Method and system for filtering text messages

• US 20080201411A1
• Filed: 02/21/2007
• Published: 08/21/2008
• Est. Priority Date: 02/21/2007
• Status: Active Grant

• Current Assignee: Vibes Media LLC
• Original Assignee: Vibes Media LLC
• Inventors: Paritosh, Praveen K.
• Granted Patent: US 8,909,713 B2
• Time in Patent Office: Days
• US Class Current: 709/203
• CPC Class Codes: H04L 51/212 using filtering or selective blocking
• CPC Class Codes: H04L 51/58 Message adaptation for wireless communication
• CPC Class Codes: H04L 63/0245 Filtering by information in the payload

Abstract

A system and method is provided for filtering text messages to determine which of the messages, if any, contains undesirable or unsuitable content. The method includes receiving a message containing at least one text character. The text is manipulated to generate a plurality of tokens that are compared with data contained in a plurality of databases. As a result, a plurality of probabilities are generated related to the suitability of the message. The probabilities are weighted to generate an overall probability related to the suitability of the message. The overall probability is then compared to a threshold value to rate the suitability of the message. Further, the rating associated with the message is displayed on a computer display screen or the like.

Claims

1. A method comprising the steps of:

receiving a message comprising text having at least one character;

manipulating the text to generate a plurality of tokens;

comparing the plurality of tokens with data contained in at least one database to generate a plurality of probabilities related to the suitability of the message;

weighing the probabilities to generate an overall probability related to the suitability of the message;

comparing the overall probability to a threshold value to rate the suitability of the message; and

,

displaying the rating associated with the message.

2. The method of claim 1 further comprising the step of rating the suitability of a fragment of another message to generate at least a portion of the data contained in the at least one database.

3. The method of claim 1 further comprising the step of rating the suitability of another message to generate at least a portion of the data contained in the at least one database.

4. The method of claim 1 further comprising the step of comparing historical data based on a selected tokenization strategy to generate a plurality of weights used in the step of weighing the probabilities.

5. The method of claim 4 further comprising the step of automatically updating the weights.

6. The method of claim 1 further comprising the step of selecting unacceptable text within another message to generate at least a portion of the data contained in the at least one database.

7. The method of claim 1 further comprising the step of executing the method on a personal handheld mobile device.

8. The method of claim 1 further comprising the step of executing the method on a carrier network.

9. The method of claim 1 wherein the message is received from a short message service.

10. The method of claim 1 wherein the plurality of tokens comprise at least one from a group comprising:

words, phrases, n-grams, numbers and characters.

11. The method of claim 1 wherein the data contained in the at least one database is derived, at least in part, from historical message data.

12. The method of claim 1 further comprising the step of displaying the message if the overall probability is within a defined range.

13. The method of claim 1 wherein the data within the at least one database comprising at least one trademark.

14. A method comprising the steps of:

manipulating a text message having less than 161 characters to generate a plurality of tokens;

generating at least two probabilities related to the suitability of the message based, at least in part, on a comparison between the plurality of tokens and data contained in at least one database;

generating an overall probability related to the suitability of the message based, at least in part, on a weighing of the at least two probabilities; and

,

displaying the message if the overall probability is within a defined range.

15. The method of claim 14 further comprising the step of rating the suitability of a fragment of another message to generate at least a portion of the data contained in the at least one database.

16. The method of claim 14 further comprising the step of rating the suitability of another message to generate at least a portion of the data contained in the at least one database.

17. The method of claim 14 further comprising the step of comparing historical data based on a selected tokenization strategy to generate a plurality of weights for weighing the at least two probabilities.

18. The method of claim 17 further comprising the step of automatically updating the weights.

19. The method of claim 14 further comprising the step of selecting unacceptable text within another message to generate at least a portion of the data contained in the at least one database.

20. The method of claim 14 further comprising the step of executing the method on a personal handheld mobile device.

21. The method of claim 14 further comprising the step of executing the method on a carrier network.

22. The method of claim 14 further comprising the step of receiving the message from a short message service.

23. The method of claim 14 wherein the plurality of tokens comprise at least one from a group comprising:

words, phrases, n-grams, numbers and characters.

24. The method of claim 14 wherein the data contained in the at least one database is derived, at least in part, from historical message data.

25. The method of claim 14 further comprising the step of displaying the overall probability related to the suitability of the message.

26. The method of claim 14 wherein the data within the at least one database comprising at least one trademark.

27. A method comprising the steps of:

manipulating text within a text message having 160 characters or less to generate a plurality of tokens;

comparing the plurality of tokens with data contained in at least one database to generate a plurality of probabilities related to the suitability of the message;

comparing historical data based on a selected tokenization strategy to generate a plurality of weights;

generating with the plurality of probabilities and the plurality of weights an overall probability related to the suitability of the message; and

,

comparing the overall probability to a threshold to rate the suitability of the message.

