A COMPUTER IMPLEMENTED APPRAISAL SYSTEM AND METHOD THEREOF

• US 20200134535A1
• Filed: 07/11/2018
• Published: 04/30/2020
• Est. Priority Date: 07/11/2017
• Status: Active Grant

• Current Assignee: Cybage Software Private Limited
• Original Assignee: Cybage Software Private Limited
• Inventors: NATHANI, Arun Vijay
• Granted Patent: US 11,379,780 B2
• Time in Patent Office: Days
• CPC Class Codes: G06Q 10/06393 Score-carding, benchmarking or key performance indicator [KPI] analysis
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function

Abstract

The present disclosure relates to a computer implemented appraisal system (100). A repository (102) stores a set of pre-defined organization rules, a lookup table having a list of employees, and actual emoluments, computed historical appraisal score values, employee details, and a set of pre-determined parameters corresponding to each of the employees, and a predicted weightage corresponding to each of the set of pre-determined parameters. An analyzer (104) analyzes the stored employee details to generate a plurality of clusters of employees. A matrix creator (106b) creates a matrix for each of the pre-determined parameters, and populates each cell of the created matrix with a rating value by comparing a score value of each of the employees associated with the cell. A ranking module (106a) generates a rank value for each of the employees. A validation module (110) identifies an error or a bias. A computation module (112) computes emoluments for each of the employees.

Claims

1. A computer implemented appraisal system (100), said system (100) comprising:

a repository (102) configured to store a set of pre-defined organization rules, a lookup table having a list of employees, and actual emoluments, computed historical appraisal score values, employee details, and a set of pre-determined parameters corresponding to each of said employees, and a predicted weightage corresponding to each of said set of pre-determined parameters;

an analyzer (104) configured to cooperate with said repository (102), said analyzer further configured to analyze said stored employee details for each of said employees based on said set of pre-defined organization rules to generate a plurality of clusters of employees;

a ranking engine (106) configured to cooperate with said repository (102) and said analyzer (104), said ranking engine (106) comprising;

a matrix creator (106b) configured to create a matrix for each of said clusters of employees for each of said pre-determined parameters, and further configured to populate each cell of said created matrix with a rating value by comparing a score value of each of the employees associated with said cell; and

a ranking module (106a) configured to cooperate with said matrix creator (106b), and further configured to generate a rank value for each of the employees of said created matrix based on said rating value;

a validation module (110) configured to cooperate with said ranking engine (106), and further configured to identify at least one error or at least one occurrence of biasness by comparing the rank value of each employee with rank values of other employees of said created matrix;

an autocorrection engine (111) configured to cooperate with said validation module (110), said autocorrection engine (111) configured to autocorrect said identified error or biasness using said computed historical appraisal score values and said set of pre-defined rules; and

a computation module (112) configured to cooperate with said repository (102) and said ranking engine (106), and further configured to compute emoluments for each of said employees based on said rank value, said actual emoluments, and said set of pre-defined organization rules,

wherein said analyzer (104), said ranking engine (106), said validation module (110), said autocorrection engine (111), and said computation module (112) are configured to be implemented using one or more processor(s).

2. The system (100) as claimed in claim 1, wherein said set of pre-determined parameters is selected from the group consisting of on-time project deliverables, discipline, attentiveness, punctuality, obedience to an organization policies, technical knowledge, productivity, and quality of work.

3. The system (100) as claimed in claim 1, wherein said autocorrection engine (111) comprises:

an updater (111a) configured to cooperate with said validation module (110), and further configured to autocorrect said identified error by updating the cell of said created matrix using said computed historical appraisal score values and said set of pre-defined rules; and

a flag generator (111b) configured to cooperate with said updater (111a), and further configured to generate a flag to indicate autocorrection of said rank value,

wherein, said flag generator (111b) and said updater (111a) are configured to be implemented using one or more processor(s).

4. The system (100) as claimed in claim 1, wherein said validation module (110) is configured to generate an alert if biasness or error is identified.

5. The system (100) as claimed in 1, which includes a prediction module (114) configured to predict said weightage of each of said set of pre-determined parameters using a best fit technique, wherein said best fit technique is selected from the group consisting of a least square technique, a curve fitting technique, and a regression analysis technique, said prediction module (114) is configured to be implemented using one or more processor(s).

6. The system (100) as claimed in claim 1, wherein said matrix creator (106b) comprises:

an input module (108a) configured to facilitate a user to provide said score value of each employees;

a comparator (108b) configured to cooperate with said input module (108a), and further configured to compare said score value of each of the employees associated with each cells of said created matrix to generate said rating value for each employee of said created matrix; and

a populating module (108c) configured to cooperate with said comparator (108b), and further configured to populate each cell of said created matrix with said rating value,

wherein said input module (108a), said comparator (108b), and said populating module (108c) are configured to be implemented using one or more processor(s).

7. The system (100) as claimed in claim 1, wherein said matrix creator (106b) includes a splitting module (108d) configured to diagonally split said created matrix into an upper triangulation matrix and a lower triangulation matrix, wherein either of said upper triangulation matrix or said lower triangulation matrix is a non-editable triangulation matrix, said splitting module (108d) is configured to be implemented using one or more processor(s).

8. A computer implemented method (200) for providing appraisal to employees, said method (200) comprising the steps of:

storing (202), in a repository (102), a set of pre-defined organization rules, a lookup table having a list of employees, and actual emoluments, computed historical appraisal score values, employee details, and a set of pre-determined parameters corresponding to each of said employees, and a predicted weightage corresponding to each of said set of pre-determined parameters;

analyzing (204), by an analyzer (104), stored employee details for each of said employees based on said set of pre-defined organization rules to generate a plurality of clusters of employees;

creating (206), by a matrix creator (106b) of a ranking engine (106), a matrix for each of said clusters of employees for each of said pre-determined parameters;

populating (208), by said matrix creator (106), each cell of said created matrix with a rating value by comparing a score value of each of the employees associated with said cell;

generating (210), by a ranking module (106a) of said ranking engine (106), a rank value for each of the employees of said created matrix based on said rating value;

identifying (212), by a validation module (110), at least one error or at least one occurrence of biasness by comparing the rank value of each employee with rank values of other employees of said created matrix;

autocorrecting (214), by an autocorrection engine (111), said identified error or biasness using said computed historical appraisal score values and said set of pre-defined rules; and

computing (216), by a computation module (112), emoluments for each of said employees based on said rank value, said actual emoluments and said set of pre-defined organization rules.