# US 10,484,738 B2 · Television and method for filtering television program content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,484,738 B2 - Document ID: US10484738B2 - Status: Granted - Kind: B2 - Application number: 15/997,882 - Filed: 2018-06-05 - Published: 2019-10-17 - Granted: 2019-11-19 - Earliest claimed: 2018-04-17 - Assignees: Hon Hai Precision Industry Co., Ltd. - Applicants: Hon Hai Precision Industry Co., Ltd. - Inventors: Jung-Yi Lin; Chin-Pin Kuo - Web page: https://patentgrep.com/patent/US10484738B2 ## CPC - H04N 21/44008: {involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59)} - H04N 21/4542: {Blocking scenes or portions of the received content, e.g. censoring scenes} - G06N 20/00: Machine learning - G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)} - H04N 21/45457: {applied to a time segment} - H04N 21/4666: {using neural networks, e.g. processing the feedback provided by the user} - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method for filtering a television program includes capturing preview content of a television program, analyzing the preview content to generate a specific image model, determining, when the television program is displayed, whether the specific image model is displayed in the television program, and prompting a user to take a specific action when the specific image model is displayed in the television program. The preview content is captured within a preset time duration before the television program is displayed on the television. ## Claims ### Claim 1 A non-transitory storage medium having stored thereon instructions that, when executed by at least one processor of a television, causes the at least one processor to execute the instructions of a method for filtering a television program, the method comprising: capturing preview content of a television program within a preset time duration before the television program is displayed on the television; analyzing the preview content to generate a specific image model; determining, when the television program is displayed, whether the specific image model is displayed in the television program; and prompting a user to take a specific action when the specific image model is displayed in the television program. ### Claim 2 (depends on 1) The non-transitory storage medium of claim 1, wherein the specific image model is determined to be displayed in the television program by comparing contents of the television program to the specific image model and determining that a similarity of the contents of the television program to the specific image model is greater than or equal to a preset value. ### Claim 3 (depends on 1) The non-transitory storage medium of claim 1, wherein the specific image model is generated by analyzing one or more frames of the preview content within the preset time duration and grouping similar frames together into a group to generate the specific image model. ### Claim 4 (depends on 3) The non-transitory storage medium of claim 3, wherein the preview content is analyzed by a machine learning algorithm. ### Claim 5 A method for filtering a television program, the method comprising: capturing preview content of a television program within a preset time duration before the television program is displayed on the television; analyzing the preview content to generate a specific image model; determining, when the television program is displayed, whether the specific image model is displayed in the television program; and prompting a user to take a specific action when the specific image model is displayed in the television program. ### Claim 6 (depends on 5) The method of claim 5, wherein the specific image model is determined to be displayed in the television program by comparing contents of the television program to the specific image model and determining that a similarity of the contents of the television program to the specific image model is greater than or equal to a preset value. ### Claim 7 (depends on 5) The method of claim 5, wherein the specific image model is generated by analyzing one or more frames of the preview content within the preset time duration and grouping similar frames together into a group to generate the specific image model. ### Claim 8 (depends on 7) The method of claim 7, wherein the preview content is analyzed by a machine learning algorithm. ### Claim 9 A television comprising a display and a processor, the processor configured to: capture preview content of a television program within a preset time duration before the television program is displayed on the television; analyze the preview content to generate a specific image model; determine, when the television program is displayed, whether the specific image model is displayed in the television program; and prompt a user to take a specific action when the specific image model is displayed in the television program. ### Claim 10 (depends on 9) The television of claim 9, wherein the specific image model is determined to be displayed in the television program by comparing contents of the television program to the specific image model and determining that a similarity of the contents of the television program to the specific image model is greater than or equal to a preset value. ### Claim 11 (depends on 9) The television of claim 9, wherein the specific image model is generated by analyzing one or more frames of the preview content within the preset time duration and grouping similar frames together into a group to generate the specific image model. ### Claim 12 (depends on 11) The television of claim 11, wherein the preview content is analyzed by a machine learning algorithm.