2873results about "Model driven code" patented technology

An example operation may include one or more of storing software architecture documents which include text-based descriptions of architecture components, training a generative artificial intelligence (GenAI) model to understand the architecture components based on the software architecture documents in the memory, receiving an input comprising a description of a software architecture implemented by a computing platform, executing the GenAI model based on the description of the software architecture to generate a description of a change to be made to the software architecture, and outputting the description of the change on a user interface.

A generative artificial intelligence (AI) driven code fixing pipeline has been created that uses a transformer-based large language model (LLM) to patch flawed program code. A pre-trained LLM is fine-tuned to generate a response that is a modified version of a code fragment in a prompt to the pre-trained model. After fine-tuning, the pre-trained LLM (hereinafter “code fix model”) is integrated into a pipeline that includes a program code cybersecurity scanner and a prompt generator. The scanner generates indications of flaws in program code and weakness types for those flaws. These indications flow into the prompt generator. The prompt generator retrieves reference code pairs based on weakness type and programming language to generate a batch of prompts to run inference on with the code fix model. The responses generated by the code fix model are presented as patching alternatives.

An example operation may include one or more of ingesting data from one or more websites via one or more application programming interfaces (APIs) and storing the data within a data store of a host platform, generating one or more prompts and displaying the one or more prompts on a user interface of a user profile page within a software application hosted by the host platform, receiving one or more responses to the one or more prompts, generating a design of a structure based on execution of an artificial intelligence (AI) model on the data from the one or more websites, the one or more prompts, and the one or more responses, and displaying the design of the structure via the user interface of the user profile page of the software application.

A self-improving code / prompt system (e.g., an operating system or a process layer) for generating and / or reusing code / prompt processes is provided. Code / prompt processes include a sequence of prompts for a model, such as an LLM and traditional logic (code) which augments the input / output to the LLM and orchestrates interaction with other third party processes. The system includes an interpreter for managing the execution of code / prompt processes and corresponding interactions with external models, system processes, a process database (e.g., of existing code / prompt processes), and other sources.

An example method can include providing a natural language instruction and user interface image data to a machine-learned sequence processing model that is configured to process image data and generate commands for controlling the target computing device, wherein the machine-learned sequence processing model has parameters learned using an interface recognition objective based on an evaluation of an interface recognition output generated based on processing a rendered training interface from a pre-training dataset and an interface navigation objective based on an evaluation of a user interface command generated based on processing a rendered training interface from a fine-tuning dataset; receiving, from the machine-learned sequence processing model, a command indicating an interaction with the user interface to implement the natural language instruction; and generating, based on the command, a control signal configured to initiate the interaction.

Software code development and quality assurance through generative Artificial Intelligence systems and methods that streamline continuous integration and continuous deployment (CI / CD) pipelines without increasing review or development durations.

Systems and methods disclosed herein perform privacy-preserving evaluations of artificial intelligence (AI) agents. A first AI agent associated with a first entity obtains a machine-readable data structure defining one or more operative boundaries for a second AI agent associated with a second entity. The system generates a unique fixed reference value representing the machine-readable data structure by applying a first transformation operation set, and transmits the unique fixed reference value to a multi-agent storage to store the value. The system receives, via the multi-agent storage, a verification artifact from the second AI agent that indicates an observed value based on internal operational data of the second AI agent corresponding to the operative boundaries. The first AI agent determines a verification status of the verification artifact by comparing the unique fixed reference value with the observed value, and autonomously generates a verification record including a representation of the verification status.

A system, method, and computer-program product includes identifying a plurality of code synthesis items for a target programming language, generating a code synthesis prompt based on a first sampling of the plurality of code synthesis items, synthesizing, via a large language model, a plurality of raw code segments using the code synthesis prompt, executing the plurality of raw code segments with a code interpreter associated with the target programming language, determining one or more valid code segments of the plurality of raw code segments that the code interpreter successfully executed, aggregating, via a second sampling, the one or more valid code segments into one or more validated code synthesis training samples, and training a code generation model using the one or more validated code synthesis training samples. User interfaces may be provided to allow target coding tasks to be specified via text or speech.

