59results about How to "Improve task processing efficiency" patented technology

The invention discloses an intelligent server management method and system in an edge computing environment, and relates to the field of electrical digital data process.The method comprises the steps that a dynamic load buffer database is established; calculating a load stability coefficient of each server node; when the load stability coefficient of the server node is smaller than a first preset threshold value, marking the server node as a fluctuation node; calculating a node cooperation efficiency value; determining a target server candidate set, and calculating to obtain a task allocation weight; distributing tasks on the fluctuation nodes to server nodes in the target server candidate set; when the continuous preset duration of the real-time load value of the fluctuation node is lower than a third preset threshold value, calculating a processing efficiency improvement proportion; for the task of which the processing efficiency improvement proportion is greater than a fourth preset threshold value, keeping continuous processing at the current server node; and for the tasks of which the processing efficiency improvement proportion is smaller than or equal to a fourth preset threshold value, returning to the original fluctuation node. The method and the device are used for reducing communication overhead and service processing delay between nodes.

The invention relates to the technical field of dynamic migration, in particular to an edge computing management system supporting dynamic migration of an AI model. The system comprises a state mining module used for identifying available edge computing devices; performing multi-frequency information monitoring on the available edge computing devices, and performing device comprehensive state mining to generate edge device comprehensive state features; the edge topology module is used for carrying out node position positioning one by one based on edge equipment comprehensive state characteristics and carrying out instant state mapping modeling so as to construct an edge computing node topology model; the task flow trend module is used for acquiring an AI model task running log; and performing task queue analysis on the AI model task running log, and then performing model task traffic trend analysis to obtain AI model task traffic trend data. According to the invention, edge computing management with quick response and high processing efficiency is realized.

The invention belongs to the field of natural language processing, and particularly discloses a task processing method and system based on multiple expert layers, a terminal and a medium, a multi-layer expert network is constructed, and the multi-layer expert network comprises a basic expert layer used for processing general field tasks, a field expert layer used for processing a plurality of specific field tasks and a task expert layer used for processing a plurality of task types; receiving an input task, and analyzing the input task to obtain task characteristics of the input task, including a task field, a task type and task complexity; formulating an expert selection strategy according to the task characteristics; and according to the expert selection strategy, inputting the input task into the target expert layer for processing to obtain a processing result. According to the method, the multi-layer expert network is constructed, the corresponding expert layer is selected according to the task characteristics, adaptation to multiple fields and multiple tasks is achieved, the flexibility and pertinence of the model are improved, and the task processing efficiency is improved.

The invention discloses a batch task optimization method based on dynamic priority scheduling. The method comprises the steps of creating tasks, setting priority information of the tasks, adding the tasks into a scheduling queue of a task execution system, sorting the tasks according to an initial priority, scanning all the tasks in the scheduling queue at a set first time interval so as to obtain the priority of each task, performing resource data acquisition on the task execution system at a set second time interval to obtain a resource utilization rate of the task execution system, judging whether the resource utilization rate is lower than a corresponding safety threshold or not, if the resource utilization rate is lower than the corresponding safety threshold, controlling tasks with high initial priorities to be executed preferentially, and otherwise, controlling tasks with high initial priorities to be executed preferentially. And adjusting the initial priority of the task. The task sequence is dynamically adjusted according to the priorities and resource conditions of the tasks, so that the tasks with high priorities are processed preferentially, and the overall task processing efficiency and response speed are improved.

The invention provides a server device control method and device and a medium. The server device control method comprises the steps that a sensor is used for collecting operation data, automatic modeling is carried out to determine a resource allocation scheme, and resource allocation is controlled. Collecting data after resource allocation, dividing a task queue, matching a server, and dividing sub-tasks; acquiring subtask execution information data; controlling the plurality of servers to execute tasks according to a preset speed, and acquiring environment information and data processing temperature; the processing speed is adjusted in real time by combining task execution information data, environment data and data processing temperature; and evaluating the completion degree after task processing is completed, and judging whether processing is continued or not. According to the method, the resource allocation and task processing speed can be optimized, the task processing quality and efficiency of the server are improved, and the running stability and reliability of the server are ensured.

