METHOD AND APPARATUS FOR DETECTING SENSITIVE CONTENT IN A DOCUMENT

• US 20100076957A1
• Filed: 09/10/2008
• Published: 03/25/2010
• Est. Priority Date: 09/10/2008
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: King, Tracy Holloway, de Paiva, Valeria, Staddon, Jessica N., Chow, Richard, Golle, Philippe J.P., Fang, Ji
• Granted Patent: US 8,271,483 B2
• Time in Patent Office: Days
• US Class Current: 707/722
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing

Abstract

One embodiment of the present invention provides a system that detects sensitive content in a document. In doing so, the system receives a document, identifies a set of terms in the document that are candidate sensitive terms, and generates a combination of terms based on the identified terms that is associated with a semantic meaning. Next, the system performs searches through a corpus based on the combination of terms and determines hit counts returned for each term in the combination and for the combination. The system then determines whether the combination of terms is sensitive based on the hit count for the combination and the hit counts for the individual terms in the combination, and generates a result that indicates portions of the document which contain sensitive combinations.

Claims

1. A computer-executed method for detecting sensitive content in a document, the method comprising:

receiving a document;

identifying a set of terms in the document that are candidate sensitive terms;

generating a combination of terms, based on the identified terms, that is associated with a semantic meaning;

performing searches through a corpus based on the combination of terms and determining hit counts returned for each term in the combination and for the combination;

determining whether the combination of terms is sensitive based on the hit count for the combination and the hit counts for the individual terms in the combination; and

generating a result that indicates portions of the document which contain sensitive combinations.

2. The method of claim 1, wherein identifying the set of terms in the document that are candidate sensitive terms comprises processing the document with a part-of-speech (POS) tagger to identify words that belong to a predetermined set of word classes.

3. The method of claim 1, further comprising determining a relationship between the identified terms by processing the document with a syntactic parser to determine relationships between the terms.

4. The method of claim 3, wherein determining the relationship between the identified terms further comprises scoring a respective relationship based on a determined relevance to the document and a likelihood of being sensitive.

5. The method of claim 1, wherein determining whether the combination of terms is sensitive comprises:

for a respective term, T₁, in the combination of k terms, determining a number, q_i, of public documents that include the respective term T_i; and

computing an occurrence ratio, r, as the ratio between a predetermined function, ƒ

, of T_i, and a predetermined function, g, of q_i;

$r=\frac{f<br><br>\left(T_1,T_2,\mathrm{\dots <br><br>}<br><br>,T_k\right)}{g<br><br>\left(q_1,q_2,\mathrm{\dots <br><br>}<br><br>,q_k\right)}.$

6. The method of claim 1, further comprising disregarding the combination if the combination is not associated with sensitive information by determining that the respective combination can be inferred from public information.

7. The method of claim 6, wherein determining that the combination can be inferred from public information comprises:

for a respective term in the combination, gathering supplemental information related to the term based on corpus searches and/or synonym/hypernym databases;

determining a degree of separation between two terms in the combination by determining the relationship between a first term in the combination and the supplemental information associated with a second term in the combination; and

determining whether the degree of separation between the two terms in the combination is below a predetermined threshold.

8. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for detecting sensitive content in a document, the method comprising:

receiving a document;

identifying a set of terms in the document that are candidate sensitive terms;

generating a combination of terms, based on the identified terms, that is associated with a semantic meaning;

performing searches through a corpus based on the combination of terms and determining hit counts returned for each term in the combination and for the combination;

determining whether the combination of terms is sensitive based on the hit count for the combination and the hit counts for the individual terms in the combination; and

generating a result that indicates portions of the document which contain sensitive combinations.

9. The computer-readable storage medium of claim 8, wherein identifying the set of terms in the document that are candidate sensitive terms comprises processing the document with a part-of-speech (POS) tagger to identify words that belong to a predetermined set of word classes.

