1109 results about "Scalability" patented technology

The invention discloses a data analysis method and device based on multi-agent cooperation and a storage medium. The method comprises the following steps: receiving a natural language request by a workflow arrangement agent, and generating an execution plan comprising a plurality of subtasks and corresponding task processing units by consulting a data exploration agent and a data engine understanding agent; in the execution stage, the professional agent matched with the subtask converts the subtask into an executable instruction, and the data engine dispatch agent calls and coordinates the corresponding task processing unit to execute the instruction. According to the method, through a layered collaborative architecture, the separation of planning, translation and execution is realized, and the automation level, modularization and expandability of data analysis are remarkably improved.

The invention discloses a TSN scheduling optimization method and device based on flow sensing autonomous learning, equipment and a medium. The method comprises the following steps: deploying a lightweight flow detection module in a switch or a router, and after a controller receives a data request, automatically identifying a newly arrived unknown service flow by using the lightweight flow detection module, and judging whether the newly arrived unknown service flow is a periodic TT flow or an unpredictable burst flow; the controller performs classification management on the identified service flow types, collects topological information and flow requirements of the whole network and issues the topological information and the flow requirements to the terminal nodes through a network management interface; the controller constructs an intelligent queue scheduling task based on the collected network topology information and traffic demand and converts the task into a Markov decision process MDP, network resources, queue states and priorities are used as a state space, a scheduling strategy is used as an action space, a reward function is designed in combination with throughput and delay indexes, and an intelligent queue scheduling task is obtained. Driving a dynamic environment through real-time data and training a DRL model; an enhanced queue scheduling mechanism Pro-CQF is adopted, different priority labels are configured according to classified flow types, and then mixed flow scheduling is carried out; the controller periodically collects time delay, packet loss rate and end-to-end transmission delay indexes and feeds back the indexes to the DRL model, and a scheduling strategy is updated online. According to the method, the traffic sensing and scheduling efficiency is greatly improved in a network environment in which multiple service flows coexist and end-side equipment functions are different, and the reliability and the expandability of the TSN in industrial Internet of Things, edge computing and other high-real-time application scenes are remarkably enhanced.

The various embodiments herein provide a system and method for networked digital twins with autonomous collaborative decision-making. The system comprises a Digital Twin Engine for real-time data acquisition, model synthesis, and simulation, an AI Module for advanced data analysis, an autonomous collaborative decision-making module for optimized decision-making, a communication layer for secure data exchange, and supporting modules for coordination, storage, security, and user interaction. The method for generating and deploying digital twins comprises data collection, transmission, preprocessing, model synthesis, simulation, validation, and deployment. The method for networking and collaboration comprises AI-based data processing, complex event processing, autonomous decision-making, task distribution, decision communication, real-time monitoring, and continuous improvement. This system enhances operational efficiency, scalability, and security, reducing the need for human intervention and providing a comprehensive management solution for complex systems.

The invention relates to the technical field of information security, in particular to a security baseline setting method and system equipment based on clustering decision and a medium, and the method comprises the steps: collecting original data, carrying out the construction of a feature vector through feature conversion, generating a sample, and marking and extracting the sample; constructing a classification model by using manifold learning, inputting the extracted feature vectors into the constructed classification model, optimizing the model through training, and outputting classification labels; processing the decision boundary by using constraint optimization and feature scaling to obtain a standardized feature vector converted by a decision boundary model, grouping based on the standardized feature vector, and extracting a baseline; the security policy is generated through data analysis, and the data is dynamically updated and continuously monitored, so that the unified configuration and centralized management of the security policy are realized, and the policy implementation efficiency and the system expansibility are remarkably improved.

The invention discloses a distribution line load prediction and optimal scheduling method and system, and relates to the technical field of intelligent scheduling of power systems, and the method comprises the steps: generating a time-aligned multi-source fusion input data set; constructing a mixed time sequence load prediction model, and introducing a weighted quantile loss function in a model training process; constructing a joint probability distribution model of the renewable energy output and demand response participation rate, and sampling joint probability distribution; constructing a rolling time domain power distribution network optimization scheduling model; a two-layer mixed strategy is adopted to deal with uncertainty, an optimization problem is decomposed into a plurality of sub-problems, and an alternating direction multiplier method with adaptive penalty parameters is used for distributed solution. According to the method, a multi-objective optimization scheduling model is established in a rolling time domain, and dynamic closed-loop optimization is realized; and by introducing a two-layer hybrid solving strategy and an ADMM distributed algorithm with an adaptive penalty parameter, the calculation efficiency and expandability are remarkably improved while the global consistency is ensured.

