# US 2022/0035677 A1 · Dynamic allocation of resources in surge demand

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0035677 A1
- Document ID: US20220035677A1
- Status: Published application
- Kind: A1
- Application number: 17/150,203
- Filed: 2021-01-15
- Published: 2022-02-03
- Earliest claimed: 2020-07-28
- Assignees: Optum Services (Ireland) Limited
- Applicants: Optum Services (Ireland) Limited
- Inventors: Vicente Ruben Del Pino Ruiz; Hendrik Kleine
- Web page: https://patentgrep.com/patent/US20220035677A1

## CPC

- G06F 9/5038: {considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration (scheduling strategies G06F9/4881 and subgroups)}
- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06F 9/505: {considering the load}
- G06F 9/5077: {Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455)}
- G06Q 10/0631: Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q 50/00: Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism (healthcare informatics G16H)
- G06F 2209/5019: Workload prediction
- G06F 2209/5021: Priority
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for optimized resource transformation given a set of resource optimization parameters. In accordance with one embodiment, a method is provided that includes: identifying a demand surge scenario associated with resource demand conditions; in response to identifying the scenario: determining a downgrade set of resources; determining whether a downgrade-only resource transformation scenario characterized by downgrade transformation of the downgrade set satisfies the conditions; and responsive to determining the downgrade-only resource transformation scenario fails to satisfy the conditions: identifying residual resources that are transformable to meet the conditions, processing the residual resources using a machine learning model characterized by the set of resource optimization parameters to generate resource priority scores, and generating a optimized resource transformation scenario from a scenario based at least in part on the resource priority scores and the downgrade-only resource transformation scenario.

## Claims

### Claim 1

A computer-implemented method for optimized resource transformation given a set of resource optimization parameters, the computer-implemented method comprising:
identifying, using one or more processors, a demand surge scenario, wherein the demand surge scenario is associated with one or more resource demand conditions;
in response to identifying the demand surge scenario:
determining, using the one or more processors and based at least in part on a plurality of resource transformation data objects associated with a plurality of resources, a downgrade set of the plurality of resources;
determining, using the one or more processors, whether a downgrade-only resource transformation scenario characterized by downgrade transformation of the downgrade set of the plurality of resources satisfies the one or more resource demand conditions;
in response to determining that the downgrade-only resource transformation scenario satisfies the one or more resource demand conditions, generating, using the one or more processors, an optimized resource transformation scenario based at least in part on the downgrade-only resource transformation scenario; and
in response to determining that the downgrade-only resource transformation scenario fails to satisfy the one or more resource demand conditions: (i) identifying, using the one or more processors, one or more residual resources of the plurality of resources that are deemed transformable to meet the one or more resource demand conditions but are not in the downgrade set, (ii) processing, using the one or more processors, the one or more residual resources using a resource optimization machine learning model that is characterized by the set of resource optimization parameters to generate one or more resource priority scores for the one or more residual resources, (iii) generating, using the one or more processors, a hybrid resource transformation scenario based at least in part on the one or more resource priority scores and the downgrade-only resource transformation scenario, and (iv) generating, using the one or more processors, the optimized resource transformation scenario based at least in part on the hybrid resource transformation scenario; and
causing, using the one or more processors, one or more resource transformation actions to be performed based at least in part on the optimized resource transformation scenario.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein each resource transformation data object for a resource of the plurality of resources that is either in the downgrade set or among the one or more residual resources indicates that the resource has a capability to be transformed to satisfy the one or more resource demand conditions within an expected time occurrence for the demand surge scenario.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein identifying the demand surge scenario comprises:
generating, using a trend surge prediction machine learning model, a trend surge indicator based at least in part on a recent trend for one or more resource demand indicators associated with the one or more resource demand conditions;
generating, using a historical surge prediction machine learning model, a historical surge indicator based at least in part on a cyclical trend for the one or more resource demand indicators;
generating a surge score based at least in part on the trend surge indicator and the historical surge indicator; and
identifying the demand surge scenario based at least in part on whether the surge score satisfies a surge score threshold.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein identifying the demand surge scenario comprises:
identifying a first demand surge scenario associated with one or more first resource demand conditions;
identifying a second demand surge scenario associated with one or more second resource demand conditions;
determining the one or more resource demand conditions based at least in part on the one or more first resource demand conditions and the one or more second resource demand conditions; and
determining the demand surge scenario based at least in part on the one or more resource demand conditions.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein determining the one or more resource demand conditions based at least in part on the one or more first resource demand conditions and the one or more second resource demand conditions comprises merging the one or more first resource demand conditions and the one or more second resource demand conditions to generate the one or more resource demand conditions.

