SYSTEMS AND METHODS FOR GENERATING LANGUAGE MODEL CONTEXT USING USER PROFILE DATA
Systems and methods for generating language model context using user profile data are disclosed. A system can maintain a data structure identifying a historical actions performed using a player profile and a vector database comprising a plurality of encoded data structures. The system can receive, from a client device during a communication session, a prompt identifying a request for a data structure recommendation. Using the prompt, the system can generate an encoded data structure comprising at least a subset of the plurality of historical actions in an encoded format. The system can select, from the vector database, at least one encoded data structure based on the encoded data structure generated from the prompt. The system can use a language model with the prompt, the encoded data structure, and the at least one encoded data structure to generate an output message identifying the data structure recommendation in response to the prompt.
1 . A system, comprising:
one or more processors coupled to non-transitory memory, the one or more processors configured to:
maintain a data structure identifying a plurality of historical actions performed using a player profile;
maintain a vector database comprising a plurality of encoded wager opportunities;
receive, from a client device during a communication session, a prompt identifying a request for a wager recommendation;
generate, using the prompt, an encoded data structure comprising at least a subset of the plurality of historical actions in an encoded format;
select, from the vector database, at least one encoded wager opportunity of the plurality of encoded wager opportunities based on the encoded data structure; and
generate, using a language model, the prompt, the encoded data structure, and the at least one encoded wager opportunity to generate an output message identifying the wager recommendation in response to the prompt.
2 . The system of claim 1 , wherein the one or more processors are further configured to:
receive an update to at least one wager; and
update the vector database to include the update to the at least one wager in an encoded format.
3 . The system of claim 2 , wherein the one or more processors are further configured to:
receive the update to the at least one wager from an external computing system.
4 . The system of claim 1 , wherein the one or more processors are further configured to:
generate an input context using the prompt, the encoded data structure, and the at least one encoded wager; and
providing the input context to the language model to generate the output message.
5 . The system of claim 1 , wherein the one or more processors are further configured to:
receive a second prompt identifying a plurality of wager selections;
generate a parlay wager including the plurality of wager selections; and
execute the language model using the second prompt, the encoded data structure, and the parlay wager to generate a second output message identifying the parlay wager.
6 . The system of claim 1 , wherein the one or more processors are further configured to:
determine a wager type identified in the prompt; and
select the at least one encoded wager further based on the wager type.
7 . The system of claim 6 , wherein the one or more processors are further configured to:
determine the wager type using a machine-learning model trained to generate classifications of wager types.
8 . The system of claim 1 , wherein the one or more processors are further configured to:
retrieve, using data of the at least one encoded wager, real-time odds information for the at least one encoded wager; and
update the output message to include the real-time odds information.
9 . The system of claim 1 , wherein the at least one encoded wager comprises real-time odds information.
10 . The system of claim 1 , wherein the plurality of historical actions comprise one or more historical wagers, one or more historical interactions, one or more historical prompts, or one or more historical preferences.
11 . A method, comprising:
maintaining, by one or more processors coupled to non-transitory memory, a data structure identifying a plurality of historical actions performed using a player profile;
maintaining, by the one or more processors, a vector database comprising a plurality of encoded wager opportunities;
receiving, by the one or more processors, from a client device during a communication session, a prompt identifying a request for a wager recommendation;
generating, by the one or more processors, using the prompt, an encoded data structure comprising at least a subset of the plurality of historical actions in an encoded format;
selecting, by the one or more processors, from the vector database, at least one encoded wager opportunity of the plurality of encoded wager opportunities based on the encoded data structure; and
generating, by the one or more processors, using a language model, the prompt, the encoded data structure, and the at least one encoded wager opportunity to generate an output message identifying the wager recommendation in response to the prompt.
12 . The method of claim 11 , further comprising:
receiving, by the one or more processors, an update to at least one wager; and
updating, by the one or more processors, the vector database to include the update to the at least one wager in an encoded format.
13 . The method of claim 12 , further comprising:
receiving, by the one or more processors, the update to the at least one wager from an external computing system.
14 . The method of claim 11 , further comprising:
generating, by the one or more processors, an input context using the prompt, the encoded data structure, and the at least one encoded wager; and
providing, by the one or more processors, the input context to the language model to generate the output message.
15 . The method of claim 11 , further comprising:
receiving, by the one or more processors, a second prompt identifying a plurality of wager selections;
generating, by the one or more processors, a parlay wager including the plurality of wager selections; and
executing, by the one or more processors, the language model using the second prompt, the encoded data structure, and the parlay wager to generate a second output message identifying the parlay wager.
16 . The method of claim 11 , further comprising:
determining, by the one or more processors, a wager type identified in the prompt; and
selecting, by the one or more processors, the at least one encoded wager further based on the wager type.
17 . The method of claim 16 , further comprising:
determining, by the one or more processors, the wager type using a machine-learning model trained to generate classifications of wager types.
18 . The method of claim 11 , further comprising:
retrieving, by the one or more processors, using data of the at least one encoded wager, real-time odds information for the at least one encoded wager; and
updating, by the one or more processors, the output message to include the real-time odds information.
19 . The method of claim 11 , wherein the at least one encoded wager comprises real-time odds information.
20 . The method of claim 11 , wherein the plurality of historical actions comprise one or more historical wagers, one or more historical interactions, one or more historical prompts, or one or more historical preferences.