The invention discloses a hyper-converged server system suitable for edge and end side data centers, and relates to the field of cloud computing. A calculation module; the computing module is arranged at the front part of the case and comprises a plurality of CPU (Central Processing Unit) modules, and the CPU modules are used for providing computing power required by general services; a GPU module; the GPU module is arranged at the rear part of the case, the GPU module comprises a plurality of GPU modules, and the GPU modules are used for providing computing power required by services of cloud rendering, cloud games, AI reasoning and small model training; a fan module; a network switching module; an out-of-band management module; a redundant power source; and a middle plate. By implementing the method, a plurality of computing modules are fused in one server architecture, so that hardware construction is more flexible.

The invention provides a task processing method and device based on a network state. The method comprises the following steps: acquiring a target task through an edge end; task attributes are extracted, semantic coding is conducted on the task attributes, and semantic coding features are obtained; obtaining a time queue of network real-time bandwidth values, and extracting network state time sequence characteristics from the queue; performing feature fine-grained pairing interaction based on the semantic coding feature and the network state time sequence feature to obtain an alignment fusion feature; and distributing the target task to an edge end or a cloud end according to the alignment fusion feature, so that a distributed end processes the target task. According to the invention, dynamic allocation between the edge end and the cloud end can be realized according to different attributes and requirements of tasks and current network conditions; compared with a traditional technical scheme based on static indexes, the method fully considers the characteristics of the task and the real-time network state, enables the target task to be processed more efficiently, and improves the overall response speed and task processing efficiency of the system.

The invention relates to a resource collaborative scheduling method and device, computer equipment, a medium and a program product, and relates to the technical field of power grids. The resource collaborative scheduling method comprises the following steps: acquiring a plurality of operation task requests sent by a distributed subsystem in a power grid system and resource state information of the distributed subsystem; determining task types of corresponding operation tasks according to the operation task requests; and according to each task type and the resource state information, cooperatively scheduling different equipment resources in the distributed subsystem to execute each operation task so as to monitor a power subsystem in the power grid system. The method can improve the resource utilization rate of the power grid system.

The invention provides video processing equipment and a video processing method. The video processing device comprises a multi-core processor, a task scheduling module, a visual processing unit and a cooperative control module, and the multi-core processor is used for sending a task queue corresponding to a video stream to the task scheduling module; the task queue comprises a plurality of to-be-processed tasks and real-time levels corresponding to the tasks; the cooperative control module is used for monitoring the states of the visual processing unit and the multi-core processor to obtain state information and sending the state information to the task scheduling module; the task scheduling module is used for dynamically distributing each task to a target processing component corresponding to each task according to the real-time level and state information corresponding to each task, and each target processing component comprises a multi-core processor and a visual processing unit for processing; the target processing component is used for processing each task to obtain an output result corresponding to the video stream; and the multi-core processor is used for outputting an output result corresponding to the video stream.

The invention provides a task scheduling method and device, electronic equipment and a storage medium, and belongs to the technical field of cloud computing. Compared with the prior art, the method has the advantages that the historical scheduling information is utilized, so that the to-be-processed task can be matched with the virtual machine type more accurately; resource waste in the task processing process can be reduced, and the task processing efficiency is improved. By monitoring the resource use condition of each cloud host and calculating the resource utilization rate based on the monitoring data, the load state of each host can be known in real time, and when the resource utilization rate of a source cloud host is within a relatively low first threshold range, a task and a virtual machine in which the task runs can be dynamically migrated to a target cloud host with a relatively high resource utilization rate; the migration strategy is beneficial to balancing the resource load of the cloud data center and improving the overall resource utilization rate; through virtual machine resource migration, the energy consumption of the whole cloud data center is reduced.

The invention relates to the technical field of computing power, and discloses a task processing method and device for a computing power node, and the method comprises the steps: analyzing an expected transmission link of the computing power node according to the obtained computing power resource demand information of the computing power node; determining at least one first target transmission node in the expected transmission link, wherein the first target transmission node comprises first multi-dimensional attribute information; for each first target transmission node, predicting transmission efficiency range information of the first target transmission node in a preset first time period according to the first multi-dimensional attribute information of the first target transmission node; and according to the computing power resource demand information, all the transmission efficiency range information and the expected transmission link, analyzing a target transmission link, corresponding to the expected transmission link, of the computing power node and computing power transmission mode information of the target transmission link. Therefore, the flexibility and the accuracy of computing power resource allocation and transmission of the computing power node are improved by implementing the method and the device, so that the task processing efficiency and the flexibility of the computing power node are improved.

