Natural Language Interface for Querying Hardware and Software Configuration of a Local Area Network
Year: 2019
Type: article
Abstract: In this digital era, it is virtually impossible to find even a single business premise that does not host a local area network in place. Knowledge of all softwares installed and all hardwares connected to LAN is extremely essential to a lab technician. Because on many occasions, any minor error in LAN requires the lab technician to check virtually all computers connected to LAN manually which is extremely time consuming and a lengthy process. In majority of cases, only few machines in the network contain softwares owning to the limited user licenses. Some machines contain softwares which are occasionally used. Locating such an information in a large local area network is an extremely time consuming task. The aim of current research is to design and develop an interface for LAN which accepts the queries pertaining to hardware and software installed in LAN in natural language (NL) which is parsed using NLP parser designed and developed by the authors for the domain under consideration for facilitating the human-machine interaction. For this a set of alphabets, a set of tokens, and a context free grammar is designed. The parts-of-speech tags are numerically encoded and a pattern is generated for a syntactically valid statements. A set of rules are generated by observing the statements which are syntactically valid. The research is carried out in two phases. In the first phase, the query entered by the user in a natural language is parsed using NLP parser. In the second phase of the research, the queries which are found to be syntactically correct in phase I are further evaluated by mapping them to the corresponding prolog queries which interfaces with the knowledge base for retrieving the desired set of information. Finally, the model is implemented in a hypothetical educational institute to evaluate the operational feasibility of the model.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2931702328
