PREDICTING NEED FOR GUEST ASSISTANCE BY DETERMINING GUEST BEHAVIOR BASED ON MACHINE LEARNING MODEL ANALYSIS OF VIDEO DATA

Number: 20230419729
Published: 2023-12-28
Filed: 2023-09-11
Assignee: Disney Enterprises, Inc.
Inventors: Hale; Gregory Brooks et al.
CPC: G06V40/20; G06V40/28; G06V20/41; G06V20/52; G06V40/10; G06V40/1365; G09B19/003
Verdict: Set aside guest behavior analytics, business/ops surveillance
Source: Google Patents · FreePatentsOnline

Abstract

A behavior detection platform may obtain video data of an environment including a guest and may determine a set of normal guest behaviors associated with the environment. The platform may analyze, using a first machine learning model, the video data to identify features of the guest and analyze, using a second machine learning model, the video data and the features to determine an actual guest behavior of the guest. The platform may predict, using the second machine learning model, a predicted guest behavior of the guest based on the actual guest behavior. The behavior detection platform may determine that at least one of the actual guest behavior or the predicted guest behavior is not included in the set of normal guest behaviors. The platform may cause assistance to be provided to the guest based on determining that the actual guest behavior or the predicted guest behavior are not included.

Background

BACKGROUND

Closed-circuit television (CCTV) is a system that includes video camera devices that provide signals (e.g., video feeds) to specified monitors located at a specified location. In this regard, a CCTV system differs from a broadcast television system that broadcasts signals to multiple monitors located at multiple locations. A CCTV system is typically used to perform surveillance of areas monitored by the video camera devices. SUMMARY

In some implementations, a method performed by a behavior detection platform includes obtaining video data of an environment that includes a guest; determining a set of normal guest behaviors associated with the environment; analyzing the video data, using a first machine learning model, to determine an actual guest behavior of the guest; predicting, using a second machine learning model, a predicted guest behavior of the guest, wherein the predicted guest behavior is predicted based on the actual guest behavior; determining that at least one of the actual guest behavior or the predicted guest behavior is not a normal guest behavior of the set of normal guest behaviors; and responding to the at least one of the actual guest behavior or the predicted guest behavior based on determining that the at least one of the actual guest behavior or the predicted guest behavior is not a normal guest behavior of the set of normal guest behaviors.

In some implementations, a device includes one or more processors configured to: ob

Claims

1. A method performed by a behavior detection platform, the method comprising: obtaining video data of an environment that includes a guest; determining a set of normal guest behaviors associated with the environment; analyzing, using a first machine learning model, the video data to identify keypoints of the guest; analyzing, using a second machine learning model, the video data and the keypoints to determine an actual guest behavior of the guest; predicting, using the second machine learning model, a predicted guest behavior of the guest, wherein the predicted guest behavior is predicted based on the actual guest behavior; determining that at least one of the actual guest behavior or the predicted guest behavior is not a normal guest behavior of the set of normal guest behaviors; and responding to the at least one of the actual guest behavior or the predicted guest behavior based on determining that the at least one of the actual guest behavior or the predicted guest behavior is not a normal guest behavior of the set of normal guest behaviors. || 8. A device, comprising: one or more processors configured to: obtain video data of an environment that includes a guest; analyze the video data, using a deep learning model, to identify body parts of the guest; analyze the video data and the body parts to determine an actual guest behavior of the guest; determine that the actual guest behavior is an abnormal guest behavior with respect to a set of normal guest behaviors of guests in the environment; determine that assistance is to be provided to the guest based on determining that the actual guest behavior is an abnormal guest behavior; and provide a notification indicating that assistance is to be provided to the guest based on determining that assistance is to be provided to the guest. || 16. A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to: obtain video data of an environment that includes a guest; analyze the video data using one or more object recognition techniques; determine an actual guest behavior of the guest based on analyzing the video data using the one or more object recognition techniques; determine that the actual guest behavior is not part of a set of normal guest behaviors of guests in the environment; determine that assistance is to be provided to the guest based on determining that the actual guest behavior is not part of the set of normal guest behaviors; and cause an action to be performed to provide assistance to the guest.