1673 results about "Execution plan" patented technology

The invention discloses a method and a system for collecting decision data by an intelligent agent driven by a multi-modal large model. The method comprises the following steps: collecting original data of a predetermined sensor, calculating information entropy and a normalized mass score, and generating a fusion feature vector through self-adaptive multi-modal information fusion; time sequence sensitive multi-mode alignment processing is carried out on the image, and time sequence alignment features are obtained by combining timestamp embedding and a self-attention mechanism; based on this, decision distribution is generated by using a Bayesian neural network, uncertainty is evaluated, and a final decision and index set is generated; evaluating a task score in combination with task description, and making an execution plan according to a resource state; initializing the model, generating synthetic data, optimizing the model and storing experience. According to the invention, the efficient decision-making process of the intelligent trolley is realized, and the execution capability and task completion precision of the intelligent trolley are improved.

The invention belongs to the technical field of multi-target global dynamic production scheduling, and discloses a manufacturing resource dynamic production scheduling data comprehensive processing method, which comprises the following steps: acquiring multi-source heterogeneous data, constructing a field mapping table, constructing an equipment fingerprint database in combination with historical equipment performance data, dynamically adjusting confidence coefficient weight, and further judging an equipment state. Based on an equipment state judgment result, integrating operator report data and multi-source heterogeneous data through a preset rule base trigger event, and generating an abnormal event flow with a context tag; based on the abnormal event type and the equipment state judgment result, a recommendation scheme is constructed through a production scheduling knowledge graph, and a production scheduling instruction set is generated; according to the production scheduling instruction set, generating a local optimization scheme and a global optimization strategy, and forming a final execution scheme; calculating a resource utilization rate and a bottleneck process index through the 3D virtual workshop model, and generating a difference analysis report; according to the method, global resource scheduling and closed-loop iteration are realized, and the production efficiency and the system robustness are improved.

The invention relates to a computing power network resource scheduling method. The method comprises the following steps: acquiring floating point operation performance parameters and operation states of node processors and energy index data of data centers where the node processors are located, and calculating to generate a node list; constructing a global resource pool based on the list, and generating a resource distribution table containing the total calculation power of the region; obtaining calculation requirements and time delay constraints of the task queue, extracting feature vectors in combination with the resource distribution table, and generating a resource utilization rate table; obtaining network link flow data, predicting a link congestion probability through a long short-term memory network, and generating a flow control strategy table; and finally, updating resource pool network constraints according to the resource utilization rate table and the flow control strategy table, and remapping tasks by taking node effective computing power as a weight to generate a scheduling execution scheme. According to the method, accurate quantitative evaluation of the computing power resources is realized, the matching precision of tasks and the computing power resources is effectively improved, the resource utilization rate of the computing power network can be remarkably improved, and the overall scheduling efficiency and stability of the system are enhanced.

Some implementations related to using a large language model (LLM) in generating (and potentially refining) a plan for the execution of a long-horizon robotic task. Various implementations include processing, using the LLM, a free-form natural language instruction and textual feedback to generate LLM output. In many implementations, the free-form natural language instruction describes the robotic task. In additional or alternative implementations, the textual feedback can include task-specific feedback, passive scene description feedback, active scene description feedback, one or more additional or alternative types of environmental feedback, and / or combinations thereof. In some implementations, the system can select one or more robotic skills to perform based on the LLM output.

The invention relates to the technical field of industrial equipment scheduling, in particular to a HarmonyOS industrial equipment intelligent scheduling and real-time cooperative control method, which comprises the following steps: S1, industrial equipment autonomous behavior design and dynamic role switching based on bionic swarm intelligence; by introducing bionic swarm intelligence, multi-modal perception, transfer learning and block chain technologies, the scheduling efficiency and task execution capability of industrial equipment in a complex dynamic environment are remarkably improved, and in the actual use process, the equipment can dynamically adjust task priority and resource allocation according to the real-time operation state and scene change, so that the service life of the equipment is prolonged. And meanwhile, environment data is collected by utilizing a multi-mode sensor, prediction and reasoning are performed through a machine learning model, and the equipment can pre-judge a fault risk and optimize a task chain execution scheme, so that the fault rate and energy consumption in the production process are reduced, and the production efficiency and stability are remarkably improved.

