The anatomy of the Octopus




how it works
how it works

On your behalf, the Octopus attaches its "tentacles" to your data. It discovers new insights and explanations. It enhances your understanding of the data.

All cognitive tasks executed by the Cognitum Octopus are specified in English, using a 5GL, programming language.




Proven Solutions




Clinical Decision Support System

for Gist Cancer in cooperation with the Maria Sklodowska-Curie Memorial Cancer Center and Institute of Oncology in Warsaw

Evidence-based medicine can be effective only if regularly tested against errors in medical practice. The automation of a decision support system occurs when the computer can make use of patients’ clinical data, follow its algorithm, and present the information relevant to the current clinical situation.

The Clinical Decision Support System application for Gist Cancer is devoted to Gastrointestinal Stromal Tumours (GIST). Oncology is a field where recommendations are well defined and studied and where the quality of the clinical data needs to improve to allow for the more sophisticated analysis of these data.

Cognitum platform was used because on the one hand; it allows the domain expert to model recommendations, thus ensuring a high standard of patient treatment. The deployed expert system allows the expert to directly modify the executable knowledge on the fly, making the overall system cost efficient. On the other hand, the strict formalisation of the domain knowledge produces consistent data that can be later reused for clinical studies (e.g. for clinical trials).

In the GIST-CDSS application, we have modeled the oncological history of a patient and organised it in a complex structure that ensures that all the data entered into the application is stored consistently. Furthermore, we were able, together with the domain expert, to model recommendations for the physician that are reasoned depending on the form and on the patient history. The application is currently being used at the Maria Sklodowska-Curie Memorial Cancer Center and Institute of Oncology in Warsaw.

Fraud Detection System

for a state in Brazil in cooperation with SmartCloud Inc from Boston, US.

Detection of large-scale fraudulent activities requires heavy usage of the online (real-time) data analysis. It requires complicated, and time-consuming investigations and deals with various domains of knowledge like financial, economics, business practices and law. Nevertheless, the real challenge is to build adaptive and self-learning fraud detection system, as it needs special methods of intelligent data analysis to detect and prevent losses.

On the one hand, desired fraud detection system must be able to deal with gargantuan computational complexity. It needs to recognise complex patterns over time periods spanning seconds to months. It also must be easily customizable and readily maintainable by specialists in frequently changing business environment. Ensuring compliance and finding fraud requires monitoring millions of daily transactions in real time and not error-prone invoice data which complicates processing and analysis. On the other hand, auditable proof of non-compliance is critical to tax enforcement and needs to be provided by the system too.

A state in Brazil dealt with revenue loss on VAT estimated at the level of 80M USD per year in retail only. Fraud Detection System created with the use of Cognitum Platform currently reduces lost tax revenues by 40%, and it is still learning. It now meals 2,000,000 transactions per day from 60,000 vendors at a speed of 200,000 rules per second.

The reasoning engine of the Fraud Detection System recognises complex fraud and non-compliance patterns. Natural language rules enable decision makers and specialists to manage and maintain tax fraud knowledge base by themselves, with an only sporadic support of programmers. Situation awareness is provided by operation dashboard that combines data visualisations and reports to give operators and management comprehensive situational awareness of fraud detection analysis and prevention.

Collaborative Ontology Engineering

with Fluent Editor WEB allows creating Machine Executable Knowledge in teams.

Formal knowledge appears naturally in almost every area of endeavour where computers are used intensively, and knowledge management is required. Nowadays we observe the evolution process that brings knowledge from the human-readable form (i.e. archive of documents with searchable information) into the more-and-more computer-readable form that allows for automated deductive reasoning – Ontologies. One can say that Ontologies contain Machine Executable Knowledge - knowledge that can be executed by a machine.

Unfortunately, to understand the ontology one is required to have a background in the field of an artificial intelligence, knowledge representations and knowledge modelling. Moreover, it is also desirable to know supporting tools that intensively use advanced diagramming techniques. While without formal methods it is almost impossible to understand the knowledge immersed in the given ontology, it is still very hard to trace a formal knowledge model for an authority that is not familiar with a particular diagramming language. In consequence, even data-driven, strategic decisions made by the executives not familiar with tools might reveal a lack of crucial information.

Fluent Editor WEB being a critical part of Cognitum Platform allows building complex ontologies collaboratively using Controlled Natural Language - language that anyone that can read this text can use without prior training. Fluent Editor WEB guides the Knowledge Engineer during sentence writing to enter only such a sentences that are grammatical, morphologically and logically valid.