Claims:WE CLAIM:
1. A method (300) for refining a job description document using Artificial Intelligence, the method (300) comprising processor implemented steps of:
identify a set of skills for a job role associate with a new project corresponding to an organization by,
receiving one or more documents corresponding to the new project,
processing the one or more documents to generate a set of document vectors,
identifying a subset of projects, from the set of projects, which are similar to the new project based on the set of document vectors,
identifying a set of team members, associated with the subset of projects, based on the job role,
processing one or more text documents associated with the subset of projects to determine project documentation corresponding to each team member, from the set of team members,
analysing the project documentation, corresponding to each team member, using LDA (latent Dirichlet allocation) techniques, to identify a set of phases associated with the subset of projects, wherein the set of phases are processed to generate the list of skills; and
refining a job description document associated with the job role based on the list of skills, wherein the job description document is refined by including one or more skills, from the list of skills.

2. The method (300) of claim 1, wherein the one or more documents are processed using a trained doc2vec module, wherein the trained doc2vec module is generated by analysis of a set of projects associated with the organization.
3. The method (300) of claim 1 further comprising steps for identifying critical aspects of the new projects for assisting the recruitment team in analysing shortlisted candidates by,
modelling a critical aspect identification module (205) based on the subset of projects and the set of phases, wherein the critical aspect identification module (205) is trained by utilizing JIRA tracker of the subset of projects, wherein each task in JIRA tracker is analysed based on a set of parameters including Number of Bugs raised, Number of sub tasks created, Number of people in task implementations, and Issue resolving time,
identifying one or more tasks which are greater than the mean of each task in JIRA tracker,
identify a phase to which the one or more tasks belongs to, by using cosine similarity based on comparison of the one or more tasks description data in JIRA with phases identified, and
determine the critical aspect based on the number of tasks in each phase.

4. The method of claim 1 further comprising steps for identifying a target stakeholder from a recruitment team, for handle a recruitment process for the job role associate with the new project, by modelling each recruitment team member from the recruitment team with a set of attributes, wherein the set of attributes include years of experience in recruitment, connects on Social platform, skills of the person, Number of Resumes gathered for job skill, and BU level.

5. The method of claim 4 further comprising steps for analysing the set of attributes corresponding to each recruitment team member to identify the target stakeholder from the recruitment team.

6. A system (101) for refining a job description document using Artificial Intelligence, the system (101) comprising:
a processor (201) and a memory (203) coupled to the processor (201), wherein the processor (201) is configured to execute instructions stored in the memory (203) for:
identify a set of skills for a job role associate with a new project corresponding to an organization by,
receiving one or more documents corresponding to the new project,
processing the one or more documents to generate a set of document vectors,
identifying a subset of projects, from the set of projects, which are similar to the new project based on the set of document vectors,
identifying a set of team members, associated with the subset of projects, based on the job role,
processing one or more text documents associated with the subset of projects to determine project documentation corresponding to each team member, from the set of team members,
analysing the project documentation, corresponding to each team member, using LDA (latent Dirichlet allocation) techniques, to identify a set of phases associated with the subset of projects, wherein the set of phases are processed to generate a list of skills; and
refining a job description document associated with the job role based on the list of skills, wherein the job description document is refined by including one or more skills, from the list of skills.

7. The system (101) of claim 6, wherein the one or more documents are processed using a trained doc2vec module, wherein the trained doc2vec module is generated by analysis of a set of projects associated with the organization.

8. The system (101) of claim 6 further configured for identifying critical aspects of the new projects for assisting the recruitment team in analysing shortlisted candidates by,
modelling a critical aspect identification module (205) based on the subset of projects and the set of phases, wherein the critical aspect identification module (205) is trained by utilizing JIRA tracker of the subset of projects, wherein each task in JIRA tracker is analysed based on a set of parameters including Number of Bugs raised, Number of sub tasks created, Number of people in task implementations, and Issue resolving time,
identifying one or more tasks which are greater than the mean of each task in JIRA tracker,
identify a phase to which the one or more tasks belongs to using cosine similarity based on comparison of the one or more tasks description data in JIRA with phases identified, and
determine the critical aspect based on the number of tasks in each phase.

9. The system of claim 6 further configured for identifying a target stakeholder from a recruitment team, for handle a recruitment process for the job role associate with the new project, by modelling each recruitment team member from the recruitment team with a set of attributes, wherein the set of attributes include years of experience in recruitment, connects on Social platform, skills of the person, Number of Resumes gathered for job skill, and BU level.

