Determining topics of interest

Patent metadata

Field	Value
Publication number	US-9330174-B1
Application number	US-201314034865-A
Country	US
Kind code	B1
Filing date	Sep 24, 2013
Priority date	Sep 24, 2013
Publication date	May 3, 2016
Grant date	May 3, 2016

Abstract

A computer-implemented method that includes the actions of receiving a request for data indicative of topics of interest for a user segment of a social networking platform, accessing user data for one or more users of the social networking platform, comparing the one or more user characteristics that are associated with the user segment to user characteristics associated with the accessed user data, identifying, based on comparing, a portion of the accessed user data that pertains to the user segment, analyzing contents of the portion of the accessed user data that pertains to the user segment, determining, based on analyzing, one or more elements in the portion of the accessed user data that pertain to a topic of interest for the user segment, and transmitting, to a client device that sent the request, data indicative of elements pertaining to the topics of interest for the user segment.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving a request for data indicative of topics of interest for a pre-defined user segment of a social networking platform, with the pre-defined user segment representing a subset of users of the social networking platform who are each associated with one or more user characteristics;
in response to the request,
accessing user data for one or more users of the social networking platform, with an item of the accessed user data being associated with one or more user characteristics indicative of a type of user associated with the item of accessed user data;

comparing the one or more user characteristics that are associated with the pre-defined user segment to user characteristics associated with the accessed user data;
identifying, based on comparing, a portion of the accessed user data that pertains to the pre-defined user segment;
analyzing contents of the portion of the accessed user data that pertains to the pre-defined user segment;
for the pre-defined user segment, determining, based on analyzing, previously unspecified topics of interest for the pre-defined user segment;
ranking the determined topics of interest that were previously unspecified for the pre-defined user segment; and
transmitting, to a client device that sent the request, data indicative of elements pertaining to the ranked topics of interest for the pre-defined user segment.

2. The computer-implemented method of claim 1 , further comprising:
generating, in a data repository, an association among data indicative of the one or more elements determined and data indicative of a topic of interest.

3. The computer-implemented method of claim 1 , further comprising:
receiving a user input that indicates a time period;
wherein identifying comprises:
identifying, based on comparing, a portion of the accessed user data that pertains to the pre-defined user segment and that is associated with the time period.

4. The computer-implemented method of claim 1 , further comprising:
accessing data indicative of a mapping of one or more keywords to one or more topics of interest;
wherein analyzing comprises:
identifying a match among (i) at least one of the one or more keywords that are mapped to the one or more topics of interest, and (ii) a word included in the portion of the accessed user data that pertains to the pre-defined user segment.

5. The computer-implemented method of claim 1 , wherein analyzing comprises:
determining a semantic relationship between data indicative of a topic of interest for the pre-defined user segment and a word included in the portion of the accessed user data.

6. The computer-implemented method of claim 1 , further comprising:
receiving data indicative of a selection of at least one of the topics of interest.

7. The computer-implemented method of claim 1 , wherein the elements comprise one or more of:
a sentiment score that pertains to the topic of interest for the pre-defined user segment;
data indicative of one or more entities that pertain to the topic of interest for the pre-defined user segment;
one or more terms that pertain to the topic of interest for the pre-defined user segment; and
one or more themes that pertain to the topic of interest for the pre-defined user segment.

8. The computer-implemented method of claim 1 , wherein transmitting, to the client device that sent the request, the data indicative of the elements pertaining to the ranked topics of interest for the pre-defined user segment comprises:
transmitting, to the client device that sent the request, data indicative of representations of the elements pertaining to the topics of interest for the pre-defined user segment; and
wherein the method further comprises:
receiving data indicative of a selection of at least one of the representations of the elements;
determining trend data based on the selected at least one of the representations of the elements; and
transmitting, to the client device, data indicative of the determined trend data.

9. The computer-implemented method of claim 8 , further comprising:
receiving data indicative of a selection of filtering criteria for the trend data; and
filtering the trend data based on the received data indicative of the selection of filtering criteria.

10. The computer-implemented method of claim 9 , further comprising:
determining that the data indicative of the selection of at least one of the representations of the elements pertains to one or more entities; and
presenting filtering criteria that pertain to at least one of the one more entities determined.

11. The computer-implemented method of claim 1 , further comprising:
determining a frequency of occurrence of a particular type of user data included in the accessed user data; and
comparing the frequency of occurrence to a threshold value;
wherein identifying comprises:
identifying, based on comparing frequencies of occurrence of various types of user data and based on comparing the one or more user characteristics, a portion of the accessed user data that pertains to the pre-defined user segment and that includes types of user data that occur with frequencies that satisfy the threshold value.

12. The computer-implemented method of claim 1 , further comprising:
determining a frequency of occurrence of a particular type of user data included in the accessed user data; and
comparing the frequency of occurrence to a threshold value;
wherein identifying comprises:
identifying, based on comparing frequencies of occurrence of various types of user data and based on comparing the one or more user characteristics, a portion of the accessed user data that pertains to the pre-defined user segment and that includes types of user data occurring with increased frequency relative to other frequencies at which other types of user data occur in the accessed user data.

13. The computer-implemented method of claim 1 , further comprising:
receiving data indicative of a selection of filtering criteria for user characteristics; and
generating a definition of the pre-defined user segment to include users associated with one or user characteristics specified by the filtering criteria.

14. A system comprising:
one or more processing devices; and
one or more machine-readable media configured to store instructions that executable by the one or more processing devices to perform operations comprising:
receiving a request for data indicative of topics of interest for a pre-defined user segment of a social networking platform, with the pre-defined user segment representing a subset of users of the social networking platform who are each associated with one or more user characteristics;
in response to the request,
accessing user data for one or more users of the social networking platform, with an item of the accessed user data being associated with one or more user characteristics indicative of a type of user associated with the item of accessed user data;

comparing the one or more user characteristics that are associated with the pre-defined user segment to user characteristics associated with the accessed user data;
identifying, based on comparing, a portion of the accessed user data that pertains to the pre-defined user segment;
analyzing contents of the portion of the accessed user data that pertains to the pre-defined user segment;
for the pre-defined user segment, determining, based on analyzing, previously unspecified topics of interest for the pre-defined user segment;
ranking the determined topics of interest that were previously unspecified for the pre-de

Assignees

• Microstrategy Inc

Inventors

• Zhang Jeff

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F17/30861 Primary

  Physics · mapped topic

• G06Q10/42

  Determination of affinities or common interests between users · CPC title

• G06Q10/48

  using social graphs · CPC title

• G06Q10/44

  Identification of trends within social networks, e.g. identification of trending topics · CPC title