Performance evaluation based on resource dynamics

Patent metadata

Field	Value
Publication number	US-2020159174-A1
Application number	US-201816197684-A
Country	US
Kind code	A1
Filing date	Nov 21, 2018
Priority date	Nov 21, 2018
Publication date	May 21, 2020
Grant date	—

Abstract

Methods and systems of evaluating a performance of an entity are described. A processor may obtain first data indicating tier attributes of resources of the entity, second data indicating function attributes of the resources, and third data indicating productivity attributes of the resources. The processor may train a model based on the first data, the second data, and the third data, the model may represent transitions of the resources over time. The processor may receive a set of controls including at least an objective to optimize a performance of the entity. The processor may generate a controlled model by integrating the set of controls into the model. The processor may determine a set of outcomes from the controlled model that includes at least a set of transitions relating to the resources that may optimize the performance of the entity.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
obtaining, by a processor, first data indicating tier attributes of a plurality of resources of an entity; obtaining, by the processor, second data indicating function attributes of the plurality of resources; obtaining, by the processor, third data indicating productivity attributes of the plurality of resources; training, by the processor, a model based on the first data, the second data, and the third data, wherein the model represents one or more transitions of the plurality of resources over time, and the transitions of the plurality of resources are based on the tier attribute, the function attribute, and the productivity attribute of the plurality of resources; receiving, by the processor, a set of controls comprising at least an objective to optimize a performance of the entity; generating, by the processor, a controlled model by integrating the set of controls into the model; and determining, by the processor, a set of outcomes from the controlled model, wherein the set of outcomes comprises at least a set of transitions relating to the plurality of resources, and the set of transitions optimizes the performance of the entity.

2 . The computer-implemented method of claim 1 , wherein the model is based on a time inhomogeneous Markov chain.

3 . The computer-implemented method of claim 1 , wherein the first data comprises a quantified tier of the tier attributes of the plurality of resources.

4 . The computer-implemented method of claim 1 , wherein the second data comprises a competency level of each function among the function attributes possessed by each resource among the plurality of resources.

5 . The computer-implemented method of claim 1 , wherein the productivity attributes are based on historical data relating to performance of the plurality of resources.

6 . The computer-implemented method of claim 1 , wherein the set of outcomes indicate at least one of:
a recommendation to add at least one resource of a particular attribute to the plurality of resources, the particular attribute comprising at least one of the tier attribute, the function attribute, and the productivity attribute; a recommendation to modify at least one composition of resources in the entity; and a recommendation to assign different tasks to at least one composition of the resources in the entity.

7 . The computer-implemented method of claim 1 , further comprising:
determining an amount of resources of the plurality of resources exceeds a threshold; and applying an approximation technique on the model to determine the set of outcomes.

8 . The computer-implemented method of claim 1 , further comprising retraining the model using the set of outcomes.

9 . A system comprising:
a memory device configured to store a database that comprises:
first data indicating tier attributes of a plurality of resources of an entity;
second data indicating function attributes of the plurality of resources;
third data indicating productivity attributes of the plurality of resources;
a hardware processor configured to be in communication with the memory device, the hardware processor being configured to: obtain the first data, the second data, and the third data from the memory device; train a model based on the first data, the second data, and the third data, wherein the model represents one or more transitions of the plurality of resources over time, and the transitions of the plurality of resources are based on the tier attribute, the function attribute, and the productivity attribute of the plurality of resources; receive a set of controls comprising at least an objective to optimize a performance of the entity; generate a controlled model by integrating the set of controls into the model; and determine a set of outcomes from the controlled model, wherein the set of outcomes comprises at least a set of transitions relating to the plurality of resources, and the set of transitions optimizes the performance of the entity.

10 . The system of claim 9 , wherein the model is based on a time inhomogeneous Markov chain.

11 . The system of claim 9 , wherein:
the first data comprises a quantified tier of the tier attributes of the plurality of resources; the second data comprises a competency level of each function among the function attributes possessed by each resource among the plurality of resources; and the productivity attributes are based on historical data relating to performance of the plurality of resources.

12 . The system of claim 9 , wherein the set of outcomes indicate at least one of:
a recommendation to add at least one resource of a particular attribute to the plurality of resources, the particular attribute comprising at least one of the tier attribute, the function attribute, and the productivity attribute; a recommendation to modify at least one composition of resources in the entity; and a recommendation to assign different tasks to at least one composition of the resources in the entity.

13 . The system of claim 9 , wherein the hardware processor is further configured to:
determine an amount of resources of the plurality of resources exceeds a threshold; and apply an approximation technique on the model to determine the set of outcomes.

14 . The system of claim 9 , wherein the hardware processor is further configured to retrain the model using the set of outcomes.

15 . A computer program product of evaluating a performance of an entity, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing element of a device to cause the device to:
obtain first data indicating tier attributes of a plurality of resources of an entity; obtain second data indicating function attributes of the plurality of resources; obtain third data indicating productivity attributes of the plurality of resources; train a model based on the first data, the second data, and the third data, wherein the model represents one or more transitions of the plurality of resources over time, and the transitions of the plurality of resources are based on the tier attribute, the function attribute, and the productivity attribute of the plurality of resources; receive a set of controls comprising at least an objective to optimize a performance of the entity; generate a controlled model by integrating the set of controls into the model; and determine a set of outcomes from the controlled model, wherein the set of outcomes comprises at least a set of transitions relating to the plurality of resources, and the set of transitions optimizes the performance of the entity.

16 . The computer program product of claim 15 , wherein the model is based on a time inhomogeneous Markov chain.

17 . The computer program product of claim 15 , wherein:
the first data comprises a quantified tier of the tier attributes of the plurality of resources; the second data comprises a competency level of each function among the function attributes possessed by each resource among the plurality of resources; and the productivity attributes are based on historical data relating to performance of the plurality of resources.

18 . The computer program product of claim 15 , wherein the set of outcomes indicate at least one of:
a recommendation to add at least one resource of a particular attribute to the plurality of resources, the particular attribute comprising at least one of the ti

Assignees

• IBM

Inventors

• Lu Yingdong
• Sharma Mayank
• Squillante Mark S
• Zhang Bo
• Yamazaki Kazutoshi

Classifications

• G06F9/5055

  considering software capabilities, i.e. software resources associated or available to the machine · CPC title

• G05B13/041 Primary

  in which a variable is automatically adjusted to optimise the performance · CPC title

• G05B13/0265

  the criterion being a learning criterion · CPC title

• G06F9/5061 Primary

  Partitioning or combining of resources · CPC title