# US 2023/0267389 A1 · Methods, systems, and devices to predict walk-out of customers associated with a premises

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

- Number: US 2023/0267389 A1
- Document ID: US20230267389A1
- Status: Published application
- Kind: A1
- Application number: 17/678,616
- Filed: 2022-02-23
- Published: 2023-08-24
- Earliest claimed: 2022-02-23
- Assignees: AT&T Intellectual Property I, L.P.
- Applicants: AT&T Intellectual Property I, L.P.
- Inventors: Sumeet Aneja; John Francis; Eli Schultz; Krishna Giduturi; Andrew Durden
- Web page: https://patentgrep.com/patent/US20230267389A1

## CPC

- G06Q 10/063114: {Status monitoring or status determination for a person or group}
- G06Q 10/06312: {Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling}
- G06V 20/44: {Event detection}
- 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}
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- G06F 18/2411: based on the proximity to a decision surface, e.g. support vector machines
- 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
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Aspects of the subject disclosure may include, for example, obtaining a group of images of a premises from a group of cameras associated with a first time period, generating computer vision data associated with a premises from the group of images for a first time period utilizing a group of image recognition techniques, obtaining employee schedule information associated with the premises for the first time period, and obtaining point-of-sale information associated with the premises for the first time period. Further embodiments include determining a first walk-out metric associated with the premises for the first time period according to the computer vision data, the employee schedule information, and the point-of-sale information. The first walk-out metric is based on a first number of customers leaving the premises without interacting with an employee associated with the premises during the first time period. Other embodiments are disclosed.

## Claims

### Claim 1

A device, comprising:
a processing system including a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:
obtaining a group of images of a premises from a group of cameras associated with a first time period;
generating computer vision data associated with the premises from the group of images for the first time period utilizing a group of image recognition techniques;
obtaining employee schedule information associated with the premises for the first time period;
obtaining point-of-sale information associated with the premises for the first time period; and
determining a first walk-out metric associated with the premises for the first time period according to the computer vision data, the employee schedule information, and the point-of-sale information, wherein the first walk-out metric is based on a first number of customers leaving the premises without interacting with an employee associated with the premises during the first time period.

### Claim 2 (depends on 1)

The device of claim 1, wherein the operations comprise:
determining an average transaction time for a customer associated with the premises;
generating a walk-out queuing model based on the computer vision data, the employee schedule information, the point-of-sale information, and the average transaction time; and
identifying a walk-out metric threshold based on the walk-out queuing model.

### Claim 3 (depends on 2)

The device of claim 2, wherein the operations comprise determining an arrival rate distribution associated with a group of customers for the walk-out queuing model based on the computer vision data, wherein the identifying of the walk-out metric threshold comprises identifying the walk-out metric threshold based on the arrival rate distribution.

### Claim 4 (depends on 2)

The device of claim 2, wherein the operations comprise obtaining a store size associated with the premises for the walk-out queuing model, wherein the identifying of the walk-out metric threshold comprises identifying the walk-out metric threshold based on the store size.

### Claim 5 (depends on 2)

The device of claim 2, wherein the operations comprise determining a second walk-out metric is less than the walk-out metric threshold for a second time period based on the walk-out queuing model.

### Claim 6 (depends on 5)

The device of claim 5, wherein the operations comprise determining a first employee schedule associated with the premises for the second time period based on the second walk-out metric.

### Claim 7 (depends on 2)

The device of claim 2, wherein the operations comprise determining a walk-out tolerance associated with the premises.

### Claim 8 (depends on 7)

The device of claim 7, wherein the operations further comprise determining a second employee schedule associated with the premises for a third time period based on the walk-out queuing model and the walk-out tolerance.

### Claim 9 (depends on 8)

The device of claim 8, wherein the third time period comprises a fourth time period and a fifth time period.

### Claim 10 (depends on 9)

The device of claim 9, wherein the operations comprise determining a third walk-out metric for the fourth time period is less than the walk-out metric threshold.

### Claim 11 (depends on 9)

The device of claim 9, wherein the operations comprise determining a fourth walk-out metric for the fifth time period is less than a sum of the walk-out metric threshold and the walk-out tolerance.

### Claim 12 (depends on 1)

The device of claim 1, wherein the determining the first walk-out metric comprises determining the first number of customers leaving the premises based on the computer vision data.

### Claim 13

A non-transitory, machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
obtaining a group of images of a premises from a group of cameras associated with a first time period;
generating computer vision data associated with the premises from the group of images for the first time period utilizing a group of image recognition techniques;
obtaining employee schedule information associated with the premises for the first time period;
obtaining point-of-sale information associated with the premises for the first time period;
determining a first walk-out metric associated with the premises for the first time period according to the computer vision data, the employee schedule information, and the point-of-sale information, wherein the first walk-out metric is based on a first number of customers leaving the premises without interacting with an employee associated with the premises during the first time period;
determining an average transaction time for a customer associated with the premise;
generating a walk-out queuing model based on the computer vision data, the employee schedule information, the point-of-sale information, and the average transaction time;
identifying a walk-out metric threshold based on the walk-out queuing model; and
determining a second walk-out metric is less than the walk-out metric threshold for a second time period based on the walk-out queuing model.

### Claim 14 (depends on 13)

The non-transitory, machine-readable medium of claim 13, wherein the operations further comprise determining an arrival rate distribution associated with a group of customers for the walk-out queuing model based on the computer vision data, wherein the identifying of the walk-out metric threshold comprises identifying the walk-out metric threshold based on the arrival rate distribution.

### Claim 15 (depends on 13)

The non-transitory, machine-readable medium of claim 13, wherein the operations comprise obtaining a store size associated with the premises for the walk-out queuing model, wherein the identifying of the walk-out metric threshold comprises identifying the walk-out metric threshold based on the store size.

### Claim 16 (depends on 13)

The non-transitory, machine-readable medium of claim 13, wherein the operations comprise determining a first employee schedule associated with the premises for the second time period based on the second walk-out metric.

### Claim 17

A method, comprising:
obtaining, by a processing system including a processor, a group of images of a premises from a group of cameras associated with a first time period;
generating, by the processing system, computer vision data associated with the premises from the group of images for the first time period utilizing a group of image recognition techniques;
obtaining, by the processing system, employee schedule information associated with the premises for the first time period;
obtaining, by the processing system, point-of-sale information associated with the premises for the first time period;
determining, by the processing system, a first walk-out metric associated with the premises for the first time period according to the computer vision data, the employee schedule information, and the point-of-sale information, wherein the first walk-out metric is based on a first number of customers leaving the premises without interacting with an employee associated with the premises during the first time period;
determining, by the processing system, an average transaction time for a customer associated with the premise;
generating, by the processing system, a walk-out queuing model based on the computer vision data, the employee schedule information, the point-of-sale information, and the average transaction time; and
determining, by the processing system, a walk-out tolerance associated with the premises; and
determining, by the processing system, an employee schedule associated with the premises for a second time period based on the walk-out queuing model, and the walk-out tolerance.

### Claim 18 (depends on 17)

The method of claim 17, wherein the second time period comprises a third time period and a fourth time period.

### Claim 19 (depends on 18)

The method of claim 18, comprising determining, by the processing system, a second walk-out metric for the third time period is less than a walk-out metric threshold.

### Claim 20 (depends on 19)

The method of claim 19, comprising determining, by the processing system, a third walk-out metric for the fourth time period is less than a sum of the walk-out metric threshold and the walk-out tolerance.