The application discloses a media task resource quota calculation method and device, a storage medium and a computer device, and relates to the technical field of media task resource quota calculation. The method comprises the following steps: in response to a media task creation request, extracting multimedia task parameters of a media task, wherein the multimedia task parameters comprise a service type and a service attribute; if the service attribute is contained in a service-specific configuration list corresponding to the service type, determining a weight value corresponding to the media task based on the service-specific configuration list; if the service attribute is not contained in the service-specific configuration list corresponding to the service type, querying a configuration item matched with a resolution parameter of the media task in a resolution configuration list according to the video resolution parameter corresponding to the media task, and determining the weight value corresponding to the media task based on the configuration item; and determining a resource quota value according to the weight value corresponding to the media task, so as to perform server resource scheduling based on the resource quota value.

The invention discloses a GPGPU (General Purpose Graphics Processing Unit) stream multiprocessor source-saving scheduling method, equipment and a medium, belongs to the technical field of GPGPU scheduling execution, and is used for solving the technical problems that in the existing GPGPU scheduling execution process, the energy efficiency utilization rate of an intensive load is low, memory contention is easy to form, waste of resources and energy consumption is caused, and power consumption is not favorably saved. The method comprises the following steps of: performing all activation processing on the stream multiprocessor unit connected with the thread block scheduling unit; performing category judgment on the task load related to the intensive load, and determining a memory access SM core corresponding to the memory access intensive load; performing suspension processing on the stream multiprocessor unit corresponding to the memory access SM core; computing control is carried out on a computing SM core in the residual stream multiprocessor unit to obtain a computing execution state of the computing SM core; and performing activation control on the stream multiprocessor unit corresponding to the memory access SM core to obtain a task execution state of the current task load.

The invention relates to a sketch general configuration method and system based on a data processing unit, and belongs to the technical field of data processing. The method comprises the following steps: (1) identifying resource parameters; (2) selecting a process model; (3) resource constraint input; (4) optimizing target configuration; and (5) parameter configuration recommendation. The invention aims to optimize the communication efficiency of the DPU and the host, reasonably allocate hardware resources, and realize flexible process model selection and efficient state operation configuration, thereby achieving the goals of high accuracy and high throughput of network measurement under limited resources.

The application discloses an AGV task compiling and script executing method based on an RDS scheduling system, and relates to the technical field of AGV scheduling. The method comprises the following steps: a task compiling unit and a script configuration unit are built in the RDS scheduling system, and a visual interface and a script language are provided as two operation modes; a running script containing a task allocation sub-script, a driving control sub-script and an exception handling sub-script is compiled through the script configuration unit; the compiled task and the running script are subjected to syntax checking and parameter matching checking, and are stored in a task database after the checking; the RDS scheduling system calls the task and the corresponding running script in the task database, generates executable instructions and sends the executable instructions to a target AGV, the AGV analyzes the task logic according to the running script, completes the task execution and feeds back the execution state. The application can realize flexible configuration of AGV tasks, high adaptation of scripts and tasks and efficient execution of complex tasks, and improves the adaptability, execution efficiency and reliability of the scheduling system.

This invention provides a multi-task learning resource optimization method based on the lottery hypothesis, belonging to the field of multi-task learning and neural network optimization technology. This method employs a sparse expert hybrid approach based on the lottery hypothesis to effectively prune neural network model parameters, thereby significantly reducing the computational cost and storage overhead of the neural network model. The sparse expert network structure retains high sensitivity to key task information. The introduction of a softmax-based router and mask matrix allows each task to select and activate suitable expert network components based on the features of its input data. Cross-training and iterative amplitude pruning optimize the omnipotent expert matrix, further enhancing the model's generalization ability in handling complex tasks and different data distributions. Task-specific layers independently process and optimize the features of each task, reducing mutual interference between tasks and improving the accuracy of feature extraction and the efficiency of task processing.

The present application discloses an edge computing resource scheduling method, a storage medium, and a server, wherein the method includes a server obtaining the operating data of each edge device, and determining a target edge device according to the operating data of each edge device; the server simulates the target edge device, and executes the task data corresponding to the target edge device. The present application improves the task processing efficiency by arranging a server in an edge system, obtaining the operating data of each edge device in the edge system, determining the target edge device based on the operating data, and executing the task data received by the target edge device by simulating the target edge device by the server.

