IP Library Granted Patent US 12,373,761
Granted Patent B2
US 12,373,761 · App. 18/153,893 · Granted Jul 29, 2025

Resource parity scaling using key performance indicator metrics

Inventors: Rashmi Ananth (North Brunswick, NJ); Mary Bittar (Houston, TX); Rohit Chandran (Wilton, CT); Elisabeth Kjersten Vehling (San Jose, CA); Zachary A. Silverstein (Georgetown, TX)
Assignee: International Business Machines Corporation
G06Q10/06393G06Q10/105
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,373,761
App. No.
18/153,893
Granted
Jul 29, 2025
Kind
B2
Abstract

Resource parity scaling includes receiving in real time a plurality of machine-generated input signals from a computer network, the machine-generated signals generated during simultaneous real-time executions of multiple processes using human and compute resources. Based on analyzing the plurality of machine-generated signals, a performance level of each process is determined. The performance level of each process is compared with one or more predetermined key performance indicator (KPI) metrics corresponding to each process. Responsive to the comparing different combinations of the human and compute resources are allocated for performing different ones of the multiple processes. The allocating is based on resource-specific incremental conversion factors corresponding to the compute and human resources. One or more output signals are conveyed to the computer network indicating the different combinations.

Claims (60)

1. A method, comprising:

receiving in real time, by a processor, a plurality of machine-generated input signals from a computer network, wherein the plurality of machine-generated input signals are generated during simultaneous real-time executions of multiple processes using human and compute resources;

determining, based on analyzing the plurality of machine-generated input signals by the processor, a performance level of each process of the multiple processes;

comparing, by the processor, the performance level of each process with one or more predetermined key performance indicator (KPI) metrics corresponding to each process;

allocating, by the processor, in response to the comparing, different combinations of the human and compute resources for performing different ones of the multiple processes, wherein the allocating is based on resource-specific incremental conversion factors corresponding to the human and compute resources, and wherein the resource-specific incremental conversion factors are measures of change in the performance level of each process owing to adding to each process or removing from each process, the human and compute resources; and

conveying, by the processor, to the computer network, at least one output signal indicating the different combinations, wherein the conveying includes conveying the at least one output signal to an auto-orchestration system configured to automatically reallocate the computer resources, and automatically reallocating, by the auto-orchestration system, the compute resources, wherein the reallocation improves a performance of a call center, and wherein compute resource performance measures are derived from real-time execution of computer procedures executed for processing calls by the call center.

2. The method of claim 1 , further comprising:

determining for each process a trend in the performance level of the process based on monitoring the performance level over time;

predicting, based on the trend, a likelihood that the process upon completion fails to conform to a specific KPI; and

in response to the likelihood exceeding a predetermined threshold, determining a reallocation of the human and compute resources that reduces the likelihood of exceeding the predetermined threshold.

3. The method of claim 2 , wherein the predicting is performed using a machine learning prediction model.

4. The method of claim 1 , wherein the predetermined KPI metrics are based on KPIs associated with a service level agreement (SLA), and further comprising:

performing an optimization based on the resource-specific incremental conversion factors given the KPIs associated with the SLA; and

performing the allocating different combinations of the human and compute resources based on the optimization, wherein the different combinations enable the multiple processes to conform to the KPIs associated with the SLA.

5. The method of claim 1 , wherein

the multiple processes are performed within the call center.

6. The method of claim 1 , wherein each resource-specific incremental conversion factor of the resource-specific incremental conversion factors is derived from process mining human resource and compute resource data generated by prior executions of the multiple processes.

7. The method of claim 1 , further comprising:

monitoring performance of the multiple processes; and

generating a post-completion report, wherein the post-completion report includes an indication of whether one or more of the multiple processes failed to align with an SLA-specified KPI.

8. A system, comprising:

one or more processors configured to initiate operations including:

receiving in real time a plurality of machine-generated input signals from a computer network, wherein the plurality of machine-generated input signals are generated during simultaneous real-time executions of multiple processes using human and compute resources;

determining, based on analyzing the plurality of machine-generated input signals, a performance level of each process of the multiple processes;

comparing the performance level of each process with one or more predetermined key performance indicator (KPI) metrics corresponding to each process;

allocating, in response to the comparing, different combinations of the human and compute resources for performing different ones of the multiple processes, wherein the allocating is based on resource-specific incremental conversion factors corresponding to the human and compute resources, and wherein the resource-specific incremental conversion factors are measures of change in the performance level of each process owing to adding to each process or removing from each process, the human and compute resources; and

conveying to the computer network at least one output signal indicating the different combinations, wherein the conveying includes conveying the at least one output signal to an auto-orchestration system configured to automatically reallocate the computer resources, and automatically reallocating, by the auto-orchestration system, the compute resources, wherein the reallocation improves a performance of a call center, and wherein compute resource performance measures are derived from real-time execution of computer procedures executed for processing calls by the call center.