28. The method of claim 27 further comprising the step of rating the suitability of a fragment of another message to generate at least a portion of the data contained in the at least one database.

29. The method of claim 27 further comprising the step of rating the suitability of another message to generate at least a portion of the data contained in the at least one database.

30. The method of claim 27 further comprising the step of automatically updating the weights.

31. The method of claim 27 further comprising the step of selecting unacceptable text within another message to generate at least a portion of the data contained in the at least one database.

32. The method of claim 27 further comprising the step of executing the method on a personal handheld mobile device.

33. The method of claim 27 further comprising the step of executing the method on a carrier network.

34. The method of claim 27 further comprising the step of receiving the message from a short message service.

35. The method of claim 27 wherein the plurality of tokens comprise at least one from a group comprising:

words, phrases, n-grams, numbers and characters.

36. The method of claim 27 wherein the data contained in the at least one database is derived, at least in part, from historical message data.

37. The method of claim 27 further comprising the step of displaying the message if the message is found suitable.

38. The method of claim 27 wherein the data within the at least one database comprising at least one trademark.

39. A method comprising the steps of:

selecting a tokenization strategy from a plurality of tokens comprising words, phrases, n-grams, numbers and characters.

manipulating text within a text message to generate data for each of the tokens selected;

comparing the token data with data contained in at least one database to generate a plurality of probabilities related to the suitability of the message;

weighing the probabilities to generate an overall probability related to the suitability of the message;

comparing the overall probability to a threshold to rate the suitability of the message; and

,

displaying the rating associated with the message.

40. The method of claim 39 further comprising the step of rating the suitability of a fragment of another message to generate at least a portion of the data contained in the at least one database.

41. The method of claim 39 further comprising the step of rating the suitability of another message to generate at least a portion of the data contained in the at least one database.

42. The method of claim 39 further comprising the step of comparing historical data based on a selected tokenization strategy to generate a plurality of weights for the step of weighing the probabilities.

43. The method of claim 42 further comprising the step of automatically updating the weights.

44. The method of claim 39 further comprising the step of selecting unacceptable text within another message to generate at least a portion of the data contained in the at least one database.

45. The method of claim 39 further comprising the step of executing the method on a personal handheld mobile device.

46. The method of claim 39 further comprising the step of executing the method on a carrier network.

47. The method of claim 39 further comprising the step of receiving the text message from a short message service.

48. The method of claim 39 wherein the plurality of tokens comprise at least one from a group comprising:

words, phrases, n-grams, numbers and characters.

49. The method of claim 39 wherein the data contained in the at least one database is derived, at least in part, from historical message data.

50. The method of claim 39 further comprising the step of displaying the message if the rating is within a defined range.

51. The method of claim 39 wherein the data within the at least one database comprising at least one trademark.

52. A method comprising the steps of:

receiving a message comprising text having at least one character;

manipulating the text to generate a plurality of tokens;

comparing the plurality of tokens with data contained in at least one database to generate a plurality of probabilities related to the suitability of the message;

weighing the probabilities to generate an overall probability related to the suitability of the message;

comparing the overall probability to a threshold to rate the suitability of the message; and

,

displaying the rating associated with the message.

53. The method of claim 52 further comprising the step of rating the suitability of a fragment of another message to generate at least a portion of the data contained in the at least one database.

54. The method of claim 52 further comprising the step of rating the suitability of another message to generate at least a portion of the data contained in the at least one database.

55. The method of claim 52 further comprising the step of comparing historical data based on a selected tokenization strategy to generate a plurality of weights for the step of weighing the probabilities.

56. The method of claim 55 further comprising the step of automatically updating the weights.

57. The method of claim 52 further comprising the step of selecting unacceptable text within another message to generate at least a portion of the data contained in the at least one database.

58. The method of claim 52 further comprising the step of executing the method on a personal handheld mobile device.

59. The method of claim 52 further comprising the step of executing the method on a carrier network.

60. The method of claim 52 wherein the message is received from a short message service.

61. The method of claim 52 wherein the plurality of tokens comprise at least one from a group comprising:

words, phrases, n-grams, numbers and characters.

62. The method of claim 52 wherein the data contained in the at least one database is derived, at least in part, from historical message data.

63. The method of claim 52 further comprising the step of displaying the message if the rating is within a defined range.

64. The method of claim 52 wherein the data within the at least one database comprising at least one trademark.