The invention relates to a water-light storage area power grid optimization method based on federated and layered multi-agent reinforcement learning. The method comprises the steps of constructing a federated and layered multi-agent model, defining states, actions and reward spaces of layered agents, implementing federated reinforcement learning offline training with privacy enhancement, deploying the model and executing online distributed optimization. Through the federal learning framework, it is ensured that private data of all the energy main bodies are locally calculated, the privacy leakage risk caused by data collection in a traditional centralized method is avoided, and a technical basis is provided for building collaborative trust among multiple main bodies. Meanwhile, the designed hierarchical intelligent agent architecture decouples a complex power grid system into subproblems with clear hierarchies, and when the scale of the system is expanded, new energy units can be accessed in a modular mode, so that the overall maintenance and upgrading difficulty of the system is reduced, and the expandability of the system is improved.

A modular system designed for privacy-preserving content recognition and supplemental content delivery across web and mobile environments. The system employs lightweight character sampling and vision-based recognition to generate unique content fingerprints without storing or replicating original data. It features a hybrid processing architecture, using local computing resources for intensive tasks while optimizing performance on resource-constrained devices. Core functionalities include multi-method content fingerprinting, real-time monitoring with adaptive sampling, and secure supplemental content association. Operating entirely on the client-side, it complies with website terms of service and privacy regulations. Advanced features include AI-driven content recognition, blockchain-based verification, and granular content targeting through resizable selection interfaces. This technology enables seamless delivery of supplemental content while preserving privacy, reducing resource usage, and ensuring scalability across browsers, mobile applications, and edge devices. It is particularly applicable in industries such as education, retail, and secure data sharing.

The invention relates to a computer technology, discloses a marine monitoring data real-time processing method and system based on edge computing, and solves the problems that an existing marine monitoring system is insufficient in real-time performance, too heavy in communication load, poor in toughness and limited in expansibility. According to the invention, data processing, analysis and decision making are deployed in the edge intelligent unit, original data are collected and preprocessed through the edge monitoring unit, and real-time analysis and local response are carried out; selective communication with a cloud platform is carried out, and global decision and model optimization deployment are carried out by cloud aggregation data. According to the scheme, the real-time response can be improved, the communication load can be reduced, the system toughness can be enhanced, the processing efficiency and energy can be optimized, and the monitoring precision and expandability can be improved.

The invention provides a system and method for managing the lifecycle of machine learning models, from development to deployment and ongoing operation, across various environments including on-premises, cloud, and hybrid infrastructures. The system features a model build platform for data processing, feature generation, model development, training, and hyperparameter tuning. A model analytics engine extracts metadata, performs complexity analysis, and generates configuration files specifying environment settings and resource needs. A secure model repository enables version-controlled storage, while a deployment platform retrieves, validates, and deploys models in containerized environments like OpenShift or Kubernetes. The platform dynamically allocates resources, supports real-time and batch scoring, and monitors model performance with guardrails. Customizable agents provide real-time feedback and automated optimization, and the system can securely decommission models while maintaining detailed lifecycle records. The invention enhances the efficiency, security, and scalability of machine learning operations with continuous performance improvement and compliance automation.

The invention provides a pollution site multi-medium restoration intelligent decision-making system based on a large language model, which comprises a multi-source data input and standardization module, a site feature analysis module, a large language model knowledge inference engine, a dynamic matrix scoring system and a restoration scheme optimization and decision-making module, a set of full-process intelligent decision-making framework is constructed by integrating a large language model and professional knowledge in the environmental field, and intelligent matching, automatic scheme generation and optimization decision-making of a polluted site remediation technology are realized. The method is suitable for a plurality of complex pollution treatment scenes, and has good expandability, cross-domain adaptability and interpretability.