Techniques are described herein that are capable of providing a recommendation of AI-modified code in context of a developer tool. Based at least on code being developed in a developer tool, an interface element is provided in a user interface of the developer tool. The interface element is configured to receive a prompt that specifies a modification to be performed on the code. Based at least on receipt of the prompt, an AI model is automatically caused to perform the modification on at least a snippet of the code to provide a modified snippet. The modified snippet is processed using a language intelligence tool of the developer tool to provide a processed version of the modified snippet. A recommendation to replace the snippet in the code with the modified snippet is provided by causing the processed version of the modified snippet to be displayed via the user interface.

A digital documentation system for preparation of engineering documents utilizing one or more artificial intelligence (AI) algorithms is provided. The system includes a user interface for selecting and populating templates with data, and one or more AI algorithms for creating and recommending templates, and preparing documents based on the recommended templates. The system uses natural language processing and semantic analysis algorithms to understand the content of the templates, documents, and associated engineering data, and to generate and recommend relevant templates to the user based on user prompts. The system also uses machine learning and predictive modeling and decision-tree algorithms to assist with the preparation of documents, by generating suggestions for data fields and values based on the user's previous inputs and the overall context of the document and available engineering data, including model data and metadata from digital models accessed in a zero-trust framework.

A method for creating and deploying plugins for use with one or more web-hosted large language model applications includes: displaying a user interface comprising a code template for creation of a plugin, wherein the code template comprises a context template, a native function template, and a semantic prompt template; receiving modifications to the code template via the user interface to form a modified code template, the modified code template comprising: custom context based on the context template; custom native code comprising one or more computer executable functions based on the native function template; and a custom prompt configured to prompt a large language model based on the semantic prompt template; generating a plugin based on the modified code template; and storing the plugin within a database of a plugin registry.

Computer-implemented systems and methods use a Large Language Model (LLM) for converting a legacy computer program in a first language to a human-language description of the legacy computer program, which description can be validated as being an accurate description of the legacy computer program. Once validated, the human-language description can be converted, again using an LLM, to a computer program in a target programming language. An LLM can also be used to generate test scripts for the new target-language program to test the performance of the target-language program in a production environment. An LLM can also be used to reconcile outputs from the legacy program to the new target program, such as on a function-by-function basis. If the differences between the outputs (if any) are sufficiently negligible, the legacy computer program can be decommissioned, and the new, target language program can be used in production.

The invention discloses an intelligent low-code development method and system based on deep learning model optimization, and relates to the technical field of deep learning. A multi-dimensional domain knowledge graph is constructed, a three-dimensional space-time fusion training sample set is constructed based on the domain knowledge graph, and cross-modal feature alignment is performed on the training sample set, so that the multi-dimensional domain knowledge graph is constructed; the method comprises the following steps: generating an executable logic flow template, encoding the executable logic flow template into a Markov decision process, and performing joint strategy optimization on an optimization target of logic flow by integrating a feature importance index generated by a gradient back propagation path and a multi-target reinforcement learning framework of a Pareto leading edge analysis module. Extracting a strategy parameterization sequence after joint strategy optimization, injecting the strategy parameterization sequence into a dynamic verification sandbox environment, and performing abnormal mode detection and feedback type parameter distillation iteration on an execution track through an online variational auto-encoder to complete dynamic adjustment of the strategy; and the elasticity, the stability and the expandability of the low-code platform are improved.

A method include receiving a natural language prompt from a user comprising a command to generate a code script for an automated assistant to perform a routine. The routine includes multiple discrete actions specified by the natural language prompt. The method further includes processing, by a pre-trained large language model (LLM), the natural language prompt to generate the code script as an LLM output, and processing the code script to determine the code script is incomplete, thereby rendering the code script unsuitable for the automated assistant to fulfill performance of the routine. Based on determining the code script is incomplete, the method includes issuing a user prompt soliciting the user to provide additional information needed to complete the code script and receiving user input of the additional information needed to complete the code script. The method includes supplementing the code script with the additional information to render completed code script.

A method for using a large language model to generate executable code for workflow execution in a manner that integrates user feedback and adjusts the workflow as needed while preserving data privacy is provided. The method includes: receiving first information that relates to a workflow context, second information that relates to at least one application programming interface (API), and third information that relates to a code generation request; using the received information to generate a lecture, and transmitting the lecture to a language model; receiving a user query that relates to performing a task, and transmitting the query to the language model; receiving a workflow that is automatically generated by the language model based on the lecture and the query; and executing the workflow in order to generate an output that is responsive to the query.

