IP Library › Patent Application 19360886

Patent Application

App. No. 19/360,886

SYSTEMS AND METHODS FOR ASSIGNING WEIGHTS TO INTERACTION TYPES IN A DISTRIBUTED NETWORKING ENVIRONMENT USING LANGUAGE MODELS

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US None
App. No.: 19/360,886

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Described herein are systems and methods for providing wager recommendations and wager comparisons based on a player prompt by preparing the input context of a large language model. A system can maintain an indexed data structure comprising a plurality of wager scenarios corresponding to a plurality of live events, wherein each wager scenario is associated with a respective odds value. The system can receive, from a client device, a prompt comprising an indication of a game parameter tolerance. The system can select a subset of the wager scenarios based on the game parameter tolerance indicated in the prompt and the respective odds values retrieved via indexes of the indexed data structure. Using a language model, the system can generate an output message identifying at least one of the selected wager scenarios to satisfy the game parameter tolerance. The system can provide the output message to the client device in response to the prompt.

Claims (146)

1 . (canceled)

2 . (canceled)

3 . A method for responding to game parameter tolerances with a series of wager scenarios that exist within the game parameter tolerances, the method comprising:

maintaining an indexed data structure comprising a plurality of wager scenarios corresponding to a plurality of live events, wherein each scenario of the plurality of wager scenarios associated with a respective odds value of a respective wager scenario, wherein the indexed data structure is indexed by a set of indexes, and wherein the set of indexes comprise a first vector index and a second vector index;

receiving, from a client device, a prompt comprising an indication of a game parameter tolerance;

identifying a first ordered tolerance category from a series of tolerance categories based on the game parameter tolerance indicated in the prompt;

selecting a subset of the plurality of wager scenarios based on the indication of the game parameter tolerance determined from the prompt and the respective odds value of the plurality of wager scenarios retrieved via the indexed data structure;

selecting the subset of the plurality of wager scenarios that correspond to the first ordered tolerance category by:

selecting a first group of wager scenarios assigned to the first ordered tolerance category by searching through the first vector index based on the first ordered tolerance category; and

selecting a second group of wager scenarios assigned to a second ordered tolerance category that is adjacent to the first ordered tolerance category;

generating, using a language model, the subset of the plurality of wager scenarios, and the prompt, an output message identifying at least one of the subset of the plurality of wager scenarios to satisfy the game parameter tolerance of the prompt; and

providing the output message to the client device in response to the prompt.

4 . A method for responding to game parameter tolerances with a series of wager scenarios that exist within the game parameter tolerances, the method comprising:

receiving, from a client device, a prompt comprising an indication of a game parameter tolerance, wherein the client device is associated with a player profile;

selecting the subset of the plurality of wager scenarios further based on odds values of historical wagers identified in the player profile by:

retrieving the historical wagers identified in the player profile from a player profile database; and

determining a set of game parameter tolerances based on the historical wagers, wherein generating an output message comprises providing the set of game parameter tolerances to a language model:

generating, using the language model, the subset of the plurality of wager scenarios, and the prompt, the output message identifying at least one of the subset of the plurality of wager scenarios to satisfy the game parameter tolerance of the prompt; and

providing the output message to the client device in response to the prompt.

5 . A method for responding to game parameter tolerances with a series of wager scenarios that exist within the game parameter tolerances, the method comprising:

receiving, from a client device, a prompt comprising an indication of a game parameter tolerance;

providing the output message to the client device in response to the prompt;

selecting the subset of the plurality of wager scenarios based on a second output of the language model by:

providing the prompt to the language model to produce a second output, wherein at least a portion of the second output is used as a query; and

submitting a query to a database based on the second output.

6 . The method of claim 3 , further comprising:

determining a threshold odds value based on the game parameter tolerance indicated in the prompt; and

selecting a respective scenario for inclusion in the subset of the plurality of wager scenarios responsive to the respective odds value of the respective scenario satisfying the threshold odds value.

7 . The method of claim 3 , further comprising:

generating, for each respective scenario of the plurality of wager scenarios, a respective weight value based on a respective odds value of the respective scenario and one or more respective odds changes of the respective scenario; and

selecting the respective scenario for inclusion the subset of the plurality of wager scenarios based on the respective weight value.

8 . The method of claim 3 , wherein the client device is associated with a game parameter tolerance setting, further comprising:

determining that the game parameter tolerance indicated in the prompt exceeds a value of the game parameter tolerance setting; and

generating the output message to include a second indication that the game parameter tolerance indicated in the prompt exceeds the value of the game parameter tolerance setting.

