Document information extraction system using sequenced comparators

1. A computer-implemented method for determining a hierarchical structure of an electronic document, the method comprising:

segmenting the document into a plurality of elements that, in aggregate, include the hierarchical structure, and each element having one or more visual characteristics and one or more location characteristics;

applying a master comparator including a set of unit comparators to the segmented plurality of elements from the document to determine the hierarchical structure of the document, the master comparator determining the hierarchical structure by:

for each pair of elements in the document:

applying a unit comparator of the set of unit comparators to the pair of elements according to a predefined ordered sequence to generate an output digit, the unit comparator comparing a visual characteristic or a location characteristic of the pair of elements in the document to determine the output digit;

determining a familial relationship between the pair of elements indicated by the output digit;

responsive to the determined familial relationship for the pair of elements being a sibling relationship, applying a next unit comparator of the set of unit comparators to the pair of elements according to the predefined ordered sequence, the next unit comparator comparing a different visual characteristic or a different location characteristic of the pair of elements; and

responsive to the determined familial relationship for the pair of elements being a parent relationship or an unrelated relationship, applying the master comparator to a next pair of elements in the document;

wherein the determined familial relationships between each pair of elements of the plurality of elements identify the hierarchical structure of the document; and

generating, for display on a client device, a visualization of a document hierarchy tree representing the hierarchical structure of the document, the visualization illustrating the determined familial relationships between each pair of elements of the plurality of elements in the document.

2. The method of claim 1 , further comprising:

for each element, determining a plurality of directional relationships for the element, the directional relationship defining an adjacency type between the element and any adjacent element in the document, and

wherein the master comparator compares pairs of elements based on the directional relationships.

3. The method of claim 2 , wherein the familial relationships are further based on the directional relationships between elements.

4. The method of claim 1 , wherein each unit comparator in the set of set of unit comparators compares a different visual characteristic.

5. The method of claim 1 , wherein each unit comparator of the set of unit comparators compares a different location characteristic.

6. The method of claim 1 , wherein determining the hierarchal structure further comprises:

determining a formatting structure for the plurality of elements in the document, and

wherein hierarchical structure is based on the formatting structure.

7. The method of claim 1 , wherein determining the hierarchal structure further comprises:

determining an indexing structure for the plurality of elements in the document, and

wherein hierarchical structure is based on the indexing structure.

8. The method of claim 1 , wherein the hierarchical structure of the document comprises a plurality of familial relationships, and the plurality of familial relationships comprises a plurality of parent relationships, a plurality of child relationships, and a plurality of sibling relationships.

9. The method of claim 8 , wherein:

the document includes a first element and a second element,

a parent relationship between the first element and the second element defines the first element having a higher-level hierarchy in the hierarchical structure of the document than the second element,

a child relationship between the first element and the second element defines the first element having a lower-level hierarchy in the hierarchical structure of the document than the second element, and

a sibling relationship between the first element and the second element defines the first element and the second element having a same-level hierarchy in the hierarchical structure of the document.

10. The method of claim 1 , further comprising:

validating the familial relationships between the plurality of elements by applying the master comparator to pairs of elements having a grandparent and a grandchild relationship in the hierarchical structure of the document.

11. The method of claim 1 , further comprising:

receiving, from a remote client system, a request to generate the visualization; and

transmitting the visualization to the remote client system.

12. The method of claim 11 , wherein the request includes a configuration request comprising the predefined sequence of the set of unit comparators of the master comparator.

13. The method of claim 1 , wherein applying the set of unit comparators to each pair of elements in the document comprises sequentially comparing individual visual characteristics or location characteristics for each pair of elements.

14. The method of claim 1 , wherein each unit comparator in the ordered set of unit comparators compares only one visual characteristic for each pair of elements in the electronic document.

15. The method of claim 1 , wherein each unit comparator in the ordered set of unit comparators compares only one location characteristic for each pair of elements in the electronic document.

16. The method of claim 1 , wherein applying the set of unit comparators in the ordered sequences comprises applying less than all of the unit comparators in the set.

