Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

449 results about "System Generation" patented technology

System Generation (SysGen) is a two-stage process for installing or updating OS/360, OS/VS1, OS/VS2 (SVS), OS/VS2 (MVS) and chargeable systems derived from them. There are similar processes for, e.g., DOS/360, which this article does not cover. Also, some of the details have changed between releases of OS/360 and many details do not carry over to later systems.

Natural language generation

Techniques for generating a prompt for a language model to determine an action responsive to a user input, are described. In some embodiments, the system receives a user input, determines one or more application programming interfaces (APIs) configured to perform actions that are relevant to the user input and exemplars representing examples of using the APIs with respect to user inputs similar to the current user input. The system further determines device states of devices that are determined to be related to the user input and also determines other contextual information (e.g., weather information, time of day, geographic location, etc.). The system generates a prompt including the user input, the APIs, the exemplars, the device states, and the other contextual information. A language model processes the prompt to determine an action responsive to the user input and the system causes performance of the action.
Owner:AMAZON TECH INC

Efficiently serving machine-learned model computations with high throughput and low latency

An example method includes receiving input requests to process a plurality of input sequences using the machine-learned sequence processing model to generate a plurality of output sequences respectively corresponding to the plurality of input sequences; generating a plurality of initial attention tensors respectively for the plurality of input sequences, wherein: one or more respective initial attention tensors are generated for each respective input sequence in parallel over input elements of the respective input sequence; and the one or more respective initial attention tensors are generated in one or more batches having a first batch size using a prefill system that comprises one or more prefill computing devices and executes one or more layers of the machine-learned sequence processing model; and autoregressively generating, using the plurality of initial attention tensors, a plurality of output elements for each of the plurality of output sequences in one or more batches having a second batch size, wherein: the plurality of output elements are generated using a generation system that comprises one or more generation computing devices.
Owner:GOOGLE LLC

System and method for detecting prompt injection attacks to large language models

A computing system receives a prompt to be provided as input to a large language model. The computing system generates generating an input string to the large language model by appending a plurality of contexts to the prompt. The plurality of contexts defines rules for the large language model to follow when generating the prompt. The plurality of contexts includes a negative context. Based on the prompt and the plurality of contexts, the computing system generates an attention matrix representing relationships between the prompt and the plurality of contexts. The computing system provides the attention matrix to a trained neural network to determine a likelihood that the prompt is malicious. Responsive to determining that the prompt is likely a malicious prompt, the computing system initiates a remedial action.
Owner:DROPBOX INC

Scaling utilization of large language models

The present disclosure relates to efficiently receiving and processing input tasks in a way that is scalable and which reduces both the quantity of tokens processed by a foundation model (e.g., an LLM) as well as the number of API calls that are made in processing the input tasks. A system batches a set of inputs to provide as a single batch of input(s) into an LLM. The system generates one or more permutations of the batched input(s) to determine outputs based on variable orders in which the input data is provided within the respective permutations of the batched inputs. The system further may eliminate one or more of the data inputs within the respective batches to facilitate smaller batched inputs without sacrificing accuracy in a set of outputs generated by the LLM responsive to the batch permutations.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Programmatically generating evaluation data sets for code generation models

Evaluation data sets may be programmatically generated for code generation models. An evaluation data set is obtained that includes items that correspond to different evaluation tests for a code generation system. The individual items of the evaluation data set maybe converted, including the conversion of a function signature for the items, the test statements for the items and using a code generation system to generate the body of the function.
Owner:AMAZON TECH INC

Anomaly detection method for model outputs

Systems and methods for detecting anomalies in generative outputs are disclosed herein. The system receives a user prompt indicating a request for data over a time period. The system inputs, into a model, the user prompt to cause the model to generate an output based on the user prompt. The system then generates the first tokens based on the output. To generate the second tokens, the system retrieves, based on the user prompt, sources relating to the data requested by the user prompt. The system then generates queries to request, from the sources, the data over the time period and generates the second tokens based on the retrieved data. The system then performs a comparison of the first tokens and the second tokens and accepts or rejects the output of the model based on the comparison.
Owner:CITIBANK N A

