This discussion has been locked.

You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Intelligent services

Hi all,

I am somehow confused with all these different intelligent services that partially do the same and partially built on top of each other.
So if I understand correctly, Smart Classifier and Smart Metadata are cloud-based services with a essence of knowledge graph and I assume some AI learning capabilities.

On the other side, there is Discovery and Information Extractor (Text Analytics and Matcher). My understanding of Discovery service is that it enforce classification of documents and properties based on configuration and rules and that not really work with concept of suggestions. Also it needs Smart Classifier for categorization (which means 2 licences) and is dependent to cloud service as well.
Information Extractor seems to be the only service which works on-premise without need of cloud services. Is my understanding so far right?

I am wondering if Information Extractor services can be used with documents coming through connectors to suggest users class and properties during promotion process. Could they be configured in a way when people bring documents from "outside" and just drop them to M-Files that these services suggest class and properties for dropped document? Somehow all documentation explains cases that these services run periodically in backend and need their time for processing. It is not clear if they would support such on-demand cases. Of course, if possible, this would help users a lot not to always need to provide all metadata by themselves.

Thanks for thoughts and clarifications.

Dejan

Parents

dejan over 3 years ago

Thanks Joonas!

Intelligence services are at work in the background, for example, when the user drags and drops a new document to M-Files
or modifies a specific property value on the metadata card. In such instances, intelligence services analyze the contents of
new documents and metadata modifications and offer metadata suggestions based on the analyses that they conduct. See
the subsections below for a more specific description of how intelligence services produce metadata suggestions.

I suppose that answers my question if users get a benefit by bringing new documents manually.
Page 29 kind of scratches my other question if intelligent services can be used to automatically promote documents or if promotion needs always to be done manually. I suppose that selection of document class could be a problem. Can you confirm how promotion process would work with intelligent services or if it always need to be done manually by user?

Thanks.

Dejan
Cancel
Vote Up 0 Vote Down

Cancel

Reply

dejan over 3 years ago

Thanks Joonas!

Intelligence services are at work in the background, for example, when the user drags and drops a new document to M-Files
or modifies a specific property value on the metadata card. In such instances, intelligence services analyze the contents of
new documents and metadata modifications and offer metadata suggestions based on the analyses that they conduct. See
the subsections below for a more specific description of how intelligence services produce metadata suggestions.

I suppose that answers my question if users get a benefit by bringing new documents manually.
Page 29 kind of scratches my other question if intelligent services can be used to automatically promote documents or if promotion needs always to be done manually. I suppose that selection of document class could be a problem. Can you confirm how promotion process would work with intelligent services or if it always need to be done manually by user?

Thanks.

Dejan
Cancel
Vote Up 0 Vote Down

Cancel

Children

No Data