Unlock instant, AI-driven research and patent intelligence for your innovation.

Dependency graph conversation modeling for use in conducting human-to-computer dialog sessions with a computer-implemented automated assistant

A man-machine dialogue and graph-dependent technology, applied in computing, natural language data processing, electrical digital data processing, etc., can solve the problems of unrealistic, complex labor intensity, and inflexible input of various users.

Pending Publication Date: 2020-12-25
GOOGLE LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, with traditional automated assistants, especially for actions associated with third parties and other computing services that require a large number of input parameters to perform efficiently, modeling conversations to gather the required input parameters can be complicated are labor intensive and can necessitate significant development overhead associated with handling all possible inputs and their combinations and sequences
These complex models may occupy a relatively large amount of space in computer memory, and may also need to be updated over time to account for previously unforeseen inputs and their combinations and sequencing
Conversation can also be constrained and inflexible to various user inputs, resulting in more robotic and less lifelike interactions with automated assistants

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Dependency graph conversation modeling for use in conducting human-to-computer dialog sessions with a computer-implemented automated assistant
  • Dependency graph conversation modeling for use in conducting human-to-computer dialog sessions with a computer-implemented automated assistant
  • Dependency graph conversation modeling for use in conducting human-to-computer dialog sessions with a computer-implemented automated assistant

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] now turn figure 1 , illustrates an example environment in which the techniques disclosed herein may be implemented. The example environment includes multiple client computing devices 106 1-N . Each client device 106 may execute a respective instance of the auto attendant client 118 . One or more cloud-based automated attendant components 119, such as natural language understanding engine 135, can be implemented on one or more computing systems (collectively referred to as "cloud" computing systems) via One or more local area networks and / or wide area networks (e.g., the Internet) indicated at 110 are communicatively coupled to client device 106 1-N .

[0031] In some implementations, an instance of the auto attendant client 118, through its interaction with one or more cloud-based auto attendant components 119, can form an auto attendant that appears to the user to have a human-machine conversation with it from the user's perspective. Logical instance of assistant ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Conversations are modeled using dependency graph data structures to facilitate the interaction of users with automated assistants when performing actions performed by computing services. An automatedassistant may utilize a dependency graph data structure to guide or otherwise control a human-to-computer dialog session with a user, e.g., by generating one or more outputs or prompts that are presented to the user on a computing device operated by that user, and may thereby enable efficient use of technical hardware.

Description

Background technique [0001] Humans can interact with software referred to herein as "automated assistants" (also referred to as "chatbots," "interactive personal assistants," "intelligent personal assistants," "personal voice assistants," "talking agents," etc.) Application for man-machine dialogue. For example, humans - who may be referred to as "users" when they interact with an automated assistant - can provide commands, queries and / or requests using free-form natural language input. Free-form natural language may include spoken utterances converted to text using speech recognition and / or typed free-form language input. [0002] Auto attendants enable users to obtain information, access services, and / or perform various tasks. For example, users are able to perform searches, get directions, and in some cases interact with third-party computing services. These third-party computing service interactions (access may be facilitated using an application programming interface (...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F40/253
CPCG10L15/19G10L15/22G06F9/453G06F16/9024G06N5/022G06F16/9535G06F40/35H04L51/02
Inventor 阿米特·巴拉德瓦杰
Owner GOOGLE LLC