Voice Assistant Unsolicited Content Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computing devices lack the ability to provide users with unsolicited, interesting content related to their queries, even when the requested information is unknown, limiting the engagement and value of voice-controlled interactions.
Innovation Solution
A system that outputs requested information alongside unsolicited, interesting content by associating user utterances with entities and selecting relevant facts based on user profiles, time, location, and other factors, using network-accessible resources and components like ASR, NLU, and TTS engines to generate and deliver audio and visual responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If the system only outputs requested information, then the response is concise and direct, but user engagement and information value are limited
Solution Approach 1:
The system pre-associates entities with multiple interesting facts in advance, storing them in a database structure that links entities to their related facts. This preliminary preparation allows the system to quickly retrieve and output relevant unsolicited content without complex real-time processing, thereby increasing information value while maintaining system simplicity
Solution Approach 2:
The patent introduces an intermediary component (the interesting facts application and database) that sits between the information retrieval system and the user. This intermediary automatically selects and adds relevant unsolicited facts to responses, enhancing information value without requiring the main system to become more complex
2Adaptability or versatility
If the system provides unsolicited interesting content, then user engagement and information value increase, but the response time and processing complexity increase
Solution Approach 1:
By pre-associating entities with their interesting facts in a database during system setup or offline processing, the system eliminates the need for complex real-time analysis. When a user query is processed, the system simply retrieves pre-prepared facts related to the query entities, significantly reducing response time while maintaining high user engagement
Solution Approach 2:
The system implements a configurable approach where it can add one or more unsolicited facts to each response based on query type and user profile. This partial action (adding selective facts rather than all available facts) optimizes the balance between user engagement and response time by providing enough additional content to be interesting without overwhelming the user or excessive processing
3Adaptability or versatility
If the system outputs unsolicited content for all queries, then user engagement increases, but information relevance and accuracy decrease
Solution Approach 1:
The system applies different rules for adding unsolicited content based on the local characteristics of each query type. For example, it selectively adds facts to informational queries but may skip or modify the approach for transactional or time-sensitive queries. This localized quality control maintains information relevance while preserving user engagement benefits
Solution Approach 2:
The system changes parameters such as the number of unsolicited facts to add, the types of facts selected, and the conditions under which they are added based on query analysis, user profile, and context. This dynamic parameter adjustment ensures that unsolicited content remains relevant and appropriate for each specific interaction while maintaining high user engagement
Data Source
AI summary
This disclosure describes systems and techniques receiving a request for information from a user and, in response, outputting the requested information along with unsolicited, interesting content that is related to, yet nonresponsive to, the requested information. In some instances, if the requested information is unknown, the techniques may output an indication that the information is unknown, followed by the additional, unsolicited, interesting content.


