400 results about "Task analysis" patented technology

The invention discloses an automatic code generation and optimization system based on multiple modes, which relates to the technical field of automatic programming, and comprises a task analysis module for analyzing task description and constraint conditions in combination with a CLIPS rule engine and a knowledge graph and original data, identifying task targets and requirements, and outputting a task risk assessment report and a task intention set; the optimization decision module is used for selecting an optimal modal data subset by using a particle swarm optimization algorithm and a path planning algorithm, performing optimization adjustment according to task requirements, and outputting a code generation strategy; and the test evaluation module is used for evaluating and improving the unit test and the integration test by utilizing the variation test, carrying out quality and performance evaluation on the code through continuous integration and continuous delivery, and outputting a code evaluation report and an optimization suggestion. According to the method, the optimal modal data subset is dynamically screened, and the data transmission path is optimized, so that the code performance is ensured, the computing resource consumption is reduced, and the global optimization of the code generation strategy is realized.

The invention relates to the technical field of patrol path optimization, and particularly discloses an unmanned aerial vehicle patrol path optimization method and system based on a mobile unmanned aerial vehicle nest, and the method comprises the steps: carrying out the dynamic environment perception and multi-source data fusion, generating a global environment situation map, carrying out the task intelligent analysis and dynamic priority sorting, and obtaining a task distribution matrix; the method comprises the steps of performing multi-target hierarchical path planning, outputting a dynamic flight path set with a timestamp, constructing a real-time obstacle avoidance and emergency self-healing system, obtaining a safety correction path set, performing mobile nest collaborative scheduling and energy optimization, outputting a nest mobile instruction set, triggering global environment situation map updating, obtaining an unmanned aerial vehicle execution log, and performing knowledge evolution. And end-to-end technical iteration is completed. According to the method, the problems that the route planning of the traditional patrol path planning unmanned aerial vehicle cannot achieve refinement and is not high in applicability under complex terrain conditions are solved.

The invention relates to the technical field of distributed computing, and discloses a distributed computing power scheduling method and system based on dynamic load balancing. The method comprises the following steps: acquiring real-time resource state data of a plurality of nodes in the distributed system and demand characteristics of a task to be allocated, generating a dynamic task allocation strategy, allocating the task to a target node for execution, monitoring a resource state of the target node in real time, and triggering task reallocation when the resource state deviates from a preset threshold value. The system comprises a monitoring acquisition module, a task analysis module, a strategy generation module, a scheduling execution module and a resource abstraction module. According to the method, tasks and node resources can be accurately matched, the resource utilization rate is improved, the real-time performance and reliability of the tasks are guaranteed, the overall performance of a distributed system is optimized through heterogeneous resource unified scheduling and a resource reserving and recycling mechanism, and the method is suitable for various distributed computing scenes.

The invention relates to a multi-agent cooperation strategy generation method, device and equipment and a medium, and the method comprises the steps: separating acoustic spectrum features and text semantic features of conference voice through environment perception processing, solving a cross-modal information conflict problem, and generating an accurate semantic understanding result; identifying the essence of the problem based on task analysis, associating the responsibility field, and constructing a classifiable problem point set; calling an agent capability library to dynamically match problem requirements, and generating a candidate agent list; quantifying a problem influence range and a decision time limit through weighted emergency scores, and generating a priority-sorted agent sequence; screening and confirming a core problem point and a primary agent; and finally, generating an executable cooperation scheme through multi-agent collaborative optimization. According to the method, the problems of incomplete feature extraction, task allocation delay and resource conflict in the prior art are solved, and the operability and decision-making efficiency of a cooperation strategy are remarkably improved.

The invention provides a multi-round automatic machine learning agent system based on reinforcement learning optimization. Comprising a task analysis module used for generating an initial prompt for an MLE agent to call; the MLE agent module is used for generating an executable code; the code executor is used for generating an execution result; the evaluator is used for outputting a normalized value of each index and a code correctness identifier; the reward construction module is used for generating a reward value; the reinforcement learning optimizer is used for calculating group average return and candidate advantages and updating strategy parameters of the MLE intelligent agent module based on the candidate advantages; and the multi-round interaction control module is used for feeding back the execution result of the previous round and the reward value to the MLE agent module in the multi-round interaction process, and controlling code generation of the next round until a preset termination condition is met. According to the invention, strategy adaptive evolution, reinforcement learning optimization of fine-grained credit distribution and multi-round closed-loop automatic process improvement can be realized.

