Job Parsing

Parse job descriptions and vacancies with a few lines of code.

Depending on their origin, jobs come in various structured formats. Therefore, a standardization step is necessary to unify your talent data channels.

By using Text Parsing, this article shows the different steps to design, enrich and standardize all your job offers into job objects. These objects work well with all HrFlow.ai layers (e.g., Searching, Scoring, Embedding, etc.).

Moreover, through a dashboard, you can track your recruiting strategy in real-time and more efficiently.

📘

Prerequisites

  1. ✨ Create a Workspace
  2. 🔑 Get your API Key
  3. 🧠 Activate Text Parsing API
  4. 🔌 Create a Board
  5. Download HrFlow.ai's Postman

📘

API Endpoint

Get more information about the endpoint 🧠 Parse a raw Text.

Step 1: Configure your Postman Environment

Following the steps from the HrFlow.ai Postman publication will make you land on this page:

2880

First, click on the "Environments" tab on the left side of your Postman window. Then, fill in the Empty - Environment template with the correct values. The compulsory variables for Job Parsing are:

Finally, save the environment and ensure that you selected Empty - Environment as your current environment.

1920

Step 2: Prepare your Job's Text for Text Parsing API

Starting with a Job Object (or any structured Job format), building a text similar to the original text of the Job is necessary before calling the Text Parsing endpoint. This task can be done by:

  • merging description and their title with a single line jump
  • joining sections with double line jumps

Here is an example with the Text Parsing results:

{
  "name": "Data Scientist",
  "url": "",
  "summary": "Under general direction or assignment, develops high quality prediction systems integrated into existing systems and applications. Works collaboratively with a team utilizing industry knowledge, technology, data and statistical modeling to support fast-paced business decisions leading to improved outcomes. Responsible for applying data mining techniques, statistical analysis of performance metrics, applying various machine-learning tools, predictive modeling, and experimental design. Must be able to work independently on development and selection of machine learning techniques and algorithms.",
  "location": {"text": null},
  "archive": null,
  "archived_at": null,
  "updated_at": "2021-12-27T15:16:05+0000",
  "created_at": "2020-12-24T09:32:11+0000",
  "sections": [
    {
      "description": "Master's Degree in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field and\nExcellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Random Forests, etc.\nProficiency in common data science toolkits, such as R, Python, and Julia\nProficiency in data visualization tools\nProficiency in simulation software such as Simio or Arena\nProficiency in using query languages such as SQL\nGood applied statistics skills, such as distributions, statistical testing, regression, etc.\nGood scripting and programming skills",
      "name": "Minimum Required",
      "title": "Minimum Required"
    },
    {
      "description": "PhD in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field\nClinical Training or Experience\nLean & Six Sigma Training or Experience\nProject Management Training or Experience\nExperience in a Start-Up or Small Business Environment",
      "name": "Preferred",
      "title": "Preferred"
    }
  ],
  "skills": [],
  "languages": [],
  "certifications": [],
  "courses": [],
  "tasks": [],
  "tags": [],
  "metadatas": [],
  "ranges_float": [],
  "ranges_date": []
}
Data Scientist

Under general direction or assignment, develops high quality prediction systems integrated into existing systems and applications. Works collaboratively with a team utilizing industry knowledge, technology, data and statistical modeling to support fast-paced business decisions leading to improved outcomes. Responsible for applying data mining techniques, statistical analysis of performance metrics, applying various machine-learning tools, predictive modeling, and experimental design. Must be able to work independently on development and selection of machine learning techniques and algorithms.

Minimum Required
Master's Degree in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field and
Excellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Random Forests, etc.
Proficiency in common data science toolkits, such as R, Python, and Julia
Proficiency in data visualization tools
Proficiency in simulation software such as Simio or Arena
Proficiency in using query languages such as SQL
Good applied statistics skills, such as distributions, statistical testing, regression, etc.
Good scripting and programming skills

