Systems and methods for dynamic queue control using machine learning techniques

Patent metadata

Field	Value
Publication number	US-11657173-B2
Application number	US-202117237985-A
Country	US
Kind code	B2
Filing date	Apr 22, 2021
Priority date	Nov 19, 2018
Publication date	May 23, 2023
Grant date	May 23, 2023

Abstract

Certain embodiments of the present disclosure relate to systems and methods that control access to system resources, such as interfaces, access rights to events, query systems, and other suitable system resources. Further, certain embodiments of the present disclosure relate to a collision detection technique that is implemented to control which and/or a number of queue positions within a queue that are processed. In some implementations, a collision may be detected when two or more users request the same access right within a defined time period.

First claim

What is claimed is:

1. A method for managing assignment of access rights to a resource, comprising:
receiving, at a primary load management system, a communication from a user device, wherein the communication corresponds to a request for the access rights to the resource;
determining a user identifier associated with the user device based on the communication;
accessing one or more data points associated with the user identifier, wherein the one or more data points correspond to an attribute of the user identifier;
generating a resource-affinity parameter comprises:
accessing a first data set that includes one or more first data points associated with a user,
accessing a second data set that includes one or more second data points associated with the user,
inputting the first data set into a first trained machine-learning model,
inputting the second data set into a second trained machine-learning model, and
generating the resource-affinity parameter based on a combination of a first output of the first trained machine-learning model and a second output of the second trained machine-learning model, wherein:
the resource-affinity parameter represents a likelihood that the user associated with the user device will meet an objective, and
the resource-affinity parameter is generated by inputting the one or more data points into a machine learning model;

determining a current system load, wherein the current system load represents a load of requests received at the primary load management system during a current time period;
determining a first throttle factor based on the resource-affinity parameter and the current system load;
controlling a first workflow associated with the resource, wherein:
controlling the first workflow comprises enabling the user device to query the access rights as a part of the first workflow controlled by the first throttle factor, and
the query includes a constraint for querying the access rights;

determining a second throttle factor based on the resource-affinity parameter; and
controlling a second workflow based on the second throttle factor, wherein the second workflow comprises assigning the access rights to the user device.

2. The method of claim 1 , further comprising storing a plurality of access rights to the resource, each access right of the plurality of access rights being associated with a digital ticket that enables access to the resource, wherein the resource is associated with an event, and each access right of the plurality of access rights being unique from other access rights of the plurality of access rights.

3. The method of claim 1 , wherein the first throttle factor is used to control a speed or a frequency at which steps of the first workflow are provided to the user device.

4. The method of claim 1 , wherein the second throttle factor is used to control a speed or a frequency at which steps of the second workflow are provided to the user device.

5. The method of claim 1 , wherein the one or more data points include information about the user or the user device.

6. The method of claim 1 , further comprising an interface, wherein:
the interface is displayed on the user device, and
the interface enables the user to query the access rights associated with the resource for at least one access right that satisfies the constraint.

7. A system for managing assignment of access rights to a resource, comprising:
one or more processors; and
a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more processors, cause the one or more processors to perform operations including:
receiving, at a primary load management system, a communication from a user device, wherein the communication corresponds to a request for the access rights to the resource;
determining a user identifier associated with the user device based on the communication;
accessing one or more data points associated with the user identifier, wherein the one or more data points correspond to an attribute of the user identifier;
generating a resource-affinity parameter comprises:
accessing a first data set that includes one or more first data points associated with a user,
accessing a second data set that includes one or more second data points associated with the user,
inputting the first data set into a first trained machine-learning model,
inputting the second data set into a second trained machine-learning model, and
generating the resource-affinity parameter based on a combination of a first output of the first trained machine-learning model and a second output of the second trained machine-learning model, wherein:
the resource-affinity parameter represents a likelihood that the user associated with the user device will meet an objective, and
the resource-affinity parameter is generated by inputting the one or more data points into a machine learning model;
determining a current system load, wherein the current system load represents a load of requests received at the primary load management system during a current time period;
determining a first throttle factor based on the resource-affinity parameter and the current system load;
controlling a first workflow associated with the resource, wherein:
controlling the first workflow comprises enabling the user device to query the access rights as a part of the first workflow controlled by the first throttle factor, and
the query includes a constraint for querying the access rights;

determining a second throttle factor based on the resource-affinity parameter; and
controlling a second workflow based on the second throttle factor, wherein the second workflow comprises assigning the access rights to the user device.

8. The system of claim 7 , further comprising storing a plurality of access rights to the resource, each access right of the plurality of access rights being associated with a digital ticket that enables access to the resource, wherein the resource is associated with an event, and each access right of the plurality of access rights being unique from other access rights of the plurality of access rights.

9. The system of claim 7 , wherein the first throttle factor is used to control a speed or a frequency at which steps of the first workflow are provided to the user device.

10. The system of claim 7 , wherein the second throttle factor is used to control a speed or a frequency at which steps of the second workflow are provided to the user device.

11. The system of claim 7 , wherein the one or more data points include information about the user or the user device.

12. The system of claim 7 , further comprising an interface, wherein:
the interface is displayed on the user device, and
the interface enables the user to query the access rights associated with the resource for at least one access right that satisfies the constraint.

13. A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause a processing apparatus to perform operations including:
receiving, at a primary load management system, a communication from a user device, wherein the communication corresponds to a request for access rights to a resource;
determining a user identifier associated with the user device based on the communication;
accessing one or more data points associated with the user identifier, wherein the one or more data points correspond to an attribute of the user identifier;
generating a resource-affinity parameter comprises:
accessing a first data set that includes one or more first data points associated with a user,
acce

Assignees

• Live Nation Entertainment Inc

Inventors

• Roden Mark
• Cernoch Dan
• Chung Victoria

Classifications

• G06N3/0895

  Weakly supervised learning, e.g. semi-supervised or self-supervised learning · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/047

  Probabilistic or stochastic networks · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N20/20

  Ensemble learning · CPC title