The invention provides a rules engine that evaluates, modifies, and dynamically routes inputs to AI models based on provider restrictions and management rules. Provider restrictions are stored. Based on management rules and the detected provider restrictions, the input can be modified with contextual placeholders and prompts can be injected for input into the destination model. Reversal of the modifications can occur to the outputs. The system can notify the user, an administrator, and a supervisor regarding the security evaluation and remedial actions. The evaluations can be logged for auditing purposes.

Systems, methods, and other embodiments automated fine-tuning of chatbot performance for large language models are described herein. In one embodiment, a method accesses a collection of sample conversations between two entities. An individual sample conversation includes one or more rounds of natural language example prompt by a querent and example response by an agent. The method fine-tunes an LLM to generate responses in natural language based on a chatbot loss function that evaluates first responses generated by the LLM to the example prompts by the querent. The method generates an evaluation score for performance of the tuned LLM as a chatbot based on second responses generated by the tuned LLM to test prompts from a test conversation. And, the method automatically signals that the fine-tuning of the tuned LLM is complete in response to the evaluation score satisfying a threshold.

Disclosed herein are systems and methods for enabling decentralized, schema-driven interoperability across distributed computing environments through the use of a Standard Knowledge Language (SKL). An Enterprise Mesh Platform (EMP) interprets and executes SKL specifications—such as capabilities, objects, mappings, policies, and workflows—as composable, machine-interpretable contracts that define data structures, logic, and governance protocols. The system supports dynamic versioning, validation, semantic linking, and recursive execution of SKL-defined components. A mesh-wide analytics server coordinates execution, issue detection, and resolution propagation. Capabilities can be orchestrated, remediated, and adapted in real-time based on SKL-defined relationships, while preserving compliance and traceability. The disclosed architecture facilitates federated development, adaptive system integration, and fine-grained policy enforcement across complex digital ecosystems.

A method for automating a software development lifecycle by using artificial intelligence is disclosed. The method includes receiving a request to generate software components, the request including requirements in a natural language format; determining, by using a first model, tasks to generate the requested software components based on the request, each of the tasks including a sequence of subtasks, an acceptance criterion, and a predicted effort level; generating, by using a second model, sets of software code based on the tasks, the sets of software code corresponding to the requested software components; generating, by using a third model, unit tests for each of the sets of software code; initiating the unit tests for each of the sets of software code; and releasing, by using a fourth model, the sets of software code based on a result of the corresponding unit tests.

The invention provides an agent construction method and system based on a large language model, a medium and equipment, and relates to the technical field of decision agent construction. According to the method, an appropriate large language model is selected, a series of prompt project texts are established for the large language model, target codes are generated as required by utilizing the large language model and prompt projects, and class library functions of a network model library, a reinforcement learning algorithm and a simulation training environment can be correspondingly called by running the codes. Finally, auxiliary construction and training of the decision-making agent are realized, and the problems in the existing decision-making agent construction and training process are solved.

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 present disclosure relates to systems, non-transitory computer-readable media, and methods for modifying a fillable digital document. In particular, the disclosed systems can receive a user interaction requesting to populate one or more aggregated data fields in a fillable digital document. In response to the request, the field object generation system can determine the data relevant to one or more aggregated data fields in the fillable digital document by utilizing a large language model to process one or more source content items for a user account. Further the systems and generate a field object from the data relevant to one or more aggregated data field and modify the fillable digital document by including the field object in the fillable digital document.

An issue source scanning system scans a source of information about an issue to identify characteristics of code which indicate that the issue will manifest in code. A code scanning system scans code to match the identified characteristics against the code to determine whether the source code includes the identified characteristics. The code scanning system automatically generates a suggested operation to perform based upon a match between the identified characteristic and the code.