10. The computer-readable storage medium of claim 8, further comprising determining a relationship between the identified terms by processing the document with a syntactic parser to determine relationships between the terms.

11. The computer-readable storage medium of claim 10, wherein determining the relationship between the identified terms further comprises scoring a respective relationship based on a determined relevance to the document and a likelihood of being sensitive.

12. The computer-readable storage medium of claim 8, wherein determining whether the combination of terms is sensitive comprises:

for a respective term, T₁, in the combination of k terms, determining a number, q_i, of public documents that include the respective term T_i; and

computing an occurrence ratio, r, as the ratio between a predetermined function, ƒ

, of T_i, and a predetermined function, g, of q_i;

$r=\frac{f<br><br>\left(T_1,T_2,\mathrm{\dots <br><br>}<br><br>,T_k\right)}{g<br><br>\left(q_1,q_2,\mathrm{\dots <br><br>}<br><br>,q_k\right)}.$

13. The computer-readable storage medium of claim 8, wherein the method further comprises disregarding the combination if the combination is not associated with sensitive information by determining that the respective combination can be inferred from public information.

14. The computer-readable storage medium of claim 13, wherein determining that the combination can be inferred from public information comprises:

for a respective term in the combination, gathering supplemental information related to the term based on corpus searches and/or synonym/hypernym databases;

determining a degree of separation between two terms in the combination by determining the relationship between a first term in the combination and the supplemental information associated with a second term in the combination; and

determining whether the degree of separation between the two terms in the combination is below a predetermined threshold.

15. An apparatus for detecting sensitive content in a document, comprising:

a receiving mechanism configured to receive a document;

an analysis mechanism configured to;

identify a set of terms in the document that are candidate sensitive terms; and

generate a combination of terms, based on the identified terms, that is associated with a semantic meaning; and

a search engine interface configured to perform searches through a corpus based on the combination of terms and determining hit counts returned for each term in the combination and for the combination;

wherein the analysis mechanism is further configured to;

determine whether the combination of terms is sensitive based on the hit count for the combination and the hit counts for the individual terms in the combination; and

generate a result that indicates portions of the document which contain sensitive combinations.

16. The apparatus of claim 15, wherein while identifying the set of terms in the document that are candidate sensitive terms, the analysis mechanism is further configured to process the document with a part-of-speech (POS) tagger to identify words that belong to a predetermined set of word classes.

17. The apparatus of claim 15, wherein the analysis mechanism is further configured to determine a relationship between the identified terms by processing the document with a syntactic parser to determine relationships between the terms.

18. The apparatus of claim 17, wherein while determining the relationship between the identified terms, the analysis mechanism is further configured to score a respective relationship based on a determined relevance to the document and a likelihood of being sensitive.

19. The apparatus of claim 15, wherein while determining whether the combination of terms is sensitive, the analysis mechanism is configured to:

for a respective term, T_i, in the combination of k terms, determine a number, q_i, of public documents that include the respective term T_i; and

compute an occurrence ratio, r, as the ratio between a predetermined function, ƒ

, of T_i, and a predetermined function, g, of q_i;

$r=\frac{f<br><br>\left(T_1,T_2,\mathrm{\dots <br><br>}<br><br>,T_k\right)}{g<br><br>\left(q_1,q_2,\mathrm{\dots <br><br>}<br><br>,q_k\right)}.$

20. The apparatus of claim 15, wherein the analysis mechanism is further configured to disregard the combination if the combination is not associated with sensitive information by determining that the respective combination can be inferred from public information.

21. The apparatus of claim 20, wherein while determining that the combination can be inferred from public information, the analysis mechanism is configured to:

for a respective term in the combination, gather supplemental information related to the term based on corpus searches and/or synonym/hypernym databases;

determine a degree of separation between two terms in the combination by determining the relationship between a first term in the combination and the supplemental information associated with a second term in the combination; and

determine whether the degree of separation between the two terms in the combination is below a predetermined threshold.