Suggestions

This page describes the Suggestions capability.

Suggestions

Notice the "Suggestions" Section in the Right Sidebar.

Every time a Topic appears in the Advisor Workspace, Crystal proposes a set of dynamic suggestions: suggestions of Topics that are related to the one you just asked and change based on your questions.

Suggestions serve as a guide for you to continue data exploration, allowing you to pose new questions and uncover fresh insights.

If you are new on Crystal, Suggestions can also inspire you to understand how to formulate effective questions for the Advisor, since the Topics inside the cards are expressed in the form of questions.

Explore Suggestions

Exploring Suggestions is easy: simply click on the suggestion of your interest and you will immediately find it open in the Advisor for you to explore.

Each time you ask a question, the suggestions will be refreshed accordingly, based on the Topic asked.

Please Note

Whenever possible, the algorithm will suggest up to six related Topics, where the first four Topics are the most similar ones, whether the last two Topics are the most different ones.

By showing a mix of similar and different Topics, Crystal offers you a balance between informed guidance and out-of-the-box tips that may spark curiosity for alternative data exploration paths.

Remember

The Topics inside the Suggestion tips are only the ones that have been configured by the Admin and that you actually have viewing permissions for.

How Does It Work?

The Suggestions capability employs an algorithm called Recommender System, which is powered by the Business Knowledge Graph, a data model that provides a personalised representation of the data behind your Crystal Project.

Deep Dive on the Business Knowledge Graph

The Business Knowledge Graph (BKG) serves as the foundational knowledge base that Crystal leverages to answer your questions.

It can be envisioned as a network of interconnected information and metadata, built upon the private data linked to Crystal.

For each Crystal Project, the Business Knowledge Graph is unique and isolated, tasked with a very clear objective: to extract from the metadata all the information AI models need to transform information into conversation.

The construction of the BKG begins with Crystal’s configuration, where data sources are selected and Business Entities are defined, along with their semantic properties.

The BKG interprets both the content of the data connected to Crystal and the decisions made during configuration to establish semantic links between elements of the corporate knowledge base.

Through this process, the BKG learns the corporate lexicon, its taxonomy, and specific expressions, achieving a deep understanding of the business.

Additionally, the BKG adapts and evolves based on the questions asked to Crystal, identifying new correlations among data and learning from users, ensuring that the results produced are always accurate, certified, and contextual.

This is one of the core technologies underlying Crystal.

Based on your customized Business Knowledge Graph, the Recommender System analyzes the dataset and selects the Topics that are more relevant to the Topic asked based on their similarity to it, in terms of content.

In particular, the algorithm compares Topics based on their Entities, Objectives, or Data Sources, like this:

1. Entities Matching: first, it searches for Topics containing the same Entities as those in the Advisor’s Topic

2. Objective Alignment: in absence of similar Entities, it looks for Topics with matching Objectives

3. Source Correlation: if no matching Objectives are found, it extends the search to Topics from the same Table or Data Source

Whenever possible, the algorithm will suggest up to six related Topics, where the first four Topics are the most similar ones, whether the last two Topics are the most different ones.

Rules & Limitations

Following, a set of rules and limitations to consider when using the Suggestion capability.

• Suggestions Based on Configured Topics Suggestions only consider Configured Topics, i.e. the ones that have been manually created by the Admin, whereas auto-generated Topics are not included

• Dependency on Focused Topic The activation of the algorithm requires a “Topic in focus”, i.e. a Topic open in Advisor

• Need for a Minimum Number of Topics For the algorithm to suggest six correlated Topics, there must be at least 7 Topics configured and published in Console

• Potential for Random Suggestions When optimal conditions are not met, the algorithm defaults to random suggestions

Remember

Some of the circumstances where the suggestions will be random include:

• when you did not ask a question yet e.g. right after logging into Crystal

  • in this case, you will see six random Suggestions

• on the first usages of the environment, when still not enough Topics are configured

• if you have few viewing permissions

  • in these cases, you may see less then six Suggestions and some of them may be random

Keep exploring your data!

---