9 . The method of claim 3 , further comprising:

determining the game parameter tolerance indicated in the prompt using a machine-learning model different from the language model.

10 . (canceled)

11 . (canceled)

12 . A system, comprising:

one or more processors coupled to non-transitory memory, the one or more processors to:

maintain a data structure comprising a plurality of wager opportunities corresponding to a plurality of live events, each of the plurality of wager opportunities associated with a respective odds value;

receive, from a client device, a prompt comprising an indication of a risk tolerance;

determine a respective risk category of a plurality of risk categories for each of the plurality of wager opportunities;

identify a first risk category from the plurality of risk categories based on the risk tolerance indicated in the prompt;

select a subset of the plurality of wager opportunities based on the indication of the risk tolerance determined from the prompt and the respective odds value of the plurality of wager opportunities;

select the subset of the plurality of wager opportunities that correspond to the first risk category;

generate, using a language model, the subset, and the prompt, an output message identifying at least one of the subset of the plurality of wager opportunities to satisfy the risk tolerance of the prompt; and

provide the output message to the client device in response to the prompt.

13 . A system, comprising:

one or more processors coupled to non-transitory memory, the one or more processors to:

receive, from a client device, a prompt comprising an indication of a risk tolerance, wherein the client device is associated with a player profile;

select a subset of the plurality of wager opportunities based on the indication of the risk tolerance determined from the prompt and the respective odds value of the plurality of wager opportunities;

select the subset of the plurality of wager opportunities further based on odds values of one or more historical wagers identified in the player profile;

provide the output message to the client device in response to the prompt.

14 . A system, comprising:

one or more processors coupled to non-transitory memory, the one or more processors to:

receive, from a client device, a prompt comprising an indication of a risk tolerance;

select a subset of the plurality of wager opportunities based on the indication of the risk tolerance determined from the prompt and the respective odds value of the plurality of wager opportunities;

select the subset of the plurality of wager opportunities based on an output of a language model;

generate, using the language model, the subset, and the prompt, an output message identifying at least one of the subset of the plurality of wager opportunities to satisfy the risk tolerance of the prompt; and

provide the output message to the client device in response to the prompt.

15 . The system of claim 12 , wherein the one or more processors are further configured to:

determine a threshold odds value based on the risk tolerance indicated in the prompt; and

select each wager opportunity for inclusion in the subset responsive to the respective odds value of the wager opportunity satisfying the threshold odds value.

16 . The system of claim 12 , wherein the one or more processors are further configured to:

generate, for each wager opportunity of the plurality of wager opportunities, a respective weight value based on the respective odds value and one or more respective odds changes of the wager opportunity; and

select the subset of the plurality of wager opportunities based on the weight value.

17 . The system of claim 12 , wherein the client device is associated with a risk tolerance setting, and wherein the one or more processors are further configured to:

determine, using the one or more processors, that the risk tolerance indicated in the prompt exceeds a value of the risk tolerance setting; and

generate the output message to include a second indication that the risk tolerance indicated in the prompt exceeds the value of the risk tolerance setting.

18 . The system of claim 12 , wherein the plurality of wager opportunities comprises at least one of a single wager, a parlay wager, a same-game parlay (SGP) wager, or an exotic wager.

19 . The system of claim 12 , wherein the one or more processors are further configured to:

determine the risk tolerance indicated in the prompt using a machine-learning model different from the language model.

20 . (canceled)

21 . The method of claim 3 , wherein the client device is associated with a player profile, further comprising selecting the subset of the plurality of wager scenarios further based on odds values of historical wagers identified in the player profile by:

retrieving the historical wagers identified in the player profile from a player profile database; and

determining a set of game parameter tolerances based on the historical wagers, wherein generating the output message comprises providing the set of game parameter tolerances to the language model.

22 . The method of claim 3 , further comprising selecting the subset of the plurality of wager scenarios based on a second output of the language model by:

providing the prompt to the language model to produce a second output, wherein at least a portion of the second output is used as a query; and

submitting a query to a database based on the second output.

23 . The system of claim 12 , wherein the client device is associated with a player profile, and wherein the one or more processors are further configured to:

select the subset of the plurality of wager opportunities further based on odds values of one or more historical wagers identified in the player profile.

