9768results about "Program initiation/switching" patented technology

A coherent, intelligent, packet-switched memory fabric enables predictive, cache-coherent access across distributed compute, accelerator, and memory resources using a Memory-Fabric Transaction Layer Protocol (MF-TLP). MF-TLP defines routable packet formats for read, write, vectorized, atomic, reduction, collective, and predictive-prefetch transactions executed by memory-centric network interface controllers (MC-NICs). Each MC-NIC performs packet parsing, address translation, coherence management, and near-memory arithmetic or tensor operations while coordinating with MF-TLP-aware switches providing hierarchical directory control, multi-path routing, and in-network aggregation. Vectorized and multimodal packets encode multiple addresses or tensor offsets to reduce scatter / gather overhead, and programmable caching and quality-of-service modules manage tiered memory and tenant fairness. MF-TLP supports extension headers for predictive prefetch, collective coordination, and tenant governance, operating across hierarchical leaf-spine topologies using Ultra-Ethernet Transport, InfiniBand, or CXL fabrics. The system delivers scalable, low-latency, memory-centric orchestration for large-language-model training, multimodal AI, and data-intensive analytics.

The invention relates to the technical field of computing power scheduling, and discloses a heterogeneous resource computing power intelligent scheduling method and system. According to the method, real-time state monitoring is conducted on heterogeneous computing resources, and resource state parameters such as the computing unit utilization rate and the memory occupancy rate are obtained; task attributes and user request parameters of the task queue are collected, historical task data are processed based on the genetic algorithm optimization model to execute task demand prediction, and predicted demand parameters are generated. A dependency graph containing resource unit nodes and communication link roadsides is constructed through a resource topology analysis tool, predicted demand parameters are input into a scheduling priority classifier trained by a graph neural network, and an actual scheduling priority is identified. And executing resource conflict prediction based on the priority, inputting task feature vectors into a conflict resolution module of a fuzzy logic decision maker, outputting actual conflict resolution parameters, and finally integrating to generate a scheduling scheme containing a resource allocation sequence and an execution time table.

The invention discloses a computing power scheduling method and system based on dynamic load prediction and resource priority ranking. The computing power scheduling method comprises the following steps: collecting historical load data, task submission data and resource state data of each node in a computing power cluster; on the basis of the preprocessed multi-dimensional load feature data set, constructing an improved hybrid prediction model, optimizing model parameters through training, and predicting the load change trend of each computing power node in a future preset time period by using the trained model to obtain a node load prediction result; extracting a service level protocol parameter, a resource demand type and historical execution efficiency data of a to-be-scheduled task, and establishing a multi-dimensional resource priority evaluation index system; according to the computing power scheduling method, the problems of low resource utilization rate and high task response delay caused by low load prediction precision and mismatching of resource allocation and task priority in a traditional computing power scheduling method are solved, and the overall operation efficiency and service quality of a computing power cluster are improved.

The invention relates to the technical field of artificial intelligence, can be applied to service scenes such as pension service, financial science and technology and medical health, and discloses a multi-agent cooperative task processing method, device and equipment and a medium, and the method comprises the steps: obtaining a task instruction, analyzing a core target, and decomposing the core target into a plurality of subtasks; obtaining environment information, dividing task areas, and generating a cooperation framework in combination with agent capability and area weight; real-time states of the agents are obtained, and the optimal agents are matched based on the cooperation framework to generate a task allocation table; a task distribution table is issued to control the intelligent agent to execute the task and upload execution information; monitoring an execution process, and performing dynamic adjustment and updating a task allocation table when detecting path conflicts or equipment faults; and after the subtask is completed, obtaining environment completion state data, and comparing the data with a preset standard model for acceptance. According to the method, efficient task decomposition and intelligent distribution are realized by fusing task semantics, environment information and intelligent agent capability, and the cooperation stability is improved by introducing a real-time state perception and self-adaptive mechanism.

The invention belongs to the field of natural language processing, and provides a task complexity driven graph semantic multi-agent collaborative decision-making method and system.The task complexity driven graph semantic multi-agent collaborative decision-making method comprises the steps that a task text is obtained and subjected to semantic coding to obtain a task semantic vector, evaluation is conducted based on the task semantic vector to obtain a complexity vector, and a task complexity score of the complexity vector is calculated; the task semantic vector and the complexity vector are fused to obtain a task representation vector, an agent capability relation graph is constructed, the participation probability of each agent node is obtained according to the task representation vector and the agent capability relation graph, and a dynamic agent combination scheme is formed; and performing task decomposition according to the agent combination scheme, constructing a sub-task dependency graph, scheduling the execution sequence of the sub-tasks through topological sorting, realizing cooperative execution of the agents, and generating a task result. According to the method, precise matching and efficient cooperation of the agent combination are realized, and the capability of processing complex tasks and the resource utilization efficiency of the multi-agent system are remarkably improved.

