206 results about "Pipeline (software)" patented technology

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.

The present disclosure provides systems and methods that support identification of vulnerabilities within a dataset, such as an unknown binary, using customizable pipelines and workflows. The pipelines may be configured to apply various analysis techniques, including reverse engineering, machine learning / artificial intelligence, and other techniques to elicit various types of data and information from the unknown binary. The pipeline may include stages configured to analyze outputs of prior stages of the pipeline detect whether vulnerabilities or malicious code are present. Different stages of the pipeline may also be configured to initiate additional workflows for further analysis of the binary or intermediate representations of the binary output by prior stages of the pipeline. Additionally, the disclosed systems and methods provide functionality that enables generation of a reverse software bill of materials (SBOM) from an unknown binary or confirmation of contents of an existing SBOM.

The invention belongs to the technical field of pipeline arrangement optimization, and particularly relates to a pipeline optimization design auxiliary platform based on a BIM (Building Information Modeling) technology, which comprises a preprocessing module, a BIM modeling module, a collision detection module, a simulation module, a collaborative design module and a feedback module, comprising design drawings, landforms and existing pipe network distribution parameters. The BIM modeling module utilizes BIM software, the pipeline optimization design auxiliary platform based on the BIM technology can fully combine specifications or design requirements, input requirements for pipeline space arrangement, on-way resistance, construction cost and the like in advance, automatically provide various optimization schemes for comparison and selection, input according to parameters of the space arrangement, the on-way resistance and the construction cost, reduce the resistance of a pipeline system, and improve the pipeline optimization design efficiency. And the material cost in construction is reduced, so that the construction cost and the construction period are comprehensively controlled, and energy waste caused in the operation process of the pipeline system is prevented.

Techniques are provided for software deployment pipeline generation using generative artificial intelligence (AI). One method comprises obtaining a trained generative AI model, trained using a plurality of continuous integration / continuous deployment (CI / CD) configuration files; obtaining information characterizing a selected software development project; and applying at least some of the information characterizing the selected software development project as one or more system prompts to the trained generative AI model, wherein the trained generative AI model predicts a portion of a software deployment pipeline associated with the selected software development project. The CI / CD configuration files used for training may be associated with an organization that is associated with the selected software development project. The predicted portion of the software deployment pipeline may comprise pipeline jobs, an automatic code completion and / or a correction of a syntax and / or a structure of at least one CI / CD configuration file being edited.

The invention discloses an efficient Transform model reasoning accelerator deployment method based on Versaal ACAP, and belongs to the field of software and hardware collaborative acceleration numerical calculation. Firstly, load analysis is carried out on the model, and meanwhile, according to hardware performance, the types and scales of operators needing to be borne by hardware of all parts are determined; then, hardware is equipped with a data transmitter, a data receiver, a nonlinear operator and other modules; then, the modules are reasonably deployed and connected in hardware, pipeline parallelization is completed, and calculation of a multi-head attention stage and a feedforward neural network stage is achieved; and finally, integrating the two stages to realize accelerated calculation of the whole encoder / decoder layer so as to accelerate the reasoning speed of the upper layer model. Experiments prove that the throughout of the model is effectively improved, the reasoning delay is reduced, meanwhile, the accelerator has huge advantages in the aspect of batch reasoning, and the accelerator has wide application prospects in the aspects of reducing the model reasoning cost and improving the model reasoning speed.

Techniques are provided for automated evaluation of software items of a software deployment pipeline. One method comprises, in response to a request to add a software item to a software deployment pipeline: determining an approval status of the software item for inclusion in one or more stages of the software deployment pipeline based on an evaluation of designated properties of the software item relative to designated criteria; and initiating an automated action based on at least one result of the determining. The designated properties (such as a version and / or an approval status) of the software item are specified for a particular product. Real-time changes may be applied to the designated properties of the software item. The software item may be classified into a designated license category having associated license guidelines. Metadata for the software item may be based on the designated license category.

Systems, methods, and machine-readable media may facilitate one or a combination of the following. A software change operation within a deployment pipeline for testing and deploying a software change to a production computing service may be processed. The software change operation may be identified as corresponding to a software change with the deployment pipeline, where the software change may be identified as being configured to make a pipeline change to a configuration of the deployment pipeline itself. Responsive to the identifying, a regression suite configured to run a plurality of test applications on the deployment pipeline to test the deployment pipeline with respect to the software change may be invoked, and the plurality of test applications may be run with the software change. The running the plurality of test applications may include simulating pipeline runs with a plurality of use cases.

