157 results about "Services computing" patented technology

The invention provides a task parallel processing intelligent scheduling method and system oriented to large model services, and belongs to the technical field of service computation.The method comprises the steps that semantic features of instructions and texts of parallel subtasks are extracted through a LaBSE model, embedded vectors are generated, the vector dimension of the embedded vectors is reduced through a compression module, and the embedded vectors are distributed in parallel; inputting the compressed embedded vector into a regression device to predict the generation length; constructing a segmentation algorithm based on semantic integrity constraint, and segmenting the text into a text fragment list; dividing the segmented text fragments in the text fragment list into different batches of tasks by adopting a multi-constraint task batching algorithm according to a similar length constraint and a same instruction constraint to obtain a batch task set; and optimizing the batch task set by adopting a task allocation algorithm oriented to heterogeneous resources, and determining an optimized sub-task scheduling scheme. According to the method, efficient parallel processing of large model services is realized, and the reasoning speed, the resource utilization rate and the intelligent level of task scheduling are remarkably improved.

The invention discloses a large model online reasoning service implementation method based on no-service calculation, and relates to the technical field of model reasoning, and the implementation method comprises the following operations: constructing a large model resource sniffing interface for realizing an API Server mode of sniffing server resources first and then transmitting reasoning data JSON; the model preloading module is constructed and used for rapidly loading a large model by using a model fragmentation technology; a shared memory module is constructed and used for planning and managing GPU and CPU memories and dynamically deducing the utilization rate of the simulated memories; gPU resource sharing is used when model reasoning and concurrent elastic capacity expansion and contraction are realized based on a service-free computing principle. According to the method, the problems of relatively high occupation of online reasoning resources, slow preheating of the resources and the like of a large model are solved, resource waste can be avoided, the utilization rate of the resources is improved, online reasoning service with quick response is realized, and the user experience is remarkably improved.

The invention relates to the technical field of distributed computing, and discloses a heavy truck charging load scheduling-oriented distributed energy intelligent matching method, which comprises the following steps of: establishing a charging service computing power mapping table at a scheduling node; maintaining a shadow counter in a local memory, extracting a pre-estimated computing power consumption value according to an event type and accumulating the pre-estimated computing power consumption value to the shadow counter, and executing linear numerical deduction on the shadow counter according to a reference logic subtraction rate so as to simulate a scheduling data throughput evolution process; adjusting a linear deduction rate parameter according to the deviation between the state feedback data and the numerical value of the shadow counter; and distributing the charging matching task to a charging station edge computing node of which the shadow counter value does not exceed a preset logic saturation threshold value. According to the invention, through an open-loop estimation and closed-loop calibration mechanism of a local logic state, an instantaneous congestion risk caused by physical feedback lag is eliminated; and logic state consistency and self-adaptive distribution of the whole network computing power resources are realized.

The invention relates to the technical field of intelligent power grids, in particular to a power chip computing power resource scheduling method, system and device and a medium, and the method comprises the steps: obtaining original computing power resource data needed by a power chip to execute a computing task from a power system in real time, and preprocessing the original computing power resource data to obtain to-be-processed computing power resource data; according to the to-be-processed computing power resource data, obtaining the total load capacity of service computing data; in response to the chip computing power distribution instruction, determining a fitness function according to the total load of service computing data, and obtaining an optimal computing power resource scheduling strategy by using a firefly algorithm according to the fitness function; and dynamically scheduling the computing power resources on the power chip according to the optimal computing power resource scheduling strategy, and allocating the computing power resources to different computing tasks. According to the method, the calculation power resource of the power chip is optimized and dispatched by adopting the firefly algorithm, so that the resource utilization rate is improved, and the adaptability and reliability of the power chip in a complex power grid environment are enhanced.

The invention relates to the technical field of base station computing power distribution, and particularly provides a 5G base station computing power dynamic prediction and resource distribution system based on digital twinning, and the system comprises a platform computing power total demand prediction module which is used for generating a platform computing power prediction total demand according to a historical operation data set; the user service computing power total demand prediction module is used for generating a user service computing power prediction total demand according to the historical user computing power total demand set; the allocation scheme generation module is used for generating a computing power allocation scheme according to the base station total computing power information, the platform computing power prediction total demand and the user service computing power prediction total demand; the computing power distribution module is used for carrying out computing power distribution on tasks and user services of the digital twin platform according to the computing power distribution scheme; the system can generate a computing power distribution scheme for balancing the computing power requirements of the digital twin platform and the user service by comprehensively considering the total computing power limitation and the predicted requirements of the digital twin platform and the user service on the computing power.