The invention discloses a structured decision-making method based on multi-agent collaborative decision-making and reinforcement learning, and relates to the technical field of natural language processing, knowledge engineering and agent collaboration, and the method comprises the steps: receiving an original rule document, analyzing the document type, complexity and constraint conditions, and defining a task target and a success standard; and according to the task target, matching and scheduling the intelligent agent from the registered intelligent agent library, and further analyzing the capacity configuration of the intelligent agent for standby. Through the multi-agent cooperation and reinforcement learning technology, full-process automation of rule documents from input to structured analysis is realized, document types, complexity evaluation and constraint condition analysis can be automatically identified, and a clear task target and a success standard are generated; and the large language model generates a structured workflow according to task requirements and agent capabilities, so that the performability is ensured through logic verification, manual intervention is greatly reduced, and the processing efficiency and the system intelligence degree are improved.

The invention relates to the technical field of information management, in particular to an information scheduling scenarized service agent system. The system comprises an information scheduling acquisition and analysis module, a scene classification and service matching module, a service scheme instruction generation module and a service intelligent execution module, user behavior data, environment perception data and business system data corresponding to information scheduling can be obtained, and an original information set is generated; the original information set is preprocessed, an information scheduling scene classifier is constructed, the service matching degree is calculated in combination with the real-time service resource state, and a candidate service scheme set is generated; performing optimization sorting on the candidate service scheme set to generate an optimal service scheme, and disassembling the optimal service scheme into an executable service instruction sequence; receiving a service instruction sequence and generating a service evaluation report; and if the display does not reach the preset service quality threshold value, triggering a dynamic adjustment mechanism to realize self-iteration upgrading of the information scheduling scenarized service. According to the invention, intelligent scheduling and service of information in a complex scene can be realized.

The invention discloses a cross-container application fusion switching method of a swan monk system, which comprises the following steps: a system service layer deploys a container application management service, an application framework layer realizes a proxy application manager, when a container application is started, a container side allocates a shared memory and configures authority, the container manager collects metadata to initiate registration, and the application framework layer realizes a proxy application manager; the container application management service converts a memory handle into a texture handle, allocates a unique identifier and triggers a proxy application manager to generate a proxy application, and the proxy application initializes a Vulkan rendering environment; the container side renders an application interface to a shared memory, the proxy application imports texture and constructs a lightweight Vulkan rendering pipeline, and scaling sampling is carried out to generate a thumbnail of the container application; and when the container application exits, the shared memory is released, the container application management service cleans the shared memory reference, triggers and destroys the proxy application, and recycles the texture resources through the reference counter, so that seamless fusion, low-delay switching and efficient resource utilization of the container application in a native application thumbnail form are realized.

The invention discloses a software multi-agent collaboration method and system based on a large language model, and the method comprises the steps: receiving natural language task description submitted by a user at the same time, carrying out the semantic understanding and intention recognition through a pre-trained large language model center, and generating a structured task element set; based on the structured task element set, the large language model center generates a task dependency graph through multiple rounds of reasoning, and the task dependency graph comprises a plurality of atomic subtasks, logic relations among the tasks and data flow constraints; according to a topological structure and resource demand characteristics of a task dependency graph, a double-layer graph attention network is adopted to dynamically match a professional agent with specific domain capability, and a distributed collaborative network is formed. Through the dynamic graph network scheduling and cross-domain semantic alignment mechanism, the problems that the multi-agent dynamic collaborative adaptation capability is insufficient and cross-domain semantic fusion is difficult are solved.

The invention relates to the technical field of computing power resources, and discloses a flexible allocation monitoring system for computing power resources, which defines a clear resource use boundary for different types of tasks through a container-level QoS strategy of a resource isolation unit, and adjusts resource allocation in real time in combination with a dynamic partition management module, thereby avoiding resource waste in a traditional fixed allocation mode, and improving the resource allocation efficiency. The dynamic preemption unit accurately screens low-priority tasks for resource recovery through a multi-factor decision engine and a preemption cost evaluation algorithm, in 50 concurrent task scenes, the resource preemption response time is shortened to 20-35 ms and is improved by 50%-70% compared with 70-100 ms of Docker / K8s, the blocking duration of high-priority tasks is reduced to 15-25 ms from 80-120 ms, and the core service interruption risk is greatly reduced.

