Patent US6675162B1 successfully refreshed from Google Patents.
US6675162B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for scanning, analyzing and handling various kinds of digital information content
Assignee: Microsoft Technology Licensing LLC
•
Filing: 2001-05-07
•
Granted: 2004-01-06
•
Expires: 2021-05-07
Abstract
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.
Inventors
- 👤 Adrian Peter Russell-Falla
- 👤 Andrew Bard Hanson
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-28 15:46
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/90; G06F16/95; G06F16/953; G06F16/9535; Y; Y10; Y10S; Y10S707/00; Y10S707/953; Y10S707/959; Y10S707/99931; Y10S707/99933; Y10S707/99935; Y10S707/99939
Claims Analysis
Total Claims: 25
Claim 1
Independent Claim
144 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email relative to a selected characteristic, the program comprising: first means for identifying natural language textual portions of the email and forming a list of words that appear in the identified natural language textual portions of the email; a database of predetermined words that are associated with the selected characteristic; second means for acquiring 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; and neural network means for calculating a rating for the email responsive to the weighted set of terms, the neural network means including means for determining and taking into account a total number of natural language words that appear in the identified natural language textual portions of the email.
Claim 2
Dependent Claim
144 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email relative to a selected characteristic, the program comprising: first means for identifying natural language textual portions of the email and forming a list of words that appear in the identified natural language textual portions of the email; a database of predetermined words that are associated with the selected characteristic; second means for acquiring 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; and neural network means for calculating a rating for the email responsive to the weighted set of terms, the neural network means including means for determining and taking into account a total number of natural language words that appear in the identified natural language textual portions of the email.
Claim 3
Dependent Claim
48 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email according to claim 1 wherein the selected characteristic is pornographic content; and the database includes a predetermined a list of words and phrases that are associated with emails having pornographic content.
Claim 4
Dependent Claim
52 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email according to claim 1 and further comprising means for storing a predetermined threshold rating, and means for comparing the calculated rating to the threshold rating to determine whether the email likely has the selected characteristics.
Claim 5
Dependent Claim
48 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email according to claim 1 wherein the selected characteristic is hate-mongering content; and the database includes a predetermined a list of words and phrases that are associated with emails having hate-mongering content.
Claim 6
Dependent Claim
48 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email according to claim 1 wherein the selected characteristic is racist content; and the database includes a predetermined a list of words and phrases that are associated with emails having racist content.
Claim 7
Dependent Claim
48 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email according to claim 1 wherein the selected characteristic is terrorist content; and the database includes a predetermined a list of words and phrases that are associated with emails having terrorist content.
Claim 8
Dependent Claim
48 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email according to claim 1 wherein the selected characteristic is neo-Nazi content; and the database includes a predetermined a list of words and phrases that are associated with emails having neo-Nazi content.
Claim 9
Dependent Claim
52 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email according to claim 1 wherein the selected characteristic is illicit drugs content; and the database includes a predetermined a list of words and phrases that are associated with emails having content pertaining to illicit drugs.
Claim 10
Dependent Claim
81 words
A computer-readable medium storing executable instructions for use in conjunction with a program to rate an email according to claim 1 wherein the selected characteristic is content selected as presenting a liability risk to persons having managerial responsibility for the email material accessed by others; and the database includes a predetermined list of words and phrases that are associated with emails having content likely to present a liability risk to persons having managerial responsibility for the email material accessed by others.
Claim 11
Independent Claim
106 words
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; and in a neural network system, calculating a rating for the email responsive to the weighted set of terms.
Claim 12
Independent Claim
106 words
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; and in a neural network system, calculating a rating for the email responsive to the weighted set of terms.
Claim 13
Dependent Claim
44 words
A method according to claim 10 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.
Claim 14
Dependent Claim
59 words
A method according to claim 10 wherein said calculating includes: summing the weighted set of terms together to form a sum; multiplying the sum by a predetermined modifier to scale the sum; determining a 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.
Claim 15
Dependent Claim
18 words
A method according to claim 10 wherein the preexisting database comprises words selected as indicative of pornographic content.
