Artificial intelligence recommendation system
AssigneeOptum Services (Ireland) Limited
InventorsDarragh Hanley, Damian Kelly, Julie Zhu, Jonathan Lawrence Herke, Gregory J. Boss
Life of this patent
Estimating the term…
Abstract
Various embodiments of the present disclosure facilitate recommendation prediction using machine learning. In one example, an embodiment provides for generating embeddings data related to one or more provider entities, predicting a set of provider entities for a patient entity based on a provider machine learning model, ranking provider entities in the set of provider entities to generate a ranked set of provider entities, and performing one or more actions to provide a recommendation for the patient entity based on the ranked set of provider entities.
Claims20
A computer-implemented method for facilitating recommendation predictions using machine learning, the computer-implemented method comprising:
- generating embeddings data that encodes semantic relations among latent features for provider entities, wherein the embeddings data comprises at least a first embedding vector that provides a first vector representation for a first provider entity and a second embedding vector that provides a second vector representation for a second provider entity;
- generating, using a provider machine learning model that comprises a machine learning network layer communicatively coupled to a first machine learning network cell and a second machine learning network cell, a prediction of a set of provider entities for a patient entity based at least in part on (a) a first vector associated with the first provider entity and generated by the first machine learning network cell using a first concatenation of user data for the patient entity and the first embedding vector and (b) a second vector associated with the second provider entity and generated by the second machine learning network cell using a second concatenation of the user data and the second embedding vector, wherein the set of provider entities comprises the first provider entity and the second provider entity;
- ranking each provider entity in the set of provider entities to generate a ranked set of provider entities;
- and
- initiating the performance of one or more actions to provide a recommendation for the patient entity based at least in part on the ranked set of provider entities.
An apparatus for facilitating recommendation predictions using machine learning, the apparatus comprising a processor and a memory including a computer program code, the memory and the computer program code configured to, with the processor, cause the apparatus to:
- generate embeddings data that encodes semantic relations among latent features for provider entities, wherein the embeddings data comprises at least a first embedding vector that provides a first vector representation for a first provider entity and a second embedding vector that provides a second vector representation for a second provider entity;
- generate, using a provider machine learning model that comprises a machine learning network layer communicatively coupled to a first machine learning network cell and a second machine learning network cell, a prediction of a set of provider entities for a patient entity based at least in part on (a) a first vector associated with the first provider entity and generated by the first machine learning network cell using a first concatenation of user data for the patient entity and the first embedding vector and (b) a second vector associated with the second provider entity and generated by the second machine learning network cell using a second concatenation of the user data and the second embedding vector, wherein the set of provider entities comprises the first provider entity and the second provider entity;
- rank each provider entity in the set of provider entities to generate a ranked set of provider entities;
- and
- initiate the performance of one or more actions to provide a recommendation for the patient entity based at least in part on the ranked set of provider entities.
A non-transitory computer storage medium comprising instructions for facilitating recommendation predictions using machine learning, the instructions being configured to cause one or more processors to at least perform operations configured to:
- generate embeddings data that encodes semantic relations among latent features for provider entities, wherein the embeddings data comprises at least a first embedding vector that provides a first vector representation for a first provider entity and a second embedding vector that provides a second vector representation for a second provider entity;
- generate, using a provider machine learning model that comprises a machine learning network layer communicatively coupled to a first machine learning network cell and a second machine learning network cell, a prediction of a set of provider entities for a patient entity based at least in part on (a) a first vector associated with the first provider entity and generated by the first machine learning network cell using a first concatenation of user data for the patient entity and the first embedding vector and (b) a second vector associated with the second provider entity and generated by the second machine learning network cell using a second concatenation of the user data and the second embedding vector, wherein the set of provider entities comprises the first provider entity and the second provider entity;
- rank each provider entity in the set of provider entities to generate a ranked set of provider entities;
- and
- initiate the performance of one or more actions to provide a recommendation for the patient entity based at least in part on the ranked set of provider entities.
Dependencies are inferred from the claim text.