The invention relates to the technical field of artificial intelligence, in particular to a multi-model agent collaboration method and system, and the method comprises the following steps: obtaining a task execution plan and an actual state, recognizing a deviation node, generating a synchronous deviation list, analyzing a task trend, labeling a progress label, recognizing a tool influence section, screening uninfluenced nodes, and judging the distribution efficiency. And extracting abnormal fluctuation, analyzing resource and task cycle difference, and generating a monitoring structure index. According to the method, task deviation identification is realized by extracting the task plan number and the time interval and comparing the real-time state of the intelligent agent, the plan execution monitoring precision is improved, the perception of progress change is enhanced, and the task distribution efficiency is evaluated by performing cross comparison on fluctuation tasks and tool calling data, identifying interference sections, mapping running logs and dispatching data. And in combination with resource release and task fluctuation differences, progress monitoring indexes are extracted, and the cooperation efficiency and the system regulation and control capability are improved.

The invention relates to the technical field of workshop scheduling, in particular to a multi-online collaborative scheduling method and system for a flexible intelligent processing production line, and the method comprises the steps: building a numerical control parameter model for processing equipment, decomposing a processing program into basic process instruction units, combining the numerical control parameter model and the real-time operation state of the equipment to analyze the adaptation degree of the basic process instruction unit and the equipment, and generating a preliminary task allocation scheme; constructing a distributed control network among the devices, generating a local task sequence of each device based on the preliminary task allocation scheme and the adaptation degree, and obtaining a final task allocation scheme and a task execution plan set based on a contract network protocol algorithm; establishing a multi-constraint collaborative framework, and generating a collaborative production scheduling scheme under the multi-constraint collaborative framework; and establishing a heterogeneous equipment motion cooperative control model, and performing multi-level adjustment through event-driven feedback control. According to the invention, flexible cooperative scheduling of heterogeneous equipment can be realized.

Various embodiments of the present disclosure provide access control for data provided by a federated query system based on attributes of a federated query. The techniques include determining a user identifier associated with a federated query, determining a set of access controls for a plurality of third-party data sources based on the user identifier, and generating an execution plan for resolving the federated query via one or more executable tasks with respect to the plurality of third-party data sources. The techniques also include generating, using a first portion of the execution plan, a result set that comprises information aggregated from the plurality of third-party data sources in accordance with the federated query. The techniques also include generating, using a second portion of the execution plan, a user result set that masks a portion of the information for the result set in accordance with the set of access controls.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses an intelligent optimization method, device and equipment for query statements and a medium. The method comprises the steps of recording execution plan information and resource consumption information of an original query statement, generating original execution information, preprocessing the original query statement and the original execution information to generate preprocessing data, extracting feature information from the preprocessing data, generating optimization information through a pre-trained optimization model based on the feature information, and sending the optimization information to a server. And according to the optimization information, adjusting the content or execution mode of the original query statement, and generating an optimization query instruction. According to the method, the feature information is extracted by monitoring the actual query behavior and combining the execution performance, and the optimization strategy is generated by utilizing the training model, so that the automatic optimization of the original query statement is realized, the manual intervention cost is reduced, and the intelligent adaptation capability of the query performance is improved.

Certain aspects of the disclosure provide techniques for prompt processing. A method generally includes generating a representation of a prompt using a large language model (LLM), the representation comprising semantic features of the prompt, wherein the prompt requests a state change from an initial state to a desired goal state; generating a task description based on using the representation and a domain description; generating an execution plan for the task description, the execution plan comprising a sequence of steps used to transform the initial state to the desired goal state; executing the sequence of steps; and generating a natural language response to the prompt after completing the execution of the sequence of steps, wherein the natural language response is based on the information obtained or the desired goal state.

