36 results about "Execution model" patented technology

The invention discloses a method for evaluating the code generation capability of a fine-tuned credential large model, and relates to the technical field of artificial intelligence, and the method comprises the steps: S1, constructing an evaluation data set which is constructed according to a half-and-half rule, S2, executing a model generation test, and based on the evaluation data set, carrying out a model generation test; the method comprises the following steps of S1, adjusting a code output result, S2, calling the adjusted credential large model to generate a corresponding code output result, S3, carrying out multi-dimensional evaluation analysis, S4, forming a comprehensive evaluation result, and calculating the credibility 7 degree of the large model code generation capability for guiding model performance optimization and subsequent iteration improvement; according to the fine-tuned evaluation method for the code generation capability of the credential large model, evaluation deviation caused by a single index is effectively reduced, and the obtained quality credibility is more practical and explanatory and can be used as a decision basis for supporting large model optimization strategy formulation and parameter fine tuning.

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 benchmark test-driven prompt word tuning method, device, equipment and medium, and the method comprises the following steps: analyzing input data to generate a benchmark test set; generating a cue word parameter configuration set based on the benchmark test set; calling a language model interface to process the input text to obtain a model output set; comparing the model output set with expected output to generate a comprehensive performance index set; updating a cue word parameter configuration set according to the comprehensive performance index set; and judging whether a termination condition is met or not, if not, continuing to execute model calling and parameter updating, and if yes, outputting a target cue word configuration and optimization report. According to the method, a structured evaluation and parameter iteration mechanism is introduced, cue word optimization is converted into a systematic process from artificial experience driving, repeated trial and error are reduced, cue word tuning efficiency is improved, and stability and mobility of the model in different tasks are achieved.

Provided in the present disclosure are a task execution method, and a method and apparatus for training a task execution model, which can be applied to the technical fields of artificial intelligence, natural language processing and large models. The method comprises: in response to having received an instruction for executing a target task, on the basis of a plurality of preset keys, performing information extraction on text corresponding to the instruction, so as to obtain a value information set, wherein the types of the preset keys comprise at least one of the following: an instruction object for indicating a subject in the text, an instruction action for indicating a predicate in the text and an instruction parameter for indicating an object in the text, and value information corresponding to the instruction object is used for representing an object required for executing the target task, value information corresponding to the instruction action represents an action required for executing the target task, and value information corresponding to the instruction parameter represents a parameter related to the object or the action; on the basis of the value information set, determining a plurality of sub-tasks used for implementing the target task; and on the basis of an association relationship between the plurality of sub-tasks, sequentially executing the plurality of sub-tasks.

The invention provides a multi-language-oriented source code automatic verification method and system, and relates to the technical field of computers.The method comprises the steps that multi-language source codes are obtained; compiling the multi-language source code through an LLVM compiler to generate an intermediate file; the intermediate file is optimized; analyzing the optimized intermediate file through an IR analyzer to generate a symbolic execution model; performing simulation execution operation on the symbolic execution model; and performing security verification on the symbolic execution model after simulation execution operation to obtain a verification report. Unified verification of multi-language source codes can be achieved, the verification environment building and development cost is greatly reduced, and the overall verification efficiency is improved; and the analysis capability of the intermediate file can be enhanced, the logic constraint relationship in the code can be accurately captured, the comprehensiveness and reliability of the verification work can be practically guaranteed, and diversified software security verification requirements can be met.

The invention discloses a deep learning model multi-NPU end-side one-button deployment system and method.The system comprises a front-end interaction module, a service-side control module, an end-side execution module and a result integration module.The method comprises the steps that front-end configuration is carried out on a user side, the front-end configuration is received on a service side, a unified version container environment is called to execute model conversion, and a unified version container environment is called to execute model conversion; pushing to the end side; receiving a file pushed by the service side at the end side, starting a reasoning script, and obtaining a reasoning result and NPU performance data; and receiving a side deployment report at a user side, and feeding back the report to the user through a front-end interface. By integrating the front-end interaction module, the service-side control module, the container environment management unit, the end-side execution module and the result integration module, automatic model deployment on various NPU devices is realized. One-stop automatic deployment is realized, from front-end configuration to end-side execution, the whole process of result analysis does not need manual intervention, and the efficiency is greatly improved.

