Rating and controlling access to emails

• US 7,130,850 B2
• Filed: 10/01/2003
• Issued: 10/31/2006
• Est. Priority Date: 10/01/1997
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Hanson, Andrew Bard, Russell-Falla, Adrian Peter
• Primary Examiner(s): Ali, Mohammad
• Assistant Examiner(s): LIN, SHEW FEN
• Application Number:
  US10/676,225
• Publication Number:
  US 20050108227A1
• Time in Patent Office: 1,126 Days
• Field of Search: 707 1- 10, 709/201, 709/206
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: Y10S 707/959 Network
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99939 Privileged access

Abstract

Computer-implemented methods are described for, first, characterizing a specific category of information content—pornography, for example—and then accurately identifying instances of that category of content within a real-time media stream, such as a web page, e-mail or other digital dataset. This content-recognition technology enables a new class of highly scalable applications to manage such content, including filtering, classifying, prioritizing, tracking, etc. An illustrative application of the invention is a software product for use in conjunction with web-browser client software for screening access to web pages that contain pornography or other potentially harmful or offensive content. A target attribute set of regular expression, such as natural language words and/or phrases, is formed by statistical analysis of a number of samples of datasets characterized as “containing,” and another set of samples characterized as “not containing,” the selected category of information content. This list of expressions is refined by applying correlation analysis to the samples or “training data.” Neural-network feed-forward techniques are then applied, again using a substantial training dataset, for adaptively assigning relative weights to each of the expressions in the target attribute set, thereby forming an awaited list that is highly predictive of the information content category of interest.

Claims

1. A method of controlling access to offensive or harmful emails comprising:

in conjunction with a program executing on a digital computer, examining a downloaded email before the email is displayed to the user;

said examining operation including analyzing the email natural language content relative to a predetermined database of regular expressions to form a rating, the database including regular expressions previously associated with offensive or harmful emails; and

the database further including a relative weighting associated with each regular expression in the database for use in forming the rating;

comparing the rating of the downloaded email to a predetermined threshold rating;

if the rating indicating that the downloaded email is more offensive or harmful than an email having the threshold rating, preventing the downloaded email from being displayed to the user; and

incrementally adjusting the weighting associated with each regular expression in the database based on error data accumulated from analyzing content of emails.

2. A method according to claim 1 wherein preventing comprises blocking the downloaded email from being displayed to the user or deleting the downloaded email.

3. The method according to claim 1 further comprising providing an indication of a reason that the downloaded email was prevented from display.

4. A computer-readable medium storing a computer program for use in conjunction with a program to rate an email relative to unwanted commercial solicitations, the program comprising instructions to:

identify natural language textual portions of the email and form a list of words that appear in the identified natural language textual portions of the email;

access a database of predetermined words that are associated with the unwanted commercial solicitations;

acquire a corresponding weight from the database for each such word having a match in the database so as to form a weighted set of terms;

calculate a rating for the email responsive to the weighted set of terms, the instructions to calculate including instructions to determine and take into account a total number of natural language words that appear in the identified natural language textual portions of the email; and

incrementally adjusting the weighting associated with each regular expression in the database based on error data accumulated from analyzing content of emails.

5. A computer-readable medium storing a computer program for use in conjunction with a program to rate an email according to claim 4 and further comprising instructions to prevent the downloaded email from being displayed to the user if the rating indicated that the downloaded email includes an unwanted commercial solicitation.

6. A computer-readable medium storing a computer program for use in conjunction with a program to rate an email according to claim 5 further comprising instructions to block the downloaded email from being displayed to the user or instructions to delete the downloaded email.

7. A computer-readable medium storing a computer program for use in conjunction with a program to rate an email according to claim 4 and further comprising instructions to store a predetermined threshold rating, and instructions to compare the calculated rating to the threshold rating to determine whether the email has the unwanted commercial solicitations.

8. A method according to claim 4 wherein said predetermined words include words selected from the following categories:

sexually themed content, undesired content and pornographic content.

9. A method of analyzing content of an email, the method comprising:

identifying natural language textual portions of the email;

forming a word listing including all natural language words that appear in the textual portion of the email;

for each word in the word list, querying a preexisting database of selected words to determine whether or not a match exists in the database;

for each word having a match in the database, reading a corresponding weight from the database so as to form a weighted set of terms;

calculating a rating for the email responsive to the weighted set of term; and

incrementally adjusting the weighting associated with each regular expression in the database based on error data accumulated from analyzing content of emails.

10. A method according to claim 9 wherein the method further comprises:

if the rating indicated that the email includes an unwanted commercial solicitation, preventing the email from being displayed to the user.

11. A method according to claim 10 wherein preventing comprises blocking the downloaded email from being displayed to the user or deleting the downloaded email.

12. A method according to claim 9 wherein the method further comprises:

identifying meta-content in the email; and

identifying words from the meta-content of the email in the word list so that the meta-content is taken into account in calculating the rating for the email.

13. A method according to claim 9 wherein said calculating step includes:

summing the weighted set of terms together to form a sum;

multiplying the sum by a predetermined modifier to scale the sum;

determining the total number of words on the email; and

dividing the scaled sum by the total number of words on the email to form the rating.

14. A method according to claim 9 wherein said preexisting database of selected words include words selected from the following categories:

sexually themed content, undesired content and pornographic content.

15. A method according to claim 9 wherein the rating is with respect to whether the email is an unwanted commercial solicitation.

16. A method according to claim 9 wherein the rating is with respect to whether the email is an unwanted commercial solicitation and, based on the rating the email is deleted.

17. A method according to claim 9 wherein based on the rating the email is deleted.

18. A method according to claim 9 wherein the rating is with respect to whether the email is one or more of pornographic, sexually themed, or offensive.

19. A method of controlling access to emails including an unwanted commercial solicitation comprising:

in conjunction with a program executing on a digital computer, examining a downloaded email before the email is displayed to the user;

said examining operation including analyzing the email natural language content relative to a predetermined database of regular expressions to form a rating, the database including regular expressions relating to unwanted commercial solicitations; and

the database further including a relative weighting associated with each regular expression in the database for use in forming the rating;

comparing the rating of the downloaded email to a predetermined threshold rating;

if the rating indicated that the downloaded email is more likely to include an unwanted commercial solicitation than an email having the threshold rating, preventing the downloaded email from being displayed to the user; and

incrementally adjusting the weighting associated with each regular expression in the database based on error data accumulated from analyzing content of emails.

20. A method according to claim 19 wherein preventing comprises blocking the downloaded email from being displayed to the user or deleting the downloaded email.

21. A method according to claim 19 wherein, if the downloaded email is prevented from display, displaying an alternative email to the user.

22. A method according to claim 21 wherein preventing comprises blocking the downloaded email from being displayed to the user or deleting the downloaded email.

23. A method according to claim 19 further comprising providing an indication of a reason that the downloaded email was prevented from display.

24. A method according to claim 19 wherein said regular expressions include expressions selected from the following categories:

sexually themed content, undesired content and pornographic content.