AI, Profiling & Predictive AlgorithmsBased on robust Machine Learning techniques, its Artificial Intelligence Algorithms predict and anticipate users’ needs before they are even expressed.

Predictive Algorithms

Using advanced predictive Machine Learning algorithims, based on complex probabilistic models, Sherpa is able to learn and codify complex functions that allow it to infer and anticipate relevant information at any given time. Having the knowledge of different domains of information allows the identification and exploitation of latent relationships between the various elements present and users, without the need for them to interact with the system.

The AI engine works constantly to analyze all the information and to always have the most relevant available, without the need for search. Our algorithims are able to find patterns that underlie the data and give coherence to the information coming from different domains, which is theoretically unconnected.

The algorithms developed by Sherpa are capable of predicting the future of our users, before they're even aware of it themselves

Ph.D. JOSE ANTONIO LOZANO

Head of AI Research at Sherpa

  • Ph.D. in Computer Science.
  • Degree in mathematics & M.Sc.
  • Degree in Computer Science
  • 100 ISI journal papers published which accounts for more than 8550 citations.
  • Associate editor of top journals as IEEE Transactions on Neural Networks and Learning Systems and IEEE Trans. on Evolutionary Computation.
  • Several best papers awards in international conferences such as World Conference on Computational Intelligence or IEEE Congress on Evolutionary Computation.

AI & Profiling

User profiling

Its personalised predictive capabilities set it apart from market competitors. Sherpa analyses over 100,000 parameters per user per day in order to formulate and continously update individual profiles:

  • Demographics (Business traveler, electronic buyer, golfer, etc)
  • Personal Interests (Fashion, technology, etc)
  • Commuting habits
  • Social media habits
  • Personal Relationships (Family, friends, coworkers, etc)
  • Top Brands
  • Restaurant preferences
  • Sports preferences
  • Among others

NLP and Conversational manager

Unparalleled linguistic intelligence

Sherpa incorporates five levels of linguisticstic analysis to eliminate all possibility of misinformationterpretation- morphology, syntax, semantics, pragmatics and function. Its sophisticated natural language technology mimics human understanding ti dismiss impossible or unlikely matches.

  • MORPHOLOGIC
  • SYNTACTIC
  • SEMANTIC
  • PRAGMATIC
  • FUNCTIONAL

Built-in natural language capabilities

Packed with over 300,000 concepts and 5,000 syntactic and semantic rules, Sherpa's thoroughly tested core system provides the basis for a reliable and comprehensive approachch to human-computer interaction.

The Sherpa dialog manager and Sherpa natural language processing technology together represent an extremely capable and comprehensive approach to human-computer interaction That's Sherpa.

Sherpa’s extensive resources of conceptual and linguistic information and its detailed, five-level approach to linguistic analysis make it a highly accurate and flexible tool for building innovative natural language-based solutions

Ph.D. DEBORAH DAHL

Speech and natural language processing expert.

Co-Principal Investigator on the Defense Advanced Research Projects Agency (DARPA) of the U.S. Department of Defense funded project which integrated Unisys natural language understanding technology with speech recognition.