Systems and methods for processing user profile data structures using language model output

A method, comprising:

• maintaining, by one or more processors coupled to non-transitory memory, a plurality of wager opportunities corresponding to a plurality of live events;
• receiving, by the one or more processors, from a client device, a first prompt including one or more first natural language text strings identifying a request for a wager recommendation;
• generating, by the one or more processors, based on providing data corresponding to the first prompt as an input to a language model, output identifying at least one wager opportunity of the plurality of wager opportunities selected to satisfy the request;
• receiving, by the one or more processors, from the client device, a second prompt including one or more second natural language text strings identifying a request to update a player profile associated with the client device;
• generating, by the one or more processors, based on providing data corresponding to the second prompt as an input to the language model, a command to update a data structure of the player profile based on the at least one wager opportunity;
• and
• updating, by the one or more processors, the data structure of the player profile according to the command and the at least one wager opportunity.