Natural Language Search

Natural language search is meant to help users to create structured queries. To overcome the difficulty of finding the appropriate fields and suitable values for each aspect of a search request, the natural language search feature automates this process. A user can just formulate a request in natural language, and an AI-powered service will then transform it into a suitable query for the given Search environment.

The natural language search feature roughly works in two steps:

1. extract keywords from the natural language input related to concepts like job title, location, or skills.
2. map the extracted keywords to the right fields of the current Search environment.

Recognized Concepts

The configured Concept Tagging of fields is used by the natural language search to map semantic aspects of the natural language query to the respective fields of the configuration. The following table gives an overview of the Search concepts that can get recognized by the natural language search:

• RECENT_JOB_TITLES, LAST_JOB_TITLE, DESIRED_JOB_TITLE, resp. JOB_TITLE
• LOCATION
• IT_SKILLS
• PROFESSIONAL_SKILLS
• SOFT_SKILLS
• LANGUAGE_SKILLS
• WORK_FIELD combined with
  • PROFESSION_GROUP
  • EXPERIENCE_LEVEL_CV, resp. EXPERIENCE_LEVEL_VAC
• EDUCATION_LEVEL
• DEGREE_NAME
• EMPLOYER
• LAST_MODIFIED
• FULLTEXT