The application provides a body intelligent robot control method and device, a terminal and a storage medium, and relates to the technical field of robot autonomous task planning and motion control. The method comprises the following steps: collecting multi-modal prompt information of a robot to be controlled; based on a large-scale pre-training language model, multi-modal prompt information and an atomic skill library suitable for long sequence whole body linkage motion of the robot, generating a corresponding chain reasoning text when the robot to be controlled executes a task description, and decomposing the task description into an atomic skill calling sequence according to the chain reasoning text, wherein the atomic skill calling sequence comprises a plurality of atomic skills in calling order; after each atomic skill is called and activated one by one in the calling order, the robot to be controlled is controlled to execute each atomic skill in the calling order. The application can realize seamless connection of whole body motion and local operation of the robot, so that the robot can efficiently complete a long sequence task in a complex environment.

The present application relates to a task processing method, system, computer device and storage medium. The method includes: in the above-mentioned task processing method, by improving the task template, multiple tasks are executed uninterruptedly, and the next task is automatically jumped to be processed after the previous task is completed, which can improve the data processing efficiency.

The invention discloses an RDMA network batch task processing method and device based on selective signals. The method comprises the steps that a driving program initializes a work queue; the application program issues work requests in batches; the driving program sets a work request type for each work request; the driving program submits a work request to the host adapter card; the host adapter card executes the work request and completes a data transmission task according to work request information; the host adapter card selectively reports a completion message; and the driving program processes a completion result of the batch tasks, and after a completion signal is received, state codes of completion queue elements in the completion queue are analyzed and subsequent processing is carried out. According to the RDMA network batch task processing method and device based on the selective signal, the completion signal is only reported to the key task through a selective signal mechanism, so that the completion state analysis and processing overhead caused by the fact that each task reports the completion signal to a driving program and an application program is avoided; therefore, the utilization rate of computing resources of the processor is optimized.

This application relates to a service management method, apparatus, computer device, computer-readable storage medium, and computer program product. The method includes: acquiring a renewal request initiated by a target organization for an advanced service; parsing the renewal request to determine the expected number of organizational members in the target organization who wish to have access to the service in the next cycle after the advanced service expires; if the expected number of members differs from the actual number of target members, determining the service type matched to each organizational member in the next cycle based on the expected number of members, and, upon the expiration of the advanced service, matching organizational members of the advanced service type in the next cycle and assigning access to the advanced service. The target organization includes multiple organizational members; the target members among these organizational members currently possess access to the advanced service. This method can improve work efficiency.

This application discloses a task processing method, electronic device, storage medium, and program product, relating to the field of distributed technology. The method includes: a scheduling node constructing corresponding tasks to be executed based on product data and multiple processing procedures of each product to be processed that meet preset splitting processing conditions; writing each task to be executed into a task to be executed list; and sending the task to be executed list and pre-set target scheduling parameters for splitting services to a management center node; the management center node writing the tasks to be executed from the task to be executed list into a task to be executed queue according to preset writing rules; allocating execution nodes to the tasks to be executed dequeued from the task to be executed queue based on the target scheduling parameters; and distributing the dequeued tasks to the corresponding execution nodes; and the execution nodes parsing product data and multiple processing procedures from the received tasks to be executed, and executing multiple processing procedures based on the product data, thereby improving task processing efficiency and scalability.

The embodiment of the invention provides a data processing method and system, terminal equipment, a storage medium and a program product, and the method comprises the steps: determining a plurality of first processing tasks which are used for indicating to-be-processed data and information required for processing the data; obtaining resource information of a plurality of first resources, and sorting the plurality of first resources according to the resource information to obtain a first sequence identifier of each first resource; and determining a first processing task required to be executed by each first resource according to the first sequence identifier of each first resource, and processing a plurality of first processing tasks required to be executed according to the plurality of first resources. And the data processing efficiency is improved.

The invention provides a task processing method and device, electronic equipment, a storage medium and a program product. The method comprises the steps of obtaining a plurality of first tasks to be processed, task states of the first tasks and memories needed for processing the first tasks, wherein the task states are used for indicating stages where the first tasks are located; according to the plurality of task states, determining a memory resource pool corresponding to each first task, the memory resource pool being used for processing the first tasks with the same task state, and the memory resource pool comprising a memory unit for providing and executing the first tasks; determining a target memory unit in a plurality of memory units of a memory resource pool corresponding to the first task according to the memory corresponding to the first task, and processing the first task according to the target memory unit; after the first task is processed, the data in the target memory unit is emptied, and the emptied target memory unit is recycled into the corresponding memory resource pool, so that the task processing efficiency is improved.

