We recommend the following practices for maximizing relevancy and empowering self-service:

1. Create descriptive document titles unique to each article. Title matches carry more weight than content matches in the default relevancy ranking model.
2. Clean up HTML heading and paragraph tags for an optimal Q&A experience. Use the

   to

   tags for headings. Split longer paragraphs into shorter, more digestible chunks of information (500 chars or less when possible) with corresponding

   tags.

3. Use the meta field to annotate Knowledge articles with pertinent keywords that may not appear in the title or content. As machine learning–based relevancy collects and learns from user interactions, manual annotation will become less necessary.
4. Take advantage of synonym dictionaries for higher recall. Synonyms expand search queries to include additional terms equivalent in meaning.

Relevancy Ranking

AI Search relies on a variety of content features for relevancy ranking of search result documents. These include:

• Title match — how well the query matches the document’s title
• Content match — how well the query matches the document’s body content
• 'Keyword' match — how well the query matches the document’s tags
• Document freshness — how recently the document was created and/or updated
• Document popularity — how often the document has been viewed

Labels:

• AI Search
• Content Management
• Knowledge Management
• Search