202 results about "Task completion" patented technology

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

The invention provides an agent visual language navigation method and system based on task completion prediction. The method comprises the step of constructing a dual-drive structure composed of a self-adaptive mixed pooling mechanism and a task completion analysis module. Firstly, in the visual information processing process, a dynamic weight distribution strategy is adopted to carry out multi-scale adaptive mixed pooling on panoramic features, so that the fusion effect of local and global semantic information is optimized, and the retention capability and semantic integrity of navigation historical information in a dynamic topological map are improved. And then, inspired by a human navigation cognitive behavior mechanism, a task completion analysis module is designed and introduced, and the task execution progress is dynamically estimated based on the recognition condition of a key landmark in a navigation path, so that an intelligent agent is driven to preferentially select a key path node and invalid exploration is reduced. And finally, realizing efficient understanding and execution of the natural language instruction by the intelligent agent through a multi-round cyclic cross-modal reasoning and action prediction mechanism.

The invention discloses a multi-agent cooperation system construction method, a medium and equipment, and the method comprises the steps: carrying out the task modeling of a target business scene, and constructing a task dependence graph; initial cooperation strength weights are set for the atomic tasks with the cooperation relationship, and multi-stage cooperation training courses from easy to difficult are generated based on the cooperation complexity of the atomic tasks; the intelligent agent is controlled to execute a task in a training course, interaction behavior data is collected, the overall task completion efficiency is calculated, the cooperation weight is dynamically updated, and interaction data and the updated weight are input into a reinforcement learning model to iteratively optimize a cooperation strategy; and finally, solidifying the converged cooperation strategy into the constructed multi-agent cooperation system. According to the invention, through the combination of course learning and reinforcement learning, the cooperation efficiency and robustness of the system in a complex business scene can be significantly improved.

The embodiment of the invention discloses a distributed data transfer method and device based on fault prediction and a medium, belongs to the technical field of data migration, and solves the problem that when a distributed system breaks down, the timeliness of task completion is seriously influenced. Comprising the following steps: performing health degree evaluation and stable operation duration prediction on nodes in a distributed system through a preset fault prediction algorithm to obtain a node fault prediction result; wherein the fault prediction result at least comprises a node in which a fault is predicted to occur, fault occurrence time and a to-be-transferred task corresponding to the node in which the fault is predicted to occur; performing priority analysis on the to-be-transferred tasks based on the time sequence diagram neural network to obtain task priorities; determining a target node based on the multi-dimensional features corresponding to the nodes and the association relationship between the nodes; and transferring the task to be transferred to a target node through a preset multi-stage progressive transfer strategy according to the node fault prediction result and the task priority.

The invention discloses a construction management system and method based on multi-source data analysis, and relates to the technical field of building construction informatization and intelligent management and control, and the method comprises the steps: capturing a front path task completion signal and a subsequent task starting instruction; obtaining preposed task completion time, a dynamic condition type and a threshold parameter; executing time logic verification based on the dynamic condition type, and judging a construction dynamic context ready state; bIM design coordinates, field positioning coordinates and space tolerance parameters of the construction machinery are obtained, and space logic verification is executed by calculating space deviation; when both the time verification and the space verification pass, subsequent task state conversion is allowed, and otherwise, blocking is carried out; and finally generating a structured report containing all verification parameters and results.

The embodiment of the invention provides a context information management method and device based on hierarchical memory, equipment and a medium, and the method comprises the steps: analyzing a task request to generate a sub-task node sequence containing a target description and acceptance function, and arranging a plurality of agents to cooperatively execute a task, and after the audit is passed, a complete execution context is stored in a long-term memory, and a structured abstract is generated and stored in a short-term memory, so that the problem that the context management mechanism of the existing multi-agent system is single is effectively solved, stable maintenance of cross-session cognitive continuity is realized, and the efficiency of the multi-agent system is improved. The method improves the execution reliability of a complex long-process task, optimizes the information storage and retrieval efficiency through hierarchical memory, reduces the risk of semantic deviation accumulation and amplification, clarifies the task target and acceptance standard of each stage, enhances the multi-agent cooperation consistency, and improves the efficiency of task execution. And the execution efficiency and the task completion quality of the intelligent agent system in a complex application scene are comprehensively improved.

