Conversational list management

• US 10,282,417 B2
• Filed: 02/19/2016
• Issued: 05/07/2019
• Est. Priority Date: 02/19/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Clark, Adam T., Huebert, Jeffrey K., Payton, Aspen L., Petri, John E.
• Primary Examiner(s): Ortiz-Sanchez, Michael
• Application Number:
  US15/048,057
• Publication Number:
  US 20170242845A1
• Time in Patent Office: 1,173 Days
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation

Abstract

Software that generates list items from user conversations by performing the following operations: (i) capturing natural language statement(s) spoken by a first user; (ii) converting the natural language statement(s) to text; (iii) performing a natural language processing (NLP) analysis of the text to identify a first list item, wherein the first list item includes one or more words in the text that are likely to be included in a list associated with the first user; and/or performing a first list action utilizing the first list item based, at least in part, on the performed NLP analysis, wherein the first list action includes modifying a first list associated with the first user.

Claims

1. A computer-implemented method comprising:

capturing, by one or more processors, a set of natural language statements spoken by a plurality of individuals;

identifying, by one or more processors, natural language statement(s) of the set of natural language statements that have been spoken by a first user associated with a list management application;

filtering, by one or more processors, the set of natural language statements to remove statement(s) spoken by individual(s) other than the first user;

converting, by one or more processors, the filtered set of natural language statements to text;

performing, by one or more processors, a natural language processing (NLP) analysis of the text to identify a first list item, wherein the first list item includes one or more words in the text that are likely to be included in a first list associated with the first user in the list management application, wherein the first list corresponds to a first data structure stored in a database;

determining, by one or more processors, whether the first list item is a list-starting item or a list-continuing item, based, at least in part, on a set of list-starting indicators and a set of list-continuing indicators, wherein the set of list-starting indicators includes;

(i) one or more directional prepositions and their corresponding prepositional phrases, and (ii) a score generated by a deep question answering (QA) system based on asking the deep QA system whether the first list item is the start of a list, and wherein the set of list-continuing indicators includes;

(i) one or more words or phrases that have ontological relationships to items in other, existing lists associated with the first user corresponding to other, existing data structures stored in the database, and (ii) a score generated by the deep QA system based on asking the deep QA system whether the first list item is a continuation of a known list; and

performing, by one or more processors, a first list action in the list management application utilizing the first list item based, at least in part, on the determination of whether the first list item is a list-starting item or a list-continuing item, wherein the first list action includes modifying the first data structure corresponding to the first list, wherein if the first list item is a list-starting item, the first list action includes modifying the first data structure to begin the first list with the first list item, and wherein if the first list item is a list-continuing item, the first list action includes modifying the first data structure to include the first list item in the first list at a location other than the beginning of the first list.

2. The computer-implemented method of claim 1, further comprising:

scoring, by one or more processors, the first list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database; and

selecting, by one or more processors, the first list from the plurality of lists based, at least in part, on the scoring.

3. The method of claim 2, further comprising:

upon selecting the first list, presenting, by one or more processors, via a display device, the first list to the first user; and

providing, by one or more processors, the first user with an opportunity to approve the selection of the first list using a user interface.

4. The computer-implemented method of claim 1, further comprising:

scoring, by one or more processors, the first list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database;

responsive to determining that the first list item does not meet a score threshold for any of the lists of the plurality of lists, creating, by one or more processors, the first list and a corresponding data structure.

5. The computer-implemented method of claim 1, further comprising:

identifying, by one or more processors, a second list item based, at least in part, on the performed NLP analysis, wherein the second list item includes one or more words in the text that are likely to be included in a list associated with the first user in the list management application;

scoring, by one or more processors, the second list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database;

selecting, by one or more processors, the first list from the plurality of lists based, at least in part, on the scoring; and

performing, by one or more processors, a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the selection of the first list, wherein the second list action includes modifying the first data structure corresponding to the first list.

6. The computer-implemented method of claim 1, further comprising:

identifying, by one or more processors, a second list item based, at least in part, on the performed NLP analysis, wherein the second list item includes one or more words in the text that are likely to be included in a list associated with the first user in the list management application;

scoring, by one or more processors, the second list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database;

responsive to determining that the second list item does not meet a score threshold for any of the lists of the plurality of lists, creating, by one or more processors, a second list and a corresponding second data structure; and

performing, by one or more processors, a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the creation of the second list, wherein the second list action includes modifying the second data structure corresponding to the second list.

