5006 results about "Application procedure" patented technology

An example operation may include one or more of receiving a loan application of a user, extracting a plurality of personal attributes about the user from the loan application, querying a machine learning model via an application programming interface (API) based on the plurality of attributes about the user to identify one or more rules for auto-adjudicating the loan application, determining whether or not to approve the loan application based on the one or more rules identified via the machine learning model, and transmitting notice of the determination to a device associated with the user.

An example operation may include one or more of executing a waiting period of time within a software application being accessed by a user, executing an animation via the software application during the waiting period, determining a result of the software application being accessed by the user, determining additional time to add to the waiting period of time based on the result, via the software application, executing the waiting period with the additional time, augmenting the animation based on the additional time to add to the waiting period, via the software application, and executing the augmented animation via the software application during the additional time. At least one portion of the example operation: integrates with an artificial intelligence (AI) chatbot, interacts with the AI chatbot, is performed by the AI chatbot, and / or is associated with an AI model.

Systems and methods for large language model (LLM)-agnostic data anonymization. Data anonymization includes data obfuscation (and data deobfuscation) to protect confidential information a user is going to send to an LLM service or application programming interface (API). Encryption can be used for data obfuscation and particularly, for securing data from unauthorized access. Likewise, decryption can be used for data de-obfuscation.

A computer-implemented method for intelligent query response in an enterprise resource planning (ERP) system is disclosed. The method can receive, from a user interface of the ERP system, a natural language user query for processing data of a target object and invoke a function call through an application programming interface of the ERP system based on the user query. Invoking the function call includes extract denormalized data from one or more database tables, generating a prompt using a prompt template and the denormalized data, prompting a large language model using the prompt, and receiving a response generated by the large language model. The method can generate an output on the user interface based on the response generated by the large language model. Related systems and software for implementing the method are also disclosed.

Various embodiments of the technology described herein cause an LLM to intelligently process data based on a user query and a schema determined for a data set. Certain embodiments programmatically leverage an LLM and utilize its output based on a user query. In this manner, data is processed without the LLM having to access an entire data set, and instead only utilizes information associated with the user query and the schema. The schema comprises a textual description, such as a string of alphanumeric characters, that describes the data, data types, and / or data structure of the data set. Embodiments of the technology described herein are performed by an LLM interface layer separate from a user device layer and an LLM layer. The LLM interface layer is positioned between an LLM abstraction layer and an application layer by which a user can interface with the LLM interface layer.

The invention provides a cross-environment AI task collaborative execution method and device based on an MCP protocol and a storage medium, a plurality of different application programs deployed on a local system are packaged into uniform interface APIs, each application program corresponds to one uniform interface API, and the packaged uniform interface APIs support context awareness operation; the method comprises the following steps: constructing an MCP protocol at a cloud end, and obtaining a current state of each application program executing a task through a uniform interface API based on the MCP protocol, so that data among different application programs are kept consistent; an operation request input by a user is received at a cloud end, the operation request of the user is converted into an operation command of at least one application program based on an MCP protocol, the operation command is transmitted to a corresponding application program deployed on a local system through a uniform interface API, and the application program executes corresponding operation based on the operation command. According to the invention, a two-way operation path between the cloud AI and the local non-API software is established, and the success rate of cross-environment tasks is improved.

The invention discloses a system (100) for generating conversational content using a generative artificial intelligence (AI), said system (100) comprising: a user (101), an administrator (102), an application programming interface (API) server (103), a generative artificial intelligence (AI) server (104), a plurality of databases (105), a generative artificial intelligence (AI) processor (106), an audio generate processor (107), a text-to-speech processor / service provider (108), a video generation service (109), a video generation processor (110), and a memory communicatively coupled to the processor, wherein the memory stores processors instructions, which, on execution, causes the processor to generate at least one of conversational script, audio, video, or combination thereof. The system (100) allows users to create and customize various aspects of conversational content, including characters / personas / speakers, groups (of personas / characters / speakers), tones, content types, topics, conversation formats, and tone.

An application mapping engine may determine dependencies in existing executable application by monitoring and analyzing process flow and data flow of the application during runtime execution. The application mapping engine may generate dependency visualization maps that illustrate dependency interaction information.

Techniques are disclosed relating to a multi-agent search client. In an example method, a search agent application receives a query. The search agent application determines, using a search agent, one or more agents to each execute a portion of the query. The search agent application outputs, to a domain agent, a portion of the query. The search agent application determines, using the domain agent, an execution step based on the portion of the query and information about an executor. The executor generates instructions based on the execution step that are configured to generate a response to the execution step and outputs a command to execute the instructions. The executor then outputs, to the first domain agent, the response to the execution step. The search agent application outputs, using the search agent, a response to the query based on the response to the execution step.

Apparatuses, systems, and techniques to perform an application programming interface (API) to cause dependency type information of one or more user-indicated graph nodes of a software graph to be indicated. In at least one embodiment, one or more dependency types from a graph are indicated.

Embodiments of the present invention provide computer-implemented methods, computer program product, and computer systems. One or more processors analyze user prompts using one or more natural language understanding techniques. One or more processors then enrich the user prompts by integrating contextual data from user interaction history and adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.

