51 results about "Task dependency" patented technology

This invention discloses a method, apparatus, and medium for scheduling image chunks in ultra-high resolution images. It receives and processes image chunking tasks in real time, obtaining target image chunking task description information. When an image chunking execution command is received, the image chunking algorithm module is instructed to parse the task description information, which is then placed in the task scheduler cache pool, and a parent-child task dependency table and a subtask dependency table are established. When a task scheduling command is received, the task scheduling module is instructed to schedule the tasks in the task scheduler cache pool using the task scheduling method until all chunk subtasks are scheduled, thus scheduling the image chunking task to the target hardware device. This invention solves the problems of high hardware bandwidth cost and low efficiency caused by direct processing, as well as the semantic integrity destruction and low accuracy of traditional chunking processing due to ignoring chunk dependencies, thereby improving the efficiency and accuracy of ultra-high resolution image chunking scheduling.

This invention provides an adaptive multi-agent cooperative task planning method based on confidence feedback adjustment, belonging to the field of data processing technology. The method includes: semantically parsing received natural language instructions to obtain a task dependency graph and an initial set of agents; having at least one agent in the initial agent set execute a target sub-task according to the task dependency graph to generate an intermediate result; having a critic agent evaluate the intermediate result to generate a quantified confidence score; and, based on a comparison of the confidence score with at least one preset low and high thresholds, executing one of the following feedback control steps: triggering a topology reconstruction mechanism, triggering a prompt word optimization mechanism, or solidifying the intermediate result. This method significantly improves the robustness of the system and the efficiency of computational resource utilization while ensuring the solution rate of complex tasks, achieving intelligent, efficient, and adaptive multi-agent cooperation.

This invention discloses a satellite communication terminal simulation task orchestration system and device based on intelligent scheduling. It adopts a microservice architecture, with five modules working collaboratively via RESTful APIs or gRPC. The system constructs a multi-dimensional global resource view, combining historical data to drive a regression prediction model to quantify resource requirements. The intelligent scheduling decision module models complex task allocation as a multi-dimensional optimization problem, using the PSO algorithm combined with a multi-objective fitness function to find the optimal solution, supplemented by a task preprocessing mechanism to improve efficiency and effectiveness. The system manages task dependencies using a DAG and deeply integrates with Kubernetes to achieve automated task orchestration, status monitoring, and fault recovery. This effectively solves the pain points of traditional scheduling, such as resource fragmentation and static configuration waste, achieving dual-dimensional global dynamic scheduling of business and resources. This significantly improves cluster resource utilization and simulation execution efficiency, adapting to the needs of large-scale, high-concurrency simulation scenarios.

The application discloses a public health performance evaluation task parallel scheduling method based on priority sorting, which comprises the following steps: acquiring multi-source information in a public health performance evaluation process, splitting the public health performance evaluation process into multiple evaluation task units, constructing task dependency relationship, and generating a task basic feature set; calculating the comprehensive priority of each evaluation task based on the task basic feature set; screening schedulable tasks according to the task dependency relationship, combining the priority and task relevance to generate a parallel task batch, determining the allocation relationship between the tasks in the parallel candidate task batch and the computing nodes, executing the evaluation tasks in parallel according to the allocation relationship, and obtaining the task execution result; feeding back and correcting the task scheduling parameters according to the task execution result, judging the rescheduling, and outputting the performance evaluation result by summarizing the completed tasks. The method can realize ordered parallel scheduling of tasks, improve the evaluation efficiency and resource utilization rate, and guarantee the accuracy and reliability of the evaluation result.

This invention relates to the field of distributed computing technology, specifically to a method and system for multi-agent collaborative task allocation based on a large model. It addresses the technical problem of existing methods struggling to effectively assess and mitigate the risk of blocking propagation along task chains in scenarios with complex task dependencies and semantic relationships, leading to low system resource utilization. The method includes: constructing a semantic blocking risk index based on the semantic blocking strength and semantic transmission capability of all preceding tasks of the task to be allocated, the exclusivity index of candidate agents, and the real-time load data of candidate agents; adjusting the observation window length of the time-series prediction model based on the semantic blocking risk index; predicting the future load and blocking trend of each agent using the adjusted time-series prediction model; and allocating tasks based on the prediction results and the semantic blocking risk index. This invention is applicable to multi-agent collaborative task allocation scenarios.