The invention provides a processing method, system and device for expanding an OpenResty request based on a WASM plug-in and a medium, and belongs to the fields of network communication, application gateways and the like, and the method specifically comprises the steps that in the starting stage of an OpenResty working process, a WASM running environment supporting a WASI interface is initialized and embedded; the method comprises the following steps: dividing execution stages of an OpenResty request processing flow, and setting a hook point in each stage; a WebAssessment plug-in module is called, and the WebAssessment plug Executing access control, security detection or request filtering processing according to the input data, and generating a processing result containing an allowing, intercepting or modifying instruction; and the plug-in management module judges whether to continue to execute a subsequent OpenResty processing flow or not according to the received processing result, and supports hot updating or unloading operation on the WebAssembly plug-in module when the configuration is changed. By introducing a WASM plug-in mechanism, the OpenResty is endowed with higher expandability and flexibility in the aspects of flow processing, access control, security detection and the like.

The invention discloses an electric energy data processing method, system and device based on a DSP and multi-thread parallel computing and a medium, and belongs to the technical field of electric energy data processing.The method comprises the steps that multi-source operation data is collected, a structured data set is constructed and written into a buffer structure, and a channel thread binding structure is generated; when the running state changes, activating the processing threads of each bound channel according to the channel thread binding structure to form a thread set; and extracting data from the current binding channel, generating a channel processing result, carrying out unified correction on a time label, constructing a state data matrix with a unified format, inputting the state data matrix into a preset evaluation model, executing operation state identification, and calculating an output result. According to the method, high-speed processing, time consistency fusion and intelligent risk identification of multi-source heterogeneous electric energy data are realized, and the method has high real-time performance and strong expansibility and is suitable for scenes such as dynamic monitoring of a power grid.

The invention relates to a micro-service architecture system based on business function and data double isolation, and the system comprises a business function splitting module which splits a single application into independent micro-services; the data physical isolation module is used for distributing an independent database instance for each micro-service; the dynamic routing control module is used for dynamically distributing flow through a load sensing strategy and integrating a fusing mechanism; and the gray release module supports flow hierarchical diversion and abnormal automatic rollback, and ensures safe switching of service versions. According to the invention, by realizing double isolation of service functions and data, the independence and the expandability of the system are improved, and the data coupling degree and the maintenance cost are reduced; the stability and reliability of the system are ensured, and the risk in the migration process is reduced; according to the method, rapid iteration and continuous delivery can be realized, the development and deployment period of new functions is accelerated, and the user experience is improved through efficient service governance and data consistency guarantee, so that the system can better cope with challenges of high concurrent access and distributed transaction processing.

The invention belongs to the technical field of mobile edge computing, and discloses a task scheduling method based on dynamic cloud edge collaboration. According to the invention, through link-level modeling and graph neural network feature extraction, adaptive expansion of different numbers of terminals and servers is realized; according to the method, the problems of instability and over-estimation in training are effectively avoided by combining cutting updating of a near-end strategy optimization algorithm and a generalized advantage estimation method. According to the method, the elastic computing power of the cloud and the edge low-delay characteristic can be fully utilized, the dynamically changing network scale and terminal requirements can be adapted, flexible unloading of tasks and dynamic resource allocation can be realized, task processing delay can be effectively reduced in a dynamic environment, the resource utilization rate is improved, and the resource utilization rate is increased. And good expansibility and stability are maintained under the condition that the number of terminals and the scale of the server fluctuate, the problems of computing resource bottleneck and task scheduling stiffness existing in the virtual reality video service of the existing mobile edge computing are solved, and the interaction experience of the user is remarkably improved.

The invention discloses an interface design and implementation method of a BMC (Baseboard Management Controller) remote management system based on Redfish. According to the method, a multi-module resource model conforming to Redfish specifications is constructed in a baseboard management controller (BMC), management modules including Systems, Chassis, Managers, Account Service, Session Service, TaskService, Update Service, FRU and the like are integrated, and a unified RESTful interface architecture is formed. The method supports standardized access to management functions such as a server system state, hardware assets, a user account, remote control and firmware upgrading, and meanwhile, a unified authentication mechanism and an asynchronous task mechanism are introduced, so that an efficient and safe out-of-band management process is realized. The system has the advantages of uniform interface, clear structure, safety, controllability, high expandability and the like, and is suitable for various data center and server remote management scenes.