A task management system detects condition(s) are satisfied with respect to task record(s), and triggers action(s) at least in part by substituting information from the task record(s) into placeholder(s) of user-modifiable template(s) to prompt large language model(s) for generating narrative(s) about how the condition(s) were satisfied. The triggered action(s) retrieve information from identified task record(s), substitute value(s) from the record(s) into the placeholder(s) of the user-modifiable template(s), and trigger(s) call(s) to large language model(s) to generate task completion narrative(s) or other narrative(s) for the task record(s). The narrative(s) may be stored in narrative field(s) of the record(s) for use in displaying the narrative(s) on a user interface, email notification, or other message.

The invention discloses a distributed computing task scheduling security guarantee method and system based on dynamic trust evaluation, and the method comprises the steps: collecting and preprocessing the operation state data of each computing node in real time, and dynamically calculating and updating the trust degree of each node according to the operation state data; according to the credibility and in combination with node resource loads, the tasks are only allocated to nodes with the credibility not lower than a preset threshold value and sufficient resources to be executed; the node state is continuously monitored in the task execution process, when a node fault is detected or the node trust degree is lower than the threshold value, task rescheduling is triggered, and the affected task is migrated to the remaining nodes with high trust degree and sufficient resources to continue to be executed; the key data of task allocation, node selection and task completion state are written into the block chain by using the characteristics of decentralization, non-tampering and encryption protection of the block chain so as to ensure the transparency and data security of the task execution process.

The invention discloses a message-driven enterprise multi-service system centralized to-do processing method and system, and the method comprises the steps: S1, obtaining resource investment and task processing data, and obtaining a resource consumption and task state cluster through clustering; s2, using a regression algorithm to analyze correlation between the two, and determining a resource utilization rate change trend; s3, when the threshold value is exceeded, calculating a task completion rate statistical characteristic to obtain a resource optimization index; s4, constructing an interactive model by using a decision tree in combination with historical data, and judging an input strategy adjustment point; s5, rendering visual resource distribution; s6, abnormal tasks are screened, and an optimization area is determined; and S7, updating an instrument panel to obtain a decision view. Through data clustering, correlation analysis and dynamic adjustment, the resource and task matching degree is improved, and decision scientificity and efficiency are enhanced.

The invention provides a complex task multi-agent collaborative disassembling method and system based on a business process, and relates to the technical field of artificial intelligence, and the method comprises the steps: constructing a graph through analyzing a business process document, matching a complex task with a process node, identifying a closed loop dependence path, and selecting an agent based on a constraint logic formula. And establishing a causal tracing chain to process abnormal conditions, and performing semantic alignment to ensure data transmission between subtasks. According to the method, the automation degree and the execution efficiency of multi-agent cooperative processing of complex tasks are improved, and the fault-tolerant capability of the system and the reliability of task completion are enhanced.

The invention provides a laser cutting production line task automatic allocation control method based on multi-device state coupling analysis, and belongs to the technical field of intelligent manufacturing and industrial automation. The method comprises the following steps: constructing a dynamic closed-loop control process through a central control scheduling system: receiving a task information packet of an MES; constructing an equipment state vector based on a real-time station state, and introducing a dynamic weight factor set to generate a weighted state vector; performing task triggering judgment through a coupling triggering judgment function in combination with the task dependency graph and historical task records; when the conditions are met, a task instruction is issued to the target station; and feeding back the state and updating the historical record after the task is completed. The invention further relates to AGV intelligent scheduling, visual positioning compensation, process parameter dynamic adjustment, predictive conflict detection, weight self-optimization and the like. According to the method, the production line cooperation efficiency is remarkably improved, manual intervention and system delay are reduced, and the method is suitable for an intelligent laser processing scene in which multiple devices run in parallel.

