Construction and Integration of Knowledge Grid in Agricultural Information Management Services

Abstract

Agriculture is a major employment source in the world. In India, 55% of the population is employed in the agriculture and allied sectors. The Gross Domestic Production (GDP) contribution of agriculture is 15% levels. Managing crops, soil, climate, irrigation, fertilisers, disease, pest, market, and trade information is essential to guide the farmers and other industries. Data collection, analysis, organisation and presentation are the key operations of the knowledge management structures. The knowledge grid is a graph or network formed by element entities and relational links between element entities. The concepts, events and relationships are represented in the knowledge grids. The schema layer and data layers are used in the knowledge grids. The knowledge representation, extraction, fusion and reasoning operations are applied knowledge grid models. The crop disease and pest information are managed under the knowledge grids. The knowledge grid is utilised with expert structures and crop query answering models. The Agriculture Information Management Services (AIMS) are building with knowledge grids. The knowledge grid construction process is enhanced with crop, soil, season, fertiliser and disease and pest information. Food manufacturing was hypercritical action in which every single country desired to have their own sustenance. Our country, India, is the largest Autotroph of the nutrition corpuscle in the biosphere. In our country, close to seventy percentage of agricultural family stagnant be contingent on farming for their living. Being farm growers blessed mostly essential in our country by way of agriculturalists making a huge elect-vote group which leaders challenge, not spoil. All together, Administrations are necessary to stabilise the involvement of agriculturalists with patrons, the mediator, and then the social group at huge. The entire farming body is extremely statistics serious. Even with tremendous information gathering and quantities from different administration areas, proceed to be statistics gaps. In this section, sensing the Societal Statistics Organization Supporting structure will assist in examining the agronomic segment and modifying the similar using a holistic approach. The automatic knowledge extraction, knowledge map quality enhancement and entity alignment methods are combined in the knowledge grid process. The Machine Learning (ML) based crop pest prediction models are integrated with the knowledge grids. The Java language and MongoDB are used for the structure development process.