9. The system of claim 8 , wherein the one or more processors are configured to initiate operations further including:

determining for each process a trend in the performance level of the process based on monitoring the performance level over time;

predicting, based on the trend, a likelihood that the process upon completion fails to conform to a specific KPI; and

in response to the likelihood exceeding a predetermined threshold, determining a reallocation of the human and compute resources that reduces the likelihood of exceeding the predetermined threshold.

10. The system of claim 8 , wherein the predetermined KPI metrics are based on KPIs associated with a service level agreement (SLA), and wherein the one or more processors are configured to initiate operations further including:

performing an optimization based on the resource-specific incremental conversion factors given the KPIs associated with the SLA; and

performing the allocating different combinations of the human and compute resources based on the optimization, wherein the different combinations enable the multiple processes to conform to the KPIs associated with the SLA.

11. The system of claim 8 , wherein

the multiple processes are performed within the call center.

12. The system of claim 8 , wherein each resource-specific incremental conversion factor of the resource-specific incremental conversion factors is derived from process mining human resource and compute resource data generated by prior executions of the multiple processes.

13. The system of claim 8 , wherein the one or more processors are configured to initiate operations further including:

monitoring performance of the multiple processes; and

generating a post-completion report, wherein the post-completion report includes an indication of whether one or more of the multiple processes failed to align with an SLA-specified KPI.

14. A computer program product, the computer program product comprising:

one or more computer-readable storage media and program instructions collectively stored on the one or more computer-readable storage media, the program instructions executable by one or more processors to cause the one or more processors to initiate operations including:

receiving in real time a plurality of machine-generated input signals from a computer network, wherein the plurality of machine-generated input signals are generated during simultaneous real-time executions of multiple processes using human and compute resources;

determining, based on analyzing the plurality of machine-generated input signals, a performance level of each process of the multiple processes;

comparing the performance level of each process with one or more predetermined key performance indicator (KPI) metrics corresponding to each process;

allocating, in response to the comparing, different combinations of the human and compute resources for performing different ones of the multiple processes, wherein the allocating is based on resource-specific incremental conversion factors corresponding to the human and compute resources, and wherein the resource-specific incremental conversion factors are measures of change in the performance level of each process owing to adding to each process or removing from each process, the human and compute resources; and

conveying to the computer network at least one output signal indicating the different combinations, wherein the conveying includes conveying the at least one output signal to an auto-orchestration system configured to automatically reallocate the computer resources, and automatically reallocating, by the auto-orchestration system, the compute resources, wherein the reallocation improves a performance of a call center, and wherein compute resource performance measures are derived from real-time execution of computer procedures executed for processing calls by the call center.

15. The computer program product of claim 14 , wherein the one or more processors are configured to initiate operations further including:

determining for each process a trend in the performance level of the process based on monitoring the performance level over time;

predicting, based on the trend, a likelihood that the process upon completion fails to conform to a specific KPI; and

in response to the likelihood exceeding a predetermined threshold, determining a reallocation of the human and compute resources that reduces the likelihood of exceeding the predetermined threshold.

16. The computer program product of claim 15 , wherein the predicting is performed using a machine learning prediction model.

17. The computer program product of claim 14 , wherein the predetermined KPI metrics are based on KPIs associated with a service level agreement (SLA), and wherein the one or more processors are configured to initiate operations further including:

performing an optimization based on the resource-specific incremental conversion factors given the KPIs associated with the SLA; and

performing the allocating different combinations of the human and compute resources based on the optimization, wherein the different combinations enable the multiple processes to conform to the KPIs associated with the SLA.

18. The computer program product of claim 14 , wherein the multiple processes are performed within the call center.

19. The computer program product of claim 14 , wherein each resource-specific incremental conversion factor of the resource-specific incremental conversion factors is derived from process mining human resource and compute resource data by generated prior executions of the multiple processes.

20. The computer program product of claim 14 , wherein the one or more processors are configured to initiate operations further including:

