Optum, Inc.

Unitedhealth Group Incorporated

Ayush Tomar

Vinit Garg

Laura D Hamilton

Ramin Anushiravani

Lun Yu

Fazle Shahnawaz Muhibul Karim

Adam Russell

Somadev Pasala

Ravi Kondadadi

Hadi D Halim

Yizhao Ni

Zengpan Fan

Ketki Savle

Preet Kamal S Bawa

Donald E Johnson, Jr

Rupesh Kartha

Robert K Rossmiller

Martin R Linenweber

Chenwei Liu

David Armbrust

Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing personalized autocomplete predictions. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform personalized autocomplete predictions using a general search corpus and/or individual curated search corpus.

Machine learning techniques for generating personalized autocomplete prediction

Various embodiments of the present disclosure provide automated data compliance techniques for complex access controlled datasets subject to a plurality of data access constraints. Some of the techniques may include generating, using one or more natural language models, entity-relationship data for an access controlled dataset and generating a knowledge graph based on the entity-relationship data. The knowledge graph includes a plurality of vertices connected by a plurality of edges that may be traversed to identify a data access condition indicative of a data access violation or a data coverage violation. Some of the techniques may include generating, using the knowledge graph, a natural language condition description based on the data access condition and providing a condition alert indicative of the natural language condition description.

Graph-based data compliance using natural language text

Various embodiments of the present disclosure provide query processing techniques for generating optimized query results. The techniques include generating using a machine learning framework, one or more predictions for a natural language query. The one or more predictions may include an intent prediction and an event prediction. The technique may include generating an intent classification for the natural language query based on the intent prediction and the event prediction. The techniques may include in response to the intent classification corresponding to a target query intent: generating, a plurality of candidate data objects based on an identifier associated with the natural language query, identifying one or more relevant data objects from the plurality of candidate data objects based on a relevancy score for each of the plurality of candidate data object; and providing, via a user interface, a natural language query result.

Methods, apparatuses and computer program products for intent-driven query processing

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.

Search analysis and retrieval via machine learning embeddings

Systems and methods for improved spelling checking are disclosed. A method includes receiving a search query from a user device and determining that the search query does not exist in a data store that stores (a) a corpus of correctly spelled words or (b) forced correction mapping data. The method further includes, in response to the determining, determining a plurality of suggested search queries generated by a plurality of respective spell corrector models, selecting a suggested search query determined using a spell corrector model from the plurality of spell corrector models based on at least one of a frequency of the suggested search query in historical search data or a weightage associated with the spell corrector model, and causing the suggested search query to be displayed on the user device.

Systems and methods for improved spell check

Various embodiments of the present disclosure provide computer interpretation techniques for implementing a query resolution process to improve upon traditional search resolutions within a search domain. The techniques may include generating a plurality of interaction embeddings for a plurality of textual descriptions corresponding to a plurality of interaction codes identified within an interaction dataset and a plurality of taxonomy embeddings for a plurality of taxonomy categories identified within a taxonomy dataset. The techniques may include generating similarity scores for a plurality of description-category pairs based on a comparison between the plurality of interaction embeddings and the plurality of taxonomy embeddings. The techniques may include generating an enhanced taxonomy by augmenting one or more of the plurality of taxonomy categories with one or more of the plurality of textual descriptions based on the similarity scores and initiating, using the enhanced taxonomy, the performance of a query resolution operation.

Text embedding-based search taxonomy generation and intelligent refinement

Growing community of inventors

Morgan Hill, CA, United States of America

Ayush Tomar