Encoding and using information about distributed group discussions

• US 9,542,669 B1
• Filed: 03/14/2014
• Issued: 01/10/2017
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Deloitte Development LLC
• Original Assignee: Blab Incorporated
• Inventors: Harrison, Trinity Alana, Browning, Randolph, Snelling, David Aaron, Papp, Stefan Nicholas, Zimmermann, Bernhard G., Young, James Robert Jr., Bressler, Benjamin Ralph
• Primary Examiner(s): SALAD, ABDULLAHI ELMI
• Application Number:
  US14/213,866
• Time in Patent Office: 1,033 Days
• US Class Current: 1/1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/109 Time management, e.g. calendars, reminders, meetings or time accounting

Abstract

Techniques are described for analyzing user-supplied information, including to predict future aspects of additional related information that will be supplied by users. The user-supplied information may include distributed group discussions that involve numerous users and occur via user comments and other content items supplied to one or more social networking sites and/or other computer-accessible sites. The analysis of user-supplied information may, for example, include determining particular topics that are of interest for a specified category during one or more periods of time, summarizing and encoding information about multiple selected factors for comments supplied for particular topics or a category during each period of time (such as to quantify an amount of user interest), predicting future values for the selected factors for the topics and category during one or more future period of times, and taking one or more further actions based on the predicted information.

Claims

1. A computer-implemented method comprising:

obtaining, by one or more configured computing systems of a group discussion prediction service, information about a distributed group discussion involving a plurality of users submitting a plurality of content items for the distributed group discussion over multiple time periods, wherein the plurality of content items include multiple content items submitted during each of the multiple time periods;

receiving, by the one or more configured computing systems, a selection of one of multiple encoding schemes, each encoding scheme having a distinct group of multiple factors to use in summarizing information about groups of content items;

generating, by the one or more configured computing systems and based on the selected encoding scheme, an aggregation of encoded summary information to represent the distributed group discussion for the multiple time periods, the generating of the aggregation including determining, for each of the multiple factors of the selected encoding scheme and each of the multiple time periods, a value that summarizes information for that factor about the multiple content items submitted for the distributed group discussion during that time period;

matching, by the one or more configured computing systems, the generated aggregation of encoded summary information to a first portion of a defined prediction template having encoded information representing changes over time related to one or more other distributed group discussions;

predicting, by the one or more configured computing systems, future information about the distributed group discussion for multiple future time periods using a second portion of the defined prediction template that is distinct from the first portion, the predicting including determining, for each of the multiple factors of the selected encoding scheme and for each of the multiple future time periods, an expected value that summarizes information for that factor about future content items that are expected to be submitted for the distributed group discussion during that future time period; and

providing, by the one or more configured computing systems, at least some of the predicted future information for the multiple future time periods.

2. The method of claim 1 wherein the plurality of content items includes textual user comments supplied by the plurality of users related to multiple categories, wherein the multiple factors of the selected encoding scheme further include a total quantity of content items supplied during a time period that are associated with a category and include a rate of change in total quantity of content items supplied between two or more time periods that are associated with a category, and wherein the predicting of the future information for the multiple future time periods is performed for each of the multiple categories.

3. The method of claim 1 wherein the plurality of content items includes textual user comments supplied by the plurality of users related to multiple topics within a category, wherein the multiple factors of the selected encoding scheme include a total quantity of content items during a time period that are associated with a topic, a rate of change in total quantity of content items supplied between two or more time periods that are associated with a topic, and an aggregate sentiment of content items during at least one time period for a topic, and wherein the predicting of the future information for the multiple future time periods is performed for each of the multiple topics.

4. The method of claim 1 wherein the matching of the generated aggregation of encoded summary information to the first portion of the defined prediction template includes:

selecting, by the one or more configured computing systems, multiple defined prediction templates that include information encoded using the selected encoding scheme, wherein the multiple defined prediction templates are a subset of a plurality of defined prediction templates having information encoded using the multiple encoding schemes; and

determining, by the one or more configured computing systems, one of the selected multiple defined prediction templates to use for the predicting of the future information by comparing the generated aggregation of encoded summary information to initial portions of each of the selected multiple defined prediction templates and identifying the determined one defined prediction template as having a best match.

