Distributing computational workload according to tensor optimization

Patent metadata

Field	Value
Publication number	US-11107100-B2
Application number	US-201916536425-A
Country	US
Kind code	B2
Filing date	Aug 9, 2019
Priority date	Aug 9, 2019
Publication date	Aug 31, 2021
Grant date	Aug 31, 2021

Abstract

Optimizing market assets using tensor optimization across cloud and edge resources by generating a tensor space associated with market assets, calculating matrices associated with the tensor space according to market asset correlations, determining market asset allocation opportunities, and suggesting market asset allocations according to a user risk assessment.

First claim

What is claimed is:

1. A computer implemented method for managing application execution, the method comprising:
generating a first tensor space associated with market assets, by a cloud resource;
generating a second tensor space associated with users, by a cloud resource;
allocating a generation of a combined tenor space from the first tensor space and the second tensor space to cloud resources according to a magnitude of the computational problem;
generating a combined tensor space from the first tensor space with the second tensor space using cloud resources;
allocating a mapping of correlations between the market assets and positive user outcomes to cloud resources according to a magnitude of the computational problem;
mapping correlations between the market assets and positive user outcomes, within the combined tensor space;
allocating a determination of market asset allocation opportunities according to the correlations to edge cloud resources according to a magnitude of the computational problem;
determining market asset allocation opportunities according to the correlations; and
suggesting market asset allocations according to a user risk assessment.

2. The computer implemented method according to claim 1 , further comprising:
allocating computing tasks according to a factor selected from the group consisting of: matrix density, data location, and edge asset capacity.

3. The computer implemented method according to claim 1 , wherein a rate of suggesting market asset allocations is determined according to an assessment of user risk tolerance.

4. The computer implemented method according to claim 1 , wherein mapping correlations associated with the market assets and positive user outcomes within the combined tensor space comprises calculating Gaussian mix models for tensor spaces.

5. The computer implemented method according to claim 4 , further comprising comparing Gaussian mix models of the tensor spaces.

6. The computer implemented method according to claim 1 , further comprising:
acquiring user biometric data; and
suggesting market asset allocations according to the user biometric data.

7. The computer implemented method according to claim 1 , wherein market asset correlations include market ranking and market class factors.

8. A computer program product for managing application execution, the computer program product comprising one or more computer readable storage devices and stored program instructions on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions for generating a first tensor space associated with market assets by a cloud resource;
program instructions for generating a second tensor space associated with users, by a cloud resource;
program instructions for allocating a generation of a combined tenor space from the first tensor space and the second tensor space to cloud resources according to a magnitude of the computational problem;
program instructions for generating a combined tensor space from the first tensor space with the second tensor space using cloud resources;
program instructions for allocating a mapping of correlations between the market assets and positive user outcomes to cloud resources according to a magnitude of the computational problem;
program instructions for mapping correlations between the market assets and positive user outcomes, within the combined tensor space;
program instructions for allocating a determination of market asset allocation opportunities according to the correlations to edge cloud resources according to a magnitude of the computational problem;
program instructions for determining market asset allocation opportunities according to the correlations; and
program instructions for suggesting market asset allocations according to a user risk assessment.

9. The computer program product according to claim 8 , further comprising program instructions for allocating computing tasks according to a factor selected from the group consisting of: matrix density, data location, and edge asset capacity.

10. The computer program product according to claim 8 , further comprising program instructions for determining a rate of suggesting market asset allocations according to an assessment of user risk tolerance.

11. The computer program product according to claim 8 , wherein mapping correlations associated with the market assets and positive outcomes within the combined tensor space comprises calculating Gaussian mix models for tensor spaces.

12. The computer program product according to claim 11 , further comprising program instructions for comparing the Gaussian mix models of the tensor space.

13. The computer program product according to claim 8 , further comprising program instructions for: acquiring user biometric data; and suggesting market asset allocations according to the user biometric data.

14. The computer program product according to claim 8 , wherein market asset correlations include market ranking and market class factors.

15. A computer system for managing application execution, the computer system comprising:
one or more computer processors;
one or more computer readable storage devices; and
stored program instructions on the one or more computer readable storage devices for execution by the one or more computer processors, the stored program instructions comprising:
program instructions for generating a first tensor space associated with market assets by a cloud resource;
program instructions for generating a second tensor space associated with users, by a cloud resource;
program instructions for allocating a generation of a combined tenor space from the first tensor space and the second tensor space to cloud resources according to a magnitude of the computational problem;
program instructions for generating a combined tensor space from the first tensor space with the second tensor space using cloud resources;
program instructions for allocating a mapping of correlations between the market assets and positive user outcomes to cloud resources according to a magnitude of the computational problem;
program instructions for mapping correlations between the market assets and positive user outcomes, within the combined tensor space;
program instructions for allocating a determination of market asset allocation opportunities according to the correlations to edge cloud resources according to a magnitude of the computational problem;
program instructions for determining market asset allocation opportunities according to the correlations; and
program instructions for suggesting market asset allocations according to a user risk assessment.

16. The computer system according to claim 15 , further comprising program instructions for allocating computing tasks according to a factor selected from the group consisting of: matrix density, data location, and edge asset capacity.

17. The computer system according to claim 15 , further comprising program instructions for determining a rate of suggesting market asset allocations according to an assessment of user risk tolerance.

18. The computer system according to claim 15 , wherein mapping correlations associated with the market assets and positive outcomes within the combined tensor space comprises calculating Gaussian mix models for tensor spaces.

19. The computer system according to claim 18 , further comprising program instructions for comparing the Gaussian mix models of the tensor spaces.

20. The computer system accor

Assignees

• IBM

Inventors

• Baughman Aaron K
• Cannon Gray
• Forster Micah
• Kwatra Shikhar

Classifications

• G06Q30/0206 Primary

  Price or cost determination based on market factors · CPC title

• G06Q10/0635 Primary

  Risk analysis of enterprise or organisation activities · CPC title

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title