Systems, apparatuses and methods for communication flow modification

• US 9,218,410 B2
• Filed: 02/06/2015
• Issued: 12/22/2015
• Est. Priority Date: 02/06/2014
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Contact Solutions Incorporated
• Inventors: Gray, Joshua, Hibbard, Mike, Holl, Randal E., Dellostritto, James J.
• Primary Examiner(s): Mamillapalli, Pavan
• Application Number:
  US14/616,037
• Publication Number:
  US 20150220619A1
• Time in Patent Office: 319 Days
• Field of Search: 707/738
• US Class Current: 1/1
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/2246 Trees, e.g. B+trees
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/25 Integrating or interfacing systems involving database management systems
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 9/451 Execution arrangements for user interfaces
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: H04M 2203/556 Statistical analysis and interpretation
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends

Abstract

An apparatus includes a user interface module configured to receive user information associated with a user. The apparatus also includes a classification module configured to apply a classifier defined within a classification tree to the user information, and to calculate a classification score representing an estimated likelihood that the user is associated with at least one user type. The classification module is also configured to classify the user to an identified user type based on the classification score. The apparatus also includes a database configured to store at least one of user account information associated with the user, historical information associated with the user, or historical information associated with a group of users including the user. The apparatus also includes an interface generation module configured to generate a signal based on the information in the database, the signal specifying a user interface to be presented to the user.

Claims

1. An apparatus, comprising:

a user interface module implemented in at least one of a memory or a processing device, the user interface module configured to receive, from a user device associated with a user, user information associated with the user;

a classification module operatively coupled to the user interface module, the classification module configured to;

apply a classifier defined within a classification tree to the user information, including calculating a classification score representing an estimated likelihood that the user is associated with at least one user type from a plurality of user types,

compare the classification score to a classification criterion associated with an identified user type from the plurality of user types, and

classify, when the classification score meets the classification criterion, the user as the identified user type;

a database configured to store at least one of user account information associated with the user, historical information associated with the user, or historical information associated with a group of users including the user; and

an interface generation module configured to generate a signal based on the identified user type, the user account information, the historical information associated with the user, and the historical information associated with the group of users, the signal specifying a user interface to be presented to the user,

the user interface module configured to transmit the signal to the user device.

2. The apparatus of claim 1, wherein the user interface is a mobile-based interface for an interactive system implemented on a host device.

3. The apparatus of claim 1, wherein each user type from the plurality of user types is associated with at least one of a different level of fraudulent activity by the user, or a different type of fraudulent activity by the user.

4. The apparatus of claim 1, wherein the classifier defines an internal node of the classification tree and each user type from the plurality of user types defines a terminal node of the classification tree.

5. An apparatus, comprising:

a user interface module of an interactive system and implemented in at least one of a memory or a processing device, the user interface module configured to receive, from a user device associated with a user, user information associated with the user; and

a classification module operatively coupled to the user interface module, the classification module configured to;

apply a classifier to the user information to calculate a classification score, the classification score representing an estimated likelihood that the user belongs to at least one user type from a plurality of user types, each user type from the plurality of user types associated with at least one of a different level of fraudulent activity by the user, or a different type of fraudulent activity by the user; and

classify the user to an identified user type from the plurality of user types based on the classification score by (1) comparing the classification score to a classification criterion and (2) classifying, when the classification score meets the classification criterion, the user as the identified user type specified by the classification criterion,

the user interface module configured to transmit a signal to the user device, the signal specifying a user interface for the IVR system to be presented to the user based on the identified user type.

6. The apparatus of claim 5, wherein the classification module is configured to apply a plurality of classifiers in the form of a classification tree, each classifier from the plurality of classifiers defining an internal node of the classification tree, each user type from the plurality of user types defining a terminal node of the classification tree.

7. The apparatus of claim 5, wherein the classifier is a support vector network, the classification module further configured to train the classifier using predetermined user information associated with predetermined user types from the plurality of user types.

8. The apparatus of claim 5, wherein the user interface module is further configured to:

request additional information from the user device; and

receive, in response to the request, the additional information,

the classification module further configured to apply the classifier to the additional infonnation, the additional information including at least one of geospatial information, position information, environmental information, motion information, user device information, or user authentication information.

9. The apparatus of claim 5, wherein the user information includes user device information, the classification module configured to calculate the classification score by comparing the user device information with user account information.

