142 results about "PLANC" patented technology

A computer-implemented method generates workflow definitions in workflow definition language using one or more large language models, LLMs. The method includes receiving a natural language description of an automated workflow and generating a plan generation prompt including the natural language description and plan generation instructions. The plan generation prompt is input to one of the LLMs and in response a structured plan comprising a plurality of actions are received. For each action, a corresponding segment of workflow definition language is generated to provide a plurality of segments of workflow definition language. The segments are combined to form a workflow definition corresponding to the natural language description.

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 discloses a cloud platform operation and maintenance method and device, equipment, a medium and a product, relates to the technical field of operation and maintenance, is applied to a server, and comprises the following steps: receiving a natural language instruction input by a user side; performing intention recognition and parameter extraction on the natural language instruction to obtain at least one atomic task, and generating an execution plan according to a target dependency relationship between the atomic tasks; screening an optimal execution path from at least two preset execution paths for each atomic task based on the task attribute of each atomic task in the execution plan; performing simulation drill analysis on the execution plan based on the optimal execution path to generate a risk pre-judgment report, and sending the risk pre-judgment report to the user side; and after execution confirmation information sent by the user side based on the risk pre-judgment report is obtained, a task executor corresponding to the optimal execution path is utilized to initiate calling to the cloud platform to execute the execution plan, and an execution result of the cloud platform is converted into a natural language response to be sent to the user side.

The embodiment of the invention provides a software development method based on artificial intelligence and related equipment. In the embodiment of the invention, an AI software development method and mode are provided, and a user and a technical design document generation agent cooperate to complete a technical design document of a programming task; and the programming agent autonomously performs task planning based on the technical design document, and autonomously executes the programming task based on the planned execution plan. In at least one of the technical design stage or the task execution stage of the programming task, a man-machine cooperation interface is provided, and the man-machine cooperation interface is used for a user to participate in the software development process for the programming task. Therefore, the software development efficiency and the code quality are greatly improved through division cooperation and man-machine cooperation interaction among the intelligent agents.

The invention relates to the field of DevOps intelligent execution, in particular to an MCP-based DevOps task intelligent arrangement and execution method and system, and the method comprises the steps: obtaining a tool function of each MCP server to form a global tool library; receiving a natural language task instruction of a user, and inputting the natural language task instruction into the large language model; performing task decomposition on the natural language task instruction to generate a structured tool calling plan; the client side executes the structured tool calling plan and calls target tool functions on the corresponding MCP server in sequence or in parallel through the MCP according to the execution logic and the dependency relationship; monitoring execution of each tool function, determining a subsequent process or triggering a preset rollback operation according to an execution state, and feeding back a final execution result to the large language model; and generating a natural language abstract containing the overall task execution state based on the execution result, and outputting the natural language abstract to a user. And cross-environment seamless operation automation is realized.

The invention discloses a method for generating a text system, and aims to solve the problems of long development cycle, disjunction of requirements and technology implementation and the like of traditional software and realize automatic generation from a natural language requirement to a deployable service system based on a large language model. The method is divided into two stages: in the first stage, a system is disassembled into a logic subsystem through man-machine cooperation, core business logic is extracted, a large language model is called by adopting a divide-and-conquer strategy, and a detailed specification containing a functional process and an interface form is generated; in the second stage, a large language model is called to generate a database table structure and a DDL script, an engineering framework of a basic technology stack is initialized and integrated through a predefined scaffold, CRUD codes are generated, the codes are analyzed to generate a transformation plan for structured data, and target logic codes are incrementally integrated. According to the method, control is achieved through Python, the problem of large model input limitation is solved, and generated codes are standard and extensible. The development cycle is shortened, the requirement-design-code consistency is guaranteed, the threshold is lowered, platform locking is avoided, and enterprise digital transformation is assisted.