Systems and Methods for Simulating Over-The-Air Software Updates for Vehicles

Methods, computing systems, and technology for testing an update controller within a virtual environment are presented. An example computing system accesses data indicative of a rule for distributing the OTA software update. The computing system determines an action to be taken for implementing the OTA software update. The action is based on the rule for distributing the OTA software update and a mocked behavior of an external software service available to the update controller. The mocked behavior simulates a response of the external software service to a request from the update controller within the isolated virtual environment. The computing system accesses data indicating that a vehicle simulator is available for the OTA software update. The computing system generates a task package including the OTA software update and indicating the action to be taken for implementing the OTA software update. The computing system outputs the task package to the vehicle simulator.
Owner:MERCEDES BENZ GROUP AG

Code synthesis model evaluation harnessing real-world code repositories

A computer system identifies a code synthesis model and a set of software repositories, each comprising corresponding source code and corresponding tests for testing the corresponding source code. The computer system tests a plurality of generated source code predictions using the set of software repositories. The testing includes, for each software repository in the set of software repositories, identifying a portion of the corresponding source code of the software repository that is covered by the corresponding tests of the software repository, using the code synthesis model to generate a source code prediction for the portion of the corresponding source code, and using the corresponding tests of the software repository to test the source code prediction that was generated using the code synthesis model. Based on testing the plurality of generated source code predictions using the set of software repositories, the computer system generates an evaluation of the code synthesis model.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Input rewriting method and device of intelligent question answering system and computer equipment

The invention relates to an input rewriting method and device of an intelligent question answering system, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring dialogue data input by a user for the intelligent question-answering system, and judging whether the dialogue data needs to be rewritten or not; generating a plurality of candidate rewriting results by adopting a preset rewriting model, a predefined rewriting template and a preset rewriting rule under the condition of determining that the dialogue data needs to be subjected to type rewriting processing; inputting the plurality of candidate rewriting results into a pre-trained rewriting scoring model to obtain rewriting scores corresponding to the plurality of candidate rewriting results; and according to the rewriting score, determining a target rewriting result from the plurality of candidate rewriting results, and inputting the target rewriting result into the intelligent question and answer system. By adopting the method, the answer generation accuracy of the intelligent question-answering system can be improved.
Owner:CHINA LIFE INSURANCE CO LTD

Micro front-end composition and polymorphism

A system including at least one processor and non-transitory computer-readable storage storing instructions that, when executed by the at least one processor, cause the system to: generate a context configuration module programmed to compose a user experience based on a user context and a registry of micro front-ends; and generate a rendering module programmed to render one or more micro front-ends from the registry of micro front-ends into a framework to deliver the user experience.
Owner:WELLS FARGO BANK NA

Model-based process to validate build integrity of software products

Techniques are described for a model-based process to validate build integrity of software products. A build integrity validation system generates a build artifact model including one or more software components extracted from a build artifact resulting from a software build process of source code and generates a source code including one or more software components extracted from the source code. The system compares the software components of the build artifact model and the software components of the source code model, and identifies at least one discrepancy between the build artifact model and the source code model. The system determines a level of risk associated with the at least one discrepancy and, in response to determining the level of risk associated with the at the least one discrepancy, generates a decision indicating whether the at least one build artifact is approved for use in a software product.
Owner:WELLS FARGO BANK NA