The invention relates to the technical field of data analysis, in particular to a cloud-based teaching platform student learning behavior trajectory analysis method, which comprises the following steps: acquiring a student interaction log, extracting task completion and control operation discontinuity points, identifying continuous learning behaviors and switching types, constructing a candidate period sequence, analyzing time and label changes, and generating a trajectory analysis result. According to the method, the non-interaction time period of the student in task switching can be identified by collecting the time interval between task completion and first control operation, so that the potential attention distraction or task interruption behavior of the student is captured, and the interaction characteristic and the duration of the continuous behavior segment are combined; and active and inactive learning period switching characteristics are further marked, and a task label difference degree and a time interval are introduced in the process of constructing a learning period sequence as a screening basis, so that the analyzed learning paragraph is ensured to have content continuity and behavior pattern difference, and the recognition capability of rule switching behaviors in trajectory analysis is enhanced.

Configuration-driven conversational artificial intelligence (AI) for task completion is disclosed. An AI-first, conversational approach may be utilized that leverages the capabilities of large language models (LLMs) to streamline the process of mapping user queries to a series of actions (e.g., application programming interface (API) calls). Such implementations may provide the user with a more intuitive and efficient experience.

A computer-implemented method, apparatus and system is provided for robotic task completion from natural language requests. The method may include: receiving a natural language command, processing the natural language command with a generative large language model to extract an intent and associated context, creating a three-dimensional (3D) open-vocabulary semantic scene graph of the environment, associating the scene graph with the intent and associated context, creating, based at least in part on the scene graph, an execution plan comprising a sequence of actions to complete the natural language command, and generating executable code or tool calls corresponding to one or more actions in the sequence of actions, and controlling one or more robotic manipulators and / or actuators to perform one or more actions of the sequence of actions based on the execution plan.

The invention provides a self-adaptive personalized learning path generation method and system, and the method comprises the steps: extracting a target capability list from an existing training model or post competency requirements, and constructing a capability map; based on a user historical course test result and a practical operation task completion condition, generating a user capability state vector by adopting a weighted scoring mechanism; performing priority scoring on the capability nodes, screening the capability nodes according to the priority score to form a learning path, distributing learning resources in combination with user preference, and generating a task scheduling plan; issuing a task according to the task scheduling plan, and collecting behavior data; calculating a behavior effectiveness score, identifying an abnormal task of which the behavior effectiveness score is lower than a threshold value, and adding a behavior deviation label; and based on the behavior deviation label matching correction strategy of the abnormal task, adjusting a path and a scheduling plan, and outputting a corrected learning path and a scheduling table.

The invention discloses a service robot fine-grained task planning method based on hierarchical collaboration. Firstly, a scene graph and an article knowledge graph are constructed; then, the task instruction is converted into an abstract high-level action sequence through high-level task planning, and the abstract high-level action sequence is converted into a fine-grained low-level action sequence through low-level task planning; and finally, converting the low-layer action into a plurality of action primitives, executing the action primitives in a simulation environment, selecting feasible action primitives, executing the feasible action primitives in a physical world, and synchronously monitoring the running state of the robot. If the operation state is stable, selecting an optimal action element for execution; if the operation state is not stable, the operation state is fed back to a low-layer task planner; if the comprehensive scores of all the action elements are smaller than a score threshold value, feeding back to a low-layer task planner; and repeating the steps until the task is completed. Accurate mapping from task instructions to physical actions is achieved, and the fine granularity and reliability of task execution of the robot are improved.