An example operation may include one or more of executing an artificial intelligence (AI) model on a query via a software application to generate a formatted data structure, executing a filter on the formatted data structure and conditions of the formatted data structure to determine that the formatted data structure does not satisfy a condition from among the conditions, identifying a prompt that corresponds to the condition, executing the AI model on the formatted data structure and the prompt to generate a modified formatted data structure, executing the filter on the modified formatted data structure and the conditions associated with the formatted data structure to determine that the modified formatted data structure matches the conditions, and in response, deploying a software system via a host platform and executing the modified formatted data structure as part of the software system.

The invention provides a task execution method and device, equipment, a storage medium and a program product, and the method comprises the steps that a thinking chain model automatically generates instruction information according to task description information and current state information of at least one mode; the instruction execution model obtains instruction information and state information, executes a corresponding instruction and outputs execution information; wherein the state information is updated after the instruction is executed; the matching model determines whether the execution result is matched with the instruction information at least according to the instruction information and the execution information; if the task description information is matched with the task description information, and the updated state information does not conform to the task completion state corresponding to the task description information, the updated state information is used as current state information to be input into the thinking chain model, and the thinking chain model continues to automatically generate next piece of instruction information according to the task description information and the state information; and the state information accords with the task completion state corresponding to the task description information.

This application provides an autonomous game operation AI agent method and device. The method includes: S10, capturing the game screen in real time after the AI ​​agent takes over the control of the game operation; S11, analyzing the game screen and tasks through a large language model (LLM) to generate tactical intentions; S12, generating operation instructions based on the tactical intentions and game screens through a pre-trained action execution model, and executing the operation instructions. During the execution of the above scheme, the game screen is analyzed to monitor whether the task is completed or failed. When the task is completed or failed, the control of the game operation is returned to the user. This fundamentally solves the pain point of players' "operation not keeping up with awareness". It can adapt to the dynamic changes and uncertainties in the game and execute highly complex and non-linear tasks, providing substantial operational assistance to users in playing games.

The invention relates to the technical field of building information models, in particular to a design collaborative modification method and system based on semantic packaging and BCF file transfer, and aims to convert a fuzzy natural language instruction into structured design modification semantics and transfer the design modification semantics through a BCF file, reduce communication cost and misunderstanding and ensure that the instruction is accurately understood; after approval is passed, the system can automatically execute model modification, low efficiency and error-prone performance of manual operation are avoided, and the advantages are more obvious especially for modification involving a large number of components or complex associations; by updating a BCF file and generating an XML log, information such as modification is completely recorded, and quality tracing, problem review and knowledge accumulation are facilitated; standardized semantics and BCF files provide common language and communication basis for designers with different professional backgrounds, and the cross-professional coordination process is simplified; and specific modification execution is automatically completed by the system, so that the dependence of common designers on complex BIM software operation commands is reduced.

The invention provides a software security test method and device, equipment, a medium and a program product, relates to the technical field of information security, and aims to solve the problem of poor test effect of a traditional application security test method in related technologies. The method comprises the following steps: analyzing a source code file of software to be tested to generate an abstract syntax tree; performing taint analysis on the abstract syntax tree to determine at least one code execution path of at least one API endpoint of the to-be-tested software as a taint source and at least one sensitive operation point as a taint sink; performing taint tracking simulation on the at least one code execution path based on a code execution model constructed by the abstract syntax tree to obtain an execution result; and under the condition that the execution result indicates that the to-be-tested software does not pass the security test, determining a problem code based on a vulnerability triggering path corresponding to the execution result. The software security testing method and device can improve the testing effect of software security testing.

The application provides a simulation scheduling method and system, and belongs to the technical field of control simulation. The method comprises the following steps: constructing a Simulink mathematical model and generating an initial model file; converting the initial model file into an RTW file; calling a target language compiler to convert the RTW file into a to-be-called model file; calling a make tool to automatically generate a code and to compile the to-be-called model file to generate an execution model file; and executing closed-loop simulation in a Vxworks system according to the execution model file. The application realizes simulation scheduling distribution of the whole system in the form of auxiliary clock scheduling tasks, realizes simulation scheduling between a Simulink simulation system and a Vxworks operating system, and improves the real-time performance of the Simulink simulation process.

