# US 11,445,272 B2 · Video processing method and apparatus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,445,272 B2 - Document ID: US11445272B2 - Status: Granted - Kind: B2 - Application number: 17/263,425 - Filed: 2019-07-24 - Published: 2021-10-07 - Granted: 2022-09-13 - Earliest claimed: 2018-07-27 - Assignees: Beijing Jingdong Shangke Information Technology Co., Ltd.; Beijing Jingdong Century Trading Co., Ltd. - Applicants: Beijing Jingdong Shangke Information Technology Co, Ltd.; Beijing Jingdong Century Trading Co., Ltd. - Inventors: Junfu Wang - Web page: https://patentgrep.com/patent/US11445272B2 ## CPC - H04N 21/8549: Creating video summaries, e.g. movie trailer {(retrieval in video databases by using presentations in form of a video summary G06F16/739)} - G06F 16/735: Filtering based on additional data, e.g. user or group profiles - G06F 16/7867: {using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings} - G06F 40/30: Semantic analysis - G06N 20/00: Machine learning - H04N 21/235: Processing of additional data, e.g. scrambling of additional data or processing content descriptors - H04N 21/43074: {of additional data with content streams on the same device, e.g. of EPG data or interactive icon with a TV programme} - 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 21/4661: {Deriving a combined profile for a plurality of end-users of the same client, e.g. for family members within a home (user profiles in network data switching protocols H04L67/306)} - H04N 21/4667: {Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections} - H04N 21/4884: {for displaying subtitles} - 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 The present disclosure relates to the technical field of multimedia, and provides a video processing method and apparatus. The video processing method according to the present disclosure includes: performing semantic analysis on subtitles of a video to acquire compressed subtitles; determining a weight of each frame of images in the video based on a preset image processing strategy; acquiring a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generating a shortened video according to the shortened video images and the compressed subtitles. ## Claims ### Claim 1 A video processing method, comprising: performing semantic analysis on subtitles of a video to acquire compressed subtitles; determining a weight of each frame of images in the video based on a preset image processing strategy; acquiring a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generating a shortened video according to the shortened video images and the compressed subtitles, wherein the preset image processing strategy comprises: determining a weight assignment strategy according to a type tag of the video; and performing one or more of the following operations according to the weight assignment strategy: increasing a weight of each close-up image frame according to the weight assignment strategy; increasing a weight of each facial expression image frame according to the weight assignment strategy; or, increasing a weight of each wide-angle image frame according to the weight assignment strategy. ### Claim 2 A video processing method, comprising: performing semantic analysis on subtitles of a video to acquire compressed subtitles; determining a weight of each frame of images in the video based on a preset image processing strategy; acquiring a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generating a shortened video according to the shortened video images and the compressed subtitles, wherein the video processing method further comprises: adjusting the weight of each frame of images according to video playing behavior information of a user, and re-generating the shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to update the shortened video; or adjusting a weight of each image frame through an item-based collaborative filtering algorithm and a machine learning algorithm, and generating the shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to update the shortened video; or acquiring playing behavior information of a user on videos with a same type tag, and updating the weight assignment strategy of the user on the videos with the same type tag according to the playing behavior information of the user, adjusting a weight of each image frame in the videos with the same type tag according to the updated weight assignment strategy, and generating a user personalized shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to generate a user personalized shortened video. ### Claim 3 A video processing method, comprising: performing semantic analysis on subtitles of a video to acquire compressed subtitles; determining a weight of each frame of images in the video based on a preset image processing strategy; acquiring a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generating a shortened video according to the shortened video images and the compressed subtitles, wherein the video processing method further comprises: updating a weight assignment strategy for a type of users, according to playing behavior information of the type of users on one of a same video and videos with a same type tag; adjusting a weight of each image frame in all videos having the same type tag which corresponds to the one of the same video and the videos with the same type tag, according to a updated weight assignment strategy; and generating a user type personalized shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to generate a user type personalized shortened video. ### Claim 4 (depends on 3) The video processing method according to claim 3, further comprising: determining watching preferences of users by collecting the playing behavior information of the users; determining similarities among the users according to the watching preference information of the users; and determining the users with a similarity which exceeds a preset threshold as the same type of users. ### Claim 5 A video processing apparatus, comprising: a processor; and a memory coupled to the processor and storing instructions that when executed by the processor, cause the processor to: perform semantic analysis on subtitles of a video to acquire compressed subtitles; determine a weight of each frame of images in the video based on a preset image processing strategy; acquire a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generate a shortened video according to the shortened video images and the compressed subtitles, wherein the preset image processing strategy comprises: determining a weight assignment strategy according to a type tag of the video; and performing