IP Library › Granted Patent US 11,868,935
Granted Patent B2
US 11,868,935 · App. 17/070,375 · Granted Jan 9, 2024

System and method for allocating computer-based resources based on incomplete policy data

Inventors: Jinyu Feng (Mountain View, CA); Haotian Xu (Los Angeles, CA)
Assignee: YOTASCALE, INC.
G06Q10/06315G06N5/04G06N20/00G06Q10/06312G06Q10/103G06Q10/105
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 11,868,935
App. No.
17/070,375
Filed
Oct 14, 2020
Granted
Jan 9, 2024
Kind
B2
Examiner
ULLAH, ARIF
Art Unit
3683
USPC
705/7.25
Abstract

A system and method for allocating computer resources. The method includes generating a resource allocation policy defined for an organization for allocating the computer resources, determining a resource category allocation based on the generated resource allocation policy, generating a usage data, allocating the computer resource based on at least one of the generated usage data or the determined resource category allocation, executing allocation engines to allocate remaining unallocated computer resources, and providing a predicted resource allocation to implement the allocating of the computer resource.

Claims (48)

1. A method for allocating computer resources, comprising:

generating a resource allocation policy defined for an organization for allocating the computer resources;

determining a resource category allocation based on the generated resource allocation policy;

generating a usage data;

automatically generating, by a machine learning model, a new predicted resource allocation policy based on at least one of the generated usage data or the determined resource category allocation, the generating including:

detecting drifts in key application to the computer resources that is input over time, isolating factors that influence the key application based on a known output including total expenditure of the keyed computer resources and unkeyed computer resources, and transforming the usage data to a new feature space,

executing allocation engines to allocate remaining unallocated computer resources;

automatically providing a predicted resource allocation based on the new predicted resource allocation policy to implement a reallocation of the computer resources;

refining the machine learning model by generated feedback, wherein the generated feedback indicates one of an allocation that received a specific feedback, or an identified correct allocation of the computer resources;

reallocate the remaining unallocated resources based on the generated feedback and a feature matching technique.

2. The method of claim 1 , wherein the organization includes one of an external or an internal organization.

3. The method of claim 1 , wherein the resource allocation policy is generated by receiving data indicative of an aspect of the organization.

4. The method of claim 1 , wherein the usage data includes a plurality of features, the plurality of features including one of characteristics of the computer resources used, time stamp, quantity of the computer resources used, tags associated with the use of the computer resources, user identifiers associated with the use of the computer resources, inter-resource interactions, Application Program Interface (API) calls, relationships among the computer resources, or security access groups.

5. The method of claim 1 , further comprising detecting the remaining unallocated computer resources using a kernel-based method.

6. The method of claim 1 , wherein the feedback is provided by one of a model-based feedback assistance engine or an allocation dispute management engine.

7. The method of claim 1 , further comprising generating a feedback, wherein the feedback is generated by one of a model-based feedback assistance engine or an allocation dispute management engine.

8. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprising:

generating a resource allocation policy defined for an organization for allocating computer resources;

determining a resource category allocation based on the generated resource allocation policy;

generating a usage data;

automatically generating, by a machine learning model, a new predicted resource allocation policy automatically based on at least one of the generated usage data or the determined resource category allocation, the generating including:

detecting drifts in key application to the computer resources that is input over time,

isolating factors that influence the key application based on a known output including total expenditure of the keyed computer resources and unkeyed computer resources, and

transforming the usage data to a new feature space;

executing allocation engines to allocate remaining unallocated computer resources; and

automatically providing a predicted resource allocation based on the new predicted resource allocation policy to implement a reallocation of the computer resources automatically;

refining the machine learning model by generated feedback, wherein the generated feedback indicates one of an allocation that received a specific feedback, or an identified correct allocation of the computer resources;

reallocate the remaining unallocated resources based on the generated feedback and a feature matching technique.

9. A system for allocating computer resources, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

generate a resource allocation policy defined for an organization for allocating the computer resources;

determine a resource category allocation based on the generated resource allocation policy;

generate a usage data;

automatically generate, by a machine learning model, a new predicted resource allocation policy automatically based on at least one of the generated usage data or the determined resource category allocation, the generating including:

detecting drifts in key application to the computer resources that is input over time,

isolating factors that influence the key application based on a known output including total expenditure of the keyed computer resources and unkeyed computer resources, and

transforming the usage data to a new feature space;

execute allocation engines to allocate remaining unallocated computer resources;

and provide a predicted resource allocation based on the new predicted resource allocation policy to implement a reallocation of the computer resources automatically;

refining the machine learning model by generated feedback, wherein the generated feedback indicates one of an allocation that received a specific feedback, or an identified correct allocation of the computer resources;

reallocate the remaining unallocated resources based on the generated feedback and a feature matching technique.

10. The system of claim 9 , wherein the organization includes one of an external or an internal organization.

11. The system of claim 9 , wherein the resource allocation policy is generated by receiving data indicative of an aspect of the organization.

12. The system of claim 9 , wherein the usage data includes a plurality of features, the plurality of features including one of characteristics of the computer resources used, time stamp, quantity of the computer resources used, tags associated with the use of the computer resources, user identifiers associated with the use of the computer resources, inter-resource interactions, Application Program Interface (API) calls, relationships among the computer resources, or security access groups.

13. The system of claim 9 , wherein the system is further configured to detect the remaining unallocated computer resources using a kernel-based method.

14. The system of claim 9 , wherein the feedback is provided by one of a model-based feedback assistance engine or an allocation dispute management engine.

15. The system of claim 9 , further comprising generating a feedback, wherein the feedback is generated by one of a model-based feedback assistance engine or an allocation dispute management engine.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 19, 2023
From: FENG, JINYU; XU, HAOTIAN
To: YOTASCALE, INC.
Reel/Frame 062429/0283 →
Continuity (2)
Provisional Application 62914730 · Oct 14, 2019
Related Publication 20210182756A1 · Jun 17, 2021