Connected Vehicle Conversational Agent Message Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current messaging protocols, such as the GSMA RCS standard, are not well-suited for interaction between conversational agents and vehicle users while driving, as they do not adapt to the vehicle's communication interfaces and driving constraints, leading to a suboptimal user experience.
Innovation Solution
A method and device for processing messages from conversational agents that determine and render both vocal and visual data, allowing users to interact via voice and graphical interfaces, even when visually occupied, by analyzing message content and structure to prioritize relevant data for vocalization and display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If graphical interface messages are used for conversational agent interaction, then information presentation is enhanced, but usability deteriorates when user visual attention is occupied during driving
Solution Approach 1:
The patent segments the message content into different channels: graphical interface elements and vocalization elements. The processing device divides the message data to be presented to the user into at least one datum to be vocalized and at least one datum to be graphically rendered, allowing simultaneous use of both modalities without interfering with each other.
Solution Approach 2:
The patent adds a temporal dimension to the communication interface by incorporating vocalization alongside the graphical interface. This allows the user to receive information through multiple channels (visual and auditory) simultaneously, resolving the contradiction between comprehensive information presentation and ease of operation during driving.
2Loss of information
If all message data is displayed graphically, then complete information is provided, but user safety deteriorates due to visual distraction during driving
Solution Approach 1:
The patent extracts critical information from the graphical display channel and transfers it to the vocalization channel. The processing device identifies and extracts at least one datum to be vocalized from the message, allowing this information to be conveyed through audio instead of visual means, thereby reducing visual distraction while maintaining complete information delivery.
Solution Approach 2:
The vocalization system acts as an intermediary channel between the conversational agent and the driver. Instead of relying solely on the graphical interface that requires visual attention, the system uses vocalization as an intermediate medium to convey important information, thereby mediating between complete information provision and driver safety.
3Ease of operation
If message processing includes both vocalization and graphical rendering determination, then interaction quality is improved, but processing complexity increases
Solution Approach 1:
The processing device is designed with multi-functionality to handle both graphical rendering and vocalization processing. The same processing device that manages the graphical user interface also processes the vocalization elements, allowing one device to perform multiple functions and thereby reducing overall system complexity while maintaining high interaction quality.
Data Source
AI summary
A method for processing at least one message sent by a conversational agent, the message including a plurality of data. The processing method is implemented by a processing device and includes: a step of receiving the at least one message; a step of determining at least one first datum to be vocalized and at least one second datum to be displayed, with the data being included in the plurality of data; a step of providing the at least one first datum and the at least one second datum for rendering.