The invention particularly relates to a spacecraft formation flight mission planning method based on cooperation of a large language model and a professional tool set. The method comprises the following steps: constructing a three-layer mission planning architecture of the professional tool set, an LLM and a high-level dynamic execution engine; constructing the professional tool set for spacecraft formation flight; disassembling the user instruction into a meta-task sequence through a complex task decomposition model; and calling the tool set in sequence to execute the meta-task through the task sequence execution model. The invention provides a more efficient and flexible intelligent solution with scene generalization ability for the spacecraft formation flight task planning problem.

The application particularly relates to a spacecraft formation flight task planning method based on cooperation of a large language model and a professional tool set, and comprises the following steps: constructing a three-layer task planning architecture of the professional tool set, the LLM and a high-level dynamic execution engine; constructing the professional tool set for the spacecraft formation flight; decomposing a user instruction into a meta-task sequence through a complex task decomposition model; and calling the tool set to execute the meta-task in sequence through a task sequence execution model. The application provides a more efficient, flexible and intelligent solution with scene generalization capability for the spacecraft formation flight task planning problem.

A computerized method and system for providing and implementing an artificial intelligence (AI) model that includes a plurality of models are provided. The method employs, for example, a computer having at least one processor and at least one memory and comprises receiving a query, identifying a user's context based on the query, and receiving the identified context through at least one artificial intelligence model and generating a response to the query, wherein the generating of a response may comprise controlling at least one router to determine at least one of a plurality of artificial intelligence models as a task execution model for the query, ingesting input data based on the context into the at least one determined task execution model, and sequentially or concurrently operating the at least one task execution model into which the input data has been ingested to generate a response to the query.

Provided are a data processing method and apparatus, and a model optimization method and apparatus. The data processing method comprises: respectively sampling in a plurality of data sets so as to determine target sample data on the basis of sampling results; inputting the target sample data into a plurality of language models for respectively processing to obtain target prediction data respectively outputted by the plurality of language models; using a preset text annotation model to perform text annotation processing on each piece of target prediction data to obtain text annotation information corresponding to each piece of target prediction data; and constructing a sample data group on the basis of the target sample data, the target prediction data, and the text annotation information, wherein the sample data group is used for executing a model training task and a model verification task.

The invention provides a multi-model cooperative task processing method and system and related equipment, and the method comprises the steps: receiving a user instruction, carrying out the semantic understanding and task decomposition of the user instruction through a preset task planning model, and generating a task target list; utilizing a preset task creation model to convert the task target list into a structured task flow which accords with a predefined workflow DSL specification and comprises task node information, constraint rule information of task nodes and dependency relationship information among the task nodes; calling a preset task execution model library based on the structured task flow to perform redundancy execution on each task node in sequence, and generating a processing result of each task node; and summarizing and comprehensively analyzing all the processing results through the task planning model, and generating a final output result after the comprehensive analysis is passed. The illusion output of multiple models is reduced by reasonably decomposing the model task and cooperating with the structured workflow DSL and verification before output.

Agentic Experience Automation (AXA) is a novel system for dynamic, autonomous workflow execution within enterprise environments. AXA introduces a Multi-Agent System where specialized AI agents, tailored to specific industry verticals, leverage a fine-tuned language model provided by an AXA vendor to reason, plan, and act independently. The system employs AXA Declarations, a proprietary declarative framework, to translate high-level intents into actionable workflows, allowing the AI agents to adapt execution in real time based on contextual data, end-user interactions, and industry-specific requirements. The system seamlessly integrates security and compliance mechanisms into AI Agents. The AI Agents encapsulate all platform functions, workflows, and policies, dynamically adjusting to specific industry needs. Additionally, AXA supports a hybrid execution model, combining the predictability of rule-based micro-engagement engines with the flexibility of agentic oversight. Extensibility through plug-in components for future functions and dynamic policy modules ensures scalability, adaptability, and compliant with evolving industry standards.

The invention discloses a hot patch implementation method and system based on program defect dynamic detection and redirection replacement, and belongs to the technical field of computer software security. According to the method, a dynamic addressing technology for a fault code in a memory space during terminal operation is adopted, a fault code address is positioned by aggregating process memory mapping and byte code signature information, code loading is processed in combination with a memory patch fragmentation injection mechanism, so that isolation and independence of patches are realized, a patch instance in a memory state is obtained, and the service life of the patch is prolonged. A hot patch execution model based on dynamic redirection replacement is constructed, and a complete execution context is aggregated by backing up and reusing an original instruction. Compared with a traditional shutdown updating or static patch tool, the method can more comprehensively adapt to different platforms, the problems of repair failure and service interruption caused by dependence on a fixed address and a specific environment in a traditional method are solved, and the repair precision and the system availability are improved.

