Automated Assistant Intercom Message Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing human-to-computer dialog systems, such as automated assistants, lack efficient methods to determine the location of users within an environment and selectively convey spoken messages to intended recipients, often resulting in unnecessary broadcasts or missed communications due to the inability to differentiate between commands, messages, and background noise.
Innovation Solution
The implementation of a system that uses presence sensors and machine learning classifiers to detect user locations and classify utterances, allowing for targeted intercom-style communication by identifying invocation phrases, intended recipients, and background noise, and selecting appropriate devices for message delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If explicit commands are used to convey messages to explicitly-defined computing devices, then message delivery can be achieved, but the system requires user knowledge of device locations and explicit invocation, reducing ease of operation
Solution Approach 1:
The system automatically determines user location and message intent without requiring explicit commands. The automated assistant client analyzes voice input, identifies intended recipients, and selects appropriate computing devices autonomously, allowing the system to serve itself rather than requiring detailed user instructions.
Solution Approach 2:
The patent replaces manual device selection and explicit intercom invocation with automated voice-based intent recognition. Machine learning models analyze voice patterns to determine message intent and recipient identity, substituting mechanical device selection with intelligent automated decision-making.
2Reliability
If messages are broadcast at all computing devices, then message delivery is ensured, but unnecessary broadcasts increase energy consumption and reduce communication efficiency
Solution Approach 1:
The system delivers messages to specific computing devices based on the determined location of the intended recipient rather than broadcasting to all devices. This localized message delivery approach ensures reliability for the target user while avoiding unnecessary energy consumption at other devices.
Solution Approach 2:
The automated assistant client changes the parameter of message delivery scope from global (all devices) to local (specific device based on recipient location). By dynamically adjusting the delivery parameters based on analyzed voice input and location data, the system maintains reliability while reducing energy waste.
3Loss of information
If the system cannot differentiate between commands, messages, and background noise, then all voice input must be processed, but this increases processing time and reduces productivity
Solution Approach 1:
The system performs preliminary analysis of voice input to determine intent before full processing occurs. The automated assistant client analyzes voice patterns, identifies intended recipients, and classifies input as command, message, or background noise in advance, allowing efficient routing and preventing unnecessary processing of non-communicative inputs.
4Measurement precision
If presence sensors and machine learning classifiers are implemented, then accurate user location detection and utterance classification is achieved, but device complexity increases
Solution Approach 1:
The automated assistant client performs multiple functions including voice input analysis, intent determination, recipient identification, and device selection using a single integrated system. This multi-functional approach achieves high measurement precision for location and utterance classification while avoiding the need for separate specialized components that would increase overall system complexity.
Data Source
Figure 1A~1B
Figure 2
Figure 3
AI summary
Techniques are described related to improved intercom-style communication using a plurality of computing devices distributed about an environment. In various implementations, voice input may be received, e.g., at a microphone of a first computing device of multiple computing devices, from a first user. The voice input may be analyzed and, based on the analyzing, it may be determined that the first user intends to convey a message to a second user. A location of the second user relative to the multiple computing devices may be determined, so that, based on the location of the second user, a second computing device may be selected from the multiple computing devices that is capable of providing audio or visual output that is perceptible to the second user. The second computing device may then be operated to provide audio or visual output that conveys the message to the second user.