The invention discloses an agent collaborative optimization data center management system based on knowledge graph driving, and relates to the technical field of data center management. The system specifically comprises the following modules: a modeling and entity management module, a cross-regional global scheduling optimization module, an agent game negotiation optimization module, an agent trust management module, a game negotiation conflict identification module, a reasoning evidence management module and a cross-regional consistency verification module. By establishing a complete knowledge graph model, systematic modeling of resource attributes, constraints, historical decisions and strategy preferences is realized, a unified data basis is provided for negotiation among multiple agents, the problem of a suboptimal solution caused by information asymmetry is effectively solved, a hierarchical reasoning mechanism is adopted, and the probability of resource disruption is reduced. In combination with global-region-node three-level reasoning and multi-round game negotiation, recursive optimization from global to local is realized, the reasoning complexity is effectively reduced, and the negotiation efficiency is improved.

The invention relates to the technical field of cloud side end computing, and discloses a cloud side end cooperative computing resource dynamic allocation method based on task-aware migration. The method comprises the following steps: acquiring real-time load characteristics and resource demand characteristics of calculation tasks in a cloud side end system, and dividing task priority queues in combination with task type identifiers; extracting historical execution records of tasks at cloud, edges and terminal nodes, constructing a task execution feature library, and generating a resource demand prediction model in combination with real-time load features; analyzing network transmission time delay characteristics of a cloud end and edge nodes, measuring real-time calculation capability fluctuation data of terminal equipment, and establishing an inter-node resource collaboration degree evaluation matrix; generating an initial migration strategy according to the prediction model and the evaluation matrix, monitoring actual resource occupancy deviation of the task, forming a final decision in combination with a node resource state correction strategy, triggering cross-node migration, and synchronously updating the priority queue and the evaluation matrix.

The invention provides a resource scheduling control method and system for a big data server, and the method comprises the steps: constructing a multi-dimensional resource portrait module, collecting the CPU, memory, network, storage I / O load and task queue length of each node in real time, and predicting a resource demand trend through a time sequence algorithm; extracting characteristics such as calculation intensity, data dependence, memory requirements, network transmission quantity and the like; adjusting the weight coefficients of the resource utilization rate, the task completion time and the energy consumption efficiency according to the system load and the historical effect; establishing a bipartite graph model by taking a resource trend as a node feature and a task vector as an edge feature, and calculating a matching score through graph convolution and a multi-objective optimization function; the scheduling scheme is synchronized by adopting a consistency algorithm; automatic rollback and reallocation are carried out when resources are detected to be insufficient; and optimizing a weight coefficient and a network parameter through reinforcement learning. Through the method, the system resource utilization rate can be improved, the task execution efficiency is improved, the overall scheduling effect stability is improved, and the system fault recovery time is shortened.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a task scheduling execution method, device, equipment and medium based on intention recognition, and the method comprises the steps: fusing an interaction request and a dialogue history library to generate a session context, and carrying out the analysis to obtain an intention recognition result; task planning is carried out based on the intention recognition result and a knowledge base, and a task subitem set and an execution sequence are generated; matching the task subitem set with a resource directory to generate an execution resource list; scheduling the task subitem set by using the execution sequence to generate an ordered task sequence; generating an execution plan in combination with the ordered task sequence and the execution resource list; and triggering execution based on the execution plan, and aggregating output to generate an execution result and a process tracking record. According to the method, automatic connection of session analysis, task planning, resource matching, sequential scheduling and execution triggering is achieved, manual operation splitting among multiple systems is eliminated, and task processing efficiency and execution accuracy are improved.

The invention provides a large model lightweight reasoning deployment method under limited hardware resources, and the method comprises the steps: quantifying the weight importance of a large model through a composite index of gradient sensitivity and activation frequency, and carrying out pruning operation in combination with an improved index weighted moving average strategy, thereby obtaining a structured sparse model; the sparse model is divided into sub-networks by adopting double rules, a routing decision network is trained, and an adaptive feature shunting architecture model is constructed; a multi-precision weight set is generated through a nested quantization technology, quantization bit width is dynamically adjusted, and edge equipment hardware parameters are adapted to complete reasoning environment initialization; after a reasoning request is received, an optimal sub-network is selected based on the trained routing decision network, corresponding weights are loaded in parallel, and a reasoning result is fused and output; and converting a reasoning result format, and dynamically optimizing a scheduling strategy based on a system real-time monitoring index. The method is compatible with a mainstream large model and a hardware platform, and an efficient and universal deployment scheme is provided for end-side AI engineering landing.