The invention discloses a dynamic operator-oriented incremental compilation optimization method and system, belongs to the technical field of deep learning, and aims to solve the technical problem of how to provide a fine-grained, reusable and extensible compilation strategy for dynamic operator-oriented incremental compilation optimization. Comprising the following steps: extracting attributes of a dynamic operator and constructing a dynamic operator hash signature according to the extracted attributes; dividing the calculation graph into a static sub-graph and a dynamic sub-graph, establishing a mapping table of a dynamic operator hash signature and a compiling kernel, and caching the mapping table in an incremental compiling cache; solving and instantiating the dynamic sub-graph through a dynamic specifying engine, generating a specialized sub-graph, querying whether a matched compiling result exists in an incremental cache or not, and updating the incremental cache; and for the static sub-graph which is not changed, directly multiplexing the last compiling result of the static sub-graph, executing cross-sub-graph fusion optimization work between the dynamic sub-graph and the static sub-graph which are subjected to specialized processing, and submitting a fusion execution plan to a runtime engine.

The embodiment of the invention provides an agent system-oriented parallel task execution method and device and electronic equipment, and is applied to the technical field of artificial intelligence. The method comprises the following steps: acquiring a structured plan, identifying a dependency relationship of the structured plan, and generating a dependency relationship table; obtaining a legal directed acyclic structure according to the obtained dependency relationship table; the task graph structure which accords with semantic logic and has concurrent scheduling and execution state monitoring capabilities is automatically generated from natural language input, so that the task execution efficiency and the system elasticity are conveniently improved; constructing a candidate node set according to the nodes of the legal directed acyclic structure, generating a to-be-executed node set, and constructing execution context information for the to-be-executed nodes; and starting the corresponding node to be executed according to the execution context information, and performing intelligent processing according to the execution result, thereby constructing a complete closed loop from a natural language task to structured scheduling, supporting efficient concurrent execution, and realizing real-time monitoring and dynamic feedback of the execution process.

The invention discloses an automatic code debugging and optimizing system and method based on an AI agent, and relates to the technical field of artificial intelligence and automatic programming, the system comprises a coordinator module, a plan generation module, a code generation module, a test verification module, a deployment operation module, a project summary module, a language model module and a context management module; the coordinator module supports to select and call an Agent for specific task execution according to the current task process, and the plan generation module is configured to automatically generate a development task plan according to the requirements of a user and transmit a task list to the code generation module. Through the exception retry mechanism and the task backtracking mechanism, the system can automatically detect errors in the code generation process and repair the errors, and the tedious process of traditional manual debugging is avoided. The system optimizes the code generation process by backtracking the historical task and adjusting the generation strategy, and the quality of the final code is ensured.

A computer-implemented technique for generating program code includes receiving a natural language description of a hardware module, generating a first plan based on the natural language description, extracting first circuit information from the natural language description, generating a second plan based on the first plan and the first circuit information, and generating first program code in a hardware description language based on the second plan.

The invention discloses a large language model multi-agent end-to-end stowage method considering outbound equipment collaborative scheduling, which comprises the following steps: acquiring description data of a stowage task, and decomposing the stowage task into sub-tasks of multiple stages based on the description data; aiming at the first subtask, based on the description data of the first subtask, constructing a first model by utilizing a modeling agent, and generating a first code for solving the first model through a model code agent; aiming at the second subtask, based on the description data of the second subtask, constructing a second model by utilizing the heuristic intelligent agent, and generating a second code for solving the second model through the heuristic code intelligent agent; matching target codes from the first codes and the second codes according to the types of the sub-tasks, and executing the target codes according to the sequence of the sub-tasks to obtain a final container stowage plan. The method can meet the reality and feasibility and completely meet all complex requirements.

The invention discloses a multi-agent parallel planning and execution-oriented dynamic task cooperation method and system. The method comprises the following steps of: constructing agents containing planning threads and execution threads which are independent and run in parallel, configuring a callable large language model and a readable and writable centralized memory system for the planning threads, and configuring a callable tool library for the execution threads; a planning thread and an execution thread of each agent establish an exclusive communication link, and a centralized memory system configures a file lock mechanism; the planning thread obtains latest environment information, team communication logs and execution history from the centralized memory system at each time step, calls a large language model to generate a formatted tool library API instruction as a next plan, independently judges whether an interrupt mechanism is triggered or not by the large language model, generates an interrupt signal if the interrupt mechanism is triggered, and sends the interrupt signal to the centralized memory system; writing the tool library API instruction into an action buffer area; the execution thread continuously obtains the latest tool library API instruction from the action buffer area and calls a tool library to execute a corresponding task; if an interrupt signal sent by the planning thread is received through the exclusive communication link, the current task is terminated immediately, and after occupied resources are released, the latest instruction of the buffer area is loaded for execution; and the centralized memory system updates contents at each time step, including an environment observation result returned by the tool library, a communication log between the intelligent agents and a task execution history of each intelligent agent, for all planning threads to access.

