Smart Device Non-Dialog Data Transformation for Chatbot Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current chatbot conversations lack context and realism due to generic speech patterns resulting from inadequate training data, leading to a mechanical or 'machine-like' quality that can be off-putting to human users.
Innovation Solution
A system that collects and transforms non-dialog data from smart devices into standardized formats using machine learning algorithms, enabling the incorporation of contextual information into chatbot training data structures, thereby enhancing conversational flow and realism.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If chatbot models use generic speech patterns due to lack of context in training data, then the chatbot system is simple to implement, but the conversation quality and realism deteriorate
Solution Approach 1:
The system performs preliminary actions by collecting and transforming smart device data into contextual training data before chatbot model training. This pre-processing of contextual information from multiple data sources enables the chatbot to learn realistic speech patterns and user behaviors in advance, improving conversation quality without adding complexity during runtime operations
Solution Approach 2:
The patent introduces an intermediary data transformation process that bridges smart device data and chatbot training requirements. This intermediary layer transforms raw device data into contextual training data through machine learning algorithms, enabling seamless integration of external data sources while maintaining system modularity and managing complexity
2Loss of information
If smart device data is collected and transformed using machine learning algorithms, then contextual information is enhanced, but data processing complexity increases
Solution Approach 1:
The system implements a universal data transformation process that handles multiple types of smart device data through a single machine learning-based framework. This multi-functional approach transforms diverse device data into standardized contextual training data, reducing overall system complexity by consolidating multiple transformation processes into one versatile system
Solution Approach 2:
The patent applies parameter changes by transforming raw device data parameters into contextual training data parameters through machine learning algorithms. This parameter transformation process extracts meaningful contextual information from device data while standardizing the output format, enhancing information quality without requiring complex custom processing for each data type
3Adaptability or versatility
If non-dialog data from smart devices is integrated into training data, then user-specific context is improved, but data processing time increases
Solution Approach 1:
The system performs preliminary transformation of smart device data into contextual training data before chatbot deployment. This pre-processing enables user-specific context adaptation to be established in advance through machine learning-based transformation, reducing runtime processing time while maintaining high adaptability to individual user patterns and behaviors
Data Source
AI summary
Disclosed are an apparatus, a system and a non-transitory computer readable medium that implement processing circuitry that receives non-dialog information from a smart device and determines a data type of data in the received non-dialog information. Based on the determined data type, the processing circuitry transforms the received first data using an input from a machine learning algorithm into transformed data. The transformed data is standardized data that is palatable for machine learning algorithms such as those used implemented as chatbots. The standardized transformed data is useful for training multiple different chatbot systems and enables the typically underutilized non-dialog information to be used to as training input to improve context and conversation flow between a chatbot and a user.