The invention provides a privacy calculation dynamic strategy selection method and device based on data sensitivity identification. The method comprises the following steps: acquiring a privacy computing task request, and analyzing to obtain a target data set and a corresponding operation type; performing sensitivity identification on each field in the target data set to obtain a sensitivity level label corresponding to each field; retrieving a candidate privacy protection strategy set from a preset strategy mapping relation; for the candidate privacy protection strategy set, calculating resource consumption parameters and privacy budget occupation parameters of all strategies are evaluated; performing operator-level splitting and arrangement on the privacy computing task to generate a task scheduling plan; and if it is detected that the resource threshold value or the budget threshold value is triggered, re-executing the step of retrieving the candidate privacy protection strategy set to the step of generating the task scheduling plan based on the resource occupation data and the usage measurement data so as to adjust the target privacy protection strategy. According to the application, accurate identification of sensitivity, on-demand switching of privacy protocols and adaptive balance of resources and budget can be realized.

The invention provides a cache management method, a cache management device, a computer storage medium and electronic equipment, and relates to the technical field of computers. The method comprises the steps of receiving a reasoning task request and distributing the reasoning task request to a target storage page; key value cache information of the first round of reasoning task is stored in a hard disk cache, and when the second round of reasoning task is executed, key value cache information generated before the second round of reasoning task is preloaded layer by layer from the hard disk cache; when the last round of reasoning task is received, storing first target key value cache information correspondingly generated by the last round of reasoning task into the matched target physical block; and performing hybrid grouping compression on key cache information and value cache information in the first target key value cache information to obtain second target key value cache information after quantization compression. According to the invention, triple balance of video memory-calculation performance-precision can be realized.

The invention is suitable for the field of GPU management, and provides an intelligent dynamic management method for GPU computing power and a cloud platform, and the method comprises the following steps: collecting task data and GPU state data, and generating a task queue and a resource allocation strategy in combination with a scheduling plug-in; based on the task queue and the GPU real-time load, dynamically adjusting a resource allocation proportion through reinforcement learning to analyze a task dependency relationship and generate a migration plan; optimizing a communication path and adjusting asynchronous transmission delay according to the task dependency relationship and the GPU communication topology, and outputting a synchronous state mark; and monitoring abnormity in combination with the synchronization state and the GPU hardware state, executing thermal migration according to the migration plan, performing video memory recovery, and updating the resource idle list. According to the invention, through algorithm innovation and hardware collaborative optimization, intelligent, dynamic and efficient resource scheduling in the multi-GPU system is realized.

The invention provides a heterogeneous GPU resource management scheduling method, and relates to the technical field of GPU resource allocation, heterogeneous equipment management and unified abstract modeling are carried out, GPU resources of different architectures are registered to a container arrangement platform, and a unified abstract layer is constructed to shield bottom layer hardware differences; gPU cluster optimization management based on a multi-dimensional real-time monitoring and intelligent scheduling strategy is carried out, GPU operation indexes are collected, priorities are dynamically calibrated for tasks, and task performance portraits are constructed; scheduling decision making is carried out through multi-strategy cooperation, and optimal GPU resources are distributed for tasks; carrying out fine-grained resource allocation, carrying out space or time segmentation on the GPU, and dynamically adjusting resource allocation according to a load state; aPI conversion of cross-architecture tasks is realized through a unified runtime library, and task execution data is collected to feed back an optimization scheduling model; automatic detection, isolation and task migration of GPU faults are carried out, and unified monitoring and alarm are provided.