10. The system of claim 9 further configured for analysing the set of attributes corresponding to each recruitment team member to identify the target stakeholder from the recruitment team.
, Description:FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION
(Specification 10 and Rule 13)

Title of the invention:
A SYSTEM AND METHOD FOR REFINING A JOB DESCRIPTION DOCUMENT USING ARTIFICIAL INTELLIGENCE

APPLICANT:
Zensar Technologies Limited.
(An Indian entity having address)
Zensar Knowledge Park, Plot # 4, MIDC, Kharadi, Off
Nagar Road, Pune-411014, Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.
CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY
The present application does not claim priority from any other patent application.
TECHNICAL FIELD
The present subject matter described herein, in general, relates to a system and a method of recruiter assistance. More specifically, the present subject matter discloses the system and the method of refining a job description document using artificial intelligence for recruiter assistance.
BACKGROUND
The subject matter discussed in the background section should not be assumed to be prior art merely because of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
One of the most important activity in any organization is the recruitment process of new candidate for a project. Many large organizations have dedicated recruitment team for the purpose of identifying and hiring new candidates. However, these recruitment team members do not have a technical background and end up in generating standard job description templates for posting new openings for the organization. Due to these standard job description templates, many irrelevant CV are shortlisted.
Furthermore, the typical recruitment process often does not lead to fruitful outcomes and it is a highly time-consuming process due to huge pool of resource availability for internal/external search. Some of the tools available in the art focus on automatically identifying the most relevant candidates by comparing a job description with the CV of a set of candidates. However, if the job description is not comprehensive, the identified candidates are also not a perfect match for the job role.
Thus, there is always a challenge in front of the recruitment team to effectively identifying right skills for a job opening, identifying critical aspect of the project, and identifying right SPOC for candidate search. There are many AI -powered recruitment assistance tools available in the market. These tools provide recruiters with highly personalized services. However, these tools fail to capture the right skill required for a job because of the use of templated Job Description Documents for job positions.
For example, in a Requirements Specification Document (SRS) a client for a new project may specify that the software to be developed should operate on a cloud platform (ex: azure, then JD contains the term Azure expertise in technical skills) as one of the requirements. In this scenario, Azure expertise may have wide range of possible candidates such as Candidates having experience in migrating traditional DBs to Azure cloud, Candidates having experience in Azure analytics, and Candidates having experience in Azure administration. All these candidates have different expertise in frameworks such as Azure blob storage, Azure data bricks, Azure Ops respectively. This results in a huge pool of resource availability but may not be the right pool of resources for the new project. The right technology skill now becomes key to differentiate among them. With the project RFP/description being related to Analytics, the candidate having experience in Azure analytics would be the right shortlisted candidate. However, such detailed analysis is not possible by the Recruitment team which leads to unnecessary shortlisting of irrelevant candidates.
Clearly, the need for a tool that can refine comprehensive job description documents and assist the recruitment team in identifying the right candidate for a particular job role.
SUMMARY
This summary is provided to introduce concepts related to a system and a method of refining a job description document using Artificial Intelligence, and the concepts are further described below in the detailed description. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.
In one implementation, a system for refining a job description document using Artificial Intelligence, is illustrated in accordance with an embodiment of the present invention. The system may comprise a processor and a memory coupled to the processor, wherein the processor is configured to execute instructions stored in the memory. The processor may execute programmed instructions for identifying a set of skills for a job role associate with a new project corresponding to an organization. For the purpose of identifying the set of skills for the job role, the processor is configured for receiving one or more documents corresponding to the new project. Further, the processor is configured for processing the one or more documents to generate a set of document vectors, wherein the one or more documents are processed using a trained doc2vec module. Further, the processor is configured for identifying a subset of projects, from the set of projects, which are similar to the new project based on the set of document vectors. Further, the processor is configured for identifying a set of team members, associated with the subset of projects, based on the job role. Further, the processor is configured for processing one or more text documents associated with the subset of projects to determine project documentation corresponding to each team member, from the set of team members. Further, the processor is configured for analysing the project documentation, corresponding to each team member, using LDA (Latent Dirichlet Allocation) techniques, to identify a set of phases associated with the subset of projects, wherein the set of phases are processed to generate a list of skills. Furthermore, the processor is configured for refining a job description document associated with the job role based on the list of skills, wherein the job description document is refined by including one or more skills, from the list of skills.
