# US 2021/0241249 A1 · Terminal access and load management

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

- Number: US 2021/0241249 A1
- Document ID: US20210241249A1
- Status: Published application
- Kind: A1
- Application number: 16/777,080
- Filed: 2020-01-30
- Published: 2021-08-05
- Earliest claimed: 2020-01-30
- Assignees: NCR Corporation
- Applicants: NCR Corporation
- Inventors: Zachary Christopher DeBardlebon; James Emery Fugedy, II; Aleah Jean Kadry
- Web page: https://patentgrep.com/patent/US20210241249A1

## CPC

- G06Q 20/202: {Interconnection or interaction of plural electronic cash registers [ECR] or to host computer, e.g. network details, transfer of information from host to ECR or from ECR to ECR}
- G06N 20/00: Machine learning
- 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)
- G06Q 10/0631: Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 20/53: {Recognition of crowd images, e.g. recognition of crowd congestion}
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Cameras capture time-stamped images of customers, carts, and items possessed by the customers. Customer queues at checkout stations/transaction terminals are monitored for queue lengths, opened terminals, closed terminals, and a total number of items possessed by each customer within each queue. Queue wait times are calculated for each queue and the queue wait times are displayed on monitors adjacent to the queues. Customers approaching the checkout stations are directed to specific queues based on the queue wait times. Closed terminals are opened in advance of a time when a shortest expected wait time for the queues is expected to exceed a threshold wait time. In an embodiment, each queue length is managed based on staff performance metrics associated with staff operating the terminals.

## Claims

### Claim 1

A method, comprising:
obtaining transaction performance metrics for staff members operating checkout terminals;
determining from video frames a total number of individuals in each of a plurality of queues associated with the checkout terminals;
identifying a total number of items with each individual based on the video frames;
calculating a total wait time for checkout at each queue based on the determining and the identifying and further based on the transaction performance metrics of each staff member and the corresponding checkout terminal being operated by the corresponding staff member;
displaying the total wait times for the queues on at least one monitor;
maintaining current transaction performance metrics for the staff members as checkouts are processed at the checkout terminals; and
updating the transaction performance metrics for the staff members with the current transaction performance metrics.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining further includes determining a total number of individuals within a store that are not yet associated with any of the queues.

### Claim 3 (depends on 2)

The method of claim 2, wherein determining further includes determining closed checkout terminals available for checkouts but currently not processing any of the checkouts.

### Claim 4 (depends on 3)

The method of claim 3, wherein determining further includes determining staff identities of the staff members operating the checkout terminals and other staff identifies of other staff members that are available in the store but are not currently operating any of the checkout terminals.

### Claim 5 (depends on 4)

The method of claim 4, wherein obtaining further includes obtaining the transaction performance metrics for each of the staff identities and each of the other staff identities from a transaction history log.

### Claim 6 (depends on 5)

The method of claim 5, wherein identifying further includes determining the total number of items with each individual by using a trained machine-learning algorithm that takes as input the video frames and provides as output the total number of items for each individual.

### Claim 7 (depends on 5)

The method of claim 5, wherein identifying further includes checking the total number of items for each individual against sensor data read for wireless tags associated with the items as each individual passes by sensors before entering the queues.

### Claim 8 (depends on 5)

The method of claim 5, wherein calculating further includes processing: the total number of individuals within the store, the total number of individuals per queue, the total number of items per individual, closed checkout terminal identifiers for the closed terminals, the staff identities, and the performance metrics to calculate each of the total wait times.

### Claim 9 (depends on 8)

The method of claim 8, wherein displaying further includes displaying a suggested queue identifier for a select one of the queues on the monitor for viewing by a next individual approaching the queues for checkout based on each of the total wait times and the performance metrics associated with each of the staff identities.

### Claim 10 (depends on 1)

The method of claim 1 further comprising, sending a staff member message to a staff operated device of a particular staff member to open a closed checkout terminal for checkouts based on a shortest total wait time from the total wait times approaching a threshold wait time and based on the corresponding transaction performance metrics associated with the particular staff member.

### Claim 11

A method, comprising:
maintaining a customer count for customers present within a store from video;
obtaining staff identifiers for staff working at the store;
obtaining transaction performance metrics associated with each staff identifier;
tracking first customers from the customers that are waiting in lanes of checkout terminals for checkouts;
calculating expected wait times for second customers that are approaching the lanes based on a total number of the first customers at each lane and the corresponding transaction performance metrics for first staff identifiers associated with first staff of the staff that is operating at least some of the checkout terminals;
displaying the expected wait times per lane on monitors when the second customers approach or are adjacent to any of the lane;
maintaining current transaction performance metrics for the first staff members as checkouts are processed at the checkout terminals; and
updating the transaction performance metrics for the first staff members with the current transaction performance metrics.

### Claim 12

(canceled)

### Claim 13 (depends on 11)

The method of claim 11 further comprising, pushing a notification to a second staff member of the staff to open a closed checkout terminal based on a shortest expected wait time from the expected wait times that is approaching a threshold wait time and based on the second customers and third customers from the customers that remain in the store and that have not checked out and further based on the corresponding transaction performance metrics associated with the second staff member.

### Claim 14 (depends on 11)

The method of claim 11, wherein tracking further includes identifying a total number of items per first customer from the video.

### Claim 15 (depends on 15)

The method of claim 15, wherein identifying further includes providing at least one image of a cart that includes the items per first customer to a trained machine-learning algorithm and receiving as output the total number of items per first customer as output from the trained machine-learning algorithm.

### Claim 16 (depends on 11)

The method of claim 11, wherein displaying further includes displaying on the monitors display information comprising: a checkout terminal identifier for each checkout terminal, the total number of first customers per checkout terminal identifier; and the expected wait time per checkout terminal identifier.

### Claim 17 (depends on 16)

The method of claim 16, wherein displaying further includes sorting the display information presented on the monitors from shortest expected wait times to longest expected wait times.

### Claim 18 (depends on 17)

The method of claim 17, wherein displaying further includes organizing the display information presented on the monitors into two groups of separately sorted information comprising a first group of staff-assisted checkout terminals being operated by the first staff and a second group of Self-Service Checkout (SSCO) terminals operated by select ones of the first customers performing self-checkouts.

### Claim 19

A system, comprising:
cameras configured to capture images within a store;
transaction terminals configured to perform checkouts from the store;
a server that includes a processor and a non-transitory computer-readable storage medium comprising executable instructions representing a terminal load manager;
the terminal load manager when executed by the processor from the non-transitory computer-readable storage medium configured to cause the processor to perform processing comprising:
tracking a total number of customers in a queue for the checkouts per transaction terminal from the images captured by the cameras;
tracking a total number of items possessed by each customer from the images;
obtaining transaction performance metrics for operators of each of the transaction terminals, wherein the transaction performance metrics represent historical transaction performance for each of the operators;
predicting an expected wait time for entering each of the queues based on the total number of the customers per queue, the total number of items per customer, and the transaction performance metrics per operator;
sending a notification to a second operator that instructs the second operator to open a closed transaction terminal for assisting in the checkouts based on a shortest expected wait time selected from the expected wait times approaching a threshold wait time;
displaying on monitors adjacent to the transaction terminals the expected wait time for each of the transaction terminals;
maintaining current transaction performance metrics for the operators as checkouts are processed at the transaction terminals; and
updating the transaction performance metrics for the operators with the current transaction performance metrics.

### Claim 20 (depends on 19)

The system of claim 19, wherein the transaction terminals comprise:
Point-Of-Sale (POS) terminals and Self-Service Terminals (SSTs).