The invention provides a method for realizing large-scale language model training through computing power of an intelligent computing center, and relates to the technical field of computing power infrastructure and artificial intelligence, and the method comprises the following steps: S1, a first agent receives and understands a large-scale language model training task given by a user on a dialogue interface; s2, the first intelligent agent divides the task into a plurality of sub-tasks, and the sub-tasks are distributed to a plurality of second intelligent agents; s3, the first agent determines an execution plan of the task and notifies the second agent to execute the allocated sub-task based on the execution plan; and S4, the first agent or the second agent generates a report result of the task and reports the report result to the user. Due to the adoption of cooperation of multiple agents, the computing power of the intelligent computing center can be fully utilized to process a relatively complex task for training the large language model, and meanwhile, in the process of executing the task for training the large language model, a dialogue interface is adopted to display a communication process and a decision process, so that the processing process is clearer.

The invention relates to the technical field of data optimization, and discloses a financial data warehouse intelligent SQL (Structured Query Language) optimization method based on a large model, which comprises the following steps: S1, SQL statement analysis and preprocessing: carrying out word segmentation, grammatical analysis and logic structure analysis on an SQL statement submitted by a user, and identifying keywords, table structures and query conditions in query; s2, large model semantic understanding and optimization suggestion: performing semantic understanding and logical reasoning on the analyzed SQL statements by using a large model, and automatically generating optimization suggestions, the optimization suggestions including index recommendation, query rewriting and execution plan optimization; and S3, generating and selecting a dynamic execution plan. According to the method, the advantages of a large model in the aspects of natural language processing and intelligent decision making are fully utilized and combined with the specific requirements of the financial data warehouse, and the execution efficiency of SQL query and the overall performance of the system are remarkably improved; the query response time of the financial data warehouse can be effectively shortened, and the resource utilization rate is improved.

The embodiment of the invention provides a humanoid robot flexible assembly method and system based on a thinking chain and a medium, and belongs to the technical field of natural language processing. According to the scheme, the assembly task instruction provided by the user is obtained, the assembly task instruction is subjected to task analysis through the thinking chain model, the weight of each word in the assembly task instruction is calculated through the attention mechanism in the analysis process, and the analysis target related to the current task is dynamically adjusted according to the weight; the task is decomposed into a plurality of subtasks layer by layer according to an analysis target, a task tree structure is obtained, the task tree structure is traversed to determine an assembly plan, the assembly plan comprises an execution arrangement sequence, task path planning and assembly action parameters, and the humanoid robot is controlled to execute assembly operation according to the assembly plan. The task information is automatically extracted by combining a hierarchical thinking chain and an attention mechanism and is converted into assembly operation, a clear execution plan is generated, and the flexibility of task analysis is improved.

The invention discloses a multi-table combined natural language query SQL (structured query language) generation method, which comprises the following steps of: 1, constructing a database meta-knowledge graph, and establishing a triple storage comprising a table structure, a primary and foreign key relationship and business description for each data table; 2, receiving a natural language query request, and calculating the topic relevancy between query semantics and each database table through a pre-trained topic matching model; 3, dynamically constructing a view, and logically associating the database tables of which the theme relevancy exceeds a threshold value to form a temporary view; 4, generating a context enhancement prompt, and combining the temporary view structure, the field semantic description of the view and the view content sample to form a structured prompt; 5, inputting the natural language query and the structured prompt into the large language model to generate candidate SQL statements; and step 6, executing verification and iterative optimization on the candidate SQL statements, verifying logic correctness through SQL execution plan analysis and result sampling, and triggering and prompting a reconstruction mechanism when detection is abnormal.

