Interactive Voice Response for Storage Configuration Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Storage system management applications have become increasingly complex, requiring extensive user training to navigate and make configuration changes, with existing interfaces like graphical user interfaces and command line interfaces being difficult for users to manage.
Innovation Solution
A method and apparatus for training a large language model to learn a textual description of a storage system configuration, enabling an interactive voice response interface that allows users to interact with the storage system management application using natural language, by generating training text from a machine-readable model and using Java introspection and annotations to identify relationships between objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If graphical user interface or command line interface is used for storage system management, then the application can provide comprehensive configuration access, but the user requires extensive training and considerable skill to navigate and make changes
Solution Approach 1:
The patent replaces the mechanical interaction of graphical user interfaces and command line interfaces with a voice-based natural language interface. Users can verbally query configuration information and issue change commands, which are processed by speech recognition and natural language interpretation systems, eliminating the need for manual navigation through complex UI elements or memorization of command syntax.
Solution Approach 2:
The patent introduces an intermediary natural language processing layer between the user and the storage system management application. This intermediary translates spoken language into structured commands and queries, mediating the interaction between human users and the complex configuration system, thereby simplifying the user interface while maintaining full configuration access capability.
2Adaptability or versatility
If storage system management application provides extensive features, then the application functionality is comprehensive, but the interface complexity increases requiring more training
Solution Approach 1:
The patent substitutes the complex visual and textual interfaces with a voice-based natural language interface. This allows the system to maintain comprehensive functionality across multiple configuration areas while presenting a simpler, more intuitive interface through spoken communication, reducing the perceived complexity despite extensive underlying features.
Solution Approach 2:
The patent creates a universal natural language interface that can handle multiple types of configuration tasks through a single consistent interaction model. Whether querying configuration information, navigating to different settings, or making changes, users employ the same voice-based approach, eliminating the need to learn different interface paradigms for different functions.
3Measurement precision
If traditional interface requires user navigation skill, then precise configuration control is achievable, but user training time increases
Solution Approach 1:
The patent replaces the skill-based mechanical navigation of traditional interfaces with voice-driven natural language processing. Users can precisely specify configuration parameters through spoken language without requiring training on interface navigation, as the system interprets natural language queries and commands to achieve the desired configuration control precision.
Solution Approach 2:
The system employs self-service mechanisms where the natural language interface automatically understands and processes user intent without requiring pre-training. The speech recognition and natural language interpretation systems are pre-configured to comprehend configuration-related queries and translate them into appropriate system commands, eliminating the need for user training while maintaining precise configuration control.
Data Source
AI summary
A textual description of a machine-readable model describing a configuration of the storage system is created. The textual description includes a plurality of textual statements, in which each individual textual statement describes a relationship between a pair of objects of the machine-readable model, or describes a relationship between a given object and a respective value of the given object. The textual statements describing the configuration of the storage system are provided as training input to a large language model to train the large language model to learn the textual description of the storage system configuration. The large language model is then used, by an interactive voice response system to respond to natural language queries about the storage system configuration. The machine-readable model may be implemented using a Java model that is annotated to identify relationships between objects that should be used to generate textual statements describing the storage system configuration.