Digital Assistant Preference Modeling for Ambiguous Device Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing intelligent automated assistants struggle to interpret ambiguous speech inputs and intelligently identify the correct electronic device from multiple devices for providing an accurate response to user requests, often requiring multiple commands or failing to distinguish between devices capable of processing the request.
Innovation Solution
A digital assistant system that retrieves historical interactions, contextual information, and location data to apply preference rules for intelligent device selection, automatically identifying the most appropriate device to fulfill user requests based on historical usage patterns and context.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing digital assistants process user requests using basic device availability checks, then the system complexity remains low, but the ability to interpret ambiguous speech input and identify the correct device deteriorates
Solution Approach 1:
The system performs preliminary actions by retrieving historical interactions and context information before making device selection decisions. This allows the system to pre-process and analyze user preferences, device states, and interaction patterns in advance, enabling more accurate interpretation of ambiguous speech inputs without significantly increasing real-time processing complexity
Solution Approach 2:
The patent introduces an intermediary preference model that acts as a mediator between raw speech input and device selection. This preference model translates ambiguous user requests into structured device selection criteria by incorporating historical interaction data and context information, thereby improving identification accuracy while managing system complexity through modular architecture
2Measurement precision
If the system retrieves and analyzes historical interactions and context information for device selection, then the accuracy of device identification improves, but the time and computational resources required increase
Solution Approach 1:
Historical interactions and context information are retrieved and pre-processed in advance, allowing the system to have historical data ready when device selection is needed. This preliminary action reduces the time required during actual device selection by avoiding real-time computation of historical patterns
Solution Approach 2:
The system dynamically adjusts the depth and scope of historical interaction analysis based on the ambiguity of the user request. For clear requests, minimal historical analysis is performed, while for ambiguous requests, more extensive historical data is retrieved and analyzed, optimizing the balance between accuracy and time consumption
3Measurement precision
If the digital assistant requires multiple commands or user clarifications to identify the correct device, then device selection accuracy may improve, but the ease of operation and user experience deteriorate
Solution Approach 1:
The system performs self-service by automatically analyzing historical interactions and context information to identify the correct device without requiring user clarification. The preference model autonomously interprets ambiguous requests by inferring user intent from past behavior patterns, enabling the system to make accurate device selections independently
Solution Approach 2:
The system incorporates feedback from historical user interactions to improve real-time device selection. By learning from past user preferences and device selection patterns, the system refines its ability to interpret ambiguous requests accurately, reducing the need for additional user commands while maintaining high identification accuracy
Data Source
AI summary
This relates generally to intelligent automated assistants and, more specifically, to provide intelligent device selections by the intelligent automated assistants for performing requested actions. An example method includes, at an electronic device receiving a user request from a user, identifying the user, a domain type of the user request, and one or more electronic devices available for handling the user request; retrieving one or more historical interactions involving at least one of the identified user, the domain type, and the one or more electronic devices, generating metadata based on the one or more historical interactions, location information of the one or more electronic devices, and context information associated with the one or more electronic devices; identifying a delivery device by interpreting the metadata using a preference model; and transmitting a response command to the delivery device for providing the result output.