Systems and methods for extraction of policy information
View Patent ↗In a system for extracting policy information from text, a processor analyzes if the text is relevant to a top-level category, and then determines if at least a portion of the text is relevant to categories and subcategories within a taxonomy of categories and subcategories related to the top-level category. If at least a portion of the text is determined to be relevant to the category/subcategory, a classifier extracts policy information associated with the category/subcategory. Using text that includes a known policy the classifiers can be trained to correctly recognize categories/subcategories, and the values associated therewith.
1. A method of extracting privacy policy information for a website from its text, the method comprising:
by a processor, determining using statistical classification whether the text is relevant to the website privacy policy;
when the text is determined to be relevant to the privacy policy, determining, by the processor, whether at least a portion of the text is relevant to a category within a taxonomy of categories related to the privacy policy;
when at least a portion of the text is determined to be relevant to the category, extracting from the text, using a first classifier, privacy policy information associated with the category;
by the processor, deriving data based on the extracted privacy policy information, the data being a subset of the privacy policy and providing a summary of the privacy policy that includes the website's policies regarding collection of personally-identifiable information, collection of non-personally-identifiable information, sharing of collected information, and permission to opt-out, wherein the summary of the privacy policy, when presented to a user, obviates the need for the user to read the entire text of the privacy policy such as portions of the privacy policy concerning matters other than the policies on the collection of personally-identifiable information, the collection of non-personally-identifiable information, the sharing of collected information, and the permission to opt-out;
using the processor, presenting to the user when the user visits the website, the data along with a user prompt to accept or decline the privacy policy; and
by the processor, restricting access to at least a portion of the website when an instruction is received, in response to the presented data, to decline the privacy policy.
2. The method of claim 1 , further comprising extracting from the relevant portion of the text, using a second classifier, policy information associated with a subcategory within the taxonomy, the subcategory being related to the category.
3. The method of claim 2 , wherein the subcategory is related to collecting personally-identifiable information, and the subcategory is selected from the group consisting of collection of name, collection of address, collection of email address, and collection of (“Internet Protocol”) IP address.
4. The method of claim 1 , wherein the text comprises one of a sentence and a document.
5. The method of claim 1 , wherein at least one of analyzing, determining, and extracting comprises machine learning by the processor.
6. The method of claim 1 , wherein at least one of analyzing, determining, and extracting comprises natural language processing.
7. The method of claim 1 , wherein extracting the policy information using the first classifier comprises employing statistical classification.
8. The method of claim 7 , wherein at least one of the statistical classification used during analyzing the text and the statistical classification employed during extracting the policy information comprises at least one of multinomial logistic regression, word profile similarity comparison, naive Bayes classification, k-nearest neighbor classification, and maximal likelihood based classification.
9. The method of claim 1 , wherein the category is selected from the group consisting of collecting personally-identifiable information, collecting non-personally-identifiable information, sharing collected information, and allowing opt-out.
10. The method of claim 1 , further comprising:
storing the extracted policy information in a database; and
transmitting the stored policy information.
11. The method of claim 10 , wherein the database comprises at least one of a local database and a distributed database.
12. The method of claim 1 , wherein the statistical classification includes at least one of machine learning and natural language processing.
13. The method of claim 1 , further comprising permitting, by the processor, access to the website when an instruction is received, in response to the presented data, to accept the privacy policy.
14. The method of claim 1 , further comprising:
detecting a requirement by the website that a user accept or decline the privacy policy, wherein deriving and presenting the data is effected in response to the requirement.
15. The method of claim 1 , wherein the summary of the privacy policy includes information on the category within the taxonomy of categories.
16. A system for extracting privacy policy information for a website from its text, the system comprising:
at least one storage medium, at least one of the at least one storage medium storing the text; and
a processor configured, by instructions stored in at least one of the at least one storage medium, as:
(i) an analyzer operative to (a) determine using statistical classification if the text is relevant to the website privacy policy and (b) when the text is determined to be relevant to the privacy policy, determine whether at least a portion of the text is relevant to a category within a taxonomy of categories related to the privacy policy; and
(ii) a first classifier operative to extract, from the text, privacy policy information associated with the category, when at least a portion of the text is determined to be relevant to the category, wherein the processor is configured to derive data based on the extracted privacy policy information, present to a user when the user visits the website, the data along with a user prompt to accept or decline the privacy policy, and restrict access to at least a portion of the website when an instruction is received, in response to the presented data, to decline the privacy policy, the data being a subset of the privacy policy and providing a summary of the privacy policy that includes the website's policies regarding collection of personally-identifiable information, collection of non-personally-identifiable information, sharing of collected information, and permission to opt-out, wherein the summary of the privacy policy, when presented to the user, obviates the need for the user to read the entire text of the privacy policy such as portions of the privacy policy concerning matters other than the policies on the collection of personally-identifiable information, the collection of non-personally-identifiable information, the sharing of collected information, and the permission to opt-out.
