Online video playback analysis and assistance

Patent metadata

Field	Value
Publication number	US-10417022-B2
Application number	US-201615184383-A
Country	US
Kind code	B2
Filing date	Jun 16, 2016
Priority date	Jun 16, 2016
Publication date	Sep 17, 2019
Grant date	Sep 17, 2019

Abstract

In an approach for providing assistance to a user viewing an online video, the computer receives an online video. The computer determines that an uncommon action occurs with the online video. The computer receives an issue based on the uncommon action. The computer receives one or more responses associated with the received issue. The computer identifies an at least one response from the received one or more responses associated with the received issue. The computer provides the identified at least one response.

First claim

What is claimed is:

1. A method for providing assistance to a user viewing an online video, the method comprising:
receiving, by one or more computer processors, an online video;
determining, by one or more computer processors, that an uncommon action occurs with an associated start and stop time within the received online video;
identifying, by one or more computer processors, prior stored viewing occurrences of the received online by another users that include stored issues, wherein the stored issues occurs within a tolerance of the identified start and stop time;
automatically determining, by one or more computer processors, an issue that the user experiences based on the stored issues within the identified prior stored viewing occurrences, wherein the issue hinders the ability of the user to understand the content of the received online video;
providing, by one or more computer processors, the automatically determined issue to the user;
receiving, by one or more computer processors, an update to the automatically determined issue;
sending, by one or more computer processors, the updated issue to one or more concurrent users wherein the concurrent users include users that are currently online and viewing the received online video and users that are currently online and previously viewed the received online video;
receiving, by one or more computer processors, one or more responses associated with the updated issue from the one or more concurrent users, wherein the one or more responses are received in real-time and provide an answer to the updated issue;
identifying, by one or more computer processors, an at least one response from the received one or more responses associated with the updated issue based on locating keywords of the updated issue within structures of the received one or more responses that determine relevance; and
providing, by one or more computer processors, the identified at least one response.

2. The method of claim 1 , further comprising;
receiving, by one or more computer processors, a submission of the automatically determined issue;
performing, by one or more computer processors, a content analysis of the automatically determined issue and stored issues from the another users, wherein the content analysis identifies one or more similar issues within the stored issues from the another users;
calculating, by one or more computer processors, a frequency of occurrence associated with the automatically determined issue, based on the performed content analysis;
determining, by one or more computer processors, whether the frequency of occurrence associated with the automatically determined issue at least meets a threshold, wherein the threshold is a percentage of a total number of users for a time period that encounter the automatically determined issue and the identified one or more similar issues;
responsive to determining that the frequency of occurrence associated with the automatically determined issue at least meets the threshold, inserting, by one or more computer processors, a new caption into the received online video for a portion of the received online video associated with the determined issue, wherein the caption is based on the identified at least one response that provides the answer from the another users;
updating, by one or more computer processors, the received online video with the inserted new caption; and
storing, by one or more computer processor, the updated online video that includes the inserted new caption as the received online video.

3. The method of claim 1 , wherein determining that the uncommon action occurs further comprises:
monitoring, by one or more computer processors, individual instances of user actions with respect to the received online video for a repeating pattern, wherein the user actions includes a change to a rate of playback and a keyword search;
incrementing, by one or more computer processors, a frequency of occurrence associated with the individual instances of user actions;
determining, by one or more computer processors, whether the frequency of occurrence associated with the individual instances of user actions at least meets a threshold; and
responsive to determining that the frequency of occurrence associated with the individual instance of the user actions at least meets the threshold, identifying, by one or more computer processors, the individual instance of user actions as an uncommon action.

4. The method of claim 1 , wherein receiving one or more responses associated with the updated issue further comprises:
sending, by one or more computer processors, a request for a response to the one or more concurrent users, wherein the request for the response includes the updated issue;
receiving, by one or more computer processors, one or more responses from the identified one or more concurrent users; and
storing, by one or more computer processors, the received one or more responses.

5. The method of claim 4 , further comprising:
extracting, by one or more computer processors, one or more keywords for the determined issue;
identifying, by one or more computer processors, one or more responses associated with the received online video from memory based on natural language processing and content analysis of the one or more keywords within the determined issue;
retrieving, by one or more computer processors, one or more responses from memory that include the determined issue; and
adding, by one or more computer processors, the retrieved one or more responses from memory to the received one or more responses.

6. The method of claim 4 , further comprising:
performing, by one or more computer processors, an Internet search based on the updated issue; and
adding, by one or more computer processors, the Internet search results to the received one or more responses, wherein the Internet search results include one or more of: online videos with related content, related titles, and a description that includes the extracted one or more keywords.

7. The method of claim 1 , wherein identifying the at least one response from the received one or more responses associated with the updated issue further comprises:
analyzing, by one or more computer processors, the received one or more online responses with respect to answering the updated issue;
calculating, by one or more computer processors, a probability for each instance of the analyzed one or more online responses based on the extracted one or more keywords and an associated user review rating of the each instance of the analyzed one or more online responses, wherein the probability for each instance of the analyzed one or more online responses predicts a likelihood that the each instance of the analyzed one or more online responses provides an answer to the updated issue, wherein the associated user review rating is a rating factor that indicates a usefulness of each instance of the analyzed one or more online responses as perceived by one or more prior users;
ranking, by one or more computer processors, the one or more online responses based on the calculated probability, wherein the ranking is based from a highest probability to a lowest probability; and
selecting, by one or more computer processors, at least the highest probability from the ranked one or more online responses as the at least one response.

8. The method of claim 1 , wherein determining the one or more concurrent users that are currently active at a website that includes the online video further comprises:
determining by one or more computer processors, the one or more users based on an online user that is viewing the received online video at the same time as the user and an online user that previously viewed the received online video;

Assignees

• IBM

Inventors

• Harpur Liam S
• Katzen Erik H
• Patel Sumit
• Wagner Pascal

Classifications

• H04N21/4884

  for displaying subtitles · CPC title

• H04N21/4758

  for providing answers, e.g. voting · CPC title

• H04L65/4015

  where at least one of the additional parallel sessions is real time or time sensitive, e.g. white board sharing, collaboration or spawning of a subconference · CPC title

• H04N21/658

  Transmission by the client directed to the server · CPC title

• H04N21/44008

  involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title