The invention discloses a control method for a multi-modal information fusion intelligent robot with a body. The control method comprises the following steps: initializing a system, and collecting surrounding physical environment and object state information and a natural language instruction of a user; performing scene understanding and task analysis, processing data through a multi-modal information fusion mechanism and a cross-modal attention module, and generating unified multi-modal data; task planning and priority ranking are carried out, complex tasks are decomposed into subtask sequences, and a priority ranking layer dynamically adjusts the execution sequence; performing action execution and feedback adjustment, and generating a control instruction through a self-adaptive operation control algorithm; continuous learning and strategy verification are carried out, integrated execution is realized by using a hybrid AI system, and the robustness of an operation strategy is verified through a simulation environment; and closed-loop iteration is carried out to realize real-time response of the intelligent robot with the body. According to the method, the perception understanding precision and the task execution efficiency of the intelligent robot with the body are improved, the operation precision adaptability and the system robustness flexibility are guaranteed, and the method is suitable for multiple scenes.

The invention relates to the technical field of artificial intelligence, and discloses an agent rapid construction method and system based on enhanced retrieval, and the method comprises the steps: constructing a multi-dimensional task analysis system, retrieval task characteristics are automatically represented through characteristics such as data distribution, query complexity and semantic requirements; executing a progressive architecture evolution algorithm, and automatically searching an optimal architecture meeting multi-dimensional balance of retrieval precision, calculation complexity and memory occupation based on the task characteristic vector; constructing a hierarchical knowledge distillation transfer chain, and realizing efficient knowledge migration from a large model to a small model through feature matching and attention guidance; implementing mixing precision quantification and structured pruning on different hierarchies based on sensitivity analysis, and adapting to a target deployment environment; according to the method, the model volume is reduced, the reasoning speed is increased, the energy consumption is reduced, and the enhanced retrieval agent can efficiently operate on resource-constrained equipment.

The invention discloses a high-density stereoscopic warehouse ex-warehouse scheduling and transportation system and method based on RGVs, and relates to the technical field of warehouse ex-warehouse scheduling and transportation, and the system comprises a scheduling management center which is in communication connection with a virtual model construction module, a task analysis and planning module, a task distribution module and a real-time monitoring intervention module. Wherein the modules are connected through electric signals; and the virtual model construction module is used for constructing a virtual model of the warehouse and the RGV. By constructing the virtual models of the warehouse and the RGVs and combining the digital twinning technology, the state of a physical entity can be synchronized in real time, the space-time paths of the multiple RGVs can be accurately simulated, path conflicts and traffic congestion are effectively avoided, the efficiency of warehouse-out operation is remarkably improved, task delay caused by the path conflicts is greatly reduced, and the working efficiency of warehouse-out operation is improved. And the accuracy and timeliness of warehouse-out operation are ensured, so that the overall logistics efficiency is improved.

The invention relates to a multi-modal agent collaborative orchestration method and system, and relates to the technical field of agent collaborative orchestration, and the method comprises the steps: a generative AI orchestration layer analyzes a multi-modal task description after obtaining the multi-modal task description submitted by a client, obtains a task analysis result, queries an adaptive agent based on the task analysis result, and carries out agent collaborative orchestration; the method comprises the steps that an execution layer obtains an intelligent agent matching result, constructs a multi-modal DAG according to the intelligent agent matching result, carries out modal-to-path optimization on the multi-modal DAG to obtain an optimal path planning result, generates a workflow scheme according to the optimal path planning result and sends the workflow scheme to a client side, and the execution layer executes the workflow scheme after receiving a workflow execution request submitted by the client side. And executing the workflow execution request, generating an execution result, and sending the execution result to the client. According to the method, the dynamic requirement of the multi-modal task can be met, cross-modal resource allocation is optimized, and finally the processing efficiency of the multi-modal task is improved.

The invention relates to the technical field of digital twinning, in particular to a digital twinning task scheduling system and a digital twinning task scheduling method oriented to multi-machine cooperation, which realize intelligent mapping between resources and tasks by introducing a topological resource space model. Comprising a topological resource space builder, a task analysis and modeling device, a task resource mapping decision-making device, a global monitoring and optimizing unit and a data fusion processor, the topological resource space builder builds a topological space model of a resource and task mapping relation, and the task analysis and modeling device extracts feature information and a dependency relation of a digital twin task; a task resource mapping decision maker generates a task scheduling decision based on a topological space model and feature information, a global monitoring and optimizing unit dynamically adjusts connectivity parameters of the topological space model according to execution information, a scheduling strategy is optimized, the resource utilization rate is increased, and a data fusion processor merges execution result data and improves the task scheduling efficiency. And through multi-dimensional task feature analysis and intelligent decomposition combination, complex tasks are flexibly dealt with, and the execution efficiency is improved.

