Release Notes - PoolParty 2022 R2 (9.1.0)

This release introduces the new PoolParty Semantic Recommender as a beta feature.

The PoolParty Semantic Recommender is a knowledge-based middleware recommendation solution. The structured data it uses is a knowledge graph (KG) with highly expressive taxonomic and ontological information to leverage the knowledge for high quality recommendations. One major advantage of our semantic recommendation approach is that the results are clear, traceable and transparent. It is possible to follow the reasoning path from input to result.

The information space for the PoolParty Recommender is any corpus of documents of a domain represented in the knowledge graph and can therefore be analyzed by the PoolParty Extractor to identify knowledge graph entities. In contrast to content-based recommenders, PoolParty represents textual content as a graph structure based on extracted information and thereby directly integrates it into the knowledge graph.

The PoolParty approach to recommenders provides high recall as it is able to retrieve results not obviously related to the input, rather via ontology-based classifications and relations in the knowledge graph. It also maintains high precision due to the knowledge graph including explicitly defined facts and being based on a knowledge graph representing a curated domain model. With the adaptable architecture of the PoolParty Semantic Recommender solution it will be possible to link knowledge graph entities to statistical AI implementations (ML, LLMs, …) in the architecture thereby synergistically combining their functionalities.

If you would like to see the new recommender feature in action then simply reach out to us at any time.

This release also introduces the new PoolParty Recommender Workbench providing configuration capabilities for the PoolParty Recommender. The PoolParty Recommender Workbench supports subject-matter experts in finding the optimal combination of parameters for the semantic recommender system. Entire configurations or just parts of the recommendation query can be saved, tested and validated as well as exported for both use in another Recommender Workbench instance and as cURL requests.

We are pleased to announce an upcoming release of the new PoolParty Application Development Framework (ADF) coming along with a set of APIs facilitating building semantic AI applications layered over PoolParty. This Framework will also offer a user interface where you can configure and run simple semantic search as well as recommender applications. The planned release date is November 2023.