Method for deriving intelligence from activity logs

Patent metadata

Field	Value
Publication number	US-9454455-B2
Application number	US-11132508-A
Country	US
Kind code	B2
Filing date	Apr 29, 2008
Priority date	Apr 29, 2008
Publication date	Sep 27, 2016
Grant date	Sep 27, 2016

Abstract

Techniques for segregating one or more logs of at least one multitasking user to derive at least one behavioral pattern of the at least one multitasking user are provided. The techniques include obtaining at least one of at least one action log, configuration information, domain knowledge, at least one task history and open task repository information, correlating the at least one of at least one action log, configuration information, domain knowledge, at least one task history and open task repository information to determine a task associated with each of one or more actions and segregate the one or more logs based on the one or more actions, and using the one or more logs that have been segregated to derive at least one behavioral pattern of the at least one multitasking user. Techniques are also provided for deriving intelligence from at least one activity log of at least one multitasking user to provide information to the at least one user.

First claim

What is claimed is:

1. A method for segregating multiple action logs of at least one multitasking user to derive at least one behavioral pattern of the at least one multitasking user, comprising the steps of:
obtaining multiple action logs for a user from multiple web sites, configuration information, domain knowledge, at least one task history and open task repository information;
correlating the multiple action logs, configuration information, domain knowledge, at least one task history and open task repository information to determine a task associated with each of one or more actions in the multiple action logs, where there is no explicit indication of the task associated with each of the one or more actions performed, wherein said correlating comprises:
associating each of one or more actions in the multiple action logs with a task in the open task repository;
computing a confidence score for each task in the open task repository associated with the one or more actions, said computing comprising:
computing a first probability distribution for a set of tasks associated with the user from the open task repository as a normalized weighted average of distributions over a pre-determined number of previous actions restricted to the set of tasks performed by the user;
computing a distribution of recency of tasks opened in the set of tasks; and
combining the probability distribution and the distribution of recency of tasks to determine a second probability distribution for the user; and

identifying the task with the highest confidence score, wherein the highest confidence score corresponds to the task having the maximal probability in the second probability distribution;

automatically segregating the multiple action logs of the at least one multitasking user on a per-task basis based on the identified task; and
using the multiple action logs that have been segregated on a per-task basis to derive at least one behavioral pattern of the at least one multitasking user and a sequence of one or more additional actions based on the identified task and the at least one behavioral pattern.

2. The method of claim 1 , wherein each log comprises usage information, and wherein the usage information comprises at least one of user name, session, time, action performed, one or more parameters to an action, one or more items passed to an action, duration of an action and one or more preceding linked actions.

3. The method of claim 1 , wherein segregating the one or more logs comprises using at least one constraint, and wherein the at least one constraint comprises at least one of a smoothness constraint, a contextual constraint, a domain knowledge based constraint and a task-based constraint.

4. The method of claim 1 , further comprising using the one or more logs that have been segregated to monitor user activity.

5. A method for deriving intelligence from multiple activity logs of at least one multitasking user to provide information to the at least one user, comprising the steps of:
obtaining information about at least one past action from multiple action logs for a user, configuration information, domain knowledge, at least one task history and open task repository information;
correlating the information about the at least one past action, configuration information, domain knowledge, at least one task history and open task repository information to determine a task associated with each action where there is no explicit indication of the task associated with each action performed, wherein said correlating comprises:
associating each action from the multiple action logs with a task in the open task repository;
computing a confidence score for each task in the open task repository associated with each action, said computing comprising:
computing a first probability distribution for a set of tasks associated with the user from the open task repository as a normalized weighted average of distributions over a pre-determined number of previous actions restricted to the set of tasks performed by the user;
computing a distribution of recency of tasks opened in the set of tasks; and
combining the probability distribution and the distribution of recency of tasks to determine a second probability distribution for the user; and

identifying the task with the highest confidence score, wherein the highest confidence score corresponds to the task having the maximal probability in the second probability distribution;

automatically segmenting the multiple activity logs of the at least one multitasking user on a per-task basis based on the identified task; and
using each segmented activity log, current configuration of an application, domain knowledge, configuration information and one or more action histories to provide a sequence of one or more additional actions based on the identified task to the user.

6. The method of claim 5 , further comprising:
generating at least one suggestion for the at least one user based on a current user interface (UI) configuration and a predicted task; and
displaying the at least one suggestion in the UI.

7. The method of claim 5 , further comprising:
generating at least one suggestion for the at least one user based on a current user interface (UI) configuration and a predicted task;
executing the at least one suggestion; and
displaying a result in the UI.

8. The method of claim 5 , further comprising reconfiguring a user interface (UI) using information gained by mining one or more task-based segmented user logs.

9. The method of claim 5 , further comprising reconfiguring a user interface (UI) to drive a user towards using one or more frequent long and effective sequences.

10. The method of claim 5 , further comprising placing at least one automation button at a place in a user interface (UI) to facilitate execution of a common frequent sequence of action.

11. The method of claim 5 , further comprising reconfiguring a user interface (UI) using at least one contiguous action pattern.

Assignees

• Deshpande Prasad M
• Krishnapuram Raghuram
• Majumdar Debapriyo
• Padmanabhan Deepak S
• IBM

Inventors

• Deshpande Prasad M
• Krishnapuram Raghuram
• Majumdar Debapriyo
• Padmanabhan Deepak S

Classifications

• G06F11/3438

  monitoring of user actions (tracking the activity of the user H04L67/535) · CPC title

• G06F11/3476 Primary

  Data logging (G06F11/14, G06F11/2205 take precedence) · CPC title