The invention discloses a self-adaptive load balancing method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the hierarchical modeling based on different semantic granularities in response to a preset heterogeneous resource and service calculation demand, and constructing a global semantic computing power model; obtaining a first semantic vector representation of a resource node in the target heterogeneous resource cluster; performing similarity calculation according to the first semantic vector representation corresponding to each resource node and the service computing power semantic vector to obtain a similarity list; target resources in the target heterogeneous resource cluster are obtained through screening based on the similarity list; obtaining a comprehensive evaluation score corresponding to each resource node through fuzzy evaluation; and determining the scheduling priority of each resource node based on the comprehensive evaluation score so as to perform load balancing scheduling. The self-adaptive load balancing method can efficiently and accurately realize self-adaptive load balancing and can be widely applied to the technical field of data processing.

The invention relates to the technical field of streaming computing, and provides a real-time service computing system based on a dynamic rule engine, which comprises a rule management module and a streaming computing engine, the rule management module is used for providing visual configuration and release functions of service rules and performing versioning storage on the released service rules; the streaming computation engine comprises a rule synchronization unit and a plurality of parallel processing units; the rule synchronization unit is used for acquiring service rules from the rule management module and distributing the acquired service rules to each parallel processing unit based on a broadcast mechanism; and each parallel processing unit is used for receiving the business event flow and performing real-time rule matching on the business event flow according to the received business rule so as to output a decision result. According to the system, complete decoupling of business rule configuration and execution is realized, and the problem that rule updating in a traditional business system needs shutdown deployment is effectively solved.

The invention relates to the technical field of enterprise management and information processing, in particular to an intelligent contract-driven enterprise tax risk management system, which adopts a rule management layer and contract execution layer separation architecture: the rule management layer is responsible for configuring and testing a tax rule and generating a rule version identifier; and the contract execution layer is composed of intelligent contracts deployed in the block chain, and comprises a rule state contract for anchoring a rule version and a business risk contract for executing business logic. And coupling the off-chain rule with the on-chain contract through the rule version identifier. And the business risk contract monitors an on-chain evidence storage event, obtains a current effective rule version, delegates under-chain service calculation, verifies a returned result by signature, version, time and the like, and executes corresponding treatment after the verification is passed. For high-risk disposal, the system provides an on-chain arbitration mechanism by governing a contract. According to the method, dynamic and safe updating of the tax risk management rule is realized on the premise of ensuring that the process is automatic, credible and non-tampering.

Client support for applications to access services can be provided. In an example, a computing system can receive, from a client device, text input for an in-progress application to access a service. The client may be prevented from accessing the service prior to the in-progress application being approved. The computing system can detect an error associated with processing the in-progress application based on the text input and contextual information. the computing system can determine that the error is associated with the text input or with a technical issue associated with the in-progress application. The computing system can generate a recommendation associated with the error based on determining that the error is associated with the text input or the technical issue. The computing system may output the recommendation to the client device for use in resolving the error with processing the in-progress application.

The invention relates to the technical field of service computing and high-performance computing, and provides a heterogeneous computing resource allocation method and system, and the method comprises the following steps: obtaining a user request set and a resource set; allocating the computing resources of the resource set to each user request of the user request set, calculating the value of each allocated computing resource to the corresponding user request and summing to obtain the sum of the values of the allocated computing resources to the user request set; taking maximization of the sum of values of the allocated computing resources to the user request set as an optimization target, considering the resource quantity constraint of the allocated computing resources and the constraint of the number of resources allocated to the user requests, and constructing a computing resource allocation optimization model; and solving the computing resource allocation optimization model to obtain an optimal resource allocation result, and the method can effectively improve the resource allocation efficiency in a scene of dual dynamic arrival of resources and requests.

A computer implemented method of deployment and resource allocation of microservices of a distributed computing environment is disclosed. The distributed computing environment includes a microservice deployment scheduler and one or more computing nodes. The microservice deployment scheduler includes a reinforcement learning based dynamic workload orchestration module. The method includes receiving microservice constraints descriptive of a microservice computing task by the microservice deployment scheduler. The method further includes receiving node specific properties from the one or more computing nodes by the microservice deployment scheduler. The node specific properties are descriptive of a computing capacity and / or computing capabilities of the one or more computing nodes. The method further includes orchestrating operation of the one or more computing nodes by the microservice deployment scheduler by inputting the microservice constraints and the node specific properties into the reinforcement learning based dynamic workload orchestration module.

