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:
- extract keywords from the natural language input related to concepts like job title, location, or skills.
- map the extracted keywords to the right fields of the current Search environment.
NOTE: the NLQS LLMs are non-deterministic, so the same input may generate different query results. That is normal/expected behaviour.
Recognized Search 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 configured in the search index.
The following table gives an overview of the Search concepts that are recognized by natural language search:
- AVAILABLE_FROM
- DEGREE_NAME
- EDUCATION_LEVEL
- EMPLOYER
- FULLTEXT
- IT_SKILLS
- JOB_TITLE
- JOB_TITLES
- LANGUAGE_SKILLS
- LAST_ACTIVE
- LAST_JOB_TITLE
- LAST_MODIFIED
- LOCATION
- PROFESSIONAL_SKILLS
- RECENT_JOB_TITLES
- SALARY_RANGE
- SOFT_SKILLS
- WORK_FIELD combined with
- EXPERIENCE_LEVEL_CV
- EXPERIENCE_LEVEL_VAC
- PROFESSION_GROUP