Object interactive user interface using speech recognition and natural language processing
First Claim
1. A method of interacting with an object via a computer using utterances, the method comprising:
- searching a context-specific grammar file for a matching phrase for the utterance;
searching a general grammar file for the matching phrase if the matching phrase is not found in the context-specific grammar file;
searching a dictation grammar for the matching phrase if the matching phrase is not found in the general file;
searching a context-specific dictation model for the matching phrase if the matching phrase is not found in the dictation grammar file, searching a database for a matching entry for the matching phrase with a natural language processor; and
performing an action associated with the matching entry if the match entry is found in the database.
4 Assignments
0 Petitions
Accused Products
Abstract
A system and method for interacting with objects, via a computer using utterances, speech processing and natural language processing. A Data Definition File relates networked objects and a speech processor. The Data Definition File encompasses a memory structure relating the objects, including grammar files, a context-specific dictation model, and a natural language processor. The speech processor searches a first grammar file for a matching phrase for the utterance, and for searching a second grammar file for the matching phrase if the matching phrase is not found in the first grammar file. The system also includes a natural language processor for searching a database for a matching entry for the matching phrase; and an application interface for performing an action associated with the matching entry if the matching entry is found in the database. The system utilizes context-specific grammars and dictation models, thereby enhancing speech recognition and natural language processing efficiency. Additionally, for each user the system adaptively and interactively “learns” words and phrases, and their associated meanings, storing the adaptive updates into user voice profiles. Because the user voice profiles can be stored locally or remotely, users can access the adaptively learned words and phrases at various locations.
610 Citations
76 Claims
-
1. A method of interacting with an object via a computer using utterances, the method comprising:
-
searching a context-specific grammar file for a matching phrase for the utterance;
searching a general grammar file for the matching phrase if the matching phrase is not found in the context-specific grammar file;
searching a dictation grammar for the matching phrase if the matching phrase is not found in the general file;
searching a context-specific dictation model for the matching phrase if the matching phrase is not found in the dictation grammar file, searching a database for a matching entry for the matching phrase with a natural language processor; and
performing an action associated with the matching entry if the match entry is found in the database. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 20, 21)
replacing at least one word in the matching phrase prior to searching the database.
-
-
3. The method of claim 2 wherein the replacing of the at least one word comprises substituting a wildcard for the at least one word.
-
4. The method of claim 3 wherein the replacing of the at least one word comprises substituting a proper name for the at least one word.
-
5. The method of claim 4 further comprising:
text formatting the matching phrase prior to searching the database.
-
6. The method of claim 4 further comprising:
weighting individual words in the matching phrase according to a relative significance of the individual words prior to searching the database.
-
7. The method of claim 1 further comprising:
updating a user voice profile with at least one of the database, the context-specific grammer file and the general grammar file with the matching phrase if the matching entry is not found in the database.
-
8. The method of claim 7 further comprising:
storing the user voice profile locally.
-
9. The method of claim 7 further comprising:
storing the user voice profile at a remote location over a network.
-
10. The method of claim 7 further comprising:
storing the user voice profile locally and at a remote location over a network.
-
11. The method of claim 1 further comprising:
generating a confidence value for the matching entry.
-
12. The method of claim 11 further comprising:
comparing the confidence value and a threshold value.
-
20. The method of claim 1 wherein the object is a web page.
-
21. The method of claim 1 wherein the object is a help file.
-
13. The method of 12 further comprising:
-
determining whether a required number of words from the matching phrase are present in the matching entry. - View Dependent Claims (14, 15, 16, 17, 18, 19)
prompting a user whether the matching entry is a correct interpretation of the utterance if the required number of words from the matching phrase are not present in the matching entry.
-
-
15. The method of claim 14 further comprising:
prompting a user for additional information if the matching entry is not a correct interpretation of the utterance.
-
16. The method of claim 15 further comprising:
updating at least one of the database, the context-specific grammar file and the general grammer file with the additional information.
-
17. The method of claim 16 further comprising:
storing the user voice profile locally.