Preferred
PhD in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field
Clinical Training or Experience
Lean & Six Sigma Training or Experience
Project Management Training or Experience
Experience in a Start-Up or Small Business Environment
{
  "code": 200,
  "message": "Text parsing results",
  "data": {
    "ents": [
      {
        "end": 14,
        "label": "job_title",
        "start": 0
      },
      {
        "end": 846,
        "label": "skill_hard",
        "start": 842
      },
      {
        "end": 859,
        "label": "skill_hard",
        "start": 848
      },
      {
        "end": 864,
        "label": "skill_hard",
        "start": 861
      },
      {
        "end": 880,
        "label": "skill_hard",
        "start": 866
      },
      {
        "end": 941,
        "label": "skill_hard",
        "start": 940
      },
      {
        "end": 949,
        "label": "skill_hard",
        "start": 943
      },
      {
        "end": 960,
        "label": "skill_hard",
        "start": 955
      },
      {
        "end": 1049,
        "label": "skill_hard",
        "start": 1044
      },
      {
        "end": 1058,
        "label": "skill_hard",
        "start": 1053
      },
      {
        "end": 1107,
        "label": "skill_hard",
        "start": 1104
      },
      {
        "end": 1273,
        "label": "education_title",
        "start": 1250
      },
      {
        "end": 1434,
        "label": "education_title",
        "start": 1395
      },
      {
        "end": 1531,
        "label": "skill_hard",
        "start": 1505
      }
    ],
    "parsing": {
      "certifications": [],
      "companies": [],
      "courses": [],
      "dates": [],
      "durations": [],
      "education_titles": [
        "PhD in Computer Science",
        "Lean & Six Sigma Training or Experience"
      ],
      "emails": [],
      "first_names": [],
      "interests": [],
      "job_titles": [
        "Data Scientist"
      ],
      "languages": [],
      "last_names": [],
      "locations": [],
      "phones": [],
      "schools": [],
      "skills_hard": [        
        "k-NN",
        "Naive Bayes",
        "SVM",
        "Random Forests",
        "R",
        "Python",
        "Julia",
        "Simio",
        "Arena",
        "SQL",
        "Small Business Environment"
      ],
      "skills_soft": [],
      "tasks": []    
    },
    "text": "Data Scientist\n\nUnder general direction or assignment, develops high quality prediction systems integrated into existing systems and applications. Works collaboratively with a team utilizing industry knowledge, technology, data and statistical modeling to support fast-paced business decisions leading to improved outcomes. Responsible for applying data mining techniques, statistical analysis of performance metrics, applying various machine-learning tools, predictive modeling, and experimental design. Must be able to work independently on development and selection of machine learning techniques and algorithms.\n\nMinimum Required\nMaster's Degree in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field and\nExcellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Random Forests, etc.\nProficiency in common data science toolkits, such as R, Python, and Julia\nProficiency in data visualization tools\nProficiency in simulation software such as Simio or Arena\nProficiency in using query languages such as SQL\nGood applied statistics skills, such as distributions, statistical testing, regression, etc.\nGood scripting and programming skills\n\nPreferred\nPhD in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field\nClinical Training or Experience\nLean & Six Sigma Training or Experience\nProject Management Training or Experience\nExperience in a Start-Up or Small Business Environment"
  }
}

📘

Text Parsing API

You can refer to Text Parsing to get more details about the Text Parsing API.

Step 3: Build your New Job Object

Using the results of the Parsing, we can enrich the initial Job Object by accumulating:

  • skills: append all entities of type HardSkill and SoftSkill
  • languages: append all entities of type Language
  • certifications: append all entities of type Certification
  • courses: append all entities of type Course
  • tasks: append all entities of type Task
{
  "created_at": "2020-12-24T09:32:11",
  "languages": [],
  "location": {"text": null},
  "metadatas": [],
  "name": "Data Scientist",
  "ranges_date": [],
  "ranges_float": [],
  "reference": null,
  "sections": [
    {
      "description": "Master's Degree in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field and\nExcellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Random Forests, etc.\nProficiency in common data science toolkits, such as R, Python, and Julia\nProficiency in data visualization tools\nProficiency in simulation software such as Simio or Arena\nProficiency in using query languages such as SQL\nGood applied statistics skills, such as distributions, statistical testing, regression, etc.\nGood scripting and programming skills",
      "name": "Minimum Required",
      "title": "Minimum Required"
    },
    {
      "description": "PhD in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field\nClinical Training or Experience\nLean & Six Sigma Training or Experience\nProject Management Training or Experience\nExperience in a Start-Up or Small Business Environment",
      "name": "Preferred",
      "title": "Preferred"
    }
  ],
  "skills": [],
  "summary": "Under general direction or assignment, develops high quality prediction systems integrated into existing systems and applications. Works collaboratively with a team utilizing industry knowledge, technology, data and statistical modeling to support fast-paced business decisions leading to improved outcomes. Responsible for applying data mining techniques, statistical analysis of performance metrics, applying various machine-learning tools, predictive modeling, and experimental design. Must be able to work independently on development and selection of machine learning techniques and algorithms.",
  "tags": [],
  "url": ""
}
{
  "code": 200,
  "message": "Text parsing results",
  "data": {
    "ents": [
      {
        "end": 14,
        "label": "job_title",
        "start": 0
      },
      {
        "end": 846,
        "label": "skill_hard",
        "start": 842
      },
      {
        "end": 859,
        "label": "skill_hard",
        "start": 848
      },
      {
        "end": 864,
        "label": "skill_hard",
        "start": 861
      },
      {
        "end": 880,
        "label": "skill_hard",
        "start": 866
      },
      {
        "end": 941,
        "label": "skill_hard",
        "start": 940
      },
      {
        "end": 949,
        "label": "skill_hard",
        "start": 943
      },
      {
        "end": 960,
        "label": "skill_hard",
        "start": 955
      },
      {
        "end": 1049,
        "label": "skill_hard",
        "start": 1044
      },
      {
        "end": 1058,
        "label": "skill_hard",
        "start": 1053
      },
      {
        "end": 1107,
        "label": "skill_hard",
        "start": 1104
      },
      {
        "end": 1273,
        "label": "education_title",
        "start": 1250
      },
      {
        "end": 1434,
        "label": "education_title",
        "start": 1395
      },
      {
        "end": 1531,
        "label": "skill_hard",
        "start": 1505
      }
    ],
    "parsing": {
      "certifications": [],
      "companies": [],
      "courses": [],
      "dates": [],
      "durations": [],
      "education_titles": [
        "PhD in Computer Science",
        "Lean & Six Sigma Training or Experience"
      ],
      "emails": [],
      "first_names": [],
      "interests": [],
      "job_titles": [
        "Data Scientist"
      ],
      "languages": [],
      "last_names": [],
      "locations": [],
      "phones": [],
      "schools": [],
      "skills_hard": [        
        "k-NN",
        "Naive Bayes",
        "SVM",
        "Random Forests",
        "R",
        "Python",
        "Julia",
        "Simio",
        "Arena",
        "SQL",
        "Small Business Environment"
      ],
      "skills_soft": [],
      "tasks": []    
    },
    "text": "Data Scientist\n\nUnder general direction or assignment, develops high quality prediction systems integrated into existing systems and applications. Works collaboratively with a team utilizing industry knowledge, technology, data and statistical modeling to support fast-paced business decisions leading to improved outcomes. Responsible for applying data mining techniques, statistical analysis of performance metrics, applying various machine-learning tools, predictive modeling, and experimental design. Must be able to work independently on development and selection of machine learning techniques and algorithms.\n\nMinimum Required\nMaster's Degree in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field and\nExcellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Random Forests, etc.\nProficiency in common data science toolkits, such as R, Python, and Julia\nProficiency in data visualization tools\nProficiency in simulation software such as Simio or Arena\nProficiency in using query languages such as SQL\nGood applied statistics skills, such as distributions, statistical testing, regression, etc.\nGood scripting and programming skills\n\nPreferred\nPhD in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field\nClinical Training or Experience\nLean & Six Sigma Training or Experience\nProject Management Training or Experience\nExperience in a Start-Up or Small Business Environment"
  }
}
{
  "name": "Data Scientist",
  "url": "",
  "summary": "Under general direction or assignment, develops high quality prediction systems integrated into existing systems and applications. Works collaboratively with a team utilizing industry knowledge, technology, data and statistical modeling to support fast-paced business decisions leading to improved outcomes. Responsible for applying data mining techniques, statistical analysis of performance metrics, applying various machine-learning tools, predictive modeling, and experimental design. Must be able to work independently on development and selection of machine learning techniques and algorithms.",
  "location": {"text": null},
  "archive": null,
  "archived_at": null,
  "updated_at": "2021-12-27T15:16:05+0000",
  "created_at": "2020-12-24T09:32:11+0000",
  "sections": [
    {
      "description": "Master's Degree in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field and\nExcellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Random Forests, etc.\nProficiency in common data science toolkits, such as R, Python, and Julia\nProficiency in data visualization tools\nProficiency in simulation software such as Simio or Arena\nProficiency in using query languages such as SQL\nGood applied statistics skills, such as distributions, statistical testing, regression, etc.\nGood scripting and programming skills",
      "name": "Minimum Required",
      "title": "Minimum Required"
    },
    {
      "description": "PhD in Computer Science, Computer Engineering, Industrial and Systems Engineering, Mathematics, or related field\nClinical Training or Experience\nLean & Six Sigma Training or Experience\nProject Management Training or Experience\nExperience in a Start-Up or Small Business Environment",
      "name": "Preferred",
      "title": "Preferred"
    }
  ],
  "skills": [
    {
      "name": "NN",
      "value": null,
      "type": "hard"
    },
    {
      "name": "Naive Bayes",
      "value": null,
      "type": "hard"
    },
    {
      "name": "SVM",
      "value": null,
      "type": "hard"
    },
    {
      "name": "Random Forests",
      "value": null,
      "type": "hard"
    },
    {
      "name": "Python",
      "value": null,
      "type": "hard"
    },
    {
      "name": "Julia",
      "value": null,
      "type": "hard"
    },
    {
      "name": "Simio or Arena",
      "value": null,
      "type": "hard"
    },
    {
      "name": "SQL",
      "value": null,
      "type": "hard"
    }
  ],
  "languages": [],
  "certifications": [],
  "courses": [],
  "tasks": [
    {
      "name": "Responsible for applying data mining techniques",
      "value": null
    },
    {
      "name": "statistical analysis of performance metrics",
      "value": null
    },
    {
      "name": "applying various machine-learning tools",
      "value": null
    },
    {
      "name": "Must be able to work independently on development and selection of machine learning techniques and algorithms",
      "value": null
    }
  ],
  "tags": [],
  "metadatas": [],
  "ranges_float": [],
  "ranges_date": []
}

Step 4: Index your Job

We can now Index the enriched Job Object:

1920

What’s Next