one or more of the following operations according to the weight assignment strategy: increasing a weight of each close-up image frame according to the weight assignment strategy; increasing a weight of each facial expression image frame according to the weight assignment strategy; or, increasing a weight of each wide-angle image frame according to the weight assignment strategy. ### Claim 6 A video processing apparatus, comprising: a processor; and a memory coupled to the processor and storing instructions that when executed by the processor, cause the processor to: perform semantic analysis on subtitles of a video to acquire compressed subtitles; determine a weight of each frame of images in the video based on a preset image processing strategy; acquire a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generate a shortened video according to the shortened video images and the compressed subtitles, wherein the memory further storing instructions that when executed by the processor, cause the processor to: adjust the weight of each frame of images according to video playing behavior information of a user, and re-generate the shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to update the shortened video; or adjust a weight of each image frame through an item-based collaborative filtering algorithm and a machine learning algorithm, and generating the shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to update the shortened video; or acquire playing behavior information of a user on videos with a same type tag, and updating the weight assignment strategy of the user on the videos with the same type tag according to the playing behavior information of the user, adjust a weight of each image frame in the videos with the same type tag according to the updated weight assignment strategy, and generate a user personalized shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to generate a user personalized shortened video. ### Claim 7 A video processing apparatus, comprising: a processor; and a memory coupled to the processor and storing instructions that when executed by the processor, cause the processor to: perform semantic analysis on subtitles of a video to acquire compressed subtitles; determine a weight of each frame of images in the video based on a preset image processing strategy; acquire a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generate a shortened video according to the shortened video images and the compressed subtitles, wherein the memory further storing instructions that when executed by the processor, cause the processor to: update a weight assignment strategy for a type of users, according to playing behavior information of the type of users on one of a same video and videos with a same type tag; adjust a weight of each image frame in all videos having the same type tag which corresponds to the one of the same video and the videos with the same type tag, according to a updated weight assignment strategy; and generate a user type personalized shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to generate a user type personalized shortened video. ### Claim 8 (depends on 7) The video processing apparatus according to claim 7, wherein the memory further storing instructions that when executed by the processor, cause the processor to: determine watching preferences of users by collecting the playing behavior information of the users; determine similarities among the users according to the watching preference information of the users; and determine the users with a similarity which exceeds a preset threshold as the same type of users. ### Claim 9 A non-transitory computer-readable storage medium storing computer instructions which, when executed by a processor, cause the processor to: perform semantic analysis on subtitles of a video to acquire compressed subtitles; determine a weight of each frame of images in the video based on a preset image processing strategy; acquire a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generate a shortened video according to the shortened video images and the compressed subtitles, wherein the non-transitory computer-readable storage medium stores computer instructions which, when executed by a processor, cause the processor to: adjust the weight of each frame of images according to video playing behavior information of a user, and re-generate the shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to update the shortened video; or acquire playing behavior information of a user on videos with a same type tag, and updating the weight assignment strategy of the user on the videos with the same type tag according to the playing behavior information of the user, adjust a weight of each image frame in the videos with the same type tag according to the updated weight assignment strategy, and generate a user personalized shortened video images according to all the image frames after the weight of each frame of images is adjusted, so as to generate a user personalized shortened video. ### Claim 10 (depends on 1) The video processing method according to claim 1, wherein the generating a shortened video comprises: determining a position of each image frame of the shortened video images in an original video time axis; determining positions of original subtitles corresponding to each compressed subtitle in the original video time axis; and synchronizing a playing progress of the shortened video images with that of the compressed subtitles according to the original video time axis, to generate the shortened video. ### Claim 11 (depends on 5) The video processing apparatus according to claim 5, wherein generating a shortened video comprises: determining a position of each image frame of the shortened video images in an original video time axis; determining positions of original subtitles corresponding to each compressed subtitle in the original video time axis; and synchronizing a playing progress of the shortened video images with that of the compressed subtitles according to the original video time axis, to generate the shortened video. ### Claim 12 (depends on 9) The non-transitory computer-readable storage medium according to claim 9, wherein generating a shortened video comprises: determining a position of each image frame of the shortened video images in an original video time axis; determining positions of original subtitles corresponding to each compressed subtitle in the original video time axis; and synchronizing a playing progress of the shortened video images with that of the compressed subtitles according to the original video time axis, to generate the shortened video.