US-12621525-B2 - Gesture-based parental control system

Abstract

Systems and methods for presenting user-selectable options for parental control in response to detecting a triggering action by a user are disclosed. A system generates for output a first content item on a device. The system identifies a first user and a second user in proximity to the device and determines that a first gesture is performed by the first user wherein the first gesture is covering the eyes of the second user. In response to determining that the first gesture is performed, the system presents a selectable option for a user input such as (a) skipping a portion of the first content item; (b) lowering the volume; (c) removing the video of the first content item; or (d) presenting a second content item instead of presenting the first content item. In response to receiving a user input selecting the selectable option, the system performs an action corresponding to the selectable option.

Inventors

• Daina Emmanuel

Assignees

• ADEIA GUIDES INC.

Dates

Publication Date

20260505

Application Date

20240722

Claims (20)

1. 1 . A method comprising: capturing an image of a first user and a second user while the first user and the second user are consuming a first content item; determining whether the captured image depicts the first user covering eyes of the second user; after determining that the captured image depicts the first user covering the eyes of the second user, presenting in a user interface selectable options comprising at least two of (a) skipping a portion of the first content item, (b) reducing a volume for the first content item, or (c) censoring the first content item; and based at least in part on receiving, via the user interface, input selecting one of the selectable options, causing an action corresponding to the selectable option to be performed to the first content item.
2. 2 . The method of claim 1 , further comprising retrieving user profile data to determine an age of the second user.
3. 3 . The method of claim 1 , wherein determining whether the captured image depicts the first user covering the eyes of the second user comprises using gesture detection algorithms.
4. 4 . The method of claim 3 , wherein the gesture detection algorithms comprise a machine learning algorithm.
5. 5 . The method of claim 1 , wherein the selectable options are determined based at least in part on metadata associated with the first content item.
6. 6 . The method of claim 1 , wherein presenting in the user interface selectable options further comprises presenting in the user interface an option to switch to a second content item.
7. 7 . The method of claim 1 , further comprising storing user preferences based at least in part on receiving the input selecting one of the selectable options.
8. 8 . The method of claim 1 , wherein determining an age of the second user comprises analyzing visual features of the second user.
9. 9 . The method of claim 1 , wherein censoring the first content item comprises blurring, masking, or pixelating portions of the first content item.
10. 10 . The method of claim 1 further comprising detecting audio input to identify a change in presence of the first user or the second user.
11. 11 . A system comprising: a sensor configured to: capture an image of a first user and a second user while the first user and the second user are consuming a first content item; control circuitry configured to: determine whether the image captured by the sensor depicts the first user covering eyes of the second user; after determining that the captured image depicts the first user covering the eyes of the second user, present in a user interface selectable options comprising at least two of (a) skipping a portion of the first content item, (b) reducing a volume for the first content item, or (c) censoring the first content item; and based at least in part on receiving, via the user interface, input selecting one of the selectable options, cause an action corresponding to the selectable option to be performed to the first content item.
12. 12 . The system of claim 11 , wherein the control circuitry is further configured to further retrieve user profile data to determine an age of the second user.
13. 13 . The system of claim 11 , wherein the control circuitry is configured to determine whether the captured image depicts the first user covering the eyes of the second user using gesture detection algorithms.
14. 14 . The system of claim 13 , wherein the gesture detection algorithms comprise a machine learning algorithm.
15. 15 . The system of claim 11 , wherein the selectable options are determined by the control circuitry based at least in part on metadata associated with the first content item.
16. 16 . The system of claim 11 , wherein the control circuitry is configured to present in the user interface selectable options by further presenting in the user interface an option to switch to a second content item.
17. 17 . The system of claim 11 , wherein the control circuitry is further configured to store user preferences based at least in part on receiving the input selecting one of the selectable options.
18. 18 . The system of claim 11 , wherein the control circuitry is configured to determine an age of the second user by analyzing visual features of the second user.
19. 19 . The system of claim 11 , wherein the control circuitry is configured to censor the first content item by blurring, masking, or pixelating portions of the first content item.
20. 20 . The system of claim 11 , wherein the control circuitry is further configured to detect audio input to identify a change in presence of the first user or the second user.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application is a continuation of U.S. patent application Ser. No. 17/362,484, filed Jun. 29, 2021, which is hereby incorporated by reference herein in its entirety. BACKGROUND With the rapid development of media technology, numerous content items are available from a variety of sources to media consumers. However, there may be some content items that the parents may deem inappropriate for their child based on the child's age or maturity level. To address this issue, in one existing approach, content items are rated based on parental guidelines set by the industry and organizations (e.g., PG-13). Content items with certain ratings, such as R-rated content items, may be restricted to minor viewers. This approach is deficient because a local standard may not be applied throughout all of the content items that can be accessed from a variety of sources (e.g., international content), and the parents may have their own standards different from the parental guidelines set by the industry. This may require additional attention for the parents to control and restrict the access of the content items that otherwise may be accidentally viewed by their child. SUMMARY To overcome such deficiencies, methods and systems are described herein for detecting a user gesture that indicates the user's intent in restricting access to inappropriate content (e.g., censored content) by minor viewers. For example, a system receives a request to present a content item for display on a device. The system may use one or more sensors implemented on the device to determine the presence of one or more users that are in the vicinity of the device. For instance, the device may use a camera to detect that a user who is within a threshold distance from the device (e.g., TV) or may use a speaker to identify a user who is having a conversation with another user near the device while the content item is output for display. Based on the detection, the system determines that at least one user is watching the content item and retrieves user age information from user profile data. The system may store user profiles that are associated with the device or access the user profiles that are stored remotely. For example, the system may use user credentials or user data that have been received (e.g., parents setting the parental control for a child). From the user profile data, the system may determine the age of the user who is engaged with the device and who is performing the user gesture. The system also may determine the user's age based on the visual features of the user received from the sensors implemented on the device using one or more age-profiling techniques. While the family is watching the content item, if a first user (e.g., mother) performs a specific action, such as covering the eyes of another user (e.g., child) for a predetermined time period, then the system determines that the content item includes content that is inappropriate for the minor user. Any material that is harmful, violent, sensitive, or objectionable may be deemed inappropriate for users under a certain age. The parents may put their hands over the child's eyes to ensure that the child does not watch the violent portion of the content item. In some embodiments, the parents may cover their own eyes with their hands (self-blocking) or the minor users may cover their eyes with their hands if startling content is being displayed. Any of these actions may trigger temporary content restriction. Although the above-listed actions are used as exemplary triggering actions, any user-defined or system-defined gesture may be used to trigger content restriction. When such an action is performed by the user, the system analyzes the user gesture using one or more gesture detection algorithms and determines that the performed gesture triggers temporary restriction of the content item. In response to determining that the triggering gesture is performed, the system may present user-selectable options for display. The user-selectable options include: (a) skipping a portion of the content item; (b) lowering the volume; (c) removing the video of the content item and presenting only subtitles associated with the content item; or (d) presenting another content item. The list is not an exclusive list; there may be other options that can obstruct the presentation of a portion of the content item. When a user selects one of the selectable options, the system performs an action corresponding to the selection. For example, if option (a) is selected, then the system skips a portion of the content item such that a segment that is deemed inappropriate is entirely skipped, and a subsequent segment of the content item is presented for display. In some embodiments, a segment that is deemed inappropriate is fast-forwarded at a predetermined speed. A skipping amount may be selected by the user. In one embodiment, a skipping amount may be determined by the system based