Systems and methods for disambiguating a voice search query
US-2024005923-A1 · Jan 4, 2024 · US
US11526547B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11526547-B2 |
| Application number | US-201916404486-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 6, 2019 |
| Priority date | Sep 7, 2012 |
| Publication date | Dec 13, 2022 |
| Grant date | Dec 13, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A device includes a processor that is configured to identify a base topic of a personalized media stream and to identify a first media item based on first data. The first data is assigned a first weighting based on an identified level of familiarity associated with the first media item and an identified level of popularity of the first media item in another personalized media stream. The processor is configured to build a collection of candidate media items that includes the first media item and a second media item and to order the collection of candidate media items to form the personalized media stream. Ordering the collection includes ordering the first media item within the collection based on the first weighting. The processor is configured to initiate transmission of the first media item to a client device for playback based on ordering of the first media item within the collection.
Opening claim text (preview).
What is claimed is: 1. A device comprising: a communication interface configured to communicate with a client device; and a processor configured to: identify a base topic of a personalized media stream; obtain first data from a first data service; obtain second data from a second data service, wherein the first data and the second data include data characterizing at least one of relationships between artists or relationships between media items; build a first collection of candidate media items using an automated media selection model that selects candidate media items from a media library without human intervention, wherein the automated media selection model selects the candidate media items based on the first data from the first data service indicating that a first media item is associated with the base topic; determine, based on a first-accuracy associated with the first data from the first data service relative to a second accuracy associated with the second data from the second data service, that the first collection of candidate media items is deficient; apply a media selection override in response to determining that the first collection of candidate media items is deficient, wherein applying a media selection override includes: building a second collection of candidate media items based on the second data from the second data service; and adjusting the automated media selection model to use the media selection override when building future collections of candidate media items; and initiate transmission, via the communication interface, of the second collection of candidate media items to the client device. 2. The device of claim 1 , wherein building the first collection of candidate media items includes applying a weighting based on a first integrity value associated with the first data from the first data service. 3. The device of claim 1 , wherein the processor is further configured to build the second collection of candidate media items to include second media items selected from a media library based on a determination that a second media item is associated with the base topic based on the second data from the second data service, wherein the second media item identified based on a similarity of the second media item to the base topic satisfying a similarity threshold. 4. The device of claim 3 , wherein the first data service and the second data service are associated with different types of media categorization data, and wherein the media categorization data includes at least two of broadcast radio spin counts, acoustic analysis data, data derived from analysis of web pages, commercially-sourced media metadata, or data that indicates public user interaction with media-related entities. 5. The device of claim 1 , wherein the processor is further configured to, subsequent to transmission of the second collection of candidate media items to the client device: identify a media item associated with the base topic based on third data from a third data service based on an integrity value associated with the third data service; and initiate transmission of the media item to the client device for playback. 6. The device of claim 5 , wherein the processor is further configured to: generate a graphical user interface (GUI) including a similarity interface element and a display element that identifies at least one media item included in the second collection of media items; initiate transmission of the GUI, via the communications interface, to the client device; and receive, via the communications interface, a user update of the similarity interface element during playback of the at least one media item, the user update indicating a user selection of a similarity threshold. 7. The device of claim 1 , wherein the device is further configured to: build the first collection of candidate media items based on a level of influence of a particular type of media categorization data associated with the first data from the first data service. 8. The device of claim 1 , wherein the device is further configured to: order the second collection of candidate media items by changing an initial order of the second collection of candidate media items to place the candidate media items into regulatory or licensing compliance. 9. A method comprising: obtaining first data from a first data service; obtaining second data from a second data service, wherein the first data and the second data include data characterizing at least one of relationships between artists or relationships between media items; generating, at a processing device including a processor and associated memory, a collection of candidate media items using an automated media selection model that selects candidate media items from a media library without human intervention, wherein the automated media selection model selects the candidate media items based on a based on the first data from the first data service indicating that a first media item is associated with a base topic; determining, based on a first accuracy associated with the first data from the first data service relative to a second accuracy associated with the second data from the second data service, that the collection of candidate media items is deficient; applying a media selection override in response to determining that the collection of candidate media items is deficient, wherein applying a media selection override includes: building a second collection of candidate media items based on the second data from the second data service; and adjusting the automated media selection model to use the media selection override when building future collections of candidate media items; and initiating transmission of the second collection of candidate media items to a client device. 10. The method of claim 9 , further comprising: generating, at the device, a graphical user interface (GUI) including a similarity interface element and a display element that identifies the first media item; initiating transmission of the GUI to the client device; and receiving, at the device from the client device, a user update of the similarity interface element during playback of the first media item, the user update indicating a user selection of a second similarity threshold. 11. The method of claim 9 , wherein building the second collection of candidate media items further comprises biasing a play order of the second collection of candidate media items according to artist similarity to the base topic.
using ranking · CPC title
Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title
Filtering based on additional data, e.g. user or group profiles · CPC title
Network streaming of media packets · CPC title
using playlists · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.