In another implementation, a method for refining a job description document using Artificial Intelligence, is illustrated in accordance with an embodiment of the invention. The method may comprise one or more steps for identifying a set of skills for a job role associate with a new project corresponding to an organization. For identifying the set of skills for the job role, the method may comprise one or more steps for receiving one or more documents corresponding to the new project. The method may further comprise one or more steps for processing the one or more documents to generate a set of document vectors, wherein the one or more documents are processed using a trained doc2vec module. The method may further comprise one or more steps for identifying a subset of projects, from the set of projects, which are similar to the new project based on the set of document vectors. The method may further comprise one or more steps for identifying a set of team members, associated with the subset of projects, based on the job role. The method may further comprise one or more steps for processing one or more text documents associated with the subset of projects to determine project documentation corresponding to each team member, from the set of team members. The method may further comprise one or more steps for analysing the project documentation, corresponding to each team member, using LDA (latent Dirichlet allocation) techniques, to identify a set of phases associated with the subset of projects, wherein the set of phases are processed to generate a list of skills. The method may further comprise one or more steps for refining a job description document associated with the job role based on the list of skills, wherein the job description document is refined by including one or more skills, from the list of skills.
BRIEF DESCRIPTION OF DRAWINGS
The detailed description is described with reference to the accompanying Figures. The same numbers are used throughout the drawings to refer to like features and components.
Figure 1 illustrates a network implementation 100 of a system 101 for refining a job description document using Artificial Intelligence, in accordance with an embodiment of the present disclosure.
Figure 2 illustrates components of the system 101 for refining the job description document using Artificial Intelligence, in accordance with an embodiment of the present disclosure.
Figure 3 illustrates a method 300 for refining the job description document using Artificial Intelligence, in accordance with an embodiment of the present disclosure.
Figure 4a and 4b the job description document, in accordance with an embodiment of the present disclosure.
DETAILED DESCRIPTION
Reference throughout the specification to “various embodiments,” “some embodiments,” “one embodiment,” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in various embodiments,” “in some embodiments,” “in one embodiment,” or “in an embodiment” in places throughout the specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments.
Referring to Figure 1, implementation 100 of system 101 for refining a job description document using Artificial Intelligence is illustrated, in accordance with an embodiment of the present subject matter. The system 101 may be connected to a project database 102. The project database may be configured to maintain documentation corresponding to a set of projects associated with an organization. Further, the system 101 may be connected to a set of devices 103 to enable the users/ stakeholders in an organization to establish communication with the system 101. The system 101 is enabled with a set of modules to enable Artificial Intelligence capabilities for processing information corresponding to new projects and refining job description documents.
In one embodiment, the system 101 may comprise a processor and a memory. Further, the system 101 may be connected to the project database 102 through a network 104. It may be understood that the system 101 may be accessed by multiple stakeholders/ users in the organization using one or more devices 103-1, 103-2, 103-3..., 103-n collectively referred to as devices 103.
In one embodiment, the network 104 may be a cellular communication network used by devices 103 such as mobile phones, tablets, virtual devices, electronic devices, communication devices, machines, Softwares, automated computer programs, robots or a combination thereof. In one embodiment, the cellular communication network may be the Internet.
In one embodiment, the devices 103 may support communication over one or more types of networks in accordance with the described embodiments. For example, some devices and networks may support communications over a Wide Area Network (WAN), the Internet, a telephone network (e.g., analog, digital, POTS, PSTN, ISDN, xDSL), a mobile telephone network (e.g., CDMA, GSM, NDAC, TDMA, E-TDMA, NAMPS, WCDMA, CDMA-2000, UMTS, 3G, 4G), a radio network, a television network, a cable network, an optical network (e.g., PON), a satellite network (e.g., VSAT), a packet-switched network, a circuit-switched network, a public network, a private network, and/or other wired or wireless communications network configured to carry data. The aforementioned devices 103 and network 104 may support wireless local area network (WLAN) and/or wireless metropolitan area network (WMAN) data communications functionality in accordance with Institute of Electrical and Electronics Engineers (IEEE) standards, protocols, and variants such as IEEE 802.11 (“WiFi”), IEEE 802.16 (“WiMAX”), IEEE 802.20x (“Mobile-Fi”), and others.
