Verb-Based Query Resolution via Dynamic App Binding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in accessing specific application entities on client devices using interactive assistants due to the need for explicit identification, leading to incomplete queries and repeated attempts, which consume computing and battery resources.
Innovation Solution
Implementing a dynamic application capability binding information database that allows verb-based succinct queries to identify and perform actions on application entities without explicit identification, using natural language understanding and fulfillment engines to resolve intents and parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If users provide explicit queries identifying application and entity, then the interactive assistant can correctly understand and fulfill the action, but the query complexity and user effort increase
Solution Approach 1:
The system performs self-service by automatically resolving the application entity and action parameters without requiring explicit user input. The interactive assistant analyzes the succinct query, automatically identifies the intended application and entity based on context and usage information, and executes the action without prompting the user for additional details.
Solution Approach 2:
The system performs preliminary actions by pre-processing and storing usage information about applications and entities before the query is executed. This includes maintaining capability binding information and usage patterns that enable the system to quickly resolve succinct queries without requiring users to provide complete information.
2Ease of operation
If users provide incomplete or inadequate queries, then the query is simpler and faster to input, but the interactive assistant cannot respond and no action is fulfilled
Solution Approach 1:
The system fills in missing information automatically by analyzing the succinct query and using stored usage information to infer the intended application and entity. This self-service capability allows the system to successfully fulfill actions even when users provide incomplete queries, thereby maintaining high productivity without requiring users to input complete information.
3Reliability
If users make repeated attempts to provide appropriate queries, then the desired action can be fulfilled, but computing and battery resources are extensively consumed
Solution Approach 1:
The system performs preliminary processing by storing usage information and capability bindings in advance, enabling it to resolve succinct queries in a single attempt without requiring repeated user inputs. This reduces the number of processing cycles needed and consequently decreases battery consumption while maintaining reliable action fulfillment.
4Adaptability or versatility
If the system stores dynamic application capability binding information and usage information, then succinct queries can be resolved without explicit identification, but the database complexity increases
Solution Approach 1:
The system creates a universal database structure that stores both capability binding information and usage information in a unified format that can serve multiple purposes. This multi-functional database supports various types of queries and resolutions, enabling the system to handle different query formats and contexts while managing complexity through a standardized approach.
Data Source
AI summary
Some implementations receive audio data capturing a verb-based succinct query that includes an action but is void of any app entity and determine, based on processing of the audio data, the action and one or more instance candidates associated with the action. Some of those implementations further query an app entity database for usage information and/or capability information of one or more app entities that correspond to the one or more instance candidates and generate, based on selecting from the one or more app entities, a response or action responsive to the verb-based succinct query.