Systems and methods for behavioral pattern mining

• US 9,305,104 B2
• Filed: 06/21/2012
• Issued: 04/05/2016
• Est. Priority Date: 06/21/2012
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Wu, Changjun, Gnanasambandam, Shanmuga-Nathan, Jung, Gueyoung, Zhao, Shi
• Primary Examiner(s): Chen, Susan
• Application Number:
  US13/529,111
• Publication Number:
  US 20130346447A1
• Time in Patent Office: 1,384 Days
• Field of Search: 706/40, 706/48
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]

Abstract

Methods and systems of performing data mining may include receiving a plurality of web log records and a plurality of call log records; associating one or more web log records with a call log record, wherein the associated user for each of the associated one or more web log records and the call log record are the same; identifying one or more patterns among the web log records for the plurality of call log records, wherein each pattern comprises one or more web accesses, a time stamp at which each of the one or more web accesses is performed and the call topic for the call log record; identifying one or more web log records associated with a new call, and predicting a call topic for the new call based on at least one pattern and the one or more web log records.

Claims

1. A method of predicting a topic of a call, comprising:

receiving a web log having a plurality of web log records for a website, wherein each web log record comprises a website access, a time stamp and an identity of a user who accessed the website;

receiving a call log having a plurality of call log records containing information regarding calls placed to one or more telephone numbers, wherein each call log record comprises a call topic, a time stamp and an identity of a user;

grouping, by a pattern identification engine, one or more calls of the call log with one or more website accesses of the web log into a web-phone session so that the user associated with the one or more website accesses of the web log and the user associated with the one or more calls of the call log in the web-phone session are the same user;

identifying, by the pattern identification engine, one or more patterns within a web-phone session by identifying a general topic of the web-phone session based on;

a topic accessed in the one or more website accesses of the web log records of the web-phone session, or

a call topic in the call log records of the web-phone session;

receiving a new call from a caller;

identifying, by the pattern identification engine, that one or more previous website accesses exist in the web log records from the caller associated with the new call;

reviewing the previous website accesses to identify a pattern from a previous web-phone session for one or more of the previous website accesses;

predicting, by the pattern identification engine, a call topic for the new call based on the identified pattern from the previous web-phone session; and

by a processing device, outputting the predicted call topic.

2. The method of claim 1, further comprising:

presenting the predicted call topic to the caller;

receiving, from the caller, an affirmative response that the predicted call topic is correct; and

in response to receiving the affirmative response, routing the new call to an agent or system capable of receiving the new call based on the predicted call topic.

3. The method of claim 1, wherein:

each of the website accesses comprises a time stamp;

each of the call log records comprises a time; and

grouping the one or more calls of the call log with the one or more website accesses of the web log into a web-phone session comprises matching website accesses and call log records that occurred during a same time period.

4. The method of claim 1, wherein identifying the general topic of the web-phone session is based upon one or more website pages that were accessed during the web-phone session.

5. The method of claim 1, wherein each web log record further comprises a plurality of clicks arranged in a sequence, and wherein the identified pattern further comprises a sequence of clicks for one or more website accesses, and a time between each click in the sequence.

6. The method of claim 5, wherein identifying the pattern comprises associating the sequence of clicks with calls to one or more monitored telephone lines made by the same user.

7. The method of claim 3, wherein grouping the one or more calls of the call log with the one or more website accesses of the web log during the same time period also comprises identifying any website accesses that correspond to a mistaken click on an incorrect link.

8. A system for predicting a topic of a call, comprising:

a processing device;

a pattern identification engine;

a logs module comprising;

a web log having a plurality of web log records for a website, wherein each web log record comprises a website access, a time stamp and an identity of a user who accessed the website, and

a call log having a plurality of call log records containing information regarding calls placed to one or more telephone numbers, wherein each call log record comprises a call topic, a time stamp and an identity of a user; and

a non-transitory computer-readable storage medium in communication with the processing device, wherein the computer-readable storage medium contains one or more programming instructions that, when executed, cause the processing device to;

instruct the pattern identification engine to group a call topic of the call log with one or more website accesses of the web log records into a web-phone session so that the one or more website accesses of the web log and the one or more calls of the call log in the web-phone session are from the same user,

instruct the pattern identification engine to identify one or more patterns within the web-phone session by identifying a general topic of the web-phone session based on one or more topics accessed in the one or more website accesses of the web log records of the web-phone session,

receive a new call from a caller who is the same user,

review a previous web-phone session for the caller to identify a pattern for one or more previous website accesses in the previous web-phone session, and

predict a call topic for the new call based on the identified pattern from the one or more previous website accesses; and

output the predicted call topic.