-
18. The method of claim 16 further comprising:
storing the user voice profile at a remote location over a network.
-
19. The method of claim 16 further comprising;
storing the user voice profile locally and at a remote location over a network.
-
22. A system of interacting with a computer using utterances, the system comprising:
-
a speech processor configured to search a context-specific grammar file for a matching phrase for the utterance, to search a general grammar file for the matching phrase if the matching phrase is not found in the context-specific grammer file, to search a dictation grammar for the matching phrase if the matching phrase is not found in the general grammar file, and to search a context-specific dictation model if the matching phrase is not found in the dictation grammar;
a natural language processor configured to search a database for a matching entry for the matching phase; and
an application interface configured to perform an action associated with the matching entry if the matching entry is found in the database. - View Dependent Claims (23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38)
a variable replacer in the natural language processor configured to substitute a wildcard for the at least one word in the matching phrase.
-
-
30. The system of claim 28 further comprising:
a pronoun substituter in the natural language processor configure to substitute a proper name for at least one word in the matching phrase.
-
31. The system of claim 22 further comprising:
a string formatter configured to text format the matching phrase prior to searching the database.
-
32. The system of claim 22 further comprising:
a word weighter configured to weigh individual words in the matching phrase according to a relative significance of the individual words prior to searching the database.
-
33. The system of claim 22 further comprising:
a search engine in the natural language processor configured to generate a confidence value for the matching entry.
-
34. The system of claim 33 wherein the natural language processor is further configured to compare the confidence value with a threshold value.
-
35. The system of claim 34 further comprising:
a boolean tester configured to determine whether a required number of words from the matching phrase are present in the matching entry.
-
36. The system of claim 35 wherein the natural language processor is further configured to prompt a user whether the matching entry is a correct interpretation of the utterance if the required number of words from the matching phrase are not present in the matching entry.
-
37. The system of claim 35 wherein the natural language processor is further configured to prompt a user for additional information if the matching entry is not a correct interpretation of the utterance.
-
38. The system of claim 37 wherein the natural language processor is further configured to update at least one of the database, the context-specific grammar file and the general grammar file with the additional information.
-
39. A computer readable medium encoded with data and instructions, when read by a computer will cause the computer to:
-
search a context-specific grammar file for a matching phrase for an utterance;
search a general grammar file for the matching phrase if the matching phrase is not found in the context-specific grammar file;
search a dictation grammar for the matching phrase if the matching phrase is not found in the general grammar file;
search a context-specific dictation model for the matching phrase if the matching phrase is not found in the dictation grammar file;
search a database for a matching entry for the matching phrase with a natural language processor; and
perform an action associated with the matching entry if the matching entry is found in the database. - View Dependent Claims (40, 41, 42, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57)
replace at least one word in the matching phrase prior to searching the database.
-
-
41. The computer readable medium of claim 40 wherein the replacing of the at least one word comprises substituting a wildcard for the at least one word.
-
42. The computer readable medium of claim 41 wherein the replacing of the at least one word comprises substituting a proper name for the at least one word.
-
44. The computer readable medium of claim 42 wherein the instructions further causes a computer to:
weigh individual words in the matching phrase according to a relative significance of the individual words prior to searching the database.
-
45. The computer readable medium of claim 39 wherein the instructions further causes a computer to:
update a user voice profile with at least one of the database, the context-specific grammar file and the general grammar file with the marching phrase if the matching entry is not found in the database.
-
46. The computer readable medium of claim 45 wherein the instructions further causes a computer to:
store the user voice profile locally.
-
47. The computer readable medium of claim 45 wherein the instructions further causes a computer to:
store the user voice profile remote location over a network.
-
48. The computer readable medium of claim 45 wherein the instructions further causes a computer to:
store the user voice profile locally and at a remote location over a network.
-
49. The computer readable medium of claim 39 wherein the instructions further causes a computer to:
generate a confidence values for the matching entry.
