Signature generation using message summaries
View Patent ↗Systems and methods for processing a message are provided. A message may be processed to generate a message summary by removing or replacing certain words, phrases, sentences, punctuation, and the like. Message signatures based upon the message summary may be generated and stored in a signature database, which may be used to identify and/or classify spam messages. Subsequently received messages may be classified by signature and processed based on classification.
1. A method for processing an electronic-mail message, comprising:
receiving a message sent over a communication network, the message including a message body and received at an inbox of a mail device;
receiving an indication from a user that the message is a junk message; and
executing instructions stored in memory, wherein execution of the instructions by a processor:
summarizes the message body to produce a summary, wherein summarizing the message body includes grouping words in the message based on similar meaning, and replacing a group with an identifier that represents the similar meaning,
generates a signature based on the summary,
compares the generated signature to a database of signatures corresponding to signatures of previously received messages, and
processes the message based on at least the generated signature.
2. The method of claim 1 , wherein processing the message includes deleting the message from the inbox.
3. The method of claim 1 , wherein processing the message includes quarantining the message in a junk folder stored at the mail device.
4. The method of claim 1 , wherein processing the message includes rejecting the message from the inbox.
5. The method of claim 1 , further comprising storing the generated signature in memory for use in classifying a subsequently received message.
6. The method of claim 1 , wherein the signature is generated using a transform function.
7. The method of claim 1 , further comprising removing a word that is not useful in classifying the message, wherein the removed word includes a word that appears in a message previously classified as a spam message.
8. The method of claim 1 , wherein summarizing the message body further includes removing redundant information.
9. The method of claim 1 , wherein the signature is generated after the summary meets a minimum byte requirement.
10. The method of claim 1 , further comprising executing instructions by the processor to rank a word in the summary of the message body after the summary is generated, wherein the ranking is based on at least a probability the word occurs in a message.
11. The method of claim 1 , wherein summarizing the messaging body further includes correcting any incorrectly spelled word in the message body prior to removing the one or more non-useful words.
12. A system for processing an electronic-mail message, the system comprising:
memory for storing information regarding a message previously classified as a junk message, the message including a message body; and
a message gateway including a summarization and signature generation engine stored in memory, the summarization and signature engine executable by a processor to:
summarize the message body of a message received over a communications network to produce a summary, wherein summarizing the message body includes grouping words in the message based on similar meaning, and replacing a group with an identifier that represents the similar meaning,
generate a signature based on the summary,
compare the generated signature to a database of signatures corresponding to signatures of previously received messages, and
processes the message based on at least the generated signature.
13. The system of claim 12 , further comprising a communication interface for receiving the message, wherein the message has been classified as a junk message by a user.
14. The system of claim 12 , wherein the message gateway processes the message by deleting the message from the inbox.
15. The system of claim 12 , wherein the message gateway processes the message by quarantining the message in a junk folder stored at the mail device.
16. The system of claim 12 , wherein the message gateway processes the message by rejecting the message from the inbox.
17. The system of claim 12 , wherein the memory further stores the generated signature for use in classifying a subsequently received message.
18. The system of claim 12 , wherein the message gateway removes a word not useful for classifying the message, wherein the removed word includes a word that appears in a message previously classified as a spam message.
19. The system of claim 12 , wherein the execution of instructions by the processor ranks a word in the summary of the message body after the summary is generated, wherein the ranking is based on at least a probability the word occurs in a message.
20. A non-transitory computer-readable storage medium having embodied thereon a program, the program being executable by a processor to perform a method for processing an electronic-mail message, the method comprising:
receiving a message, the message including a message body,
receiving an indication from a user that the message is a junk message;
summarizes the message body to produce a summary, wherein summarizing the message body includes grouping words in the message based on similar meaning, and replacing a group with an identifier that represents the similar meaning,
generating a signature based on the summary;
comparing the generated signature to a database of signatures corresponding to signatures of previously received messages; and
processing the message based on at least the generated signature.