The application relates to the field of computer technology and artificial intelligence, and proposes an IDE scheduling platform task monitoring method and system based on a large model, wherein the method comprises the following steps: collecting task running data, system performance data and task running log text data from an IDE scheduling platform in real time; extracting key feature task dependency relationships, resource occupation trends and data partition size variances as a task feature matrix; inputting the task feature matrix into a Transformer large model to output the timeout probability of the corresponding task; triggering an early warning when the timeout probability exceeds a preset timeout threshold; fusing abnormal performance data in the task system performance data and fault keywords in the task running log text data to obtain an abnormal task feature matrix; inputting the abnormal task feature matrix into the Transformer large model to output a fault root cause by using an attention weight mechanism. The application solves the problems of low task monitoring efficiency, insufficient precision and resource waste of the IDE scheduling platform.

This application relates to the field of vehicle-mounted task scheduling technology, and discloses a task scheduling method, apparatus, system, vehicle, and readable storage medium. It addresses the problems of response delays, resource conflicts, and execution blocking inherent in existing static scheduling methods, which are prone to issues such as multi-task concurrency, platform resource fluctuations, and complex task dependencies in vehicle-mounted systems. The method includes: obtaining the task category of each task in the vehicle-mounted system, including periodic tasks, event-triggered tasks, and logically dependent tasks; constructing a task scheduling table based on task category, including task priority, task resource requirements, task dependencies, and task identifiers; acquiring real-time resource status information of the vehicle-mounted system; and determining whether to add the task to a thread pool for execution based on the task information and resource status information in the task scheduling table. This method combines task attributes with real-time resource status for dynamic scheduling, improving task execution determinism and enhancing the operational stability of the vehicle-mounted system.

This invention relates to the fields of distributed computing and virtualization technology, and provides a distributed task scheduling method and system based on disposable virtual machines. The method includes: receiving a task request submitted by a user; performing dependency resolution on the task request based on a dependency database to obtain a task dependency graph; creating a disposable virtual machine instance for the current task to be executed according to the execution order of each task in the task dependency graph; sending the execution data required by the current task to the disposable virtual machine instance, instructing the disposable virtual machine instance to execute the task in an isolated environment using the execution data; obtaining the task artifacts generated by the disposable virtual machine instance and storing them in a shared storage layer; and reclaiming resources from the disposable virtual machine instance after the current task to be executed is completed. This invention achieves complete isolated execution and automated flow scheduling of distributed tasks by automatically orchestrating tasks based on the dependency graph and combining it with a dynamic creation and destruction mechanism for disposable virtual machines.

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.

A Petri net-based task scheduling method for heterogeneous environments relates to the field of collaborative decision-making and resource optimization in edge computing systems. During scheduling, the input tasks and their dependencies are first modeled as directed acyclic graphs (DAGs), and then converted into Petri nets to uniformly represent task states, resource constraints, and device collaboration relationships, in conjunction with device status information. Subsequently, graph attention networks are used to extract PN topological features, and a dynamic transition triggering strategy is learned using a dual-deep Q-network. The task unloading and resource allocation sequences are optimized through a reward function, and the sequence validity is further verified by a sequence detection module. During task execution, tasks are scheduled in real-time according to a reinforcement learning strategy, and the network state and decision model are dynamically updated based on environmental feedback, forming a closed-loop optimization. This invention significantly improves task throughput and resource utilization in heterogeneous edge environments, and is particularly suitable for device-to-device collaborative scenarios with complex task dependencies and dynamically changing resources.

This invention provides a cross-vendor intelligent agent secure collaboration method and system based on a standardized protocol, relating to the field of intelligent agent collaboration. The method includes extracting protocol data to construct a dependency graph and converting standard fields; extracting operational features to calculate and coordinate permission vector conflict degrees; authorizing resource access based on the coordinated permission vectors and predicting release times; constructing a task dependency tree to decompose subtasks and allocate execution time periods; and correcting resource release predictions based on execution results. This invention solves the protocol compatibility and resource conflict problems in heterogeneous intelligent agent collaboration, improving system security and resource utilization efficiency.

