SYSTEMS AND METHODS FOR PRE-PROCESSING DATA STRUCTURES FOR LANGUAGE MODEL CONTEXT GENERATION IN A NETWORK ENVIRONMENT

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, a prompt for a language model;

determine, using the prompt, a classification of an intent for the prompt;

generate an input context for the language model using the prompt and the classification of the intent; and

generate, using the language model and the input context, an output message in response to the prompt.

2 . The system of claim 1 , wherein the one or more processors are further configured to:

determine that the classification indicates an unknown intent; and

provide an indication to the client device that the classification indicates the unknown intent.

3 . The system of claim 2 , wherein the one or more processors are further configured to:

receive a second prompt from the client device in response to the indication;

generate a second input context for the language model based on the prompt and the second prompt; and

generate, using the language model and the second input context, a second output message in response to the second prompt.

4 . The system of claim 1 , wherein the classification of the intent indicates a request for a wager opportunity, and wherein the one or more processors are further configured to:

retrieve a set of wager opportunities corresponding to the intent; and

generate the input context further based on the set of wager opportunities.

5 . The system of claim 1 , wherein the one or more processors are further configured to generate the classification of the intent by executing a machine-learning model trained to generate intent classifications.

6 . The system of claim 5 , wherein the one or more processors are further configured to:

identify a training dataset comprising a plurality of training examples, each example of the plurality of training examples comprising input text data and a corresponding ground truth intent classification; and

train the machine-learning model using the training dataset.

7 . The system of claim 5 , wherein the machine-learning model comprises the language model.

8 . The system of claim 1 , wherein the classification of the intent corresponds to one or more of a request for one or more wager recommendations, a request to modify a wager, a request for information relating to a live event, a request for information relating to a sports team, a request for information relating to at least one wager opportunity, a request to place a wager, or a request for information maintained by the one or more processors.

9 . The system of claim 1 , wherein the one or more processors are further configured to:

generate a plurality of portions of the prompt;

generate a plurality of classifications of intent for the plurality of portions, respectively; and

generate the input context further based on the plurality of classifications of intent for the plurality of portions.

10 . The system of claim 1 , wherein the one or more processors are further configured to:

extract one or more wager attributes from the prompt based on the classification of the intent; and

generate the input context further based on the one or more wager attributes.

11 . A method, comprising:

receiving, by one or more processors coupled to non-transitory memory, from a client device, a prompt for a language model;

determining, by the one or more processors, using the prompt, a classification of an intent for the prompt;

generating, by the one or more processors, an input context for the language model using the prompt and the classification of the intent; and

generating, by the one or more processors, using the language model and the input context, an output message in response to the prompt.

12 . The method of claim 11 , further comprising:

determining, by the one or more processors, that the classification indicates an unknown intent; and

providing, by the one or more processors, an indication to the client device that the classification indicates the unknown intent.

13 . The method of claim 12 , further comprising:

receiving, by the one or more processors, a second prompt from the client device in response to the indication;

generating, by the one or more processors, a second input context for the language model based on the prompt and the second prompt; and

generating, by the one or more processors, using the language model and the second input context, a second output message in response to the second prompt.

14 . The method of claim 11 , wherein the classification of the intent indicates a request for a wager opportunity, the method further comprising:

retrieving, by the one or more processors, a set of wager opportunities corresponding to the intent; and

generating, by the one or more processors, the input context further based on the set of wager opportunities.

15 . The method of claim 11 , further comprising:

generating, by the one or more processors, the classification of the intent by executing a machine-learning model trained to generate intent classifications.

16 . The method of claim 15 , further comprising:

identifying, by the one or more processors, a training dataset comprising a plurality of training examples, each example of the plurality of training examples comprising input text data and a corresponding ground truth intent classification; and

training, by the one or more processors, the machine-learning model using the training dataset.

17 . The method of claim 15 , wherein the machine-learning model comprises the language model.

18 . The method of claim 11 , wherein the classification of the intent corresponds to one or more of a request for one or more wager recommendations, a request to modify a wager, a request for information relating to a live event, a request for information relating to a sports team, a request for information relating to at least one wager opportunity, a request to place a wager, or a request for information maintained by the one or more processors.

19 . The method of claim 11 , further comprising:

generating, by the one or more processors, a plurality of portions of the prompt;

generating, by the one or more processors, a plurality of classifications of intent for the plurality of portions, respectively; and

generating, by the one or more processors, the input context further based on the plurality of classifications of intent for the plurality of portions.

20 . The method of claim 11 , further comprising:

extracting, by the one or more processors, one or more wager attributes from the prompt based on the classification of the intent; and

generating, by the one or more processors, the input context further based on the one or more wager attributes.