Identifying and utilizing the availability of enterprise resources

Patent metadata

Field	Value
Publication number	US-10810528-B1
Application number	US-201916517270-A
Country	US
Kind code	B1
Filing date	Jul 19, 2019
Priority date	Jul 19, 2019
Publication date	Oct 20, 2020
Grant date	Oct 20, 2020

Abstract

Various embodiments are directed to techniques for organizing fulfillment of enterprise products, such as by using a request manager informed by enterprise resources and resource utilization to recommend a facility to fulfill a product request. Some embodiments are directed to identifying a product request and determining the equipment and skills necessary to fulfill the product request. Based on this information and location data, embodiments may determine a set of facilities as candidates to fulfill the request. A machine learning model may be used to analyze current resource utilization of the facilities and predict facility availability and estimated completion times for the request fulfillment. A candidate facility may be recommended for fulfillment of a request based on facility availability and estimated completion times. In some embodiments, historical resource utilization may be used to inform further staffing and equipment service decisions.

First claim

The invention claimed is:

1. An apparatus, comprising:
a processor; and
a memory comprising instructions that when executed by the processor cause the processor to:
identify a request for a product from a user;
determine two or more requisite resources to provide the product requested by the user, the two or more requisite resources comprising at least one device and at least one skill;
identify a location associated with the user based on the request for the product from the user;
determine a set of candidate facilities to fulfill the request for the product based on the two or more requisite resources to provide the product requested by the user and the location associated with the user, wherein each candidate facility in the set of candidate facilities to fulfill the request for the product comprises each of the two or more requisite resources to provide the product requested by the user and satisfy a proximity threshold to the location associated with the user;
compute a set of current resource utilizations for each candidate facility in the set of candidate facilities, the set of current resource utilizations computed based on status data that is automatically updated with data generated by one or more sensors at least one candidate facility in the set of candidate facilities, wherein the set of current resource utilizations for a respective candidate facility includes an availability of at least one of the two or more requisite resources to provide the product requested by the user;
evaluate the set of current resource utilizations for each candidate facility in the set of candidate facilities with a machine learning model to determine a set of available facilities and an estimated completion time to fulfill the request for each available facility in the set of available facilities;
determine one or more recommended facilities based on the set of available facilities and the estimated completion time to fulfill the request for each available facility in the set of available facilities; and
generate output comprising the one or more recommended facilities.

2. The apparatus of claim 1 , the memory comprising instruction that when executed by the processor cause the processor to compute the set of current resource utilizations for a candidate facility in the set of candidate facilities based on one or more of a number of appointments at the candidate facility, a number of existing requests at the candidate facility, a number of scheduled activities for requisite resources at the candidate facility, a number of customers en route to the candidate facility, a size of a check in queue at the candidate facility, a number of vehicles in a parking lot of the candidate facility, and a number of navigation systems with the candidate facility as a destination.

3. The apparatus of claim 1 , the memory comprising instruction that when executed by the processor cause the processor to generate output comprising the one or more recommended facilities and the estimated completion time for each of the one or more recommended facilities, the output to cause a user interface to present the one or more recommended facilities and the estimated completion time for each of the one or more recommended facilities to the user for selection.

4. The apparatus of claim 3 , the memory comprising instruction that when executed by the processor cause the processor to:
identify a selected facility from the one or more recommended facilities based on input received via the user interface; and
communicate the request for the product to the selected facility.

5. The apparatus of claim 1 , the memory comprising instruction that when executed by the processor cause the processor to determine one or more future staffing requirements for an available facility in the set of available facilities based on the set of current resource utilizations for the available facility in the set of available facilities.

6. The apparatus of claim 1 , the at least one device of the two or more requisite resources to provide the product requested by the user comprising one or more of the one or more devices associated with the facility comprising one or more of an automated teller machine, a money counter, a vault, safety deposit boxes, coffee machine, a certified check printer, a bank card encoder, and a bank card blank.

7. The apparatus of claim 1 , the at least one skill of the two or more requisite resources to provide the product requested by the user comprising one or more of mortgage sales, small business banking, teller, public notary, and training certification.

8. The apparatus of claim 1 , wherein the machine learning model is trained on historical resource utilizations for one or more candidate facilities in the set of candidate facilities.

9. At least one non-transitory computer-readable medium comprising a set of instructions that, in response to being executed by a processor circuit, cause the processor circuit to:
determine two or more requisite resources to provide a product based on a request for the product from a user, the two or more requisite resources comprising at least one device and at least one skill;
identify a location associated with the user based on the request for the product from the user;
determine a set of candidate facilities to fulfill the request for the product based on the two or more requisite resources to provide the product requested by the user and the location associated with the user, wherein each candidate facility in the set of candidate facilities to fulfill the request for the product comprises each of the two or more requisite resources to provide the product requested by the user and satisfy a proximity threshold to the location associated with the user;
compute a set of current resource utilizations for each candidate facility in the set of candidate facilities, the set of current resource utilizations computed based on status data that is automatically updated with data generated by one or more sensors at least one candidate facility in the set of candidate facilities, wherein the set of current resource utilizations for a respective candidate facility includes an availability of at least one of the two or more requisite resources to provide the product requested by the user;
evaluate the set of current resource utilizations for each candidate facility in the set of candidate facilities with one or more machine learning models to determine a set of available facilities and an estimated completion time to fulfill the request for each available facility in the set of available facilities;
determine one or more recommended facilities based on the set of available facilities and the estimated completion time to fulfill the request for each available facility in the set of available facilities; and
provide the one or more recommended facilities as output.

10. The at least one non-transitory computer-readable medium of claim 9 , comprising instructions that, in response to being executed by the processor circuit, cause the processor circuit to compute the set of current resource utilizations for a candidate facility in the set of candidate facilities based on one or more of a number of appointments at the candidate facility, a number of existing requests at the candidate facility, a number of scheduled activities for requisite resources at the candidate facility, a number of customers en route to the candidate facility, a size of a check in queue at the candidate facility, a number of vehicles in a parking lot of the candidate facility, and a number of navigation systems with the candidate facility as a destination.

11. The at least one non-transitory computer-readable medium of claim 9 , compr

Assignees

• Capital One Services Llc

Inventors

• Phillips Jeremy
• Awadallah Ehab
• Hill St John G

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q10/1093

  Calendar-based scheduling for persons or groups · CPC title

• G06Q10/06315 Primary

  Needs-based resource requirements planning or analysis · CPC title

• G06Q20/1085

  involving automatic teller machines [ATMs] · CPC title