公开(公告)号：US20250036674A1

公开(公告)日：2025-01-30

申请号：US18458739

申请日：2023-08-30

Applicant: Cisco Technology, Inc.

Inventor： M. David Hanes ,  Vivek Kumar Singh ,  Gonzalo A. Salgueiro ,  Derek William Engi

IPC: G06F16/335 ,  G06F16/332

Abstract: A method comprises: receiving a query on a topic from a user associated with user attributes indicative of a user comprehension level on the topic; providing the query to an AI model; receiving from the AI model a response to the query that has a response comprehension level on the topic that is less than the user comprehension level; iteratively adding, to the query, topically-relevant user attributes of the user attributes to produce iterative queries that increase in technical detail on the topic; providing the iterative queries to the AI model; responsive to providing the iterative queries, receiving, from the AI model, iterative responses that increase in technical detail on the topic and have response comprehension levels that increase on the topic; and determining, among the iterative responses, a final response having a response comprehension level that most nearly matches the user comprehension level.

公开(公告)号：US20240388571A1

公开(公告)日：2024-11-21

申请号：US18359060

申请日：2023-07-26

Applicant: Cisco Technology, Inc.

Inventor： M. David Hanes ,  Vivek Kumar Singh ,  Gonzalo Salgueiro ,  Derek William Engi

IPC: H04L9/40 ,  G06F21/62

Abstract: A system and method for an artificial intelligence (AI) confidentiality proxy that can protect a network from the transferal of sensitive AI data sets to outside AI systems. A data contract is established between the proxy and outside AI systems could function as well as user personas for additional protection. This system can also integrate with the network and provide security policy content and inspection rules.