# US 2021/0240794 A1 · Machine learned curating of videos for selection and display > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0240794 A1 - Document ID: US20210240794A1 - Status: Published application - Kind: A1 - Application number: 17/167,127 - Filed: 2021-02-04 - Published: 2021-08-05 - Earliest claimed: 2020-02-05 - Assignees: Loop Now Technologies, Inc. - Applicants: Loop Now Technologies, Inc. - Inventors: Edwin Chiu; Stefan Backor; Shi Feng; Wu-Hsi Li; Fuhong Liu; Jerry Ting Kwan Luk; Vincent Yang - Web page: https://patentgrep.com/patent/US20210240794A1 ## CPC - 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) - G06F 16/9577: {Optimising the visualization of content, e.g. distillation of HTML documents} - G06F 16/735: Filtering based on additional data, e.g. user or group profiles - G06F 16/739: {in form of a video summary, e.g. the video summary being a video sequence, a composite still image or having synthesized frames} - G06F 16/783: using metadata automatically derived from the content - G06F 16/7834: {using audio features} - G06F 16/7844: {using original textual content or text extracted from visual content or transcript of audio data} - G06F 16/90332: {Natural language query formulation or dialogue systems} - G06F 16/972: {Access to data in other repository systems, e.g. legacy data or dynamic Web page generation} - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Techniques for video manipulation based on machine learned video curating are disclosed. Web page content is loaded, where the content includes a frame for short-form videos. The content of the web page is analyzed for textual information. A short-form video server is accessed. Short-form videos are selected from the short-form video server, where the selecting includes automatically curating the short-form videos. Adaptive learning is used for the selecting, based on a user's web page behavior. The adaptive learning includes collecting the user's web page behavior before the selecting. Automatic curating includes selecting, by a neural network, a subset of short-form videos appropriate for the web page. The web page frame is populated with the short-form videos obtained from the video server. Representations of the short-form videos are displayed within the frame on the web page. The short-form videos are auto played within the frame. ## Claims ### Claim 1 A computer-implemented method for video manipulation comprising: loading content of a web page, wherein the content includes a frame for a plurality of short-form videos; analyzing the content of the web page for textual information; accessing a short-form video server; selecting a plurality of short-form videos from the short-form video server based on the textual information, wherein the selecting includes automatically curating the plurality of short-form videos; populating the frame on the web page with the plurality of short-form videos obtained from the short-form video server; and displaying representations of the plurality of short-form videos within the frame on the web page. ### Claim 2 (depends on 1) The method of claim 1 wherein the automatic curating comprises selecting, by a neural network, a subset of the plurality of short-form videos that are appropriate for the web page. ### Claim 3 (depends on 2) The method of claim 2 wherein the automatic curating comprises machine learning. ### Claim 4 (depends on 2) The method of claim 2 wherein the automatic curating provides the subset of videos based on contextual information from the web page. ### Claim 5 (depends on 4) The method of claim 4 wherein the contextual information is based on natural language processing for audio information from the web page. ### Claim 6 (depends on 4) The method of claim 4 wherein the contextual information is based on video information from the web page. ### Claim 7 (depends on 1) The method of claim 1 wherein the automatic curating is based on a long short-term memory model which tracks recent behavior by a user accessing the web page. ### Claim 8 (depends on 1) The method of claim 1 wherein the curating uses temporally weighted behaviors by a user accessing the web page. ### Claim 9 (depends on 1) The method of claim 1 wherein the frame is added to an existing web page to facilitate display of relevant short-form videos. ### Claim 10 (depends on 1) The method of claim 1 wherein the frame on the web page pulls the plurality of short-form videos from the short-form video server. ### Claim 11 (depends on 1) The method of claim 1 further comprising augmenting the textual information with metadata and performing the selecting the plurality of short-form videos based on the metadata. ### Claim 12 (depends on 11) The method of claim 11 further comprising augmenting the textual information with image information and performing the selecting the plurality of short-form videos based on the image information. ### Claim 13 (depends on 11) The method of claim 11 further comprising augmenting the textual information with themes extracted from the web page and wherein the selecting is based on ranking associations of metadata with short-form video theme information. ### Claim 14 (depends on 1) The method of claim 1 further comprising auto playing the plurality of short-form videos within the frame. ### Claim 15 (depends on 1) The method of claim 1 further comprising receiving a response to a call to action embedded within the frame on the web page. ### Claim 16 (depends on 15) The method of claim 15 further comprising providing a second plurality of short-form videos, based on the response to the call to action, from the short-form video server wherein criteria for the second plurality of short-form videos modifies the automatic curating of the plurality of short-form videos. ### Claim at position 17 17-18. (canceled) ### Claim 19 (depends on 1) The method of claim 1 further comprising using adaptive learning for the selecting, based on a user's web page behavior. ### Claim 20 (depends on 19) The method of claim 19 wherein the adaptive learning includes collecting the user's web page behavior before the selecting. ### Claim 21 (depends on 19) The method of claim 19 wherein the adaptive learning includes collecting the user's swipes and/or clicks on the web page. ### Claim 22 (depends on 21) The method of claim 21 wherein the adaptive learning includes collecting the user's swipes and/or clicks on web pages related to the web page. ### Claim 23 (depends on 19) The method of claim 19 wherein the adaptive learning comprises comparing other users' historical patterns of web page behavior with the user's web page behavior. ### Claim 24 (depends on 19) The method of claim 19 wherein the adaptive learning combines the user's web page behavior with contextual information from the web page. ### Claim 25 (depends on 19) The method of claim 19 wherein the adaptive learning includes demographic data about the user. ### Claim 26 (depends on 19) The method of claim 19 further comprising an opting-in by the user to collect additional web page behavior. ### Claim 27 (depends on 26) The method of claim 26 wherein the additional web page behavior includes monitoring the user's web page behavior on additional websites. ### Claim 28 (canceled) ### Claim 29 A computer program product embodied in a non-transitory computer readable medium for video manipulation, the computer program product comprising code which causes one or more processors to perform operations of: loading content of a web page, wherein the content includes a frame for a plurality of short-form videos; analyzing the content of the web page for textual information; accessing a short-form video server; selecting a plurality of short-form videos from the short-form video server based on the textual information, wherein the selecting includes automatically curating the plurality of short-form videos; populating the frame on the web page with the plurality of short-form videos obtained from the short-form video server; and displaying representations of the plurality of short-form videos within the frame on the web page. ### Claim 30 A computer system for video manipulation comprising: a memory which stores instructions; one or more processors attached to the memory, wherein the one or more processors, when executing the instructions which are stored, are configured to: load content of a web page, wherein the content includes a frame for a plurality of short-form videos; analyze the content of the web page for textual information; access a short-form video server; select a plurality of short-form videos from the short-form video server based on the textual information, wherein the selecting includes automatically curating the plurality of short-form videos; populate the frame on the web page with the plurality of short-form videos obtained from the short-form video server; and display representations of the plurality of short-form videos within the frame on the web page.