The invention discloses an industrial personal computer and multi-graphics card collaborative parallel computation acceleration system, which relates to the technical field of industrial resource allocation and parallel computation, and comprises a resource monitoring and predicting module, a resource management module and a prediction type resource preparation module, the task splitting and collaborative execution module comprises a task splitting module, a cross-node collaborative module and a collaborative operation engine; the intelligent scheduling and dynamic resource allocation module comprises an intelligent scheduler, a dynamic resource allocation module and a conflict avoidance module. According to the method, the GPU video memory utilization rate, the core utilization rate, the temperature, the video memory fragment rate, the available video memory total amount, the CPU core total utilization rate, the load condition and the idle core number index are collected in real time through a resource monitoring module, and the video memory capacity, the GPU core occupancy rate and the CPU load requirement are predicted in advance before a task is submitted in combination with a gradient boosting decision tree and a neural network prediction model; and resources are reserved, so that the scheduling delay is remarkably reduced, and the scheduling hit rate is improved.

The invention discloses a cloud side-end cooperative task scheduling and efficiency optimization method and system for heterogeneous patrol resources, and relates to the technical field of intelligent scheduling and resource optimization. According to the method, accurate perception of a resource state is realized by constructing a digital twinborn and federated learning mechanism, resource contention conflicts are solved by adopting a space-time diagram attention network and multi-agent reinforcement learning, and multi-target optimization and trusted execution are realized in combination with a quantum genetic algorithm and a block chain smart contract. Finally, the stability of the system is verified through Lyapunov optimization, a complete scheduling system from resource perception and conflict resolution to steady state maintenance is formed, and the task scheduling efficiency and the system stability in the heterogeneous resource environment are remarkably improved.

The invention discloses an energy-efficient task scheduling method for an edge computing system, which comprises the following steps of: acquiring a task state, a computing node resource state, a link state and an energy consumption state according to a unified time slot under a computing power network control domain, and constructing a system state vector; performing priority evaluation on the to-be-scheduled task based on the residual delay budget, the candidate node energy efficiency coefficient and the queue position to obtain a target task set; inputting a system state vector and a target task set into an energy efficiency perception deep reinforcement learning scheduling model, outputting a task-node allocation decision under the constraint of computing node resources and task time delay, and introducing a system-level energy consumption ratio, self-adaptive energy consumption penalty and exploration bias facing high-energy-efficiency nodes into rewards; and scheduling tasks according to the allocation decision, recording state transition and instant rewards, updating a double-commentator and actor network, and performing iterative execution in continuous time slots. According to the method, task success rate, time delay, load balancing and energy-saving performance are considered, and system energy consumption is reduced.

The invention discloses a visual algorithm self-training method based on multi-agent collaborative optimization, and the method comprises the following steps: constructing a multi-agent system architecture which comprises a user interaction layer, an intelligent scheduling layer, an A2A protocol communication layer and a professional agent cluster layer; the user interaction layer analyzes a user task intention and generates an execution plan; the scheduling agent calls the professional agent to complete data processing, model construction, training, testing and deployment; a task process is coordinated through a standardized communication mechanism, and task execution is supported by combining an MCP tool set, a knowledge base module and a memory system; and when the task fails, automatically executing rescheduling operation, and finally outputting a self-training result. According to the method, the development efficiency, the self-adaptability and the intelligent level are remarkably improved, and the method is suitable for computer vision tasks such as industrial detection, intelligent security and protection and automatic driving.

The invention relates to the technical field of automatic data analysis, in particular to an intelligent data report generation method and system based on an MCP protocol. The method comprises the following steps: constructing a semantic intention vector through a context semantic structure according to an obtained natural language instruction of a user; constructing a semantic task path graph based on the semantic intention vector by utilizing a knowledge graph; according to the constructed semantic task path diagram, performing intention path and tool capability mapping based on an MCP protocol; constructing a task flow based on an MCP protocol and performing task scheduling optimization; carrying out data source unified modeling based on the constructed task flow, and generating a stable and controllable calculation task flow; and visual expression generation from data to graphs is realized through an intelligent recommendation and structural modeling mechanism. According to the method, a semantic-driven MCP plug-in tool chain and a chart capability component index are constructed, so that a full-automatic closed loop from a natural language intention to data analysis and chart generation is realized, and meanwhile, the use threshold of non-technical users is reduced.

The invention discloses a full-scene task autonomous execution method and system based on a large model, belongs to the technical field of computer application and artificial intelligence, and aims to solve the technical problems that an existing RPA technology is lack of autonomous thinking ability, and a browser use technology is limited in application range, is greatly influenced by factors such as webpage change and the like, and is poor in reliability. The Computer use technology is inaccurate in operation, high in development difficulty and has security risks, and the technical scheme comprises the following steps: establishing an MCP service, and compiling a task autonomous execution tool set containing various basic operation instructions including software opening, browser starting, precise clicking and information filling; the MCP service is deployed in the Windows virtual machine environment, and stable operation of the service is ensured; constructing a task autonomous execution workflow agent with task understanding, planning and scheduling capabilities; the user inputs a task target through a natural language, and the agent receives and records the specific demand of the user as a target guide for subsequent task generation and execution.