This disclosure provides a task processing method, apparatus, electronic device, storage medium, and computer program product, relating to the field of computer technology, specifically large-scale models, natural language understanding, and intelligent agents, and applicable to task processing scenarios. The specific implementation scheme is as follows: a static graph scheduling system determines the task dependency data of the natural language task; the static graph scheduling system processes the natural language task according to a static flowchart; based on the task dependency data and tool description data of tools in a tool set, a dynamic flowchart representing the processing logic of the natural language task is generated; according to the dependency relationships of operators in the dynamic flowchart, the operators in the dynamic flowchart are executed sequentially, generating operator execution results; combining the execution results of each operator, the task processing result of the natural language task is generated. This disclosure can quickly adapt to new tools and complex tool combinations, improving the flexibility of the task processing process and meeting the needs of different business scenarios.

This invention discloses an artificial intelligence-based engineering resource scheduling optimization system and method, belonging to the field of engineering management technology. It establishes a resource status perception network by deploying IoT sensors and constructs a progress benchmark system based on the project plan. By comparing the actual progress with the progress benchmark system, it identifies tasks with excessive deviations that need to be scheduled. It constructs a task urgency classification model, extracts the progress dynamics, task dependencies, and resource supply characteristics of the tasks to be scheduled, generates a resource demand urgency level for each task, and generates a scheduling demand description. It matches the scheduling demand with the resource status, constructs a multi-objective optimization function considering spatial distance, workload, and type suitability, obtains a resource allocation scheme by solving the function, sends scheduling instructions according to the allocation scheme, monitors the execution status, tracks resource location and task progress in real time, and re-triggers the scheduling process when a new deviation is detected, forming a closed-loop dynamic optimization mechanism.

This invention discloses a multi-agent dynamic scheduling and skill sharing system and method, comprising a user interaction layer, a main scheduling layer, an execution layer, and a skill registration layer. The main scheduling layer uses a lightweight large language model to achieve task semantic understanding, subtask decomposition, and dependency analysis, constructing a directed acyclic graph (DAG) of task dependencies and automatically determining serial and parallel execution strategies. The execution layer consists of multi-domain-specific execution agents, supporting differentiated configuration of the underlying model according to task complexity. The skill registration layer decouples skills from execution agents through a global skill registration center, enabling cross-agent sharing, on-demand mounting, and hot-swappable expansion in a skill-as-a-service model. This invention significantly improves task matching accuracy, execution efficiency, and resource utilization, with auditable operation links and lower costs, making it suitable for complex task automation scenarios such as autonomous driving software development, enterprise process automation, and content creation.

The present application relates to the technical field of medical information parallel computing, in particular to a multi-thread parallel computing method and system for brucella spondylitis diagnosis parameters, the method comprising: a diagnosis task dependency graph construction step, a directed acyclic graph is constructed based on the calculation dependency relationship of the diagnosis parameters and the task priority is determined; an adaptive thread scheduling step, a dynamic load balancing is realized by using a work stealing strategy and a lock-free concurrent queue; a vectorized parallel computing step, a single instruction multiple data stream instruction is used to perform batch calculation on the diagnosis parameters; a feedback-driven optimization step, a closed-loop optimization is formed by dynamically adjusting the scheduling strategy according to the performance index, the four core modules are deeply coupled to realize synergistic effect.

The application provides a kind of edge cloud collaborative data processing system and method based on deep learning, related to edge cloud collaborative technical field, the task characteristic vector of edge terminal equipment is extracted from data task flow;Further construct task dependency graph, determine the allocation label of subtask processing through the resource allocation granularity of subtask in task dependency graph and data task flow;Confidence adjustment is carried out to each allocation label, to obtain the execution confidence of subtask in edge terminal equipment, further load transfer analysis is carried out to edge terminal equipment, to obtain the load transfer amount of edge terminal equipment;When load transfer amount is less than preset load transfer threshold, the subtask in data task flow is executed asynchronously in edge terminal equipment, otherwise, the data task flow in edge terminal equipment is sent to cloud server for batch processing through edge cache server, can be realized in the condition of limited heterogeneous computing resources, the task load between edge terminal equipment and cloud server is divided.

