Using a virtual assistant to store a personal voice memo and to obtain a response based on a stored personal voice memo that is retrieved according to a received query
The technology disclosed relates to retrieving a personal memo from a database. The method includes receiving, by a virtual assistant, a natural language utterance that expresses a request, interpreting the natural language utterance according to a natural language grammar rule for retrieving memo data from the natural language utterance, the natural language grammar rule recognizing query information, responsive to interpreting the natural language utterance, using the query information to query the database for a memo related to the query information, and providing, to a user, a response generated in dependence upon the memo related to the query information.
1. A method of retrieving a personal memo from a database, the method comprising:
receiving, from a user, multiple natural language utterances, each including language to trigger storage of memos and each including memo information;
interpreting the received natural language utterances to extract the memo information;
storing, in the database, the memo information as memos that relate to a subject and that have time information associated therewith;
receiving, by a virtual assistant, a natural language utterance that expresses a request;
interpreting the natural language utterance according to a natural language grammar rule for retrieving a memo using the natural language utterance, the natural language grammar rule recognizing query information;
responsive to interpreting the natural language utterance, using the query information to query the database for memos related to the query information and related to the subject;
identifying multiple memos in response to the database query, the identified memos being related to the subject and having the time information associated therewith;
identifying a memo, from the multiple identified memos, that has been most recently stored according to the time information associated with the multiple memos; and
providing, to the user, a response generated in dependence upon the identified memo related to the subject and having been most recently stored.
2. The method of claim 1 , wherein the natural language grammar rule for retrieving the memo is selected from a plurality of domain dependent grammar rules in accordance to contents of the received natural language utterance.
3. The method of claim 1 , wherein the database is queried for the memo related to the query information by searching the database to identify any memo that includes information sufficient to provide an appropriate response to the user.
4. The method of claim 1 , wherein the response is provided to the user, such that the response answers the request expressed by the natural language utterance as opposed to providing a word-for-word repeat of a transcription.
5. The method of claim 1 , further comprising receiving an indication that the user spoke a memo-specific wake phrase before the natural language utterance.
6. The method of claim 1 , wherein the database storing the memo is a structured database, such that the memo is stored in a structured format.
7. The method of claim 1 , wherein the database storing the memo is an unstructured database, such that the memo is stored in an unstructured format.
8. The method of claim 1 , wherein at least one stored memo of the stored memos includes personal information about the user.
9. The method of claim 1 , further comprising:
replacing other previously stored memos that relate to a subject with a most recently stored memo that relates to the subject when multiple natural language utterances including the memo information are received, interpreted and stored in the database as a memo that relates to a subject.
10. The method of claim 1 , further comprising:
assigning a time period to at least one of the stored memos, after which the at least one memo will expire; and
removing the at least one memo from the database when the time period has expired.
11. The method of claim 1 , wherein the memo indicates that a specific entity is the user's favorite.
12. The method of claim 1 , further comprising:
identifying a trigger phrase from the received natural language utterance; and
responsive to identifying the trigger phrase, selecting the natural language grammar rule for retrieving the memo in dependence upon the identified trigger phrase.
13. The method of claim 12 , wherein the trigger phrase includes both a personal pronoun followed by an interrogative pronoun or a relative pronoun that is within 5 words of the personal pronoun.
14. The method of claim 1 , further comprising allowing the user to confirm or acknowledge whether or not the user intended for at least one of the natural language utterances including the memo information to be stored as a memo.
15. The method of claim 14 , further comprising deleting the stored memo related to the at least one of the natural language utterances including the memo information when the user indicates that that natural language utterance including the memo information was not intended to be stored as the memo.
16. A non-transitory computer-readable recording medium having a computer program for retrieving a personal memo from a database recorded thereon, the computer program, when executed on one or more processors, causing the processors to perform a method comprising:
receiving, from a user, multiple natural language utterances, each including language to trigger storage of memos and each including memo information;
interpreting the received natural language utterances to extract the memo information;
storing, in the database, the memo information as memos that relate to a subject and that have time information associated therewith;
receiving, by a virtual assistant, a natural language utterance that expresses a request;
interpreting the natural language utterance according to a natural language grammar rule for retrieving a memo using the natural language utterance, the natural language grammar rule recognizing query information;
responsive to interpreting the natural language utterance, using the query information to query the database for memos related to the query information and related to the subject;
identifying multiple memos in response to the database query, the identified memos being related to the subject and having the time information associated therewith;
identifying a memo, from the multiple identified memos, that has been most recently stored according to the time information associated with the multiple memos; and
providing, to the user, a response generated in dependence upon the identified memo related to the subject and having been most recently stored.
17. The non-transitory computer-readable recording medium of claim 16 , wherein the natural language grammar rule for retrieving the memo is selected from a plurality of domain dependent grammar rules in accordance to contents of the received natural language utterance.
18. The non-transitory computer-readable recording medium of claim 16 , wherein the database is queried for the memo related to the query information by searching the database to identify any memo that includes information sufficient to provide an appropriate response to the user.
19. The non-transitory computer-readable recording medium of claim 16 , wherein the response is provided to the user, such that the response answers the request expressed by the natural language utterance as opposed to providing a word-for-word repeat of a transcription.