17. The system of claim 16 , wherein the processor is further configured as a second classifier operative to extract, from the relevant portion of the text, policy information associated with a subcategory within the taxonomy, the subcategory being related to the category.
18. The system of claim 17 , wherein the subcategory is related to collecting personally-identifiable information, and the subcategory is selected from the group consisting of collection of name, collection of address, collection of email address, and collection of IP address.
19. The system of claim 16 , wherein the text comprises one of a sentence and a document.
20. The system of claim 16 , wherein at least one of the analyzer and the first classifier is configured for machine learning.
21. The system of claim 16 , wherein at least one of the analyzer and the first classifier is configured for natural language processing.
22. The system of claim 16 , wherein the first classifier employs statistical classification.
23. The system of claim 22 , wherein at least one of the statistical classification used by the analyzer and the statistical classification employed by the first classifier comprises at least one of multinomial logistic regression, word profile similarity comparison, naive Bayes classification, k-nearest neighbor classification, and maximal likelihood based classification.
24. The system of claim 16 , wherein the category is selected from the group consisting of collecting personally-identifiable information, collecting non-personally-identifiable information, sharing collected information, and allowing opt-out.
25. The system of claim 16 , wherein the processor is further configured to:
store the extracted policy information in a database; and
transmit the stored policy information.
26. The system of claim 25 , wherein the database comprises at least one of a local database and a distributed database.
27. The system of claim 16 , wherein the processor is further configured to adjust the first classifier.
28. The system of claim 16 , wherein the statistical classification includes at least one of machine learning and natural language processing.
29. The system of claim 16 , wherein the processor is further configured to permit access to the website when an instruction is received, in response to the presented data, to accept the privacy policy.
30. The system of claim 16 , wherein the summary of the privacy policy includes information on the category within the taxonomy of categories.
31. A method of extracting privacy policy information for a website from its text, the method comprising:
by a processor, determining using statistical classification whether the text is relevant to the website privacy policy;
when the text is determined to be relevant to the privacy policy, determining, by the processor, whether at least a portion of the text is relevant to a category within a taxonomy of categories related to the privacy policy;
when at least a portion of the text is determined to be relevant to the category, extracting from the text, using a first classifier, privacy policy information associated with the category;
by the processor, deriving data based on the extracted privacy policy information, the data being a subset of the privacy policy and providing a summary of the privacy policy that includes the website's policies regarding collection of personally-identifiable information, collection of non-personally-identifiable information, sharing of collected information, and permission to opt-out, wherein the summary of the privacy policy, when presented to a user, obviates the need for the user to read the entire text of the privacy policy such as portions of the privacy policy concerning matters other than the policies on the collection of personally-identifiable information, the collection of non-personally-identifiable information, the sharing of collected information, and the permission to opt-out;
using the processor, presenting to the user in real-time the data along with a user prompt to accept or decline the privacy policy; and
by the processor, restricting access to at least a portion of the website when an instruction is received, in response to the presented data, to decline the privacy policy.
32. A system for extracting privacy policy information for a website from its text, the system comprising:
at least one storage medium, at least one of the at least one storage medium storing the text; and
a processor configured, by instructions stored in at least one of the at least one storage medium, as:
(i) an analyzer operative to (a) determine using statistical classification if the text is relevant to the website privacy policy and (b) when the text is determined to be relevant to the privacy policy, determine whether at least a portion of the text is relevant to a category within a taxonomy of categories related to the privacy policy; and
(ii) a first classifier operative to extract, from the text, privacy policy information associated with the category, when at least a portion of the text is determined to be relevant to the category, wherein the processor is configured to derive data based on the extracted privacy policy information, present to a user in real-time the data along with a user prompt to accept or decline the privacy policy, and restrict access to at least a portion of the website when an instruction is received, in response to the presented data, to decline the privacy policy, the data being a subset of the privacy policy and providing a summary of the privacy policy that includes the website's policies regarding collection of personally-identifiable information, collection of non-personally-identifiable information, sharing of collected information, and permission to opt-out, wherein the summary of the privacy policy, when presented to the user, obviates the need for the user to read the entire text of the privacy policy such as portions of the privacy policy concerning matters other than the policies on the collection of personally-identifiable information, the collection of non-personally-identifiable information, the sharing of collected information, and the permission to opt-out.