We are happy to show you the advantages of our AI chatbots in a short online demo. Just arrange a free consultation here.
Features and functions
A knowledge graph stands for a special kind of knowledge representation. Data/content is modeled in order to describe relationships between individual “entities”, make them machine-readable and to enable answering complex queries.
Data Modeling & Semantics
The knowledge graph stores facts in the form of edges between nodes in a graph/network. In addition, the schema of the data is stored in the graph (e.g. class hierarchies) and semantic models are developed. This ensures machine readability.
Knowledge graphs allow to reduce the complexity of data integration, as new data sources only need to be modeled according to one format and schema. Knowledge graphs are easily extendable and can be linked to other graphs. Therefore, strongly scalable knowledge systems can be created.
Existing knowledge is extended by connecting it with other nodes and new relationships are thus created. For example, Falco was a musician. He lived in Vienna, Vienna is a city in Austria. The question of Austrian musicians must also result in Falco without “Falco lived in Austria” being modeled directly in the background.
The knowledge graph offers multiple benefits for conversation optimization:
Extension of natural language recognition:
The stored knowledge in the knowledge graph – e.g. names, synonyms and entities – is used to improve and extend the natural language understanding of the bot.
Reduction of intents & better management
The management of intents is significantly improved, since knowledge graphs allow to abstract many intents and thereby reduce the number.
Improved answers and dialogues
The use of a knowledge graph and the underlying data modeling make it possible to answer very specific and complex questions.
Calculations directly in chatbot
By modeling the corresponding data in the background, it is possible to perform calculations directly in the chatbot, e.g. prices can be calculated.
Reasoning/generation of new knowledge
Existing knowledge is extended by connecting to other nodes, new relationships are thus created or generated.
Onlim’s Conversational AI platform allows to connect external data sources such as CRM or PIM via standardized interfaces, manage conversations, multilingual content, and conversation modules.