Proactive personalization of multimedia content and dialog content through utilization of large language model(s)

A system comprising:

• at least one processor;
• and
• memory storing instructions that, when executed, cause the at least one processor to be operable to:
• receive an indication of user input to initiate streaming of multimedia content at a client device of a user;
• in response to receiving the indication of the user input to initiate the streaming of the multimedia content:
• generate, based on at least contextual data associated with the user of the client device, a structured large language model (LLM) query;
• generate, based on processing the structured LLM query, LLM output;
• determine, based on the LLM output, given multimedia content and given dialog content, wherein the instructions to determine the given multimedia content based on the LLM output comprise instructions to:
• establish, based on the LLM output, a communication session with a multimedia content service provider;
• and
• obtain, from the multimedia content service provider and during the communication session, the given multimedia content;
• and
• in response to determining the given multimedia content and the given dialog content:
• cause the client device to initiate the streaming of the given multimedia content that was obtained from the multimedia content service provider and during the communication session established based on the LLM output;
• and
• cause the client device to render the given dialog content before the client device initiates the streaming of the given multimedia content or while the given multimedia content is being streamed at the client device;
• determine when to generate an additional structured LLM query to continue the streaming of the multimedia content;
• in response to determining to generate the additional structured LLM query to continue the streaming of the multimedia content:
• generate, based on at least additional contextual data associated with the user of the client device, the additional structured LLM query;
• generate, based on the additional structured LLM query, additional LLM output;
• and
• determine, based on the additional LLM output, given additional multimedia content and given additional dialog content, wherein the instructions to determine the given additional multimedia content based on the additional LLM output comprise instructions to:
• continue, based on the additional LLM output, the communication session with the multimedia content service provider;
• and
• obtain, from the multimedia content service provider and during the communication session, the given additional multimedia content;
• and
• subsequent to determining the given additional multimedia content and the given additional dialog content:
• cause the client device to initiate the streaming of the given additional multimedia content that was obtained from the multimedia content service provider and during the communication session continued based on the additional LLM output;
• and
• cause the client device to render the given additional dialog content before the client device initiates streaming of the given additional multimedia content or while the given additional multimedia content is being streamed at the client device.

A non-transitory computer-readable storage medium storing instructions that, when executed, cause at least one processor to perform operations, the operations comprising:

• receiving an indication of user input to initiate streaming of multimedia content at a client device of a user;
• in response to receiving the indication of the user input to initiate the streaming of the multimedia content:
• generating, based on at least contextual data associated with the user of the client device, a structured large language model (LLM) query;
• generating, based on processing the structured LLM query, LLM output;
• determining, based on the LLM output, given multimedia content and given dialog content, wherein determining the given multimedia content based on the LLM output comprises:
• establishing, based on the LLM output, a communication session with a multimedia content service provider;
• and
• obtaining, from the multimedia content service provider and during the communication session, the given multimedia content;
• and
• in response to determining the given multimedia content and the given dialog content:
• causing the client device to initiate the streaming of the given multimedia content that was obtained from the multimedia content service provider and during the communication session established based on the LLM output;
• and
• causing the client device to render the given dialog content before the client device initiates the streaming of the given multimedia content or while the given multimedia content is being streamed at the client device;
• determining when to generate an additional structured LLM query to continue the streaming of the multimedia content;
• in response to determining to generate the additional structured LLM query to continue the streaming of the multimedia content:
• generating, based on at least additional contextual data associated with the user of the client device, the additional structured LLM query;
• generating, based on the additional structured LLM query, additional LLM output;
• and
• determining, based on the additional LLM output, given additional multimedia content and given additional dialog content, wherein determining the given additional multimedia content based on the additional LLM output comprises:
• continuing, based on the additional LLM output, the communication session with the multimedia content service provider;
• and
• obtaining, from the multimedia content service provider and during the communication session, the given additional multimedia content;
• and
• subsequent to determining the given additional multimedia content and the given additional dialog content:
• causing the client device to initiate the streaming of the given additional multimedia content that was obtained from the multimedia content service provider and during the communication session continued based on the additional LLM output;
• and
• causing the client device to render the given additional dialog content before the client device initiates streaming of the given additional multimedia content or while the given additional multimedia content is being streamed at the client device.