Telephony-Integrated Digital Assistant for In-Call Speech Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional telephonic systems lack the ability to effectively recognize speech input directed to digital assistants and speech input intended for communication participants, preventing users from handing off calls to digital assistants and monitoring sessions where the assistant acts on their behalf.
Innovation Solution
A system is developed to integrate digital assistants with telephony, allowing for the recognition of speech input and enabling the digital assistant to interact with call participants and perform tasks on behalf of the user during a communication session.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional telephonic systems are used, then basic call functionality is provided, but the ability to recognize speech input directed to digital assistants and distinguish it from speech input for call participants is lost
Solution Approach 1:
The patent introduces a speech routing intermediary that sits between the microphone input and the processing destinations (digital assistant vs. call participant). This intermediary analyzes speech characteristics, determines intent, and routes the speech input to the appropriate destination, enabling both digital assistant integration and call functionality without requiring complete system redesign
Solution Approach 2:
The speech processing system is segmented into distinct pathways: one pathway handles speech directed to the digital assistant (with separate recognition and processing components), while another pathway handles speech directed to call participants. This segmentation allows independent optimization of each pathway without interfering with the other, resolving the contradiction between added capability and system complexity
2Adaptability or versatility
If digital assistant functionality is integrated into telephony, then user interaction capability is enhanced, but the ability to effectively manage incoming and outgoing calls is compromised
Solution Approach 1:
The digital assistant is designed with multi-functionality to handle both traditional call management tasks (answering, transferring, ending calls) and assistant-specific tasks (scheduling, information retrieval). This universal design allows a single integrated system to perform multiple functions without requiring separate dedicated systems, maintaining ease of operation while enhancing interaction capability
Solution Approach 2:
The digital assistant autonomously performs call management tasks without requiring user intervention. It can independently answer incoming calls, transfer calls between participants, end calls, and manage call routing based on contextual understanding, freeing the user from manual call management while enhancing interaction capabilities
3Adaptability or versatility
If speech-based digital assistant technology is integrated with speech-based telephony, then functionality is enhanced, but the ability to distinguish between assistant-directed speech and participant-directed speech is lost
Solution Approach 1:
The system performs preliminary actions by analyzing speech characteristics before routing the speech to its destination. It examines acoustic features, contextual cues, and directional information in advance to determine whether the speech is directed at the digital assistant or a call participant, enabling accurate distinction before the speech processing pathway is selected
Solution Approach 2:
The patent replaces traditional mechanical speech routing (based on physical direction or manual selection) with acoustic and contextual analysis. Instead of relying on the physical direction of the microphone or manual user selection, the system uses acoustic field analysis, speech pattern recognition, and contextual understanding to automatically determine speech destination, enhancing both functionality and recognition accuracy
4Adaptability or versatility
If users can interact with digital assistants during ongoing calls, then interaction flexibility is improved, but system complexity increases
Solution Approach 1:
The speech routing system is designed to be dynamic rather than static. It continuously adapts its routing decisions based on the current call state, the nature of the speech input, and contextual factors. This dynamic approach allows the system to handle multiple interaction scenarios (interrupting the assistant, interrupting the call, switching between modes) without requiring separate rigid systems for each scenario, managing complexity through adaptive behavior
Data Source
AI summary
Systems and processes for integrating a digital assistant with telephony are provided. For example, an incoming call may be received, from a caller, at an electronic device. A communication session may be established between the caller and the digital assistant of the electronic device. In accordance with a determination that the identification of the caller is unknown, determination is made whether the caller corresponds to an automated calling system. In accordance with a determination that the identification of the caller is known, a response is provided by the digital assistant to the caller. An output including information corresponding to the communication is provided at the electronic device.