Information retrieval (IR) is the key technology for finding relevant data from large collections. The main challenge of IR is to collect and manage all the information in the collection. People need to access the information that suits their needs at the right time. However, the excessive availability of information causes information overload and makes it difficult to find the relevant information. To overcome these difficulties, several automated tools are used to search for information that matches the user’s needs. The role of IR is to collect and represent the information and enable the retrieval of the relevant information for specific problems in real time. This paper focuses on the different IR models that identify the user’s query and retrieve the information from the collection of documents in a specific application domain. If the user’s query matches the search engine, it retrieves the relevant information from the collection. This paper presents different IR models with solved examples and analyzes the IR metrics for ranked and unranked models. It also compares the classical and probabilistic models using different parameters.

Information retrieval, query, IR Models