormer model, obtaining a storage cost time sequence attention result through a resource occupation coding module, a cost connection enhancement module and a storage time sequence attention module; and step five: extracting a high-cost conduction risk path according to the storage cost time sequence attention result, calculating a shared warehouse comprehensive cost, and obtaining a shared storage resource reallocation scheme. The improved Graphormer model is used to realize intelligent reallocation of shared storage.

This invention discloses a cockpit-driving fusion redundancy system and method based on dynamic resource scheduling. The system includes an intelligent driving domain controller, an intelligent cockpit domain controller, environmental perception sensors, an intelligent sensor hub, a shared memory pool, and a dynamic resource scheduling kernel. The intelligent sensor hub sends sensor data to the intelligent driving domain controller and the intelligent cockpit domain controller via a first data channel (raw data) and a second data channel (feature data), respectively, achieving perception redundancy. The intelligent driving domain controller writes the intermediate perception feature data generated during processing into the shared memory pool. The dynamic resource scheduling kernel virtualizes the computing resources of the two domain controllers into a unified resource pool and triggers resource reallocation when an anomaly is detected in the intelligent driving domain controller, dynamically scheduling computing power to the intelligent cockpit domain controller. This invention solves the problems of single perception dimension, high takeover latency, and low resource utilization in existing redundancy schemes, achieving seamless and secure takeover with high reliability, low latency, and high resource utilization.

The application discloses an LCD display screen production whole-process collaborative management method and system based on an Internet of Things, and particularly relates to the technical field of production process collaborative management, and is used for solving the problems of circular waiting and resource deadlock caused by the lack of global resource allocation dependency relationship analysis in the complex production scene of the existing collaborative management method; by acquiring the equipment state data and material position data of each process in real time, a resource allocation relationship graph taking production equipment as a resource node and production task as a task node is constructed, the resource access sequence of each production task is analyzed to identify a circular waiting path, the blocking propagation risk is evaluated in combination with a process correlation network and a production flow network, and the urgency is quantitatively released according to the task priority, and finally, the production task is selected based on the release urgency to realize the resource re-allocation of the circular waiting path, so that the overall efficiency and resource utilization of the production line are improved.

The present application relates to the technical field of marine information processing, and specifically relates to a heterogeneous computing resource dynamic allocation method for a marine supercomputing environment, comprising the following steps: S1: real-time monitoring of dynamic demand characteristics of marine data processing tasks, including task computing amount and task real-time level; S2: dynamically calibrating task priority; S3: screening out target resources that simultaneously meet the task computing amount requirement and the response speed and real-time level match; S4: allocating the task to the target resources; S5: if the load rate of the target resources exceeds the preset threshold, triggering resource reallocation; S6: outputting the final resource allocation scheme, and recording the completion time of the corresponding task and the utilization rate of each computing resource. Through the task priority driven dynamic scheduling and real-time load perception reallocation mechanism, the present application realizes the time-effect guarantee of key tasks and the efficient use of heterogeneous resources in the marine supercomputing environment.

This invention discloses a method for scheduling and optimizing real-time tasks in a heterogeneous cloud environment, comprising: receiving real-time arriving tasks and allocating them to various computing nodes in the lower layer; after receiving the allocated tasks, assigning the tasks to the computing resources of the nodes for computation; setting up a bottom-up resource reallocation mechanism, and when resource load imbalance is detected within a certain period of time, adopting an effective adjustment strategy to restore the load balance of computing resources in a short time; and scheduling tasks in real time according to the scheduling strategy and resource reallocation mechanism to achieve the optimization goals of load-balanced task allocation and minimizing the total latency upon completion. By ensuring the completion of real-time tasks and minimizing the total latency of real-time tasks while achieving load-balanced scheduling, this method improves the resource utilization of the cloud data center, effectively guarantees the quality of task execution, and enhances the user experience.

A system may obtain performance signals associated with at least one of a plurality of servers used in connection with performing a task. A system may provide the performance signals to a machine learning model. A system may receive as output from the machine learning model a health metric related to the at least one of the plurality of servers. A system may determine whether the health metric meets a migration condition. A system may, responsive to the health metric meeting the migration condition, initiate a reallocation of resources for performing the task, wherein the reallocation of resources includes migration of responsibility for performing the task to at least one other server of the plurality of servers.