The invention relates to the technical field of sharing management, in particular to an instrument sharing management method and system based on a cloud platform, and the method comprises the following steps: obtaining a task generation structure sequence, generating and publishing screening equipment, constructing a channel list generation partition table, and binding a resource output management record. According to the method, the experimental task text content is automatically extracted to perform refined analysis on the behavior structure relationship, the cooperative relationship between the devices is accurately split according to the operation sequence and the behavior difference, and the device response capability and the resource occupancy characteristic are quantitatively identified through the multi-dimensional index; the conflict relation is executed to jointly judge by difference analysis and resource intersection, a priority execution path is constructed in the equipment operation sorting and channel scheduling process according to a response level, and task blocks are accurately divided by jointly deducing an execution proportion and a starting interval in operation time interval arrangement; and automatic closed-loop linkage management of task analysis, equipment identification, conflict detection, priority ordering, block division, resource allocation and sharing registration is realized.

The invention belongs to the field of unmanned aerial vehicle control, and particularly relates to a complex task-oriented unmanned aerial vehicle modular integrated control platform, which comprises an acquisition module for acquiring and processing information such as a real-time flight state of an unmanned aerial vehicle group, a complex task text, meteorological data and the like; the task analysis module decomposes a complex task into a single subtask set and an incidence matrix, and evaluates the task complexity for resource allocation; the atmospheric analysis module is used for inverting a real-time flight association adjustment graph based on the corrected meteorological data, flight states and the like in combination with a target optimization algorithm and an optimization function taking resource quantity minimization and task completion probability maximization as targets; the record analysis module generates a performance transfer matrix by using a hidden Markov algorithm; and the flight control module responds to the adjustment graph to correct the flight state, and ensures that the task completion probability meets a preset safety threshold. According to the platform, efficient cooperative control and resource optimization allocation of the unmanned aerial vehicle group under complex tasks are realized through modular integration.

The invention discloses an intelligent sand excavation supervision system based on multi-source data fusion, and relates to the technical field of machine learning, and the system collects target river reach data in real time through a multi-source sensing network module; the spatial-temporal feature fusion module generates a dynamic state fingerprint matrix; the adaptive baseline monitoring module establishes and dynamically updates a normal state baseline under multiple conditions, and triggers an abnormal disturbance alarm by calculating a mahalanobis distance between a real-time fingerprint and the baseline and combining collaborative deviation verification of acoustics, turbidity and water flow characteristics, and the multi-task analysis module adopts a parallel neural network architecture, so that a multi-task analysis result is obtained. The illegal operation type probability, the strength estimation value and the environment disturbance level are synchronously output; the three-dimensional visualization early warning module generates an early warning interface based on the analysis result; the dynamic knowledge management module and the self-adaptive optimization module are used for improving the analysis accuracy and continuously optimizing the system performance by using historical experience; the method has the advantages that abnormal disturbance events such as illegal sand excavation and the like can be accurately and intelligently supervised in real time, and powerful capability is provided.

The invention relates to the technical field of computing power-energy consumption optimization, in particular to an edge AI reasoning computing power-power consumption cooperative system, which comprises a task decomposition module for decomposing a complete reasoning task into n independent sub-tasks, n being greater than or equal to 1; the task analysis module is used for extracting feature parameters of the subtasks and generating task feature vectors; and the computing power prediction module inputs the obtained sub-task feature vectors and different computing unit type labels into a pre-constructed task computing power demand prediction model, and predicts the computing power demands of the sub-tasks on different computing units. In the scheme construction and task allocation stage, the system carries out candidate calculation unit screening and combination generation based on a multi-scheme calculation power energy consumption matrix, calculates the total energy consumption and time delay matching degree of each combination, and selects an execution scheme with the lowest energy consumption under the real-time condition from the total energy consumption and time delay matching degree. The mechanism enables each subtask to be flexibly migrated between different types of computing units.