The present disclosure provides a task execution method and device, electronic equipment and storage medium, relates to the technical field of artificial intelligence, in particular to deep learning, natural language processing and large language model technology. The method comprises: performing semantic analysis on task information, determining a plurality of sub-tasks according to the analysis result; generating a task dependency graph according to the dependency relationship between the plurality of sub-tasks; generating a workflow configuration file according to the information of each sub-task node in the task dependency graph; and executing the plurality of sub-tasks according to the workflow configuration file to obtain the execution result of the task information. The present disclosure improves the logic, stability and efficiency of complex task execution.

A complex request that exceeds a predefined complexity threshold is received. The complex request is decomposed into a plurality of subtasks. A task dependency graph is generated to define an execution order for the plurality of subtasks. For each subtask, a respective AI model is selected from a plurality of available AI models based on task-specific requirements and the capabilities of the respective AI model. Each subtask is routed to its respective selected AI model according to the task dependency graph, wherein at least two of the plurality of subtasks are processed in parallel. Responses from the respective selected AI models for the plurality of subtasks are aggregated to form a consolidated response. The consolidated response is then transmitted to a requester.

The application belongs to the technical field of artificial intelligence and natural language processing, and discloses a multi-agent collaborative dialogue as a service business agent construction method and system, which comprises the following steps: performing hierarchical intent recognition on a semantic request description, constructing a task dependency directed acyclic graph through recursive decomposition and dependency relationship recognition, and generating a task plan; combining short-term memory sliding window management and long-term memory semantic vector retrieval to generate an enhanced context representation; adaptively selecting and executing a corresponding reasoning mode for each task; encapsulating tools by using a preset model context standard protocol, and constructing a tool capability dynamic registration and scheduling management mechanism through a skill registration center; according to the tool capability dynamic registration and scheduling management mechanism, aggregating and arranging the task execution results and uniformly formatting them, and returning the formatted results to the user. The application realizes automatic decomposition and dynamic arrangement of a single natural language instruction to a multi-step task.

This invention provides a method and system for dynamic power consumption control of industrial terminals based on load prediction. The method includes: determining idle time periods based on the execution time information of each task in the task queue of the industrial terminal; if no tasks are being executed, determining candidate power-off power domains based on the target functional modules dependent on the last task before the idle time period and the first task after the idle time period, combined with the affiliation relationship between functional modules and power domains; performing islanding region analysis based on the electrical relationships between candidate power-off power domains to obtain target power-off power domains, and generating a power-off strategy for each target power-off power domain based on the duration of the idle time period and the recovery energy cost of each target power-off power domain; controlling the corresponding target power-off power domain to enter a power-off state based on the power-off strategy of each target power-off power domain, and maintaining its power-off state during the duration of the idle time period. This invention achieves fine-grained control of power consumption of industrial terminals.

A multi-task dynamic scheduling method and device, the method comprising: sequentially performing dependency check, resource conflict check and hard constraint check on each detection task in a detection task set, generating a single-task scheduling plan for each detection task passing all checks; for each detection task not passing any of the checks, determining its corresponding associated detection task through resource competition relationship and task dependency chain, and generating a corresponding multi-task collaborative scheduling plan by combining a multi-objective optimization algorithm; and scheduling the detection tasks according to the single-task scheduling plan and / or the multi-task collaborative scheduling plan. The method realizes automatic and intelligent scheduling of detection tasks, significantly improves scheduling efficiency, effectively reduces detection task cost through a multi-objective optimization algorithm, and improves resource utilization by collaboratively scheduling detection tasks with resource competition and task dependency.

The application provides a kind of intelligent terminal computing power distribution and processing control method based on vehicle-mounted video stream, which comprises: generating video processing task based on vehicle-mounted video stream and user service intention, constructing task dependency graph based on the interdependence of each video processing task in input data area, output data use and execution timing;Topological sorting is carried out on the task dependency graph to generate a task execution sequence;Based on the computing complexity characteristics of each task in the task execution sequence and the total amount of schedulable computing power resources of the intelligent terminal, allocate corresponding computing power resource share for each task;According to the computing power resource share, generate binding instructions for processor core and acceleration unit to obtain task scheduling instruction set;After monitoring that each task in the task execution sequence completes its computing process, release the occupied computing power resources.The application improves the real-time response certainty and computing power resource utilization rate of the vehicle-mounted intelligent terminal in complex and variable road environment.