Summarizing computer system alerts using generative machine learning models

Techniques for summarizing a set of alert logs associated with a computer system using a generative machine learning model are described herein. In some cases, an example system receives a set of alert logs, such as logs associated with a detected security incident. The system generates a summarization prompt that includes the set of alert logs, instructions to summarize the logs, and one or more output constraints. The system then provides the summarization prompt to a generative machine learning model M times to determine M summarization outputs. The system determines N of the M summarization prompts that satisfy the output constraint(s) and are thus determined to be valid. The system then determines N scores for the N validated summarization outputs and determines an aggregated summarization output based on a subset of the N summarization outputs as determined based on the corresponding N output scores.
Owner:CISCO TECHNOLOGY INC

Task management interfaces for end-to-end task processing and sub-task generation and modification

Systems and methods are provided for facilitating management of interactions and training for AI (artificial intelligence) agents. Systems generate and display interfaces for training AI agents and for receiving user instructions. The systems parse user instructions to identify tasks to be performed by the AI agents. The systems cause the tasks to be split into subtasks to be performed by the AI agent. The systems also display a dialog frame that presents the user instructions along with AI agent responses that identify the subtasks. The systems also display a graph that visually identifies a processing flow of the subtasks and that dynamically updates the processing flow to reflect a status of progress for the AI agent performing the subtasks.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Interface for generating documents with generative artificial intelligence

A data processing system includes: a processor; and a memory comprising programming instructions for execution by the processor alone or in combination with other processors, to implement a service to generate a work as specified by a user. The service includes: a service-side component of a User Interface (UI) to receive user input about the work from the user, the user input including an initial prospective description of the work that the user intends to generate using the system and a set of parameters for the work; a prompt generator to generate prompts for a Large Language Model (LLM) based on the user input to generate both an outline for the work and a proposed version of the work, the prompt generator further to generate additional prompts to the LLM to update either the outline or the proposed version of the work based a user editing of the other of the outline or the proposed version of the work; and an Application Programming Interface to deliver prompts to the LLM and receive responses from the LLM for presentation in the UI.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Code agent construction system, construction method thereof and code generation method

The invention provides a code agent construction system, a construction method thereof and a code generation method, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as large models. According to the specific implementation scheme, the code agent construction system comprises an intelligent cooperation engine, a layered template library, a semantic understanding and layered retrieval system, a T-RAG generation and optimization system and a closed loop verification system; wherein the layered template library comprises a project-level template, a function-level template and an API-level template; the semantic understanding and hierarchical retrieval system is configured as follows: analyzing user requirements through a natural language understanding module to generate an intention vector, and sequentially executing project-level, function-level and API-level three-level progressive template retrieval; and the T-RAG generation and optimization system is configured to inject the hierarchical retrieval result into the cue word of the large language model to generate deployable codes containing front-end and rear-end logics.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

Compiling verification system generation method, driving program compiling verification method, system, device, equipment, medium and program product

The invention relates to a compilation verification system generation method, a driver compilation verification method, a driver compilation verification system, a driver compilation verification device, a driver compilation verification device, equipment, a medium and a product. The method comprises the following steps: generating each operating system container mirror image based on each target operating system required to be supported by each driver; obtaining a kernel file required for compiling a driving program according to the kernel version used by each target operating system; generating a container compiling environment corresponding to each operating system container mirror image based on each tool chain required for compiling each driving program; determining a written automatic verification program which is used for verifying each drive program by using each kernel version and each tool chain based on each kernel file in a container compiling environment corresponding to each operating system container mirror image; and obtaining a compiling verification system based on the operating system container mirror image, the kernel file, the container compiling environment and the automatic verification program. By adopting the method, the driver can be automatically verified to adapt to different operating systems, kernel versions and compiling tool chain environments.
Owner:GLENFLY TECH CO LTD

Large model parallel training strategy generation method oriented to domestic supercomputing system

