Austin Grelle: Patents
Austin's focuses
TOOLS FOR LARGE LANGUAGE MODEL AGENTS (US20250322374A1)
Abstract: An example computer system for providing one or more tools for large language model agents can include: one or more processors; and non-transitory computer-readable storage media encoding instructions which, when executed by the one or more processors, causes the computer system to: authenticate a user; provide a description of the one or more tools available for use by the large language model agents; execute the one or more tools upon receipt of a request from the large language model agents; and provide information in response to the request.
DOCUMENT SET INTERROGATION TOOL (US12450292B2)
Abstract: Disclosed herein is a workflow for a chatbot system based on an ad hoc set of documents. The chatbot enables users to ask questions of these documents. The workflow then searches for relevant information and generates a response. The response may include an answer to a question and a relevant section of a document.
CLARIFYING POLICY CONTEXTUAL EXTRACTIVE CHATBOT (US20250265280A1)
Abstract: A chatbot system described herein uses a two-staged approach to answer a question. The first stage consists of a contextual search that takes in the question, searches a library of documents and finds a relevant piece of text. The second stage is to use the relevant piece of text, present it to a large language model, and have the model answer the question give the context of the text. The model in question formulates the answer by extracting the most relevant section of the text. When asked an ill-posed question, the chat bot will ask the user clarifying questions until a well-defined question is found.
SYSTEMS AND METHODS FOR RATIONALIZING POLICIES USING ARTIFICIAL INTELLIGENCE (US20250307536A1)
Abstract: Various examples are directed to systems and methods for rationalizing policies using artificial intelligence. A method includes receiving policy data of a plurality of policies from one or more data sources, and comparing policy data of a first policy of the plurality of policies to policy data of one or more second policies of the plurality of policies. Using artificial intelligence, the compared policy data is analyzed to determine overlaps and gaps in the first irst policy and the one or more second policies, and the first policy and the one or more second policies are optimized to reduce the overlaps and gaps in the first policy and the one or more second policies. The optimized first policy and the optimized one or more second policies are stored in a storage library, and an interactive interface to the storage library is provided for one or more users of the system.
SYSTEM AND METHOD FOR LARGE LANGUAGE MODEL (LLM) POLICY ALERTING AND ADVISING (US20250315764A1)
Abstract: Systems and methods are provided. In one example, a method includes monitoring data stores storing policy records for changes to the policy records, and retrieving, from the data stores, the changes to the policy records. The method further includes determining, via a large language model (LLM) using the changes to the policy records, a list of one or more entities in an organization affected by the changes to the policy records, and deriving, via the LLM, an impact metric for each of the one or more affected entities. The method additionally includes identifying, via the LLM using a customizable threshold, for each of the one or more affected entities, that their impact metric exceeds the customizable threshold. The method also includes generating, via the LLM, an impact assessment report of detailing a predicted effect of the changes to the policy records, and transmitting the impact assessment report.
METHOD AND DEVICE FOR PROVIDING CONSUMER SENTIMENT ANALYSIS (US20240330942A1)
Abstract: Systems and methods may generally be used for detecting presence of a customer at a geographic location associated with an institution. Sentiment of the customer can be determined prior to interaction of the customer with the institution based on analysis of a characteristic of the customer. A recommendation can be generated for interacting with the customer based on the sentiment.
