US 11,451,496 B1Granted

Intelligent, personalized, and dynamic chatbot conversation

AssigneeMicrosoft Technology Licensing, LLC

InventorsYi Zhang, Omar Aftab, Eslam Kamal Abdelaal Abdelreheem, Mohammed Mustafa Mohammed Ali Moussa, Senthilkumar Chandramohan, Ahmed Mostafa Othman Abdelmotaleb

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

The disclosed technology is generally directed to chatbot conversation management. In one example of the technology, a generic model associated with a first property associated with a chatbot manager is received. The generic model is generated based on machine learning. A refined model that is associated with the first property is generated based on the generic model and a first plurality of phrases. A first conversation is held between a chatbot and an end user. Upon determining that the value of the first property for the end user is not stored in the database, via the chatbot, during the first conversation, the refined model is used to dynamically ask questions to the end user to determine a value of the first property for the end user. In a second conversation between the chatbot and the end user, the value of the first property for the end user is referenced.

Claims20

Dependent claims

An apparatus, comprising:

at least one memory adapted to store run-time data, and at least one processor that is adapted to execute processor-executable code that, in response to execution, enables the apparatus to perform actions, including:
associating a plurality of properties with a first chatbot manager;
receiving a first generic model that is associated with a first property of the plurality of properties, wherein the first generic model is generated based on machine learning;
receiving a first plurality of phrases that is associated with the first property;
generating a first refined model that is associated with the first property based on the first generic model and the first plurality of phrases;
holding a first conversation between a first chatbot and a first end user;
determining whether a value of the first property for the first end user is stored in a database;
upon determining that the value of the first property for the first end user is not stored in the database, via the first chatbot, during the first conversation, using the first refined model to dynamically ask questions to the first end user to determine a value of the first property for the first end user;
storing the value of the first property for the first end user in the database;
and
in a second conversation between the first chatbot and the first end user, referencing the value of the first property for the first end user.

8 more elements

A processor-readable storage medium, having stored thereon processor-executable code that, upon execution by at least one processor, enables actions, comprising:

storing property names for a plurality of properties with a first chatbot manager;
receiving a first generic model that is associated with a first property of the plurality of properties, wherein the first generic model is created based on machine learning;
receiving a first plurality of phrases that is associated with the first property;
creating a first refined model that is associated with the first property based on the first generic model and the first plurality of phrases;
managing a first conversation between a first chatbot and a first end user;
determining whether a value of the first property for the first end user is stored in a database;
upon determining that the value of the first property for the first end user is not stored in the database, via the first chatbot, during the first conversation, using the first refined model to dynamically question to the first end user to determine a value of the first property for the first end user;
saving the value of the first property for the first end user in the database;
and
in a second conversation between the first chatbot and the first end user, retrieving the value of the first property for the first end user for use in the second conversation.

7 more elements

Dependencies are inferred from the claim text.