Computer-Implemented System And Method For Identifying Tasks Using Temporal Footprints

• US 20130185247A1
• Filed: 03/04/2013
• Published: 07/18/2013
• Est. Priority Date: 04/24/2009
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Brdiczka, Oliver, Begole, James (Bo) M.A.
• Granted Patent: US 9,576,239 B2
• Time in Patent Office: Days
• US Class Current: 706/58
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

A computer-implemented system and method for identifying tasks using temporal footprints is provided. A database of temporal footprints is maintained. Each temporal footprint is representative of a different task and includes one or more significant patterns of two or more sequential events. Events performed by one or more users are tracked. At least one pattern including sequential occurrences of two or more of the tracked events is identified. The identified pattern is compared to each of the significant patterns of the temporal footprints. A footprint score for the identified pattern is determined with respect to each temporal footprint. The task associated with the temporal footprint having the highest footprint score is assigned to the identified pattern.

Claims

1. A system for identifying tasks using temporal footprints, comprising:

a database of temporal footprints, each temporal footprint representative of a different task and comprising one or more significant patterns of two or more sequential events;

a tracking module to track events performed by at least one user;

a pattern module to identify at least one pattern comprising sequential occurrences of two or more of the tracked events;

a comparison module to compare the identified pattern to each of the significant patterns of the temporal footprints;

a scoring module to determine a footprint score for the identified pattern with respect to each temporal footprint; and

a task assignment module to assign the task associated with the temporal footprint having the highest footprint score to the identified pattern.

2. A system according to claim 1, further comprising:

a score calculation module to calculate the footprint score according to the following equation;

arg max_i[tfidf_score (Candidate Task, T_i)]

where T_i refers to one of the temporal footprints and tfidf_score refers to a footprint score of the newly recognized pattern for the temporal footprint.

3. A system according to claim 1, wherein the identified pattern comprises at least one of a string sequence, in which the tracked events occur without any intervening events and a causal sequence in which the tracked events include intervening events.

4. A system according to claim 1, further comprising:

an event module to allow an application associated with one of the tracked events to run for a predetermined length of time and to designate an end of the tracked event when the predetermined length of time has been reached, and no further events have been tracked within the application or within a different application.

5. A system according to claim 1, further comprising:

a stress level module to determine stress levels based on stress factors comprising at least one of pattern length, number of event occurrences, type of pattern, and temporal measures of the events, wherein the stress factors are derived from the identified pattern.

6. A system according to claim 5, wherein the stress levels are related to at least one of word load, repetitiveness of events, and a deviation from a routine patterns

7. A system according to claim 1, further comprising:

a footprint generator to generate the temporal footprints, comprising;

the sequential events;

a pattern submodule to identify a pattern of two or more of the sequential events, to determine a temporal interval between each of the sequential events in the pattern, and to determine whether the pattern is significant based on the temporal intervals; and

a footprint designation module to designate the significant patterns as the temporal footprint.

8. A system according to claim 1, further comprising:

a significance value module to assign significance values to the significant patterns within each temporal footprint, to identify the significant patterns that match the identified pattern, and to calculate the footprint scores for the identified pattern based on the significance values of each matching significant pattern.

9. A system according to claim 8, further comprising:

a footprint determination module to identify two or more significant patterns from the same temporal footprint that match the identified pattern and to total the significance values for each of the two or more significant patterns as the footprint score for the identified pattern with respect to that temporal footprint.

10. A system according to claim 1, wherein each event comprises an action performed by a user on or within one or more applications.

11. A method for identifying tasks using temporal footprints, comprising:

maintaining a database of temporal footprints, each temporal footprint representative of a different task and comprising one or more significant patterns of two or more sequential events;

tracking events performed by at least one user;

identifying at least one pattern comprising sequential occurrences of two or more of the tracked events;

comparing the identified pattern to each of the significant patterns of the temporal footprints;

determining a footprint score for the identified pattern with respect to each temporal footprint; and

assigning the task associated with the temporal footprint having the highest footprint score to the identified pattern.

12. A method according to claim 11, further comprising:

calculating the footprint score according to the following equation;

arg max_i[tfidf_score (Candidate Task, T_i)]

where T_i refers to one of the temporal footprints and tfidf_score refers to a footprint score of the newly recognized pattern for the temporal footprint.

13. A method according to claim 11, wherein the identified pattern comprises at least one of a string sequence, in which the tracked events occur without any intervening events and a causal sequence in which the tracked events include intervening events.

14. A method according to claim 11, further comprising:

allowing an application associated with one of the tracked events to run for a predetermined length of time; and

designating an end of the tracked event when the predetermined length of time has been reached, and no further events have been tracked within the application or within a different application.

15. A method according to claim 11, further comprising:

determining stress levels based on stress factors comprising at least one of pattern length, number of event occurrences, type of pattern, and temporal measures of the events, wherein the stress factors are derived from the identified patterns.

16. A method according to claim 15, wherein the stress levels are related to at least one of word load, repetitiveness of events, and a deviation from a routine patterns

17. A method according to claim 11, further comprising:

generating the temporal footprints, comprising;

recording the sequential events;

identifying a pattern of two or more of the sequential events and determining a temporal interval between each of the sequential events in the pattern;

determining whether the pattern is significant based on the temporal intervals; and

designating the significant patterns as the temporal footprint.

18. A method according to claim 11, further comprising:

assigning significance values to the significant patterns within each temporal footprint;

identifying the significant patterns that match the identified pattern; and

determining the footprint scores for the identified pattern based on the significance values of each matching significant pattern.

19. A method according to claim 18, further comprising:

identifying two or more significant patterns from the same temporal footprint that match the identified pattern; and

totaling the significance values for each of the two or more significant patterns as the footprint score for the identified patterns with respect to that temporal footprint.

20. A method according to claim 11, wherein each event comprises an action performed by a user on or within one or more applications.