The invention provides an LLM technology-based real-time voice conversation method and system applied to an operation and maintenance platform, and relates to the technical field of data processing, the method comprises the following steps: receiving user voice input, carrying out noise reduction preprocessing, and converting a voice signal into text data; semantic analysis is conducted on the text data through an LLMAgent module, the intention of a user instruction is recognized, and a task execution plan is generated based on the intention; decomposing the task execution plan into a basic operation sequence which can be executed by a Unity platform, and determining the priority of task execution; executing the basic operation sequence in a Unity environment, synchronizing an operation state in real time and feeding back an execution result; user interaction data and system performance data are collected, and LLM model parameters and decision strategies are optimized. The technical problems of poor voice interaction effect, large response delay, low accuracy and the like in the existing Unity platform are solved.

The invention provides a different types of database visualization table management method and system, and relates to the technical field of computers.The method comprises the steps that a database general operation system comprising a general operation interface and a dialect abstract base class is constructed, and a query performance evaluation system is established based on performance data; and predicting an optimal database connection mode through deep reinforcement learning and generating a multi-stage execution plan. Meanwhile, an anomaly feature knowledge base based on a graph neural network is constructed, and anomaly prediction and preventive processing are carried out based on the anomaly feature knowledge base. A multi-stage execution plan is executed after a database operation request is subjected to grammar adaptation, and a distributed transaction processor dynamically adjusts a transaction isolation level and a concurrency control parameter. And finally, according to the terminal and the data volume, selecting a proper data display mode to carry out visual presentation.

The invention discloses an Internet of Things sensing command and dispatch intelligent method and system based on a multi-modal large model, which deeply fuses multi-terminal field information, combines with a dynamically updated expert knowledge base, realizes high-precision alarm level judgment and processing suggestion generation, and realizes high-precision alarm level judgment and processing suggestion generation through a multi-agent collaboration method. According to the method, a complex command and dispatch task is decomposed into a series of executable subtasks, the subtasks are executed in a division-of-labor cooperation mode according to a professional agent, the execution conditions of the subtasks are output, and in the execution process of the subtasks, through a quality detection system including logic verification, fact verification, compliance examination and effect evaluation, the execution efficiency of the subtasks is improved. The method comprises the steps that task execution is completed, reliability, authenticity and legality of task execution are ensured, after task execution is completed, sub-task execution results are integrated, an execution log and a comprehensive report are generated, a task execution plan is dynamically adjusted by means of real-time environment perception and a user feedback mechanism, and an optimization scheme is stored in a historical case knowledge base; and continuous learning ability and experience accumulation are realized.

The invention discloses an intelligent agent automatic arrangement method and system based on a large language model, and relates to the technical field of artificial intelligence. The method comprises the following steps: decomposing a natural language instruction of a user into a structured subtask sequence by utilizing a first large language model; based on the agent portrait library, matching and allocating agents for each sub-task to generate an initial execution plan; task execution is scheduled and monitored in real time through an event-driven architecture; when abnormity is monitored, a self-adaptive adjustment mechanism is triggered, the affected plan part is re-planned, and an updating instruction is issued. According to the invention, efficient, flexible and robust multi-agent automatic arrangement is realized.

The invention provides a three-dimensional modeling design method based on multi-robot cooperation of building robots. The method comprises the following steps: taking a set of tasks and paths allocated to each robot as task allocation information; a task execution scheme after error correction based on real-time feedback and task distribution information; performing global analysis on execution errors of all robots according to the corrected task execution scheme; based on the optimized task execution scheme, constructing a task-robot cooperation matrix, and performing task scheduling on the task-robot cooperation matrix by using a cooperation scheduling algorithm; and combining the adjusted point cloud data and the optimized three-dimensional model into a complete three-dimensional model. According to the invention, by optimizing a collaborative operation mechanism of the robot cluster and introducing an error correction mechanism of dynamic task allocation and real-time feedback, the defects in the existing building robot technology are overcome, so that the efficiency of building construction and the modeling precision are remarkably improved.

