Our Blog Inbenta improves the memory and detection of context in the dialogs of its 5th generation Virtual Assistants
Monday, 16 January 2012 09:06
Inbenta improves the memory and detection of context in the dialogs of its 5th generation Virtual Assistants

As part of our never-ending goal to improve user satisfaction, Inbenta has completely redesigned the functionality of cognitive retention, memory and detection of context in interactions between the users and the virtual assistants. This new feature allows our Assistants to be able to remember parts of the conversation had with the user, resulting in more personalized searches and an easier discussion.

The Virtual Assistant of Iberia, the leading company in the airline sector, is able to remember the user's name, giving the consultations a custom-made feel that increases user confidence in the obtained results and, therefore, in the company.

 

 

 

ASSISTANT: Hello, how can I help you?

USER: Hi! My name is Peter.

ASSISTANT: Hi Peter! It's great to talk to you,what can I do for you?

 

Moreover, it has also the memory feature in flight searches in order to optimize interaction with the users. Our Assistant is able to remember the location of the user in such a way that it doesn't keep asking about it every time they search for this type of information.

 

USER: flights to Nice

ASSISTANT: You would like to go to Nice which origin?

USER: from Barcelona

ASSISTANT: You would like to fly from Barcelona to Nice: Offers to fly from Barcelona to Rome

USER: and if I want to travel to London?

ASSISTANT:  You would like to fly from Barcelona to London: Offers to fly from Barcelona to London

 

Notice that our linguistic analysis is able to distinguish the city of Nice from the adjective "nice", thanks to our disambiguation modules that can choose between the most suitable meaning of a polisemous word depending on its context of appearance.