Technical solutions are directed to creation and deployment of multi-stage test problems. A processor can provide, to a client, a first data structure for a first stage of a multi-stage test problem including a description for generation of a client solution for the first stage and a test case to evaluate the client solution. The processor can receive, from the client, a client data structure comprising the client solution including a client computer code generated at the client for the first stage. The processor can determine, by evaluating the client solution using an input value and an output value of the test case, that the output of the client solution satisfies a validity condition of the output value. The processor can provide, to the client, based on satisfying the validity condition, a second data structures for a second stage of the multi-stage test problem.

An integrated development environment (IDE) for designing, programming, and configuring aspects of an industrial automation system uses a generative artificial intelligence (AI) model and associated neural networks to generate portions of an industrial automation project in accordance with functional requirements provided to the industrial IDE system in intuitive formats, such as spoken or written plain language text. The system uses generative AI to translate plain language requests or functional specifications into industrial control code, human-machine interface (HMI) applications, device configuration settings, or other aspects of an industrial control project.

A method includes generating a modeling language diagram that is indicative of a compiled version of program code. The modeling language diagram includes at least one node corresponding to at least one function in the program code. The method also includes identifying at least one function signature associated with anode state transition between nodes in the modeling language diagram. The method also includes identifying, using a large language model, a particular policy to attribute to the at least one function signature associated with the node state transition. The method further includes performing, using the large language model, a policy compliance operation that ensures a particular portion of the program code complies with the particular policy. The particular portion of the program code is associated with the node state transition. Performing the policy compliance operation includes generating a policy-compliant version of the particular portion of the program code.

The invention discloses a digital production plan scheduling method and system, and belongs to the technical field of optimal scheduling, and the method comprises the steps: constructing a distributed storage architecture based on edge computing nodes; a central coordinator is adopted to realize cross-node data synchronization through an improved Raft consensus algorithm, multi-version concurrency control is realized based on a vector clock, and a global consistent data view is established; a visual scheduling platform is built based on a Vue3 framework, and man-machine interaction is realized by adopting a Canvas and WebGL collaborative rendering framework; establishing a dynamic coordinate conversion model based on bilinear interpolation, designing a space mapping function containing distortion compensation, establishing a multi-thread coordinate service based on WebWorker, and realizing submillimeter-level bidirectional mapping of pixel coordinates and physical coordinates; constructing a three-dimensional space-time analysis model fused with the multi-dimensional features; and all the units are subjected to feature fusion through residual connection, and finally a scheduling scheme with a confidence coefficient weight is output. The method and the device have the effect of meeting various scheduling requirements.

The invention discloses an automatic control code generation and verification method and device, equipment and a storage medium, and relates to the technical field of automatic control, the method is applied to a large language model, and a natural language command is received; performing matching retrieval on the vector database according to the natural language command to obtain an example code snippet; obtaining API structured information corresponding to the example code snippets from a knowledge graph database; generating an initial control code based on the example code snippet and the API structured information; and performing multi-stage virtual operation verification on the initial control code in the software motion control system, and generating a target control code according to a multi-stage verification result confirmed by a user for multiple times and the initial control code. According to the method, the initial control code is automatically generated through double-database retrieval based on the large language model, then multi-stage code verification is performed through the software motion control system, the target control code is generated in combination with verification results confirmed by a user for multiple times, and the code generation speed and reliability are improved.

Systems, methods, and other embodiments associated with automated fine-tuning of software code generation by large language models are described herein. In one embodiment, a method accesses a collection of software code samples that intermix sample code and human language description. The method generates prompts to an LLM to write code that performs as described by the human language description of the sample code. The method fine-tunes a large language model to generate software code based on a code generation loss function that evaluates code generated by the LLM in response to the prompts. The method generates an evaluation score for performance of the tuned large language model as a code generator based on code generation loss for second generated code. And, the method automatically signals that fine-tuning of the tuned large language is complete in response to the evaluation score satisfying a threshold.

Disclosed are various approaches for large language model (LLM) application risk mitigation. A large language model (LLM) application that interacts with a network LLM service can be identified. A portion of the LLM application can be provided as input to an LLM risk mitigation code generation function that outputs LLM-specific risk mitigation code. A runtime environment can be deployed to include a modified version of the LLM application that includes the LLM-specific risk mitigation code, a kernel-layer LLM risk mitigation program that can intercept LLM interaction system calls to apply the LLM-specific risk mitigation code, or any combination thereof.