Content knowledge query generation through computer analysis
In an approach to improve knowledge content query generation, embodiments identify one or more drift points based on implicit user feedback-based assessment and a user experience to generate one or more knowledge content queries of different complexity from a multi-media file. Further, embodiments adjust a threshold for the one or more drift points to generate different variations of the one or more knowledge content queries and perform iterative refinement on the one or more knowledge queries based on one or more previous iteration evaluations. Additionally, embodiments generate the one or more knowledge content queries in different modalities based on the multi-media file and the threshold for the one or more drift points.
1 . A computer-implemented method for generating a knowledge content query associated with a multi-media file, the computer-implemented method comprising:
identifying, by a computing device, one or more drift points based on implicit user feedback-based assessment and a user experience to generate one or more knowledge content queries of different complexity from the multi-media file by detecting changes in objects, background, text, audio context, or object movement between extracted frames of the multi-media file to identify drift points;
determining a learned threshold for the one or more drift points based on drift-calculation metrics derived from the frame-level semantics;
adjusting a threshold for the one or more drift points to generate different variations of the one or more knowledge content queries;
performing iterative refinement on the one or more knowledge queries based on one or more previous iteration evaluations, wherein performing iterative refinement comprises:
regenerating updated knowledge content queries until a predetermined learning threshold score is satisfied;
generating the one or more knowledge content queries in different modalities based on the multi-media file and the threshold for the one or more drift points;
generating and outputting the one or more knowledge queries to a user based on the one or more knowledge content queries, wherein the one or more knowledge queries comprise: a video puzzle, textual puzzle, and image puzzle; and
executing and displaying a final textual puzzle and a final image puzzle to the user through a computer-based user interface, wherein evaluation and puzzle refinement from the user is received through the computer-based user interface.
2 . The computer-implemented method of claim 1 , further comprising:
extracting one or more frames from the multi-media file;
executing frame level semantics on the one or more extracted frames.
3 . The computer-implemented method of claim 1 , further comprising:
outputting the one or more knowledge content queries to a user, wherein the one or more knowledge content queries are a responsive prompt that query the user to answer or solve a prompt in the one or more generated knowledge queries.
4 . The computer-implemented method of claim 1 , further comprising:
evaluating one or more received responses from a user against one or more previously generated and scored knowledge content queries, predetermined thresholds, or predetermined learning objectives associated with the multi-media file.
5 . The computer-implemented method of claim 1 , further comprising:
determining a received response from a user, associated with the one or more knowledge content queries, does not satisfy a predetermined learning threshold score.
6 . The computer-implemented method of claim 1 , further comprising:
responsive to determining a received responses to the one or more knowledge content queries satisfies a learning threshold score, storing the received responses and the one or more knowledge content queries.
7 . The computer-implemented method of claim 1 , wherein adjusting the threshold further comprises:
dynamically adjusting a learning threshold and a complexity of the one or more generated knowledge content queries by refining one or more of the points based on a received user feedback, the user experience, or a user input.
8 . A computer system for generating a knowledge content query associated with a multi-media file, the computer system comprising:
one or more computer processors;
one or more computer readable storage devices; and
program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising:
program instructions to identify, by a computing device, one or more drift points based on implicit user feedback-based assessment and a user experience to generate one or more knowledge content queries of different complexity from the multi-media file by detecting changes in objects, background, text, audio context, or object movement between extracted frames of the multi-media file to identify drift points;
program instructions to determine a learned threshold for the one or more drift points based on drift-calculation metrics derived from the frame-level semantics;
program instructions to adjust a threshold for the one or more drift points to generate different variations of the one or more knowledge content queries;
program instructions to perform iterative refinement on the one or more knowledge queries based on one or more previous iteration evaluations, wherein performing iterative refinement comprises:
regenerating updated knowledge content queries until a predetermined learning threshold score is satisfied;
program instructions to generate the one or more knowledge content queries in different modalities based on the multi-media file and the threshold for the one or more drift points;
program instructions to generate and output the one or more knowledge queries to a user based on the one or more knowledge content queries, wherein the one or more knowledge queries comprise: a video puzzle, textual puzzle, and image puzzle; and
program instructions to execute and display a final textual puzzle and a final image puzzle to the user through a computer-based user interface, wherein evaluation and puzzle refinement from the user is received through the computer-based user interface.
