IP Library › Granted Patent US 12705542
Granted Patent B2
US 12705542 · App. 18/468,540 · Granted Aug 11, 2026

Machine learned resource allocation models for centralized database predictions

Inventors: Christian Franklin Hillson (Highlands Ranch, CO); Jacques Robert Caspi (Denver, CO); Andrew Collins Bessey (New York, NY); Lilly Anne Pieper (Boston, MA); Ryan David Kappedal (Olympia, WA); Jasmine Walker Motupalli (Centennial, CO); Addison Woodford Bohannon (Chicago, IL); Rebecca Alice Carter (Oakland, CA)
Assignee: Gusto, Inc.
G06N20/00
View Patent ↗
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 12705542
App. No.
18/468,540
Granted
Aug 11, 2026
Kind
B2
Abstract

A central database system trains and applies machine-learned models based on characteristics of one or more entities associated with the central database system. For instance, the central database system trains a machine-learned model configured to identify issues a target entity is likely to encounter based on training data identifying characteristics of historical entities and issues faced by the historical entities. Likewise, the central database system trains machine-learned models configured to predict actions that entities are likely to take in the future, and resources required to take those actions. The central database system can then perform one or more proactive actions or make one or more recommendations based on the predicted issues, the predicted future actions, and the predicted required resources.

Claims (33)

1 . A method comprising:

accessing, by a central database system for each of a set of historical entities, historical data describing 1) a historical time period, 2) historical actions requested by the historical entity during the historical time period, and 3) historical resources required by the central database system to perform the requested historical actions during the historical time period;

generating, by the central database system, a training set of data based on the accessed historical data;

training, by the central database system, a machine-learned model using the training set of data, the machine-learned model configured to predict, for an entity and a time period, resources required to perform actions requested by the entity during the time period;

applying, by the central database system, the machine-learned model to a target entity and a target time period to predict a set of target resources that will be required for the target entity and the target time period; and

modifying, by the central database system, a configuration of the central database system by reserving the predicted set of target resources for the target entity such that the predicted set of target resources are available to the target entity in advance of the target time period and such that another entity is unable to access the reserved set of target resources after the target time period beings until after the target time period has ended.

2 . The method of claim 1 , wherein the historical actions requested by the historical entities during the historical time period comprise actions performed using the central database system or data stored by the central database system, and wherein the historical resources required by the central database system comprises computing resources used by the central database system during the performance of the historical actions.

3 . The method of claim 1 , wherein the historical time period comprises one or more of: an hour, a day, a week, two weeks, a month, a quarter, and a year.

4 . The method of claim 1 , wherein the machine-learned model is at least one of a neural network, a logistic regression model, a random forest, a bagged tree, and a decision tree.

5 . The method of claim 1 , wherein the predicted set of target resources comprises one or more of: central database system memory, central database system data storage capacity, central database system bandwidth, central database system processing power, server capacity, network resources, and cloud resources.

6 . The method of claim 1 , wherein modifying the configuration of the central database system comprises re-allocating resources currently available to or used by another entity to the target entity.

7 . A non-transitory computer-readable storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

accessing, by a central database system for each of a set of historical entities, historical data describing 1) a historical time period, 2) historical actions requested by the historical entity during the historical time period, and 3) historical resources required by the central database system to perform the requested historical actions during the historical time period;

generating, by the central database system, a training set of data based on the accessed historical data;

training, by the central database system, a machine-learned model using the training set of data, the machine-learned model configured to predict, for an entity and a time period, resources required to perform actions requested by the entity during the time period;

applying, by the central database system, the machine-learned model to a target entity and a target time period to predict a set of target resources that will be required for the target entity and the target time period; and

modifying, by the central database system, a configuration of the central database system by reserving the predicted set of target resources for the target entity such that the predicted set of target resources are available to the target entity in advance of the target time period and such that another entity is unable to access the reserved set of target resources after the target time period beings until after the target time period has ended.

8 . The non-transitory computer-readable storage medium of claim 7 , wherein the historical actions requested by the historical entities during the historical time period comprise actions performed using the central database system or data stored by the central database system, and wherein the historical resources required by the central database system comprises computing resources used by the central database system during the performance of the historical actions.

9 . The non-transitory computer-readable storage medium of claim 7 , wherein the historical time period comprises one or more of: an hour, a day, a week, two weeks, a month, a quarter, and a year.

10 . The non-transitory computer-readable storage medium of claim 7 , wherein the machine-learned model is at least one of a neural network, a logistic regression model, a random forest, a bagged tree, and a decision tree.

11 . The non-transitory computer-readable storage medium of claim 7 , wherein the predicted set of target resources comprises one or more of: central database system memory, central database system data storage capacity, central database system bandwidth, central database system processing power, server capacity, network resources, and cloud resources.

12 . The non-transitory computer-readable storage medium of claim 7 , wherein modifying the configuration of the central database system comprises re-allocating resources currently available to or used by another entity to the target entity.

13 . A central database system comprising one or more hardware processors and a non-transitory computer-readable storage medium storing executable instructions that, when executed by the one or more hardware processors, cause the one or more hardware processors to perform operations comprising:

accessing, by the central database system for each of a set of historical entities, historical data describing 1) a historical time period, 2) historical actions requested by the historical entity during the historical time period, and 3) historical resources required by the central database system to perform the requested historical actions during the historical time period;

generating, by the central database system, a training set of data based on the accessed historical data;

training, by the central database system, a machine-learned model using the training set of data, the machine-learned model configured to predict, for an entity and a time period, resources required to perform actions requested by the entity during the time period;

applying, by the central database system, the machine-learned model to a target entity and a target time period to predict a set of target resources that will be required for the target entity and the target time period; and

modifying, by the central database system, a configuration of the central database system by reserving the predicted set of target resources for the target entity such that the predicted set of target resources are available to the target entity in advance of the target time period and such that another entity is unable to access the reserved set of target resources after the target time period beings until after the target time period has ended.

14 . The central database system of claim 13 , wherein the historical actions requested by the historical entities during the historical time period comprise actions performed using the central database system or data stored by the central database system, and wherein the historical resources required by the central database system comprises computing resources used by the central database system during the performance of the historical actions.

15 . The central database system of claim 13 , wherein the historical time period comprises one or more of: an hour, a day, a week, two weeks, a month, a quarter, and a year.

16 . The central database system of claim 13 , wherein the machine-learned model is at least one of a neural network, a logistic regression model, a random forest, a bagged tree, and a decision tree.

17 . The central database system of claim 13 , wherein the predicted set of target resources comprises one or more of: central database system memory, central database system data storage capacity, central database system bandwidth, central database system processing power, server capacity, network resources, and cloud resources.

18 . The central database system of claim 13 , wherein modifying the configuration of the central database system comprises re-allocating resources currently available to or used by another entity to the target entity.