# US 10,872,116 B1 · Systems, devices, and methods for contextualizing media > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,116 B1 - Document ID: US10872116B1 - Status: Granted - Kind: B1 - Application number: 16/581,584 - Filed: 2019-09-24 - Granted: 2020-12-22 - Earliest claimed: 2019-09-24 - Assignees: Timecode Archive Corp. - Applicants: Timecode Archive Corp. - Inventors: Ji Yim; Baik Hoh - Web page: https://patentgrep.com/patent/US10872116B1 ## CPC - G06F 16/65: Clustering; Classification - G06F 40/35: Discourse or dialogue representation - G06F 3/0484: for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range - G06F 3/165: {Management of the audio stream, e.g. setting of volume, audio stream path} - G06F 16/61: Indexing; Data structures therefor; Storage structures - G06F 16/635: Filtering based on additional data, e.g. user or group profiles - G06F 16/639: {using playlists} - G06F 40/30: Semantic analysis - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Disclosed herein are systems, devices, and methods for contextualizing media. In some variations, a method of organizing audio may comprise generating first graph data nodes from structured text data comprising a predetermined audio data model and generating second graph data nodes from unstructured data. The first and second graph data nodes may be associated with the audio. The one or more first graph data nodes may be linked to the one or more corresponding second graph data nodes using a natural language processing model. ## Claims ### Claim 1 A method of organizing audio, comprising: generating first graph data nodes from structured text data comprising a predetermined audio data model; processing unstructured data using a natural language processing (NLP) model to generate second graph data nodes, wherein the first and second graph data nodes are associated with the audio; and linking the one or more first graph data nodes to the one or more corresponding second graph data nodes using the NLP model. ### Claim 2 (depends on 1) The method of claim 1, further comprising: processing the second graph data nodes using the NLP model to determine one or more relationships between the first and second graph data nodes, wherein linking is based on the one or more relationships. ### Claim 3 (depends on 2) The method of claim 2, further comprising: processing the second graph data nodes using the NLP model to generate a plurality of keywords; associating the plurality of keywords with a respective word vector; and calculating a similarity between the second graph data nodes based on a similarity between each of the word vectors. ### Claim 4 (depends on 1) The method of claim 1, wherein the unstructured data comprises image data. ### Claim 5 (depends on 1) The method of claim 1, further comprising: computing similarity between the second graph data nodes; linking the second graph data nodes based on the similarity; and generating a narrative associated with the audio based at least on the similarity. ### Claim 6 A method of providing an audio program, comprising: playing one or more songs of the audio program; providing a narrative comprising one or more sentences of unstructured data associated with one or more of the songs of the audio program in response to the one or more songs being played; sequentially accompanying one or more of the songs being played with the narrative spoken by a virtual host, wherein providing the narrative is based at least on user activity and preferences; receiving the user activity using a conversation simulator on a computing device; and outputting one or more of the narrative using a natural language generation model and a suggested song using the conversation simulator in response to the user activity. ### Claim 7 (depends on 6) The method of claim 6, wherein the virtual host comprises a set of configurable voice characteristics. ### Claim 8 (depends on 6) The method of claim 6, wherein the virtual host comprises a plurality of voices. ### Claim 9 (depends on 6) The method of claim 6, wherein the narrative comprises one or more of a response to user activity, music, news, traffic, weather, events, and advertisements. ### Claim 10 (depends on 6) The method of claim 6, wherein the user activity comprises one or more of time and user geolocation. ### Claim 11 (depends on 6) The method of claim 6, wherein the narrative comprises an image displayed on a user interface. ### Claim 12 (depends on 6) The method of claim 6, wherein the conversation simulator comprises a natural language processing model and the natural language generation model. ### Claim 13 (depends on 6) The method of claim 6, further comprising providing a chatroom comprising a plurality of users simultaneously playing one or more of the songs and the narrative. ### Claim 14 (depends on 6) The method of claim 6, further comprising providing a graphical user interface for independent playback selection of one or more of the songs and the narrative comprising unstructured data to a playlist. ### Claim 15 (depends on 6) The method of claim 6, further comprising generating a shared playlist for a plurality of users, the shared playlist comprising the narrative and the song. ### Claim 16 (depends on 15) The method of claim 15, wherein the shared playlist is based on one or more of physical proximity of at least two users and online activity. ### Claim 17 (depends on 6) The method of claim 6, further comprising: generating the narrative from graph data; and updating the graph data based on crowd-sourced input. ### Claim 18 A method of displaying a graphical user interface for a virtual radio, comprising: displaying a graphical representation of a media player and search interface on a display; processing user input to the search interface; and displaying a narrative associated with a song being played by the media player in response to the user input, the narrative comprising one or more sentences generated from unstructured graph data. ### Claim 19 (depends on 18) The method of claim 18, further comprising displaying a graphical representation of a chatroom for a plurality of users simultaneously playing the song. ### Claim 20 (depends on 18) The method of claim 18, further comprising displaying a graphical representation of a playlist editor for independent playback selection of the song and the narrative in a playlist. ### Claim 21 (depends on 18) The method of claim 18, wherein the narrative comprises a first narrative, and the method further comprises displaying a graphical representation of a second narrative related to the first narrative. ### Claim 22 (depends on 18) The method of claim 18, further comprising displaying a graphical representation of a suggested song based on the narrative. ### Claim 23 A method of providing an audio program, comprising: playing one or more songs of the audio program; providing a narrative comprising one or more sentences of unstructured data associated with one or more of the songs of the audio program in response to the one or more songs being played; sequentially accompanying one or more of the songs being played with the narrative spoken by a virtual host generating graph data associated with the one or more songs based on the user activity of a plurality of users in response to playing the audio program and the narrative in a chatroom; and processing the graph data using a natural language processing model. ### Claim 24 (depends on 23) The method of claim 23, wherein the virtual host comprises a set of configurable voice characteristics. ### Claim 25 (depends on 23) The method of claim 23, wherein the virtual host comprises a plurality of voices. ### Claim 26 (depends on 23) The method of claim 23, wherein the narrative comprises one or more of a response to user activity, music, news, traffic, weather, events, and advertisements. ### Claim 27 (depends on 23) The method of claim 23, wherein the user activity comprises one or more of time and user geolocation. ### Claim 28 (depends on 23) The method of claim 23 wherein the narrative comprises an image displayed on a user interface. ### Claim 29 (depends on 23) The method of claim 23, wherein the conversation simulator comprises a natural language processing model and the natural language generation model. ### Claim 30 (depends on 23) The method of claim 23, further comprising providing a chatroom comprising a plurality of users simultaneously playing one or more of the songs and the narrative.