The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating context engine outputs by utilizing an interpreter specially constructed for executing code generated by a large language model. For example, the disclosed system generates executable computer code for responding to a query by utilizing a large language model. Further, the disclosed system executes model-generated computer code using an interpreter integrated with a context engine, the context engine further including interchangeable logic interchangeable across multiple actuators. Further, the disclosed system may also generate a first context engine output by implementing the interpreter at the first executor as part of executing the computer code with the interpreter. In addition, the disclosed system may also generate a second context engine output by implementing an interpreter at a second actuator.

The invention discloses a self-adaptive MPC control method based on data driving, and the method comprises the steps: constructing a quadratic programming objective function containing a tracking error term, a control input change penalty term and a soft landing term, determining control input and increment thereof, outputting constraint conditions of a predicted value, converting the constraint conditions into a quadratic programming problem, solving the problem, executing model mismatch detection, and carrying out soft landing. The unit step response model is corrected in a self-adaptive mode, the steady-state gas flow recommended value is estimated online, and rolling optimization and feedback correction are carried out. The method can improve the precision and robustness of temperature control under a complex working condition, reduces the modeling cost, achieves the smooth transition of control input, and is suitable for industrial edge deployment.

This application relates to a model training task execution method, a graphics processing unit (GPU), and a model training system. The model training task execution method includes: when performing attention calculations for the forward propagation of the model on the current text segment, sequentially loading the key-value pair activation values ​​corresponding to each preceding text segment from the central processing unit (CPU) for attention calculation; simultaneously unloading the key-value pair activation values ​​corresponding to the current text segment to the CPU; when performing attention calculations for the backpropagation of the model on the current text segment, loading the forward propagation output and key-value pair activation values ​​corresponding to the current text segment from the CPU, and sequentially loading the attention activation values ​​corresponding to each preceding text segment, performing attention calculations with the forward propagation output and key-value pair activation values ​​corresponding to the current text segment to obtain gradient values; and unloading the gradient values ​​to the CPU. This method can improve the execution efficiency of text training tasks for large language models under GPU resource constraints.

This application provides a method and apparatus for updating a semantic codec model. The method includes: obtaining the current data distribution drift intensity for evaluating the performance degradation of the semantic codec model; calculating the current model's performance degradation rate based on the correlation function between the drift intensity and the model performance degradation rate; constructing an average drift-aware model age expression based on the model performance degradation rate and the queuing model type; calculating the relative computational load based on the drift intensity; calculating the total service time for a single model update based on the relative computational load; and periodically executing the model update steps until the update termination requirements are met, at which point execution stops. The model update steps include: solving a preset objective function to obtain an optimal update frequency; and updating the current model at the optimal update frequency to obtain the updated semantic codec model. This application enables dynamic adjustment of the update frequency, improving system resource utilization efficiency while ensuring semantic reconstruction performance.

The application discloses a natural language operation method and system of architecture modeling software, and belongs to the technical field of architecture modeling and artificial intelligence. In view of the problem that existing architecture modeling relies on graphical interface operation and natural language requirements are difficult to be directly converted into modeling execution actions, the application abstracts the operable ability of the architecture modeling software into a named tool set, generates a machine-readable tool mode list, constructs a multi-role message chain with a calling identifier, inputs the message chain and the tool mode list into an external natural language model for reasoning, analyzes and executes the structured tool call output by the model by a unified tool executor, backfills the execution result into the message chain for iterative reasoning, and realizes automatic mapping of natural language requirements to architecture modeling operations. The application can adapt to language models with different capability levels, and improves the executability and stability of natural language driven architecture modeling.

This application relates to the field of artificial intelligence technology, and provides a task execution method and related equipment based on a large language model. The method includes: decomposing a complex task into multiple subtasks using a task decomposition model, and constructing an execution model for each subtask; planning all subtasks using a task planning model to obtain the logical execution order of all subtasks; calibrating each subtask to obtain multiple final subtasks, and then combining all final subtasks according to the execution order to obtain a combined task; and executing the combined task using all execution models to obtain the final execution result of the complex task. The method of this application can improve the versatility of task execution methods.