The invention discloses an electrocardiogram analysis method and device based on a deep learning model and a medium, and relates to the field of deep learning, and the method comprises the steps: carrying out the preprocessing of an electrocardiogram, and carrying out the noise suppression; inputting the electrocardiosignals into a pre-trained deep learning model, extracting time features and spatial features, and performing cross-modal feature fusion; synchronously executing a plurality of anomaly detection tasks, and synchronously executing a time sequence prediction task; aiming at the abnormal detection result, correcting the abnormal detection result according to the clinical information and the time sequence prediction result; and outputting an analysis result corresponding to the electrocardiogram. A complete closed loop is formed from signal processing to feature extraction, multi-task analysis and result correction, manual intervention links are reduced, electrocardiogram analysis time is remarkably shortened, result consistency is guaranteed, end-to-end automation is achieved, and efficiency is improved.

The invention relates to the technical field of medical care, and discloses an operating room nursing task automatic scheduling system, which is characterized in that a data acquisition module acquires initial data related to an operating room in real time; the task analysis module is used for receiving the initial data acquired by the data acquisition module and analyzing the nursing task; the task scheduling module is used for automatically distributing the nursing tasks according to a result of the task analysis module, generating a task scheduling scheme and sending the task scheduling scheme to corresponding nursing personnel and related departments; the real-time monitoring module performs data interaction with a mobile terminal carried by a nurse and monitoring equipment in an operating room to monitor the execution condition of a nursing task in real time, and when an abnormal condition occurs in the task execution process, an alarm is given out immediately; the feedback and optimization module evaluates and optimizes the task scheduling scheme and adjusts a task allocation strategy; the overall operation efficiency of the operating room is improved, and the professionality and high efficiency of operation cooperation work are ensured.

The invention provides a multimodal transport scheme generation system and method based on multiple agents. Comprising a task analysis module used for generating a task context; the network modeling module is used for acquiring data related to a transportation network and an operation state and constructing environment situation representation; the candidate path generation module is used for generating a candidate path set meeting constraints on the multimodal transport network; the resource checking module is used for carrying out resource availability and time sequence connection checking on the candidate path set; the decision module is used for generating an evaluation vector for the checked candidate path set and generating a structured description; and the output module is used for generating a scheme document and a machine readable instruction and providing the scheme document and the machine readable instruction to an external execution system. According to the method, environment situation representation unification of multi-source dynamic data, constraint-based candidate path set automatic generation and resource time sequence checking, target scheme selection and structured description generation under intelligent agent collaboration, event-triggered increment re-planning and machine readable instruction output can be realized.

The invention relates to an owned task planning method and system based on search guided by a large language model. The method comprises the steps that in the preprocessing stage, a simulation module based on a large language model is used for generating a precondition function and an effect function corresponding to each action type according to environment meta-information; in a task analysis stage, a translation module based on a large language model is used for translating task description in a natural language form into a structured landing predicate set; in the exploration stage, an exploration module based on a large language model is used for guiding the intelligent agent to explore the environment until all objects related to tasks are observed; in the searching stage, a searching and screening module based on a large language model is used for executing a searching algorithm from the current state, an action space during searching is compressed, a complete task plan is generated, and the task plan is executed by an intelligent agent in the environment. According to the method, the interpretability and controllability of planning can be improved, so that the search process is feasible and efficient in a real task environment.

The invention discloses an agent construction and development system based on a knowledge graph, and the system comprises a data collection and ontology construction module which is used for generating basic graph data; the polymorphic knowledge cell construction module is used for generating a machine-readable rule and an evidence template; the semantic mapping and deduction module is used for determining forward and reverse mapping modes and setting a consistency threshold value and a violation degree weight; the task analysis and planning module is used for outputting a feasible path and generating a plan sequence and tool arrangement; the execution and correction module is used for generating an evidence packet, constructing a forward chain, carrying out reverse reconstruction by utilizing reverse mapping, generating anti-fact candidates and writing back or backing back the anti-fact candidates; and the version and audit module is used for generating a version fingerprint for the polymorphic knowledge cellular graph which is written back and providing query and audit functions. According to the method, adaptive planning, reliable execution and traceable auditing of the intelligent agent in a dynamic task are realized by constructing polymorphic knowledge cells and cross-layer semantic mapping.