5. A computer-implemented method comprising:

obtaining, by one or more configured computing systems of a group discussion prediction service, information about a distributed group discussion that involves a plurality of users submitting a plurality of content items for the distributed group discussion, wherein the plurality of content items include multiple content items submitted for the distributed group discussion during each of multiple time periods;

selecting, by the one or more configured computing systems, an encoding scheme that has multiple factors to use in summarizing information about the distributed group discussion;

generating, by the one or more configured computing systems, an aggregation of encoded summary information to represent the distributed group discussion for the multiple time periods, the generating of the aggregation including determining, for each of the multiple factors of the selected encoding scheme and each of the multiple time periods, a value that summarizes information for that factor about the multiple content items submitted for the distributed group discussion during that time period;

assessing, by the one or more configured computing systems, the generated aggregation of encoded summary information to generate predicted summary information for the distributed group discussion for one or more future time periods, the generating of the predicted summary information including identifying, for each of the multiple factors of the selected encoding scheme and each of the one or more future time periods, a predicted value that summarizes information for that factor about future content items that are predicted to be submitted for the distributed group discussion during that future time period; and

providing, by the one or more configured computing systems, one or more indications of at least some of the generated predicted summary information for the distributed group discussion.

6. The method of claim 5 wherein the generated aggregation of encoded summary information includes a sequence of the determined values that summarize information for the multiple time periods and the multiple factors of the selected encoding scheme.

7. The method of claim 6 wherein the sequence of the determined values is ordered based on time period, such that determined values summarizing information for the multiple factors of the selected encoding scheme for a first time period are included in the sequence before determined values summarizing information for the multiple factors of the selected encoding scheme for a next second time period after the first time period.

8. The method of claim 6 wherein the sequence of the determined values is ordered based on factors of the selected encoding scheme, such that determined values summarizing information for all of the multiple time periods for a first factor of the selected encoding scheme are included in the sequence before determined values summarizing information for all of the multiple time periods for a second factor of the selected encoding scheme.

9. The method of claim 6 wherein the sequence of the determined values includes one or more characters to separate determined values summarizing information for different time periods or to separate determined values summarizing information for different selected factors.

10. The method of claim 5 wherein the multiple factors of the selected encoding scheme include a total quantity of content items that are supplied during a time period for the distributed group discussion and a rate of change in total quantity of content items supplied between two or more time periods for the distributed group discussion.

11. The method of claim 10 wherein the plurality of content items includes textual user comments supplied by the plurality of users related to multiple topics within a category, and wherein the multiple factors of the selected encoding scheme are determined in a manner specific to each of the multiple topics, such that the generating of the aggregation of encoded summary information further includes determining, for each of the multiple topics, a value that summarizes information for each of the multiple factors and each of the multiple time periods for submitted content items associated with that topic.

12. The method of claim 10 wherein the multiple factors of the selected encoding scheme further include multiple of a group of factor types that include at least one factor associated with one or more of multiple data sources to which the content items are submitted by users, at least one factor associated with one or more of multiple geographical locations from which users submit content items, at least one factor associated with a subset of one or more users of the plurality of users that have an indicated characteristic, and at least one factor associated with aggregate sentiment of contents of submitted content items.

13. The method of claim 10 wherein the multiple factors of the selected encoding scheme each further has associated information about allowable summarization values for the factor, wherein the determining of a value that summarizes information for a factor includes determining one of the allowable summarization values for that factor, and wherein the generating of a predicted value that summarizes information for a factor includes determining one of the allowable summarization values for that factor.

14. The method of claim 5 wherein the assessing of the generated aggregation of encoded summary information to generate predicted summary information for the distributed group discussion for the one or more future time periods includes, for each of at least one of the multiple factors, generating trend information based on the determined values that summarize information for that factor for at least some of the multiple time periods, and wherein the generating of the predicted values that summarizes information for each of the at least one factors and for the one or more future time periods is based on the generated trend information for that factor.