To assist users in artificial intelligence driven software development, techniques for agentic software development assistance leveraging application behavioral models are disclosed. A software agent receives a codebase issue and orchestrates an iteration of a refining process. To orchestrate the process, the software agent feeds the codebase issue and instructions to generate a plan into a development assistant, which automatically returns a plan to the agent. The agent feeds the plan and instructions to generate a solution to the codebase issue back to the development assistant, which automatically returns a solution to the agent. The agent feeds the solution back to the development assistant, which tests the solution in order to verify the solution's quality in responding to the codebase issue. The solution is awarded a quality score, and the quality score is returned to the agent. Based on the quality score, another iteration of the refining process can be performed.

One embodiment of a method for modifying program code includes processing, using a first trained language model, program code to identify one or more modifications to the program code; processing, using a second trained language model, the program code and the one or more modifications to generate a plan for applying the one or more modifications; and processing, using a third trained language model, the program code and the plan to generate a modified program code.

The invention discloses a kernel-level heterogeneous collaborative AI reasoning method and device, equipment and a storage medium, and relates to the field of AI reasoning acceleration. When the KDS receives a reasoning request submitted by a user space, generating a cross-device plan list according to a global system resource state and issuing the cross-device plan list to the HCEE; the HCEE drives the corresponding target execution equipment according to the task execution sequence, reads the data information from the UCMP, or restores intermediate / result data reasoned and output by the target execution equipment; after reasoning of the plan list is completed, the kernel space triggers an event notification mechanism, and a user process of the user space is awakened; and the user process directly reads the reasoning result from the UCMP. According to the scheme, deep collaboration of task scheduling, memory management and equipment execution is realized on a Linux kernel level, the problems of high overhead, resource islands, memory redundant copy, extensive scheduling granularity and the like of a user mode reasoning framework system are solved, and end-to-end low-delay, high-throughput and high-energy-efficiency AI reasoning acceleration is realized.

The embodiment of the invention relates to a plan release method and device in project management, equipment, a medium and a program product. The method comprises: in a draft mode of a schedule for a work item, receiving at least one editing operation on the schedule, the schedule being configured to orchestrate one or more items for at least partially completing the work item; in response to a release operation for the plan table, presenting a publishable range of the plan table based on the at least one editing operation; and in response to a selection operation on at least one target item in the publishable range, publishing the at least one target item from the draft mode to the plan table.

The invention provides a controller program generation method based on semantic planning and quality optimization, and belongs to the technical field of automation. A multi-stage PLC program generation and optimization method oriented to natural language task description is adopted, and semantic retrieval enhanced task planning, structured code synthesis and a quality closed-loop optimization mechanism based on feedback are fused. A natural language task is automatically converted into a verifiable plan with logic constraints by constructing a semantic index, reasoning scheduling and an intermediate representation structure; through module clustering and multi-round prompt guiding type logic reconstruction, generation of a high-quality PLC program meeting the IEC 61131-3 standard is realized. And static analysis and test feedback are combined, and the code quality is evaluated and enhanced by adopting iterative optimization and a scoring mechanism, so that the problems of intelligence, structuring and verification of the whole process from natural language to PLC program are systematically solved, and the development efficiency, the program robustness and the feasibility of industrial deployment are remarkably improved.