The invention relates to the technical field of intelligent inspection system and multi-device cooperative scheduling, and discloses an inspection method based on multi-device cooperation. Modeling inspection tasks and equipment in a unified manner in a scheduling period, registering time, types and maximum operation duration parameters, and constructing an executable relation of the task equipment; calculating residual response time, and generating normalized task priority according to the residual response time and the execution duration; and setting task unique allocation, equipment maximum load and task performability constraint, introducing Lagrange optimization, selecting tasks for equipment according to task density, iteratively updating until convergence, generating an execution sequence sorted according to residual response time, and issuing the execution sequence. Through the steps, task attributes are unified, the equipment capacity is quantified, unbalance caused by single time or duration sorting is avoided, timeliness and load are considered under multiple constraints, tasks can be executed, the equipment is not overloaded, and the resource utilization rate and the task completion rate are increased.

The invention discloses an agent and tool chain collaborative data processing method and device and a medium, and relates to the technical field of agent application. The method comprises the steps of receiving a data processing task target and related configuration parameters input by a user, and initializing task context data based on the task target and the configuration parameters; executing a circular processing process by an agent based on a ReAct framework, and dynamically adjusting a task strategy by iteratively executing a thinking stage, an action stage and an observation stage until a task completion condition is met; in the circular processing process, based on standardized tool calling instruction data generated by the intelligent agent, cooperatively calling the MCP tool chain and a plurality of tools in the external tool adaptation layer to execute a data processing task; performing aggregation processing and data verification on the multi-source result data returned by the tool execution to generate integrated analysis result data; and displaying task execution process data and a final analysis result in real time through a front-end interaction interface, and dynamically adjusting a task execution process based on user intervention instruction data.

The invention relates to the technical field of automatic programming, in particular to a front-end and back-end code generation and deployment system based on a text AI model, and the system comprises a demand analysis module, a code generation module, an environment adaptation module, a task scheduling module and a process optimization module. According to the method, through the intelligent task scheduling and environment adaptation strategy, the efficiency and accuracy of front and rear end code deployment are remarkably improved, the task execution path and time interval are optimized, the resource utilization rate of the system is increased, the priority and execution area of task deployment are accurately matched, redundant calculation and resource waste are reduced, and the task deployment efficiency is improved. The execution efficiency of distributed tasks is accelerated, an intelligent adaptive script identifies and adjusts environment differences in real time, the problems caused by environment configuration differences are solved, the code deployment automation and precision are improved, resource allocation and task scheduling path selection are optimized, the system can quickly meet the complex deployment requirement, and the deployment efficiency is improved. And efficient completion and quick response of tasks are ensured.

The invention relates to the technical field of computing resource optimization, and discloses a joint resource allocation and task unloading optimization method and system, and the method comprises the steps: constructing a global resource view to sense the real-time residence state of each computing node cache line in a distributed system; a cache-aware task unloading and data prefetching combined optimization model is established, decision variables of the model include task unloading variables and data prefetching variables at the same time, and cache capacity constraints are constructed in an endogenous mode by means of a task unloading scheme so as to predict a cache line set to be expelled due to task execution; the joint optimization model is solved with the purpose of minimizing the total task completion time, a task unloading decision and a collaborative prefetching decision are synchronously generated, and the prefetching decision is determined according to the predicted expelling set and the task data dependency relationship. According to the method, task unloading and data prefetching are cooperatively decided in a unified optimization framework, so that the problem of mutual interference caused by independent optimization of task unloading and data prefetching is solved, and global active arrangement of calculation and cache resources is realized.

The invention discloses a dynamic optimization method for multi-agent task allocation in a distributed environment, and the method comprises the steps: carrying out the scoring of an unexecuted task of each agent through the operation state of each agent when each agent is about to complete a currently executed task; and broadcasting the scores with lower scores in all the unexecuted tasks to other agents in a broadcast form, scoring the received unexecuted tasks by all the agents receiving the unexecuted tasks based on the running states of the agents, and broadcasting the scoring results to other agents or directly sending the scoring results to the agents which are broadcasted previously. The intelligent agent broadcasted in advance performs independent highest-score screening on each non-executed task after receiving scores of the non-executed tasks, distributes the non-executed tasks based on a screening result, and performs real-time adjustment on subsequent executed tasks based on the state of each intelligent agent after completing the tasks. Therefore, the completion quality and efficiency of the task are improved.