The invention discloses a two-stage multi-dimensional fusion retrieval enhancement generation method and system, and belongs to the field of large model language processing. Comprising the following steps: dual-stage mixed retrieval: performing BM25 retrieval and vector retrieval in parallel and performing dynamic weighted fusion to realize file-level rough selection and content-level fine selection so as to give consideration to literal matching and semantic understanding; performing intelligent content integrity judgment: performing three-dimensional evaluation on a retrieval result by utilizing a lightweight language model, and triggering supplementary retrieval when information is insufficient; and multi-source information fusion generation: fusing multi-source information by adopting a model based on an attention mechanism, and driving a large language model to generate accurate and traceable answers. The method is also matched with a continuous training optimization method of a small model and an efficient system management architecture based on an asynchronous queue. According to the method, the accuracy and the integrity of the answers are remarkably improved, the retrieval efficiency and the expandability of the system are improved, and the calculation cost is effectively reduced.

The invention discloses a hard disk access method of a hard disk backboard, a substrate management controller, a server and a storage medium, and relates to the technical field of server hardware management, and the method comprises the following steps: accessing a register of a programmable logic device with a first preset fixed address in a target hard disk backboard, and obtaining topological information of the target hard disk backboard; determining a target hard disk adaptation type of the target hard disk backboard from a plurality of hard disk adaptation types based on the NVME support state of each port contained in the topological information; and accessing the in-place target hard disk based on the access strategy information matched with the target hard disk adaptation type. The problem of high coupling of the BMC code and the hard disk backboard adaptation type is effectively solved, and the flexibility and expandability of server hardware adaptation are improved.

The application provides a Windows three-dimensional cloud rendering system, method and device, relates to the technical field of cloud computing, and the system comprises a model data acquisition unit which judges whether a corresponding historical rendering model is stored in a cloud server; three-dimensional model data to be rendered and rendering parameters corresponding to the three-dimensional model data are acquired according to a judgment result; a load balancing unit dynamically distributes according to the node state of a service node, and distributes rendering tasks to a plurality of rendering nodes; a task scheduling unit constructs a cloud rendering node cluster according to all the rendering nodes; rendering tools are deployed according to the cloud rendering node cluster, and local resources are called; and a rendering unit utilizes the rendering tools and the local resources to perform rendering according to the rendering parameters. The application performs task acquisition, load balancing, resource scheduling and rendering execution through various units, enhances the reliability and scalability of the system, and improves the cloud rendering efficiency of Windows.

Along with continuous development of technologies such as deep learning and natural language processing, the AI model shows powerful capabilities in the aspects of understanding user intentions, processing complex information, realizing accurate matching and the like. The large star model is a large AI model which is developed by China Telecom and is based on an advanced Transform architecture. The Transformer architecture obtains significant results in the fields of natural language processing, image recognition and the like due to good expandability and strong performance of the Transformer architecture. When the method is applied to a customer service scene, the large star model can deeply understand the appeal of the user. Through natural language processing and semantic understanding technologies, the model can accurately identify and analyze questions of a user and quickly give corresponding answers or suggestions. In addition, the large star model also has strong copywriting generation ability and knowledge question-answering ability, can provide personalized exchange recommendation and shopping preferential information for the user, and further improves the user experience.

The invention discloses an intelligent operation and maintenance method and system for a rail transit communication machine room based on digital twinning, and belongs to the technical field of digital twinning and three-dimensional visualization of a rail transit system. An intelligent operation and maintenance server side in the system comprises a data acquisition module, a three-dimensional modeling module, a digital twinning engine module and a database module; the intelligent operation and maintenance client comprises a dynamic loading scheduling module, a real-time data binding module and a visual interaction module; according to the system, a lightweight Web3D engine is adopted to dynamically load and render a three-dimensional model of a communication machine room as required, and real-time sensing, data synchronization, fault warning and remote operation and maintenance of the operation state of communication equipment are realized in combination with a digital twinning technology. According to the method, the functions of hierarchical loading of a multi-level model, alarm driving state rendering, operation and maintenance closed-loop management and the like can be realized. Compared with the prior art, the method has the advantages of light model weight, quick response, easiness in deployment, high expandability and the like, and is widely applicable to communication infrastructure operation and maintenance scenes in the field of rail transit.