20. The non-transitory computer-readable recording medium of claim 16 , wherein the method further comprises receiving an indication that the user spoke a memo-specific wake phrase before the natural language utterance.
21. The non-transitory computer-readable recording medium of claim 16 , wherein the database storing the memo is a structured database, such that the memo is stored in a structured format.
22. The non-transitory computer-readable recording medium of claim 16 , wherein the database storing the memo is an unstructured database, such that the memo is stored in an unstructured format.
23. The non-transitory computer-readable recording medium of claim 16 , wherein at least one stored memo of the stored memos includes personal information about the user.
24. The non-transitory computer-readable recording medium of claim 16 , wherein the method further comprises:
replacing other previously stored memos that relate to a subject with a most recently stored memo that relates to the subject when multiple natural language utterances including the memo information are received, interpreted and stored in the database as a memo that relates to a subject.
25. The non-transitory computer-readable recording medium of claim 16 , wherein the method further comprises:
assigning a time period to at least one of the stored memos, after which the at least one memo will expire; and
removing the at least one memo from the database when the time period has expired.
26. The non-transitory computer-readable recording medium of claim 16 , wherein the memo indicates that a specific entity is the user's favorite.
27. The non-transitory computer-readable recording medium of claim 16 , wherein the method further comprises:
identifying a trigger phrase from the received natural language utterance; and
responsive to identifying the trigger phrase, selecting the natural language grammar rule for retrieving the memo in dependence upon the identified trigger phrase.
28. The non-transitory computer-readable recording medium of claim 27 , wherein the trigger phrase includes both a personal pronoun followed by an interrogative pronoun or a relative pronoun that is within 5 words of the personal pronoun.
29. The non-transitory computer-readable recording medium of claim 16 , wherein the method further comprises allowing the user to confirm or acknowledge whether or not the user intended for at least one of the natural language utterances including the memo information to be stored as a memo.
30. The non-transitory computer-readable recording medium of claim 29 , wherein the method further comprises deleting the stored memo related to the at least one of the natural language utterances including the memo information when the user indicates that that natural language utterance including the memo information was not intended to be stored as the memo.
31. A system including one or more processors coupled to memory, the memory loaded with computer instructions to retrieve a personal memo from a database, the instructions, when executed on the one or more processors, implement actions comprising:
receiving, from a user, multiple natural language utterances, each including language to trigger storage of memos and each including memo information;
interpreting the received natural language utterances to extract the memo information;
storing, in the database, the memo information as memos that relate to a subject and that have time information associated therewith;
receiving, by a virtual assistant, a natural language utterance that expresses a request;
interpreting the natural language utterance according to a natural language grammar rule for retrieving a memo using the natural language utterance, the natural language grammar rule recognizing query information;
responsive to interpreting the natural language utterance, using the query information to query the database for memos related to the query information and related to the subject; and
identifying multiple memos in response to the database query, the identified memos being related to the subject and having the time information associated therewith;
identifying a memo, from the multiple identified memos, that has been most recently stored according to the time information associated with the multiple memos; and
providing, to the user, a response generated in dependence upon the identified memo related to the subject and having been most recently stored.
32. The system of claim 31 , wherein the natural language grammar rule for retrieving the memo is selected from a plurality of domain dependent grammar rules in accordance to contents of the received natural language utterance.
33. The system of claim 31 , wherein the database is queried for the memo related to the query information by searching the database to identify any memo that includes information sufficient to provide an appropriate response to the user.
34. The system of claim 31 , wherein the response is provided to the user, such that the response answers the request expressed by the natural language utterance as opposed to providing a word-for-word repeat of a transcription.
35. The system of claim 31 , wherein the actions further comprise receiving an indication that the user spoke a memo-specific wake phrase before the natural language utterance.
36. The system of claim 31 , wherein the database storing the memo is a structured database, such that the memo is stored in a structured format.
37. The system of claim 31 , wherein the database storing the memo is an unstructured database, such that the memo is stored in an unstructured format.
38. The system of claim 31 , wherein at least one stored memo of the stored memos includes personal information about the user.
39. The system of claim 31 , wherein the actions further comprise:
replacing other previously stored memos that relate to a subject with a most recently stored memo that relates to the subject when multiple natural language utterances including the memo information are received, interpreted and stored in the database as a memo that relates to a subject.
40. The system of claim 31 , wherein the actions further comprise:
assigning a time period to at least one of the stored memos, after which the at least one memo will expire; and
removing the at least one memo from the database when the time period has expired.
41. The system of claim 31 , wherein the memo indicates that a specific entity is the user's favorite.
42. The system of claim 31 , wherein the actions further comprise:
identifying a trigger phrase from the received natural language utterance; and
responsive to identifying the trigger phrase, selecting the natural language grammar rule for retrieving the memo in dependence upon the identified trigger phrase.
43. The system of claim 42 , wherein the trigger phrase includes both a personal pronoun followed by an interrogative pronoun or a relative pronoun that is within 5 words of the personal pronoun.
44. The system of claim 31 , wherein the actions further comprise allowing the user to confirm or acknowledge whether or not the user intended for at least one of the natural language utterances including the memo information to be stored as a memo.
45. The system of claim 44 , wherein the actions further comprise deleting the stored memo related to the at least one of the natural language utterances including the memo information when the user indicates that that natural language utterance including the memo information was not intended to be stored as the memo.