The invention provides a large language model service request scheduling method and system, and belongs to the technical field of large language models and service computing. Fine-tuning the large language model by constructing an instruction fine-tuning data set and predicting the length of a response text, and constructing a relation model between the response time of the fine-tuned large language model and the length of the response text to obtain an approximate solution of the response time; performing batch processing on the service request of the large language model and setting a batch scheduling strategy; an error processing mechanism is introduced, the predicted response text length is compared with the response text length output after the large language model receives the service request, and the service response state of the large language model is determined according to the comparison result. According to the method, the task characteristics in the service response process can be fully utilized on the basis of ensuring accurate prediction of the service response time, so that effective and ordered scheduling of the large language model service response is realized.

Disclosed herein is a computer implemented method of deployment and resource allocation of microservices of a distributed computing environment. The distributed computing environment comprises a microservice deployment scheduler and one or more computing nodes. The microservice deployment scheduler comprises a reinforcement learning based dynamic workload orchestration module. The method comprises receiving microservice constraints descriptive of a microservice computing task by the microservice deployment scheduler. The method further comprises receiving node specific properties from the one or more computing nodes by the microservice deployment scheduler. The node specific properties are descriptive of a computing capacity and / or computing capabilities of the one or more computing nodes. The method further comprises orchestrating operation of the one or more computing nodes by the microservice deployment scheduler by inputting the microservice constraints and the node specific properties into the reinforcement learning based dynamic workload orchestration module.

The invention relates to the technical field of content distribution network resource management, and provides a resource scheduling method, device and equipment, a storage medium and a computer product, a service request is received, a feature vector of the service request is determined, and the feature vector represents the service processing complexity, the service quality level and the service weight factor of the service request; obtaining one or more of load information, performance information and fault information of the node to determine a computing power score of the node; and determining a resource scheduling strategy of the service request based on the feature vector and the computing power score. The computing power demand of the service request is measured from multiple angles, the computing power demand evaluation accuracy is improved, the resource scheduling strategy is determined based on the computing power demand of the service request represented by the feature vector and the computing power score of the node, the service computing power demand can be dynamically matched, and the resource scheduling efficiency is improved. The computing power score of the node is determined based on one or more of load information, performance information and fault information, and burst traffic and node state dynamic changes can be handled.

Systems and methods are provided for implementing automated cloud buildout and / or run state management using cloud hosted orchestration of configuration and installation of cloud services. A configuration file, which outlines configurations and services to be applied to servers installed within a data center, is used by a computing system to orchestrate configuration or reconfiguration of the servers during buildout operations and / or run state operations of a cloud network(s). The computing system monitors for configuration changes or inconsistencies in the servers, as compared with the configuration file. If the configurations have been changed or are otherwise inconsistent with the configuration file, the computing system automatically restores, resets, or reconfigures the first servers or services / apps to be consistent with the configurations as outlined in the configuration file. A user interface may be provided to enable a user to view statuses of the buildout operations and / or the run state operations.

Optimizing the presentation of data is described. A payment service computing platform may apply a trained artificial intelligence (AI) model to user data associated with users of a payment service, wherein the trained AI model associates a value with each of the users, and wherein the value represents a predicted engagement metric indicating a change in a level of engagement if an individual user of the users is offered an incentive having a particular attribute. The payment service computing platform may generate the incentive having the particular attribute, identify a subset of the users based at least in part on the value, and cause the incentive to be presented via a user interface of a payment application associated with the payment service and executing on a device of a user in the subset.

The invention discloses a cold start strategy optimization method and device in no-service computing, equipment and a medium, and relates to the technical field of cloud computing, and the method comprises the steps: determining a reward function of a target cold start strategy model according to a state space and an action space; predicting the number of times of function calling in a future time period to obtain a prediction result; determining action selection of a target deep reinforcement learning algorithm, and determining a target value based on the action selection and a reward function; determining a comprehensive loss function based on the Q value loss function, the Huber loss function and the target loss function; updating the strategy network by using the action change difference value, obtaining an updated network, optimizing the value network through the comprehensive loss function, obtaining an optimized network, determining a target cold start strategy model through the updated network and the optimized network, and optimizing the cold start strategy without service calculation by using the target cold start strategy model. Therefore, the response speed and the resource utilization efficiency of the system are improved.

