Systems and methods for generating personalized content using a language model and reinforcement techniques

A device, comprising:

• one or more processors configured to:
• receive user activity data identifying activities of a user;
• receive content data identifying text transcripts associated with the user;
• generate a first custom embedding associated with the user based on the user activity data;
• process the content data, with a clustering model, to remove duplicate content from the content data;
• process the first custom embedding, with a machine learning model, to generate an intent of the user and a next action for the user based on the intent;
• process the content data to generate a second custom embedding for the user and an end user vector based on the second custom embedding;
• generate a document vector for the user based on the next action for the user;
• process the document vector and the end user vector, with a language model, to generate a document for the user;
• and
• perform one or more actions based on the document, wherein the one or more processors, to perform the one or more actions, are configured to one or more of:
• provide the document for display to the user;
• receive a request from the user based on the document;
• perform an action requested by the user based on the document;
• or
• retrain the language model or the machine learning model based on the document.

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

• one or more instructions that, when executed by one or more processors of a device, cause the device to:
• receive user activity data identifying activities of a user;
• receive content data identifying text transcripts associated with the user;
• generate a first custom embedding associated with the user based on the user activity data;
• process the first custom embedding, with a machine learning model, to generate an intent of the user and a next action for the user based on the intent;
• process the content data to generate a second custom embedding for the user and an end user vector based on the second custom embedding;
• generate a document vector for the user based on the next action for the user;
• process the document vector and the end user vector, with a language model, to generate a document for the user, wherein the document is a self-help document for the user;
• receive a user action associated with the document;
• determine whether the user required assistance with the document based on the user action associated with the document;
• and
• selectively:
• store the document based on the user not requiring assistance with the document, or
• process the document, with the language model, to generate a modified document for the user based on the user requiring assistance with the document.