The invention discloses an intelligent task scheduling and collaborative execution method and a heterogeneous computing system, and the method comprises the steps: receiving and analyzing a computing task, and extracting the computing, data and constraint features of the computing task; decomposing the task into sub-tasks with a dependency relationship; acquiring load, computing power and power consumption states of the NPU, the GPU and the CPU in real time; on the basis of task characteristics and real-time states, multiple allocation schemes are evaluated through a pre-constructed cost model, and an optimal scheduling decision for allocating the sub-tasks among the heterogeneous computing units is dynamically generated; a flow line collaborative execution plan across at least two computing units is arranged according to a decision, sub-task execution is scheduled, meanwhile, cross-unit data flow and synchronization are managed, and a corresponding system comprises an NPU, a GPU, a CPU, a system memory and an intelligent heterogeneous resource scheduler for executing the method. According to the method, fine scheduling, self-adaptive load balancing and multi-objective optimization of heterogeneous computing resources are realized, and the comprehensive efficiency and energy efficiency of the system are remarkably improved.

In some implementations, a fault diagnosis system may track information associated with a first execution of a code pipeline to deploy an updated version of software associated with the code pipeline. The fault diagnosis system may receive an indication of a failure in a second execution of the code pipeline, wherein the second execution of the code pipeline is triggered by a commit of source code to a source code repository. The fault diagnosis system may determine whether the updated version of the software associated with the code pipeline or the source code committed to the source code repository is a cause of the failure in the second execution of the code pipeline. The fault diagnosis system may send a request to plan code development to resolve the cause of the failure in the second execution of the code pipeline.

Embodiments of the disclosed technologies include generating a first thread classification prompt based on a first thread portion of an online dialog involving a user of a computing device, sending the first thread classification prompt to a first large language model, receiving a first thread classification generated and output by the first large language model based on the first thread classification prompt, formulating a plan execution prompt based on the first thread classification, sending the plan execution prompt to a second large language model, receiving a second thread portion generated and output by the second large language model based on the plan execution prompt and the online dialog, and generating a label for a third thread portion of the online dialog.

The invention discloses a plan curve system and method based on multi-terminal separation interactive design. The system comprises a protocol processing layer, an interface tool layer and a plan value access service layer. The protocol processing layer is used for distinguishing a plan value operation type and carrying out structured forwarding on a plan value and an instruction thereof; the interface tool layer is used for receiving and responding to operation instructions edited, inquired, stored and uploaded by a user and displaying plan value discrete points on canvas; the plan value access service layer is used for monitoring the structured instruction packet forwarded by the protocol processing layer, analyzing the instruction type, responding to the pushing and uploading module, and reading and writing a curve library and a file library in a storage medium; by designing a multi-terminal separation interaction technology, the problems of storage and uploading of daily power generation or power utilization plan curves can be efficiently and accurately solved.

Embodiments of the disclosed techniques include generating a first thread classification cue based on a first thread portion of an online conversation involving a user of a computing device; sending the first thread classification prompt word to a first large language model; receiving a first thread classification generated and output by the first large language model based on the first thread classification prompt word; formulating a plan execution cue word based on the first thread classification; sending the plan execution cue word to a second large language model; receiving a second thread part generated and output by the second large language model based on the plan execution cue word and the online dialogue; and generating a tag for a third thread portion of the online conversation.

In some implementations, a device may receive a plurality of natural language inputs that indicate desired characteristics for a communication plan, where the communication plan is defined by a plurality of plan parameters. The device may generate, in a plurality of iterations and using a large language model, the plurality of plan parameters and a plurality of response outputs relating to the plurality of plan parameters. Each iteration, of the plurality of iterations, may be based on a respective natural language input, of the plurality of natural language inputs, analytics conclusions relating to one or more of the desired characteristics of the communication plan indicated by the respective natural language input, and state information indicating previously-generated plan parameters of previous iterations. The plurality of natural language inputs and the plurality of response outputs may alternate in a conversational format.