The invention relates to the technical field of industrial internet of things and mobile edge computing crossing, in particular to a computing task unloading and service caching collaborative optimization method, which comprises the following steps of: acquiring an IIOT equipment state, channel quality and edge server resources in real time by constructing a dynamic network awareness architecture, and analyzing a task DAG topological structure; designing a service cache delay compensation mechanism, parallelizing a cache process and task execution, predicting future required services based on a task dependency relationship, and calculating a delay compensation factor; a deep reinforcement learning algorithm based on Transform is adopted, and an unloading decision is generated in combination with a hierarchical attention mechanism and an improved DDQN network; tasks are dynamically allocated to the local, the edge or the cloud through a three-level unloading decision tree, task completion time is minimized, a resource constraint modeling and task preemption mechanism is further included, and the system response capability and the resource utilization rate are improved.

The invention discloses a cluster computing resource allocation method. The method supports three resource service forms of a virtual machine, a container cloud and a bare computer. Wherein the virtual machine resources are used for deploying system software with a UI (User Interface) and a C / S (Client / Server) architecture; the container cloud resource is used for deployment of system software of a B / S architecture and operation of a large test sample; the bare computer resources are used for specific function system software, Kafka middleware and / or database deployment; and service computing resource elastic scheduling and control are deployed to realize cluster computing resource allocation. According to the method, multiple resource service forms are flexibly adopted, and virtual cluster management and high-availability design are applied, so that test resource automatic deployment strategy generation and computing resource flexible scheduling and control can be realized, and high-performance, high-reliability, servitization and easy-to-use cluster computing resource allocation and deployment services are provided for users.

The invention relates to a function caching method in edge service-free computing of service deep learning, which comprises the following steps of: (1) selection operation in an edge server: on the basis of a greedy strategy, according to a container state and request information on a current multi-edge server, selecting the edge server; selecting the operation with the minimum delay from the local cold start, forwarding to other servers and bypassing to the cloud server to serve the function request; (2) the multi-edge server function in the step (1) is processed in a function caching mode. According to the method designed by the invention, a function caching strategy method can be optimized, so that the total delay of all requests is minimized, and the edge no-service computing performance oriented to deep learning is improved.

The invention discloses a computing power resource evaluation scheduling method, system and device and a medium, and the method comprises the steps: obtaining business computing power demand data, a demand business type of the business computing power demand data, and processing computing power information, network computing power information, memory computing power information and storage computing power information of a data center; according to the demand service type, a center weight set is obtained, and the center weight set comprises a target processing weight, a target network weight, a target memory weight and a target storage weight; according to the target processing weight, the target network weight, the target memory weight and the target storage weight, performing resource evaluation on the processing computing power information, the network computing power information, the memory computing power information and the storage computing power information to obtain resource evaluation information; and according to the resource evaluation information, carrying out computing power scheduling distribution on the business computing power demand data. The method can effectively improve the accuracy and practicability of computing power resource scheduling. The invention relates to the technical field of data center operation and maintenance.

There is provided a computer implemented method of managing access for user account, comprising: accessing a graph mapping a plurality of nodes denoting real users to a plurality of user accounts and a plurality of resources hosted by a plurality of service computing environments external to a target computing environment accessed by the user accounts, and defining different permissions for user accounts for accessing the different resources, receiving a query for identifying user accounts for a target user, executing the query on the graph, and providing details regarding user accounts of the target users from the execution of the query on the graph, the details including at least one of: identifiers of the user accounts, resources accessible to the user accounts, access privileges for accessing the resources.

A method that includes a service computing system generating a virtual meeting space within a virtual environment and the service computing system receiving from a first party computing system a first party entrance request of a first party to enter into the virtual meeting space. The method further includes the service computing system comparing the first party identifier to a recorded first party identifier and, based on the first party identifier matching the recorded first party identifier, authorizing the first party into the virtual meeting space. The method further includes, in response to authorizing the first party into the virtual meeting space, the service computing system projecting information on a virtual display screen within the virtual meeting space. The method further includes the service computing system recording input from the first party within the virtual meeting space into an artifact and tokenizing at least a portion of the artifact.

The invention provides a data processing method, a data processing device, a computer storage medium and electronic equipment, and relates to the technical field of communication. The method comprises the following steps: in response to receiving a service request sent by user equipment for a target service, performing demand analysis on the service request based on a session management function (SMF) network element to obtain a service type demand of the target service; the SMF network element determines a to-be-coordinated network element based on the service type demand; a to-be-coordinated network element receives a service request and a service quality demand parameter corresponding to a target service, and obtains a node state parameter of an initial computing node matched with the to-be-coordinated network element, thereby determining a target computing node from the initial computing node based on the service request, the node state parameter and the service quality demand parameter, and sending the target computing node to the to-be-coordinated network element. And providing services for the target business based on the target computing node. According to the invention, multi-element cooperation of communication, calculation, intelligence and the like can be realized, and then integrated fusion services of communication services, calculation services, intelligent services and the like are provided for users.