In one embodiment, in order to identify a set of skills for a job role associate with a new project corresponding to the organization, the system 101 may receive one or more documents corresponding to the new project from a user device 103. These one or more documents may include project description/RFP documents. Further, the system may be configured to processing the one or more documents to generate a set of document vectors. The one or more documents are processed using a trained doc2vec module.
Further, the system 101 may identify a subset of projects, from the set of projects, which are similar to the new project based on the set of document vectors. The set of projects may be maintained at the project database 102.
Once the subset of projects is identified, the system 101 is configured to identify a set of team members, associated with the subset of projects, based on the job role associated with the new project.
Further, the system 101 is configured to process one or more text documents associated with the subset of projects to determine project documentation corresponding to each team member, from the set of team members. The project documentation gives insight on what activities each team member has performed in the project.
Further, the system 101 is configured to analyse the project documentation, corresponding to each team member, using LDA (Latent Dirichlet Allocation) techniques, to identify a set of phases associated with the subset of projects. Further, the set of phases are processed by the system 101 to generate a list of skills.
Furthermore, the system 101 is configured for refining a job description document associated with the job role based on the list of skills, wherein the job description document is refined by including one or more skills, from the list of skills. The steps of refining the job description document using Artificial Intelligence is further elaborated with reference to the block diagram in Figure 2.
Referring now to Figure 2, various components of the system 101 are illustrated, in accordance with an embodiment of the present subject matter. As shown, the system 101 may include at least one processor 201 and a memory 203. The memory comprises a set of modules. The set of modules may include a Skill set identification module 204, a Critical aspect identification module 205, and a Recruitment Assistance module 206. In one embodiment, the at least one processor 201 is configured to fetch and execute computer-readable instructions, stored in the memory 203, corresponding to each module.
In one embodiment, the memory 203 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and/or non-volatile memory, such as read-only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and memory cards.
In one embodiment, the programmed instructions may include routines, programs, objects, components, data structures, etc., which perform particular tasks, functions, or implement particular abstract data types. The data 207 may comprise a data repository 208, and other data 209. The other data 209 amongst other things, serves as a repository for storing data processed, received, and generated by one or more components and programmed instructions. The working of the system 101 will now be described in detail referring to Figures 2.
In one embodiment, the processor 201 may be configured for executing programmed instructions corresponding to the Skill set identification module 204 for identify a set of skills for the job role associate with the new project corresponding to the organization. The Skillset identification module 204 is an Artificial Intelligence based module which can identify a set of skills based on a set of projects stored in the projects database 102. For this purpose, the Skillset identification module 204 is configured to receive one or more documents corresponding to the new project. Further, the Skillset identification module 204 is configured to process the one or more documents to generate a set of document vectors, wherein the one or more documents are processed using a trained doc2vec module. For every project at the organization, the project description/RFP documents are utilized to create the set of document vectors. This can be achieved by training the doc2vec module. The Doc2Vec module is configured to compute a feature vector for every project document in the organisation. Doc2Vec modules learning strategy is based on the principal that the prediction of neighbouring words for a given word strongly relies on the document also and efficiently captures context at a document level. This results in generation of vector for each document which can be used for comparison in the next step.
In the next step, the Skillset identification module 204 is configured to identify a subset of projects, from the set of projects, which are similar to the new project based on the set of document vectors. For this purpose, the embeddings are compared by cosine similarity module. All the projects where similarity is greater than threshold are considered. Cosine similarity is defined as follows:
……. Equation (1)
In the above equation (1), ‘A’ represents a doc2vec vector of historical project and ‘B’ represents a doc2Vec vector of current project.
In the next step, the Skillset identification module 204 is configured to identify a set of team members, associated with the subset of projects, based on the job role associated with the new project.
Further, the Skillset identification module 204 is configured to process one or more text documents associated with the subset of projects to determine project documentation corresponding to each team member, from the set of team members associated with the subset of projects.
Further, the Skillset identification module 204 is configured to analyse the project documentation, corresponding to each team member, using LDA (Latent Dirichlet Allocation) techniques, to identify a set of phases associated with the subset of projects, wherein the set of phases are processed to generate a list of skills. For this purpose, all the technologies/frameworks mentioned in the project documentation are identified by an Entity recognition (NER) module. LDA is a technique to extract the hidden topics from large volumes of text. This technique identifies the similar topics from the large documentation and groups (clusters) them together. These clusters as they correspond to the phases associated with each project. NER is a technique of identifying and categorizing key information (entities) in text. The skills from grouped cluster can be identified by NER. Thus, all the technologies/frameworks may be an exhaustive list of skills that can be suggested. Further, the Skillset identification module 204 may refine a job description document associated with the job role based on the list of skills. The job description document is refined by including one or more skills, from the list of skills. The Skillset identification module 204 may also suggest one or more changes in the job description document for incorporating the appropriate skillset in the job description document.
