Cloud-based

AI Solutions Suite

Our FalconV™ AI technology setup powers a fully automated, multilingual, end-to-end solutions platform. Its unique ability to deliver the seamless integration of data extraction, curation, analysis and delivery sets it apart from every platform in the marketplace. 

Most solutions still involve a significant amount of human capital, whilst we utilize true AI to deliver unmatched performance and resource efficiency.

EXTRACTION

Web Scraping
  • External & Internal (text) data
  • “Humanized” general spider
  • Automated re-configuration ability
  • Unlimited scalability
  • Historic data retrieval
Blind Vision
  • Proprietary AI (web) text data extraction & labeling technology
  • Technology paradigm shift
  • Superior vs Computer Vision and other technologies
Automated Source Navigator
  • Automated Data Sourcing
  • Smart search & recommendation bots
  • Coming 2021

CURATION

Automated Text Classification
  • IAB Content Taxonomy – 600+ categories
  • 106 languages
Duplicate Detection
  • Automated detection of (near) duplicates
  • Plagiarism notification
  • Depth at 1000 articles
  • Unlimited depth in theory (server capacity)
Related Content Detection
  • Extension of Google BERT & other Transformers
  • Any text input length (!)
  • Multi-lingual & Cross-lingual
  • 2 Science papers
Fake News Detection
  • Conceptual thoughts backed by Data Science
  • New ’secret sauce’
  • Extraction of hidden features in (news) content
  • Coming 2021
Sensitive Information Discovery
  • Search & Locate sensitive information
  • Internal Data at companies
  • External Data on brands
  • Coming 2021

ANALYSIS

Named Entity Recognition
  • Extension of mT5 transformer
  • Multilingual
  • Highest accuracy in the market
  • F1 score at 0.95
  • Foundation to most NLP solutions
Advanced Sentiment Analysis
  • Natural Language Understanding (NLU)
  • Multilingual
  • Human-level sentiment polarity of content
  • Consistency across 100+ languages
  • F1 – 0.9443
Abstractive Text Summarization
  • Natural Language Understanding (NLU)
  • Natural Language Generation (NLG)
  • Multilingual (!)
  • Coming first half of 2021
Smart Keywords
  • Advancement on ‘Graph Models’
  • Smart semantic analysis
  • Location of keywords in text content
  • Human-level editing quality
  • Coming 2021
Anomaly Detection
  • Detect & Highlight anomalies in text
  • Historical timeline analysis
  • Coming 2021
Cross-Correlation
  • Different heterogeneous data sets
  • e.g. Sentiment vs. (share) Price
  • Automated predictive modeling
  • Coming 2021
Automated Poll Generation
  • Natural Language Understanding (NLU)
  • Natural Language Generation (NLG)
  • Original content construction for publishers
  • (Consumer) Engagement Engine
  • Coming H1 2021

DELIVERY

Deliverables
  • API
  • Mobile Apps
  • Webcast
  • Messenger platform
  • Chatbots
  • HIPSTO Knowledge Graph
  • Data Marketplace – ‘Supermarket’
  • Dynamic Information Search

Data Capturing

Knowledge Discovery

Delivery

Blind Vision Technology

We have dubbed our proprietary web text data extraction and labeling technology, Blind Vision. It is now, arguably, the best in class globally and superior to the established and trusted Computer Vision and other technologies.

Test studies* have been conducted versus a US based web data integration platform that uses Computer Vision, and the results are conclusive. They showed a +35% increase in accuracy and -65% lower running costs using Blind Vision technology.  

We like to remain a little secretive about the ‘sauce’, but we can say that Blind Vision combines sophisticated Raw Code Processing algorithms and our own deep learning network architecture. 

* Test results and paper available upon request

Natural Language Understanding

All of our AI microservices have been conceived using current state of the art Transformer models (e.g. BERT, XLM). In most cases, our technology team have built their own proprietary neural network architectures to extend and improve those Transformers. 

NLU is a sub-part of NLP that is considered a ‘hard AI topic’. It is in this arena that the global community of science teams at top universities, big tech (or deep tech) AI entities, like us, are pushing the boundaries to one day achieve general AI or the Human Computer Interaction (HCI).

We have moved into the advanced area of Natural Language Processing (NLP) called Natural Language Understanding (NLU), where our platform has started to actually understand the true meaning of text in a human-like way.

Advanced Sentiment Analysis

Sentiment analysis is a very powerful tool with many commercial applications. However, it is very difficult to do well. Many claim to have a sentiment solution, but upon analysis, few in the market really do. Current solutions suffer from poor consistency, limited accuracy and lack advanced deep learning techniques.

Humans can easily judge the polarity of text, unlike machines. We have developed an apex sentiment tool, using our proprietary neural network architecture, which enables real Natural Language Understanding (NLU) and emulates how humans judge the content and context of text.

Our solution provides consistent sentiment analysis of high or low frequency content, in long or short format, across 106 languages. And, we can do all of this with an impressive F1 score of 0.9443!

* Paper available on request

Named Entity Recognition (NER)

Valuable business information is buried in a largely text-based (79%) data explosion, most of which resides in unstructured data on the web. The ability to extract, organize, analyze and connect large amounts of unstructured text data has become of paramount importance.

Extracting, classifying and connecting entities via Named Entity Recognition (NER) technology plays an important role in sorting unstructured data and identifying valuable information. NER is a key foundational block for any information discovery pipeline, and the basis for most Natural Language Processing (NLP) solutions.

We have built the new industry standard: Multilingual NER (in 100+ languages) that is unrivalled in accuracy vs. current ‘open source’ solutions, and performs with a F1 score of 0.95.

* Paper available on request

REQUEST THE EXTENDED FALCONV PRESENTATION

Q
Q
Q
Q