ADVANCED RECRUITMENT SYSTEM USING ARTIFICIAL INTELLIGENCE

Abstract

Bias detection system for hiring, making use of a Raspberry Pi, NPU, camera, microphone and cloud integration that can detect and help to mitigate bias in real-time by analyzing both verbal and nonverbal cues during candidate evaluation. The video data is captured by the camera to detect non-verbal communication of a potential bias such as facial expressions or body language during interviews. The audio data is captured by the microphone facilitating tone analysis, sentiment analysis and speech pattern analysis to identify interviewer’s biases language. A neural processing unit accelerates complex data analysis in real time enabling instant identification and warning on possible biases in hiring processes.

Specification

Description:FIELD OF THE INVENTION
This invention relates to advanced recruitment system using artificial intelligence.
BACKGROUND OF THE INVENTION
Recruitment bias is among the elements, which can impede the efforts of diversifying the workplace and making it more inclusive. These biases, whether on purpose or not, at times creep into various components of the recruitment cycle, such as the creation of vacancy advertisements and the process of filtering candidates for interviews. There are of course psychological factors that would limit these potential candidates who would otherwise create a more diverse workforce.
This is where the AI may play a huge role to identify all forms of bias within the recruitment cycle. Such technologies can spot discrimination by examining the way certain words are used with respect to advertisements, resumes or interview processes. For example, there exist some keywords in an ad that appear to be less appealing for women or minority groups or similar individuals with the same qualification may be treated differently based on their demographics.
AI is able to hunt those biases with the help of machine learning algorithms over the large volume of data retrieved from different sources. Thus, these insights may help change job descriptions, enhance the criteria of resume screening, and even ensure that entering managers' training on conducting fair job interviews. Bias detection in recruitment through the use of the AI technology does not happen overnight. Rather it is a process that is moving toward hiring that is based on performance measurements rather than biases which are non conscious. Above all it enhances justice and equity in the recruitment process. It enables every candidate to be meted out the justice of being judged only on the merits that they present.
However, alternative B will aid businesses to have more efficient hiring processes through automating identification of unintentional bias that can never be attained by mere human monitoring. This is important as it makes sure that no candidate gets rejected based on factors not linked to his/her competence level during interviews. Another thing is that it raises the number of workers with diverse backgrounds in any given firm hence improving its perception as an impartial employer.
Apart from this, if firms identify and remove bias at early stages in recruitment campaigns they lower their chances of being sued over employment discrimination issues.. This not only raises work-force diversity but also creates a perception that an organization cares about everyone's interests even when some people from particular groups might think otherwise. Moreover, this will aid firms since they can detect any unconscious biases at initial stages which can prevent them from being accused of practicing discriminatory and prejudicial activities such as racism.
US20180089629A1 The inherent human biases related to hiring processes are mediated using automated computer-based systems. Computer executed logic is configured to detect and compensate for, for example, cultural, gender, and/or racial biases. Specific applications include, but are not limited to, job descriptions, review of resumes and interviews.
RESEARCH GAP: Promotes fair hiring practices: This means that the system can identify and mitigate biases in recruitment using hiring data thereby ensuring all candidates are evaluated based on skills and qualifications leading to a diverse and inclusive workforce.
US20200394615A1 A platform for providing employment assistance services to enterprises and candidates is disclosed. For example, the platform trains, based on personal attributes of employees of multiple enterprise and work culture attributes associated with each employer of the multiple enterprises, a machine learning model that defines associations between the personal attributes and the work culture attributes. Further, for example, the platform generates a resume for a candidate based upon information from the user profile. The platform can eliminate bias when managing such resume by indexing the personal attributes of all user profiles to identify hidden variables, where the hidden variables are data that has been indexed as receiving biased treatment, editing the resume to remove the hidden variables, and returning the resume to the candidate.
RESEARCH GAP: Enhances decision-making with data-driven insights: With the help of this system, HR teams get accurate information about recruitment patterns that enable them make more informed decisions. All these reduce unconscious biases and ensure fairness at every stage of the employment process.
US20200394615A1 A platform for providing employment assistance services to enterprises and candidates is disclosed. For example, the platform trains, based on personal attributes of employees of multiple enterprise and work culture attributes associated with each employer of the multiple enterprises, a machine learning model that defines associations between the personal attributes and the work culture attributes. Further, for example, the platform generates a resume for a candidate based upon information from the user profile. The platform can eliminate bias when managing such resume by indexing the personal attributes of all user profiles to identify hidden variables, where the hidden variables are data that has been indexed as receiving biased treatment, editing the resume to remove the hidden variables, and returning the resume to the candidate.
RESEARCH GAP: Improves candidate experience: As a result, where there is no partiality within the interview process, candidates will have a feeling of significance and equality. Therefore an organization should provide positive experiences for its job applicants, which can enhance its image as an employer.
US20190130512A1 A method for pre-hiring and post-hiring leadership development is performed by computing devices. A Software as a Service (SaaS) delivery model is used in which software is licensed on a subscription basis and is centrally hosted in the Internet Cloud or on a server. Organizational account login types and permissions are assigned corresponding to function. The login types include Super-users or Leads, Supervisors, Employees, and Affiliates. The software guides the login types through a process of leadership development activities, including creating, maintaining, storing, and viewing, on a computer, data that includes positions. The process also assesses the positions using numerical weighting preferences to create corresponding Competency Models and/or Culture Fit Models. The process also assesses candidates using evaluative criteria derived from the Competency Models and/or Culture Fit Models. Individual subscribers may utilize the system to create candidate and/or employee profiles, set self-improvement goals, and receive feedback, depending upon their status.
RESEARCH GAP: Supports compliance with equal opportunity laws: On one hand, while identifying possible biases embedded in their employment policies like this related to employee selection procedures; it assists organizations in conforming to regulations governing equal opportunities for all workers. Thus, by doing so businesses minimize litigation risks whilst showing their commitment towards equity.
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention relates to advanced recruitment system using artificial intelligence.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
The architecture diagram with fine details illustrates a complex system intended for the detection of bias in job recruitment through AI and computer vision. And, it is centered around a Raspberry Pi that acts as the main processing unit, and it combines things like camera, microphone, neural processing unit and connectivity modules.


BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: GENERAL STRUCTURE OF THE DEVICE
FIGURE 2: DETAILED STRUCTURE OF THE DEVICE AND CONNECTED COMPONENTS
FIGURE 3: WORKING OF ALL THE PROCESS INVOLVED INTO THE SYSTEM
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms "a"," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", "third", and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The architecture diagram with fine details illustrates a complex system intended for the detection of bias in job recruitment through AI and computer vision. And, it is centered around a Raspberry Pi that acts as the main processing unit, and it combines things like camera, microphone, neural processing unit and connectivity modules.
Visuals and sounds from interviews are collected through microphones and cameras to allow the system to assess both verbal content and non-verbal cues. Neural stick and Coral USB Accelerator offer more power for processing leading to real time analysis of complicated data.
For instance, this data can be processed using machine learning models that are either stored on external storage or sent to cloud servers for further analysis. Similarly, the system comprises secure data storage components such as SSDs which are used for handling large volumes of datasets or sensitive information.
This requires that the Raspberry Pi has a WiFi/Bluetooth module for easy linkage to a cloud server which makes continuous archiving of data much simpler.
Thus, this wireless connection ensures safe storage of all interview & application process data so that they can be analyzed later on.
To do this, a 12V 3amp lithium polymer battery is used to manage the power supply of the system. This is also coupled with the power supply management module that must not fail when the system is in use for a long time as it provides support for continuous AI algorithms operation and data processing tasks
Its NPU also handles heavy loads like deep learning models. In so doing, it has allowed real-time identification of biases using Big Data analytics. The solutions include data storage and external memory devices that guarantee secure retention of all the relevant information; thus, providing an effective scalable platform for working with sensitive data in relation to hiring processes. This kind of structure enables the system to act as a strong tool of recognizing and reducing biases leading to fairness in employment practices.
The information is then pre-processed by properly cleaning and normalizing of data, so that consistency and correctness can be maintained in the next steps. This initial stage of handling data is important because it changes the format of data for applying machine learning models as well as bias detection algorithms. Meanwhile, post-preprocessing stages include using AI models to detect language bias and tone during interviews by examining decisions for potential prejudice.
If any biases are identified, a warning system is activated to alert HR team on relevant data that need to be reviewed further. This stage sees to it that any biases identified are handled promptly as such enabling HR department take necessary corrective measures. The final step is usually the production of a report which contains graphs and charts that can visually represent these findings. It therefore acts as an advantageous guide for Human Resource professionals who have an interest in making changes needed in the hiring process by showing them how prejudiced such recruiting activities have become.
The last steps in the flowchart are to provide process improvements and execute changes based on the analysis. The system is always watching out for the hiring process, it gets new data then analyses them again to make sure that the changes put in place are effective. Such ongoing feedback loop is absolutely necessary for a fair and non-biased hiring process. Therefore, this flowchart emphasizes the need to continually monitor and adjust so as to ensure that over time, it remains an effective system of bias detection and prevention. Adherence to this structured approach can make organizations have a more equal hiring process that will eventually lead to better recruitment decisions and a diverse workforce as well.
When working to define biases, there is a need for strong feedback mechanism and a review procedure that is well depicted in this chart. These biases are reported to HR together with relevant information that allows HR to analyze what happened in detail. This is important because such understanding offers a context for situations which are to irritate or otherwise come from human common sense and so shed light into the probable bias. Such reviews will to some extent assist in the long term management of the AI models and their algorithms for improved performance.
As hiring environments evolve, this system of bias detection should elastically evolve with the time to remain very useful and accurate. Such is the case, where the AI tracking bias, is enhanced with changes with time and constantly by responding to feed back information.

