GENERATING DOMAIN-SPECIFIC MODELS IN NETWORKED SYSTEM

Title:

GENERATING DOMAIN-SPECIFIC MODELS IN NETWORKED SYSTEM

Document Type and Number:

Japanese Patent JP2022121523

Kind Code:

A

Abstract:

To generate a domain-specific model in a networked system.SOLUTION: The present disclosure is directed generally to generating a domain-specific voice-activated system in interconnected networks. The system can receive an input signal detected at a client device. The input signal can be an audio-based input signal, a text-based input signal, an image-based input signal, or any other type of input signal. Based on the input signal, the system can select a domain-specific knowledge graph and can generate a response based on the selected knowledge graph.SELECTED DRAWING: Figure 1

Inventors:

SAPTARSHI BHATTACHARYA
ZACHARIAH PHILLIPS
SHREEDHAR MADHAVAPEDDI
DAVID MAYMUDES
VIVEK RAO

Application Number:

JP2022099662A

Publication Date:

August 19, 2022

Filing Date:

June 21, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

GOOGLE LLC

International Classes:

G06F16/90; G06F40/56

Attorney, Agent or Firm:

Murayama Yasuhiko
Shinya Mihiro
Tatsuhiko Abe

Previous Patent: Humanization of rabbit antibodies using universal antibody frameworks

Next Patent: Methods and compositions for obtaining low plant height plants via gibberellin metabolic engineering...