Sap Portals Israel Limited

Sap Se

Sap Ag

Pablo Roisman

Michael Seubert

Jochen Hirth

Werner Gnan

Thilo Kraehmer

Orit Harel

Robert Getzner

Yuval Morad

Thomas Hammer

Andre Adam

Jochen Wickel

Waldemar Kramer

Eli Pripaz Cohen

Elad Heart

Tanjana Preiser-Funke

Itai Fonio

Volker Vogelmann

Yaron Livneh

Hofit Koren

Michele Kemp

Lars Hoenig

Ari Lulu

Monica Reidl

Claudia Diesner

A service descriptor file is retrieved from a remote database by a server, where the service descriptor file describes a service corresponding to a service-specific chatbot requested by a user. The received service descriptor is parsed to obtain a capability and relevant service data associated with the service. The service-specific chatbot is generated with at least one object that is based on the obtained capability and relevant service data, where the at least one object includes intents, expressions, and skills that correspond to the service. The generated service-specific chatbot is provided to the user through at least one channel to enable an interaction with the service-specific chatbot with a graphical user interface.

Automatic development of a service-specific chatbot

A rule is received at a client application from an input text control. The received rule includes a sequence of characters and is parsed into a plurality of tokens. For each of the tokens, a plurality of behaviors associated with that token are configured to generate a behavior configuration. Each of the generated behavior configurations can be modified by an authorized user. A user interface (UI) control is generated based on the behavior configurations.

Dynamic configurable rule representation

Linguistic expressions for training a chatbot can be generated in an automated system via linguistic expression templates that are associated with intents. The pre-categorized linguistic expressions can then be used for training and validation. Chatbot development can thus be improved by having a large number of expressions for development, leading to a more robust chatbot. In practice, the process can iterate with modifications to the templates until a suitable benchmark is met. The technique can be applied across human languages to generate chatbots conversant in any number of languages and is applicable to a variety of domains.

Automated chatbot linguistic expression generation

A business object model, which reflects data that is used during a given business transaction, is utilized to generate interfaces. This business object model facilitates commercial transactions by providing consistent interfaces that are suitable for use across industries, across businesses, and across different departments within a business during a business transaction. In some operations, software creates, updates, or otherwise processes information related to a business document message monitoring view, a customs arrangement, and/or a freight list business object.

Managing consistent interfaces for business document message monitoring view, customs arrangement, and freight list business objects across heterogeneous systems

Growing community of inventors

Hod Hasharon, Israel

Pablo Roisman