# US 2023/0274233 A1 · Machine learning-based recruitment system and method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0274233 A1
- Document ID: US20230274233A1
- Status: Published application
- Kind: A1
- Application number: 17/682,553
- Filed: 2022-02-28
- Published: 2023-08-31
- Earliest claimed: 2020-12-30
- Inventors: Hariharan Sivaraman
- Web page: https://patentgrep.com/patent/US20230274233A1

## CPC

- G06Q 10/1053: Employment or hiring
- G06Q 10/063112: {Skill-based matching of a person or a group to a task}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A system and method to aid in a recruitment process by providing a list of candidates that best match the job requirement. The system includes an explainable machine learning module that applies six layers of filters and profile matching to a set of job applications to shortlist a predefined number of applications. The shortlisted applications can be presented to recruited for logical assessment about the relevancy of each of the shortlisted applications. Based on the self-assessment, the set of applications can again be processed by the explainable machine learning module to shortlist a final list of candidates.

## Claims

### Claim 1

A system to aid in a recruitment process, the system comprising a processor and a memory, the system configured to implement a method comprising the steps of:
receiving a set of applications for one or more job vacancies;
subjecting the set of applications to a machine learning based multi-layered analysis module, wherein the analysis module upon execution by the processor applies a plurality of filters to the set of applications and further subject the set of applications to profile matching, wherein the analysis module is explainable;
scoring, by the analysis module, each application of the set of applications;
presenting, by the analysis module, a predetermined number of applications from the set of applications based on the scoring;
receive a logical assessment for each of the predetermined number of applications;
updating, the analysis module using reinforcement learning and the logical assessment of the each of the predetermined number of applications; and
upon updating, determining a list of shortlisted applications from the set of applications by subjecting the set of applications to the updated analysis module.

### Claim 2 (depends on 1)

The system according to claim 1, wherein the plurality of filters comprises six layers of filtering.

### Claim 3 (depends on 1)

The system according to claim 1, wherein the updated analysis module causes rescoring of the each of the set of applications.

### Claim 4 (depends on 1)

The system according to claim 1, wherein the method further comprises the steps of: receiving a self-assessment form from a plurality of candidates of the set of applications.

### Claim 5 (depends on 4)

The system according to claim 4, wherein the method further comprises the steps of:
receiving a benchmark application, wherein the benchmark application and the self-assessment form are used for the profile matching.

### Claim 6 (depends on 1)

The system according to claim 1, wherein the predetermined number of applications are presented such that certain predefined information in the predetermined number of applications is masked to prevent human bias in the logical assessment.

### Claim 7 (depends on 1)

The system according to claim 1, wherein the method further comprises the steps of:
providing an interface to receive a weightage for a plurality of hard and soft skill requirements for the one or more job vacancies.

### Claim 8

A method to aid in a recruitment process, the method implemented within a system comprising a processor and a memory, the method comprising the steps of:
receiving a set of applications for one or more job vacancies;
subjecting the set of applications to a machine learning based multi-layered analysis module, wherein the analysis module upon execution by the processor applies a plurality of filters to the set of applications and further subject the set of applications to profile matching, wherein the analysis module is explainable;
scoring, by the analysis module, each application of the set of applications;
presenting, by the analysis module, a predetermined number of applications from the set of applications based on the scoring;
receive a logical assessment for each of the predetermined number of applications;
updating, the analysis module using reinforcement learning and the logical assessment of the each of the predetermined number of applications; and
upon updating, determining a list of shortlisted applications from the set of applications by subjecting the set of applications to the updated analysis module.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the plurality of filters comprises six layers of filtering.

### Claim 10 (depends on 8)

The method according to claim 8, wherein the updated analysis module causes rescoring the each of the set of applications.

### Claim 11 (depends on 8)

The method according to claim 8, wherein the method further comprises the steps of:
receiving a self-assessment from a plurality of candidates of the set of applications.

### Claim 12 (depends on 11)

The method according to claim 11, wherein the method further comprises the steps of:
receiving a benchmark application, wherein the benchmark application and the self-assessment are used for the profile matching.

### Claim 13 (depends on 8)

The method according to claim 8, wherein the predetermined number of applications are presented such that certain predefined information in the predetermined number of applications is masked to prevent human bias in the logical assessment.

### Claim 14 (depends on 8)

The method according to claim 8, wherein the method further comprises the steps of:
providing an interface to receive a weightage for a plurality of hard and soft skill requirements for the one or more job vacancies.