Decision support system and method for distributed decision making for optimal human resource deployment

• US 8,818,832 B2
• Filed: 10/30/2009
• Issued: 08/26/2014
• Est. Priority Date: 10/30/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Goyal, Munish, Kambhatla, Nandakishore, Krishnan, Pavithra, Kulkarni, Shivaram, Lotlikar, Rohit Manohar, Majumdar, Debapriyo, Roy, Sambuddha, Soni, Soujanya, Thomas, Simon, Vaidya, Milind V., Parija, Gyana
• Primary Examiner(s): Jasmin, Lynda C
• Assistant Examiner(s): Padot, Timothy
• Application Number:
  US12/609,851
• Publication Number:
  US 20110106711A1
• Time in Patent Office: 1,761 Days
• Field of Search: 705/7.14, 705/321
• US Class Current: 705/7.14
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task
• CPC Class Codes: G06Q 50/188 Electronic negotiation

Abstract

A decision support tool which takes a high-level view of supply and demand in the realm of labor resources and produces globally-optimal recommendations for assignment of practitioners to open seats. These assignments preferably optimize a utility function composed of different business metrics and can be customizable for different organizations and priorities.

Claims

1. A system comprising:

a decision support tool comprising one or more processors and one or more modules executable by the one or more processors, the one or more modules comprising;

computer code configured to assimilate open seat data and practitioner data;

computer code configured to transform the open seat data and practitioner data into seat attributes and practitioner attributes;

computer code configured to assess viability of matching practitioners with seats based on predetermined matching criteria, and to thereupon determine feasible matches;

computer code configured to determine preferred matches via integer programming and via employing the feasible matches as input, and further via;

maximizing a utility function which employs a weighted summation of a number of already-assigned seats, a weighted summation of compatibility scores and a weighted summation of reward/penalty scores;

each compatibility score relating to a matching of a practitioner-seat pair, and being derived from a weighted combination of at least one matching score and at least one other criterion;

each reward/penalty score relating to a time factor with respect to a practitioner-seat pair;

wherein a reward is applied to at least one of;

an overdue seat, and a practitioner remaining unassigned for a period of time;

wherein a penalty is applied to at least one of a seat and a practitioner being scheduled for implementation in the future;

applying a first constraint to the utility function, the first constraint ensuring that a practitioner can be assigned to one seat only;

applying a second constraint to the utility function, the second constraint ensuring that a seat is assigned, at most, as many practitioners as the number of open positions for the seat; and

computer code configured to deliver the preferred matches to a user interface.

2. The system according to claim 1, wherein the one or more modules further comprise computer code configured for assessing viability of matching practitioners with seats based on fitness scores, wherein the compatibility score is based on at least one fitness score.

3. The system according to claim 2, wherein the one or more modules further comprise computer code configured for assessing viability of matching practitioners with seats based on text matching, the text matching contributing to the fitness scores.

4. The system according to claim 3, wherein the text matching comprises comparing text related to practitioners and seats, respectively, and yielding a result corresponding to a degree of text matching.

5. The system according to claim 4, wherein the text matching further comprises comparing text related to distinct categories relating to practitioners and seats, and assigning a comparative weight to each category.

6. The system according to claim 3, further comprising computer code configured for employing a substitutability matrix, the substitutability matrix indicating prescribed equivalencies between pairs of differing text vectors.

7. The system according to claim 2, further comprising computer code configured for assigning a lower threshold for fitness scores and discarding results not meeting the lower threshold.

8. The system according to claim 1, wherein the one or more modules further comprise computer code configured for determining preferred matches via optimization of business metrics.

9. The system according to claim 8, wherein the seat attributes include a prescribed timescale for effecting a match, and the business metrics are configured to employ the reward/penalty score to assert a preference for overdue seats with respect to the prescribed timescale.

10. The system according to claim 1, comprising:

computer code configured to display at least one optimal match corresponding to a practitioner and a seat and, adjacent thereto, cross-match information corresponding to at least one other viable seat corresponding to a practitioner.

11. The system according to claim 10, the one or more modules further comprising computer code configured to display, based on a fitness score rank, matches corresponding to a plurality of practitioners and seats.

