# US 2025/0220284 A1 · Optimizing automatic content recognition queries based on content understanding > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0220284 A1 - Document ID: US20250220284A1 - Status: Published application - Kind: A1 - Application number: 18/401,438 - Filed: 2023-12-30 - Published: 2025-07-03 - Earliest claimed: 2023-12-30 - Assignees: Roku, Inc. - Applicants: Roku, Inc. - Inventors: Shashank Merchant; Virginie M. Debelair; Yathindran Parthasarathy; Wim Michiels - Web page: https://patentgrep.com/patent/US20250220284A1 ## CPC - H04N 21/8456: {by decomposing the content in the time domain, e.g. in time segments} - H04N 21/2353: {specifically adapted to content descriptors, e.g. coding, compressing or processing of metadata} - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for processing, understanding, and defining media content. An example process can include receiving metadata corresponding to a media stream requested for playback by an application on a media device, wherein the media stream includes a plurality of media content items; determining, based on the metadata, one or more playback properties associated with the plurality of media content items within the media stream; identifying, based on the one or more playback properties, at least one targeted media content item from the plurality of media content items; determining a playback time for the at least one targeted media content item; and obtaining, during the playback time, a fingerprint corresponding to the at least one targeted media content item. ## Claims ### Claim 1 A system comprising: one or more memories; and at least one processor coupled to at least one of the one or more memories and configured to perform operations comprising: receive metadata corresponding to a media stream requested for playback by an application on a media device, wherein the media stream includes a plurality of media content items; determine, based on the metadata, one or more playback properties associated with the plurality of media content items within the media stream; identify, based on the one or more playback properties, at least one targeted media content item from the plurality of media content items; determine a playback time for the at least one targeted media content item; and obtain, during the playback time, a fingerprint corresponding to the at least one targeted media content item. ### Claim 2 (depends on 1) The system of claim 1, wherein to identify the at least one targeted media content item the at least one processor is configured to perform operations comprising: determine, based on the one or more playback properties, a playback duration associated with each of the plurality of media content items; and determine that the playback duration corresponding to the at least one targeted media content item is less than a threshold playback duration. ### Claim 3 (depends on 1) The system of claim 1, wherein to identify the at least one targeted media content item the at least one processor is configured to perform operations comprising: determine, based on the one or more playback properties, a uniform resource locator (URL) associated with each of the plurality of media content items. ### Claim 4 (depends on 1) The system of claim 1, wherein to identify the at least one targeted media content item the at least one processor is configured to perform operations comprising: determine an encryption state for each of the plurality of media content items, wherein the at least one targeted media content item is not encrypted. ### Claim 5 (depends on 1) The system of claim 1, wherein to identify the at least one targeted media content item the at least one processor is configured to perform operations comprising: determine that the at least one targeted media content item is not associated with closed caption content. ### Claim 6 (depends on 1) The system of claim 1, wherein the at least one processor is configured to perform operations comprising: send the fingerprint to a server configured to perform automatic content recognition on the at least one targeted media content item. ### Claim 7 (depends on 1) The system of claim 1, wherein the at least one processor is configured to perform operations comprising: disable automatic content recognition during playback of a remaining portion of the plurality of media content items that does not include the at least one targeted media content item. ### Claim 8 (depends on 1) The system of claim 1, wherein the media stream corresponds to at least one of a dynamic adaptive streaming over HTTP (DASH) format and a HTTP live streaming (HLS) format. ### Claim 9 (depends on 1) The system of claim 1, wherein the at least one processor is configured to perform operations comprising: receive an authorization to obtain the fingerprint from the application on the media device. ### Claim 10 (depends on 1) The system of claim 1, wherein the metadata corresponds to a manifest file. ### Claim 11 A computer-implemented method for processing media content, the computer-implemented method comprising: receiving metadata corresponding to a media stream requested for playback by an application on a media device, wherein the media stream includes a plurality of media content items; determining, based on the metadata, one or more playback properties associated with the plurality of media content items within the media stream; identifying, based on the one or more playback properties, at least one targeted media content item from the plurality of media content items; determining a playback time for the at least one targeted media content item; and obtaining, during the playback time, a fingerprint corresponding to the at least one targeted media content item. ### Claim 12 (depends on 11) The computer-implemented method of claim 11, wherein identifying the at least one targeted media content item further comprises: determining, based on the one or more playback properties, a playback duration associated with each of the plurality of media content items; and determining that the playback duration corresponding to the at least one targeted media content item is less than a threshold playback duration. ### Claim 13 (depends on 11) The computer-implemented method of claim 11, wherein identifying the at least one targeted media content item further comprises: determining, based on the one or more playback properties, a uniform resource locator (URL) associated with each of the plurality of media content items. ### Claim 14 (depends on 11) The computer-implemented method of claim 11, wherein identifying the at least one targeted media content item further comprises: determining an encryption state for each of the plurality of media content items, wherein the at least one targeted media content item is not encrypted. ### Claim 15 (depends on 11) The computer-implemented method of claim 11, wherein identifying the at least one targeted media content item further comprises: determining that the at least one targeted media content item is not associated with closed caption content. ### Claim 16 (depends on 11) The computer-implemented method of claim 11, further comprising: sending the fingerprint to a server configured to perform automatic content recognition on the at least one targeted media content item. ### Claim 17 (depends on 11) The computer-implemented method of claim 11, further comprising: disabling automatic content recognition during playback of a remaining portion of the plurality of media content items that does not include the at least one targeted media content item. ### Claim 18 (depends on 11) The computer-implemented method of claim 11, wherein the media stream corresponds to at least one of a dynamic adaptive streaming over HTTP (DASH) format and a HTTP live streaming (HLS) format. ### Claim 19 (depends on 11) The computer-implemented method of claim 11, further comprising: receiving an authorization to obtain the fingerprint from the application on the media device. ### Claim 20 A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising: receive metadata corresponding to a media stream requested for playback by an application on a media device, wherein the media stream includes a plurality of media content items; determine, based on the metadata, one or more playback properties associated with the plurality of media content items within the media stream; identify, based on the one or more playback properties, at least one targeted media content item from the plurality of media content items; determine a playback time for the at least one targeted media content item; and obtain, during the playback time, a fingerprint corresponding to the at least one targeted media content item.