Back to results
US 11,106,840 B2Granted
Models for utilizing siloed data
AssigneeClover Health
InventorsIan Blumenfeld, Brian Johnson, Brian Lucena
Life of this patent
Estimating the term…
Abstract
Systems and methods for models utilizing siloed data are disclosed. For example, data stored with and/or available to one or more systems may be siloed such that it may not be aggregated and/or shared with other systems. The presently-disclosed systems and methods generate and utilize predictive layers and models to allow each system to predict outcomes using its own data and then models are shared between systems to allow each associated system to gain the benefits of the data of other systems without aggregating such data or otherwise sharing the data.
Claims20
A system comprising:
- one or more processors;
- and
- non-transitory computer-readable media storing first computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- receiving, from a first remote system located in a first country, a first request for a first base model configured to determine a health-related outcome using first data available to the first remote system;
- identifying a first data type of the first data common to the first remote system and the system;
- generating the first predictive base model configured to utilize the first data based on identifying the first data type, the first predictive base model including pseudo-code configured for use by the first remote system to generate other predictive base models;
- sending the first predictive base model to the first remote system;
- receiving, from a second remote system located in a second country, a second request for a second predictive base model configured to determine the health-related outcome using second data available to the second remote system;
- identifying a second data type of the second data common to the second remote system and the system;
- generating the second predictive base model configured to utilize the second data based on identifying the second data type, the second predictive base model including pseudo-code configured for use by the second remote system to generate other predictive base models;
- sending the second predictive base model to the second remote system;
- receiving, from the first remote system, a third predictive base model configured to determine the health-related outcome utilizing third data of the first data type, the third predictive base model configured to generate a first feature;
- receiving, from the second remote system, a fourth predictive base model configured to determine the health-related outcome utilizing fourth data of the second data type, the fourth predictive base model configured to generate a second feature;
- and
- determining, using a predictive layer, the health-related outcome based on the first data, the second data, the third data, the fourth data, the first feature, and the second feature.
12 more elements
A method, comprising:
- receiving, at a first system, a first request for a first predictive base model configured to determine an outcome, the first request indicating first data available to a second system;
- determining that the first data is of a first data type;
- generating the first predictive base model configured to utilize the first data based on determining that the first data is of the first data type, the first predictive base model including pseudo-code configured for use by the first remote system to generate other predictive base models;
- sending the first predictive base model to the second system;
- receiving, at the first system, a second request for a predictive second base model configured to determine the outcome, the second request indicating second data available to a third system;
- determining that the second data is of a second data type;
- generating the second predictive base model configured to utilize the second data based on determining that the second data is of the second data type, the second predictive base model including pseudo-code configured for use by the third remote system to generate other predictive base models;
- and
- sending the second predictive base model to the third system.
6 more elements
A system, comprising:
- one or more processors;
- and
- non-transitory computer-readable media storing first computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- receiving, from a first system, a first predictive base model configured to determine an outcome utilizing first data of a first data type common to the first system and the system, the first predictive base model corresponding to a first feature, the first predictive base model including pseudo-code configured to generate other predictive base models;
- receiving, from a second system, a second predictive base model configured to determine the outcome utilizing second data of a second data type common to the second system and the system, the second predictive base model corresponding to a second feature, the second predictive base model including pseudo-code configured to generate other predictive base models;
- and
- determining, using a predictive layer, the outcome based on the first data, the second data, the first feature, and the second feature.
4 more elements
Dependencies are inferred from the claim text.