7. The computer-implemented method of claim 1, further comprising:

identifying, by one or more processors, natural language statement(s) spoken by a second user associated with the list management application;

converting, by one or more processors, the natural language statement(s) spoken by the second user to text;

performing, by one or more processors, a natural language processing (NLP) analysis of the text of the converted natural language statement(s) spoken by the second user to identify a second list item, wherein the second list item includes one or more words in the text of the converted natural language statement(s) spoken by the second user that are likely to be included in the first list associated with the first user in the list management application; and

responsive to determining list modification permissions for the second user in the list management application, performing, by one or more processors, a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the determined list modification permissions, wherein the second list action includes modifying the first data structure corresponding to the first list associated with the first user.

8. A computer program product comprising a computer readable storage medium having stored thereon:

program instructions to capture a set of natural language statements spoken by a plurality of individuals;

program instructions to identify natural language statement(s) of the set of natural language statements that have been spoken by a first user associated with a list management application;

program instructions to filter the set of natural language statements to remove statement(s) spoken by individual(s) other than the first user;

program instructions to convert the filtered set of natural language statements to text;

program instructions to perform a natural language processing (NLP) analysis of the text to identify a first list item, wherein the first list item includes one or more words in the text that are likely to be included in a first list associated with the first user in the list management application, wherein the first list corresponds to a first data structure stored in a database;

program instructions to determine whether the first list item is a list-starting item or a list-continuing item, based, at least in part, on a set of list-starting indicators and a set of list-continuing indicators, wherein the set of list-starting indicators includes;

(i) one or more directional prepositions and their corresponding prepositional phrases, and (ii) a score generated by a deep question answering (QA) system based on asking the deep QA system whether the first list item is the start of a list, and wherein the set of list-continuing indicators includes;

(i) one or more words or phrases that have ontological relationships to items in other, existing lists associated with the first user corresponding to other, existing data structures stored in the database, and (ii) a score generated by the deep QA system based on asking the deep QA system whether the first list item is a continuation of a known list; and

program instructions to perform a first list action in the list management application utilizing the first list item based, at least in part, on the determination of whether the first list item is a list-starting item or a list-continuing item, wherein the first list action includes modifying the first data structure corresponding to the first list, wherein if the first list item is a list-starting item, the first list action includes modifying the first data structure to begin the first list with the first list item, and wherein if the first list item is a list-continuing item, the first list action includes modifying the first data structure to include the first list item in the first list at a location other than the beginning of the first list.

9. The computer program product of claim 8, wherein the computer readable storage medium has further stored thereon:

program instructions to score the first list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database; and

program instructions to select the first list from the plurality of lists based, at least in part, on the scoring.

10. The computer program product of claim 8, wherein the computer readable storage medium has further stored thereon:

program instructions to score the first list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database; and

program instructions to, responsive to determining that the first list item does not meet a score threshold for any of the lists of the plurality of lists, create the first list and a corresponding data structure.

11. The computer program product of claim 8, wherein the computer readable storage medium has further stored thereon:

program instructions to identify a second list item based, at least in part, on the performed NLP analysis, wherein the second list item includes one or more words in the text that are likely to be included in a list associated with the first user in the list management application;

program instructions to score the second list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database;

program instructions to select the first list from the plurality of lists based, at least in part, on the scoring; and

program instructions to perform a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the selection of the first list, wherein the second list action includes modifying the first data structure corresponding to the first list.

12. The computer program product of claim 8, wherein the computer readable storage medium has further stored thereon:

program instructions to identify a second list item based, at least in part, on the performed NLP analysis, wherein the second list item includes one or more words in the text that are likely to be included in a list associated with the first user in the list management application;

program instructions to score the second list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database;

program instructions to, responsive to determining that the second list item does not meet a score threshold for any of the lists of the plurality of lists, create a second list and a corresponding second data structure; and

program instructions to perform a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the creation of the second list, wherein the second list action includes modifying the second data structure corresponding to the second list.

13. The computer program product of claim 8, wherein the computer readable storage medium has further stored thereon:

program instructions to identify natural language statement(s) spoken by a second user associated with the list management application;

program instructions to convert the natural language statement(s) spoken by the second user to text;

program instructions to perform a natural language processing (NLP) analysis of the text of the converted natural language statement(s) spoken by the second user to identify a second list item, wherein the second list item includes one or more words in the text of the converted natural language statement(s) spoken by the second user that are likely to be included in the first list associated with the first user in the list management application; and

program instructions to, responsive to determining list modification permissions for the second user in the list management application, perform a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the determined list modification permissions, wherein the second list action includes modifying the first data structure corresponding to the first list associated with the first user.