The invention relates to the technical field of software engineering and artificial intelligence crossing, in particular to an API test case rapid generation method and system based on an AI large model.The method comprises the following steps that joint analysis and semantic fusion are conducted on an API document and a demand document through a multi-modal data analysis layer, and a complete test context is constructed; generating a test case based on the pre-trained large model by using a hybrid inference engine; the method has the beneficial effects that the association constraint of the API document and the demand document is automatically extracted through semantic understanding; a parameter combination strategy is optimized through reinforcement learning, and the problem of combination explosion is solved; constructing a self-adaptive test case maintenance mechanism, and responding to API version iteration; an executable test code that can be directly integrated into the CI / CD pipeline is generated.

In some implementations, a code testing device may receive, from a first device associated with a developer, a first instruction to merge a first code branch. The code testing device may perform a first set of tests, associated with a first environment, in response to the first instruction. The code testing device may merge the first code branch based on the first set of tests resulting in a passing outcome for the first code branch. The code testing device may receive, from a second device associated with a reviewer, a second instruction to deploy the merged first code branch. The code testing device may perform a second set of tests, associated with a second environment, in response to the second instruction. The code testing device may deploy the merged first code branch based on the second set of tests resulting in a passing outcome for the merged first code branch.

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.

Systems and methods for error mitigation in a software pipeline. In some aspects, the system receives a request for evaluating a pipeline at a recurrent interval of time. The request comprises a first version of software, a second version of software, evaluation tests to execute on the second version of the software at intermittent intervals, and the recurrent interval of time. The system, in response to determining the recurrent interval of time elapsed, executes the evaluation tests on the second version of the software. The system determines that the output of the evaluation tests does not match one or more target values. The system terminates deployment of the second version of the software. The system generates instructions to replace the second version of the software with the first version of the software and transmits a notification to a remote device.

Methods and apparatus for extending OpenvSwitch (OVS) megaflow offloads to hardware to address hardware pipeline limitations. Under a method implemented on a compute platform including a Network Interface Controller (NIC) having one or more ports and running software including OVS software and a Linux operating system having a kernel including a TC-flower module and a NIC driver a new megaflow is created with a mask in the OVS software employing a subset of microflow fields for a packet. The microflow fields and the megaflow mask is sent to the NIC driver. A new megaflow is implemented in the NIC driver employing a subset of the microflow fields and the NIC driver creates a new hardware flow on the NIC employing a packet match scheme using all the microflow fields. The NIC also programs a NIC hardware pipeline with the new hardware flow using a match scheme that may depend on the available hardware resources, such as the size of a TCAM.

In an implementation of a computer-implemented method: to create extracted data records, an extract filter is instructed to extract relevant data records from log messages of two runs of a software pipeline. To create diff records using the extracted data records, a diff filter is instructed to compare and identify differences in messages between the two runs, where the diff records are amended with labeled data status information of a software pipeline run the extracted data records have been taken from. A recommendation engine is instructed to execute a machine-learning model training with the diff records. The recommendation engine is called to analyze the diff records for a failure-indicator. A determination is made that a failure causing the failure-indicator has been corrected in a later run of the software pipeline. A change is identified in a configuration or version of a software application associated with a correction. A failure-indicator-solution combination is generated.

Techniques are provided for generation of a software deployment pipeline manifest using software item metadata. One method comprises obtaining software items, requested for inclusion in a software deployment pipeline, and corresponding metadata for at least one of the requested software items, from a software repository; in response to a request to transform a given stage of the software deployment pipeline, generating a manifest for the given stage, wherein the manifest identifies the software items in the given stage and comprises the corresponding metadata for the software items in the given stage; and storing the manifest for the given stage in the software repository. The storage of the software items in the software repository may comprise evaluating, prior to the storage: (i) a presence of vulnerabilities in the software items and (ii) a license review status of the software items.

Some examples of the present disclosure relate to risk analysis of test failures that occurred during a testing phase of a continuous integration pipeline. In one particular example, a system can detect a failure of a test during a testing phase of a continuous integration pipeline. The testing phase can involve executing a group of tests in a plurality of configurations prior to merging an update to source code into a code base of a software application. Based on detecting the failure of the test during the testing phase, the system can access historical data associated with prior executions of the test, determine a risk score associated with the failure of the test based on the historical data, and perform an action associated with the source code based on the risk score.

Techniques are provided for visual generation of software deployment pipelines using recommendations of development and operations (DevOps) blueprints. One method comprises obtaining information characterizing a technology type and a programming language for a selected software development project; recommending a DevOps blueprint for the selected software development project based on a technology type and a programming language for the selected software development project, wherein the DevOps blueprint comprises reusable software development resources for the technology type and the programming language; providing a graphical interface to present a visual representation of the reusable software development resources; obtaining information characterizing interactions of a user with the graphical user interface to select the reusable software development resources for a pipeline associated with the selected software development project; and automatically generating software code in a target programming language of the DevOps collaboration tool based on the reusable software development resources in the pipeline.

