System and method thereof for determining vendor's identity based on network analysis methodology

1. A method for classifying digital images of transaction evidences, comprising:

extracting a plurality of descriptive data items and a plurality of numeric values of a transaction evidence from a digital image;

determining an association between at least one of the plurality of numeric values and at least one of the plurality of descriptive data items, wherein determining the association further comprises applying at least one positioning rule to each of the plurality of descriptive data items with respect to each of the plurality of numeric values;

determining, based on at least one expense type classification rule, at least a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and the plurality of numeric values; and

classifying the digital image based on the determined at least one primary expense type.

2. The method of claim 1 , wherein the at least one expense type classification rule is selected based on at least one of: a data item and metadata associated with the digital image of the transaction evidence.

3. The method of claim 2 , wherein at least one of the data item and the metadata indicates a country parameter that is associated with at least one of: a vendor and a consumer.

4. The method of claim 3 , further comprising:

searching in at least one data source for the at least one expense type classification rule based on the country parameter of the digital image of the transaction evidence.

5. The method of claim 1 , further comprising:

extracting at least a first sequence of textual items from the digital image;

determining a first approximate identity of a vendor entity that issued the digital image by comparing the first sequence of textual items to at least a second sequence of textual items that is associated with at least an electronic document that was previously associated with a unique vendor entity;

extracting a first multiset of textual items from the plurality of textual items of the digital image;

determining a second approximate identity of the vendor entity that issued the digital image by comparing the first multiset of textual items to at least a second multiset of textual items that was previously associated with the unique vendor entity;

determining a specific identity of the vendor entity that issued the digital image upon determination that the first approximate identity and the second approximate identity are identical, otherwise performing a resolution process; and

associating the digital image with the vendor entity that issued the digital image based on the determined specific identity.

6. A method for classifying digital images of transaction evidences, comprising:

extracting a plurality of descriptive data items and a plurality of numeric values of a transaction evidence from a digital image;

determining an association between at least one of the plurality of numeric values and at least one of the plurality of descriptive data items;

determining, based on at least one expense type classification rule, at least a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and the plurality of numeric values;

classifying the digital image based on the determined at least one primary expense type; and

generating an electronic tag indicating the classification of the digital image of the transaction evidence.

7. The method of claim 6 , further comprising:

associating the electronic tag with the digital image of the transaction evidence.

8. The method of claim 6 , wherein the at least one expense type classification rule includes rules for comparing the extracted plurality of descriptive data item to a plurality of previous descriptive data items associated with a previous transaction evidence.

9. The method of claim 6 , wherein the at least one expense type classification rule is selected based on at least one of: a data item and metadata associated with the digital image of the transaction evidence.

10. The method of claim 9 , wherein at least one of the data item and the metadata indicates a country parameter that is associated with at least one of: a vendor and a consumer.

11. The method of claim 10 , further comprising:

searching in at least one data source for the at least one expense type classification rule based on the country parameter of the digital image of the transaction evidence.

12. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process for classifying digital images of transaction evidences, the process comprising:

extracting a plurality of descriptive data items and a plurality of numeric values of a transaction evidence from a digital image;

determining an association between at least one of the plurality of numeric values and at least one of the plurality of descriptive data items, wherein determining the association further comprises applying at least one positioning rule to each of the plurality of descriptive data items with respect to each of the plurality of numeric values;

determining, based on at least one expense type classification rule, at least a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and the plurality of numeric values; and

classifying the digital image based on the determined at least one primary expense type.

13. A system for classifying digital images of transaction evidences, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

extract a plurality of descriptive data items and a plurality of numeric values of a transaction evidence from a digital image;

determine an association between at least one of the plurality of numeric values and at least one of the plurality of descriptive data items, wherein the system is further configured to apply at least one positioning rule to each of the plurality of descriptive data items with respect to each of the plurality of numeric values;

determine, based on at least one expense type classification rule, at least a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and the plurality of numeric values; and

classify the digital image based on the determined at least one primary expense type.

14. The system of claim 13 , wherein the at least one expense type classification rule is selected based on at least one of: a data item and metadata associated with the digital image of the transaction evidence.

15. The system of claim 14 , wherein at least one of the data item and the metadata indicates a country parameter that is associated with at least one of: a vendor and a consumer.

16. The system of claim 15 , wherein the system is further configured to:

search in at least one data source for the at least one expense type classification rule based on the country parameter of the digital image of the transaction evidence.

17. The system of claim 13 , wherein the system is further configured to:

extract at least a first sequence of textual items from the digital image;

determine a first approximate identity of a vendor entity that issued the digital image by comparing the first sequence of textual items to at least a second sequence of textual items that is associated with at least an electronic document that was previously associated with a unique vendor entity;

extract a first multiset of textual items from the plurality of textual items of the digital image;

determine a second approximate identity of the vendor entity that issued the digital image by comparing the first multiset of textual items to at least a second multiset of textual items that was previously associated with the unique vendor entity;

determine a specific identity of the vendor entity that issued the digital image upon determination that the first approximate identity and the second approximate identity are identical, otherwise performing a resolution process; and

associating the digital image with the vendor entity that issued the digital image based on the determined specific identity.

18. A system for classifying digital images of transaction evidences, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

extract a plurality of descriptive data items and a plurality of numeric values of a transaction evidence from a digital image;

determine an association between at least one of the plurality of numeric values and at least one of the plurality of descriptive data items;

determine, based on at least one expense type classification rule, at least a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and the plurality of numeric values; and

classify the digital image based on the determined at least one primary expense type; and

generate an electronic tag indicating the classification of the digital image of the transaction evidence.

19. The system of claim 18 , wherein the system is further configured to:

associate the electronic tag with the digital image of the transaction evidence.

20. The system of claim 16 , wherein the at least one expense type classification rule includes rules for comparing the extracted plurality of descriptive data item to a plurality of previous descriptive data items associated with a previous transaction evidence.

21. The system of claim 18 , wherein the at least one expense type classification rule is selected based on at least one of: a data item and metadata associated with the digital image of the transaction evidence.

22. The system of claim 21 , wherein at least one of the data item and the metadata indicates a country parameter that is associated with at least one of: a vendor and a consumer.

23. The system of claim 22 , wherein the system is further configured to:

search in at least one data source for the at least one expense type classification rule based on the country parameter of the digital image of the transaction evidence.

24. A method for classifying electronic documents, comprising:

extracting at least a first sequence of first textual items from a first digital image;

extracting at least a second sequence of second textual items from at least a second digital image;

generating a sequence matching score indicating an association level between the at least a first sequence and the at least a second sequence;

generating a graph that includes a plurality of nodes representing the first digital image and the at least a second digital image, and links representing the association level between the first digital image and the at least a second digital image; and,

classifying the first digital image by applying at least one clustering rule over the graph.

25. The method of claim 24 , wherein generating the sequence matching score further comprising:

calculating a term frequency-inverse document frequency (TFIDF) weight of the textual items of each of the first sequence and the at least a second sequence.

26. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process for classifying digital images of transaction evidences, the process comprising:

extracting a plurality of descriptive data items and a plurality of numeric values of a transaction evidence from a digital image;

determining an association between at least one of the plurality of numeric values and at least one of the plurality of descriptive data items;

determining, based on at least one expense type classification rule, at least a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and the plurality of numeric values;

classifying the digital image based on the determined at least one primary expense type; and

generating an electronic tag indicating the classification of the digital image of the transaction evidence.