Generating and suggesting phrases

• US 8,706,643 B1
• Filed: 01/13/2009
• Issued: 04/22/2014
• Est. Priority Date: 01/13/2009
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Jesensky, James, Oates, Isaac, Huynh, Steve, Vaidya, Vinay
• Primary Examiner(s): Smits, Talivaldis Ivars
• Assistant Examiner(s): Roberts, Shaun
• Application Number:
  US12/352,970
• Time in Patent Office: 1,925 Days
• Field of Search: 705/74, 705/44, 705/67, 704/1, 704/9, 726/6
• US Class Current: 705/74
• CPC Class Codes: G06Q 20/382 insuring higher security of transaction
• CPC Class Codes: G06Q 20/401 Transaction verification

Abstract

Techniques for generating and providing phrases are described herein. These techniques may include analyzing one or more sources to generate a first corpus of phrases, each of the phrases for use as an identifier and/or for association with a user for executing a transaction. Once a first corpus of phrases has been generated, these phrases may be filtered to define a second corpus of phrases. Phrases of this second corpus may then be suggested to one or more users. In some instances, the phrases suggested to a particular user are personalized to the user based on information previously known about the user or based on information provided by the user.

Claims

1. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed on one or more processors, perform acts comprising:

analyzing multiple corpuses of text to generate a first corpus of phrases, wherein individual phrases comprise at least two grammatically-correct words automatically generated based at least in part on information associated with a user;

filtering the first corpus of phrases to define a second corpus of phrases comprising fewer phrases than the first corpus of phrases;

suggesting, to the user, phrases of the second corpus of phrases;

receiving a selection of a phrase of the suggested phrases from the user;

associating the selected phrase with the user and with one or more of a payment instrument associated with the user, a location associated with the user, or a delivery method associated with the user;

associating one or more rules to the selected phrase;

receiving a request to conduct a transaction with use of the selected phrase;

approving the requested transaction if the associated rules allow for the requested transaction with use of the phrase; and

declining the requested transaction if the associated rules do not allow for the requested transaction with use of the phrase.

2. One or more non-transitory computer-readable media as recited in claim 1, wherein the first corpus of phrases includes statistically improbable phrases from the multiple corpuses of text, phrases that comprise two or more contiguous words from the multiple corpuses of text, and phrases constructed from part-of-speech templates and words from the multiple corpuses of text.

3. One or more non-transitory computer-readable media as recited in claim 1, further storing computer-executable instructions that, when executed on the one or more processors, perform acts comprising:

determining a keyword associated with the user; and

determining phrases that are associated with the keyword, wherein at least a portion of the suggested phrases comprise the determined phrases that are associated with the keyword.

4. One or more non-transitory computer-readable media storing computer-executable instructions for a transaction that, when executed on one or more processors, perform acts comprising:

analyzing multiple corpuses of text to generate a corpus of phrases, at least one of the phrases comprising at least two grammatically-correct words and being associated with an aspect of a user account;

determining one or more phrases of the corpus of phrases to suggest to individual ones of multiple users, wherein individual ones of the multiple users have a user account and wherein the one or more phrases are automatically generated with information inputted by at least one of the multiple users;

receiving, from a set of the multiple users, a selection of a suggested phrase; and

associating, for individual users in the set of the multiple users, the selected phrase with at least one of a payment instrument for executing a transaction or an identity of one of the multiple users.

5. One or more non-transitory computer-readable media as recited in claim 4, wherein the aspect of the respective user account comprises the payment instrument associated with the user account, a physical or digital location associated with the user account, or a delivery method associated with the user account.

6. One or more non-transitory computer-readable media as recited in claim 4, wherein the at least two grammatically-correct words are separated by a space.

7. One or more non-transitory computer-readable media as recited in claim 4, wherein the phrases include words not separated by a space.

8. One or more non-transitory computer-readable media as recited in claim 4, wherein the corpus of phrases includes statistically improbable phrases that appear in at least one of the multiple corpuses of text more than a threshold number of times.

9. One or more non-transitory computer-readable media as recited in claim 4 wherein the corpus of phrases includes phrases comprising two or more contiguous words within at least one of the multiple corpuses of text.

10. One or more non-transitory computer-readable media as recited in claim 4, wherein the corpus of phrases includes phrases that have been constructed according to part-of-speech templates.

11. One or more non-transitory computer-readable media as recited in claim 4, wherein the corpus of phrases includes phrases that are constructed by applying words to a template.

