Method and system for suggesting revisions to an electronic document

1. A method for suggesting revisions to a document-under-analysis (“DUA”) from a seed database, the seed database comprising a plurality of original texts each respectively associated with one of a plurality of final texts, the method for suggesting revisions comprising:

tokenizing the DUA into a plurality of statements-under-analysis (“SUAs”);

selecting a first SUA of the plurality of SUAs;

generating a first similarity score for each of the plurality of the original texts, the similarity score representing a degree of similarity between the first SUA and each of the original texts, respectively;

selecting a first candidate original text of the plurality of the original texts;

aligning the first SUA with the first candidate original text according to a first alignment;

aligning the first candidate original text with a first candidate final text associated with the first candidate original text according to the first alignment;

determining a first set of one or more edit operations that convert the first candidate original text to the first candidate final text according to the first alignment; and

creating a first edited SUA (first “ESUA”) by applying to the SUA the determined first set of one or more edit operations according to the first alignment.

2. The method of claim 1 further comprising:

aligning the first ESUA with the first candidate original text according to a second alignment;

aligning the first candidate original text with the first candidate final text associated with the first candidate original text according to the second alignment;

determining a second set of one or more edit operations that convert the first candidate original text to the second candidate final text according to the second alignment; and

creating a second ESUA by applying to the first ESUA the determined second set of one or more edit operations according to the second alignment.

3. The method of claim 1 further comprising:

selecting a second candidate original text of the plurality of the original texts;

aligning the first ESUA with the second candidate original text according to a second alignment;

aligning the second candidate original text with a second candidate final text associated with the second candidate original text according to the second alignment

determining a second set of one or more edit operations that convert the second candidate original text to the first candidate final text according to the second alignment; and

creating a second ESUA by applying to the first ESUA the determined second set of one or more edit operations according to the second alignment.

4. The method of claim 1 wherein the generating of the first similarity score comprises generating a cosine similarity score.

5. The method of claim 1 wherein the generating of the first similarity score comprises evaluating a word embedding model comprising at least a portion of the SUA in view of at least a portion of each of the plurality of the original texts.

6. The method of claim 1 wherein the selecting a first candidate original text comprises selecting one of the plurality of the original texts having a first similarity score indicating a highest degree of similarity from among the generated first similarity score for each of the plurality of the original texts.

7. The method of claim 1 further comprising:

selecting a first subset of the plurality of original texts; and

generating a second similarity score for each of the original texts of the first subset, the second similarity score representing a degree of similarity between the SUA and each of the original texts of the first subset.

8. The method of claim 7 wherein the degree of similarity comprises an indication of a length of a matching substring in common between the SUA and each of the original texts.

9. The method of claim 7 wherein the selecting the first subset comprises selecting a predetermined number of the plurality of original texts each, respectively, having a first similarity score higher in value than any other first similarity score from among the generated first similarity score for each of the original texts.

10. The method of claim 7 wherein the selecting the first subset comprises selecting each of the plurality of original texts having the first similarity score that exceeds a predetermined threshold.

11. The method of claim 1 further comprising:

updating the DUA with the first ESUA.

12. The method of claim 11 wherein the updating the DUA comprises substituting the first ESUA into the DUA in place of the first SUA.

13. The method of claim 11 wherein the updating the DUA comprises inserting the first ESUA into an appendix of the DUA.

14. The method of claim 1 further comprising:

creating an appendix to the DUA, the appendix comprising the first ESUA.

15. The method of claim 1 further comprising:

storing the first SUA and the first ESUA in the seed database.

16. The method of claim 15 further comprising:

expanding the SUA to create a plurality of extracted original texts;

expanding the first ESUA to create a plurality of extracted final texts;

correlating each of the plurality of extracted original texts, respectively, with one of the plurality of extracted final texts to create a plurality of extracted text correlations; and

storing the plurality of extracted original texts, the plurality of extracted final texts, and the plurality of extracted text correlations in the seed database.

17. The method of claim 1 further comprising:

creating the seed database, wherein creating the seed database comprises:

tokenizing an original document to create a plurality of original texts;

tokenizing an edited document associated with the original document to create a plurality of final texts;

correlating each of the plurality of original texts, respectively, with one of the plurality of final texts to create a plurality of correlations; and

storing the plurality of original texts, the plurality of final texts, and the plurality of correlations in a database.

