Discovering trending content of a domain

• US 9,311,406 B2
• Filed: 06/05/2013
• Issued: 04/12/2016
• Est. Priority Date: 06/05/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Ma, Tianchi, Vijaywargi, Deepak
• Primary Examiner(s): Alam, Hosain
• Assistant Examiner(s): ALLEN, NICHOLAS E
• Application Number:
  US13/910,777
• Publication Number:
  US 20140365452A1
• Time in Patent Office: 1,042 Days
• Field of Search: 707/706
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Systems and methods for identifying trending content on one or more domains is presented. In response to receiving a request for trending content on each domain of a set of domain, network activity data corresponding to network activity of a recent period of time is obtained. According to various embodiments, the network activity data corresponds to activity in the immediately previous time period and includes any of query logs from one or more search engines, social data from one or more social network sites, and browsing data corresponding to the browsing history of a plurality of computer users. Trending content from the network activity data for each domain of the set of domains is identified and the identified content is returned in response to the received request.

Claims

1. A computer implemented method for identifying trending content, the method comprising:

receiving a request for trending content;

obtaining network activity data corresponding to network activity of a recent period of time, wherein the network activity data comprises browsing data of browsing history of a first plurality of computer users of the recent time period;

identifying trending content from the network activity data for each domain of the set of domains, wherein identifying the trending content comprises;

organizing the browsing data according to a network location of each item of browsing data; and

for each network location of the resulting from organizing the browsing data, adding the network location to a trending content pool when a browsing volume of the network location during a first time period of the recent period of time meets a first threshold volume;

organizing the network locations in the trending content pool according to a domain of each network location; and

from each domain resulting from organizing the network locations in the trending content pool according to domain, identifying trending content for the corresponding domain; and

returning at least some of the identified trending content in response to the request.

2. The computer implemented method of claim 1, wherein the network activity data further comprises query logs of search queries obtained from one or more search engines of a second plurality of computer user;

and

wherein identifying trending content from the network activity data for each domain of the set of domains further comprises;

identifying a set of trending content candidates from the query logs;

aggregating the set of trending content candidates with the identified trending content; and

returning at least some of the aggregated trending content in response to the request.

3. The computer implemented method of claim 2, wherein identifying the set of trending content candidates from the query logs comprises:

grouping similar search queries from the query logs;

filtering out search queries whose volume falls below a query volume threshold;

obtaining search results for the filtered search queries, each search result having an associated score and each search result referencing content at a location on a domain, and grouping the search results according to the location of the referenced content; and

for each domain of the set of domains, selecting the highest scoring content as the set of trending content candidates for the domain.

4. The computer implemented method of claim 2, wherein identifying trending content for the corresponding domain comprises:

for each domain resulting from organizing the network locations in the trending content pool according to domain, selecting the highest scoring content as the identified trending content for the domain.

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

for each network location of the obtained browsing data, adding the network location to the trending content pool when the browsing volume of the network location of a second time period of the recent period of time meets a second threshold volume.

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

for each network location of the obtained browsing data, adding the network location to the trending content pool when the browsing volume of the network location of a third time period of the recent period of time meets a third threshold volume.

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

for each network location in the trending content pool, removing the network location from the trending content pool when the browsing volume of the network location of a fourth period of time fails to meet a fourth threshold volume.

8. The computer implemented method of claim 2, further comprising filtering the aggregated set of trending content candidates according to domain segment and category data.

9. The computer implemented method of claim 2, wherein the set of domains comprises a user-specified set of domains in the request for trending content.

10. A computer readable medium excluding transmission signals bearing computer executable instructions which, when executed on a computing system comprising at least a processor executing instructions retrieved from the medium, carry out a method for identifying trending topics, the method comprising:

receiving a request for trending content;

obtaining network activity data corresponding to network activity of a recent period of time, wherein the network activity data comprises query logs of search queries obtained by one or more search engines and browsing data of browsing history of a plurality of computer users;

identifying a first set of trending content candidates from the query logs;

identifying a second set of trending content candidates from the browsing data, wherein identifying the second set of trending content candidates from the browsing data comprises;

organizing the browsing data according to a network location; and

for each network location of the browsing data, adding the network location to a trending content pool when browsing volume of the network location during a first period of the recent period of time meets a first threshold volume;

aggregating the first and second sets of trending content candidates according to the domains of the trending content candidates;

for each domain of the set of domains, identifying a subset of the trending content candidates for the domain from the aggregated set of trending content candidates as the trending content for the domain; and

returning the identified content in response to the request.

11. The computer readable medium of claim 10, wherein identifying a first set of trending content candidates from the query logs comprises:

grouping similar search queries from the query logs;

filtering out search queries whose volume falls below a query volume threshold;

obtaining search results for the filtered search queries, each search result having an associated score and each search result referencing content at a location on a domain, and grouping the search results according to the location of the referenced content; and

for each domain of the set of domains, selecting the highest scoring content as the first set of trending content candidates for the domain.

12. The computer readable medium of claim 11, wherein identifying the second set of trending content candidates from the browsing data comprises:

adding the network location to the trending content pool when the browsing volume of the network location of a second period of the recent period of time meets a second threshold volume;

adding the network location to the trending content pool when the browsing volume of the network location of a third period of the recent period of time meets a third threshold volume; and

for each domain of the set of domains, selecting highest scoring content as the second set of trending content candidates for the domain.

13. The computer readable medium of claim 12, the method further comprising:

for each network location in the trending content pool, removing the network location from the trending content pool when the browsing volume of the network location of a fourth period of time fails to meet a fourth threshold volume.

14. A computer system for identifying trending topics, the computer system comprising a processor and a memory, wherein the processor executes instructions stored in the memory as part of or in conjunction with additional components to identify trending topics on one or more domains, the additional components comprising:

a network communication component configured to communicate with one or more external devices over a network, and where the system is configured to obtain network activity data corresponding to network activity of a recent period of time, wherein the network activity data comprises query logs of search queries obtained one or more search engines and browsing data of browsing history of a plurality of computer users;

a query log processing component to identify a first set of trending content candidates from the query logs of the network activity data;

a browsing history processing component to identify a second set of trending content candidates from the browsing data of the network activity data, wherein identifying the second set of trending content candidates from the browsing data comprises;

organizing the browsing data according to a network location; and

for each network location of the browsing data, adding the network location to a trending content pool when browsing volume of the network location during a first period of time of the recent period of time meets a first threshold volume; and

an aggregation component configured to;

aggregate the first and second sets of trending content candidates according to the domain of the trending content candidates; and

for each domain of the set of domains, identify a subset of the trending content candidates for the domain from the aggregated set of trending content candidates as the trending content for the domain;

wherein the computer system is further configured return the identified trending content in response to a request for trending content.

15. The computer system of claim 14, wherein the query log processing component is configured to identify the first set of trending content candidates from the query logs of the network activity data by:

grouping similar search queries from the query logs;

filtering out search queries whose volume falls below a query volume threshold;

obtaining search results for the filtered search queries, each search result having an associated score and each search result referencing content at a location on a domain, and grouping the search results according to the location of the referenced content; and

for each domain of the set of domains, selecting highest scoring content as the first set of trending content candidates for the domain.

16. The computer system of claim 15, wherein the browsing history processing component is configured to identify the second set of trending content candidates from the social network data of the network activity data by:

adding the network location to the trending content pool when the browsing volume of the network location of a second period of time of the recent period of time meets a second threshold volume;

adding the network location to the trending content pool when the browsing volume of the network location of a third period of time of the recent period of time meets a third threshold volume; and

for each domain of the set of domains, selecting highest scoring content as the second set of trending content candidates for the domain.