-
50. The computer readable medium of claim 49 wherein the instructions further causes a computer to:
compare the confidence value with a threshold value.
-
51. The computer readable medium of claim 50 wherein the instructions further causes a computer to:
determine whether a required number of words from the matching phrase are present in the matching entry.
-
52. The computer readable medium of claim 51 wherein the instructions further causes a computer to:
prompt a user whether the matching entry is a correct interpretation of the utterance if the required number of words from the matching phrase are not present in the matching entry.
-
53. The computer readable medium of claim 52 wherein the instructions further causes a computer to:
prompt a user for additional information if the matching entry is not a correct interpretation of the utterance.
-
54. The computer readable medium of claim 53 wherein the instructions further causes a computer to:
update at least one of the database, the context-specific grammar file and the general grammar file with the additional information.
-
55. The computer readable medium of claim 54 wherein the instructions further causes a computer to:
store the user voice profile locally.
-
56. The computer readable medium of claim 54 wherein the instructions further causes a computer to:
store the user voice profile remote location over a network.
-
57. The computer readable medium of claim 54 wherein the instructions further causes a computer to:
store the user voice profile locally and at a remote location over a network.
-
43. The computer readable medium of clam 42 wherein the instructions further causes a computer to:
text format the matching phrase prior to searching the database.
-
58. An apparatus comprising:
-
means for searching a context-specific grammar file for a matching phrase for an utterance;
means for searching a general grammar file for the matching phrase if the marching phrase is not found in the context-specific grammar file;
means for searching a dictation grammar for the mating phrase if the matching phrase is not found in the general grammar file;
means for searching a context-specific dictation model for the matching phrase if the matching phrase is not found in the dictation grammar file, means for searching a database for a matching entry for the matching phrase with a natural language processor; and
means for performing an action associated with the matching a entry if the matching entry is found in the database. - View Dependent Claims (59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76)
means for replacing at least one word in the matching phrase prior to searching the database.
-
-
60. The apparatus of claim 59 wherein the means for replacing of the at least one word is configured to substitute a wildcard for the at least one word.
-
61. The apparatus of claim 60 wherein the means for replacing of the at least one word is configured to substituting a proper name for the at least one word.
-
62. The apparatus of claim 61 further comprising:
means for text formatting the matching phrase prior to searching the database.
-
63. The apparatus of claim 61 further comprising:
means for weighting individual words in the matching phrase according to a relative significance of the individual words prior to searching the database.
-
64. The apparatus of claim 58 further comprising:
means for updating a user voice profile with at least one of the database, the context-specific grammar file and the general grammar file with the matching phrase if the matching entry is not found in the database.
-
65. The apparatus of claim 64 further comprising:
means for storing the user voice profile locally.
-
66. The apparatus of claim 64 further comprising:
means for storing the user voice profile remote location over a network.
-
67. The apparatus of claim 64 further comprising:
means for storing the user voice profile locally and at a remote location over a network.
-
68. The apparatus of claim 58 further comprising:
means for generating a confidence values for the matching entry.
-
69. The apparatus of claim 68 further comprising:
means for comparing the confidence value with a threshold value.
-
70. The apparatus of claim 69 further comprising:
means for determining whether a required number of words from the matching phrase are present in the matching entry.
-
71. The apparatus of claim 70 for comprising:
means for prompting a user whether the matching entry is a correct interpretation of the utterance if the required number of words from the matching phrase are not present in the matching entry.
-
72. The apparatus of claim 71 further comprising:
means for prompting a user for additional information if the matching entry is not a correct interpretation of the utterance.
-
73. The apparatus of claim 72 further comprising:
means for updating at least one of the database, the context-specific grammar file and the general grammar file with the additional information.
-
74. The apparatus of claim 73 further comprising:
means for storing the user voice profile locally.
-
75. The apparatus of claim 73 further comprising:
means for storing the user voice profile remote location over a network.
-
76. The apparatus of claim 73 further comprising:
means foe storing the user voice profile locally and at a remote location over a network.
Specification