9. The system of claim 8, further comprising additional instructions that, when executed, cause the processing device to:

present the predicted call topic to the caller;

receive, from the caller, an affirmative response that the predicted call topic is correct; and

in response to receiving the affirmative response, route the new call to an agent or system capable of receiving the new call based on the predicted call topic.

10. The system of claim 9, wherein:

each of the website accesses comprises a time stamp;

each of the call log records comprises a time; and

the instructions to group the one or more calls of the call log with the one or more website accesses of the web log into the web-phone session comprise instructions to match website accesses and call log records that occurred during a same time period.

11. The system of claim 9, wherein the instructions to identify the general topic of the web-phone session one or more patterns comprise instructions to identify the general topic based upon one or more website pages that were accessed during the web-phone session.

12. The system of claim 8, wherein each web log record further comprises a plurality of clicks arranged in a sequence, and wherein the instructions to identify the pattern further comprise instructions to identify a sequence of clicks for one or more website accesses and a time between each click in the sequence.

13. The system of claim 12, wherein the instructions to identify the pattern comprise instructions to associate the sequence of clicks with calls to one or more monitored telephone lines made by the same user.

14. A method of predicting a topic of a call, the method comprising:

by a pattern identification engine;

accessing a web log having a plurality of web log records, wherein each web log record comprises a website access, a time stamp and an associated user,

accessing a call log having a plurality of call log records, wherein each call log record comprises a call topic, a time stamp and an associated user, and

by a pattern identification engine, extracting one or more web log records from the web log and one or more call log records from the call log;

grouping, by the pattern identification engine, one or more calls of the call log from the extracted call log records with one or more website accesses of the web log from the extracted web log records into a web-phone session so that the user associated with the one or more website accesses of the web log and the user associated with the one or more calls of the call log are the same user;

identifying, by the pattern identification engine, one or more patterns within the web-phone session by identifying a general topic of the web-phone session based on;

a topic accessed in the one or more website accesses of the web-phone session, or

a call topic in the call log records of the web-phone session;

receiving a new call from a caller who is the same user;

identifying, by the pattern identification engine, that one or more previous website accesses exist in the web log records from the caller associated with the new call;

reviewing the previous website accesses to identify a pattern for one or more of the previous website accesses;

predicting, by the pattern identification engine, a call topic for the new call based on the identified pattern from the previous web-phone session; and

by a processing device, outputting the predicted call topic to the caller.

15. The method of claim 14, further comprising:

presenting the predicted call topic to the caller;

receiving, from the caller, an affirmative response that the predicted call topic is correct; and

in response to receiving the affirmative response, routing the new call to an agent or system capable of receiving the new call based on the predicted call topic.

16. The method of claim 14, wherein:

each of the website accesses comprises a time stamp;

each of the call log records comprises a time; and

grouping the one or more calls of the call log with the one or more website accesses of the web log into the web-phone session comprises matching website accesses and call log records that occurred during a same time period.

17. The method of claim 16, wherein identifying the general topic of the web-phone session is based upon the one or more website pages that were accessed during the web-phone session.

18. The method of claim 16, wherein grouping the one or more calls of the call log with the one or more website accesses of the web log during the same time period also comprises identifying any website accesses that correspond to a mistaken click on an incorrect link.

19. The method of claim 14, wherein each web log record further comprises a plurality of clicks arranged in a sequence, and wherein the pattern further comprises a sequence of clicks for one or more website accesses and a time between each click in the sequence.

20. The method of claim 19, wherein the identifying the pattern comprises associating the sequence of clicks with calls to one or more monitored telephone lines made by the same user.