Apparatuses, systems, and techniques to determine a matrix multiplication algorithm for a matrix multiplication operation. In at least one embodiment, a matrix multiplication operation is analyzed to determine an appropriate matrix multiplication algorithm to perform the matrix multiplication algorithm.

A user of an identity management system may configure a software agent with a set of parameters within one or more user interfaces of an agent management service. The set of parameters may include an identifier of an application programming interface (API) endpoint of a first service that the software agent is authorized to query and one or more permissions associated with queries to the API endpoint by the software agent. Further, the user may receive an authentication token for the software agent from the agent management service. The software agent may use the authentication token for accessing resources of the service via the API endpoint in accordance with the one or more permissions. Thus, the user may configure the first software agent with the authentication token to enable the software agent to perform the queries to the API endpoint of the first service.

A system and method for automatically generating a change history of source code using a generative artificial intelligence (“AI”) system. In examples, a generative AI system receives a request inquiring about one or more changes made to software code of a software service or application. In response to receiving the request, the generative AI system navigates one or more information sources to collect code change context relevant to history of the code change(s). The generative AI system generates an instruction corresponding to the received request, where the instruction and the code change context are provided as input to a language model (LM) (e.g., a generative AI model). Based on the inquiry of the request, the LM processes the input, generates, and provides a corresponding output. The generative AI system then uses the output to generates and provide an explanation about the code change(s) to a requestor of the request.

Example implementations include a method, apparatus, and computer-readable medium configured for implementing a workflow using a large language model (LLM). A workflow automation application sends a first prompt to a large language model (LLM) to transform a first input data source in a first format to a second format. The workflow automation application sends a second prompt to the LLM to define multiple steps of a workflow starting on the data source in the second format. The workflow automation application sends a third prompt to the LLM to define execution of business logic for each step of the workflow. The workflow automation application receives, from the LLM, output data indicating that each step of the workflow has been executed.

Orchestration solutions for agentic automation for artificial intelligence (AI) agents, robotic process automation (RPA) robots, agentic orchestration processes (AOPs), and humans-in-the-loop with self-healing and capabilities to increase autonomy. Agentic orchestration, via a conductor application, enables the automation, modeling, and monitoring of complex business processes from start to finish. A user or an initiating software process requests that a given AOP be run. The AOP defines a business process (e.g., in Business Process Model and Notation (BPMN)), and may utilize one or more RPA robots, one or more AI agents, and / or one or more humans to assist with accomplishing this process, such as resolving invoice discrepancies, onboarding an employee, performing compliance checks, synchronizing order data among multiple backend systems, etc.

In various examples, systems and techniques are provided that encapsulate indexing and query operations into an application programming interface (API) that automates and coordinates calls to various local and cloud-based services. When a user has a document(s) to add to a retrieval augmented generation (RAG) database, the API may offer to the user multiple document processing pipelines (DPPs) having pre-set indexing configurations. Similarly, when a user query is received, the API may generate calls to implement query processing that does not require the user to manually configure retrieval and processing of the embeddings. The API may further implement calls that locate a relevant embedding store and provide the stored embeddings, together with the query embeddings, to a search engine that identifies the most relevant matches. The API may then access the embedding-to-text indexing and identify relevant text segments and documents to a prompt generator.

The invention discloses a tool calling method based on a large language model, and the method comprises the steps: obtaining a question text which comprises task information; obtaining a matched first candidate tool set in the question text and a preset tool library; screening the first candidate tool set on the basis of locally available current hardware resources and / or available current online resources of a cloud application program interface (API) to obtain a second candidate tool set; determining a target tool matched with the task information from a second candidate tool set based on a large language model, and generating a tool calling instruction based on the target tool; selecting a called target tool based on the tool calling instruction, and obtaining an output result of the target tool; based on the question text and the output result, reply text corresponding to the large language model is obtained. According to the method, the tool with a higher matching degree can be obtained in combination with the resource occupation conditions of the tools of multiple platforms, and efficient utilization of resources and dynamic scheduling of task tools are realized.

Methods, systems, and computer-readable storage media for a software debugging system that leverages a LLM in combination with an entity matching model to propose solutions for mitigating errors. In some examples, the LLM is used to generate embeddings that are used to identify two or more matched historical errors. The matched historical errors are potential matches to a current error that needs to be resolved. The entity matching model is used to determine a matched historical error from the two or more matched historical errors. The LLM is also used to generate a proposed solution to the current error based on a historical solution to the matched historical error. The proposed solution can be executed to resolve the current error.

Latency, response times, and efficiency improvements for data querying are provided herein, particularly in the context of querying large database systems and data tables from disparate data sources. There are provided systems and methods for automatic query and data retrieval optimization through procedural generation of data tables from query patterns. A service provider may utilize different computing services for query processing and data retrieval for different applications and services used by internal and / or external users. Instead of querying large database systems and numerous data tables, pre-aggregated data tables may instead be used and searched by procedurally generating such tables based on precomputation rules and query patterns. Once patterns have been identified in queries, corresponding data may be aggregated from data sources in a pre-aggregated data table. Query optimization rules may then be used to have these data tables queried in place of their original sources.

