# US 2019/0377956 A1 · Method and apparatus for processing video > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0377956 A1 - Document ID: US20190377956A1 - Status: Published application - Kind: A1 - Application number: 16/352,526 - Filed: 2019-03-13 - Published: 2019-12-12 - Earliest claimed: 2018-06-08 - Assignees: Beijing Baidu Netcom Science Technology Co., Ltd. - Applicants: Beijing Baidu Netcom Science and Technology Co., Ltd. - Inventors: Yehan ZHENG; Yu LUO - Web page: https://patentgrep.com/patent/US20190377956A1 ## CPC - G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44) - G06V 20/47: {Detecting features for summarising video content} - G06F 16/7837: {using objects detected or recognised in the video content} - G06F 16/7844: {using original textual content or text extracted from visual content or transcript of audio data} - 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} - G06V 20/49: {Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Embodiments of the present disclosure disclose a method and apparatus for processing a video. A specific embodiment of the method comprises: acquiring a target video and target video element information of the target video; extracting, based on the target video element information, a target video clip from the target video; obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip; and matching the keyword and with preset tag information set to obtain tag information of the target video clip, and associating and storing the target video clip and the tag information. ## Claims ### Claim 1 A method for processing a video, comprising: acquiring a target video and target video element information of the target video; extracting, based on the target video element information, a target video clip from the target video; obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip; and matching the keyword with a preset tag information set to obtain tag information of the target video clip, and associating and storing the target video clip and the tag information. ### Claim 2 (depends on 1) The method according to claim 1, wherein the target video element information is an image frame included in the target video; and the extracting, based on the target video element information, a target video clip from the target video comprises: performing, for the image frame included in the target video, image recognition on the image frame to obtain an image recognition result for the image frame; and determining a video clip comprising image frames having associated image recognition results and arranged consecutively in the target video as the target video clip; or, the target video element information is a set of text information corresponding to an image frame included in the target video; and the extracting, based on the target video element information, a target video clip from the target video comprises: extracting, for the image frame included in the target video, a target vocabulary included in the text information corresponding to the image frame; and determining a video clip comprising image frames corresponding to associated target vocabularies as the target video clip. ### Claim 3 (depends on 2) The method according to claim 2, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: determining, based on a preset corresponding relationship between the image recognition result and the keyword, the keyword corresponding to the image recognition result for the image frame included in the target video clip as the keyword of the target video clip. ### Claim 4 (depends on 2) The method according to claim 2, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: selecting, from target vocabularies corresponding to image frames included in the target video clip, a target vocabulary as the keyword of the target video clip. ### Claim 5 (depends on 1) The method according to claim 1, wherein the target video element information comprises a set of text information corresponding to an image frame included in the target video, and text introduction information for the target video, and the extracting, based on the target video element information, a target video clip from the target video comprises: determining, for the image frame included in the target video, a similarity between the text information corresponding to the image frame and the text introduction information; and determining a video clip comprising image frames associated with an image frame corresponding to a similarity greater than a preset similarity threshold as the target video clip; or, the target video element information is a set of bullet screen information corresponding to an image frame included in the target video, and the extracting, based on the target video element information, a target video clip from the target video comprises: determining, for the image frame included in the target video, a number of pieces of the bullet screen information corresponding to the image frame; and determining a video clip comprising image frames corresponding to bullet screen information and arranged consecutively in the target video as the target video clip, numbers of pieces of the bullet screen information corresponding to the image frames being greater than a preset number threshold; or, the target video element information is dubbing information of the target video, and the extracting, based on the target video element information, a target video clip from the target video comprises: performing audio recognition on the dubbing information, to obtain at least one piece of dubbing category information and a dubbing clip corresponding to the dubbing category information and included in the dubbing information, the dubbing category information representing a category of the corresponding dubbing clip; and selecting target dubbing category information from the at least one piece of dubbing category information, and determining a video clip corresponding to a dubbing clip corresponding to the target dubbing category information as the target video clip. ### Claim 6 (depends on 5) The method according to claim 5, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: extracting, for image frames included in the target video clip, target vocabularies included in text information corresponding to the image frames; and selecting, from the target vocabularies corresponding to the image frames included in the target video clip, a target vocabulary as the keyword of the target video clip. ### Claim 7 (depends on 5) The method according to claim 5, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: recognizing, for image frames included in the target video clip, bullet screen information corresponding to the image frames, to obtain bullet screen category information representing a category of the bullet screen information corresponding to the image frames as the keyword of the target video clip. ### Claim 8 (depends on 5) The method according to claim 5, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: recognizing, based on a preset corresponding relationship between the dubbing category information and an audio recognition method, the dubbing clip corresponding to the target video clip, to obtain a keyword representing a category of the dubbing clip corresponding to the target video clip as the keyword of the target video clip. ### Claim 9 (depends on 1) A method for generating recommendation information, comprising: acquiring attention information representing content paid attention to by a target