24 . The system of claim 12 , wherein the one or more processors are further configured to:

select the subset of the plurality of wager opportunities based on an output of the language model.

25 . A system for responding to game parameter tolerances provided in player-provided prompts with a series of wager scenarios that exist within the game parameter tolerances, the system comprising:

one or more processors coupled to non-transitory memory, the one or more processors to:

maintain an indexed data structure comprising a plurality of wager scenarios corresponding to a plurality of live events, wherein each scenario of the plurality of wager scenarios associated with a respective odds value of a respective wager scenario, wherein the indexed data structure is indexed by a set of indexes, and wherein the set of indexes comprise a first vector index and a second vector index;

receive, from a client device, a prompt comprising an indication of a game parameter tolerance;

identify a first ordered tolerance category from a series of tolerance categories based on the game parameter tolerance indicated in the prompt;

select a subset of the plurality of wager scenarios based on the indication of the game parameter tolerance determined from the prompt and the respective odds value of the plurality of wager scenarios retrieved via indexes of the indexed data structure;

select the subset of the plurality of wager scenarios that correspond to the first ordered tolerance category by:

selecting a first group of wager scenarios assigned to the first ordered tolerance category by searching through the first vector index based on the first ordered tolerance category; and

selecting a second group of wager scenarios assigned to a second ordered tolerance category that is adjacent to the first ordered tolerance category;

generate, using a language model, the subset, and the prompt, an output message identifying at least one of the subset of the plurality of wager scenarios to satisfy the game parameter tolerance of the prompt; and

provide the output message to the client device in response to the prompt.

26 . A system for responding to game parameter tolerances provided in player-provided prompts with a series of wager scenarios that exist within the game parameter tolerances, the system comprising:

one or more processors coupled to non-transitory memory, the one or more processors to:

receive, from a client device, a prompt comprising an indication of a game parameter tolerance, wherein the client device is associated with a player profile;

select the subset of the plurality of wager scenarios further based on odds values of historical wagers identified in the player profile by:

retrieving the historical wagers identified in the player profile from a player profile database; and

determining a set of game parameter tolerances based on the historical wagers, wherein generating an output message comprises providing the set of game parameter tolerances to a language model;

generate, using the language model, the subset, and the prompt, the output message identifying at least one of the subset of the plurality of wager scenarios to satisfy the game parameter tolerance of the prompt; and

provide the output message to the client device in response to the prompt.

27 . A system for responding to game parameter tolerances provided in player-provided prompts with a series of wager scenarios that exist within the game parameter tolerances, the system comprising:

one or more processors coupled to non-transitory memory, the one or more processors to:

receive, from a client device, a prompt comprising an indication of a game parameter tolerance;

provide the output message to the client device in response to the prompt; and

select the subset of the plurality of wager scenarios based on a second output of the language model by:

providing the prompt to the language model to produce a second output, wherein at least a portion of the second output is used as a query; and

submitting a query to a database based on the second output.

28 . A method, comprising:

maintaining a data structure comprising a plurality of wager opportunities corresponding to a plurality of live events, each of the plurality of wager opportunities associated with a respective odds value;

receiving, from a client device, a prompt comprising an indication of a risk tolerance;

determining a respective risk category of a plurality of risk categories for each of the plurality of wager opportunities;

identifying a first risk category from the plurality of risk categories based on the risk tolerance indicated in the prompt;

selecting a subset of the plurality of wager opportunities based on the indication of the risk tolerance determined from the prompt and the respective odds value of the plurality of wager opportunities;

selecting the subset of the plurality of wager opportunities that correspond to the first risk category;

generating, using a language model, the subset, and the prompt, an output message identifying at least one of the subset of the plurality of wager opportunities to satisfy the risk tolerance of the prompt; and

providing the output message to the client device in response to the prompt.

29 . A method, comprising:

receiving, from a client device, a prompt comprising an indication of a risk tolerance, wherein the client device is associated with a player profile;

selecting the subset of the plurality of wager opportunities further based on odds values of one or more historical wagers identified in the player profile;

providing the output message to the client device in response to the prompt.

30 . A method, comprising:

receiving, from a client device, a prompt comprising an indication of a risk tolerance;

selecting the subset of the plurality of wager opportunities based on an output of a language model;

providing the output message to the client device in response to the prompt.

Assignments (1)

ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 12, 2025

From: MOHSENI, ROBIN; ZHANG, GENGYUAN

To: DK CROWN HOLDINGS INC.

Reel/Frame 072877/0637 →