103 results about "PLANC" patented technology

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.

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.

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 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.

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.

The invention provides a method and a system for generating a logic execution plan, which can be applied to the technical field of computers. The method comprises the following steps: firstly, generating a first logic execution plan according to a data query request; wherein in the first logic execution plan, a first association operation exists between the first table and the second table, and a second association operation exists between the second table and the third table. Then, adding a first Bloom filtering operation between the first table and the second table to obtain a first filtering result, and adding a second Bloom filtering operation between the first filtering result and the third table to obtain a second filtering result; then, setting a first association operation and a second association operation according to the first filtering result and the second filtering result to obtain a second logic execution plan; according to the method, the statements used for guiding the association operation in the logic execution plan can be optimized, so that the optimized logic execution plan can greatly reduce the amount of data needing to execute the association operation in the two tables in the subsequent implementation, and the execution efficiency of the data query request is improved.

Mechanisms to transform a multimodal hardware specification document into register-transfer level (RTL) code by configuring a large language model into multiple agents to transform the hardware specification document into a structured implementation plan comprising a sequence of hardware functions, configuring the large language model to apply progressive coding and prompt optimization to sequentially transform the hardware functions into low-level program code through a plurality of progressively lower-level code generation stages, and transforming the low-level program code of the hardware functions into the RTL code through a code optimizer and high-level synthesis tool.

The application discloses a mobile terminal LLM heterogeneous scheduling method based on hybrid parallelism, comprising: obtaining a scheduling plan; performing model inference based on an offline transformed large language model (LLM) according to the obtained scheduling plan; wherein the offline transformation of the large language model (LLM) comprises: pre-executing a benchmark test task to determine the computing power ratio of a mobile terminal heterogeneous computing device; extracting static information of the large language model (LLM), combining the determined computing power ratio, formulating a hybrid parallel strategy, and dividing the large language model (LLM) into multiple computing blocks; setting a synchronization point for each computing block, integrating the computing results, and completing the offline transformation of the original computing graph of the large language model (LLM) to a hybrid parallel computing graph. The application applies the hybrid parallel strategy to the mobile terminal heterogeneous scene, improves the inference performance of the LLM on the mobile terminal, and solves the problems of insufficient use of the existing inference framework computing device and imbalance between heterogeneous devices.

A method, (e.g., a computer-implemented method), of generating a production plan is provided. The method includes obtaining one or more product and / or production characteristics, (e.g., a production content, a production time, and / or a production quantity, for example, in a E-BOM, M-BOM, and / or CAD file format), for a product to be manufactured. The method further includes determining, by a rule engine, based on the one or more product and / or production characteristics, one or more library elements from a plurality of library elements, wherein each library element includes one or more process descriptions relating to the characteristic. The method further includes arranging, by the rule engine, the one or more process descriptions into a production plan.

Disclosed herein are system, apparatus, article of manufacture, method and / or computer program product aspects, and / or combinations and sub-combinations thereof, for generating a workflow plan for completing a process. An example embodiment operates by receiving a user request from a user device in which the user request includes a natural language description of the workflow plan. The embodiment then retrieves, from a knowledge database, workflow information associated with a step of the workflow plan. The embodiment then generates a plurality of steps associated with the workflow plan. The embodiment then retrieves plan information from a storage database in which the plan information includes a sample workflow plan generated from a sample user request and the workflow information in which the workflow information is further associated with a step of the sample workflow plan. The embodiment then generates the workflow plan using a large language model (LLM) and a prompt.

A computer-implemented method can receive an internal representation of a transformer model, an internal representation of a device cluster, and an internal representation of a workload for execution of the transformer model on the device cluster. The method can generate a plurality of candidate execution plans based on the internal representation of the transformer model and the internal representation of the device cluster. Each candidate execution plan represents a unique parallel schedule for partitioning devices in the device cluster for parallel execution of the transformer model. The method can determine an optimal execution plan, including evaluating resource usage of the plurality of candidate execution plans based on the internal representation of the workload, and selecting, among the plurality of candidate execution plans, the optimal execution plan which yields the lowest resource usage. The evaluating includes simulating execution of the transformer model on the device cluster to process the workload.

