Digital Assistant Interface Context Disambiguation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices present users with overwhelming and inconsistent interfaces, making it difficult for novice users, impaired individuals, and others to effectively interact with and utilize the available functions and information, particularly due to the ambiguity of natural language inputs which can lead to errors and incorrect actions.
Innovation Solution
A computer-implemented method for a virtual digital assistant that displays a digital assistant object on a computing device's screen, receives speech input, and determines whether information items can be fully displayed. If not, it displays a portion of the information item, with visually distinguishable regions, allowing users to scroll and translate content, using contextual information to disambiguate user inputs and execute tasks accurately.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a virtual assistant uses natural language processing to interpret user input, then ease of operation is improved, but measurement precision deteriorates due to ambiguity in natural language
Solution Approach 1:
The system performs preliminary actions by proactively obtaining contextual information from multiple sources (device state, application context, user profile, environment) before interpreting the user's natural language input. This pre-gathering of context enables more accurate disambiguation of the user's intent without requiring the user to be more precise in their speech.
Solution Approach 2:
The patent introduces contextual information as an intermediary between the user's natural language input and the system's interpretation. This intermediary layer of context (including device state, application context, user profile, and environmental data) mediates the ambiguous natural language by providing additional constraints and information that narrow down the possible interpretations to the correct one.
2Loss of information
If the interface displays all available information items, then loss of information is reduced, but device complexity increases due to overwhelming display requirements
Solution Approach 1:
The interface applies local quality by making the display characteristics context-dependent. When the digital assistant object is in the first position (information can be fully displayed), the display region has one set of visual properties (visually indistinguishable from object region). When the digital assistant object moves to the second position (information cannot be fully displayed), the display region has different visual properties (visually distinguishable from object region). This local adaptation of display quality optimizes information presentation for each context without requiring a completely different interface design.
3Measurement precision
If the system requests clarification for ambiguous input, then measurement precision is improved, but loss of time increases due to additional user interaction
Solution Approach 1:
The system performs preliminary actions by proactively gathering contextual information from multiple sources before the user even provides their input. This pre-computation of context (device state, application context, user profile, environmental data) enables the system to disambiguate user intent without requiring follow-up clarification questions, thereby maintaining measurement precision while avoiding time loss.
Data Source
AI summary
The digital assistant displays a digital assistant object in an object region of a display screen. The digital assistant then obtains at least one information item based on a speech input from a user. Upon determining that the at least one information item can be displayed in its entirety in the display region of the display screen, the digital assistant displays the at least one information item in the display region, where the display region and the object region are not visually distinguishable from one another. Upon determining that the at least one information item cannot be displayed in its entirety in the display region of the video display screen, the digital assistant displays a portion of the at least one information item in the display region, where the display region and the object region are visually distinguishable from one another.