The invention belongs to the technical field of crossing of artificial intelligence and computer system architecture, particularly relates to a computing power center equipment power supply intelligent system of a knowledge graph, and aims to solve the problem of low energy efficiency caused by extensive power supply management, unbalanced energy consumption and lagged load response. The system comprises a task analysis module, a dynamic load prediction module, a multi-source power supply scheduling module, an equipment-level power supply control module and a feedback optimization module, through load prediction and multi-source power supply cooperative scheduling driven by task semantics, voltage and current dynamic adjustment and sleep wake-up control are achieved, and a strategy is optimized online based on operation feedback. The scheme improves energy efficiency, equipment life and system stability.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an artificial intelligence data annotation and cue word automatic construction engine system, which comprises a data annotation module for firstly carrying out preliminary annotation on data based on a pre-training model, then automatically annotating a data sample through an active learning algorithm, and meanwhile, monitoring the quality of annotated data in real time; and the cue word automatic construction module generates cue words based on task analysis, optimizes the cue words by using a reinforcement learning technology, and performs classified storage and management on the generated cue words. By adopting the semi-automatic labeling and active learning labeling functions, not only can the workload be greatly reduced, but also the unnecessary labeling work can be reduced, so that the labeling efficiency is remarkably improved, the labeling time is shortened, the large-scale data labeling requirement is met, and the problem of efficiency bottleneck caused by slow manual labeling is solved.

The invention relates to the technical field of three-dimensional modeling, in particular to an on-orbit three-dimensional modeling method and system. The method comprises the following steps: mapping a task demand input by a user into a task specification object; carrying out mixed retrieval on the task template library, carrying out atlas consistency verification on the retrieved task templates, and sorting candidate templates after the verification is passed; expanding the high-score candidate template into an executable high-score operator sequence to serve as a task chain to be output; mapping each operator in the task chain into an MCP calling node to obtain an MCP calling chain; and calling a data processing tool and a three-dimensional modeling tool to generate a preliminary three-dimensional model, then performing incremental correction and local optimization through a dynamic feedback updating mechanism, and downloading the updated incremental three-dimensional data to a ground data center. Automatic task analysis is achieved, and manual intervention is not needed. The method has the lightweight modeling capability, knowledge-driven complementation can be realized, and a collaborative mode of on-orbit quick response and ground fine reconstruction is realized.

The invention provides a task analysis execution method and system based on a multi-modal large model, and belongs to the field of computers.The task analysis execution method comprises the steps that S1, multi-modal task data are received, a double-layer cross-modal fusion mechanism is adopted to conduct unified coding fusion on the multi-modal task data, and fusion features are obtained; s2, performing alignment processing on the fusion features based on a multi-modal embedding alignment mechanism to obtain alignment features, and performing structured task analysis based on the alignment features by using a pre-training language model to obtain task description; s3, decomposing the composite task into atomic tasks, and learning an optimal decomposition strategy by using an Actor-Critic network to form an atomic task set; and S4, generating a comprehensive adaptation score through a dynamic scheduling mechanism of collaborative awareness, and performing task distributed execution based on the comprehensive adaptation score. According to the method, the complex task is intelligently decomposed into the atomic task set capable of being executed in parallel for task distributed execution, and the task understanding accuracy and execution efficiency are improved.

The invention provides a medical data-oriented efficient privacy computing fusion engine method and system, and the method comprises the steps: constructing a medical data encryption and decryption system as a basis, and carrying out the standardized packaging of federated learning, homomorphic encryption, secure multi-party computing and other technologies, a unified technical framework comprising a data encryption interface, a ciphertext calculation interface and a result decryption interface is defined; an intelligent task analysis mechanism is adopted, high-level medical analysis requirements can be automatically decomposed into privacy calculation subtask sequences, and multi-technology collaboration is achieved through an execution engine; meanwhile, the functions of resource monitoring and performance analysis are achieved, technology switching and parameter adjustment and optimization during operation are supported, and a self-optimization execution environment is formed. And finally, displaying through a friendly application interface and visualization. According to the method, the problems of single technical route, low calculation efficiency, poor resource utilization rate, serious memory limitation and the like in medical data privacy protection are solved.

The invention relates to the technical field of path planning, in particular to a low-altitude airspace aircraft flight path planning system which comprises a task analysis module, an airspace modeling module, a path generation module, a feasibility verification module and a path output module. According to the method, sight distance flight rule grade judgment is introduced in airspace boundary extraction to eliminate airspace sections which do not meet the minimum sight distance reference requirement, a connection diagram is constructed, combined calculation of the wind shear angle and the building projection density is executed, and through quantitative analysis of the ratio of the path section height to the wind pressure change gradient, the wind shear angle and the building projection density are calculated. The method comprises the following steps: performing intensity risk labeling on a path in an unstable airflow area to realize path continuity and stability discrimination, constructing a continuous instruction point group based on a stable fragment sequence in a path combination stage, and setting speed and steering adjustment thresholds, so as to enhance the adaptability and execution robustness of a path execution sequence to flight control; and the air route feasibility and the risk avoidance capability in a complex low-altitude environment are improved.

