Managing a 21st century workforce requires an enriched talent database that gives a normalized, structured view on the talent.
Data on people and jobs tends to be messy: skills and job titles can be worded in different ways, and information might be locked in different sources and/or formats. Textkernel’s Data Enrichment APIs help you standardize and enrich your job and skill data, making it better suited to your needs around searching, matching and analytics. Along with Textkernel’s other products, this product line can be plugged into your system to help understand, connect and analyze your data.
How can I capture and maintain an up-to-date view of my talent landscape?
How can I make the data actionable to match people and jobs?
How can I expose data to strategize on individual and organizational level?
Textkernel’s taxonomies as the basis for meaningful data
Textkernel’s taxonomies comprise a comprehensive inventory of professions and skills found in job postings and resumes. The professions (over four thousand) and skills (over eleven thousand) are organized hierarchically, and each of them is linked to a number of synonyms, acronyms, and other ways of wording.
The taxonomies are designed to be:
Professions are available in 10 languages, skills in 6.
The taxonomies contain job titles and skills from across the job market.
The taxonomies continuously undergo improvements based on market feedback.
The profession and skills taxonomies are connected to each other through weighted links that represent the degree of association between professions and skills.
Understand job titles by mapping them to professions from the taxonomy, as well as industry standards such as O*NET and ISCO. The input to the Professions API can be a vacancy title, or a user-typed input in the context of autocomplete.
Understand skill data by extracting and standardizing skills from any text with the Skills API, be it cover letters, training descriptions, or performance reviews. The input can also be user-typed input or a skill description.
Understand relations between professions and skills relations between professions and skills
The Ontology API makes it possible to infer relevant skills given a profession, or fitting professions given a skill set. It can also reveal the ‘skill gap’ between any pair of professions.
Data Enrichment APIs: Helping you better understand skills and professions
Textkernel’s profession and skill taxonomies are at the heart of the Data Enrichment APIs. These APIs can be leveraged to Professions API, Skills, Ontology API.
Data standardization for matching
How does the standardization of profession and skill data contribute to matching people and jobs? Let’s look at an example:
On the left we see a situation where matching happens merely on the basis of textual overlap. Because the words do not match exactly, perfectly suitable candidates would be overlooked. If taxonomy-based standardization is added to the process, as on the right, the job titles and skills mentioned in the documents are recognized as identical. Thus, data enrichment helps unlock the potential of your talent data.
Connecting roles to roles
In addition to matching specific profiles and job listings, the Ontology API makes it possible to understand how roles relate to each other in terms of the skills they require. Given a current and subsequent role, it indicates which skills are “transferable”, and which are likely to require upskilling activities.
Reliable analytics also requires standardization of data. To illustrate this, let’s look at a scenario with and without standardization of job titles.
In the scenario on the left, we’re essentially counting words, not jobs. Without accounting for synonyms and variation in wording’, the results of analyses like these are not actionable. The Professions API and Skills API help achieve this: they represent your data in a way that goes beyond words: in terms of the units (professions, skills) that are actually of interest.
The Data Enrichment APIs can help you to:
Extract and normalize skills from any HR-related text to pre-populate skill profiles.
Extract skills from training descriptions, and leverage those for targeted upskilling recommendations.
Improve analytics by standardizing skill and job data to Textkernel's comprehensive, cross-lingual taxonomies.
Import the market’s most comprehensive taxonomies of skills and professions in your organization's tools and processes.
Create smart matching solutions by leveraging Textkernel's extensive knowledge base on synonyms and profession-skill relations.
Automatically enrich job architectures and job catalogues with suggestions of relevant skills.
Generate skill-based recommendations of (non-obvious) job transitions.
Understand the skill gap between two professions, or between a current skill set and an aspired next role.
Explore other solutions
Jobfeed is Textkernel’s Big Data tool for jobs that automatically searches the Internet for new job ads every day. The jobs found are automatically entered in Jobfeed and classified according to criteria such as profession, required qualifications, location and company name.
Need to draw up a rapid shortlist of candidates or employees from your database to fill a job? Want to keep candidates informed of relevant jobs? Match!, semantic job matching, automates and accelerates these processes. This enables you to get the most out of your database or talent pool.
Textkernel Resume Parsing
Get more applicants, save time on manual data entry and easily build a talent pool. Extract!, Textkernel’s CV parsing (resume parsing) software uses advanced Artificial Intelligence and Machine Learning techniques to automatically turn every CV or social media profile into a complete and searchable candidate record.
Search! is Textkernel’s semantic search software that helps you find the right jobs and candidates in your own database and in external sources, effectively and easily.