12. One or more non-transitory computer-readable media as recited in claim 4, wherein the determining comprises filtering out a portion of the corpus of phrases.

13. One or more non-transitory computer-readable media as recited in claim 12, wherein the filtering out comprises filtering the corpus of phrases based at least in part on part-of-speech combinations of the phrases.

14. One or more non-transitory computer-readable media as recited in claim 12, wherein the filtering out comprises filtering the corpus of phrases based at least in part on commonality of the phrases, commonality of the words that compose the phrases, readability of the phrases, or a number of words of the phrases.

15. One or more non-transitory computer-readable media as recited in claim 12, wherein the filtering out comprises filtering out phrases that:

(i) include words that appear on a blacklist;

(ii) do not appear on a white list of phrases;

(iii) have previously been selected by a user;

or (iv) are homophones of phrases that have previously been selected by one or more users.

16. One or more non-transitory computer-readable media as recited in claim 4, wherein the determining of the one or more phrases to suggest to individual ones of the multiple users comprises:

determining a keyword associated with individual ones of the multiple users; and

determining phrases associated with the keyword.

17. One or more non-transitory computer-readable media as recited in claim 16, wherein the keywords are:

(i) manually inputted by respective users, or (ii) based on previously-known information about respective users.

18. A system comprising:

one or more processors; and

the one or more non-transitory computer-readable media storing the computer-executable instructions to store an application configured to;

analyze multiple corpuses of text to generate a corpus of phrases, at least one of the phrases comprising at least two grammatically-correct words;

determine one or more phrases of the corpus of phrases to suggest to individual ones of multiple users, wherein individual ones of the multiple users have a user account and wherein the one or more phrases are automatically generated with information inputted by at least one of the multiple users;

receive, from a set of the multiple users, a selection of a suggested phrase; and

associate, for individual users in the set of the multiple users, the selected phrase with at least one of a payment instrument for executing a transaction or an identity of one of the multiple users.

19. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed on one or more processors, perform acts comprising:

analyzing multiple sources to generate multiple phrases, wherein individual ones of the multiple phrases comprise a string of alphanumeric characters automatically generated using information associated with a user and individual ones of the multiple phrases for association with an aspect of a user account used to execute a payment transaction;

causing at least one phrase of the multiple phrases to be suggested to the user; and

responsive to receiving a selection of a phrase from the user, associating the selected phrase with the aspect of the user account used to execute a payment transaction.

20. One or more non-transitory computer-readable media as recited in claim 19, wherein the aspect of the user account comprises a payment instrument associated with the user account, a physical or digital location associated with the user account, or a delivery method associated with the user account.

21. One or more non-transitory computer-readable media as recited in claim 19, wherein the payment transaction comprises:

(i) purchasing, renting, leasing, or receiving an item, or (ii) sending or receiving money.

22. One or more non-transitory computer-readable media as recited in claim 19, wherein the multiple sources comprises books, magazines, online content, audio content or video content.

23. One or more non-transitory computer-readable media as recited in claim 19, wherein each of the individual strings of alphanumeric characters comprise at least one grammatically-correct word.

24. One or more non-transitory computer-readable media as recited in claim 19, wherein individual strings of alphanumeric characters comprise at least two grammatically-correct words.

25. One or more non-transitory computer-readable media as recited in claim 19, wherein individual strings of alphanumeric characters comprise at least two grammatically-correct words that are separated by a space.

26. One or more non-transitory computer-readable media as recited in claim 19, wherein at least one of the generated phrases comprises a statistically improbable phrase that appears in one of the sources at least a threshold number of times.

27. One or more non-transitory computer-readable media as recited in claim 19, wherein at least one of the generated phrases comprises two or more contiguous words found within one of the sources.

28. One or more non-transitory computer-readable media as recited in claim 19, wherein at least one of the generated phrases comprises a phrase that has been constructed according to a part-of-speech template.

29. One or more non-transitory computer-readable media as recited in claim 19, wherein at least one of the generated phrases comprises a phrase that is based at least in part on a template and personalized for the respective user.

30. A system comprising:

one or more processors; and

the one or more non-transitory computer-readable media storing the computer-executable instructions to store an application configured to;

analyze multiple sources to generate multiple phrases, wherein individual ones of the multiple phrases comprise a string of alphanumeric characters automatically generated using information associated with a user and individual ones of the multiple phrases for association with an aspect of a user account used to execute a payment transaction;

cause at least one phrase of the multiple phrases to be suggested to the user; and

responsive to receiving a selection of a phrase from the user, associate the selected phrase with the aspect of the user account used to execute a payment transaction.

