Machine Learning/NLP and algorithm writing for Resume parsing project
- or -
Post a project like this$$$
- Posted:
- Proposals: 1
- Remote
- #1708096
- Expired
Description
Experience Level: Expert
General information for the business: Software development company
Kind of development: New program from scratch
Description of every module: Technologies to be used: Keras, Python, Matlab, Tensorflow, Deepdive
Hi Gurus,
We are looking for an algorithm that will be able to convert CVs from unstructured format (PDF, Word,..etc) to a smart structured database, where the algorithm will consolidate and collect information from these CVs and save them into structured database tables. for example: if I will send my CV, I expect this algorithm to be able to extract the following information from my CV (where exist)
Biography information:
Name, age, email, mobile number, country, nationality,…)
Database - Table Bio
Name | Age | Email | Mobile | Country | Nationality | Martial status
John Steve | 31 | John.Steve@gmail.com | 0599XXXXX| USA| American| Married
Education:
Bachelor degree, Master degree, Ph.D. ….
Database - Table Education
Degree | Major | Year from | Year Until
Bachelor degree | Computer engineering | 2010 | 2015
Master degree | Software engineering | 2015 | 2017
Certificates:
XX, XX2, XX3
Database - Table Certificates
Certificates
MCTIP
ITIL
SOPHOS
Skills & work experience
SQL, Java, Python, web development
The algorithm should connect each skill with the duration of the job it was mentioned under. for example:
if I have worked for Company 1 from April.2015 until Sept.2016 as a software developer, using SQL, Java.
Then I worked for Company 2 from Sept. 2016 until sept.2017 as a Senior software developer using SQL, Java and C#.
The algorithm should collect the following with regards to skills and work experience.
Database - Table Skills
Skills | Years
SQL | 29 months (1 year 5 months in company 1 + 1 year in company 2)
Java | 29 months (1 year 5 months in company 1 + 1 year in company 2)
C# | 12 months ( 1 year in company 2)
Database - Table Experience
Experience | Years
Software developer | 17 months ( 1 year 5 months in company 1)
Senior Software developer | 12 months ( 1 year in company 2)
Training material will be provided for IT industry (around 100,000 CVs) to prove the concept if we succeed to meet at least 95% accuracy using provided algorithm we could start providing material to other industries.
Please note that we need to be able to train this algorithm by ourselves in case of any future possible needs.
Please note that our training CVs are consolidated each 10 CVs in one PDF file. (Linkedin CVs).
Our expected processing speed would be 100 CV/Second
Description of requirements/functionality: API interface should be developed to facilitate communication with this software
Specific technologies required: Keras, Python, Matlab, Tensorflow, Deepdive
Extra notes:
Kind of development: New program from scratch
Description of every module: Technologies to be used: Keras, Python, Matlab, Tensorflow, Deepdive
Hi Gurus,
We are looking for an algorithm that will be able to convert CVs from unstructured format (PDF, Word,..etc) to a smart structured database, where the algorithm will consolidate and collect information from these CVs and save them into structured database tables. for example: if I will send my CV, I expect this algorithm to be able to extract the following information from my CV (where exist)
Biography information:
Name, age, email, mobile number, country, nationality,…)
Database - Table Bio
Name | Age | Email | Mobile | Country | Nationality | Martial status
John Steve | 31 | John.Steve@gmail.com | 0599XXXXX| USA| American| Married
Education:
Bachelor degree, Master degree, Ph.D. ….
Database - Table Education
Degree | Major | Year from | Year Until
Bachelor degree | Computer engineering | 2010 | 2015
Master degree | Software engineering | 2015 | 2017
Certificates:
XX, XX2, XX3
Database - Table Certificates
Certificates
MCTIP
ITIL
SOPHOS
Skills & work experience
SQL, Java, Python, web development
The algorithm should connect each skill with the duration of the job it was mentioned under. for example:
if I have worked for Company 1 from April.2015 until Sept.2016 as a software developer, using SQL, Java.
Then I worked for Company 2 from Sept. 2016 until sept.2017 as a Senior software developer using SQL, Java and C#.
The algorithm should collect the following with regards to skills and work experience.
Database - Table Skills
Skills | Years
SQL | 29 months (1 year 5 months in company 1 + 1 year in company 2)
Java | 29 months (1 year 5 months in company 1 + 1 year in company 2)
C# | 12 months ( 1 year in company 2)
Database - Table Experience
Experience | Years
Software developer | 17 months ( 1 year 5 months in company 1)
Senior Software developer | 12 months ( 1 year in company 2)
Training material will be provided for IT industry (around 100,000 CVs) to prove the concept if we succeed to meet at least 95% accuracy using provided algorithm we could start providing material to other industries.
Please note that we need to be able to train this algorithm by ourselves in case of any future possible needs.
Please note that our training CVs are consolidated each 10 CVs in one PDF file. (Linkedin CVs).
Our expected processing speed would be 100 CV/Second
Description of requirements/functionality: API interface should be developed to facilitate communication with this software
Specific technologies required: Keras, Python, Matlab, Tensorflow, Deepdive
Extra notes:
Yazan I.
0% (0)Projects Completed
-
Freelancers worked with
-
Projects awarded
0%
Last project
6 May 2024
Palestinian Territory, Occupied
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies