61 results about "Task demand" patented technology

The invention relates to a task scheduling optimization method and device based on reinforcement learning, equipment and a medium. The method comprises the steps that firstly, system resource state data are collected in real time, dynamic environment characteristics are determined through preprocessing and time sequence analysis, task characteristic data are analyzed at the same time, and a task priority sequence and a resource demand vector are generated through a priority ranking algorithm and a resource evaluation model; and then a state space and an action space are constructed by adopting a reinforcement learning algorithm, an optimal task allocation scheme is generated through strategy iteration and reward function optimization, and if the scheme meets a resource balance threshold, scheduling is executed, and performance indexes are collected. And finally, fusing real-time indexes with historical data, and updating parameters of the reinforcement learning model through experience playback and gradient descent to form a closed-loop optimized improved scheduling strategy. By adopting the method, the accurate mapping of the resource state and the task requirement can be realized, and the problem of insufficient adaptability of the traditional static scheduling to a complex scene is solved.

The invention discloses a converged communication system and method for emergency command and dispatch, and the method comprises the following steps: S1, constructing a converged communication network environment, and configuring a self-adaptive network switching module; s2, collecting and analyzing task demand data in an emergency scene, and generating a task demand prediction matrix; s3, generating a task scheduling rule; s4, acquiring current network state data, and generating task scheduling constraint conditions; s5, constructing and training a multi-agent reinforcement learning model; s6, optimizing a communication path decision strategy and a task scheduling rule by adopting a self-adaptive multi-objective optimization algorithm; s7, calculating an optimal communication path, and executing intelligent adaptive network switching; and S8, collecting task execution feedback data, and adjusting training parameters of the multi-agent reinforcement learning model. According to the method, multi-agent reinforcement learning and dynamic entropy regulation and control optimization are combined, emergency communication task scheduling and path optimization are achieved, and the method has the advantages of being high in adaptability, high in communication stability and excellent in task execution efficiency.

The invention provides a complex task full-automatic processing method based on multi-agent cooperation and a related device, and relates to the technical field of artificial intelligence such as large language models, generative models, agents and task intelligent scheduling. The method comprises the following steps: interacting with a target user who puts forward an original task demand to obtain a complete task demand; the complete task demand is split into a plurality of sub-tasks at least comprising a complex sub-task, the complex sub-task refers to a sub-task needing at least two sub-agents to process according to a cooperation process, and a single sub-agent is used for processing a simple sub-task; issuing the complex sub-tasks to corresponding target execution intelligent units, and issuing the simple sub-tasks to corresponding target sub-agents; and summarizing sub-task execution results returned by each target execution intelligent unit and each target sub-agent. According to the method, the execution intelligent unit specially used for processing the complex sub-task is introduced, and the complex sub-task is processed more intensively according to the cooperation process through the at least two sub-agents contained in the execution intelligent unit, so that the task disassembling difficulty is reduced; and a better sub-task processing result can be obtained through the execution intelligent unit integrated by the multiple sub-agents.

The invention discloses a multi-modal data driven general report generation method and system based on a large model, and belongs to the technical field of intelligent report generation. Firstly, texts, images and sensor data related to a report theme are obtained and subjected to standardized preprocessing; analyzing the report generation instruction, and matching and querying a task modal mapping library matching modal configuration scheme according to a task demand; quantitatively evaluating the data quality of each modal, dynamically calculating the final decision weight of each modal in combination with the basic weight, and distributing the final decision weight to a corresponding processing path to form dominant, supplementary and reference data; inputting the dominant data and the supplementary data into a multi-modal model for analysis to obtain a preliminary conclusion with confidence score, performing consistency judgment, if no conflict exists, performing fusion to form a comprehensive conclusion, and if the conflict exists, combining a quality evaluation result and an arbitration rule to complete conflict judgment; and finally, inputting the comprehensive conclusion and the reference data into a large language model to generate a report text, and outputting a complete report after typesetting and proofreading.

The invention discloses a multi-agent task arrangement method and system, and relates to the technical field of artificial intelligence. In the method, firstly, a task demand is obtained, key information and intention of the task demand are extracted, and task semantics are obtained; secondly, based on the task semantics and the business standard process template, obtaining a business standard process template matched with the task demand; then, according to the matched business standard process template and task semantics, a task context is constructed, and a domain specific language DSL is generated through reasoning according to the task context; thirdly, the DSL is analyzed, a task dependency graph is constructed according to the DSL analysis result, and the task dependency graph is converted into BPMN process model data; and finally, sub-task scheduling and execution of the sub-agents are carried out according to the BPMN process model data. According to the method provided by the invention, the dependence on professional developers or process engineers can be reduced, the response and planning time of complex tasks can be shortened, the result predictability can be improved, and the reasoning cost can be obviously reduced.

The invention relates to the technical field of agent systems, and provides an MCP agent-oriented dynamic tool discovery and adaptive system construction method, which comprises the following steps of: designing a uniform interface to register tools, and storing tool data through a dictionary structure; environment parameters are collected, external input and context information are received, three types of data are fused, task types are judged according to priorities, and task requirements are analyzed; according to the capability description during tool registration, the suitability of task execution is judged, a correlation score is calculated, and tools with the score lower than a preset score are screened; comprehensive calculation is carried out by combining the correlation score of the tool, the cost and the delay value, and the tool for executing the task is selected according to the score; according to the selected tool and the current operation environment, resources needed by tasks and an execution sequence are judged, and an execution chain is automatically constructed; and recording and collecting feedback data, evaluating an execution result, and iterating tool parameters.

The invention discloses a multi-agent collaborative scheduling method and system oriented to science and technology intelligence analysis, and relates to the technical field of science and technology intelligence analysis, and the method comprises the steps that a task issuing layer outputs a standardized task description by executing task demand element analysis; after the intelligent coordinated scheduling layer receives the standardized task description, closed-loop collaborative decision making is carried out, and a task distribution instruction is output; and the professional agent execution layer drives the data acquisition agent group to acquire science and technology information data through a data access adapter of the data resource layer, executes a science and technology information analysis task, outputs a structured processing result, and visually displays the structured processing result to a user through the task release layer. The technical problem that in the prior art, a science and technology information processing system lacks intelligent task allocation, and consequently the information processing efficiency is low is solved, and the technical effects that four-layer architecture closed-loop cooperation of science and technology information analysis tasks and efficient dispatching of specialized intelligent agent groups are achieved, and the task allocation accuracy and the information processing efficiency are improved are achieved.

The invention relates to the technical field of cloud edge collaboration, in particular to a production scheduling intelligent management and control system based on cloud edge collaboration, and the system comprises a task feature aggregation module which is used for extracting a task type code based on an input task request, querying a task type and calculation amount mapping table in a pre-stored knowledge base, matching the task type and extracting a calculation amount parameter. According to the method, the mapping relation between the task type and the pre-stored calculation amount is dynamically matched, the task data packet size, the real-time requirement threshold value and the bandwidth reference value are linked to calculate the transmission time consumption parameter, quantitative mapping of task requirements and resource supply is achieved, and parameter deviation caused by traditional artificial experience estimation is eliminated. The CPU occupancy rate value of the edge node process queue is collected in real time, and the multi-dimensional node state vector is generated in combination with the number of cloud virtual machine instances and memory surplus data, so that the limitation of traditional single resource index monitoring is broken through, and the space-time fine granularity of load evaluation is improved.

The invention relates to the technical field of task scheduling, in particular to a multi-agent-based construction site task scheduling method and system, and the method comprises the following steps: obtaining task starting and resource in-place time, matching task demands, setting priorities, judging task conflicts, generating a section structure table, extracting completion data, activating tasks, and generating a trigger chain. And constructing path fragments to establish a task continuous relationship, and judging section adjacent reconstruction scheduling to generate a parallel control result. According to the method, task screening is guided through cross judgment of the task starting time and the resource in-place state, priority information is dynamically given in combination with operation type requirements, intelligent recognition of task triggering conditions is achieved, and the mutual exclusion conflict relation is marked in time through overlapping comparison of regional task time intervals; the scheduling behavior is promoted to have the pre-recognition capability for resource conflicts, and the scheduling continuity and resource consistency in multi-agent task cooperative execution are enhanced.

