Using machine learning for iconography recommendations
AssigneeCapital One Services, LLC
InventorsBriana Shaver, Mark Morrison
Life of this patent
Estimating the term…
Abstract
In some implementations, a recommendation system may input text into a machine learning model that was trained using input specific to an organization associated with the text and was refined using input specific to a portion of the organization. The recommendation system may receive, from the machine learning model, a recommendation indicating one or more visual components, stored in a database associated with the organization, to use with the text. The machine learning model may use natural language processing and sentiment detection to parse the text. Accordingly, the recommendation system may receive the one or more visual components from the database and generate an initial draft including the text and the one or more visual components.
Claims20
A system for visual content generation using machine learning, the system comprising:
- one or more memories;
- and
- one or more processors, communicatively coupled to the one or more memories, configured to:
- input into a machine learning model:
- text received from a user,
- a category of content for at least one template that is to be used with the text, and
- a sentiment associated with the at least one template,
- wherein the machine learning model was trained using a set of observations specific to an organization associated with the text, the set of observations including at least a feature associated with sentiment detection and a feature associated with a content category, and
- wherein the machine learning model was refined using input specific to a portion of the organization;
- receive, from the machine learning model, a recommendation indicating one or more images, one or more colors, and one or more logos to use with the text in populating the at least one template in association with the portion of the organization, wherein the one or more images, the one or more colors, and the one or more logos are retrieved from a database associated with the organization, and wherein the machine learning model uses at least natural language processing (NLP) and sentiment detection to parse the text;
- select, based on output from the machine learning model, the at least one template associated with the portion of the organization;
- and
- populate the at least one template using the one or more images, the one or more colors, the one or more logos, and the text.
A method of visual content generation using machine learning, comprising:
- inputting into a machine learning model:
- text received from a user,
- a category of content for an initial draft that is to be used with the text, and
- a sentiment associated with the initial draft,
- wherein the machine learning model was trained using a set of observations specific to an organization associated with the text, the set of observations including at least a feature associated with sentiment detection and a feature associated with a content category;
- receiving, from the machine learning model, a recommendation indicating one or more visual components to use with the text in generating the initial draft, wherein the one or more visual components are stored in a database associated with the organization;
- receiving the one or more visual components from the database;
- and
- generating the initial draft including the text and the one or more visual components.
A non-transitory computer-readable medium storing a set of instructions for visual content generation using machine learning, the set of instructions comprising:
- one or more instructions that, when executed by one or more processors of a device, cause the device to:
- input into a machine learning model:
- text received from a user,
- a category of content for an initial draft that is to be used with the text, and
- a sentiment associated with the initial draft,
- wherein the machine learning model was trained using a set of observations specific to an organization associated with the text, the set of observations including at least a feature associated with sentiment detection and a feature associated with a content category;
- receive, from the machine learning model, a recommendation indicating one or more visual components to use with the text in generating the initial draft, wherein the one or more visual components are stored in a database associated with the organization, and wherein the machine learning model uses at least one constraint associated with equal representation;
- receive the one or more visual components from the database;
- and
- generate the initial draft including the text and the one or more visual components.
Dependencies are inferred from the claim text.