Also, there is an inherent structure which clearly outlines how bias reporting works and how bias reporting is disseminated. With the assistance of these reports, such adverse decisions that are anticipated to take place in hiring due to bias can be dealt with by policymakers. They are self-sufficient and appended with executive summaries, relevant graphics and tables that are appropriate for decision making regarding selection strategies adopted by HR departments.
ADVANTAGES OF THE INVENTION
Promotes fair hiring practices: This means that the system can identify and mitigate biases in recruitment using hiring data thereby ensuring all candidates are evaluated based on skills and qualifications leading to a diverse and inclusive workforce.
Enhances decision-making with data-driven insights: With the help of this system, HR teams get accurate information about recruitment patterns that enable them make more informed decisions. All these reduce unconscious biases and ensure fairness at every stage of the employment process.
Improves candidate experience: As a result, where there is no partiality within the interview process, candidates will have a feeling of significance and equality. Therefore an organization should provide positive experiences for its job applicants, which can enhance its image as an employer.
Supports compliance with equal opportunity laws: On one hand, while identifying possible biases embedded in their employment policies like this related to employee selection procedures; it assists organizations in conforming to regulations governing equal opportunities for all workers. Thus, by doing so businesses minimize litigation risks whilst showing their commitment towards equity.
Enhances Diversity and Inclusion Initiatives: The system's ability to detect and correct prejudices is in line with wider diversity and inclusion initiatives. This does not only build stronger company culture but also advances innovation and performance through more diverse teams.
, Claims:1. Bias detection system for hiring, making use of a Raspberry Pi, NPU, camera, microphone and cloud integration that can detect and help to mitigate bias in real-time by analyzing both verbal and nonverbal cues during candidate evaluation.
2. The system of claim 1 wherein the video data is captured by the camera to detect non-verbal communication of a potential bias such as facial expressions or body language during interviews.
3. The system of claim 1 wherein audio data is captured by the microphone facilitating tone analysis, sentiment analysis and speech pattern analysis to identify interviewer's biases language.
4. The system of claim 1 wherein a neural processing unit accelerates complex data analysis in real time enabling instant identification and warning on possible biases in hiring processes.
5. The system of claim 1 wherein connectivity module (WiFi/Bluetooth) allows for smooth transmission of collected data to a cloud server for long-term storage and further study which ensures scalability and accessibility of data.
6. In this case, the cloud server interfaces with central databases that store large datasets and provide enough computational power for complex AI model computations.
7. The system as claimed in claim 1, wherein a processor is incorporated on a neural stick, enabling the software to operate deep learning models designed to identify subtle prejudices not seen when using normal analysis techniques.
8. For example, the power supply management module uses a 12V 3amp lithium polymer battery to make sure that even during power fluctuations it can run without interrupting critical hiring processes.
9. The system as claimed in claim 1 wherein data and models are safely stored such as SSD and external storage devices for protecting confidential information in order that all hiring related data would be safeguarded and accessible for compliance or audit purposes.
10. To this end, these architectural designs will also ensure that secure transmission of sensitive information between systems results in robust frameworks which guarantee candidate data integrity throughout the recruiting process.

Documents