For example, in case the new project is related to chatbot implementation. The Skillset identification module 204 may be configured to match the project description with similar chatbot project implementations that are achieved internally/externally in the organization. If the job role is associated with a Machine learning (ML) engineer, then all the ML engineers from the subset of projects are considered.
The project documentation done by these ML engineers is extracted. These documentations are modelled by LDA to identify different phases in the subset of projects. The different phases may correspond to Data generation phase, Intent modelling phase, Dialogue modelling phase, and the like. This classification helps the Skillset identification module 204 to pick up different phases that the ML engineer must play in a chatbot implementation. Finally, a list of skills is generated by the Skillset identification module 204 based on the different phases that the ML engineer must play in a chatbot implementation. This list of skills may be used by the Skillset identification module 204 to refine the job description document corresponding to a job role of an ML Engineer for the new project of chatbot.
In another embodiment, the system 101 may enable a critical aspect identification module 205 to identify critical aspect of the new project to assist the recruiter in analysing the shortlisted candidate. The system 101 is configured to model a critical aspect identification module 205, based on the subset of projects and set of phases identified by the Skillset identification module 204. Further, the critical aspect identification module 205 may be trained by utilizing JIRA tracker of the subset of projects. JIRA is a software used for project management. The JIRA dashboard consists of many useful functions and features such as bug tracking, issue tracking, and project management which makes handling of issues easy. Analysing these aspects for historical projects gives as keen insights about what might important skill for the current project. Each task in JIRA tracker is analysed based on a set of parameters including Number of Bugs raised, Number of sub tasks created, Number of people in task implementations, and Issue resolving time for training the critical aspect identification module 205. Tasks that are greater than the mean of these attributes are now taken forward to next step.
The task description data in JIRA is now compared to phases identified to identify the phase to which the task belongs to, by using cosine similarity. Furthermore, the critical aspect identification module 205 is configured to count the tasks in each of the phases. Further, the critical aspect identification module 205 is configured to identify a phase with highest number of tasks as the critical phase of the new project.
In the above example, if Data generation has 2 critical tasks, Intent modelling has 4 critical tasks, and Dialogue modelling has 7 critical tasks, in this case Dialogue modelling is identified as the critical phase for chatbot implementations. Furthermore, the bugs/ issues may be hand overed to technical recruiter to formulate questions for this critical phase.
In one embodiment, the system 101 is further configured to enable Recruitment assistance module 206 for identify a target SPOC/ stakeholder for candidate search. For this purpose, Recruitment assistance module 206 may be configured to model each recruitment team member from the recruitment team with a set of attributes. The set of attributes may include years of experience in recruitment, connects on Social platform, skills of the person, number of resumes gathered for job skill, BU level. Further, the Recruitment assistance module 206 is configured to analyse the set of attributes corresponding to each recruitment team member to identify the target stakeholder from the recruitment team.
Now referring to Figure 3, a method 300 for refining the job description document using artificial intelligence is illustrated, in accordance with an embodiment of the present subject matter.
At step 301, the processor 201 may be configured to identify a set of skills for a job role associate with a new project corresponding to the organization. For this purpose, the processor 201 may receive one or more documents corresponding to the new project from a user device 103. These one or more documents may include project description/RFP documents.
At step 302, the processor 201 may be configured to process the one or more documents to generate a set of document vectors. The one or more documents are processed using a trained doc2vec module.
At step 303, the processor 201 may be configured to identify a subset of projects, from the set of projects, which are similar to the new project based on the set of document vectors. The set of projects may be maintained at the project database 102.
At step 304, the processor 201 may be configured to identify a set of team members, associated with the subset of projects, based on the job role associated with the new project.
At step 305, the processor 201 may be configured to process one or more text documents associated with the subset of projects to determine project documentation corresponding to each team member, from the set of team members. The project documentation gives insight on what activities each team member has performed in the project.
