Generating social media content for a user associated with an enterprise
AssigneeState Farm Mutual Automobile Insurance Company
InventorsJose Ivan Gutierrez, Lauren Mitchell, Ross Wheeler, Steve Amancha, Anthony Welcome
Life of this patent
Estimating the term…
Abstract
Systems and methods disclosed herein relate to fine-tuning machine learning (ML) chatbots for an enterprise. The systems and methods may use ML chatbots and/or generative ML to generate social media content for a user associated with an enterprise. The systems and methods may fine-tune a base ML model, and use the fine-tuned ML model for the ML chatbot. A user profile may indicate user attributes, and a fine-tuned ML model may be loaded for the ML chatbot based upon an identified user profile.
Claims20
A computer-implemented method for generating social media content for a user associated with an enterprise using machine learning (ML), the computer-implemented method comprising:
- training, by one or more processors, a base ML model using historical enterprise data, wherein the base ML model comprises an input layer, at least one connected deep layer, and an output layer;
- fine-tuning, by the one or more processors, the base ML model based upon a plurality of training data associated with a plurality of user profiles to generate a plurality of fine-tuned ML models associated with the plurality of user profiles, wherein fine-tuning the base ML model comprises adjusting at least one weight and at least one layer based upon the training data associated with the plurality of user profiles;
- receiving, by the one or more processors from the user via a user device, a request for information;
- obtaining, by the one or more processors, a user profile associated with a user;
- providing, by the one or more processors, the request for the information to an ML chatbot based upon an identified fined-tuned ML model, wherein:
- the ML chatbot is trained to generate a response based upon a user profile associated with the user;
- and
- the ML chatbot is trained using historical training data indicative of a style of communication associated with the user profile;
- obtaining, by the one or more processors, an output of the ML chatbot that is responsive to the request;
- generating, by the one or more processors, the social media content based upon the output;
- and
- providing, by the one or more processors, the social media content to the user device.
A system for generating social media content for a user associated with an enterprise using machine learning (ML), the system comprising:
- one or more processors;
- and
- one or more non-transitory memories storing processor-executable instructions that, when executed by the one or more processors, cause the system to:
- train a base ML model using historical enterprise data, wherein the base ML model comprises an input layer, at least one connected deep layer, and an output layer;
- fine-tune the base ML model based upon a plurality of training data associated with a plurality of user profiles to generate a plurality of fine-tuned ML models associated with the plurality of user profiles, wherein fine-tuning the base ML model comprises adjusting at least one weight and at least one layer based upon the training data associated with the plurality of user profiles;
- receive a request for information from the user via a user device;
- obtain a user profile associated with a user;
- identify a fine-tuned ML model of the plurality of fine-tuned ML models associated with the user profile;
- provide the request for the information to an ML chatbot based upon the identified fined-tuned ML model, wherein:
- the ML chatbot is trained to generate a response based upon a user profile associated with the user;
- and
- the ML chatbot is trained using historical training data indicative of a style of communication associated with the user profile;
- obtain an output of the ML chatbot that is responsive to the request;
- generate the social media content based upon the output;
- and
- provide the social media content to the user device.
A non-transitory computer-readable medium storing processor-executable instructions for generating social media content that, when executed by one or more processors, cause the one or more processors to:
- train a base ML model using historical enterprise data, wherein the base ML model comprises an input layer, at least one connected deep layer, and an output layer;
- fine-tune the base ML model based upon a plurality of training data associated with a plurality of user profiles to generate a plurality of fine-tuned ML models associated with the plurality of user profiles, wherein fine-tuning the base ML model comprises adjusting at least one weight and at least one layer based upon the training data associated with the plurality of user profiles;
- receive a request for information from a user via a user device;
- obtain a user profile associated with a user;
- identify a fine-tuned ML model of the plurality of fine-tuned ML models associated with the user profile;
- provide the request for the information to an ML chatbot based upon the identified fined-tuned ML model, wherein:
- the ML chatbot is trained to generate a response based upon a user profile associated with the user;
- and
- the ML chatbot is trained using historical training data indicative of a style of communication associated with the user profile;
- obtain an output of the ML chatbot that is responsive to the request;
- generate the social media content based upon the output;
- and
- provide the social media content to the user device.
Dependencies are inferred from the claim text.