A system for completing tasks using the web is disclosed. The system is programmed to receive a user query for completing a task in natural language. The system is programmed to generate from the user query a first plan having a first sequence of website action steps using a large language model. Each website action step specifies a website and includes a request for performing an action on a website in natural language or network or software protocol language. To execute a website action step, the system is programmed to generate from a corresponding request a current plan having a current sequence of function action steps using a large language model. Each function action step specifies a function in the website's application programming interface and includes values for parameters of the function. To execute a function action step, the system is programmed to call the function with the parameter value.

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.

The invention discloses a resume analysis method and system based on multiple large language models, and belongs to the technical field of large language models.The resume analysis method and system based on the multiple large language models.The resume analysis method and system based on the multiple large language models comprise the following specific steps that firstly, model parallel analysis is conducted, simultaneously inputting the data into at least two heterogeneous large language models through an application program interface; and each large language model independently performs information extraction and analysis according to the model structure and the training data of the large language model, and outputs a structured data result containing a plurality of preset fields. Through the multi-model parallel analysis and conflict re-judgment mechanism, the misjudgment risk of a single model is effectively reduced, the robustness of the whole system is improved, the resume analysis accuracy is remarkably improved, the model pool is automatically optimized and updated through the dynamic scoring mechanism, and the problem that the model is difficult to select and update is solved.

Various aspects of the disclosure relate to automated testing for application programming interfaces (APIs). A dynamic API validation computing system leverages a generative AI model to dynamically generate a multitude of data sets and rules for use during API validation activities. A federated byzantine agreement mechanism performs the validation of each API using the generated test cases and test data. A generator engine incorporates a generative AI model that may be trained on a large corpus of API metadata and / or data characteristics to predict data patterns and / or validation rules for each of the APIs under test. The generator engine may also predict a structure and format of requests based on the training model inputs. Multiple Test cases for an API created through use of the generative AI model may be distributed and executed on different testing nodes that reach a consensus about whether each API has passed or failed.

Embodiments generate state elements based on application requests from a client. The state elements may be enqueued in a state queue associated with an application session for an application requests and the application requests may be forwarded to the application. Application responses from the application may be employed to perform further actions, including: generating message elements based on the application responses such that the message elements may be enqueued in a message queue associated in the application session; determining a portion of the state elements in the state queue that may be associated the message elements; updating the portion of the state elements to advance a protocol state based on the message elements such that the application responses may be communicated to the client.

A natural language test case for an application is automatically converted into a test script by a test script generator. During the generation of the test script, the test script generator may access a blueprint of the application. The blueprint may include a time-evolving model of the application, which may include a set of translations and a state machine model of the application. The state machine model may include a state space and a set of state transitions. During the test script generation process, the blueprint may be continually updated to include new knowledge of the application. The test script generator may communicate with an artificial intelligence (AI) engine in order to determine the semantic similarity between two phrases, convert images into textual description, and perform tasks requiring the use of a large language model (LLM).

Various approaches for Multi-access Edge Computing (MEC) Dual Edge App Registration, including registration performed on behalf of edge computing platforms operating as dual deployments in a MEC and 3GPP infrastructure, are discussed. An example first computing platform may be communicatively coupled, via a network, to a second computing platform, and perform operations that: receive a dual application registration request from an application of the first computing platform; map a first application profile of the application at the first computing platform to a second application profile at the second computing platform; redirect the dual application registration request to the second computing platform; receive, in response to the redirect of the dual application registration request, an application registration acknowledgment; and provide, to the application, the application registration acknowledgment.

The invention relates to a large model agent configuration leakage vulnerability detection method and device, and the method comprises the steps: carrying out the tool pre-configuration according to the characteristic information of an online agent store, so as to generate tool pre-configuration information; respectively generating corresponding initial attack seeds for the cue word, the application programming interface and the knowledge base file leakage vulnerability; applying at least one variation strategy to the initial attack seed to bypass external and internal defense strategies of the intelligent agent, and determining a cue word after variation; interacting with the target web page by utilizing a preset automation framework to obtain the output of the intelligent agent; and detecting whether the output of the intelligent agent leaks the corresponding configuration or not by using the preset fine-tuned large model to obtain a detection result of the leakage vulnerability of the intelligent agent configuration of the large model. Therefore, the problems that existing work lacks an automatic detection mechanism for an online agent store, and lacks research and detection on leakage vulnerabilities of cue words, APIs and knowledge base files are solved.

Techniques for using machine learning (ML) model(s) to generate a textual summary of a stream of events at least in part by receiving information corresponding to the stream of events corresponding to interactions between a user and application program(s) executing on a computing device, the information comprising, for each of multiple events in the stream of events associated with a process, metadata associated with the event, wherein metadata for a particular event specifies values for attributes of the particular event; processing, using at least one ML model, the metadata associated with the multiple events to generate multiple corresponding textual summaries of the multiple events; generating, using the textual summaries of the multiple events, a textual summary of the process performed by the user through the interactions between the user and the application program(s) executing on the computing device; and outputting the textual summary of the process.