According to the domestic supercomputing system-oriented large model parallel training strategy generation method, a parallel training strategy comprises at least one of a parallel training method, a batch size and a video memory optimization method, the parallel training strategy forms a search space, and the method comprises the following steps: acquiring parameters required for generating the parallel training strategy; based on the parameters, a plurality of decision trees are constructed, the decision trees are used for decomposing a search space of the parallel training strategy, and each decision tree is used for representing a sub-search space of the parallel strategy; based on the decision tree and the parameters, the model training method is evaluated through a performance evaluation method, and the calculation performance and the communication performance of the model under different parallel strategies are determined; constructing an integer programming model based on the calculation performance and the communication performance; and determining an optimal solution of the integer programming model, and taking a parallel training strategy corresponding to the optimal solution as a determined parallel training strategy. According to the method, the most convenient and rapid large model parallel training strategy can be generated for the domestic supercomputing system.
Owner:COMP NETWORK INFORMATION CENT CHINESE ACADEMY OF SCI

Computer-Implemented Engagement System Using an LLM Module for Selecting Targets and / or Messages to Targets

A computer-implemented method of generating electronic communication messages to one or more target computer systems that comprises determining user inputs, using a large language model (LLM) module to generate a proposed search for the one or more target computer systems, prompting the LLM to modify the search based on certain criteria or user input, generating and sending proposed messages to the proposed set of targets.
Owner:RECRUITBOT INC

Systems and method for analyzing software and testing integration

An assessment system can generate a software quality value based on testing results and analysis of a multitude of factors that impact a readiness evaluation. For example, the system generates a software quality score (e.g., an Applause Quality Score “AQS”) that enables development teams to understand the level of quality they are achieving for a given release and build-over-build. In various examples, the system generates a data-driven score to enable development teams or quality assurance teams to make decisions for when a build is ready for release. In further embodiments, the system can integrate user interfaces that present a software quality score in a user dashboard that is linked to version control systems. On review and acceptance of the score, a user can trigger the release of their new code or product.
Owner:APPLAUSE APP QUALITY

Systems and methods for error mitigation in a software pipeline

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.
Owner:CAPITAL ONE SERVICES LLC

Assessment of development team factors

ActiveUS12229548B1Development teamEngineering
Techniques described herein include assessing factors that may affect the quality of software under development by a development team or that may be used to evaluate the health of software already deployed in a computing environment. In one example, this disclosure describes a method that includes collecting, by a computing system, historical information about a plurality of prior development projects; correlating, by the computing system, the historical information with each of a plurality of developers that participated in one or more of the plurality of prior development projects; collecting, by the computing system, information about an application developed by a subset of the plurality of developers; generating, by the computing system and based on the information about the application and the correlated historical information, a predicted outcome for the application; and taking an action, by the computing system and based on the predicted outcome, to prevent the predicted outcome.
Owner:WELLS FARGO BANK NA

Deploying machine learning models with automated resource management

In the implementation of techniques for deploying machine learning models with automated resource management, a system receives logic corresponding to a machine learning model and computing resource data corresponding to a plurality of computing resources available. Based on the logic and the computing resource data, the system generates the machine learning model and an allocation of one or more computing resources of the plurality of computing resources available for the machine learning model, in which the machine learning model conforms to the logic. Upon generation of the machine learning model and the allocation of the one or more computing resources, the system deploys the machine learning model and the allocation of the one or more computing resources of the plurality of computing resources available for the machine learning model.
Owner:EBAY INC

Systems and methods for training and securing a large language model with encrypted layers

A system generates an MLM comprising a plurality of layers. The system assigns a first encryption scheme for a first subset of layers in the plurality of layers. During a training phase of the MLM, the system determines whether a first input training vector comprises private data, in response to determining that the first input training vector does not comprise the private data, the system train the MLM such that, during backpropagation, an optimization algorithm is used to update any necessary weights in the plurality of layers; and in response to determining that the first input training vector comprises the private data, the system trains the MLM such that during the backpropagation, the optimization algorithm is used to update weights solely in the first subset of layers. The system executes the trained MLM on a user input vector to generate a user output value.
Owner:SIT AUTONOMOUS AG