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

Embodiments of the disclosure provide a solution for action planning. A method includes: generating a sequence of images for an action execution plan based on description information and a reference image related to an environment with an action executor located, the description information describing the action execution plan to be executed by the action executor; extracting a sequence of visual feature representations from the sequence of images, respectively; and for a respective visual feature representation of the sequence of visual feature representations, determining control information for controlling an action to be executed by the action executor in the environment to complete the action execution plan at least based on the respective visual feature representation, a reference visual feature representation prior to the respective visual feature representation in the sequence and observed information of the action executor in the environment during execution of a reference action prior to the action.

A robot fleet management platform includes a job configuration system that determines tasks to be performed by robots of a robot fleet based on a job request and a first fleet objective. A proxy service applies fleet configuration services to the tasks to produce a data structure. An intelligence layer activates intelligence services to produce a robot task and associated contextual information that facilitates robot selection and task ordering. A job workflow system generates a workflow defining a performance order of the tasks. A workflow simulation system simulates performance of the job request based on the workflow to recursively redefine the tasks, the data structure, or the workflow until the simulation result satisfies a second fleet objective. In response to the simulation result satisfying the set of fleet objectives, a plan generator generates a job execution plan based on the set of robot tasks, the data structure, and the workflow.

Training and executing machine learning pipelines for graph data sets may be orchestrated. A request for machine learning pipelines on a graph data set may be received via a machine learning pipeline building system interface. The machine learning pipeline building system may generate a profile of the graph data set from characteristics determined from the data set by the machine learning pipeline building system. Machine learning algorithms may be selected according to the profile of the graph data set and may be used to generate an execution plan that is executes the machine learning pipeline.

The invention relates to the technical field of production task decision making, in particular to a furniture production task automatic matching method and system based on intelligent manufacturing. And extracting personalized demand information corresponding to the production task, converting the personalized demand information into standard design parameters, and generating a customized task. The production task is disassembled into a plurality of sub-tasks, and each sub-task has independent attributes including process requirements, resource requirements and time requirements; and performing one-to-one mapping on the customized tasks and the subtasks to generate an execution plan. Performing resource matching by using a constraint algorithm based on the execution plan and the existing production resource information to obtain a production plan; and obtaining an optimal scheduling plan by using a constraint algorithm according to the production plan. And based on the real-time production data and the burst information, adjusting the optimal scheduling plan through the data analysis model to obtain a final scheduling plan. The method can cope with emergencies or real-time data changes, and manual decisions are reduced.

The invention discloses a data analysis method and device based on multi-agent cooperation and a storage medium. The method comprises the following steps: receiving a natural language request by a workflow arrangement agent, and generating an execution plan comprising a plurality of subtasks and corresponding task processing units by consulting a data exploration agent and a data engine understanding agent; in the execution stage, the professional agent matched with the subtask converts the subtask into an executable instruction, and the data engine dispatch agent calls and coordinates the corresponding task processing unit to execute the instruction. According to the method, through a layered collaborative architecture, the separation of planning, translation and execution is realized, and the automation level, modularization and expandability of data analysis are remarkably improved.

The invention discloses an intelligent data acquisition and conversion method based on a visual rule model, which comprises the following steps: S1, converting a configured rule chain into a data body in a JSON format by a visual rule modeling layer, analyzing the data body into an AST abstract syntax tree, and performing field mapping on the AST abstract syntax tree, the mapping fields are converted into executable codes through an intelligent conversion engine, and an execution plan is generated; s2, the intelligent acquisition layer pulls data from the heterogeneous data source, cleans the data and then allocates the data to an intelligent conversion engine for parallel processing; and S3, the intelligent conversion engine monitors the data consanguinity map and the field-level conversion path in real time, and sends a signal to the visual rule modeling layer or the intelligent acquisition layer according to the abnormal condition type so as to realize rule chain reconfiguration or data reacquisition. The method has the advantages that non-coding docking and real-time supervision of heterogeneous system data are realized, and the problems of dynamic adaptation, semantic understanding and data blood relationship interpretability in financial fund management are solved.

