# US 11,122,332 B2 · Selective video watching by analyzing user behavior and video content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,122,332 B2 - Document ID: US11122332B2 - Status: Granted - Kind: B2 - Application number: 16/663,483 - Filed: 2019-10-25 - Published: 2021-04-29 - Granted: 2021-09-14 - Earliest claimed: 2019-10-25 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Feng Rong Dang; Yun Han Li; Zheng Luan Liu; Ya Qing Chen - Web page: https://patentgrep.com/patent/US11122332B2 ## CPC - H04N 21/44218: {Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV programme (methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45)} - H04N 21/4662: {characterized by learning algorithms} - G06F 16/735: Filtering based on additional data, e.g. user or group profiles - G06F 16/74: Browsing; Visualisation therefor (end-user interfaces for requesting or interacting with video content, e.g. video on demand interfaces or electronic programme guides, H04N21/472) - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - 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 21/44222: {Analytics of user selections, e.g. selection of programmes or purchase activity (monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33)} - H04N 21/4532: {involving end-user characteristics, e.g. viewer profile, preferences (monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18)} - H04N 21/4668: {for recommending content, e.g. movies} - H04N 21/47217: {for controlling playback functions for recorded or on-demand content, e.g. using progress bars, mode or play-point indicators or bookmarks (specific graphical features in visual interfaces H04N21/4312)} - H04N 21/8405: represented by keywords - H04N 21/8455: {involving pointers to the content, e.g. pointers to the I-frames of the video stream} - H04N 21/8456: {by decomposing the content in the time domain, e.g. in time segments} - G06N 3/02: Neural networks - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Aspects of the invention include selective video-watching by analyzing user behavior and video content. A non-limiting example computer-implemented method includes playing, by a processor, a target video with a pre-fetched frame. The method extracts, by the processor, a feature from the pre-fetched frame and stores, by the processor, the feature in a repository. The method provides, by the processor, a plurality of actions to a target user based on the feature stored in the repository. The method receives, by the processor, one of the plurality of actions from the target user; and performs, by the processor, the one of the plurality of actions received from the target user. ## Claims ### Claim 1 A computer-implemented method comprising: playing, by a processor, a target video with a pre-fetched frame for a target user; extracting, by the processor, a feature from the pre-fetched frame, the extracting based at least in part on image recognition applied to the pre-fetched frame and semantic analysis of a barrage comment input by a previous user when watching the target video; storing, by the processor, the feature in a repository; determining whether a frame of a previously viewed video having the feature was skipped by a previous viewer of the previously viewed video; assigning a weight to the feature based at least in part on a similarity of the target user and the previous viewer, and on a similarity of the target video and the previously viewed video; providing, by the processor, a plurality of actions to the target user based at least in part on the determining and the weight of the feature; receiving, by the processor, one of the plurality of actions from the target user; and performing, by the processor, the one of the plurality of actions received from the target user. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein extracting a feature comprises utilizing deep learning. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, further comprising calculating the similarity between the previously viewed video and the target video. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the determining comprises finding one or more similar users to the target user, the one or more similar users including the previous viewer of the video. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the providing is further based on history and real-time data about the target user. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the determining comprises retrieving a feature set for the previously viewed video, the feature set comprising the feature. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein one of the plurality of actions received from the target user includes enabling the target video to skip intelligently to a target anchor with brief verbiage to describe any skipped plot points. ### Claim 8 A system comprising: a memory having computer readable instructions; and one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising: playing a target video with a pre-fetched frame; extracting a feature from the pre-fetched frame, the extracting based at least in part on image recognition applied to the pre-fetched frame and sematic semantic analysis of a barrage comment input by a previous user when watching the target video; storing the feature in a repository; determining whether a frame of a previously viewed video having the feature was skipped by a previous viewer of the previously viewed video; assigning a weight to the feature based at least in part on a similarity of the target user and the previous viewer, and on a similarity of the target video and the previously viewed video; providing a plurality of actions to the target user based at least in part on the determining and the weight of the feature; receiving one of the plurality of actions from the target user; and performing the one of the plurality of actions received from the target user. ### Claim 9 (depends on 8) The system of claim 8, wherein extracting a feature comprises extracting using deep learning. ### Claim 10 (depends on 8) The system of claim 8, wherein the operations further comprise calculating a similarity between the previously viewed video and the target video. ### Claim 11 (depends on 8) The system of claim 8, wherein the determining comprises finding one or more similar users to the target user, the one or more similar users including the previous viewer of the video. ### Claim 12 (depends on 8) The system of claim 8, wherein the providing is further based on history and real-time data about the target user. ### Claim 13 (depends on 8) The system of claim 8, wherein the determining comprises retrieving a feature set for the previously viewed video, the feature set comprising the feature. ### Claim 14 (depends on 8) The system of claim 8, wherein one of the plurality of actions received from the target user includes enabling the target video to skip intelligently to a target anchor with brief verbiage to describe any skipped plot points. ### Claim 15 A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising: playing a target video with a pre-fetched frame; extracting a feature from the pre-fetched frame, the extracting based at least in part on image recognition applied to the pre-fetched frame and semantic analysis of a barrage comment input by a previous user when watching the target video; storing the feature in a repository; determining whether a frame of a previously viewed video having the feature was skipped by a previous viewer of the previously viewed video; assigning a weight to the feature based at least in part on a similarity of the target user and the previous viewer, and on a similarity of the target video and the previously viewed video; providing a plurality of actions to the target user based at least in part on the determining and the weight of the feature; receiving one of the plurality of actions from the target user; and performing the one of the plurality of actions received from the target user. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein extracting a feature comprises extracting using deep learning. ### Claim 17 (depends on 15) The computer program product of claim 15, wherein the operations further comprise calculating a similarity between the previously viewed video and the target video. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein the determining comprises finding one or more similar users to the target user, the one or more similar users including the previous view of the video. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein the providing is further based on history and real-time data about the target user. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein the determining comprises retrieving a feature set for the previously viewed video, the feature set comprising the feature.