monitoring performance of the multiple processes; and

generating a post-completion report, wherein the post-completion report includes an indication of whether one or more of the multiple processes failed to align with an SLA-specified KPI.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2023
From: ANANTH, RASHMI; BITTAR, MARY; CHANDRAN, ROHIT; VEHLING, ELISABETH KJERSTEN; SILVERSTEIN, ZACHARY A.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 062364/0387 →
Continuity (1)
Related Publication 20240242160A1 · Jul 18, 2024
References Cited (48)
US 6978374B1 · Hansen · 2005 [cited by examiner]
US 7729270B2 · Bishop et al. · 2010 [cited by applicant]
US 8538787B2 · Braun et al. · 2013 [cited by applicant]
US 9336030B1 · Marr · 2016 [cited by examiner]
US 9495222B1 · Jackson · 2016 [cited by examiner]
US 9584374B2 · Bingham et al. · 2017 [cited by applicant]
US 10572650B2 · Cooper et al. · 2020 [cited by applicant]
US 10592828B2 · Farooq et al. · 2020 [cited by applicant]
US 10680914B1 · Bingham et al. · 2020 [cited by applicant]
US 10911346B1 · Choudhary et al. · 2021 [cited by applicant]
US 11023508B2 · Fletcher et al. · 2021 [cited by applicant]
US 11372705B1 · Minarik · 2022 [cited by examiner]
US 20050256946A1 · Childress · 2005 [cited by examiner]
US 20060095917A1 · Black-Ziegelbein · 2006 [cited by examiner]
US 20080154660A1 · Steinbach · 2008 [cited by examiner]
US 20080228857A1 · Ostertag · 2008 [cited by examiner]
US 20090192844A1 · Ramkumar · 2009 [cited by examiner]
US 20090271472A1 · Scheifler · 2009 [cited by examiner]
US 20120303816A1 · Kannan · 2012 [cited by examiner]
US 20140068075A1 · Bonilla · 2014 [cited by examiner]
US 20150143367A1 · Jia · 2015 [cited by examiner]
US 20160050222A1 · Lyer · 2016 [cited by examiner]
US 20160254943A1 · Maes · 2016 [cited by examiner]
US 20160295019A1 · O'Connor · 2016 [cited by examiner]
US 20170249193A1 · Brech · 2017 [cited by examiner]
US 20170353361A1 · Chopra · 2017 [cited by examiner]
US 20170364391A1 · Poghosyan · 2017 [cited by examiner]
US 20180068245A1 · Conti · 2018 [cited by examiner]
US 20180109469A1 · Nakazawa · 2018 [cited by examiner]
US 20190034242A1 · Nutter · 2019 [cited by examiner]
US 20190149617A1 · Gao · 2019 [cited by examiner]
US 20210176189A1 · Rabipour · 2021 [cited by examiner]
A Obeso Duque (Performance Prediction for Enabling Intelligent Resource Management on Big Data Processing Workflows) 2018—diva-portal.org (Year: 2018). [cited by examiner]
Wang, Y. et al., “Multiobjective optimization and hybrid evolutionary algorithm to solve constrained optimization problems,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Jun. 2007, vol. 37, … [cited by applicant]
Haralick, R.M. et al., “Increasing tree search efficiency for constraint satisfaction problems,” Artificial intelligence, Oct. 1, 1980, vol. 14, No. 3, pp. 263-313. [cited by applicant]
Ganaie, M.A. et al., “Ensemble deep learning: A review,” Engineering Applications of Artificial Intelligence, Oct. 1, 2022, vol. 115, No. 105151, [arXiv:2104.02395v3, Aug. 8, 2022], 47 pg. [cited by applicant]
Wang, F et al., “An ensemble learning based prediction strategy for dynamic multi-objective optimization,” Applied Soft Computing, Nov. 1, 2020, vol. 96, No. 106592, 13 pg. [cited by applicant]
Liu, R et al., “A novel cooperative coevolutionary dynamic multi-objective optimization algorithm using a new predictive model,” Soft Computing, Oct. 2014, vol. 18, pp. 1913-1929. [cited by applicant]
“IBM Process Mining,” IBM Automation, Sep. 2022, IBM Corporation © 2022, 4 pg. [cited by applicant]
“SPSS Software,” [online] IBM Corporation, [retrieved Sep. 28, 2022], retrieved from the Internet: <https://www.ibm.com/analytics/spss-statistics-software>, 8 pg. [cited by applicant]
“Workforce Planning,” [online] IBM Corp. [retrieved Sep. 28, 2022], retrieved from the Internet: <https://www.ibm.com/analytics/workforce-planning>, 9 pg. [cited by applicant]
“IBM Process Mining,”[online] IBM Corp. updated Jun. 29, 2022, retrieved from the Internet: <https://www.ibm.com/docs/en/cloud-paks/1.0?topic=foundation-process-mining>, 2 pg. [cited by applicant]
“Key Performance Indicators (KPIs),” [online] IBM Corp., updated Jan. 10, 2022, retrieved from the Internet: <https://www.ibm.com/docs/en/supply-chain-insight?topic=concepts-key-performance-indicators-kpis>, 5 pg. [cited by applicant]
Mell, P. et al., The NIST Definition of Cloud Computing, National Institute of Standards and Technology, U.S. Dept. of Commerce, Special Publication 800-145, Sep. 2011, 7 pg. [cited by applicant]
Staniszkis, Witold, “Modelling Business Process Performance,” Business process and services computing—1st international working conference on business process and services computing—BPSC 2007, Gesellschaft für Informati… [cited by applicant]
Wetzstein, Branimir et al., “Towards Management of SLA-Aware Business Processes Based on Key Performance Indicators,” 9th Workshop on Business Process Modeling, Development and Support (BPMDS'08)—Business Process Life-C… [cited by applicant]
Van Midden, Y., “Using process mining and event log analysis for better business strategy decision-making,” [online] Bachelor's Thesis, University of Twente, 2021, retrieved from the Internet: <http://essay.utwente.nl/8… [cited by applicant]
Kamala, B. et al., “Process Mining and Deep Neural Network approach for the Prediction of Business Process Outcome”, 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), 2022, pp. 1… [cited by applicant]