SYSTEMS AND METHODS FOR GENERATING NETWORK APPLICATION INTERFACES ACCORDING TO LANGUAGE MODEL INPUT IN A DISTRIBUTED COMPUTING ENVIRONMENT
Described herein are systems and methods for providing machine-learning system functionalities. A system can receive, from a client device during a communication session, a prompt for a language model comprising a request relating to a potential data structure. Using the language model and the prompt, the system can generate an output comprising an indication of at least one data structure opportunity to satisfy the request. Based on the prompt and the output, the system can generate a content item comprising text data corresponding to at least one second prompt for the communication session. The system can provide the output and the content item to the client device in response to the prompt, causing the client device to present the output with the content item in a graphical user interface.
1 . A system, comprising:
one or more processors coupled to non-transitory memory, the one or more processors configured to:
receive, from a client device during a communication session, a prompt for a language model comprising a request relating to a potential wager;
generate, using the language model and the prompt, an output comprising an indication of at least one wager opportunity to satisfy the request;
generate, based on the prompt and the output, a content item comprising text data corresponding to at least one second prompt for the communication session; and
provide the output and the content item to the client device in response to the prompt, causing the client device to present the output with the content item in a graphical user interface.
2 . The system of claim 1 , wherein the one or more processors are further configured to:
generate the text data of the content item using the language model.
3 . The system of claim 1 , wherein the at least one wager opportunity is a parlay wager opportunity, and wherein the text data identifies at least one additional leg for the parlay wager opportunity.
4 . The system of claim 3 , wherein the one or more processors are further configured to:
receive, from the client device during the communication session, an additional prompt comprising the text data; and
generate, using the language model, the output, and the additional prompt, second output for the communication session comprising a second indication of at least one second wager opportunity identifying the at least one additional leg.
5 . The system of claim 1 , wherein the one or more processors are further configured to:
retrieve, from one or more data structures storing data of a plurality of wager opportunities, at least one additional wager based on the prompt and the output; and
generate the text data of the content item based on the at least one additional wager.
6 . The system of claim 1 , wherein the one or more processors are further configured to:
receive, from the client device, an indication of an interaction with the content item; and
generate an input context for the language model based on the text data of the content item.
7 . The system of claim 6 , wherein the one or more processors are further configured to:
generate second output using the language model and the input context; and
generate a second content item for the communication session based on the input context and the second output.
8 . The system of claim 1 , wherein the client device is associated with a player profile, and wherein the one or more processors are further configured to:
generate the text data for the content item further based on data retrieved from the player profile.
9 . The system of claim 8 , wherein the data retrieved from the player profile identifies at least one historical action performed using the player profile, and the one or more processors are further configured to:
generate the text data for the content item further based on the at least one historical action.
10 . The system of claim 1 , wherein the one or more processors are further configured to:
generate a plurality of content items including the content item, each of the plurality of content items comprising respective second text data; and
provide the plurality of content items for display with the output generated by the language model.
11 . A method, comprising:
receiving, by one or more processors coupled to non-transitory memory, from a client device during a communication session, a prompt for a language model comprising a request relating to a potential wager;
generating, by the one or more processors, using the language model and the prompt, an output comprising an indication of at least one wager opportunity to satisfy the request;
generating, by the one or more processors, based on the prompt and the output, a content item comprising text data corresponding to at least one second prompt for the communication session; and
providing, by the one or more processors, the output and the content item to the client device in response to the prompt, causing the client device to present the output with the content item in a graphical user interface.
12 . The method of claim 11 , further comprising generating, by the one or more processors, the text data of the content item using the language model.
13 . The method of claim 11 , wherein the at least one wager opportunity is a parlay wager opportunity, and wherein the text data identifies at least one additional leg for the parlay wager opportunity.
14 . The method of claim 13 , further comprising:
receiving, by the one or more processors, from the client device during the communication session, an additional prompt comprising the text data; and
generating, by the one or more processors, using the language model, the output, and the additional prompt, second output for the communication session comprising a second indication of at least one second wager opportunity identifying the at least one additional leg.
15 . The method of claim 11 , further comprising:
retrieving, by the one or more processors, from one or more data structures storing data of a plurality of wager opportunities, at least one additional wager based on the prompt and the output; and
generating, by the one or more processors, the text data of the content item based on the at least one additional wager.
16 . The method of claim 11 , further comprising:
receiving, by the one or more processors, from the client device, an indication of an interaction with the content item; and
generating, by the one or more processors, an input context for the language model based on the text data of the content item.
17 . The method of claim 16 , further comprising:
generating, by the one or more processors, second output using the language model and the input context; and
generating, by the one or more processors, a second content item for the communication session based on the input context and the second output.
18 . The method of claim 11 , wherein the client device is associated with a player profile, and further comprising generating, by the one or more processors, the text data for the content item further based on data retrieved from the player profile.
19 . The method of claim 18 , wherein the data retrieved from the player profile identifies at least one historical action performed using the player profile, and further comprising:
generating, by the one or more processors, the text data for the content item further based on the at least one historical action.
20 . The method of claim 11 , further comprising:
generating, by the one or more processors, a plurality of content items including the content item, each of the plurality of content items comprising respective second text data; and
providing, by the one or more processors, the plurality of content items for display with the output generated by the language model.