Page Comparison

...

1. Parse the inquiry and normalize terms to determine action words, nouns, subjects to understand the user’s intent. Metadata Topic, Subject, Action, and Motivation are identified from the user’s request.

2. Perform an ontology search in Luma Knowledge databases

3. Determine and return the best response

Identifying Matching Artifacts

Luma Knowledge uses the query’s metadata to compare and find the Artifacts with the matching metadata. The system looks for Artifacts with similar Topic, Subject, Action, and Motivation and calculates Relevancy scores for each matching Artifact. The Relevancy score determines how relevant is the Knowledge Artifact to the user’s question. This is a relative score and is calculated based on the best matching Artifact. All the matching Artifacts that various search algorithms to identify relevant artifacts. As an administrator, you can configure how the search is performed for your tenant:

Metadata Search (Dynamic):

The Metadata search in Luma Knowledge uses the ontology to perform the search. This method is also referred as Dynamic Search.
When using Metadata search algorithm, the system generates metadata or ontology from the user phrase, which is then used to compare and find the Artifacts with the matching metadata. The system looks for Artifacts with similar Topic, Subject, Action, and Motivation and calculates Relevancy and Confidence scores for each matching Artifact.

Relevancy Score determines how relevant is the Knowledge Artifact to the user’s question. This is a relative score and is calculated based on the best matching Artifact. All the matching Artifacts that fall in a specific Relevancy score rangeare considered the Best Response or result for the user’s request. The Relevancy score range is derived from the Tenant configuration, Score Range percentage.

For example, If the Score Range percentage for your tenant is set to 60 and the highest Relevancy score of an Artifact for your search is 100, the system calculates the lowest permissible Relevancy score as 60 (that is 60% of 100). This means the artifacts that fall between the range of 90 and 150 are considered relevant and presented as search results.
Increase the percentage to increase the artifacts in the result set.

...

the system calculates the lowest permissible Relevancy score as 60 (that is 60% of 100). This means the artifacts that fall between the range of 90 and 150 are considered relevant and presented as search results.
Increase the percentage to increase the artifacts in the result set.

Confidence Score is calculated based on the matching metadata found in the artifact. It indicates how confident the system is that the Knowledge Artifact answers the user’s query. In Luma Knowledge, each metadata type is assigned a pre-defined confidence weightage. As matching metadata is found, the respective score is awarded to the artifact. More the number of matching metadata, the higher the confidence score. For more information, refer to Calculating Confidence score

Advanced Search:

Advanced Search in Luma Knowledge uses trilateral approach to identify the results for a user query. In addition to the Metadata search, the results are enhanced using the Key phrase search and Full text search.

Key Phrase search in Luma knowledge is based on the KeyBERT algorithm. It is a keyword extraction technique that leverages BERT embeddings to create keywords and key phrases that are most similar to a document. Luma Knowledge uses the keyword extraction technique to match the available Knowledge to the user query. Whenever an Artifact is curated, system automatically generates Keywords for the artifact, based on the Knowledge content. Similarly, Keywords are identified from the user’s search queries. These keywords are matched against the Knowledge Articles and relevant data is identified.

Full-Text Search is ideally the fallback option taken by the system in case either Metadata Search or Key Phrase generate appropriate results. In this case, Luma Knowledge searches for the requested information in complete artifact. Any Artifact with the information similar to user query appear in the search result. This type of search ensures that the Luma Knowledge can find search results even if the Metadata or Keywords are not correctly created. You may update the tenant configuration to filter the results presented in case of Full text search.

Displaying Search Results

Once the Best Response is identified, Artifacts are presented based on the following Tenant level configurations. These configurations determine which Artifacts are presented and how the Artifacts are presented, in a list or a guided conversation. For information, refer to Tenant Configurations.

How to Search for an Artifact

...