17. The method of claim 1 , wherein the predefined ordered sequence is defined by a system administrator.

18. A non-transitory computer readable storage medium including computer instructions for determining a hierarchical structure of an electronic document, the computer instructions, when executed by a processor, causing the processor to:

segment the document into a plurality of elements that, in aggregate, include the hierarchical structure, and each element having one or more visual characteristics and one or more location characteristics;

apply a master comparator including a set of unit comparators to the segmented plurality of elements from the document to determine the hierarchical structure of the document, the master comparator determining the hierarchical structure by:

for each pair of elements in the document:

applying a unit comparator of the set of unit comparators to the pair of elements according to a predefined ordered sequence to generate an output digit, the unit comparator comparing visual characteristics or location characteristics of the pair of elements in the document to determine the output digit;

determining a familial relationship indicated by the output digit;

responsive to the output digit indicating a sibling relationship between the pair of elements, applying a next unit comparator of the set of unit comparators to pair of element according to the redefined ordered sequence:

responsive to the output digit indicating a parent or unrelated relationship between the pair of elements, applying the master comparator to a next pair of elements in the document;

wherein the determined familial relationships between each pair of elements of the plurality of elements identify the hierarchical structure of the document; and

generate, for display on a client device, a visualization of a document hierarchy tree representing the hierarchical structure of the document, the visualization illustrating the determined familial relationships between each pair of elements of the plurality of elements in the document.

19. The non-transitory computer readable storage medium of claim 18 , wherein the computer instructions, when executed by the processor, further cause the processor to:

for each element, determine a plurality of directional relationships for the element, the directional relationship defining an adjacency type between the element and any adjacent element in the document, and

wherein the master comparator compares pairs of elements based on the directional relationships.

20. The non-transitory computer readable storage medium of claim 19 , wherein the familial relationships are further based on the directional relationships between elements.

21. The non-transitory computer readable storage medium of claim 18 , wherein each unit comparator in the set of set of unit comparators compares a different visual characteristic.

22. The non-transitory computer readable storage medium of claim 18 , wherein each unit comparator of the set of unit comparators compares a different location characteristic.

23. The non-transitory computer readable storage medium of claim 18 , wherein the hierarchical structure of the document comprises a plurality of familial relationships, and the plurality of familial relationships comprises a plurality of parent relationships, a plurality of child relationships, and a plurality of sibling relationships.

24. The non-transitory computer readable storage medium of claim 18 , wherein:

the document includes a first element and a second element,

a parent relationship between the first element and the second element defines the first element having a higher-level hierarchy in the hierarchical structure of the document than the second element,

a child relationship between the first element and the second element defines a the first element segment having a lower-level hierarchy in the hierarchical structure of the document than the second element, and

a sibling relationship between the first element and the second element defines the first element and the second element having a same-level hierarchy in the hierarchical structure of the document.

25. The non-transitory computer readable storage medium of claim 18 , wherein the predefined ordered sequence is defined by a system administrator.

26. A system for determining a hierarchical structure of an electronic document, the system comprising:

a computer processor for executing computer program instructions; and

a non-transitory computer-readable medium storing computer program instructions executable by the computer processor to perform operations comprising:

segmenting the document into a plurality of elements that, in aggregate, include the hierarchical structure, and each element having one or more visual characteristics and one or more location characteristics;

applying a master comparator including a set of unit comparators to the segmented plurality of elements from the document to determine the hierarchical structure of the document, the master comparator determining the hierarchical structure by:

for each pair of elements in document:

applying a unit comparator of the set of unit comparators to the pair of elements according to a predefined ordered sequence to generate an output digit, the unit comparator comparing a visual characteristic or a location characteristic of the pair of elements in the document to determine the output digit;

determining a familial relationship between the pair of elements indicated by the output digit;

responsive to the determined familial relationship for the pair of elements being a sibling relationship, applying a next unit comparator of the set of unit comparators to the pair of elements according to the predefined ordered sequence, the next unit comparator comparing a different visual characteristic or a different location characteristic of the pair of elements; and

responsive to the determined familial relationship for the pair of elements being a parent relationship or an unrelated relationship, applying the master comparator to a next pair of elements in the document;

wherein the determined familial relationships between each pair of elements of the plurality of elements identify the hierarchical structure of the document; and

generating a document hierarchy tree representing the hierarchical structure of the document, the document hierarchy tree a visualization of the familial relationships between the plurality of elements.

27. The system of claim 26 , wherein the predefined ordered sequence is defined by a system administrator.