Methods, systems, and devices for resource distribution in multi-port memory with host feedback are described. A multi-port memory system may allocate internal resources of a memory system to each of multiple ports of the memory system based on feedback from a host system. For example, the memory system may receive a resource utilization indication from one or more host systems that indicates an expected level of resource usage by each host system that is coupled with the memory system via a port. In some examples, the resource utilization indication may include an indicator of a relative intensity of input / output behavior by each of the host systems. In response to receiving the indication of resource utilization, the memory system may enter a port resource configuration mode and may re-allocate internal resources of the memory system to the one or more host systems in accordance with the received resource utilization indication.

A system may obtain performance signals associated with at least one of a plurality of servers used in connection with performing a task. A system may provide the performance signals to a machine learning model. A system may receive as output from the machine learning model a health metric related to the at least one of the plurality of servers. A system may determine whether the health metric meets a migration condition. A system may, responsive to the health metric meeting the migration condition, initiate a reallocation of resources for performing the task, wherein the reallocation of resources includes migration of responsibility for performing the task to at least one other server of the plurality of servers.

The application discloses a power special network unmanned equipment cooperative internal and external network data interaction processing method, and belongs to the technical field of power grid internal and external network cooperative data processing; is used for solving the technical problem that the data interaction efficiency and quality of the unmanned equipment in the power special network are poor in the existing scheme; task instructions, historical electromagnetic environment data and real-time working condition parameters of unmanned aerial vehicles and unmanned vehicles are collected and processed, data analysis is carried out through a pre-constructed intention-electromagnetic coupling prediction model, and initial prediction results and anti-interference resource reservation quantities are output; the collaborative resource block division of the unmanned aerial vehicle-unmanned vehicle is carried out based on the output prediction results, the channel and bandwidth allocation are optimized, and the balancing strategy is output; the working mode of cognitive radio is dynamically switched by using the balancing strategy, and intelligent merging of repeated data requests is realized by combining intention similarity clustering; the prediction results and the actual interaction behavior of the unmanned equipment are analyzed, and resource reallocation is dynamically implemented.

The invention provides an edge computing-oriented task dynamic allocation method, which comprises the following steps of: according to a computing power allocation demand, determining an obstacle avoidance task priority, preferentially allocating edge computing power to an obstacle avoidance area in front of a vehicle body, and if the bandwidth occupation of a forward-looking sensor is lower than a preset threshold value, reallocating the computing power according to instantaneous sharp increase of a video stream; calculating residual computing power resources according to the optimized storage allocation, reallocating the residual computing power resources to the obstacle avoidance task, judging whether the residual computing power meets a preset real-time decision threshold value or not, and if yes, optimizing the obstacle avoidance task processing efficiency to obtain obstacle avoidance processing computing power; and processing the video acquisition data according to the obstacle avoidance processing computing power, obtaining a final obstacle avoidance decision through collaborative optimization of real-time obstacle avoidance decision data and a computing power scheduling analysis result, and determining a continuously optimized task allocation state according to the final obstacle avoidance decision.

There is provided a method, comprising: grouping resource records based on respective timestamps and first metadata attributes, each resource record including a resource value indicating utilization of a resource of a computing cloud, adding telemetry records to an indexed dataset separate from the resource records with defined time-based validity periods, each telemetry record including a telemetry value indicating a measurable activity within the computing cloud, each telemetry record is associated with a timestamp and second metadata attributes, normalizing resource values of the resource records and telemetry values of the telemetry records to a defined range representing a common scale, matching the resource records and the telemetry records by matching the normalized resource values and the normalized telemetry values, and generating and assigning virtual tags according to the matches, each virtual tag associating utilization of a specific resource to a specific entity for a specific measurable activity.

The invention discloses an abnormal task processing method and system and a computer program product. The method relates to the field of big data, and comprises the following steps: obtaining operation data of a target system collected by a terminal device, the terminal device being a device for operating the target system; extracting feature data from the operation data, and determining an abnormal event and an event type of the abnormal event based on the feature data; a processing strategy of an abnormal task associated with the abnormal event is determined based on the event type, and the processing strategy at least comprises a retry strategy of the abnormal task, a resource redistribution strategy of the abnormal task and an alarm information pushing strategy of the abnormal task; and triggering the terminal equipment to process the abnormal task based on the processing strategy. According to the method and the device, the problems of low efficiency and low accuracy of identifying and processing the abnormal task in the process of processing the business in batches by the financial system in the related technology are solved.

