Systems and methods for generating dynamic interface options using machine learning models
AssigneeCapital One Services, LLC
InventorsMinh LE, Arturo HERNANDEZ ZELEDON, Rui ZHANG
Life of this patent
Estimating the term…
Abstract
Methods and systems are described for generating dynamic interface options using machine learning models. The dynamic interface options may be generated in real time and reflect the likely goals and/or intents of a user. The machine learning model may provide these features by interpreting multi-modal feature inputs. For example, the machine learning model may include a first machine learning model, wherein the first machine learning model comprises a convolutional neural network, and a second machine learning model, wherein the second machine learning model performs a Weight of Evidence (WOE) analysis.
Claims20
A system for generating dynamic interface options using machine learning models featuring multi-modal feature inputs, the system comprising:
- storage circuitry configured to store:
- a first machine learning model, wherein the first machine learning model comprises a convolutional neural network;
- and
- a second machine learning model, wherein the second machine learning model performs a Weight of Evidence (WOE) analysis;
- and
- control circuitry configured to:
- receive a first user action, from a first user, during a device interface session with a user interface;
- determine a first user interface image corresponding to the first user action in the user interface;
- determine metadata related to the first user interface image;
- retrieve time-dependent user account information for the first user during the device interface session with the user interface;
- generate a first feature input based on the metadata;
- generate a second feature input based on the time-dependent user account information;
- and
- input the first feature input into the first machine learning model;
- input the second feature input into the second machine learning model;
- and
- input/output circuitry configured to:
- generate, at the user interface, a dynamic interface option selected by an ensemble prediction of outputs from the first machine learning model and the second machine learning model, wherein the dynamic interface option comprises an option to modify an account of the first user.
A method for generating dynamic interface options using machine learning models featuring multi-modal feature inputs, the method comprising:
- receiving, using control circuitry, a first user action, from a first user, during a device interface session with a user interface;
- determining, using the control circuitry, a first user interface image corresponding to the first user action in the user interface;
- determining, using the control circuitry, metadata related to the first user interface image;
- retrieving, using the control circuitry, time-dependent user account information for the first user during the device interface session with the user interface;
- generating, using the control circuitry, a first feature input based on the metadata;
- generating, using the control circuitry, a second feature input based on the time-dependent user account information;
- inputting, using the control circuitry, the first feature input into a first machine learning model;
- inputting, using the control circuitry, the second feature input into a second machine learning model;
- and
- generating, at the user interface, a dynamic interface option selected by a machine learning model during the device interface session.
A non-transitory, computer-readable medium for generating dynamic interface options using machine learning models featuring multi-modal feature inputs, comprising instructions that, when executed by one or more processors, cause operations comprising:
- receiving a first user action, from a first user, during a device interface session with a user interface;
- determining a first user interface image corresponding to the first user action in the user interface;
- determining metadata related to the first user interface image;
- retrieving time-dependent user account information for the first user during the device interface session with the user interface;
- generating a first feature input based on the metadata;
- generating a second feature input based on the time-dependent user account information;
- inputting the first feature input into a first machine learning model;
- inputting the second feature input into a second machine learning model;
- and
- generating, at the user interface, a dynamic interface option selected by a machine learning model during the device interface session.
Dependencies are inferred from the claim text.