# Instruction Banksea NFT Oracle is divided into the following two modules: * **Collection-Level** Based on the transaction and listing records on the chain，Banksea NFT Oracle calculates the market floor price, AI floor price, 24-hour average price and other data of the NFT collections in real time, and synchronizes these data on chain. AI floor price is the minimum value of the AI valuation of all NFTs in a collection, preventing the instability of the market floor price and attacks from short-term manipulation. * **NFT-Level** Banksea NFT Oracle analyzes comprehensive basic data of NFTs, extracts multi-dimensional features, and trains AI models based on time series modeling. The AI model will generate a valuation for a certain NFT at regular intervals, in the meanwhile, the platform will perform regression verification based on the real-time NFT trading price and will continue to optimize the model to ensure accuracy. The result of the valuation includes a standard valuation and a valuation range. The standard valuation refers to the comprehensive evaluation result of the AI model, and the valuation range refers to the valuation boundaries of different models. At present, Banksea offer 100 free feeding service on **Collection-Level**, which can be obtained through smart contract. And this article will explain how to use feeding data on-chain. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://banksea-finance.gitbook.io/oracle/readme.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.