The invention discloses an AI development optimization system based on dynamic learning and an adaptive algorithm, and relates to the technical field of artificial intelligence, and the system comprises a collection module which collects GPU occupation data and transmission channel state data, and generates a separation operation signal; the identification module is used for triggering operation task analysis according to the separation operation signal and distributing a transmission channel identifier for the subtask; the path module queries the idle state of each computing unit of the GPU and generates an exclusive communication path; the detection module is used for running the subtasks in the exclusive communication path and outputting channel signal mixing degree; the triggering module is used for setting a mixing degree threshold value and triggering a path replacement signal and a merging operation signal; and the merging module suspends the sub-task processing process based on the merging operation signal, performs merging according to the operation sequence of the sub-tasks, and outputs a complete task. According to the method, efficient resource scheduling and task optimization of AI development are realized through coordination of dynamic task topology analysis and self-adaptive communication path binding.

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 multi-agent cooperation report generation method, device, equipment and medium, and the method comprises the steps: obtaining a compliance requirement file and a task description text; analyzing the task description text through an intention recognition agent to generate a task intention recognition result; processing the compliance requirement file and the task intention recognition result through a key point extraction agent to generate compliance requirement key points; executing the compliance requirement key points through the data processing agent to generate data visual representation; and synthesizing compliance requirement key points and data visual representation through the report generation agent to generate report content. According to the method, task analysis, key point extraction, data processing and report synthesis links are sequentially connected and automatically executed in a multi-agent division cooperation mode, so that compliance files and task description can be quickly converted into structured key points, and business data can be efficiently processed and visually presented.

The invention discloses a table data analysis method fusing a large language model and a ReAct framework. The table data analysis method comprises the following steps: receiving and processing table data and natural language query input by a user through a file analysis module; performing task analysis and code generation in the ReAct framework by using an LLM decision engine; constructing a multi-stage verification module to perform three-stage verification of semantic calibration, code pre-check and logic verification on the generated code to enhance the code robustness and improve the result accuracy; a CNN-BiLSTM hybrid neural network model is adopted to construct a self-correction module, error classification is carried out on codes which fail to be verified, and a correction strategy is fed back; and executing the generated code, and returning a structured result after the ReAct control process is finished. According to the method, the problems that error propagation is not corrected, multi-Agent resource consumption is large and complex query accuracy is low in an existing table analysis technology are effectively solved, the accuracy, efficiency and reliability of data analysis are remarkably improved, and meanwhile computing resource consumption is greatly reduced.

The invention discloses a human metabolism multi-task analysis method based on a large language model, which comprises the following steps of: firstly, constructing a unified multi-task data set containing metabolic reaction prediction, and converting tasks such as compound expert description, enzyme classification, reaction type identification and product prediction into a standardized'question-thinking-answer 'text format; and then a Qwen2.5-7B large language model is adopted as an infrastructure, and supervised training is performed through a training parameter fine tuning technology, so that the model can infer the biochemical reaction process. Experimental results show that the method disclosed by the invention has relatively high efficiency and accuracy in a test with the same standard as those of Deepseekv3 and Qwen 2.5-7B.

The invention provides a micro-service architecture implementation method for intelligent distribution of scheduled tasks, and belongs to the technical field of scheduled task distribution micro-services. A task analysis module is established to perform multi-dimensional classification marking on scheduled tasks, and a service instance monitoring module is established to acquire system load information in real time; a load evaluation algorithm is designed to quantify the comprehensive capability of a service instance, a task association engine based on multi-dimensional feature matching is established, a task optimization distribution model based on a Transform architecture is realized to carry out intelligent decision making, a task execution monitoring module is constructed to track an execution state, a feedback optimization mechanism is designed to dynamically adjust a distribution strategy according to an execution effect, and the service instance distribution efficiency is improved. Self-adaptive optimization of system parameters is realized through a distribution effect evaluation function and a multi-level weight adjustment function, and the technical problem of low distribution efficiency of scheduled task distribution under the micro-service architecture is solved.