Multimedia linked timestamp validation detection

US11928153B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-11928153-B2
Application numberUS-202217697048-A
CountryUS
Kind codeB2
Filing dateMar 17, 2022
Priority dateMar 17, 2022
Publication dateMar 12, 2024
Grant dateMar 12, 2024

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A computer-implemented method, including: receiving, by a computing device, a post referring to a multimedia content; identifying, by the computing device, a time in the post; generating, by the computing device, a validity score based on analyzing contextual data of the time in the post; determining, by the computing device, a correlation between the time in the post to the multimedia content based on the validity score; and publishing, by the computing device, the post with an interactive link to a corresponding time of the multimedia content based on the determined correlation.

First claim

Opening claim text (preview).

What is claimed is: 1. A computer-implemented method, comprising: receiving, by a computing device, a post referring to a multimedia content; identifying, by the computing device, a time in the post by analyzing a text in the post including dates and/or times embedded in the post; generating, by the computing device, a validity score based on analyzing contextual data utilizing a machine learning model of the time in the post and contextual data of a corresponding time in the multimedia content, the validity score indicating whether the time in the post is a valid timestamp; determining, by the computing device, a correlation between the time in the post to the corresponding time in the multimedia content based on the validity score, the correlation indicating the time as a relative time that indicates the time in the post be used as an interactive link to provide a pointer to the corresponding time in the multimedia content; and publishing, by the computing device, the post with the interactive link to the corresponding time of the multimedia content based on the determined correlation. 2. The computer-implemented method of claim 1 , wherein the analyzing of the contextual data of the time in the post comprises scoring based on one or more selected from the group consisting of: multimedia content processing that determines a relationship between the time in the post and the multimedia content; natural language processing of the post; historical comparison of the post to other posts; time magnitude comparison of the time in the post to a completed playback time of the multimedia content; and comparison of the time in the post to another time in the post. 3. The computer-implemented method of claim 2 , wherein the natural language processing includes Bidirectional Encoder Representation from Transformers (BERT) model processing. 4. The computer-implemented method of claim 2 , wherein the multimedia content processing includes multimedia content processing of the multimedia content at and near the time to extract entities within the multimedia content to which the post may refer. 5. The computer-implemented method of claim 2 , further comprising: determining a difference between a time format of the multimedia content and a time format of the time in the post. 6. The computer-implemented method of claim 2 , wherein the natural language processing compares extracted elements from the post to metadata of the multimedia content. 7. The computer-implemented method of claim 2 , wherein the scoring includes relative time scores determined based on the time in the post being a valid timestamp that indicates the time in the post be used as the interactive link to provide the pointer to the corresponding time in the multimedia content, and absolute time scores determined based on the time in the post being an absolute time that indicates the time in the post is an actual time. 8. The computer-implemented method of claim 1 , further comprising: requesting, by the computing device, a timestamp validity input from a posting user of the post or from other users of the post. 9. The computer-implemented method of claim 1 , further comprising: receiving, by the computing device, a timestamp validity input from other users of the post indicating a triggering event to re-evaluate the identified time for the correlation. 10. The computer-implemented method of claim 1 , wherein the multimedia content comprises a video, the post comprises a comment about the video, and the link comprises a user-selectable link to the time in the video. 11. A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to: receive a post referring to a video; identify a time in the post; generate a validity score based on analyzing contextual data of the time in the post and a corresponding time in the video, the validity score indicating whether the time in the post is a valid timestamp; responsive to determining a correlation between the time in the post to a corresponding time of the video based on the validity score, publish the post with an interactive link to the corresponding time in the video, the correlation indicating the time as a relative time; and responsive to determining a lack of the correlation between the time in the post to the corresponding time of the video based on the validity score, publish the time in the post as text without the interactive link, the lack of the correlation indicating the time in the post is an absolute time and should not be linked to the video. 12. The computer program product of claim 11 , wherein the analyzing of the contextual data of the time in the post comprises scoring based on one or more selected from the group consisting of: video processing that determines a relationship between the time in the post and the video; natural language processing of the post; historical comparison of the post to other posts; time magnitude comparison of the time in the post to a completed playback time of the video; and comparison of the time in the post to another time in the post. 13. The computer program product of claim 12 , wherein the natural language processing includes Bidirectional Encoder Representation from Transformers (BERT) model processing. 14. The computer program product of claim 12 , wherein the video analysis includes video processing of the video at and near the time in the post to extract entities within the video to which the post may refer. 15. The computer program product of claim 12 , wherein the program instructions are executable to: determine a difference between a time format of the video and a time format of the time in the post. 16. A system comprising: a processor, a computer readable memory, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to: receive a post referring to a multimedia content; identify a time in the post, wherein the time is embedded in the post; analyze contextual data of the time in the post, the analyzing including: scoring the contextual data of the time in the post indicating whether the time in the post is a valid timestamp and a corresponding time in the multimedia content, and weighting the scored contextual data to generate a validity score, the validity score indicating whether the time in the post is a valid timestamp; determine a lack of correlation between the time in the post to a corresponding time in the multimedia content based on the validity score, the lack of the correlation indicating the time as an absolute time; and publish the time in the post as text without an interactive link. 17. The system of claim 16 , wherein the scoring is based on one or more selected from the group consisting of: multimedia content processing that determines a relationship between the time in the post and the multimedia content; natural language processing of the post; historical comparison of the post to other posts; time magnitude comparison of the time in the post to a completed playback time of the multimedia content; and comparison of the time in the post to another time in the post. 18. The system of claim 17 , wherein the natural language processing includes Bidirectional Encoder Representation from Transformers (BERT) model processing. 19. The system of c

Assignees

Inventors

Classifications

  • G06F16/748Primary

    Hypervideo (linking data to content, e.g. by linking an URL to a video object in the context of video distribution systems H04N21/858) · CPC title

  • Details of hyperlinks; Management of linked annotations · CPC title

  • URL specific, e.g. using aliases, detecting broken or misspelled links · CPC title

  • Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

  • G06F16/43Primary

    Querying · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US11928153B2 cover?
A computer-implemented method, including: receiving, by a computing device, a post referring to a multimedia content; identifying, by the computing device, a time in the post; generating, by the computing device, a validity score based on analyzing contextual data of the time in the post; determining, by the computing device, a correlation between the time in the post to the multimedia content …
Who is the assignee on this patent?
Kyndryl Inc
What technology area does this patent fall under?
Primary CPC classification G06F16/748. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Mar 12 2024 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 9 related publications on this page (citations in our corpus or others sharing the same primary CPC).