Computer-based system and method for generating, classifying, searching, and analyzing standardized text templates and deviations from standardized text templates
View Patent ↗A method for generating, classifying, searching, and analyzing standardized text templates drawn from a plurality of text documents and for identifying standardized text deviations from standardized text templates. Semi-standardized documents may be represented as standardized templates and deviations from standardized templates, with such templates themselves automatically generated by a computer-implemented method from a plurality of similar text documents. The method enables enhanced analysis of semi-standardized documents and automatic extraction of information from standardized text templates.
1. A computer system configured to automatically analyze text documents by performing the following steps in the order recited:
receiving a subject text document;
comparing the text of the subject text document or the text of a subset of the subject text document to the text of a plurality of given text templates, each text template containing at least one paragraph of text;
determining which given text template or text templates has text that matches the text of the subject text document or the text of the subset of the subject text document to a given degree of correspondence; and
generating a report of the differences between the text of the subject text document or the text of the subset of the subject text document and the text of the matching text template or text templates.
2. The computer system of claim 1 also configured to perform the steps of:
comparing a family of specimen text documents;
identifying one paragraph of text within one of the family of specimen text documents that most closely matches a paragraph of text in all of the other specimen text documents, as compared to all of the other paragraphs in the one specimen text document; and
generating one of the text templates containing at least the one identified paragraph of text.
3. The computer system of claim 2 wherein the identifying the paragraph that most closely matches uses an edit distance algorithm.
4. The computer system of claim 2 wherein the identifying the paragraph that most closely matches uses a longest common subsequence algorithm.
5. The computer system of claim 1 wherein the determining matches to a degree of correspondence uses an edit distance algorithm.
6. The computer system of claim 1 wherein the determining matches to a degree of correspondence uses a longest common subsequence algorithm.
7. The computer system of claim 1 wherein the differences in the report are computed according to an edit distance algorithm.
8. Non-transitory, tangible, computer readable media containing computer programming instructions that, when loaded in a computer system having a memory, cause the computer system, in response to user commands, to automatically analyze text documents by performing the following steps in the order recited:
receiving a subject text document;
comparing the text of the subject text document or the text of a subset of the subject text document to the text of a plurality of given text templates, each text template containing at least one paragraph of text;
determining which given text template or text templates has text that matches the text of the subject text document or the text of the subset of the subject text document to a given degree of correspondence; and
generating a report of the differences between the text of the subject text document or the text of the subset of the subject text document and the text of the matching text template or text templates.
9. The media of claim 8 wherein the programming instructions, when loaded in the computer system, also cause the computer system, in response to user commands, to perform the following steps:
comparing a family of specimen text documents;
identifying one paragraph of text within one of the family of specimen text documents that most closely matches a paragraph of text in all of the other specimen text documents, as compared to all of the other paragraphs in the one specimen text document; and
generating one of the text templates containing at least the one identified paragraph of text.
10. The media of claim 9 wherein the identifying the paragraph that most closely matches uses an edit distance algorithm.
11. The media of claim 9 wherein the identifying the paragraph that most closely matches uses a longest common subsequence algorithm.
12. The media of claim 8 wherein the determining matches to a degree of correspondence uses an edit distance algorithm.
13. The media of claim 8 wherein the determining matches to a degree of correspondence uses a longest common subsequence algorithm.
14. The media of claim 8 wherein the differences in the report are computed according to an edit distance algorithm.
15. A computer-implemented method of automatically analyzing text documents in which a computer performs the following steps in the order recited:
receiving a subject text document;
comparing the text of the subject text document or the text of a subset of the subject text document to the text of a plurality of given text templates, each text template containing at least one paragraph of text;
determining which given text template or text templates has text that matches the text of the subject text document or the text of the subset of the subject test document to a given degree of correspondence; and
generating a report of the differences between the text of the subject text document or the text of the subset of the subject text document and the text of the matching text template or text templates.
16. The computer-implemented method of claim 15 further comprising the steps of:
comparing a family of specimen text documents;
identifying one paragraph of text within one of the family of specimen text documents that most closely matches a paragraph of text in all of the other specimen text documents, as compared to all of the other paragraphs in the one specimen text document; and
generating one of the text templates containing at least the one identified paragraph of text.
17. The computer-implemented method of claim 16 wherein the identifying the paragraph that most closely matches uses an edit distance algorithm.
18. The computer-implemented method of claim 16 wherein the identifying the paragraph that most closely matches uses a longest common subsequence algorithm.
19. The computer-implemented method of claim 15 wherein the determining matches to a degree of correspondence uses an edit distance algorithm.
20. The computer-implemented method of claim 15 wherein the determining matches to a degree of correspondence uses a longest common subsequence algorithm.
21. The computer-implemented method of claim 15 wherein the differences in the report are computed according to an edit distance algorithm.