The invention discloses an intelligent agent memory management method and system. According to the method, deep semantic organization of memory content is realized by defining a structured memory unit containing ternary metadata formed by a multi-label set, a multi-dimensional attribute set and a multi-level path; and receiving and processing a memory operation from any trigger event through a unified memory management framework. According to the method, the problems of low retrieval precision, poor data isolation between instances and tight coupling with service logic caused by flattening of a memory structure of an existing agent system are effectively solved, and the performance, the safety and the expandability of the agent system in enterprise-level application are remarkably improved.

The invention discloses a business document design and user-defined field modeling method supporting dynamic expansion. The method relates to the technical field of custom field modeling, and comprises the following steps: constructing a core foundation and a metadata system; a non-intrusive expansion and data association model; performing high-performance query and index optimization; and performing dynamic verification and visual application. Structural stability and flexible expansion are realized through separate design of the core table and the expansion table, field definition, storage, verification and form rendering are driven by metadata, complex query and cross-receipt field multiplexing are supported, data consistency and full-link connection are guaranteed, business receipt design and self-defined field modeling expandability are improved, and the method is suitable for large-scale popularization and application. The problem of low expandability of business document design and custom field modeling in the prior art is solved.

In order to solve the problems of insufficient compatibility, low compiling efficiency, weak management capability, limited expansibility and the like due to the fact that existing satellite information processing technologies are mostly designed for single satellites or satellites of the same type, the invention provides a differentiated information compiling management system and management method suitable for batch satellite clusters. Belongs to the technical field of satellite information processing and management. The system takes the ground management subsystem as a management control center; the on-satellite management subsystem is used for receiving and executing instructions and management contents from the ground management subsystem; the full-life-cycle standardization process is used for defining collaborative specifications of the ground management subsystem and the satellite-borne management subsystem in each stage of software from development, testing, issuing, on-orbit updating to decommissioning; wherein the ground management subsystem and the satellite-borne management subsystem cooperate through a whole life cycle standardized process to form a space-ground cooperative, autonomous and controllable closed-loop management ecology. The method is suitable for on-orbit management of large-scale different types of constellation satellite software.

The invention discloses a method for guaranteeing data integrity and traceability of a heterogeneous model. The method aims at solving the problems that multi-source heterogeneous data integration is poor in safety, whole-process traceability is difficult, and automation adaptation is insufficient. Comprising the following steps: S1, collecting multi-source data from different models, systems or platforms; s2, performing format standardization processing on the multi-source data to realize data compatibility and integration; s3, generating a security data unit through a Hash algorithm and a digital signature; s4, verifying a hash value and a signature in each link, and automatically detecting a tampering risk; s5, writing the operation record and the hash value into a block chain or a distributed account book, and constructing a chain type traceability structure; s6, identifying and generating an adaptation rule by using an automatic rule engine; and S7, automatically distributing data integrity protection and traceability strategies, and applying the data integrity protection and traceability strategies to each data processing module. According to the method, full-life-cycle safety management of heterogeneous data can be realized, and data integrity, traceability and system expansibility are improved.

The invention is suitable for the field of computer system structures, and provides a multi-core consistency dynamic synchronization method and system based on an RISC-V. The method comprises the steps that the core of a multi-core processor is spatially divided into n consistency domains, each consistency domain is configured with an independent area directory cache and an independent RCC, and transactions in the area are locally processed by the corresponding RCC; when a core in the consistency domain initiates a data operation request, the RCC to which the core belongs checks the state of target data in the consistency domain; according to the data state, the RCC carries out internal synchronization in the consistency domain by adopting an optimized broadcast protocol, or carries out directory type point-to-point communication with other consistency domains through the GDSA to realize cross-domain synchronization; on the premise of ensuring strict consistency, communication delay and energy consumption are remarkably reduced, the overall throughput and expandability of the system are improved, and an efficient consistency solution idea is provided for the RISC-V multi-core processor.