Claim 16
Dependent Claim
18 words
A method according to claim 10 wherein the preexisting database comprises words selected as indicative of hate-mongering content.
Claim 17
Dependent Claim
18 words
A method according to claim 10 wherein the preexisting database comprises words selected as indicative of racist content.
Claim 18
Dependent Claim
18 words
A method according to claim 10 wherein the preexisting database comprises words selected as indicative of terrorist content.
Claim 19
Dependent Claim
18 words
A method according to claim 10 wherein the preexisting database comprises words selected as indicative of neo-Nazi content.
Claim 20
Dependent Claim
20 words
A method according to claim 10 wherein the preexisting database comprises words selected as indicative content pertaining to illicit drugs.
Claim 21
Dependent Claim
190 words
A method according to claim 10 for building the preexisting database including a target attribute set for use in analyzing content of the email, the method further comprising: acquiring a plurality of sample emails for use as training emails; designating each of the training data sets as “yes” or “no” with respect to a predetermined content characteristic; parsing through the content of all the training emails to form a list of regular expressions that appear in the training emails; forming data reflecting a frequency of occurrence of each regular expression in the training emails; analyzing the frequency of occurrence data, in view of the “yes” or “no” designation of each email, to identify and select a set of regular expressions that are indicative of either a “yes” designation or a “no” designation of an email with respect to the predetermined characteristic; and storing the selected set of regular expressions to form a target attribute set based on the acquired training emails, whereby the target attribute set provides a set of regular expressions that are useful in the neural network system in discriminating email content relative to the predetermined content characteristic.
Claim 22
Dependent Claim
227 words
A method according to claim 10 wherein reading a corresponding weight includes assigning weights to a list of regular expressions for use in analyzing content of the email, the method further comprising: providing a predetermined target attribute set associated with a predetermined group of training emails, the target attribute set including a list of regular expressions that are deemed useful in a neural network system for discriminating email content relative to a predetermined content characteristic; assigning an initial weight to each of the regular expressions in the target attribute set, thereby forming a weight database; designating each of the group of training emails as either “yes” or “no” relative to whether it exhibits the predetermined content characteristic; examining one of the group of training emails to identify all regular expressions within the email that also appear in the target attribute set, thereby forming a match list for said email; in the neural network system, rating the examined email using the weightings in the weight database; comparing the rating of the examined email to the corresponding “yes” or “no” designation to form a first error term; repeating said examining, rating and comparing operations for each of the remaining emails in the group of training emails to form additional error terms; and adjusting the weights in the weight database in response to the first and the additional error terms.
Claim 23
Dependent Claim
16 words
A method of assigning weights according to claim 20 wherein the predetermined content characteristic is pornography.
Claim 24
Independent Claim
139 words
A method of controlling access to potentially offensive or harmful emails comprising: in conjunction with a program executing on a digital computer, examining an 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, and using a neural network system to form a rating, the database including regular expressions previously associated with potentially 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 email to a predetermined threshold rating; and if the rating indicated that the email is more likely to be offensive or harmful than an email having the threshold rating, blocking the email from being displayed to the user.
Claim 25
Independent Claim
139 words
A method of controlling access to potentially offensive or harmful emails comprising: in conjunction with a program executing on a digital computer, examining an 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, and using a neural network system to form a rating, the database including regular expressions previously associated with potentially 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 email to a predetermined threshold rating; and if the rating indicated that the email is more likely to be offensive or harmful than an email having the threshold rating, blocking the email from being displayed to the user.
References Cited (Backward Citations)
US5343251A
Cited
US5678041A
Cited
US5696898A
Cited
US5706507A
Cited
US5832212A
Cited
US6453327B1
Cited
US5835722A
Cited
US5907677A
Cited
US6072942A
Cited
US6144934A
Cited
US5911043A
Cited
US5996011A
Cited
US6047277A
Cited
US6266664B1
Cited
US6009410A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2007-01-05 | 2007-07-07 | 2008-01-06 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-01-05 | 2011-07-07 | 2012-01-06 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-01-05 | 2015-07-07 | 2016-01-06 | $7700.00 | Window Closed / Lapsed |