The invention provides a data query method and system for converting a natural language into a database query language, and the method comprises the steps: analyzing the natural language input of a user through a multi-modal understanding agent on the basis of constructing a dynamic knowledge graph based on metadata, combining a historical session with a business term table, eliminating ambiguity, and generating a standardized Query, a retrieval routing agent selects a query strategy according to Query complexity, simple query directly matches a cache template, complex query traverses a knowledge graph, and related tables, fields and service constraints are returned; then, an expert committee agent generates an SQL (Structured Query Language) by adopting multi-stage collaboration, executes plan pre-evaluation, and selects a version with the highest comprehensive score; the test agent simulates and executes the SQL in the isolation environment, and verifies the grammar legality and the field permission; and finally, executing the detected SQL, and processing a result. According to the method, the accuracy of converting the natural language into the SQL (NL2SQL) in a complex database scene can be effectively improved.

The invention relates to the technical field of robot cooperative control, in particular to a humanoid robot body intelligent cooperative control system based on multi-modal sensing fusion, and the system comprises a multi-modal sensing fusion module which recognizes a target boundary position, analyzes a pressure change, and combines with a posture to extract audio features to generate an environment sensing graph; the dynamic time sequence adjustment module optimizes an action rhythm adjustment detail generation execution plan, the cross-modal behavior correction module corrects an offset optimization track generation coordination sequence, the task priority distribution module analyzes task distribution to generate an execution list, and the time sequence conflict correction module optimizes a path adjustment conflict generation coordination path. According to the method, an environment perception graph is constructed through matching and fusion of multi-source perception data, the action sequence and interval are dynamically adjusted to optimize an execution chain, trajectory offset is corrected to improve action precision, nearest response and load balancing are achieved through real-time task allocation, conflict blocking is reduced through path rearrangement and time sequence coordination, and a perception decision execution closed loop is formed; and the identification precision and the cooperation efficiency are improved.

The invention relates to the technical field of intelligent decision making, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a knowledge graph question and answer result generation method, device, equipment and medium, which comprises the steps of performing semantic analysis on a user question to obtain entity information and a query intention, performing logic analysis on the entity information and the query intention to obtain a question and answer result; obtaining an initial execution plan; calling a sub-graph query tool according to the initial execution plan, and querying sub-graph data by using the sub-graph query tool; performing linearization processing on the sub-graph data to obtain a sub-graph data text, extracting a candidate entity set in the sub-graph data text, and screening out a matched target entity from the candidate entity set; performing logic analysis on the target entity and the query intention to obtain a target execution plan, and screening out a matched atomic query tool from the candidate tool set; and querying a knowledge graph question-answer result by using an atomic query tool. The knowledge graph question and answer result generation accuracy can be improved.

The invention relates to the technical field of production workshop scheduling. The production workshop self-adaptive scheduling method comprises the steps that a preliminary task and equipment matching scheme is formed through equipment machinable product types, current task states and line changing time parameters in a preset equipment capacity database, and the production workshop self-adaptive scheduling equipment is obtained according to the preliminary task and equipment matching scheme. The method comprises the following steps: optimizing a task scheduling sequence to form an optimized task execution plan, calculating line change time among different production tasks according to the optimized task execution plan, adjusting the task scheduling sequence through the line change time to obtain an adjusted task scheduling sequence, and optimizing the adjusted task scheduling sequence by utilizing a production task allocation optimization model to obtain a production task scheduling sequence. And determining execution time, distribution equipment and a line change plan of each production task, and generating a production scheduling scheme. The method has the effect of improving the production operation efficiency.