14. A computer system comprising:

a processor(s) set; and

a computer readable storage medium;

wherein;

the processor set is structured, located, connected and/or programmed to run program instructions stored on the computer readable storage medium; and

the stored program instructions include;

program instructions to capture a set of natural language statements spoken by a plurality of individuals;

program instructions to identify natural language statement(s) of the set of natural language statements that have been spoken by a first user associated with a list management application;

program instructions to filter the set of natural language statements to remove statement(s) spoken by individual(s) other than the first user;

program instructions to convert the filtered set of natural language statements to text;

program instructions to perform a natural language processing (NLP) analysis of the text to identify a first list item, wherein the first list item includes one or more words in the text that are likely to be included in a first list associated with the first user in the list management application, wherein the first list corresponds to a first data structure stored in a database;

program instructions to determine whether the first list item is a list-starting item or a list-continuing item, based, at least in part, on a set of list-starting indicators and a set of list-continuing indicators, wherein the set of list-starting indicators includes;

(i) one or more directional prepositions and their corresponding prepositional phrases, and (ii) a score generated by a deep question answering (QA) system based on asking the deep QA system whether the first list item is the start of a list, and wherein the set of list-continuing indicators includes;

(i) one or more words or phrases that have ontological relationships to items in other, existing lists associated with the first user corresponding to other, existing data structures stored in the database, and (ii) a score generated by the deep QA system based on asking the deep QA system whether the first list item is a continuation of a known list; and

program instructions to perform a first list action in the list management application utilizing the first list item based, at least in part, on the determination of whether the first list item is a list-starting item or a list-continuing item, wherein the first list action includes modifying the first data structure corresponding to the first list, wherein if the first list item is a list-starting item, the first list action includes modifying the first data structure to begin the first list with the first list item, and wherein if the first list item is a list-continuing item, the first list action includes modifying the first data structure to include the first list item in the first list at a location other than the beginning of the first list.

15. The computer system of claim 14, wherein the stored program instructions further include:

program instructions to score the first list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database; and

program instructions to select the first list from the plurality of lists based, at least in part, on the scoring.

16. The computer system of claim 14, wherein the stored program instructions further include:

program instructions to score the first list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database; and

program instructions to, responsive to determining that the first list item does not meet a score threshold for any of the lists of the plurality of lists, create the first list and a corresponding data structure.

17. The computer system of claim 14, wherein the stored program instructions further include:

program instructions to identify a second list item based, at least in part, on the performed NLP analysis, wherein the second list item includes one or more words in the text that are likely to be included in a list associated with the first user in the list management application;

program instructions to score the second list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database;

program instructions to select the first list from the plurality of lists based, at least in part, on the scoring; and

program instructions to perform a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the selection of the first list, wherein the second list action includes modifying the first data structure corresponding to the first list.

18. The computer system of claim 14, wherein the stored program instructions further include:

program instructions to identify a second list item based, at least in part, on the performed NLP analysis, wherein the second list item includes one or more words in the text that are likely to be included in a list associated with the first user in the list management application;

program instructions to score the second list item against a plurality of lists associated with the first user in the list management application, wherein each list of the plurality of lists corresponds to a respective data structure stored in the database;

program instructions to, responsive to determining that the second list item does not meet a score threshold for any of the lists of the plurality of lists, create a second list and a corresponding second data structure; and

program instructions to perform a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the creation of the second list, wherein the second list action includes modifying the second data structure corresponding to the second list.

19. The computer system of claim 14, wherein the stored program instructions further include:

program instructions to identify natural language statement(s) spoken by a second user associated with the list management application;

program instructions to convert the natural language statement(s) spoken by the second user to text;

program instructions to perform a natural language processing (NLP) analysis of the text of the converted natural language statement(s) spoken by the second user to identify a second list item, wherein the second list item includes one or more words in the text of the converted natural language statement(s) spoken by the second user that are likely to be included in the first list associated with the first user in the list management application; and

program instructions to, responsive to determining list modification permissions for the second user in the list management application, perform a second list action in the list management application utilizing the second list item based, at least in part, on the performed NLP analysis and the determined list modification permissions, wherein the second list action includes modifying the first data structure corresponding to the first list associated with the first user.