The present application relates to the field of equipment maintenance support, and particularly discloses a multi-stage task equipment selective maintenance decision and task allocation joint optimization method. Step S1: statistics of task type, statistics of the number of each unit continuous execution tasks under the task type and the interval period between tasks; Step S2: providing maintenance measures within the interval period, statistics of the maintenance measures and the corresponding maintenance effect, and calculation of the state probability distribution after executing the maintenance measures; Step S3: calculation of the total maintenance cost within the interval period of all tasks; Step S4: since each stage task contains multiple subtasks, the total task demand of each type unit needs to be calculated according to the state and maintenance of each unit before the task starts; Step S5: allocation of tasks and meeting the demand of each stage task; Step S6: calculation of the task completion probability according to the task demand of each stage. The present application aims to solve the problem of independent optimization of equipment selective maintenance decision and task allocation under the previous multi-stage task.

The invention discloses a multi-source sharing automation task collaborative optimization method and system of an AI Agent, and relates to the related field of data processing, and the method comprises the steps: carrying out the task complexity calculation of a target task, and generating a decomposition instruction when a calculation result meets a preset threshold value; performing hierarchical disassembly on the target task to generate a sub-task set, and establishing sub-task dependence; performing self-inspection on the environment state, and establishing a task execution balance function according to a self-inspection result and a task demand; executing scheduling optimization of the subtask set, and establishing a multi-round scheduling optimization result; and performing busy state prediction on the environment, generating scheduling compensation according to a prediction result, performing optimization result screening through the scheduling compensation, and establishing an Agent decision scheme. The technical problems of low execution efficiency, non-uniform resource allocation and task failure rate increase in existing task cooperative execution are solved, and the technical effects of high task execution efficiency, high resource utilization rate and remarkable reduction of the task failure rate are achieved.

The invention relates to the technical field of interactive design, and discloses an art design system and method based on dynamic interaction, and the system comprises an interface interaction module, an interaction management module, a data synchronization module and a task distribution module. Multiple users are supported to edit and preview at the same time, the task allocation state is clearly presented, instant communication is promoted, and the cooperation efficiency is greatly improved; according to precise allocation of member specialities, workloads and task requirements, optimization targets are to minimize task completion time and maximize member satisfaction, and reasonable allocation of tasks is guaranteed; the subtask progress is updated in real time, the data detection frequency is dynamically adjusted according to the project condition, and an incremental updating and consistency checking and repairing mechanism is adopted to ensure that members obtain latest accurate information in time; design conflicts can be effectively detected, the smooth design process is solved and maintained by means of a priority strategy and version control, and the efficiency of cooperation of an art design team is comprehensively improved.

The invention provides a task agent generation and task processing method based on a meta agent, and relates to the technical field of autonomous agent application. The method mainly comprises the steps of initialization, task input, task analysis, subtask generation, task agent generation and distribution, task execution and cooperation, and result integration and feedback. According to the method, the meta-agent with task understanding, decomposition and planning capabilities is introduced, so that the task agent is dynamically generated according to task requirements, the tool calling process is optimized, the problem of low model processing efficiency caused by tool information overload in the prior art is effectively solved, and the model processing efficiency is improved. And the response speed, the flexibility and the intelligent level of task processing of the automatic software / hardware system are remarkably improved.

The invention discloses a federal edge communication and calculation optimization method, system and device based on task prediction and a medium, and belongs to the technical field of edge intelligent collaborative optimization, and the method comprises the steps: collecting historical task data, carrying out the modeling of a communication and calculation process, building a multi-dimensional task feature modeling mechanism, extracting the heterogeneous features of the communication and calculation process, and carrying out the calculation of the communication and calculation process. Performing task demand prediction and load perception to obtain a prediction result; and establishing an integer programming model, performing approximate solution through a heuristic algorithm to complete service cache optimization, performing calculation unloading and resource joint allocation, calculating key performance indexes, performing periodic acquisition, and performing dynamic adjustment on a prediction result. According to the method, an efficient cache strategy is generated by adopting a heuristic algorithm, the defects of single resource allocation, decision lag and lack of global coordination in a traditional method are overcome through joint optimization of resource allocation and a real-time performance monitoring feedback mechanism, and the system response efficiency and the resource utilization rate are improved while the task success rate and reliability are guaranteed.