Techniques are provided for software deployment pipeline evaluation using a presence of designated functions. One method comprises obtaining information characterizing a set of designated functions; determining one or more of: (i) whether at least one stage of a given software deployment pipeline comprises one or more of the designated functions in the set and (ii) whether an execution of one or more of the designated functions in the at least one stage of the given software deployment pipeline succeeded; and initiating one or more automated actions based at least in part on at least one result of the determining. The designated functions may be specified for different technology types. Job logs associated with the at least one stage of the given software deployment pipeline may be searched for commands that execute one or more of the designated functions.

The invention discloses a building electromechanical integrated pipeline module length division method and system. Efficient and accurate division of building electromechanical integrated pipeline modules is achieved through an intelligent optimization technology. According to the method, firstly, factors influencing module division are analyzed and classified, and an optimization model comprehensively considering multiple factors such as construction conditions, cost and material utilization rate is established in combination with a modular design theory; the model is optimized through an improved genetic algorithm, and the optimal balance of module division between construction efficiency and economical efficiency is achieved. A set of software system matched with the division method is developed, functional modules including pipeline information input, support and hanger type selection, module length optimization, BIM model segmentation, connecting piece arrangement, module grouping and numbering, performance evaluation, engineering quantity statistics and the like are covered, an optimal division scheme is automatically generated, and construction guidance is provided. The building electromechanical integrated pipeline division efficiency and construction quality are improved, and the method is suitable for various building engineering projects and has wide application prospects.

The invention relates to a simulation calculation method, device, equipment and medium for an anti-impact system with a pipeline, and belongs to the technical field of simulation computation.The simulation calculation method for the anti-impact system with the pipeline comprises the steps that geometric models of all parts of the anti-impact system with the pipeline are established, and the geometric models are imported into preset simulation software for preprocessing operation; modal analysis is carried out on the geometric model after preprocessing operation, and modal parameters of the anti-impact system with the pipeline are obtained; performing spectral analysis on the geometric model after the preprocessing operation based on the modal parameters to obtain an impact response of the anti-impact system with the pipeline; and according to the impact response, adjusting component parameters of the anti-impact system with the pipeline. According to the method, accurate simulation and calculation are carried out on the impact-resistant system with the pipeline, the component parameters of the impact-resistant system with the pipeline are adjusted, and the impact resistance of the impact-resistant system with the pipeline is improved.

The invention relates to the technical field of software engineering, and discloses an assembly line flow adaptive configuration method and system. The method comprises the following steps: obtaining source code data of a software project and performing static analysis and feature extraction to generate structured language description data; querying and matching in a preset template library based on the structured language description data to generate a task template set; performing task dependency relationship analysis and process topology assembly on the task template set to generate initial pipeline data; and performing dynamic strategy adjustment on the execution process of the initial pipeline data by adopting the real-time context data corresponding to the software project to generate target pipeline data. Through automatic language recognition and intelligent process generation, automatic configuration of the continuous integration process is realized, and the technical problem of low automation level caused by lack of automatic recognition and adaptation capability for a project development language environment in a project continuous integration and continuous deployment technology is solved.

The disclosed system and process involve correlating outbound traffic with a CI / CD pipeline. CI / CD Pipelines consist of multiple jobs, and each job's steps execute on the same runner host. Network monitors relay information about domain names and network connections during job execution to the data store. Once all pipeline jobs are complete, the correlation server links domain names and connections to determine endpoints. This correlation, showing outbound traffic for each step, is accessible to the pipeline owner for review. An alert is triggered for new endpoints relative to the baseline. Owners can block unexpected endpoints based on explicitly defined lists. The correlation server also identifies file events, aiding in detecting suspicious file and software build overwrite events for combating software supply chain attacks. Observed file and network events contribute to generating a Software Bill of Materials (SBOM) through runtime events.

A continuous integration (CI) pipeline can be executed based on a type of content for a change to source code. For example, a computing system can receive the change to the source code of a software application in response to a request for changing the source code being generated. The computing system can identify the type of content included in the change to the source code. Specifically, the computing system can determine whether the type of content is associated with a prevention of an execution of the CI pipeline. In response, the computing system can perform an action associated with the change to the source code prior to a deployment of the change to the source code.

The systems and methods disclosed herein relate to a model validation platform that enables dynamic validation of a user's prompt for a large language model (LLM) in order to evaluate the validity of the prompt and the suitability of a large language model for processing the prompt. For example, the platform enables an estimation of the resource allocation associated with processing the prompt with a given LLM, as well as a modification of the prompt, prior to the processing the prompt with the selected LLM. The platform can further validate the output prior to transmitting the output to a server system for display to the user. By doing so, the platform enables dynamic evaluation of a request to execute an LLM, as well as evaluation of resulting outputs, for accuracy and efficiency improvements in data processing or software development pipelines.