The invention discloses an order type task planning method and system for real-time tasks, and relates to the field of task planning. According to two task planning modes of active request scheduling and forced priority scheduling, a task unit autonomous request model, a control center minimum cost distribution model and a multi-stage optimization model are constructed, and an improved genetic algorithm is adopted to perform task resource distribution and time sequence optimization. The advantages of the planning mode in the aspects of task completion timeliness, resource consumption, task success rate and response capability are quantitatively compared, optimization is carried out by combining a secondary autonomous request and a distribution mechanism with a forced priority strategy, the efficient planning and scheduling requirements of real-time tasks can be effectively met, the solving efficiency is remarkably improved through the improved genetic algorithm, and the real-time task scheduling efficiency is improved. And a forced priority mechanism is adopted to optimize secondary autonomous request and distribution, so that the comprehensive cost of the system can be further reduced on the basis of guaranteeing the task execution effect, and the generalization ability of the model under different task scenes and resource conditions is verified at the same time.

The invention discloses an agricultural production task scheduling and path optimization method and system, a medium and a product, and relates to the technical field of path optimization. The method comprises the steps of obtaining initial multi-source data, generating a to-be-executed task set according to crop state information, and based on the task set and the initial multi-source data, taking minimization of total energy consumption and maximization of task completion rate as optimization objectives, adopting a mixed quantum-classical algorithm for solving to obtain an initial task sequence and an energy consumption optimal path of each agricultural machine terminal; continuously monitoring the dynamic multi-source data to judge whether a preset dynamic event is triggered or not, rescheduling tasks influenced by the dynamic event through a conflict resolution mechanism based on the game theory when the dynamic event is triggered to generate an updated task sequence and an execution path, and executing the task sequence and the execution path according to the updated task sequence and the execution path. And issuing the updated task sequence and execution path to the corresponding agricultural machine terminal. By implementing the technical scheme, tasks can be reasonably scheduled and paths can be optimized.

This invention discloses a multi-agent task allocation method based on network coverage dynamic matching control, comprising the following steps: Multiple agents self-organize into a network and divide it into N sub-networks. The sub-networks adopt a leader-follower model, with the leader managing and making decisions for each sub-network. Each sub-network acquires its current environmental state and uses high-level decision-making from a hierarchical deep reinforcement learning model to choose to explore a task domain or find other sub-networks. The agents move using low-level decision-making from the hierarchical deep reinforcement learning model until they find a task domain or other sub-networks. The sub-networks that have found a task domain or other sub-networks are segmented or merged through network topology control to form a covering sub-network or a new sub-network. Agents in the covering sub-network complete task execution using a task allocation optimization model, and after task completion, they transition to the new sub-network. This method can utilize a limited number of multi-agent agents to explore task distribution and complete task allocation in environments with missing network infrastructure and unknown task distribution, thereby reducing task response time and improving task completion rate.

This application provides an autonomous collaborative scheduling method, device, robot, and storage medium, belonging to the field of intelligent collaborative scheduling technology. The method includes: receiving a broadcast message of a scheduling task; parsing the broadcast message to obtain the parsed scheduling task information; acquiring the status information of surrounding robots; autonomously making a decision based on multi-dimensional collaborative rules, combined with its own status information and the status information of surrounding robots; if it is determined to execute the scheduling task, determining the task execution priority and task execution route based on the scheduling task information and its own status information; broadcasting a task confirmation message, task execution priority, and task execution route to surrounding robots, and providing feedback on the task completion status to surrounding robots after the task is completed; if it is determined not to execute the scheduling task, broadcasting a task non-execution message and the reason for non-execution to the collaborative cluster. This application can improve overall scheduling efficiency.

