An Insight Engine that fuels your compliance wizards, decision support and risk identification with Composite AI
In corporate environments where significant operational and financial risks are at stake, fact validated insights are a must. But pure black box AI algorithms are not trustworthy enough to meet the demanding requirements of software assistants in decision support, risk identification and compliance.
Our latest generation of insight engines is able to discover insights where conventional search engines and recommendation systems reach their limits. Our XAI Insight Engine combines the strengths of symbolic and statistical AI to harness your organization’s content where traceability, factual fidelity and low error rate matter.
Actionable insights for industries where the stakes are high:
- for potentially life-changing decisions in healthcare, where full transparency is required.
- In the highly regulated banking sector, where precise and clear conclusions are required.
- in manufacturing, where deep industry knowledge is required to make sense of manuals, maintenance logs, equipment details, and historical work orders.
Actionable insights along your knowledge lifecycle.
Efficient and productive knowledge acquisition supported by the next generation of search.
Support for content creation with recourse to the company’s own content inventory
Focused and accessible human-machine dialogue in employee and customer interactions.
Effective AI tools help in lifting noble knowledge from large blocks of information.
Decisions based on an accurate and deep understanding of the company’s knowledge base.
In-depth sentiment and context analyses identify risk potentials along the entire value chain.
Composite AI – a unique technology approach
After an initial hype-driven wave of machine learning applications, the second generation of AI has recently shown that techniques from different developments can mesh to the benefit of the user. Building on this, our XAI Insight Engine is based on two proven AI concepts: statistical and symbolic AI.
We combined Squirro’s machine learning with PoolParty’s graph-based metadata, search and text mining offerings to create an Insight Engine that differs significantly from conventional AI approaches in four ways:
Unlocks new application scenarios for AI
Composite insight engines expand the application of AI and its value creation potential by serving projects that were previously considered infeasible because a fully data-driven, purely ML-based approach would have been inefficient, expensive, or inappropriate.
Works already with small amounts of data
Our Insight Engine brings the power of AI to a larger group of companies and businesses that do not have access to large amounts of historical or labelled data but do have extensive human expertise.
Bring the human into the loop
Use of domain knowledge and human expertise to train ML models for a particular context. This can be achieved by applying business rules and knowledge graphs and physical models.
Insights that solve combinatorial problems
Search and recommendation systems that identify multidimensional knowledge objects based on search intent and context.
Our partner, Squirro, was featured as a solution provider in the Gartner report, Critical Capabilities for Insight Engines, 2022. The report also notes how PoolParty can be used for extraction and enrichment of content, further affirming the technical strengths of this joint offer.
Learn more about Explainable Insights
Watch the presentation by Robert David (Poolparty) and Patrice Neff (Squirro) at SEMANTiCS Conference 2022.
Listen to Andreas Blumauer on the Squirro Academy Podcast to talk about redefining AI with knowledge graphs..
Download our Infosheet and get an overview about our unique approach to Composite AI
How Squirro and Poolparty create semantic knowledge objects that power your insight engine
Each piece of content is classified in a first step by Squirros ML according to the user’s intended insights and decomposed into corresponding content blocks. PoolParty’s knowledge graph technology contextualizes this content and links it to other meaningful concepts and data. Finally, the system packages the generated semantic knowledge objects for further use in search, recommendation, and dialogue applications.
By 2024, 70% of organizations relying solely on ML for AI initiatives will spend more money per model than those leveraging composite AI techniques.
Innovation Insight for Composite AI, Hamer, Brethenoux, Ramos, 2022