15. The method of claim 5 wherein the assessing of the generated aggregation of encoded summary information to generate predicted summary information for the distributed group discussion for the one or more future time periods includes matching at least some of the generated aggregation of encoded summary information to a first portion of a defined prediction template having encoded information representing changes over time related to one or more other distributed group discussions, and includes using information in a subsequent second portion of the defined prediction template as at least some of the identified predicted values for the one or more future time periods and the multiple factors of the selected encoding scheme.

16. The method of claim 15 further comprising generating, by the one or more configured computing systems, a second defined prediction template based at least in part on the determined values that summarize information for at least one of the multiple factor and at least some of the multiple time periods, to enable later predictions of future information for other distributed group discussions when future conditions match at least a portion of the second defined prediction template.

17. The method of claim 5 wherein the providing of the one or more indications of the at least some generated predicted summary information includes initiating display of the at least some generated predicted summary information to one or more users of the group discussion prediction service.

18. The method of claim 5 further comprising providing one or more additional indications of at least some of the generated aggregation of encoded summary information.

19. The method of claim 5 wherein the plurality of content items include multiple textual comments submitted to one or more social networking services by human users in multiple geographical locations.

20. The method of claim 5 further comprising, after the generating of the aggregation of encoded summary information to represent the distributed group discussion for the multiple time periods, storing the generated aggregation of encoded summary information, discarding the plurality of content items, and using the stored generated aggregation of encoded summary information to later provide information about the distributed group discussion for the multiple time periods.

21. The method of claim 5 further comprising:

selecting, by the one or more configured computing systems, a second encoding scheme that has a plurality of factors to use in summarizing information about the distributed group discussion, wherein the plurality of factors of the second encoding scheme are distinct from the multiple factors of the encoding scheme;

generating, by the one or more configured computing systems, a second aggregation of encoded summary information to represent the distributed group discussion for the multiple time periods, the generating of the aggregation including determining, for each of the plurality of factors of the selected second encoding scheme and each of the multiple time periods, a value that summarizes information for that factor about the multiple content items submitted for the distributed group discussion during that time period; and

providing, by the one or more configured computing systems, one or more indications of at least some of the generated second aggregation of encoded summary information for the distributed group discussion.

22. The method of claim 21 further comprising, after the generating of the second aggregation of encoded summary information:

assessing, by the one or more configured computing systems, the generated second aggregation of encoded summary information to generate second predicted summary information for the distributed group discussion for the one or more future time periods, the generating of the second predicted summary information including identifying, for each of the plurality of factors of the selected second encoding scheme and each of the one or more future time periods, a predicted value that summarizes information for that factor about future content items that are predicted to be submitted for the distributed group discussion during that future time period; and

providing, by the one or more configured computing systems, one or more indications of at least some of the generated second predicted summary information for the distributed group discussion.

23. The method of claim 5 wherein the selecting of the encoding scheme is based on a request by a user of the group discussion prediction service that indicates the encoding scheme, wherein the generating of the aggregation of encoded summary information and the assessing of the generated aggregation of encoded summary information is performed in response to the request, and wherein the providing of the one or more indications includes providing the at least some generated predicted summary information to the user.

24. The method of claim 5 wherein the selecting of the encoding scheme is based at least in part on analyzing information about multiple available prediction templates to determine that the encoding scheme is used by at least one of the available prediction templates, and wherein the generating of the predicted summary information is based on use of one of the at least one available prediction templates.

25. A non-transitory computer-readable medium having stored contents that, when executed, configure a computing system to perform a method, the method comprising:

obtaining, by the configured computing system, information about a distributed group discussion having a plurality of content items submitted by a plurality of users during multiple time periods;

selecting one of multiple encoding schemes to use for generating encoded summary information, the multiple encoding schemes each having a distinct group of multiple factors to use in summarizing information about groups of content items;

generating, by the configured computing system, encoded summary information for the distributed group discussion during the multiple time periods, the generating including determining, for each of the multiple time periods and for each of the multiple factors of the selected one encoding scheme, a value that summarizes information for that factor about content items submitted for the distributed group discussion during that time period;

assessing, by the configured computing system, the generated encoded summary information to obtain additional information for the distributed group discussion; and

providing, by the configured computing system, one or more indications of at least some of the additional information for the distributed group discussion.

