Automated Assistant Source Selection to Reduce Unnecessary Searches
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
User interactions with automated assistants often result in inefficient use of computational and network resources due to the need to re-formulate inputs to specify preferred sources for information, leading to prolonged interactions and resource wastage.
Innovation Solution
Implementing source parameter rules within automated assistants to preferentially select sources for responses based on user requests, allowing users to specify preferred sources and enabling the assistant to optimize searches and resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the automated assistant searches multiple sources to fulfill user requests, then the user receives comprehensive information, but computational and network resources are wasted
Solution Approach 1:
The system performs preliminary action by pre-establishing source parameter rules that map user preferences to specific information sources. When a user request is received, the system checks these pre-defined rules to determine the preferred source, avoiding the need to search multiple sources. This preliminary configuration of source preferences resolves the contradiction by ensuring comprehensive information retrieval through targeted searches while minimizing unnecessary computational resource expenditure.
2Adaptability or versatility
If the automated assistant requires users to reformulate inputs to specify preferred sources, then the user's source preferences are met, but interaction time and user effort increase
Solution Approach 1:
The system implements self-service by automatically determining the user's preferred information source through pre-configured source parameter rules. Instead of requiring users to manually reformulate their inputs to specify sources, the system autonomously applies the appropriate source based on the user's historical preferences and the current request type. This eliminates the need for additional user effort and interaction time while ensuring source preferences are fulfilled.
3Loss of information
If the automated assistant renders all search results, then the user has access to complete information, but device resources and user attention are overwhelmed
Solution Approach 1:
The system applies the extraction principle by selectively retrieving and presenting only the most relevant information from the preferred source, rather than rendering all search results. The source parameter rules enable the system to extract and prioritize information from the user's preferred source, filtering out unnecessary results. This maintains information availability for the user while reducing interface complexity and preventing device resource overload.
Data Source
AI summary
Implementations relate to interactions between a user and an automated assistant during a dialog between the user and the automated assistant. Some implementations relate to processing received user request input to determine that it is of a particular type that is associated with a source parameter rule and, in response, causing one or more sources indicated as preferred by the source parameter rule and one or more additional sources not indicated by the source parameter rule to be searched based on the user request input. Further, those implementations relate to identifying search results of the search(es), and generating, in dependence on the search results, a response to the user request that includes content from search result(s) of the preferred source(s) and/or content from search result(s) of the additional source(s). Generating the response further includes including, in the response, some indication that indicates whether the source parameter rule was followed or violated in generating the response.