One example method includes evaluating a function invoked by a request that is received at a local classical computing execution environment, and the request also implies performance of a quantum computing function in a quantum computing execution environment, based on an outcome of the evaluating, determining whether or not the function should be run in the local classical computing execution environment, or whether the function should be run in a separate classical computing execution environment, and when the determining indicates that the function should be run in the separate classical computing execution environment, forwarding the request to the separate classical computing environment for execution of the function. The local classical computing execution environment, the separate classical computing execution environment, and the quantum computing execution environment, are respective first, second, and third, tiers of a hybrid computing execution environment.

The application provides a kind of multilingual source code automation verification method and system, it is related to computer technology field, method includes: obtaining multilingual source code;Through LLVM compiler, multilingual source code is compiled, and intermediate file is generated;Optimize intermediate file;Through IR resolver, the intermediate file after optimization is parsed, and symbolic execution model is generated;Simulate execution operation to symbolic execution model;After simulating execution operation, the safety verification of symbolic execution model is carried out, and verification report is obtained.The application can realize the unified verification of multilingual source code, greatly reduce the cost of verification environment building and development, improve the overall efficiency of verification;It can also strengthen the analysis ability of intermediate file, accurately capture the logical constraint relationship in code, effectively guarantee the comprehensiveness and reliability of verification work, meet the diversified software safety verification demand.

A method is presented that facilitates training a very large number of machine learning execution models for detecting anomalies in computing operations. The models are grouped together according to model type and assigned to different pods of a computing environment used to perform the monitored operations. Initial training of the models in a group is performed while monitoring resource usage, and based on the resource usage, a particular pod is selected for further training. The pod selected for training preferably has minimal resource usage variation before and after the initial training. A different pod can be selected to score the trained models. The pod selected for scoring preferably has the greatest resource usage among all containers during the initial scoring.

The application discloses a prompt adaptive optimization method fusing a lightweight prompt rewriting model, and belongs to the technical field of natural language processing and artificial intelligence, and comprises the following steps: (1) filtering error samples by using a task execution model, combining a high-performance large language model to generate feedback information and optimization prompts, and constructing a prompt optimization training data set; (2) performing supervised training on a lightweight prompt rewriting model based on LoRA parameter efficient fine-tuning, so that the lightweight prompt rewriting model has prompt generation and optimization capabilities; (3) embedding the fine-tuned lightweight prompt rewriting model into a prompt optimization framework to realize automatic iterative optimization of prompt content; (4) dynamically updating the optimization prompts by using task evaluation results, and outputting final optimization prompts. The application reduces the dependence of the prompt rewriting module in the prompt optimization framework based on the example guided reflection and memory mechanism on the high-parameter large language model, reduces the model deployment and inference overhead, and improves the reproducibility and deployability of the prompt optimization method in the resource-constrained scene.

The invention discloses a simplification method and system based on a Matlab / Simulink stability control system model. The method comprises the following steps: dividing the stability control system model into a control measure execution model and a local strategy search model according to whether the stability control system model has a local strategy; classifying and simplifying the plurality of divided control measure execution models according to a generator tripping principle and a criterion, and performing e file aggregation and simplification on the divided local strategy search model; model simplification is carried out on a Matlab / Simulink platform by adopting a method of constructing a general logic expression module and packaging a general programming language. Compared with the prior art, the method has the advantages that the action result and the action time sequence of the stability control device model are reserved, the modeling efficiency during modeling of the multiple stability control devices of the stability control system is improved, and the adaptability of a simulation system to simulation of the large-scale stability control system is enhanced.

This invention discloses a method, apparatus, electronic device, storage medium, and program for operator hybrid compilation. The method includes: obtaining a first original operator code file of a first hardware instruction execution model and a second original operator code file of a second hardware instruction execution model; wherein a function call relationship exists between the first and second original operator code files; compiling the first and second original operator code files to obtain a first virtual instruction file and a second virtual instruction file; and linking and compiling the first and second virtual instruction files using a virtual instruction compiler to obtain an executable file of hardware instructions. The technical solution of this invention can improve the compatibility of operator hybrid compilation, reduce the maintenance difficulty of operators, simplify the underlying hardware scheduling and optimization logic, and enhance the versatility and stability of hardware resource utilization.