The invention provides a multi-agent collaborative task process arrangement method and system, and the method comprises the steps: carrying out the processing of a task demand through a large language model by employing a demand analysis agent, and obtaining a structured task description; determining a workflow topological graph based on the structured task description by using a process modeling agent; scheduling and operating a task execution agent corresponding to each subtask by utilizing an execution engine according to the workflow topological graph; determining an actual execution path of each sub-task based on the task execution log of each sub-task by using a deviation identification agent, comparing the expected execution path with the actual execution path by using the deviation identification agent, and comparing the expected index data with the task execution index data to obtain a comparison result; and optimizing the workflow topological graph based on the comparison result by using a process modeling agent. Therefore, a complete closed loop of demand analysis, flow generation, execution, monitoring, diagnosis, optimization and regeneration of flow arrangement can be realized.

The invention discloses a componentized integrated AI assistant system and a use method thereof, and relates to the technical field of artificial intelligence, and the componentized integrated AI assistant system comprises a task grading module, a basic framework module, a dynamic routing sub-module, a monitoring operation and maintenance module and a functional component library. Analyzing task requirements through multi-modal input to generate structured request content features, dynamically generating a component calling sequence according to the request content features based on a reinforcement learning model, realizing intelligent matching of tasks and functional components based on the request content features and a component capability atlas, generating a requirement component list according to an intelligent matching result, and sending the requirement component list to a server; the method comprises the steps of obtaining a demand component list, obtaining a real-time performance index and a historical performance index of each component on the demand component list, sequentially identifying an abnormal operation state of each component on the demand component list, updating the demand component list according to an identification result, and sending the updated demand component list to a functional component library.

The embodiment of the invention relates to the technical field of control systems, and discloses an intelligent excavator multi-joint PID (Proportion Integration Differentiation) parameter setting method which comprises the following steps: acquiring corresponding task execution information, and performing task splitting on the task execution information to determine task demand information of each stage; determining a target joint angle of a mechanical arm of the intelligent excavator according to the task demand information; a mechanical arm of the intelligent excavator is controlled to enter an excavation state, and the real-time joint angle of the mechanical arm of the intelligent excavator is determined according to the sensor assembly; and processing the target joint angle and the real-time joint angle to obtain real-time state information, and inputting the real-time state information into a pre-completed parameter optimization model for processing to obtain an optimized PID control parameter. According to the multi-joint PID parameter setting method of the intelligent excavator, the PID control parameters are automatically adjusted according to the real-time operation state of the intelligent excavator. The control performance of the multi-degree-of-freedom mechanical arm of the excavator can be remarkably improved.

The invention provides a document structuring task processing method and system and a readable storage medium. The method comprises the steps of firstly obtaining a structured task request and corresponding unstructured document data, then dynamically determining an adaptive reasoning mode in combination with a task demand, a current time period and a load state of a preset processing model group, and associating the two modes with an exclusive target reasoning model in the model group respectively. In a high-load period or when a task needs to be quickly responded, a result-oriented reasoning mode is started, a structured document is directly generated by a correlation model, the process is simplified, and resource consumption is reduced; and when a load period or a task needs a clear basis, switching to an interpretable reasoning mode, synchronously outputting a structured document and a complete reasoning process by the association model, and clearly displaying a processing logic. According to the dynamic adaptation mechanism, the real-time performance of a high-demand scene is guaranteed, the interpretability defect of a model is overcome, and the real-time performance and decision transparency of text structured processing are doubly improved.

The application provides a hybrid large language model modular fusion system, an implementation method and related devices, which comprises the following steps: firstly, receiving a task request and analyzing to generate a task characteristic vector describing the task demand; then, obtaining the ability characteristic vectors of each expert model and calculating the similarity between the ability characteristic vectors and the task characteristic vector to screen a target expert model group to realize accurate matching of the models; secondly, querying the real-time load state of the computing node where the target expert model group is located and dynamically distributing the task to improve the utilization rate of computing resources; then, controlling the target expert model group to perform multi-round iterative collaborative reasoning through a preset cooperation process, taking the output of a previous expert model as the input of a subsequent expert model to strengthen the collaborative linkage capability among the models; finally, performing fusion processing on the intermediate output result to generate a standardized task output result, ensuring the standardization and accuracy of the output result and improving the stability and reliability of the system operation.

The invention discloses a task execution method and device, equipment, a storage medium and a product, the task execution method is applied to an intelligent agent, and the method comprises the steps of obtaining task demand information input by a user; extracting demand elements from the task demand information to obtain target element information; based on the target element information, calling an architecture design module to carry out system layer-by-layer architecture design to obtain a system function module corresponding to the task demand information; converting the system function module into a subtask sequence, and configuring execution parameters for each subtask in the subtask sequence to obtain a structured subtask execution list; and executing each sub-task in the sub-task sequence according to the structured sub-task execution list, and outputting an execution result of the sub-task. The method can improve the accuracy of the task execution result.

