Generating tags for a digital video
US-2020336802-A1 · Oct 22, 2020 · US
US12566792B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12566792-B2 |
| Application number | US-202318837171-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 20, 2023 |
| Priority date | Feb 21, 2022 |
| Publication date | Mar 3, 2026 |
| Grant date | Mar 3, 2026 |
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.
Embodiments of the present disclosure provide a method, apparatus, device, storage medium, and program for information processing. The method includes: obtaining a first multimedia information set that is to be processed and includes a plurality of first multimedia information; obtaining reference information that includes a plurality of reference multimedia identifiers, one of the reference multimedia identifiers indicating a reference multimedia information set that includes a plurality of reference multimedia information; determining a multimedia identifier to be selected according to the first multimedia information set, where a matching degree between a multimedia feature corresponding to a reference multimedia information set indicated by the multimedia identifier to be selected and a multimedia feature corresponding to the first multimedia information set satisfies a predetermined condition; and determining, according to the multimedia identifier to be selected, a target multimedia identifier corresponding to the first multimedia information set.
Opening claim text (preview).
What is claimed is: 1 . A method of automatically generating identifiers for multimedia information sets, comprising: receiving a request to automatically generate an identifier for a first multimedia information set from a user device, wherein the first multimedia information set comprises a plurality of first multimedia items; extracting features from the first multimedia information set based on receiving the request and classifying the extracted features in a plurality of dimensions to generate a first set of feature labels corresponding to the first multimedia information set; extracting features from each of a plurality of reference multimedia information sets stored in a library and classifying the extracted features in the plurality of dimensions to generate a plurality of sets of reference feature labels, wherein each of the plurality of reference multimedia information sets corresponds to one of a plurality of reference multimedia identifiers, wherein each of the plurality of sets of reference feature labels corresponds to one of the plurality of reference multimedia identifiers, and wherein each of the plurality of reference multimedia information sets comprises a plurality of reference multimedia items; computing a matching degree between the first set of feature labels and each of the plurality of sets of reference feature labels; selecting at least one multimedia identifier from the plurality of reference multimedia identifiers based on determining that the matching degree between the first set of feature labels and the set of reference feature labels corresponding to the selected at least one multimedia identifier satisfies a predetermined condition; and segmenting the selected at least one multimedia identifier into a plurality of terms and combining at least a portion of the plurality of terms to determine the identifier for the first multimedia information set. 2 . The method of claim 1 , wherein selecting the at least one multimedia identifier from the plurality of reference multimedia identifiers comprises: determining a plurality of reference feature labels, according to the plurality of sets of reference feature labels, a repeated feature label being absent in the plurality of reference feature labels; determining, according to the respective reference multimedia identifiers and the plurality of sets of reference feature labels, a set of reference multimedia identifiers corresponding to each of the reference feature labels; and determining the at least one multimedia identifier, from the plurality of reference multimedia identifiers according to the first set of feature labels and the set of reference multimedia identifiers corresponding to each of the reference feature labels. 3 . The method of claim 2 , wherein selecting the at least one multimedia identifier from the plurality of reference multimedia identifiers comprises: determining at least one target feature label from the plurality of reference feature labels according to the first set of feature labels, the target feature label belonging to the first set of feature labels; and determining the at least one multimedia identifier to be selected, according to the set of reference multimedia identifiers corresponding to the at least one target feature label. 4 . The method of claim 1 , wherein combining at least the portion of the plurality of terms comprises: combining the plurality of terms corresponding to the at least one multimedia identifier to be selected to obtain a plurality of recombined multimedia identifiers, the method further comprising: modifying the plurality of recombined multimedia identifiers to obtain a plurality of modified multimedia identifiers; and determining the target multimedia identifier from the plurality of modified multimedia identifiers. 5 . The method of claim 4 , wherein modifying the recombined multimedia identifiers to obtain the modified multimedia identifiers comprises for any one of the recombined multimedia identifiers: performing at least one of the following on the recombined multimedia identifier to obtain the modified multimedia identifiers: deleting a first predetermined term in the recombined multimedia identifiers; replacing a predetermined type of terms in the recombined multimedia identifier, the predetermined type including a person name and/or a place name; updating a term incompliant to a grammar in the recombined multimedia identifier; performing synonym replacement on a term in the recombined multimedia identifier; and deleting a recombined multimedia identifier with a number of characters less than or equal to a predetermined threshold, in the recombined multimedia identifier. 6 . The method of claim 4 , wherein determining the target multimedia identifier from the plurality of modified multimedia identifiers comprises: determining a target reference multimedia identifier from the plurality of reference multimedia identifiers, a matching degree between a multimedia feature corresponding to the target reference multimedia identifier and the multimedia feature corresponding to the first multimedia information set being highest; obtaining a similarity degree between each of the modified multimedia identifiers and the target reference multimedia identifier; and determining the target multimedia identifier from the plurality of modified multimedia identifiers according to similarity degrees between respective modified multimedia identifiers of the modified multimedia identifiers and the target reference multimedia identifier. 7 . The method of claim 6 , wherein determining the target multimedia identifier from the plurality of modified multimedia identifiers according to the similarity degrees between the respective modified multimedia identifiers and the target reference multimedia identifier comprises: sorting the plurality of modified multimedia identifiers, according to a descending order of the similarity degrees between the respective modified multimedia identifiers and the target reference multimedia identifier; and determining first M modified multimedia identifiers after the sorting, as target multimedia identifiers, M being an integer greater than or equal to 1. 8 . The method of claim 1 , wherein each of the plurality of first multimedia items is any one of: an audio, a text, an image, or a video. 9 . The method of claim 1 , wherein each of the plurality of first multimedia items is a song, and where the plurality of dimensions comprises one or more of a style, an emotion, and a type. 10 . The method of claim 1 , after determining the identifier for the first multimedia information set, further comprising: setting the identifier to be an identifier of the first multimedia information set; or displaying the identifier; or sending the identifier to a predetermined device. 11 . An electronic device, comprising: a processor and a memory; the memory storing computer executable instructions; and the processor executing the computer executable instructions to implement acts comprising: receiving a request to automatically generate an identifier for a first multimedia information set from a user device, wherein the first multimedia information set comprises a plurality of first multimedia items; extracting features from the first multimedia information set based on receiving the request and classifying the extracted features in a plurality of dimensions to generate a first set of feature labels corresponding to the first multimedia information set; extracting features from each of a plurality of reference multimedia information sets stored in a library and classifying the extracted features in the pluralit
using playlists · CPC title
Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.