The invention discloses a continuous data protection method, device and equipment based on a Linux complete machine and a storage medium, and the method comprises the steps: when a backup instruction is received, creating a backup plan, and determining a to-be-backed-up Linux system and an NFS storage end for backup processing; registering a corresponding request interface in the block device of the Linux system to be backed up, and intercepting the received BIO request based on the request interface; the request type of the BIO request is judged, and the request type comprises a write request and other requests; when it is judged that the request type is a write request, whether a backup instruction is executed or not is determined according to the BIO request, and when it is determined that the backup instruction is executed, the Linux system to be backed up is backed up to the NFS storage end. By directly intercepting a block device write request on a kernel level, realizing incremental backup based on a two-dimensional mapping table and combining a metadata management mechanism, the method has the advantages of improving backup universality, reducing system overhead and realizing block-level incremental backup.

The invention relates to a mixed integer linear programming-based cabinet division optimization method and system, and the method comprises the steps: obtaining the related data of a delivered commodity and cabinet division configuration from a database based on a task ID, and the related data of the delivered commodity comprises delivery plan details, order information and SKU; splitting the delivery plan details into a plurality of delivery detail groups based on the order information; mapping the priority of the SKU in each delivery detail group based on a preset priority rule; obtaining a current sub-cabinet scene based on the sub-cabinet configuration, wherein the current sub-cabinet scene comprises a single-cabinet replenishment scene, a general high-priority sub-cabinet scene and a priority difference sub-cabinet scene; and constructing a mixed integer linear programming model of the current sub-cabinet scene based on the priority and the delivery plan details of each SKU, and calling a solver to solve the mixed integer linear programming model to obtain a sub-cabinet scheme.

Methods, systems, and computer programs are presented for implementing a tool that generates and executes the code in a controlled environment to satisfy user requests entered as text prompts. One method includes receiving a user prompt with a user request received in a user interface (UI), generating a first Large Language Model (LLM) prompt to create a plan, and receiving the plan from an LLM, the plan comprising text describing a sequence of operations. The method further includes generating a second LLM prompt, to create code, specifying which code instructions are permitted in the created code. Further, the method receives the code from the LLM that received the second LLM prompt, and executes the code in a controlled environment. Further, the results generated by executing the code are presented in the UI.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating and updating project plans for software development projects. In one aspect, a method includes obtaining data indicative of initial project plan parameters associated with a software development project; identifying multiple program modules associated with the software development project; obtaining, for a first set of modules of the multiple modules, corresponding source code segments; executing a quality assessment process to compute, for each corresponding source code segment, a corresponding quality score; identifying, based on the quality scores, that at least a subset of the corresponding source code segments are integrable into a corresponding first subset of the first set of modules; and generating a revised project plan by generating updates to the initial project plan parameters by accounting for the corresponding source code segments being integrated in to corresponding ones of the first set of modules.

The invention discloses a multi-core heterogeneous kernel real-time computing task scheduling method and electronic equipment, and belongs to the field of edge equipment resource scheduling. The method is applied to a task scheduling system which comprises a first scheduling unit and a second scheduling unit. The method comprises the steps that a second scheduling unit schedules at least one task processor to process target input data based on a first processing plan and obtains performance monitoring data; the first processing plan comprises task processors occupied by processing target input data and calling times of calling each task processing model by each task processor under different batch processing numbers, and the number of the task processing models is at least 1; if the performance monitoring data does not meet the delay criteria, the second scheduling unit sends a rescheduling signal to the first scheduling unit to cause the first scheduling unit to generate a second processing plan. According to the multi-core heterogeneous kernel real-time computing task scheduling method disclosed by the invention, the stability and the high efficiency of task scheduling processing are improved.

The invention provides a work content and progress plan association method, system and device based on a BIM model. The method comprises the steps that the BIM model of a project is acquired; obtaining a progress plan library of the project; performing dynamic code association based on the component identification code of each component in the BIM model and the progress plan code in the progress plan library to obtain an associated BIM model; acquiring a post work content library; the post work content code is consistent with the progress plan code; and based on the progress node of the associated BIM model, triggering a post work task corresponding to a post work content code which is the same as the progress plan code in the post work content library, and sending the post work task to a corresponding post worker. According to the invention, the post work content and the progress plan can be associated by using the component identification code, the progress plan code and the post work content code based on the BIM model, so that the project construction management efficiency is improved.