18. The method of claim 17 wherein creating the seed database further comprises creating the original document from a document having an embedded track-changes and creating the edited document from the document having the embedded track-changes.

19. The method of claim 17 further comprising:

expanding a compound original text of the plurality of original texts to create a plurality of extracted original texts;

expanding a compound final text corresponding with the compound original text to create a plurality of extracted final texts;

correlating each of the plurality of extracted original texts, respectively, with one of the plurality of extracted final texts to create a plurality of extracted text correlations; and

storing the plurality of extracted original texts, the plurality of extracted final texts, and the plurality of extracted text correlations in the database.

20. The method of claim 1 further comprising:

displaying in a user interface the first ESUA; and

prompting a user to accept the first ESUA.

21. A method for suggesting revisions to a document-under-analysis (“DUA”) from a seed database, the seed database comprising a plurality of original texts each respectively associated with one of a plurality of final texts, the method for suggesting revisions comprising:

tokenizing the DUA into a plurality of statements-under-analysis (“SUAs”);

selecting a first SUA of the plurality of SUAs;

generating a first similarity score for each of the plurality of original texts, the first similarity score representing a degree of similarity between the first SUA and each of the original texts, respectively;

generating a second similarity score for each of a subset of the plurality of original texts, the second similarity score representing a degree of similarity between the first SUA and each of the subset of the plurality of original texts, respectively;

selecting a first candidate original text of the subset of plurality of the original texts;

aligning the first SUA with the first candidate original text according to a first alignment;

aligning the first candidate original text with a first candidate final text associated with the first candidate original text according to the first alignment;

determining a first set of one or more edit operations that convert the first candidate original text to the first candidate final text according to the first alignment; and

creating an edited SUA (“ESUA”) by applying to the SUA the determined first set of one or more edit operations according to the first alignment.

22. The method of claim 21 wherein the selecting a first candidate original text comprises selecting one of the subset of plurality of the original texts having a longest length of a matching string sequence in common with the SUA.

23. The method of claim 21 further comprising:

storing the first SUA and the ESUA in the seed database.

24. The method of claim 23 further comprising:

expanding the SUA to create a plurality of extracted original texts;

expanding the ESUA to create a plurality of extracted final texts;

correlating each of the plurality of extracted original texts, respectively, with one of the plurality of extracted final texts to create a plurality of extracted text correlations; and

storing the plurality of extracted original texts, the plurality of extracted final texts, and the plurality of extracted text correlations in the seed database.

25. A method for suggesting revisions to a document-under-analysis (“DUA”) from a seed database, the seed database comprising a plurality of original texts each respectively associated with one of a plurality of final texts, the method for suggesting revisions comprising:

tokenizing the DUA into a plurality of statements-under-analysis (“SUAs”);

selecting a first SUA of the plurality of SUAs;

generating a first similarity score for each of the plurality of original texts, the first similarity score representing a degree of similarity between the first SUA and each of the original texts, respectively;

generating a second similarity score for each of a subset of the plurality of original texts, the second similarity score representing a degree of similarity between the first SUA and each of the subset of the plurality of original texts, respectively;

selecting a first candidate original text of the subset of plurality of the original texts;

aligning the first SUA with the first candidate original text according to a first alignment;

aligning the first candidate original text with a first candidate final text associated with the first candidate original text according to the first alignment

determining a first set of one or more edit operations that convert the first candidate original text to the first candidate final text according to the first alignment;

creating a first edited SUA (first “ESUA”) by applying to the SUA the determined first set of one or more edit operations according to the first alignment;

selecting a second candidate original text of the subset of plurality of the original texts;

aligning the first ESUA with the second candidate original text according to a second alignment;

aligning the second candidate original text with a second candidate final text associated with the second candidate original text according to the second alignment;

determining a second set of one or more edit operations that convert the second candidate original text to the second candidate final text according to the second alignment; and

creating a second ESUA by applying to the first ESUA the determined second set of one or more edit operations according to the second alignment.