12. The system according to claim 1, wherein the compatibility score is modified from an initial compatibility score associated with the feasible matches, the initial compatibility score relating to at least one unstructured attribute.

13. A method comprising:

executing with one or more processors the steps of;

assimilating open seat data and practitioner data;

transforming the open seat data and practitioner data into seat attributes and practitioner attributes;

assessing viability of matching practitioners with seats based on predetermined matching criteria, and thereupon determining feasible matches;

determining preferred matches via integer programming and via employing the feasible matches as input;

said determining comprising;

maximizing a utility function which employs a weighted summation of a number of already-assigned seats, a weighted summation of compatibility scores and a weighted summation of reward/penalty scores;

each compatibility score relating to a matching of a practitioner-seat pair, and being derived from a weighted combination of at least one matching score and at least one other criterion;

each reward/penalty score relating to a time factor with respect to a practitioner-seat pair;

wherein a reward is applied to at least one of;

an overdue seat, and a practitioner remaining unassigned for a period of time;

wherein a penalty is applied to at least one of a seat and a practitioner being scheduled for implementation in the future;

applying a first constraint to the utility function, the first constraint ensuring that a practitioner can be assigned to one seat only;

applying a second constraint to the utility function, the second constraint ensuring that a seat is assigned, at most, as many practitioners as the number of open positions for the seat; and

delivering the preferred matches to a user interface.

14. The method according to claim 13, wherein said assessing comprises assessing viability based on fitness scores, wherein the compatibility score is based on at least one fitness score.

15. The method according to claim 14, wherein said assessing based on fitness scores comprises text matching.

16. The method according to claim 15, wherein said text matching comprises comparing text related to practitioners and seats, respectively, and yielding a result corresponding to a degree of text matching.

17. The method according to claim 16, wherein said text matching further comprises comparing text related to distinct categories relating to practitioners and seats, and assigning a comparative weight to each category.

18. The method according to claim 15, further comprising computer code configured for employing a substitutability matrix, the substitutability matrix indicating prescribed equivalencies between pairs of differing text vectors.

19. The method according to claim 14, further comprising assigning a lower threshold for fitness scores and discarding results not meeting the lower threshold.

20. The method according to claim 13, wherein said determining further comprises determining preferred matches via optimization of business metrics.

21. The method according to claim 20, wherein the seat attributes include a prescribed timescale for effecting a match, and the business metrics are configured to employ the reward/penalty score to assert a preference for overdue seats with respect to the prescribed timescale.

22. The method according to claim 13, comprising:

displaying at least one optimal match corresponding to a practitioner and a seat and, adjacent thereto, cross-match information corresponding to at least one other viable seat corresponding to a practitioner.

23. The method according to claim 22, wherein said displaying comprises displaying, based on a fitness score rank, matches corresponding to a plurality of practitioners and seats.

24. The method according to claim 13, wherein the compatibility score is modified from an initial compatibility score associated with the feasible matches, the initial compatibility score relating to at least one unstructured attribute.

25. A computer program product comprising:

a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer code configured to assimilate open seat data and practitioner data;

computer code configured to transform the open seat data and practitioner data into seat attributes and practitioner attributes;

computer code configured to assess viability of matching practitioners with seats based on predetermined matching criteria, and to thereupon determine feasible matches;

computer code configured to determine preferred matches via integer programming and via employing the feasible matches as input, and further via;

maximizing a utility function which employs a weighted summation of a number of already-assigned seats, a weighted summation of compatibility scores and a weighted summation of reward/penalty scores;

each compatibility score relating to a matching of a practitioner-seat pair, and being derived from a weighted combination of at least one matching score and at least one other criterion;

each reward/penalty score relating to a time factor with respect to a practitioner-seat pair;

wherein a reward is applied to at least one of;

an overdue seat, and a practitioner remaining unassigned for a period of time;

wherein a penalty is applied to at least one of a seat and a practitioner being scheduled for implementation in the future;

applying a first constraint to the utility function, the first constraint ensuring that a practitioner can be assigned to one seat only;

applying a second constraint to the utility function, the second constraint ensuring that a seat is assigned, at most, as many practitioners as the number of open positions for the seat; and

computer code configured to deliver the preferred matches to a user interface.