### Claim 6 (depends on 4)

The computer-implemented method of claim 4, wherein determining the one or more resource demand conditions based at least in part on the one or more first resource demand conditions and the one or more second resource demand conditions comprises generating the one or more resource demand conditions based at least in part on a shared subset of the one or more first resource demand conditions and the one or more second resource demand conditions.

### Claim 7 (depends on 4)

The computer-implemented method of claim 4, determining the one or more resource demand conditions based at least in part on the one or more first resource demand conditions and the one or more second resource demand conditions comprises:
determining a first demand surge priority score for the first demand surge scenario;
determining a second demand surge priority score for the second demand surge scenario;
in response to determining that the first demand surge priority score exceeds the second demand surge priority score, determining the one or more resource demand conditions based at least in part on the one or more first resource demand conditions; and
in response to determining that the second demand surge priority score exceeds the first demand surge priority score, determining the one or more resource demand conditions based at least in part on the one or more second resource demand conditions.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein each resource transformation data object for a resource of the plurality of resources that is in the downgrade set describes that the resource can be transformed to satisfy at least one of the one or more resource demand conditions for at least one of no cost or a cost satisfying a threshold cost.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the set of resource optimization parameters comprises at least one of a transformation cost parameter or a transformation time parameter.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more resource transformation actions comprise automatically executing one or more operations to have one or more resources identified in the optimized resource transformation scenario transformed to satisfy the one or more resource demand conditions.

### Claim 11

An apparatus for optimized resource transformation given a set of resource optimization parameters, the apparatus comprising at least one processor and at least one memory including program code, the at least one memory and the program code configured to, with the at least one processor, cause the apparatus to at least:
identify a demand surge scenario, wherein the demand surge scenario is associated with one or more resource demand conditions;
in response to identifying the demand surge scenario:
determine, based at least in part on a plurality of resource transformation data objects associated with a plurality of resources, a downgrade set of the plurality of resources;
determine whether a downgrade-only resource transformation scenario characterized by downgrade transformation of the downgrade set of the plurality of resources satisfies the one or more resource demand conditions;
in response to determining that the downgrade-only resource transformation scenario satisfies the one or more resource demand conditions, generate an optimized resource transformation scenario based at least in part on the downgrade-only resource transformation scenario; and
in response to determining that the downgrade-only resource transformation scenario fails to satisfy the one or more resource demand conditions: (i) identify one or more residual resources of the plurality of resources that are deemed transformable to meet the one or more resource demand conditions but are not in the downgrade set, (ii) process the one or more residual resources using a resource optimization machine learning model that is characterized by the set of resource optimization parameters to generate one or more resource priority scores for the one or more residual resources, (iii) generate a hybrid resource transformation scenario based at least in part on the one or more resource priority scores and the downgrade-only resource transformation scenario, and (iv) generate the optimized resource transformation scenario based at least in part on the hybrid resource transformation scenario; and
cause one or more resource transformation actions to be performed based at least in part on the optimized resource transformation scenario.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein each resource transformation data object for a resource of the plurality of resources that is either in the downgrade set or among the one or more residual resources indicates that the resource has a capability to be transformed to satisfy the one or more resource demand conditions within an expected time occurrence for the demand surge scenario.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein the at least one memory and the program code are configured to, with the at least one processor, cause the apparatus to identify the demand surge scenario by:
generating, using a trend surge prediction machine learning model, a trend surge indicator based at least in part on a recent trend for one or more resource demand indicators associated with the one or more resource demand conditions;
generating, using a historical surge prediction machine learning model, a historical surge indicator based at least in part on a cyclical trend for the one or more resource demand indicators;
generating a surge score based at least in part on the trend surge indicator and the historical surge indicator; and
identifying the demand surge scenario based at least in part on whether the surge score satisfies a surge score threshold.