The application claims a service-aware resource collaborative allocation method, belonging to the field of mobile edge computing resource allocation, which comprises: analyzing task demand characteristics, obtaining task abstract categories combined with task demand characteristics, and mapping them into corresponding demand types. Based on the task demand type, candidate collaborative node clusters are selected through destruction operators and repair operators, then the task and resource matching problem is modeled as a combinatorial optimization problem, the collaborative benefits of candidate node combinations are calculated, and the edge node combination with the highest collaborative benefit is selected. The application mainly considers the problems of task demand fuzziness and task and resource matching imbalance in the computing power network, designs a task demand type identification algorithm and a resource collaborative allocation strategy, selects a reasonable collaborative node cluster, and reduces the time delay while improving the resource utilization.

The present application relates to the technical field of data processing, and provides a kind of implicit multi-section trigger chain method and device.In the present application, user submits task demand, task management module in system is activated, and a set of task label representing load power expectation that task demand is started is written in system state table, and task management module enters weak disturbance state;Energy consumption evaluation module in system identifies that energy consumption label fragment in system state table has changed, then updates system state table;Energy consumption label fragment is FB-Type data label of frequency variation type, and system state table is stored in time series database;Device state module switches data label type according to system state table, and stores the data collected according to the type of data label.The present application solves the problem that the prior art is more complex to coordinate each module based on explicit control, the amount of data required for transmission is large, resulting in poor system practicability.

The application relates to the technical field of cloud-edge collaboration, in particular to a production scheduling intelligent management and control system based on cloud-edge collaboration, which comprises a task characteristic aggregation module, which extracts a task type code based on an input task request, queries a task type and calculation amount mapping table in a pre-stored knowledge base, matches the task type and extracts a calculation amount parameter. In the application, the task data packet size, the real-time requirement threshold and the bandwidth benchmark value are linked to calculate the transmission time consumption parameter by dynamically matching the task type and the pre-stored calculation amount mapping relationship, the quantitative mapping of task demand and resource supply is realized, and the parameter deviation caused by traditional artificial experience estimation is eliminated. The CPU occupancy rate value of the edge node process queue is collected in real time, the multi-dimensional node state vector is generated by combining the cloud virtual machine instance quantity and the memory residual quantity data, the limitation of traditional single resource index monitoring is broken through, and the time and space fine granularity of load evaluation is improved.

The invention discloses an agent calling method based on a large language model and a related device, and relates to the field of artificial intelligence, and the method comprises the steps: receiving a task natural statement sent by a user, decomposing the task natural statement into sub-task statements based on a task decomposer, carrying out the task demand analysis of the sub-task statements through the large language model, and obtaining a task demand analysis result; subtask requirements are obtained, task generation operation is conducted on the subtask requirements on the basis of a task decomposer, and a subtask list is obtained; performing agent matching operation on the sub-task list by using a large language model to obtain a calling plan of an agent corresponding to each sub-task in the sub-task list, and sending the calling plan to a routing scheduler; calling the intelligent agent to process the subtask corresponding to the intelligent agent through the routing scheduler to obtain a processing result; and sending the processing result to a result aggregator for aggregation processing to obtain an aggregation result, and outputting the aggregation result. According to the method, flexible calling of different agents is realized based on the large language model.

The invention discloses a cloud-edge collaborative task scheduling method based on an optimized A2C algorithm, and belongs to the technical field of cloud computing and edge computing fusion scheduling. Aiming at the technical problems of low resource utilization rate, high system energy consumption and high delay of the existing cloud edge collaborative task scheduling method, the invention provides a method for constructing a task-host heterogeneous graph, and explicitly modeling a bidirectional constraint and competition relationship between task requirements and host resources; designing a heterogeneous graph pointer network, and respectively extracting the competitive strength of a task to a host and the supply and demand matching quality of the task and the host through a two-stage graph attention mechanism to form a joint environment state feature; a task granularity dominant function is adopted, the dominant value of each task action is calculated in a differentiated mode according to the task scheduling execution result and the global time sequence differential error, and strategy network gradient updating is carried out in combination with the pointer probability. According to the method, accurate perception and fine-grained optimization of the dynamic cloud edge environment are realized, and system energy consumption and task response delay are remarkably reduced.