The invention discloses a task scheduling method and system based on a heterogeneous pulse neural network on a GPU (Graphics Processing Unit), which are used for modeling a scheduling problem into a reward maximization task with constraints so as to optimize resource allocation and parameter adjustment. According to the priority-based multi-preemptive scheduling framework provided by the invention, the heterogeneous SNN tasks on the GPU are dynamically managed by adopting dynamic priority calculation, a self-adaptive time segmentation mechanism and an overhead perception optimization strategy. The effectiveness of the method is verified through a large number of simulation experiments, and the performance under different complexity proportions, arrival modes, load levels and time slice configurations is tested. Results show that the priority-based multi-preemptive scheduling framework provided by the invention is superior to the existing scheduling algorithm in the aspects of energy efficiency, throughput and resource utilization rate. The work promotes the practical application of the SNN workload in a service computing environment, and promotes the development of a more efficient and extensible neuromorphic computing solution.

The invention discloses a space science data collaborative computing method and system based on a no-service computing architecture. According to the method, the technical problems that in traditional space science data processing, resource elasticity is insufficient, multidisciplinary cross-domain heterogeneous computing environment collaboration is difficult and data islands are serious are solved by constructing a whole-process and service-free computing framework of data access-function encapsulation-collaborative scheduling-result aggregation. Specifically, tasks such as preprocessing, analysis and modeling of space science data are packaged into a lightweight and non-service calculation function, data calculation collaborative calling in the interdisciplinary field is achieved in combination with a multi-calculation-node permission management mechanism, and calculation resources are distributed according to needs through a dynamic resource scheduling algorithm. The multi-disciplinary cross-domain TB / PB-level spatial data processing method has the advantages of being high in resource utilization rate, low in operation and maintenance cost and high in expansibility, and can be widely applied to space science research scenes such as sun-earth space physics, deep space exploration and high-energy celestial body outbreak.

The embodiment of the invention provides a data processing system, method and device. The data processing system comprises at least one terminal device, a fog service platform and a cloud service platform. Each terminal device is configured to establish a communication connection with the fog service platform and send information of each terminal device to the fog service platform based on the communication connection; the fog service platform is configured to receive the terminal equipment information corresponding to the terminal equipment, process the terminal equipment information based on the fog service business request, generate fog computing processing results, and send the terminal equipment information and the fog computing processing results to the cloud service platform; and the cloud service platform is configured to receive the information of each terminal device and each fog computing processing result sent by the fog service platform, and process the information of each terminal device and the information of each aggregated terminal device according to the cloud service business request. By adding the fog service platform in the data processing system, high-availability, high-performance and low-delay fog service calculation is provided, the cost is reduced, and the deployment period is shortened.

A messaging system is provided to communicate messages between computing devices. The computing devices can include vehicles and service computers. The messaging system includes nodes and virtual entities that may forward messages between computing devices. The messaging system may be a publish-subscribe system. The messaging system may allocate a allocating virtual entities that are associated with the computing devices. The virtual entity may be endpoints for the messages.

The embodiment of the invention relates to the technical field of communication, and discloses a response method and system, electronic equipment and a storage medium. The method is applied to a CDN edge node, and comprises the following steps: receiving a sent first request; triggering local execution of at least one first service sub-logic according to a first event in the process of responding to the first request; and remotely executing at least one second service sub-logic according to the execution of the at least one first service sub-logic, the second service sub-logic being SaaS service logic. At least more complex CDN service customization based on non-service calculation can be supported on the CDN edge node, so that the CDN service customization requirement can be better met.

The application discloses an implementation method, system and device of a serverless computing platform and a storage medium, belongs to the technical field of Internet, and solves the technical problem that the existing serverless computing solution cannot meet the needs. The method is: initializing various components of the serverless computing platform, including a front-end service, a back-end service, an online coding integrated development environment, a construction tool, a container scheduling component, a gateway service, a code repository and a container image repository that need to be called; creating a new serverless computing function on the interface of the front-end service and deploying the serverless computing function into a Kubernetes cluster to meet different development needs. The serverless computing platform built by the Kubernetes cluster can significantly improve resource utilization, optimize the scheduling and resource configuration of the serverless computing function, and conveniently apply the perfect monitoring function of the Kubernetes platform. When starting the serverless computing function, the user does not need to write Kubernetes YAML, thereby reducing the learning cost and difficulty.