Computing system for extraction of textual elements from a document

1. A computing system, comprising:

a processor; and

memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:

obtaining an electronic document comprising a first textual element and a second textual element, wherein the first textual element is located at a first position within the electronic document, wherein the second textual element is located at a second position within the electronic document, and further wherein the electronic document has a type;

obtaining defined criteria for the type of the electronic document;

computing a score that is indicative of a likelihood that the first textual element represents relevant content in the electronic document based upon:

a contextual relationship between the first textual element and the second textual element;

spatial factors between the first position of the first textual element and the second position of the second textual element; and

the defined criteria;

selecting at least one of the first textual element or the second textual element based upon the score; and

outputting the at least one of the first textual element or the second textual element.

2. The computing system of claim 1 , wherein the spatial factors include one or more of:

a distance between the first position and the second position in the electronic document; or

an angle between the first position, the second position, and an axis of the electronic document.

3. The computing system of claim 1 , wherein outputting the at least one of the first textual element or the second textual element comprises storing the at least one of the first textual element or the second textual element in a database.

4. The computing system of claim 1 , the acts further comprising:

prior to computing the score:

determining the contextual relationship between the first textual element and the second textual element; and

computing the spatial factors between the first position of the first textual element and the second position of the second textual element.

5. The computing system of claim 1 , wherein the score is further based upon a typographical emphasis of the first textual element.

6. The computing system of claim 1 , wherein the type of the electronic document is one of:

an educational transcript;

an invoice;

a medical record;

a personnel record; or

a taxation form.

7. The computing system of claim 1 , wherein the first textual element includes one or more of:

at least one letter;

at least one number;

at least one punctuation symbol; or

at least one mathematical symbol.

8. The computing system of claim 1 , wherein the score is further based upon a font size of the first textual element.

9. The computing system of claim 1 , wherein the first textual element and the second textual element are comprised by a table within the electronic document.

10. A method executed by a processor of a computing system, the method comprising:

obtaining an electronic document comprising a first textual element and a second textual element, wherein the first textual element is located at a first position within the electronic document, wherein the second textual element is located at a second position within the electronic document, and further wherein the electronic document has a type;

obtaining defined criteria for the type of the electronic document;

determining a contextual relationship between the first textual element and the second textual element;

computing a spatial factor between the first position of the first textual element and the second position of the second textual element;

computing a score that is indicative of a likelihood that the first textual element represents relevant content in the electronic document based upon:

the contextual relationship between the first textual element and the second textual element;

the spatial factor between the first position of the first textual element and the second position of the second textual element; and

the defined criteria;

selecting at least one of the first textual element or the second textual element based upon the score; and

outputting the at least one of the first textual element or the second textual element.

11. The method of claim 10 , wherein the contextual relationship is one of:

source to object;

object to use;

person to location;

whole to part; or

type to subtype.

12. The method of claim 10 , wherein the electronic document is generated by applying an optical character recognition (OCR) process on an image of a physical version of a document.

13. The method of claim 10 , wherein outputting the at least one of the first textual element or the second textual element comprises presenting the at least one of the first textual element or the second textual element on a display.

14. The method of claim 10 , further comprising:

prior to obtaining the defined criteria, determining the type of the electronic document.

15. The method of claim 10 , wherein the defined criteria are received as input from a user.

16. The method of claim 10 , wherein the contextual relationship between the first textual element and the second textual element is determined by way of a computer-implemented neural network.

17. The method of claim 10 , wherein the electronic document is a semi-structured document.

18. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processor of a computing system, cause the processor to perform acts comprising:

obtaining an electronic document comprising a first textual element and a second textual element, wherein the first textual element is located at a first position within the electronic document, wherein the second textual element is located at a second position within the electronic document, and further wherein the electronic document has a type;

obtaining defined criteria for the type of the electronic document;

computing a first score that is indicative of a likelihood that the first textual element represents relevant content in the electronic document based upon:

a first contextual relationship between the first textual element and the second textual element;

first spatial factors between the first position of the first textual element and the second position of the second textual element; and

the defined criteria;

computing a second score that is indicative of a likelihood that the second textual element represents the relevant content in the electronic document based upon:

a second contextual relationship between the second textual element and the first textual element;

second spatial factors between the second position of the second textual element and the first position of the first textual element; and

the defined criteria;

selecting at least one of the first textual element or the second textual element based upon the first score and the second score; and

outputting the at least one of the first textual element or the second textual element.

19. The non-transitory computer-readable storage medium of claim 18 , the acts further comprising:

prior to computing the first score:

determining the first contextual relationship between the first textual element and the second textual element; and

computing the first spatial factors between the first position of the first textual element and the second position of the second textual element; and

prior to computing the second score:

determining the second contextual relationship between the second textual element and the first textual element; and

computing the second spatial factors between the second position of the second textual element and the first position of the first textual element.

20. The non-transitory computer-readable storage medium of claim 18 , wherein the first spatial factors are different than the second spatial factors.