The invention provides a real-time intelligent agent dynamic scheduling method and system composed of multiple large models, and is applied to the technical field of data processing. The method comprises the following steps: performing dynamic scheduling expansion around a plurality of large-model real-time intelligent agents, firstly receiving task request data of a real-time service scene, performing grouping according to task types, priorities and resource requirements, pre-configuring a scheduling strategy, and generating a pre-scheduling queue and resource pre-planning information; and in combination with the target configuration information, scheduling task information after secondary optimization is obtained through multi-dimensional optimization such as task splitting and priority rearrangement. Dynamically adjusting and generating a target scheduling instruction based on real-time system resources and a model operation state, and cooperatively processing the target scheduling instruction with the large model capability adaptation parameters to form scheduling execution information; and finally, issuing to model nodes according to preset service quality requirements and resource constraints, generating information such as adaptive parameters and priority rules through feature extraction, association processing and the like, and supporting multi-model cooperation to efficiently complete real-time service tasks.

The invention relates to the technical field of artificial intelligence, can be applied to business system platforms of financial science and technology, medical treatment and health and the like, and discloses a task processing method, device and equipment based on multi-agent cooperation and a medium. And constructing a sub-task dependency graph, sequentially scheduling and executing the sub-tasks, and performing parameter completion to obtain the completed sub-tasks. And tracking the execution progress and the historical record of the completion subtask through a preset progress agent, and generating an executable operation decision by using a preset decision agent. If the task execution does not reach the expected effect, feeding back difference information and a correction suggestion, adjusting an operation decision and generating an updating operation; if the task achieves the expected effect, task completion information is sent to the progress agent, and the state is updated to be task completion. According to the method, the perception accuracy is improved, a task dependence tracking and feedback correction mechanism is provided, and a cross-application automatic task is successfully realized.

The invention discloses an extended metadata-based cross-running-environment task switching method for a swan monk system, which comprises the following steps of: distributing a DRM container memory in a host machine for sharing of a container application and a task switcher so as to store thumbnail textures, starting a container management module to manage container application metadata, starting an application monitor in a container to monitor texture changes, and starting a task switcher to carry out task switching; through interaction among the container management module, the task switcher and the container, task switching is carried out in a native application mode when the container application is started, switched and quitted, and active response to changes of the container application is achieved through interaction among the container management module, the task switcher and the application monitor.

The invention provides a timed task execution optimization method and system, and aims to solve the problems of inflexible static priority scheduling, unintelligent resource allocation and the like in the prior art. According to the method, a distributed timed task intelligent scheduling framework is constructed and comprises five core components including a task management console, a scheduling decision engine, a resource monitoring agent, a task execution cluster and metadata storage. Task basic information is obtained through task feature extraction, a dynamic priority score is calculated based on decision factors such as SLA urgency, resource matching degree and service weight, and task priority ranking is achieved. And performing intelligent task allocation by adopting a BestFit algorithm, and allocating the task to the optimal execution node. The system monitors the CPU utilization rate, the memory occupation and the IO waiting time of the nodes in real time, and when the CPU utilization rate exceeds 85%, an elastic resource allocation strategy is triggered. And when the task execution time exceeds the pre-estimated duration, performing task splitting and rescheduling based on a dynamic fragmentation algorithm.

The invention relates to the technical field of artificial intelligence, and discloses a multi-agent collaborative data question-answering system and method based on a large model, and the system comprises an agent cluster module which is composed of five special agents, namely a data question-answering agent, a data extraction agent, a data analysis agent, a visualization agent and a quality examination agent, and achieves the task decomposition and collaborative execution through dynamic scheduling; the knowledge management module comprises a business knowledge base, a data element knowledge base and a user feedback base, and adopts a hierarchical knowledge fusion technology to provide domain knowledge support for the intelligent agent; and the supporting function module covers a front-end dialogue component and a verification and execution engine and is responsible for interactive interface rendering and result reliability verification. According to the method, the fine tuning requirement on the large model is remarkably reduced, the illusion of the large model is effectively intercepted through a dual verification mechanism, and the accuracy and reliability of question and answer results are improved.