The invention relates to a task processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining task information input by each user in response to task registration events initiated by different users respectively; the task information comprises task contents and task priorities; for each piece of task information, determining a task type to which the task content belongs based on task features obtained by performing task feature extraction on the task content in the task information; under the condition that the same task type corresponds to various task contents, according to task priorities corresponding to the task contents, sequentially distributing the task contents to task queues corresponding to the task types; the processing priority of the task content in the task queue is in positive correlation with the task priority. By adopting the method, the processing efficiency can be improved.

The application discloses a kind of adaptive double time scale buoy satellite temperature perception service deployment and task scheduling method.First, facing buoy-satellite collaborative ocean edge computing network, the network model of underwater node, buoy node and low-orbit satellite collaborative processing task is constructed, and the edge node temperature model is established in combination with node computing power consumption, thermal resistance thermal capacity parameters and environmental temperature.Second, the self-attention mechanism is used to fuse service request, link availability, node temperature and short time scale operation cost, and the long time scale service deployment interval is dynamically determined.Finally, the improved DQN is used in the long time scale layer to generate temperature perception service deployment scheme, and the improved TD3 is used in the short time scale layer to obtain task scheduling scheme.The application can reduce the comprehensive system cost and node overheating risk, and improve the computing task processing efficiency of cross-domain ocean edge network.

The invention provides a 5G network task unloading and shunting method and system, and belongs to the technical field of wireless communication, and the method comprises the steps: determining all available paths of each network slice; constructing a first matrix and a plurality of second matrixes; all the second matrixes are optimized with the goal of maximizing the number of nodes contained in the selected available path, and an optimized matrix population is obtained; obtaining a node load matrix based on the first matrix and the optimized matrix population; sorting all nodes based on the value of each node load matrix element in the node load matrix to generate an array; traversing each array element in the array, allocating computing resources to the network slices passing through each node, and generating a computing resource allocation scheme; and issuing the computing resource allocation scheme to a physical network through an automatic interface. According to the method, by combining network slicing and intra-network calculation, multi-path selection and resource allocation are optimized, and the participation degree of network nodes is maximized, so that efficient task unloading and shunting are realized.

The invention discloses an artificial intelligence-based information statistics management platform, which relates to the technical field of information statistics management, and comprises an artificial intelligence unit, a data set sharing unit, an expandability unit, a solution division unit and an execution unit, the problems that an existing platform is not clear in data integration and use scene, low in expandability and resource utilization rate, insufficient in model interpretation and the like exist, analysis and processing are conducted through a data set common unit, an expandability unit and a division unit of the platform, the real-time performance and accuracy of data are guaranteed, therefore, faster and more accurate service decisions are supported, and the service quality of the platform is improved. The overall data management efficiency and quality are improved; the optimal configuration and cost control of resources are realized, and the real-time processing requirements of high-concurrency and high-load scenes are met; the transparency of model decision is improved, clear model explanation is provided for users, and decision optimization is supported.

The invention discloses a distributed task scheduling method and device, and belongs to the technical field of distributed task scheduling, and the method comprises the steps: obtaining a current load parameter, a first task label and preset task processing time consumption, and sending a task pulling request signal to a task pool under the condition of judging that the task pool is in an idle state, sending the task to be processed to a task pool to enable the task pool to feed back second task labels of all the tasks to be processed, task estimated load parameters and a task preset timeout time threshold value, and then for each task to be processed, when it is determined that the current task to be processed is a target task which can be currently processed by itself, pulling the target task from the task pool; and finally, processing the target task, and feeding back a processing result to the task pool after the target task is successfully processed. By implementing the method and the device, the problems that the CPU is easy to idle, the overall resource utilization rate is reduced and the task processing efficiency is low due to the adoption of a scheduling mechanism based on an active task pushing mode in the prior art can be solved.

The invention provides a task running method and device, a medium and a program product, and can be applied to the technical field of computers. The method comprises the following steps: acquiring information of a plurality of objects related to a to-be-run task and influence information among the plurality of objects; the influence information represents the influence degree of other objects in the multiple objects on the operation executed by each object; the to-be-run task is a task used for solving a combinatorial optimization problem; each object serves as a particle, information and influence information of the multiple objects are processed by simulating the evolution process of the positions of the multiple particles along with time under the influence of other particles, and the positions indicate decision tendencies for all the objects; in response to determining that each particle reaches the target motion state, generating a target strategy based on the target motion state of each particle; wherein the target motion state is that the position of each particle exceeds a predetermined area and the evolution direction of the position of each particle is a direction far away from the predetermined area; and running the to-be-run task according to the target strategy.