Systems and methods for simulating over-the-air software updates for vehicles

Methods, computing systems, and technology for testing an update controller within a virtual environment are presented. An example computing system accesses data indicative of a rule for distributing the OTA software update. The computing system determines an action to be taken for implementing the OTA software update. The action is based on the rule for distributing the OTA software update and a mocked behavior of an external software service available to the update controller. The mocked behavior simulates a response of the external software service to a request from the update controller within the isolated virtual environment. The computing system accesses data indicating that a vehicle simulator is available for the OTA software update. The computing system generates a task package including the OTA software update and indicating the action to be taken for implementing the OTA software update. The computing system outputs the task package to the vehicle simulator.
Owner:MERCEDES BENZ GROUP AG

Automating efficient deployment of artificial intelligence model

To provide facilitating a process for automatically deploying artificial intelligence (AI) models.SOLUTION: A system receives, for a first artificial intelligence (AI) model used by an entity, a first request to deploy a first AI model to make the first AI model available for use in a production environment to process input data and generate corresponding outputs. A first model deployment location for a first model is selected based on a model deployment engine. The system generates scripts to deploy the first AI model to the selected location, then monitors operations parameters associated with the deployment of the first AI model. Based on the values of the operations parameters, the system updates the model deployment engine. In response to a second request to deploy a second AI model, the system uses the updated model deployment engine to select a second model deployment location for a second model.SELECTED DRAWING: Figure 1
Owner:CITIBANK N A

Generating Software Code Using Large Language Models

Techniques for generating proprietary software code using large language models (LLMs) are disclosed. An LLM is trained on billions of words, tokens, and code segments to generate non-proprietary software code. A system uses the LLM to generate proprietary software code by generating a set of LLM prompts and a proprietary code mapping. Based on receiving an instruction to generate a set of software code, a system generates a set of LLM prompts. The system prompts the LLM to generate a set of non-proprietary software code. The system further prompts the LLM to generate a set of pseudocode from the non-proprietary software code. The system further prompts the LLM to generate proprietary software code from the pseudocode and the proprietary code mapping.
Owner:ORACLE INT CORP

Customized user interface experience for first notice of loss

A computing system can determine a subset of users that have been affected by an event occurring in a given area. Subsequent to the event, and for each respective user of the subset of users, the system generates interactive follow-up content specifically tailored for the respective user. The system can transmit updated content data to the computing device of the respective user, causing the computing device of the respective user to present the interactive follow-up content. Based on user interaction by the respective user with the interactive follow-up content, the system can receive contextual information provided by the respective user, the contextual information corresponding to damage or loss resulting from the event as indicated by the respective user.
Owner:ASSURED INSURANCE TECH INC

Systems and Methods for Actionable Data Analysis and Storytelling with Large Language Models (LLMs)

A computer system generates and displays a first cell with a first visual characteristic. The computer system receives, via the first cell, a request associated with a task directed to a dataset. The computer system generates a set of system prompts and inputs the prompts into a data processing system to process the request. The data processing system includes one or more data processing models and is configured to operate in a single agent mode of operation and a multi-agent mode of operation. The computer system obtains, as output from the data processing system, a response to the request. The computer system generates, in real time, output data associated with the response and displays the output data in one or more second cells in the user interface, where each of the second cells has a second visual characteristic that is different from the first visual characteristic.
Owner:SALESFORCE INC

Systems and methods for emulating an environment created by the outputs of a plurality of devices

Systems and methods are disclosed for emulating an environment created by the outputs of a plurality of devices. The system receives device control data for a device in a first venue. The control of the outputs of said devices according to the device control data creates an environment within the first venue. The system retrieves profile data for devices within a second venue. The system associates a device in the second venue with a device from the first venue, both devices having a similar output type. The system then generates control information adapted from the associated device of the first venue for the device in the second venue. The system controls the outputs of each device in the second plurality of devices according to the generated control information to emulate the environment within the first venue in the second venue.
Owner:ADEIA GUIDES INC