1. The name of the design product: enterprise security risk intelligent management and control platform graphical user interface for computers. 2. The use of the design product: for running programs and displaying interface content. 3. The design points of the design product: the graphical user interface content in the computer screen. 4. The picture or photo that best indicates the design points: front view. 5. Conventional design, omit rear view; conventional design, omit left view; conventional design, omit right view; conventional design, omit top view; conventional design, omit bottom view. 6. The use of the graphical user interface: for desktop device enterprise security risk management system. 7. The human-computer interaction mode of the graphical user interface: initial interface - boot interface graph (front view), after booting into main display interface (interface change state graph 1), main display interface displays login account personal information, message notification, current date, pending tasks and historical task records. After clicking "security management foundation" in the navigation bar at the top of the page, "comprehensive dashboard" under "security management foundation" is displayed (interface change state graph 2), the remaining content of "comprehensive dashboard" under "security management foundation" is displayed (interface change state graph 3, interface change state graph 4), the left navigation bar of "comprehensive dashboard" displays 14 sub-function items including "comprehensive dashboard", and the right side displays the content of 13 sub-function items in various chart forms except "comprehensive dashboard". After clicking "facility and equipment management" in the navigation bar at the top of the page, "equipment account list" under "facility and equipment management" is displayed (interface change state graph 5), the left navigation bar of "equipment account list" displays 4 sub-function items including "equipment account list", and the right side displays the content of "equipment account list". After clicking "special operation management" in the navigation bar at the top of the page, "comprehensive dashboard" under "special operation management" is displayed (interface change state graph 6), the remaining content of "comprehensive dashboard" under "special operation management" is displayed (interface change state graph 7, interface change state graph 8), the left navigation bar of "comprehensive dashboard" displays 7 sub-function items including "comprehensive dashboard", and the right side is "special operation comprehensive dashboard", which displays "today's operation reservation", "ongoing operation", "historical operation reservation" and "historical operation" in various chart forms. Click on the navigation bar above the page "safety education and training" after entering, display "safety education and training" under the sub function item "comprehensive board" (interface change state diagram 9), the page drop-down display "safety education and training" under the sub function item "comprehensive board" remaining content (interface change state diagram 10, interface change state diagram 11), "comprehensive board" left navigation bar display contains "comprehensive board" in 6 sub function items, right display the current year "education and training comprehensive analysis", in various forms of charts on the current year "training plan management", "training task management", "examination task management", "participating training department list", "participating personnel list" has carried on the display. Click on the navigation bar above the page "more", the navigation bar shows the expansion part (interface change state diagram 12), appears "double prevention mechanism", "agile emergency", "intelligent inspection", "list management", "risk monitoring and early warning", "visualization" 6 sub function options. Click on the navigation bar above the page "double prevention mechanism" after entering, display "double prevention mechanism" under the sub function item "comprehensive board" (interface change state diagram 13), drop-down page display "double prevention mechanism" under the sub function item "comprehensive board" remaining content (interface change state diagram 14, interface change state diagram 15, interface change state diagram 16), "comprehensive board" left navigation bar display contains "comprehensive board" in 5 sub function items, right "double prevention comprehensive board", in various forms of charts on "overall security situation", "risk classification control", "hidden danger investigation", "hidden danger management" has carried on the display.

A method for transforming an abstract representation of a trained neural network into program code in a target language. The program code is convertible into executable program code using a compiler for the target language. The method includes: reading an abstract representation of a neural network which has already been trained; calculating an intermediate representation of the neural network from the abstract representation, the intermediate representation specifying a computation graph; ascertaining a plurality of plan proposals for planning the memory usage during the execution of the computation graph; ascertaining a quality level for each plan proposal; selecting a plan proposal based on the ascertained quality level; and generating the sought program code in the target language from the intermediate representation and the selected plan proposal.

Systems and methods are provided for automatically building software in a secure environment. A system includes a software development environment, having an associated security level. The software development environment generates an encrypted software module containing a software module and a cryptographic hash representing a content of the software module and provides it to a software repository. The software repository, in response to receipt of a build plan, decrypts the encrypted software module to recover the software module and the cryptographic hash representing the content of the software module, generates a new cryptographic hash for the software module, and verifies that the new cryptographic hash matches the cryptographic hash representing the content of the software module. A build environment receives the plurality of software modules from the software repository and generates a software build from the plurality of software modules based upon the build plan.

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.

The invention provides a modular code processing method and system based on dynamic plug-in discovery in Agent research and development, and relates to the technical field of computers. The method comprises the following steps: in an Agent system initialization stage, obtaining functional module metadata in a current operating environment, dynamically loading processing nodes according to the functional module metadata, and forming a candidate node set; performing type consistency verification on the data connection relationship among the candidate nodes to obtain an effective node set; constructing and analyzing a node dependency relationship graph based on the dependency relationship between the effective nodes, and generating a hierarchical execution plan; and scheduling the effective nodes according to the hierarchical execution plan, and executing the effective nodes in parallel in the same execution hierarchy. According to the method and the device, the dependence of module management on manual configuration can be reduced under the condition that the number of the function modules is increased or the function modules are updated frequently, and the modules are more consistent and predictable in the aspects of collaboration and execution organization, so that the scale expansion and operation requirements in a complex task scene are met.