# US 12,120,154 B2 · Filtering video content items > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,120,154 B2 - Document ID: US12120154B2 - Status: Granted - Kind: B2 - Application number: 18/200,333 - Filed: 2023-05-22 - Published: 2023-09-14 - Granted: 2024-10-15 - Earliest claimed: 2019-07-26 - Assignees: Rovi Guides, Inc. - Applicants: Rovi Guides, Inc. - Inventors: Nishchit Mahajan; Nainika Aggarwal; Dennis Anthony Varkey; Ankur Anil Aher - Web page: https://patentgrep.com/patent/US12120154B2 ## CPC - H04L 65/1059: End-user terminal functionalities specially adapted for real-time communication - G06F 16/735: Filtering based on additional data, e.g. user or group profiles - G06F 16/7837: {using objects detected or recognised in the video content} - G06F 18/22: Matching criteria, e.g. proximity measures - G06V 10/75: Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries - G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames} - G06V 20/48: {Matching video sequences} - H04L 65/60: Network streaming of media packets - H04L 65/612: for unicast - H04L 65/764: {at the destination (reformatting of additional data in video clients H04N21/4355)} - H04L 67/1097: for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Methods and systems for filtering video content items are described herein. The system identifies a plurality of video content items that are linked to respective image content items. The system determines, for each of the plurality of video content items, whether a video content item corresponds to a respective image content item. In response to the determining, the system causes to be provided information identifying the plurality of video content items excluding video content items that do not correspond to respective image content items. ## Claims ### Claim 1 A computer-implemented method for filtering video content items comprising: receiving a request for a content item matching a criterion; identifying a preview image linked to the content item; determining whether the preview image corresponds to the content item based on determining whether the content item and the preview image depict related subject matter and by comparing a subject of the content item with a subject of the preview image using semantic processing; based on the determining that the preview image corresponds to the content item by determining that the content item and the preview image depict related subject matter and the subject of the content item matches the subject of the preview image using semantic processing, causing to be provided information identifying the content item as verified; and based on the determining that the preview image does not correspond to the content item by determining that the content item and the preview image do not depict related subject matter and the subject of the content item does not match the subject of the preview image using semantic processing, preventing the content item and the preview image from being provided for display. ### Claim 2 (depends on 1) The method of claim 1, wherein the determining whether the preview image corresponds to the content item comprises determining whether the content item and the preview image both depict a particular subject. ### Claim 3 (depends on 2) The method of claim 2, wherein the determining whether the content item and the preview image both depict the particular subject comprises determining that each object in the preview image appears in a frame of the content item. ### Claim 4 (depends on 1) The method of claim 1, wherein the determining whether the preview image corresponds to the content item comprises determining whether the preview image comprises at least a portion of a frame of the content item. ### Claim 5 (depends on 4) The method of claim 4, wherein the determining whether the preview image comprises at least the portion of the frame of the content item comprises determining that the preview image is an exact match to the frame of the content item. ### Claim 6 (depends on 1) The method of claim 1, wherein the comparing the subject of the content item with the subject of the preview image further comprises using at least one of object recognition, machine vision, audio processing, metadata, or embedded data. ### Claim 7 (depends on 1) The method of claim 1, comprising: in response to the determining that the preview image does not correspond to the content item, in addition to the preventing of the content item and the preview image from being provided for display, causing to be provided an indication that the content item has been excluded. ### Claim 8 (depends on 1) The method of claim 1, wherein the preview image comprises the at least one of a representative image, an embedded image, a textual description, an animation, or a URL. ### Claim 9 A system for filtering video content items comprising: circuitry configured to: receive to a request for a content item matching a criterion; identify a preview image linked to the content item; determine whether the preview image corresponds to the content item based on determining whether the content item and the preview image depict related subject matter and by comparing a subject of the content item with a subject of the preview image using semantic processing; based on the determining that the preview image corresponds to the content item by determining that the content item and the preview image depict related subject matter and the subject of the content item matches the subject of the preview image using semantic processing, cause to be provided information identifying the content item as verified; and based on the determining that the preview image does not correspond to the content item by determining that the content item and the preview image do not depict related subject matter and the subject of the content item does not match the subject of the preview image using semantic processing, prevent the content item and the preview image from being provided for display. ### Claim 10 (depends on 9) The system of claim 9, wherein the circuitry configured to determine whether the preview image corresponds to the content item is configured to determine whether the content item and the preview image both depict a particular subject. ### Claim 11 (depends on 10) The system of claim 10, wherein the circuitry configured to determine whether the content item and the preview image both depict the particular subject is configured to determine that each object in the preview image appears in a frame of the content item. ### Claim 12 (depends on 9) The system of claim 9, wherein the circuitry configured to determine whether the preview image corresponds to the content item is configured to determine whether the preview image comprises at least a portion of a frame of the content item. ### Claim 13 (depends on 12) The system of claim 12, wherein the circuitry configured to determine whether the preview image comprises at least the portion of the frame of the content item is configured to determine that the preview image is an exact match to the frame of the content item. ### Claim 14 (depends on 9) The system of claim 9, wherein the circuitry configured to compare the subject of the content item with the subject of the preview image is further configured to use at least one of object recognition, machine vision, audio processing, metadata, or embedded data. ### Claim 15 (depends on 9) The system of claim 9, wherein the circuitry is configured to: in response to the determining that the preview image does not correspond to the content item, in addition to the preventing of the content item and the preview image from being provided for display, cause to be provided an indication that the content item has been excluded. ### Claim 16 (depends on 9) The system of claim 9, wherein the preview image comprises the at least one of a representative image, an embedded image, a textual description, an animation, or a URL.