9 . The computer system of claim 8 , further comprising:
program instructions to extract one or more frames from the multi-media file;
executing frame level semantics on the one or more extracted frames.
10 . The computer system of claim 8 , further comprising:
program instructions to output the one or more knowledge content queries to a user, wherein the one or more knowledge content queries are a responsive prompt that query the user to answer or solve a prompt in the one or more generated knowledge queries.
11 . The computer system of claim 8 , further comprising:
program instructions to evaluate one or more received responses from a user against one or more previously generated and scored knowledge content queries, predetermined thresholds, or predetermined learning objectives associated with the multi-media file.
12 . The computer system of claim 8 , further comprising:
program instructions to determine a received response from a user, associated with the one or more knowledge content queries, does not satisfy a predetermined learning threshold score.
13 . The computer system of claim 8 , further comprising:
responsive to determining a received responses to the one or more knowledge content queries satisfies a learning threshold score, program instructions to store the received responses and the one or more knowledge content queries.
14 . The computer system of claim 8 , wherein adjusting the threshold further comprises:
program instructions to dynamically adjust a learning threshold and a complexity of the one or more generated knowledge content queries by refining one or more of the points based on a received user feedback, the user experience, or a user input.
15 . A computer program product for generating a knowledge content query associated with a multi-media file, the computer program product comprising:
one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to identify, by a computing device, one or more drift points based on implicit user feedback-based assessment and a user experience to generate one or more knowledge content queries of different complexity from the multi-media file by detecting changes in objects, background, text, audio context, or object movement between extracted frames of the multi-media file to identify drift points;
program instructions to determine a learned threshold for the one or more drift points based on drift-calculation metrics derived from the frame-level semantics;
program instructions to adjust a threshold for the one or more drift points to generate different variations of the one or more knowledge content queries;
program instructions to perform iterative refinement on the one or more knowledge queries based on one or more previous iteration evaluations, wherein performing iterative refinement comprises:
regenerating updated knowledge content queries until a predetermined learning threshold score is satisfied;
program instructions to generate the one or more knowledge content queries in different modalities based on the multi-media file and the threshold for the one or more drift points;
program instructions to generate and output the one or more knowledge queries to a user based on the one or more knowledge content queries, wherein the one or more knowledge queries comprise: a video puzzle, textual puzzle, and image puzzle; and
program instructions to execute and display a final textual puzzle and a final image puzzle to the user through a computer-based user interface, wherein evaluation and puzzle refinement from the user is received through the computer-based user interface.
16 . The computer program product of claim 15 , further comprising:
program instructions to extract one or more frames from the multi-media file;
executing frame level semantics on the one or more extracted frames.
17 . The computer program product of claim 15 , further comprising:
program instructions to output the one or more knowledge content queries to a user, wherein the one or more knowledge content queries are a responsive prompt that query the user to answer or solve a prompt in the one or more generated knowledge queries.
18 . The computer program product of claim 15 , further comprising:
program instructions to evaluate one or more received responses from a user against one or more previously generated and scored knowledge content queries, predetermined thresholds, or predetermined learning objectives associated with the multi-media file.
19 . The computer program product of claim 15 , further comprising:
program instructions to determine a received response from a user, associated with the one or more knowledge content queries, does not satisfy a predetermined learning threshold score.
20 . The computer program product of claim 15 , wherein adjusting the threshold further comprises:
program instructions to dynamically adjust a learning threshold and a complexity of the one or more generated knowledge content queries by refining one or more of the points based on a received user feedback, the user experience, or a user input.