### Claim 14 (depends on 11)

The apparatus of claim 11, wherein the at least one memory and the program code are configured to, with the at least one processor, cause the apparatus to identify the demand surge scenario by:
identifying a first demand surge scenario associated with one or more first resource demand conditions;
identifying a second demand surge scenario associated with one or more second resource demand conditions;
determining the one or more resource demand conditions based at least in part on the one or more first resource demand conditions and the one or more second resource demand conditions; and
determining the demand surge scenario based at least in part on the one or more resource demand conditions.

### Claim 15 (depends on 11)

The apparatus of claim 11, wherein each resource transformation data object for a resource of the plurality of resources that is in the downgrade set describes that the resource can be transformed to satisfy at least one of the one or more resource demand conditions for at least one of no cost or a cost satisfying a threshold cost.

### Claim 16 (depends on 11)

The apparatus of claim 11, wherein the set of resource optimization parameters comprises at least one of a transformation cost parameter or a transformation time parameter.

### Claim 17

A non-transitory computer storage medium comprising instructions for optimized resource transformation given a set of resource optimization parameters, the instructions being configured to cause one or more computer processors to at least perform operations configured to:
identify a demand surge scenario, wherein the demand surge scenario is associated with one or more resource demand conditions;
in response to identifying the demand surge scenario:
determine, based at least in part on a plurality of resource transformation data objects associated with a plurality of resources, a downgrade set of the plurality of resources;
determine whether a downgrade-only resource transformation scenario characterized by downgrade transformation of the downgrade set of the plurality of resources satisfies the one or more resource demand conditions;
in response to determining that the downgrade-only resource transformation scenario satisfies the one or more resource demand conditions, generate an optimized resource transformation scenario based at least in part on the downgrade-only resource transformation scenario; and
in response to determining that the downgrade-only resource transformation scenario fails to satisfy the one or more resource demand conditions: (i) identify one or more residual resources of the plurality of resources that are deemed transformable to meet the one or more resource demand conditions but are not in the downgrade set, (ii) process the one or more residual resources using a resource optimization machine learning model that is characterized by the set of resource optimization parameters to generate one or more resource priority scores for the one or more residual resources, (iii) generate a hybrid resource transformation scenario based at least in part on the one or more resource priority scores and the downgrade-only resource transformation scenario, and (iv) generate the optimized resource transformation scenario based at least in part on the hybrid resource transformation scenario; and
cause one or more resource transformation actions to be performed based at least in part on the optimized resource transformation scenario.

### Claim 18 (depends on 17)

The non-transitory computer storage medium of claim 17, wherein each resource transformation data object for a resource of the plurality of resources that is either in the downgrade set or among the one or more residual resources indicates that the resource has a capability to be transformed to satisfy the one or more resource demand conditions within an expected time occurrence for the demand surge scenario.

### Claim 19 (depends on 17)

The non-transitory computer storage medium of claim 17, wherein the instructions are configured to cause the one or more computer processors to at least perform operations configured to identify the demand surge scenario by:
generating, using a trend surge prediction machine learning model, a trend surge indicator based at least in part on a recent trend for one or more resource demand indicators associated with the one or more resource demand conditions;
generating, using a historical surge prediction machine learning model, a historical surge indicator based at least in part on a cyclical trend for the one or more resource demand indicators;
generating a surge score based at least in part on the trend surge indicator and the historical surge indicator; and
identifying the demand surge scenario based at least in part on whether the surge score satisfies a surge score threshold.

### Claim 20 (depends on 17)

The non-transitory computer storage medium of claim 17, wherein the set of resource optimization parameters comprises at least one of a transformation cost parameter or a transformation time parameter.