The invention discloses a flexible AC / DC hybrid power distribution network fault recovery optimization method and system based on multi-agent deep reinforcement learning, a computer device and a non-transient computer readable storage medium, and the method comprises the steps: firstly constructing an AC / DC power distribution network model considering the operation characteristics of a flexible switch and a voltage source converter; then, flexible equipment is modeled as an independent agent, a multi-agent training architecture is established, a composite reward function fusing a load recovery rate, voltage stability and operation safety is designed, and a mechanism combining centralized training and distributed execution is adopted to realize multi-point cooperative control between the flexible equipment; and finally, designing a recovery optimization process for rapid decision and control execution after the fault. The method can realize higher load recovery rate and better voltage control performance in various fault scenes, has the advantages of strong decision real-time performance, good system expandability, strong strategy generalization ability and the like, and is suitable for autonomous recovery and intelligent regulation and control of the novel flexible AC / DC hybrid power distribution network.

The invention provides a vehicle path planning method and system based on a dynamic attention model, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining instance data containing warehouse nodes, client nodes and vehicle capacity information; a dynamic encoder-decoder architecture model is constructed, and an encoder recalculates feature embedding of unaccessed nodes every time a vehicle returns to a warehouse based on a graph attention network so as to respond to dynamic changes of instance states in the path construction process; the decoder selects a next node to be accessed according to the current path state, residual node embedding and vehicle real-time capacity; a REINFORCE algorithm is adopted to take the minimum path length as a target training model, and a greedy strategy baseline is introduced to reduce variance; and finally, the initial path is optimized by combining the local search of the 2OPT, and a final planning scheme is output. According to the method, the problem that a traditional attention model cannot adapt to a dynamic environment due to fixed node embedding is effectively solved, the total cost of a path is reduced, and good generalization and expandability are achieved.

The invention belongs to the technical field related to a power system, and provides a conversion and regional splitting method and system of a general power grid model in order to solve the problems that the flexibility and expansibility of an existing general power grid model are limited and the like. Converting power grid model data which originally depends on a specific platform and is stored in an unstructured text form into structured data which can be directly recognized by a program; performing conversion according to different types of power grid equipment model structures or parameter storage between the general power grid model and the target format platform; and on the basis of the converted target power grid model, identifying a target region by using a breadth-first search algorithm, performing equivalent processing on a direct current boundary, and eliminating a non-target region, thereby realizing accurate construction of a region simulation model. Each power grid model has complete electrical topology logic and reasonable parameter configuration, and an effective scene is provided for subsequent simulation analysis and engineering application.

The invention discloses a vulnerability intelligent collaborative detection method and system based on multi-agent reinforcement learning. The method comprises the following steps: independently executing detection according to local observation information and a strategy generation model through an intelligent agent deployed at an edge node; the strategy generation model is constructed based on a decentralized partial observable Markov decision process, and is obtained through cloud centralized training and global shared reward function optimization. When the agent obtains a forward reward, packaging a corresponding vulnerability context and related strategy parameters into an experience package; and the experience packet is diffused in the cooperative detection network in a mode of randomly selecting neighbor nodes and forwarding step by step. And after each agent receives the data, analyzing the content of the experience package and comparing the content with the local environment so as to dynamically adjust local strategy parameters and realize collaborative optimization. According to the vulnerability intelligent collaborative detection method and system based on multi-agent reinforcement learning provided by the invention, the problems that network security vulnerability detection is poor in expandability and lacks knowledge generalization ability are solved.

An RDMA queue pair multiplexing method based on a shared memory efficiently maps a large number of logical queue pairs (LQPs) to a small number of physical queue pairs (PQPs), and combines shared memory zero-copy communication and O (1) active queue management, so that ten thousand-level LQPs are supported by a small number of PQPs, the overhead of a single-connection memory is reduced by about 60%-64%, and context jitter of a network interface card (NIC) is avoided; the connection establishment time delay and the short flow end-to-end time delay are greatly reduced; through O (1) active tracking and batch processing, CPU idling and system calling overhead are greatly reduced, and high throughput and expandability are achieved; the method can be implemented in a pure user mode, a kernel or NIC does not need to be modified, and the method can be immediately deployed in an existing RDMA environment.