Search analysis and retrieval via machine learning embeddings

US12169512B2 · kind B2 · utility

Assignee

• UnitedHealth Group Incorporated · US

Inventors

• Laura D. Hamilton · Chicago, US
• Vinit Garg · Fremont, US
• Ayush Tomar · معلمی نژاد, US
• Martin R. Linenweber · San Francisco, US
• Preet Kamal BAWA · Vernon Hills, US
• David Armbrust · Glen Ellyn, US
• Rupesh Kartha · San Ramon, US
• Lun Yu · San Francisco, US

Key dates

• Filing date: Oct 21, 2022
• Grant date: Dec 17, 2024
• Expiry date: Oct 21, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N5/01
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for retrieving relevant items for user queries by generating, using a search engine machine learning model, a prediction-based action for the query input wherein query input embeddings of the query input are generated. For each query input embedding, a k-Nearest-Neighbor (KNN) search is performed with respect to search engine repository item embeddings to generate initial search results, and for each initial set result, performing N hops within a semantic graph starting from nodes associated with the initial search result to generate related search results. The search engine machine learning model is trained by generating a search engine repository item embeddings according to embedding techniques for respective content categories and generating the semantic graph based at least in part on a measure of similarity for pairs of search engine repository item embeddings.