Systems and methods for value extraction and guided review
A method of automatic extraction of values includes scanning a document and linking a first word of a plurality of words in the document, to each word of the plurality of words in the document positionally adjacent to the right, left, top, bottom of the first word. The method further includes repeating said scanning and linking for every word of the plurality of words in the document. The method further includes determining the x and y coordinate in the document for each of the plurality of words. The method further includes providing a plurality of checklist words corresponding to information of interest. The method further includes searching the plurality of words in the document for each of the plurality of checklist words. The method further includes for each checklist word found in the plurality of words of the documents determining if a linked positionally adjacent words to the right, left, top, bottom is a value that matches typical values for the plurality of checklist words and if so, extract said value. The method further includes directing a user interface to position in the document related to content of interest related to at least one of the plurality of checklist words.
1 . A method of automatic extraction of values, the method comprising:
scanning a document and linking a first word of a plurality of words in the document, to each word of the plurality of words in the document positionally adjacent to the right, left, top, bottom of the first word;
repeating said scanning and linking for every word of the plurality of words in the document;
determining the x and y coordinate in the document for each of the plurality of words;
providing a plurality of checklist words corresponding to information of interest;
searching the plurality of words in the document for each of the plurality of checklist words;
for each checklist word found in the plurality of words of the documents determining if a linked positionally adjacent words to the right, left, top, bottom is a value that matches typical values for the plurality of checklist words and if so, extract said value,
directing a user interface to position in the document related to content of interest related to at least one of the plurality of checklist words.
2 . The method of claim 1 , further comprising: creating a bounding box for each word of the plurality of words.
3 . The method of claim 2 , further comprising: extracting y coordinates of the bounding boxes for each word of the plurality of words.
4 . The method of claim 3 , further comprising: determining what words of the plurality of words are on the same y-axis using a distance formula and creating a line for each set of words of the plurality of words that are on the same line, creating a plurality of lines.
5 . The method of claim 4 , further comprising: converting the plurality of lines to lower case.
6 . The method of claim 5 , further comprising stripping special characters from the plurality of lines.
7 . The method of claim 6 , further comprising: alphabetizing the plurality of lines.
8 . The method of claim 7 , further comprising determining how similar each of the plurality of checklist words is to the plurality of lines to perform the searching the plurality of words in the document for each of the plurality of checklist words.
9 . The method of claim 8 , wherein the Jaro Winkler Distance and Dice Coefficient algorithms are used in the determining how similar each of the plurality of checklist words is to the plurality of lines.
10 . A system for automatic extraction of values comprising:
a module executing instructions in non-transitory digital storage medium to
scan a document and link a first word of a plurality of words in the document, to each word of the plurality of words in the document positionally adjacent to the right, left, top, bottom of the first word;
repeat said scanning and linking for every word of the plurality of words in the document;
determine the x and y coordinate in the document for each of the plurality of words;
provide a plurality of checklist words corresponding to information of interest;
search the plurality of words in the document for each of the plurality of checklist words;
for each checklist word found in the plurality of words of the documents determine if a linked positionally adjacent words to the right, left, top, bottom is a value that matches typical values for the plurality of checklist words and if so, extract said value,
direct a user interface to position in the document related to content of interest related to at least one of the plurality of checklist words.
11 . The system of claim 10 , wherein the module further creates a bounding box for each word of the plurality of words.
12 . The system of claim 11 , wherein the module further extracts y coordinates of the bounding boxes for each word of the plurality of words.
13 . The system of claim 12 , wherein the module further determines what words of the plurality of words are on the same y-axis using a distance formula and creating a line for each set of words of the plurality of words that are on the same line, creating a plurality of lines.
14 . The system of claim 13 , wherein the module further converts the plurality of lines to lower case.
15 . The system of claim 14 , wherein the module further strips special characters from the plurality of lines.
16 . The system of claim 15 , wherein the module further alphabetizes the plurality of lines.
17 . The system of claim 16 , wherein the module further determines how similar each of the plurality of checklist words is to the plurality of lines to perform the searching the plurality of words in the document for each of the plurality of checklist words.
18 . The system of claim 17 , wherein the Jaro Winkler Distance and Dice Coefficient algorithms are used in the determining how similar each of the plurality of checklist words is to the plurality of lines.
19 . The system of claim 18 , wherein the words are tokenized.
20 . A non-transitory digital storage medium having a computer program stored thereon to perform a method for transforming and improving the processing of information and records data related documents, the method comprising:
scanning a document and linking a first word of a plurality of words in the document, to each word of the plurality of words in the document positionally adjacent to the right, left, top, bottom of the first word;
repeating said scanning and linking for every word of the plurality of words in the document;
determining the x and y coordinate in the document for each of the plurality of words;
providing a plurality of checklist words corresponding to information of interest;
searching the plurality of words in the document for each of the plurality of checklist words;
for each checklist word found in the plurality of words of the documents determining if a linked positionally adjacent words to the right, left, top, bottom is a value that matches typical values for the plurality of checklist words and if so, extract said value,
directing a user interface to position in the document related to content of interest related to at least one of the plurality of checklist words.