This invention relates to the field of computer technology, specifically to an instruction control method, apparatus, device, and medium based on write-response words. Firstly, this application breaks away from the traditional reliance on hardware primitives by using a mechanism where asynchronous functional components write a write-response word to the corresponding register address area after completing a task. Traditional solutions suffer from limited hardware primitive adaptability, making it difficult to efficiently utilize resources across different cores. This solution, however, uses a unified write-response word to feedback completion status, enabling flexible resource allocation on demand and significantly improving resource utilization. Secondly, this solution does not involve complex API calls. The write-response word mechanism is simple and direct, easily adapting to changes in the number of processor cores, enhancing system scalability. Thirdly, traditional solutions struggle with complex dynamic cross-core task dependencies, while this solution can accurately grasp task completion status through write-response words, flexibly scheduling tasks and effectively adapting to complex dynamic scenarios.

This invention relates to the field of data processing, and more specifically, to a dynamic task scheduling method and system for AI agents using multi-model collaborative reasoning. The method includes: collecting historical data from computing nodes; statistically analyzing the mean, standard deviation, and covariance of task duration and queue length; calculating a risk adjustment factor based on the covariance and determining a directional switch; penalizing and adjusting the mean duration based on both factors to obtain the risk perception prediction duration; constructing a directed acyclic graph (DAG) of task dependencies; calculating the directed path inertia based on the signal-to-noise ratio of each node; and obtaining the scheduling priority by combining the dynamic upward rank and a suppression factor; and selecting the computing node that minimizes the earliest dynamic completion time for each task according to priority. This invention suppresses short-term scheduling oscillations by distinguishing between real congestion and random noise, and improves the stability of system throughput and task completion time by stabilizing critical path identification through directed path inertia.

The application relates to the field of data processing and task scheduling, in particular to a model publishing method, an electronic device and a program product. The method is used for solving the problems that a model publishing process depends on manual connection, a state is difficult to track, and it is difficult to recover execution according to a dependency relationship after failure. The method comprises the following steps: receiving a task publishing request corresponding to a target model; analyzing the task publishing request to generate a plurality of subtasks and a task dependency graph thereof; executing the plurality of subtasks based on the task dependency graph through a distributed task scheduling engine, and recording task states of the subtasks; when detecting that the task execution fails, recovering the execution of the publishing of the target model according to the task states of the subtasks and the task dependency graph. The scheme can realize automatic arrangement, state traceability and failure recovery of the model publishing process, and improve the automation degree, stability and execution efficiency of the model publishing.

The present application relates to the technical field of multi-agent collaboration, and particularly relates to a task execution method and system based on multi-agent collaboration, which comprises the following steps: performing semantic analysis and multi-granularity decomposition on user task instructions, generating a subtask dependency structure and storing it in a dynamic task pool; performing collaborative planning and pre-execution on the subtasks to be executed, generating a context snapshot and performing Push writing to a history state stack; retrieving an evidence chain and extracting a set of fact triplets based on a domain knowledge base, performing consistency comparison on a candidate reasoning path based on the structured evidence triplets, and outputting a conflict confidence and a consistency score; triggering a pop stack and physically clearing intermediate data in the error branch when the consistency score is lower than a threshold, restoring the historical context and injecting negative feedback to generate a new reasoning branch and return to continue pre-execution; outputting the result and entering the next subtask when the verification is passed; thereby improving the controllability and auditability of multi-agent collaborative task execution.

The application provides a task execution method and system, and relates to the technical field of artificial intelligence.In the method, firstly, a target task is decomposed into a plurality of parallel executable subtasks, and a corresponding subtask agent is created for each of the plurality of parallel executable subtasks; then, the plurality of parallel executable subtasks are written into a shared task queue, a task dependency graph is established based on the dependency relationship among the plurality of parallel executable subtasks, and all the subtask agents are started in parallel, so that the subtask agents atomically obtain tasks from the shared task queue and execute the tasks based on the task dependency graph; finally, the execution results of all the subtask agents are integrated to obtain the execution result of the target task. In this way, the accuracy and efficiency of task execution are improved.