At step 306, the processor 201 may be configured to analyse the project documentation, corresponding to each team member, using LDA (latent Dirichlet allocation) techniques, to identify a set of phases associated with the subset of projects. The set of phases are processed by the processor 201 to generate a list of skills.
At step 307, the processor 201 may be configured to refine the job description document associated with the job role based on the list of skills, wherein the job description document is refined by including one or more skills, from the list of skills.
At step 308, the processor 201 may be configured to identifying critical aspects of the new projects for assisting the recruitment team in analysing shortlisted candidates.
At step 309, the processor 201 may be configured to identifying a target stakeholder from a recruitment team, for handle a recruitment process for the job role associate with the new project.
Referring now to figure 4a and 4b a template of the job description document before and after refining by the system 101, is illustrated in accordance with an embodiment of the system 101.
In one example, the Skillset identification module 204 in the system 101 may be configured for receiving one or more documents corresponding to a new chatbot project implementation and a job role (ML engineer) corresponding to the new chatbot project. These documents may comprise SRS/ project description/RFP documents corresponding to the new chatbot project. These documents specify details about the new chatbot project including which platform is to be used for developing the project, what are the security norms to be followed, what are the database requirements of the projects, and the like. All these requirements are in descriptive language in a text format. For example, the documents may specify that the chatbot project to be developed should operate on a cloud platform (ex: azure, then JD contains the term Azure expertise in technical skills) as one of the requirements. Thus, to extract the requirements of the client in the chatbot project, the one or more documents are processed using the trained doc2vec module to generate a set of document vectors. Based on the analysis of the one or more documents, the trained doc2vec module may identify the following document vectors for the chatbot implementation:
1. Chatbot for processing Insurance claims
2.Chatbot for Financial Advice
3.Chatbot for automated Medical diagnosis
4. Chatbot for generating Leads
Once the set of document vectors corresponding to the new chatbot project are identified, in the next step, the Skillset identification module 204 may identify historical chatbot projects from a set of projects associated with the organization, based on the set of document vectors. For identifying the similar chatbot projects, all the doc2vec vector of historical projects associated with the organization are compared with doc2Vec vector of new chatbot project. Based on the comparison, the subset of projects having maximum similarity with the chatbot project are identified.
If the job role corresponding to the chatbot implementation is associated with a Machine learning (ML) engineer, then all the ML engineers from the subset of projects are identified by the Skillset identification module 204. In the current example, 5 ML engineers may be identified by the Skillset identification module 204 that are associated with the identified subset of projects.
The project documentation done by these 5 ML engineers is extracted. These project documentations may be in text format. These documentations are modelled by LDA to identify different phases in the subset of projects. The different phases may correspond be:
1. Data generation phase (Low priority)
2. Intent modelling phase (Low priority)
3. Dialogue modelling phase (High priority)
This classification helps the Skillset identification module 204 to pick up different phases that the ML engineer must play in a chatbot project implemented internally/ externally in the organization. Finally, a list of skills is generated by the Skillset identification module 204 based on the different phases that the ML engineer must play in a chatbot project implementation of historical chatbot projects. Exemplary list of skills generated by the Skillset identification module 204 is listed as below:
1. Natural Language Processing
2. Sequence Modelling
3. Python
In this example, once the above list of skills is identified, the skillset identification module 204 may be configured to receive a job description document 400a, from the Recruitment team as represented in figure 4a. The job description document 400a may comprise various fields including Project name, Job Role, Skill set, Other Skills, etc. as represent in figure 4a. The Skill set may comprise one or more skills that are desired in a candidate for the job role.
Further, the skillset identification module 204 may refine the job description document 400a to remove some of the skills that are not desired for the project and add some skills from the list of skills that are highly desired by the job role based on the different phases that the ML engineer must play in a chatbot project implementation. The refined job description document may be as represented in figure 4b. It may be observed that in this example, the skillset identification module 204 has added some of the skills (Azure analytics) in the job description document and removed some of the skills (Hadoop) from the job description document 400a. At the same time, some of the skills (5. Data generation, Intent modelling, Dialogue modelling) from the job description document may be modified. The refined job description document is represent in figure 4b.
Although implementations for the system 101 and the method 300 for job description document using Artificial Intelligence, have been described in language specific to structural features and methods, it must be understood that the claims are not limited to the specific features or methods described. Rather, the specific features and methods are disclosed as examples of implementations for the system 101 and the method 300 for job description document using Artificial Intelligence.