Natural Language Query Parsing with BNF Metadata Extension
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large-scale managed networks face challenges in efficiently and consistently parsing user queries due to varying data types, amounts, and search methods, leading to difficulties in retrieving desired data results.
Innovation Solution
A remote network management platform is configured to use natural language processing, leveraging Backus-Naur form (BNF) rules and metadata to parse user queries, generating a query object in a formal query language for efficient database search.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional database search methods are used to handle user queries, then the system can retrieve data from the database, but the parsing of user queries becomes inefficient and inconsistent as data searches increase in number and complexity
Solution Approach 1:
The patent introduces an intermediary layer (natural language processing system with BNF rules and metadata) between the user query interface and the database search engine. This intermediary translates diverse natural language queries into standardized search queries, resolving the contradiction by maintaining simple consistent parsing logic while handling increasing query complexity and volume.
2Adaptability or versatility
If the remote network management platform handles increasing numbers of searches with varying complexity, then the platform serves more users and applications, but the consistency and efficiency of query parsing deteriorates
Solution Approach 1:
The patent creates a universal query processing system using Backus-Naur form rules and metadata that can handle multiple types of queries across different users, departments, and applications through a single consistent parsing mechanism. This universal approach maintains parsing consistency while accommodating diverse query requirements.
Solution Approach 2:
The system uses metadata that can be dynamically updated to reflect changing data schemas, search requirements, and user needs without modifying the core BNF parsing rules. This allows the system to adapt to varying query complexity and types while maintaining consistent parsing behavior through parameter changes in the metadata rather than structural changes.
3Adaptability or versatility
If the platform processes large amounts of diverse data with varying search methods, then the platform supports comprehensive data retrieval, but the efficiency of data retrieval decreases
Solution Approach 1:
The patent implements preliminary organization of search logic through pre-defined BNF rules and metadata that encode common search patterns and data relationships. This preliminary structuring allows the system to quickly parse and execute diverse queries without ad-hoc processing, reducing query processing time while maintaining search flexibility.
Data Source
AI summary
An example embodiment may involve a software application executable on computing devices of a remote network management platform and a computation instance associated with a managed network. The computational instance may contain a database storing data of the managed network. The software application may receive, from a client device of the managed network, a natural language query (NLQ), and retrieve Backus-Naur form (BNF) rules and a set of metadata associated with the BNF rules. The metadata may include a text-based description of a schema of the database and abbreviations associated with the BNF rules. The NLQ may be parsed using the BNF rules together with the metadata by applying the metadata during parsing to extend the BNF rules. A query object based on the parsed query may be generated, and the database searched using the query object. A result of the search may be transmitted to the client device.