The application relates to a QoS-aware deterministic network slice resource allocation method, comprising the following steps: in an industrial Internet of Things (IIoT) scene, a resource allocation model is constructed according to the QoS requirements of each IoT device; channel gain of a wireless access network, transmission power of the IoT device and interference from other base stations are introduced to obtain a data rate model of the corresponding device under a base station b and a total rate model within a time slot t; a resource allocator is responsible for dynamically reallocating resources to a slice manager in each base station; an optimization problem of slice and resource allocation is established, and the optimization goal is to maximize the overall slice throughput; constraints are converted into virtual queues, and the maximization of user throughput is realized by maximizing the upper bound of the Lyapunov drift penalty function. In the application, the constraints are converted into virtual queues and become part of the objective function, and then the maximization of user throughput is realized by maximizing the upper bound of the Lyapunov drift penalty function.

This disclosure provides a resource management method, apparatus, and electronic device, relating to the field of artificial intelligence technology, particularly deep learning and large model technologies. The specific implementation scheme is as follows: receiving a resource reallocation request; obtaining tensor information of a target tensor from a tensor dictionary; allocating a corresponding first storage space for the target tensor on the GPU based on the tensor information; and pointing a pointer object of the target tensor to the first physical storage address of the first storage space. Thus, without relying on a unified virtual address, it achieves the allocation of a corresponding first storage space for the target tensor on the GPU and points the pointer object of the target tensor to the first physical storage address of the first storage space. This allows the GPU kernel to quickly obtain the physical storage address of the target tensor on the GPU based on the pointer object, without needing to perform a virtual address to physical address conversion step, thereby improving the access efficiency of tensor data.

The invention relates to the technical field of big data analysis and intelligent decision, and discloses an enterprise investment scale intelligent optimization system based on big data analysis. The system comprises the steps of constructing an initial investment scene model, injecting real-time market disturbance variables, simulating the cascade effect of the real-time market disturbance variables on an investment conduction path, and generating a dynamic market situation map to identify pressure nodes. And analyzing the situation map to generate a resource reconfiguration strategy, simulating a diffusion process of an abnormal state under the strategy based on a historical abnormal case library, and outputting a risk dip-dyeing early warning report defining a diffusion boundary and a penetration depth. And according to report reverse calibration strategy parameters, an optimization scheme is locked through iterative convergence. According to the scheme, chain reaction of market disturbance and networked diffusion of risks can be dynamically simulated, and the perspectiveness of investment decision and the risk prevention and control accuracy are improved.

The invention relates to the technical field of resource allocation analysis, in particular to a resource allocation method and system based on data elements, and the method comprises the steps: monitoring resource access, generating a space-time resource pulse sequence, and providing a data basis for subsequent analysis; the influence among data elements is quantified by constructing a space-time pulse response field, and the dynamic interaction relation in the system is visually displayed; a risk propagation path can be quickly positioned by identifying a strong interference data element pair and analyzing a causal link; a quantitative basis is provided for timely intervening excessive concentration of resources by calculating a resource polarization effect caused by pulse resonance; by tracking a polarization propagation trajectory and positioning key nodes, a resource bottleneck point which is most required to be intervened can be identified; pulse attenuation is started for key nodes exceeding a tolerance value, so that the risks of out-of-control resource competition and system collapse are effectively prevented; progressive resource reallocation is executed according to the instantaneous attenuation rate, and efficient system resource utilization and rapid balance recovery are ensured.

The invention belongs to the technical field of computer data processing, and particularly relates to an energy industry full-cycle data management method and system, which comprises the following steps of: establishing a service-aware data value evaluation data set, generating a dynamic value score of each piece of data through weighted aggregation and trend analysis, and obtaining a dynamic value score of each piece of data based on a storage cost and model efficiency balance judgment rule; and according to the dynamic value score and the data metadata, generating a dynamic hierarchical instruction containing a data migration priority and an execution time suggestion, and ensuring that high-performance storage resources can be preferentially allocated to data which has the maximum contribution to improvement of a model training effect and has the highest business value while controlling the total cost, so that data migration processing is executed according to the high-performance storage resources. And storage resource reallocation and access link optimization are carried out, so that the defect that self-adaptive adjustment cannot be carried out after a hierarchical strategy is set in the prior art is overcome, and the storage layout with the optimal cost is generated, and therefore, the optimal configuration of data storage resources and the collaborative improvement of the efficiency of the AI model are realized.