Providing question answering responses to how-to procedural questions

Patent metadata

Field	Value
Publication number	US-9852646-B2
Application number	US-201514740336-A
Country	US
Kind code	B2
Filing date	Jun 16, 2015
Priority date	Jun 16, 2015
Publication date	Dec 26, 2017
Grant date	Dec 26, 2017

Abstract

Selecting an instructional video is provided. It is determined that a query is requesting information on how to perform a procedure. A set of instructional videos are accessed corresponding to the information on how to perform the procedure. Information regarding a user of a client device that submitted the query is retrieved from at least one of a set of databases and a set of monitoring devices located on the user via a network. Physiological changes are predicted in the user's current cognitive state based on the information regarding the user retrieved from the set of databases and the set of monitoring devices. An instructional video is selected in the set of instructional videos corresponding to the information on how to perform the procedure based on the user's current cognitive state indicated in the retrieved information regarding the user of the client device.

First claim

What is claimed is:

1. A computer-implemented method for selecting an instructional video, the computer-implemented method comprising:
determining, by a computer, that a query is requesting information on how to perform a procedure;
accessing, by the computer, a set of instructional videos corresponding to the information on how to perform the procedure;
retrieving, by the computer, information regarding a user of a client device that submitted the query requesting the information on how to perform the procedure, wherein the information regarding the user of the client device is retrieved from at least one of a set of databases and a set of monitoring devices located on the user via a network;
predicting, by the computer, physiological changes in the user's current cognitive state based on the information regarding the user retrieved from the set of databases and the set of monitoring devices located on the user;
selecting, by the computer, an instructional video in the set of instructional videos corresponding to the information on how to perform the procedure based on the user's current cognitive state indicated in the retrieved information regarding the user of the client device;
analyzing, by the computer, the instructional video selected for the user that corresponds to the information on how to perform the procedure;
decomposing, by the computer, the instructional video selected for the user that corresponds to the information on how to perform the procedure into a set of procedural steps based on the analyzing;
responsive to the computer selecting a procedural step in the set of procedural steps on how to perform the procedure, determining, by the computer, whether the selected procedural step includes a sub-procedure;
responsive to the computer determining that the selected procedural step does include a sub-procedure, determining, by the computer, whether the user requires a different skill to perform the sub-procedure; and
responsive to the computer determining that the user requires the different skill to perform the sub-procedure, selecting, by the computer, an instructional video corresponding to the different skill required by the user to perform the sub-procedure based on the retrieved information regarding the user of the client device.

2. The computer-implemented method of claim 1 , wherein the computer utilizes at least one of natural language processing, scene detection, sound detection, voice recognition, facial recognition, gesture recognition, object recognition, and tag detection to analyze and decompose the instructional video.

3. The computer-implemented method of claim 1 , further comprising:
generating, by the computer, a playlist graph of selected instructional videos according to a depth-first ordering.

4. The computer-implemented method of claim 3 , further comprising:
identifying, by the computer, characteristics of the client device used by the user to display the selected instructional videos in the playlist graph.

5. The computer-implemented method of claim 4 , further comprising:
playing, by the computer, the selected instructional videos in the playlist graph according to at least one of the depth-first ordering of the playlist graph and the identified characteristics of the client device used by the user to display the selected instructional videos; and
sending, by the computer, a video signal to the client device via the network of the selected instructional videos played in the playlist graph according to the at least one of the depth-first ordering and the identified characteristics of the client device.

6. The computer-implemented method of claim 1 , further comprising:
responsive to the computer determining that a confidence level in an ability of the user to understand the information on how to perform the procedure in the instructional video is less than a predefined confidence level threshold based on received user data indicating the user's current cognitive state while the user is viewing the instructional video, pausing, by the computer, playing of the instructional video on how to perform the procedure; and
playing, by the computer, a video unrelated to the information on how to perform the procedure until the computer determines that the confidence level in the ability of the user to understand the information on how to perform the procedure in the instructional video has risen above the predefined confidence level threshold.

7. The computer-implemented method of claim 6 , further comprising:
responsive to the computer determining that the confidence level in the ability of the user to understand the information on how to perform the procedure in the instructional video is greater than the predefined confidence level threshold based on currently received user data, resuming, by the computer, the playing of the instructional video on how to perform the procedure.

8. A computer system for selecting an instructional video, the computer system comprising:
a bus system;
a storage device connected to the bus system, wherein the storage device stores program instructions; and
a processor connected to the bus system, wherein the processor executes the program instructions to:
determine that a query is requesting information on how to perform a procedure;
access a set of instructional videos corresponding to the information on how to perform the procedure;
retrieve information regarding a user of a client device that submitted the query requesting the information on how to perform the procedure, wherein the information regarding the user of the client device is retrieved from at least one of a set of databases and a set of monitoring devices located on the user via a network;
predict physiological changes in the user's current cognitive state based on the information regarding the user retrieved from the set of databases and the set of monitoring devices located on the user;
select an instructional video in the set of instructional videos corresponding to the information on how to perform the procedure based on the user's current cognitive state indicated in the retrieved information regarding the user of the client device;
analyze the instructional video selected for the user that corresponds to the information on how to perform the procedure;
decompose the instructional video selected for the user that corresponds to the information on how to perform the procedure into a set of procedural steps based on the analysis;
determine whether a selected procedural step includes a sub-procedure in response to selecting the procedural step in the set of procedural steps on how to perform the procedure;
determine whether the user requires a different skill to perform the sub-procedure in response to determining that the selected procedural step does include a sub-procedure; and
select an instructional video corresponding to the different skill required by the user to perform the sub-procedure based on the retrieved information regarding the user of the client device in response to determining that the user requires the different skill to perform the sub-procedure.

9. The computer system of claim 8 , wherein the computer system utilizes at least one of natural language processing, scene detection, sound detection, voice recognition, facial recognition, gesture recognition, object recognition, and tag detection to analyze and decompose the instructional video.

10. A computer program product for selecting an instructional video, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
det

Assignees

• IBM

Inventors

• Kozloski James R
• Pickover Clifford A
• Vukovic Maja

Classifications

• G09B5/065 Primary

  Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems · CPC title

• G09B5/02

  with visual presentation of the material to be studied, e.g. using film strip · CPC title