In one example, a computer system can generate a graphical user interface (GUI) for forecasting software including a drag-and-drop canvas with a set of rearrangeable nodes defining a forecasting pipeline. The computer system can detect a user interaction for attaching an external-language execution node to the pipeline, which can be used to insert custom code defined using an external programming language. The computer system can receive the custom code. The computer system can receive a user input to initiate execution of the pipeline. The computer system can generate wrapped custom code by augmenting the custom code with additional program code including shared variables. The computer system can provide the wrapped custom code to a set of execution threads configured to execute the wrapped custom code as part of the pipeline to generate one or more forecasts. The computer system can output the forecasts in the GUI.

The invention discloses an assembly line publishing method and system supporting multiple deployment modes based on agile development, the system comprises a basic software installation and deployment module, an application configuration module and an assembly line execution module, the basic software installation and deployment module is used for installation of Gitlab, Jenkins, Jenkins plug-ins, docker, kubectl and continuous delivery micro-applications; the application configuration module is used for continuously delivering configuration of related applications, assembly lines, servers, K8S clusters, mirror image warehouses and characteristic branches in the micro-applications; the assembly line execution module is used for submitting and releasing characteristic branches in the continuous delivery micro-application and operating an assembly line; the user does not need to concern about different deployment packages or mirror images caused by difference of operating environments such as system testing and production and the complexity of manual compiling, deployment and release, so that the operation risk is reduced, the deployment time is shortened, the workload of operation and maintenance personnel is reduced, the release efficiency of system update deployment is improved, and the time and labor cost is reduced.

A generative artificial intelligence (AI) pipeline has been created that employs aspects of natural language processing (NLP) to detect intents of web API calls and then summarizes the behavior expressed by the collective of intents. The pipeline uses a lightweight language model for intent classification of URLs corresponding to API calls in a time interval. The pipeline associates the intent classifications with metadata corresponding to the URLs and feeds this into another lightweight language model that summarizes the intent classifications and metadata. The natural language summarization describes exhibited behavior that can be understood by a wider audience than security experts. The capability to detect intents of API calls occurring in network traffic increases visibility and control of user behavior, particularly in Software-as-a-Service (Saas) environments. Furthermore, the enhanced visibility of user behavior with the created pipeline recognizes new and previously unseen API calls from live network traffic at enterprise scale.

A system, computer program product, and method are provided for distributed data workflow semantics. A pipeline, such as a machine learning (ML) pipeline, is represented in a data flow graph (DFG). The represented pipeline is subject to annotations, with the annotations including pipeline nodes and object references. The pre-processed pipeline is subject to execution or processing with the annotated object references capturing object lineage. Output from the executed pipeline is constructed and a corresponding control signal is formatted to dynamically and selectively control an operatively coupled physical hardware device or software.

Data processing tools often use pipeline-based workflows, which consist of a sequence of operations. Each operation is configured according to configuration settings provided by a pipeline developer. The operations may use other software components such as frameworks that may also be configured. An application developer that defines a series of operations to be performed to achieve a desired result is able to provide the configuration settings for the operations. However, the application developer may not have the expertise to efficiently define configuration settings for the underlying frameworks. As discussed herein, a pipeline configuration system is used to generate configuration settings for frameworks used by a pipeline based on configuration settings for the operations of the pipeline. The operation configuration may include non-transformable properties, transformable properties, and internal properties. The pipeline configuration system may primarily modify the transformable properties.

With invocations of a software development pipeline, organization specific remediations / fixes for a software project can be learned from scanning results of code submissions (e.g., commits or merges) across an organization for a software project(s). Fixes of detected program code flaws can be detected and / or specified across scans and associated with flaw identifiers and used for training machine learning models to identify candidate fixes for detected flaws. This ongoing learning during development propagates fixes created or chosen by experts (e.g., software engineers working on the software project) relevant to the software project. The experts can choose from suggestions mined from the learned fixes of the organization and suggestions generated from a pipeline created with the trained machine learning models. The selections are then used for further training of the machine learning models that form the pipeline.

The invention provides a heterogeneous acceleration method and system based on a parallel gene sequence alignment algorithm, and the method comprises the steps: S1, dividing DNA into n fragments, and enabling a CPU end to read the fragment data of the DNA; s2, performing parallel multi-thread processing on the fragment data at a CPU (Central Processing Unit) end to generate input data; s3, predicting the execution time of the corresponding thread at the software CPU end and the execution time of the corresponding thread at the hardware FPGA end; s4, according to the predicted execution time, selecting a position where the input data continues to be executed; s5, if acceleration processing is carried out at the FPGA end, the processed data are stored in a global memory; and S6, enabling the CPU end to perform parallel sequence alignment on the data in the global memory to complete sequence alignment. According to the invention, a strategy for realizing parallel processing of a plurality of to-be-aligned sequences based on software multithreading is realized, and the FPGA equipment end realizes parallel and streamlined processing of a plurality of sequences based on multiple cores.