This invention relates to the field of data processing and discloses a method, apparatus, computer device, and readable storage medium for generating Gantt charts. The method includes: acquiring user stories of the iterative process of a target task; determining the iteration data corresponding to each user story; determining the cycle of each task and the task completion progress of each target task subject, thereby obtaining the individual work status of each target task subject; and finally, generating a Gantt chart based on the iteration tag, cycle, task completion progress, iteration plan start time, iteration plan end time, and each target task subject. Based on this, the present invention enables the Gantt chart to display the work status of different target task subjects under the same target task, and to reflect the overlap of R&D resources / development resources in the development process of the target task, thereby clearly displaying the development progress of the target task.

The application relates to a task scheduling method and system based on a zero-work system, and relates to the technical field of data processing. The method comprises the following steps: receiving a task publishing instruction, calling a task level and a task type based on the task publishing instruction; determining a capability level based on the task type, and inquiring whether the capability level is less than preset capability information of an order-receiving user; if the capability level is less than the preset capability information of the order-receiving user, filtering the task for the order-receiving user; if the capability level is not less than the preset capability information of the order-receiving user, opening a task receiving permission for the order-receiving user; receiving a receiving instruction of the order-receiving user based on the opened task receiving permission, generating a task package based on the receiving instruction, and taking down the task; collecting identity information based on the task package, and after the identity information is consistent with preset order-receiving user information, a supervision method is matched and supervision is performed. The application has the effect of improving the task completion rate.

The invention relates to a cooperative processing method for a reservoir project operation management task and a model manager thereof, and aims to realize optimization of a task allocation strategy by dynamically adjusting performance requirements and task excitation of asynchronous subtasks in combination with computing power of nodes and real-time asynchronous subtask progress so as to improve the task allocation efficiency. Therefore, the problems of large response delay and low resource utilization rate in a traditional centralized management mode are solved, and the method has the advantages of dynamically adjusting the task allocation strategy, optimizing the resource utilization rate, improving the task cooperation efficiency and shortening the overall task completion time.

The invention provides a chip system and a task processing method, and the chip system comprises a task scheduling module which is used for cutting a calculation task into a plurality of calculation sub-tasks, and generating a task cutting signal corresponding to the calculation task; the synchronization module comprises a routing unit and a plurality of task monitoring units, and the routing unit is used for receiving the task cutting signal and routing the task cutting signal to a target task monitoring unit in the task monitoring units according to the number of idle monitoring channels contained in the task monitoring units; at least one calculation module in the plurality of calculation modules is used for receiving the plurality of calculation subtasks from the task scheduling module and executing the plurality of calculation subtasks, and the at least one calculation module is further used for generating task completion signals corresponding to the calculation tasks in the process of executing the plurality of calculation subtasks and sending the task completion signals to the task scheduling module. And the task completion signal is routed to the target task monitoring unit through the routing unit, so that the target task monitoring unit monitors the execution states of the plurality of calculation sub-tasks according to the task cutting signal and the task completion signal. According to the invention, the routing unit is introduced into the synchronization module, so that load balancing among a plurality of task monitoring units is facilitated.

The invention discloses a crowd sensing task allocation method based on direction constraint, and the method is suitable for a multi-participant and multi-task mobile crowd sensing scene, and is superior to a traditional task allocation method in the aspects of task allocation efficiency and resource utilization rate. The method comprises the following steps of: establishing a task sorting list at each vertex of a sensing area, and comprehensively considering a participant path direction, a distance budget and a dynamic progress constraint; and finding out a region vertex which is most matched with the path direction of the participant, traversing a task list of the vertex, performing feasibility verification on each candidate task, and calculating a dynamic progress constraint value to obtain a final task allocation scheme. According to the method, the influence of the moving direction of the participant and the distance budget is considered, the allocation strategy is dynamically adjusted according to the real-time position and the task distribution, the task completion rate and the data acquisition quality are effectively improved, and the method has good practical guiding significance.