The invention relates to a self-adaptive closed-loop context engineering method and device based on an intelligent agent, and belongs to the technical field of intelligent agents, and the method comprises the steps: outputting a context scheduling action intention for a current task stage through a reinforcement learning scheduling model in a decision-making layer based on a task type, a task demand and a current task state prediction decision; wherein the context scheduling action intention of the current task stage is an execution action in a predefined action space; mapping the action intention into at least one specific operation which can be triggered and executed on the execution layer on the execution layer, scheduling the action intention based on the context of the current task stage, and setting an execution condition for triggering the specific operation; and triggering and executing the corresponding specific operation based on the execution condition of the specific operation to obtain the task execution result, so that the intelligent agent can dynamically manage at least one of the context window, the associated memory network and the sub-intelligent agent cluster of the LLM intelligent agent, thereby being beneficial to improving the application efficiency of the intelligent agent.

An artificial intelligence (AI) reasoning task scheduling method and system having real-time performance and determinacy, and a storage medium. The method comprises: when receiving a scheduling request for an AI reasoning task, an AI engine assembly allocates the AI reasoning task to a matched neural network model assembly on the basis of a task demand and a time deterministic constraint of the received AI reasoning task; on the basis of a resource demand and the time deterministic constraint of the AI reasoning task, and an actual resource condition of a computing node, in a plurality of operation capsules of the computing node, the matched neural network model assembly schedules a matched AI-specific real-time operation capsule for the AI reasoning task, wherein the AI-specific real-time operation capsule comprises a real-time operation environment and a basic assembly used when the AI reasoning task is executed. The method can reasonably allocate the task, fully use the computing resources, ensure that the neural network model assembly completes output of a reasoning result within a given time period, and meet the time deterministic constraint.

The application provides a multi-agent dynamic workflow arrangement method and system based on an MCP protocol, and relates to the technical field of multi-agent collaborative work. The method comprises the following steps: constructing a standardized agent description and configuring an MCP protocol adapter; generating a task demand text through planning an agent, matching an optimal agent by using a cosine similarity algorithm, and obtaining an initial workflow arrangement graph including a task execution node and a task dependency relationship in combination with a logic analysis technology and a topological sorting algorithm; screening historical related content corresponding to the task execution node based on a context propagation strategy, determining a context dependency result according to the task dependency relationship, and generating context inheritance information by summarizing; accessing the optimal agent by using the MCP protocol adapter, and performing a task execution operation according to the initial workflow arrangement graph in combination with the context inheritance information to generate a task execution result, so that multi-agent efficient collaboration can be realized, and arrangement flexibility and interactive stability can be improved.

The invention discloses a task processing method and device based on a task knowledge base, equipment and a storage medium, and relates to the technical field of semantic communication, and the method comprises the steps: converting an index sequence of a target information source semantic representation vector into a first lexical element sequence of a large language model based on an information source semantic representation knowledge base; on the basis of a channel semantic representation knowledge base, converting the channel state information into a second lexical element sequence of the large language model; splicing the structured task demand prompt information, the first lexical element sequence and the second lexical element sequence into target prompt information, and inputting the target prompt information into a large language model for reasoning to obtain a target lexical element sequence; and based on the property of the target task, processing the target lexical element sequence to obtain a task processing result. Through the mode, a bidirectional conversion mechanism between the multi-modal task / channel environment semantics and the lexical elements of the large language model is constructed, so that the large language model can understand and process diversified task data from a dynamic channel.

The application discloses an Agent-driven computing power resource dynamic arrangement method and system, relates to the technical field of cloud computing resource scheduling, and comprises the following steps: S1, forming computing power arrangement basic data; S2, instantiating a task Agent, a resource Agent, a negotiation Agent, a constraint Agent and an execution Agent; S3, forming a task demand contract by the task Agent; S4, forming a resource state sequence by the resource Agent; S5, the negotiation Agent generating an arrangement action intervention tensor; S6, inputting an improved TimeMixer model and outputting a resource prediction state; S7, the negotiation Agent generating a candidate resource arrangement chain, and the constraint Agent forming a target resource arrangement chain; and S8, the execution Agent generating a computing power resource dynamic arrangement result. The application improves resource prediction accuracy and computing power arrangement stability.