Semantic AI Applications
EXPERIENCE END-USER SEMANTIC SOLUTIONS.
Selected Solutions
Knowledge Graph-Infused LLM
Graph RAG Search and Chatbot Solution
A Graph RAG design pattern combines symbolic AI (knowledge graphs) and generative AI (LLM) for better domain fidelity and fewer hallucinations. It uses natural language processing and semantic search to ensure that documents are found based on the user’s intent of the query, as well as generates new content and summaries about this topic while in dialogue with the chatbot.
With our newest application, you can ask the LLM environmental-related questions and it will provide answers, follow-ups, recommended articles, and summaries.
healthdirect Australia
The platform bundles content from over 140 specialized information providers. Users benefit from valuable and quality-assured medical information, which is made accessible through smart semantic search applications. Semantic capabilities such as faceted search and autocompletion enrich the portal with intelligence that enable non-experts to do specialized research.
HR Recommender
Semantic Matchmaking Demo
The HR Recommender is a semantic matchmaking tool based on a knowledge graph. It is designed to connect employees with their coworkers, show them relevant projects, and let them know about interesting career opportunities within their organization.
Education Services Australia
There is a rapidly expanding amount of online teaching materials available to schools. Indeed, teachers are often overwhelmed by the sheer volume of resources. The Schools Online Thesaurus (ScOT) provides a controlled vocabulary of terms used in Australian and New Zealand schools. It encompasses all subject areas as well as terms describing educational and administrative processes. The thesaurus links non-preferred terms to curriculum terms.
The World Bank
The Enterprise Topic Thesaurus is a thesaurus which represents the concepts and terms used to describe the World Bank Group’s topical knowledge domains and areas of expertise. It supports the collaboration process of interdisciplinary teams, where individuals are not acqainted with terminology from other departments.
Geological Survey of Austria
The thesauri displays the knowledge area of geosciences and can be used for free by the respective community. It can be downloaded and used for a variety of applications as semantic search portals and content classification. With the creation of semantic and technically interoperable geodata sets the Geological Survey implements the legal requirements of an EU directive.
Selected Functional Applications
Search and Recommender Demo
PoolParty Meets ChatGPT
ESG Chatbot Solution
While ChatGPT has had a monumental impact on the world of chatbots, it has limitations that can be remedied by a knowledge graph. Using a knowledge graph that models the Environmental – Social – Governance (ESG) domain, PoolParty Meets ChatGPT adds an additional layer to ChatGPT that not only provides more comprehensive answers but also enrichens the answers with sources from the knowledge graph.
Semantic Matchmaker Demo
The Semantic Matchmaker is a semantic matchmaking tool based on a Semantic Data Fabric using PoolParty as the Semantic Middleware and data.world as the Data Catalog. It is designed to simulate the use case of automatically connecting (matching) Consultants (based on their skills and experience) to Projects (based on the project description).
Self-Training & Support Portal
The service welcomes users with a prompt field supporting auto-complete and term concept suggestions while formulating a question. The additional semantic information enables the PoolParty Assistant to either immediately deliver the right answer or to investigate and determine what the user has indeed been looking for.
Entity Recognition Demo
The Entity Recognition Demo is a semantic extraction tool based on a knowledge graph and machine learning algorithms for Named Entity Recognition (NER). It is designed to show the capabilities of the PoolParty Extractor regarding the extraction of concepts, terms, and previously trained named entity recognizers. By also including trained classifiers from the Semantic Classifier this tool also shows how documents can be categorized.
News Classifier Demo
This is a News Classification demo built in Drupal using PoolParty Thesaurus, Extractor and Classifier API methods. Various Machine Learning Classifiers have been trained using the PoolParty Semantic Classifier!
PoolParty GraphViews Demo
PoolParty GraphViews automatically transforms your data into interactive, visual knowledge graphs tailored to the needs of analysts. Quickly discover relationships between entities without having to write complex SPARQL queries or edit data.
Multifaceted HR Knowledge Discovery
Match employee skills with salaries or technology trends in this HR Demo. With PoolParty GraphSearch you can link internal and external data sources in one user-friendly interface for better analytics, search and recommendation capabilities.
Contract Intelligence Demo
PoolParty Sense Extraction makes contract management much easier. Extract information from current and legacy contracts to minimize risk, stay compliant, uncover hidden costs and opportunities and make informed business decisions.
Graph Visualization with PoolParty
Graph visualisation with PoolParty supports knowledge discovery. Learn how you can query a RDF graph interactively, and how this supports your understanding of the subject matter.
Try out the PoolParty Semantic Suite
In the background of each of these applications, PoolParty is the foundation. To create your own cutting-edge solution, you can get started easy with PoolParty. Try it out now with our Semantic AI Starter Kit!