Response Completion Model for Mobile Messaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Composing messages on miniaturized or virtual keyboards for mobile devices is cumbersome due to the difficulty in typing, especially in conversational settings where quick and accurate responses are required.
Innovation Solution
A Response Completion Model (RCM) is implemented to provide word-by-word auto-completion of messages by predicting candidate next words based on the context of the stimulus message and the language used in the preceding words, using a combination of language and stimulus models to rank and order potential completions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If users type messages manually on miniaturized or virtual keyboards, then message composition is possible, but typing effort and time consumption increase significantly
Solution Approach 1:
The system performs preliminary action by predicting and preparing candidate next words before the user actually needs to type them. The RCM analyzes the stimulus message and preceding words in the incomplete response message to generate a ranked list of candidate completions in advance, allowing the user to simply select from pre-computed options rather than typing each character.
Solution Approach 2:
The system applies self-service by enabling the incomplete response message to complete itself through automated word prediction. The RCM autonomously analyzes the conversation context and generates candidate completions without requiring manual typing input from the user, allowing the message to compose itself based on learned patterns from stimulus-response data.
2Ease of operation
If users type messages manually on miniaturized or virtual keyboards, then message composition is possible, but typing effort and complexity increase
Solution Approach 1:
The system replaces the mechanical typing system with an intelligent prediction system. Instead of requiring physical or tactile interaction with keyboard keys, the RCM uses language modeling and stimulus-response analysis to automatically generate candidate words, substituting the mechanical input process with computational prediction and selection.
Solution Approach 2:
The system introduces an intermediary element - the RCM with its candidate word list - between the user's communication intent and the actual message composition. Rather than directly typing each word, the user interacts with the intermediary candidate list, which mediates the translation of partial input into complete messages.
Data Source
AI summary
Embodiments are directed towards providing word-by-word message completion for an incomplete response message, wherein the response message is composed in response to a received stimulus message. The message completion is based on a Response Completion Model (RCM) that may model both the language used in the incomplete response message and the contextual information in the received stimulus message. The RCM may be determined based on conversational stimulus-response data including stimulus-response message pairs. The RCM may be a mixture model and include a generic response language model based on an N-gram model, a Stimulus Model based on a Selection Model or a Topic. Model, and a mixture parameter. In some embodiments, at least one candidate next word for the incomplete response message is determined based on the RCM. The at least one candidate next word may be selected and included in the incomplete response message. A complete response message may be generated and provided to a user.