26. The non-transitory computer-readable medium of claim 25 wherein the additional information is predicted information for the distributed group discussion for one or more future time periods, and wherein the assessing of the generated encoded summary information to obtain the additional information includes generating, for each of at least one of the multiple factors and each of the one or more future time periods, a predicted value that summarizes information for that factor about future content items that are predicted to be submitted for the distributed group discussion during that future time period.

27. The non-transitory computer-readable medium of claim 25 wherein the configured computing system is part of a group discussion prediction service, wherein the providing of the one or more indications of the at least some additional information includes displaying the at least some additional information to one or more users of the group discussion prediction service, and wherein the stored contents include software instructions that, when executed, program the configured computing system to perform the method.

28. A non-transitory computer-readable medium having stored contents that, when executed, configure a computing system to perform a method, the method comprising:

obtaining, by the configured computing system, information about a distributed group discussion having a plurality of content items submitted by a plurality of users during multiple time periods;

generating, by the configured computing system, encoded summary information for the distributed group discussion during the multiple time periods, the generating including determining, for each of the multiple time periods and for each of multiple factors of an encoding scheme, a value that summarizes information for that factor about content items submitted for the distributed group discussion during that time period;

assessing, by the configured computing system, the generated encoded summary information to obtain additional information for the distributed group discussion, wherein the additional information is predicted information for the distributed group discussion for one or more future time periods, and wherein the assessing of the generated encoded summary information to obtain the additional information includes;

matching the generated encoded summary information to a first portion of a defined prediction template having encoded information representing changes over time related to one or more other distributed group discussions, and

generating, for each of at least one of the multiple factors and each of the one or more future time periods, a predicted value that summarizes information for that factor about future content items that are predicted to be submitted for the distributed group discussion during that future time period, including using a second portion of the defined prediction template that is distinct from the first portion as part of generating predicted values for the at least one factors and the one or more future time periods; and

providing, by the configured computing system, one or more indications of at least some of the additional information for the distributed group discussion.

29. A system, comprising:

one or more hardware processors of one or more computing systems; and

one or more memories with stored instructions that, when executed by at least one of the one or more hardware processors, cause the at least one hardware processor to provide predicted future information about a distributed group discussion that currently has a plurality of content items submitted by a plurality of users during multiple time periods, the providing of the summarized predicted future information including;

obtaining first information about the distributed group discussion including information about the plurality of content items submitted during the multiple time periods, and obtaining second information about the distributed group discussion regarding future content items that are predicted to be submitted for the distributed group discussion during one or more future time periods;

selecting an encoding scheme that has multiple factors to use in summarizing information about the distributed group discussion;

generating encoded summary information for the distributed group discussion based on the obtained first and second information, the generating of the encoded summary information including determining, for each of at least one of the multiple factors of the encoding scheme, a value for each of the multiple time periods that summarizes information for that factor about content items submitted for the distributed group discussion during that time period, and a predicted value for each of the one or more future time periods that summarizes information for that factor about future content items that are predicted to be submitted for the distributed group discussion during that future time period; and

providing one or more indications of at least some of the generated encoded summary information for the distributed group discussion.

30. The system of claim 29 wherein the obtaining of the second information about the distributed group discussion includes matching some of the generated encoded summary information to a first portion of a defined prediction template having encoded information representing changes over time related to one or more other distributed group discussions, and includes using a second portion of the defined prediction template that is distinct from the first portion to obtain the second information, and wherein the some generated encoded summary information used for the matching includes at least some of the determined values for the at least one factors and the multiple time periods.

31. The system of claim 29 wherein the selecting of the encoding scheme includes selecting one of multiple encoding schemes to use for the generating of the encoded summary information, the multiple encoding schemes each having a distinct group of multiple factors to use in summarizing information about groups of content items, and wherein the multiple factors used for the generating of the encoded summary information are the multiple factors of the selected one encoding scheme.

32. The system of claim 29 wherein the one or more computing systems are part of a group discussion prediction service, and wherein the providing of the one or more indications of the at least some generated encoded summary information includes displaying the at least some generated encoded summary information to one or more users of the group discussion prediction service.