31. A method implemented at least in part by a computing device, the method comprising:

determining, via the computing device, one or more phrases to suggest to a user for association with an aspect of a user account associated with a user, wherein individual ones of the one or more phrases comprise at least one grammatically-correct word automatically generated based at least in part on a phrase entered by the user;

receiving a selection of a suggested phrase or a selection of a user-generated phrase from the user;

responsive to the receiving of the selection, associating the selected phrase with the aspect of the user account;

receiving, from the user, a request to conduct a transaction with use of the selected phrase;

if the requested transaction is authorized, completing the requested transaction with use of the selected phrase; and

otherwise, declining the requested transaction.

32. A method as recited in claim 31, wherein individual ones of the one or more phrases comprises between two and seven grammatically-correct words.

33. A method as recited in claim 31, wherein the one or more suggested phrases include statistically improbable phrases, mined phrases, constructed phrases, or template-based phrases.

34. A method as recited in claim 31, wherein the determining of the one or more phrases to suggest to the user comprises:

generating a first corpus of phrases; and

filtering the first corpus of phrases to define a second corpus of phrases having fewer phrases than the first corpus of phrases.

35. A method as recited in claim 31, wherein the determining of the one or more phrases to suggest to the user comprises:

determining a keyword associated with the user; and

associating the keyword with the one or more phrases.

36. A system comprising:

one or more processors;

memory;

a phrase-generation module, stored in the memory and executable on the one or more processors to generate automatically multiple phrases based at least in part on a phrase entered by a user for association with payment instruments associated with users, locations associated with users, or delivery methods associated with users;

a phrase-suggestion module, stored in the memory and executable on the one or more processors to suggest one or more of the generated phrases to the users; and

a phrase-association module, stored in the memory and executable on the one or more processors to associate phrases with payment instruments, locations, or delivery methods associated with the users in response to receiving selections of suggested phrases from the users.

37. A system as recited in claim 36, wherein the generated phrases are between two and seven words in length.

38. A system as recited in claim 36, wherein the phrase-generation module generates the multiple phrases by analyzing one or more sources that are independent from the payment instruments of the users.

39. A system as recited in claim 38, wherein the one or more sources include a book, a dictionary, a magazine, online content, audio content, or video content.

40. A system as recited in claim 36, wherein the phrase-suggestion module personalizes the suggested one or more phrases based on the respective user to whom the one or more phrases are suggested.

41. A system as recited in claim 36, wherein the phrase-generation module generates the multiple phrases by analyzing one or more sources, and wherein the generated phrases comprise statistically improbable phrases from the one or more sources, two or more contiguous words found within the one or more sources, phrases constructed according to pre-determined part-of-speech templates, or phrases based on templates that are personalized to a respective user.

42. A system as recited in claim 36, further comprising:

a phrase-filtering module, stored in the memory and executable on the one or more processors to filter out a portion of the generated multiple phrases.

43. A system as recited in claim 42, wherein the phrase-filtering module filters the generated multiple phrases based on commonality of the phrases, commonality of words that compose the phrases, readability of the phrases, or word counts of the phrases.

44. A system as recited in claim 42, wherein the phrase-filtering module filters the generated multiple phrases based on parts-of-speech combinations of the phrases.

45. A method implemented at least in part by a computing device, comprising:

generating, via the computing device, a corpus of phrases that individually comprise at least one grammatically-correct word;

determining a portion of the phrases from the corpus of phrases to suggest to a user based at least in part on a keyword associated with a phrase associated with the user; and

responsive to receiving a user selection of a phrase, associating the selected phrase with an aspect of a user account associated with the user, the aspect of the user account used to execute a payment transaction.

47. A method as recited in claim 45, wherein the keyword is manually inputted by the user.

48. A method as recited in claim 45, wherein the keyword is based on previously-known information about the user.

46. A method as recited in 45, wherein the corpus of phrases comprises a first corpus of phrases, and wherein determining of the portion of the phrases comprises:

filtering out one or more phrases of the first corpus of phrases to define a second corpus of phrases;

determining the keyword associated with the user; and

determining phrases of the second corpus of phrases that are associated with the keyword.