...
Info |
---|
|
...
The status timeline is a visual representation of Sub flows that are triggered as part of the Semantic Analysis of an artifact. The illustration shows the sub-flow in execution, current status, and timestamp when the process is triggered.
...
FAQ Generation is also called Question-Answering Analysis. The process is intended to determine the questions that can be answered by the source document. On 'Status Timeline', Curator can view FAQ Generation process status and start time.
...
Luma Knowledge uses Azure QnA maker to generate these Question answer pairings. Each QnA pair generated through the process becomes a FAQ child Artifacts linked to the artifactParent Knowledge Artifact. In the case of FAQ generation processes encounter an error, the Semantic Analysis process is process fails, and the next steps are not executed. The timeline is updated appropriately to indicate the error.
...
Info |
---|
Luma Knowledge uses QnA maker to generate FAQs, so the process is dependent on the product limitations. The process fails in case, Source document : is not inFor successful QnA pair generation, the source document:
|
Metadata Generation
...
|
Ontology Generation
Ontology generation is intended to extract metadata from the document. Metadata represents key information (terms or phrases) that describes the artifact. It enhances searches for artifacts and assists the curation process by identifying known terms. NLP engine parses the document and identifies metadata elements for the Artifact and QnA pairs, using parts of speech and dependency rules. The identified meta-data is then normalized and can be used as search metadata for the artifact.
Info |
---|
Artifact Name and Summary are used to generate Ontology for the Artifact. |
Below are the metadata elements that are identified for each artifact:
...
On 'Status Timeline', Curator can view the Ontology Generation process status and start time.
...
Info |
---|
If the identified Topics are not present in the Knowledge Graph, thosethe Artifact is directly linked to the Domain selected at Artifact creation. The identified topics are added asto ' Identified termsSuggested Metadata'. |
Persistence
The last step in the Semantic Analysis process is Persistence. In this step, all the information identified and created in the earlier steps is saved into Luma Knowledge databases. Luma Knowledge uses three databases to save and maintain information in the system:
...
Once the FAQ and metadata are generated, the information is pushed to databases. On 'Status Timeline', Curator can view the Persistence process status and start time.
...