user, and matching the attention information with preset tag information, the tag information being obtained according to the method in claim 1, and having a corresponding video clip; and generating, in response to determining the matching being successful, recommendation information for recommending the video clip. ### Claim 10 An apparatus for processing a video, comprising: at least one processor; and a memory storing instructions, wherein the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising: acquiring a target video and target video element information of the target video; extracting, based on the target video element information, a target video clip from the target video; obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip; and matching the keyword with a preset tag information set to obtain tag information of the target video clip, and associating and storing the target video clip and the tag information. ### Claim 11 (depends on 10) The apparatus according to claim 10, wherein the target video element information is an image frame included in the target video; and the extracting, based on the target video element information, a target video clip from the target video comprises: performing, for the image frame included in the target video, image recognition on the image frame to obtain an image recognition result for the image frame; and determining a video clip comprising image frames having associated image recognition results and arranged consecutively in the target video as the target video clip.; or, the target video element information is a set of text information corresponding to an image frame included in the target video, and the extracting, based on the target video element information, a target video clip from the target video comprises: extracting, for the image frame included in the target video, a target vocabulary included in the text information corresponding to the image frame; and determining a video clip comprising image frames corresponding to associated target vocabularies as the target video clip. ### Claim 12 (depends on 11) The apparatus according to claim 11, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: determining, based on a preset corresponding relationship between the image recognition result and the keyword, the keyword corresponding to the image recognition result for the image frame included in the target video clip as the keyword of the target video clip. ### Claim 13 (depends on 11) The apparatus according to claim 11, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: selecting, from target vocabularies corresponding to image frames included in the target video clip, a target vocabulary as a keyword of the target video clip. ### Claim 14 (depends on 10) The apparatus according to claim 10, wherein the target video element information comprises a set of text information corresponding to an image frame included in the target video, and text introduction information for the target video, and the extracting, based on the target video element information, a target video clip from the target video comprises: determining, for the image frame included in the target video, a similarity between the text information corresponding to the image frame and the text introduction information; and determining a video clip comprising image frames associated with an image frame corresponding to a similarity greater than a preset similarity threshold as the target video clip; or, the target video element information is a set of bullet screen information corresponding to an image frame included in the target video, and the extracting, based on the target video element information, a target video clip from the target video comprises: determining, for the image frame included in the target video, a number of pieces of the bullet screen information corresponding to the image frame; and determining a video clip comprising image frames corresponding to bullet screen information and arranged consecutively in the target video as the target video clip, numbers of pieces of the bullet screen information corresponding to the image frames being greater than a preset number threshold; or, the target video element information is dubbing information of the target video, and the extracting, based on the target video element information, a target video clip from the target video comprises: performing audio recognition on the dubbing information, to obtain at least one piece of dubbing category information and a dubbing clip corresponding to the dubbing category information and included in the dubbing information, the dubbing category information representing a category of the corresponding dubbing clip; and selecting target dubbing category information from the at least one piece of dubbing category information, and determine a video clip corresponding to a dubbing clip corresponding to the target dubbing category information as the target video clip. ### Claim 15 (depends on 14) The apparatus according to claim 14, wherein the dobtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: extracting, for image frames included in the target video clip, target vocabularies included in text information corresponding to the image frames; and selecting, from the target vocabularies corresponding to the image frames included in the target video clip, a target vocabulary as the keyword of the target video clip. ### Claim 16 (depends on 14) The apparatus according to claim 14, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: recognizing, for image frames included in the target video clip, the bullet screen information corresponding to the image frames, to obtain bullet screen category information representing a category of the bullet screen information corresponding to the image frames as the keyword of the target video clip. ### Claim 17 (depends on 14) The apparatus according to claim 14, wherein the obtaining, based on a preset corresponding relationship between video element information and a keyword determining method for a video clip, a keyword representing a category of the target video clip comprises: recognizing, based on a preset corresponding relationship between the dubbing category information and an audio recognition method, the dubbing clip corresponding to the target video clip, to obtain a keyword representing a category of the dubbing clip corresponding to the target video clip as a keyword of the target video clip. ### Claim 18 (depends on 1) An apparatus for generating recommendation information, comprising: at least one processor; and a memory storing instructions, wherein the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising: acquiring attention information representing content paid attention to by a target user, and matching the attention information with preset tag information, the tag information being obtained according to the method in claim 1, and having a corresponding video clip; and generating, in response to determining the matching being successful, recommendation information for recommending the video clip. ### Claim 19 (depends on 1) A non-transitory computer readable medium, storing a computer program, wherein the program, when executed by a processor, causes the processor to implement the method according to claim 1. ### Claim 20 (depends on 9) A non-transitory computer readable medium, storing a computer program, wherein the program, when executed by a processor, causes the processor to implement the method according to claim 9.