10. The apparatus of claim 5, further comprising an interface generation module configured to generate the signal based on the identified user type and at least one of user account information, historical information associated with the user, or historical information associated with a group of users.

11. The apparatus of claim 5, further comprising an interface generation module configured to generate the signal based on the identified user type and based on historical information associated with the user, the historical information based on previous interactions with the user.

12. The apparatus of claim 5, further comprising an interface generation module configured to generate the signal based on the identified user type and based on historical information associated with a group of users, the historical information based on fraud analysis of previous interactions with the group of users.

13. The apparatus of claim 5, further comprising:

a database configured to store user account information associated with the user, historical information associated with the user, or historical information associated with a group of users; and

an interface generation module configured to generate the signal based on the identified user type, the user account information, the historical information associated with the user, and historical information associated with a group of users.

14. The apparatus of claim 5, wherein when the classification score does not meet the classification criterion the classification module is further configured to:

generate a new user type;

classify the user as the new user type;

update the plurality of user types to includes the new user type; and

update the classification criterion to specify at least one of the classification score or a range including the classification score, as associated with the new user type.

15. The apparatus of claim 5, wherein the classification criterion specifies a mapping between at least one of (1) one or more possible values of the classification score and one or more user types of the plurality of user types, or (2) one or more possible ranges of the classification score and one or more user types of the plurality of user types.

16. A method, comprising:

receiving at a host device, from a user device associated with a user, user information associated with the user;

calculating a classification score representing an estimated likelihood that the user belongs to at least one user type from a plurality of user types;

comparing the classification score to a classification criterion associated with an identified user type from the plurality of user types,

classifying, when the classification score meets the classification criterion, the user as the identified user type from the plurality of user types;

transmitting a signal to the user device, the signal specifying a user interface to be presented to the user based on the identified user type;

if a database associated with the host device includes preexisting user account information associated with the user, updating the user account information to include an indication of the identified user type; and

if the database does not include preexisting user account information associated with the user;

defining new user account information for the user, the new user account information including an indication of the identified user type; and

storing the new user account information in the database.

17. The method of claim 16, wherein the calculating the classification score includes applying to the user information a classifier based on the classification score, the method further comprising applying a plurality of classifiers, each classifier from the plurality of classifiers defining an internal node of a classification tree, each user type from the plurality of user types defining a terminal node of the classification tree.

18. The method of claim 16, wherein the calculating the classification score includes applying to the user information a classifier based on the classification score, the classifier being a support vector machine, the method further comprising, prior to receiving the user information, training the support vector machine using predetermined user information associated with a plurality of predetermined user types including the identified user type.

19. The method of claim 16, wherein the calculating the classification score includes:

applying, to the user information, a classification tree including a plurality of classifiers, the classification score being associated with a classifier from the plurality of classifiers; and

evaluating a classification score for each classifier from the plurality of classifiers.

20. The method of claim 16, wherein the calculating the classification score includes comparing the user information with user account information.

21. The method of claim 16, wherein the user information includes user device information, the calculating the classification score including comparing the user device information with user account information.

22. The method of claim 16, wherein the calculating the classification score includes:

requesting additional information from the user device;

receiving, in response to the request, additional information; and

applying at least one classifier to the additional information,

the additional information is at least one of geospatial information, position information, environmental information, motion information, user device information, user authentication information, or user expression information.

23. The method of claim 16, wherein the database includes preexisting user account information associated with the user, the user information including user device information, the calculating the classification score includes comparing the user device information with user account information.

24. The method of claim 16, wherein the database includes preexisting user account information associated with the user, the method further comprising:

generating the signal based on the identified user type and at least one of the user account information, historical information associated with the user, or historical information associated with a group of users including the user.

25. The method of claim 16, further comprising:

when the classification score does not meet the classification criterion;

generating a new user type;

classifying the user as the new user type; and

updating the classification criterion to associate with the new user type at least one of the classification score or a range including the classification score.

26. The method of claim 16, wherein the classification criterion specifies a mapping between at least one of a possible value of the classification score and a user type from the plurality of user types, or a possible range of the classification score and a user type from the plurality of user types associated with the possible range.

27. The method of claim 16, wherein the user interface is for an interactive voice response (IVR) system implemented on the host device.