| CPC G06F 16/93 (2019.01) [G06F 16/215 (2019.01); G06F 16/2365 (2019.01); G06F 40/174 (2020.01); G06F 40/279 (2020.01)] | 20 Claims |

|
1. A computer-implemented method, comprising:
receiving copies of notes that were originally recorded by participants, the notes corresponding to a source document;
identifying note fragments in the received copies of notes;
using one or more machine learning models to compare the identified note fragments to pages and paragraphs in the source document that the respective note fragments are located in;
merging, based at least in part on the comparison, the identified note fragments with a copy of the source document to form a pseudo-source document; and
outputting the pseudo-source document,
wherein merging the identified note fragments with the copy of the source document to form a pseudo-source document, includes:
identifying conflicting sets of note fragments; and
for each of the conflicting sets:
determining a degree of similarity between each note fragment in a given conflicting set and the respective paragraph of the source document in which the note fragment is located, and
deduplicating the note fragments in the given conflicting set based at least in part on the determined degrees of similarity.
|