The invention discloses a rRemote sensing image recommendation device based on frequent item mining

Abstract

The invention discloses a remote sensing image recommendation device based on frequent item mining. The device has the following functions: receiving an area selected by a user through a front-end webpage; according to the framed rectangular area, retrieving in a database to obtain all area data covered by the framed rectangular area, randomly combining all the area data, and after obtaining all possible frequent items, screening all the possible frequent items by utilizing a preset frequent item sample set to obtain frequent items; calculating the recommendation probability of the frequent items by using the trained GBDT model; and outputting the frequent item with the highest recommendation probability to the user to recommend the remote sensing image. The device effectively combines space-time characteristics of remote sensing data for matching and recommendation, so that a user can obtain a data combination more conforming to user expectation after interacting with a two-dimensional map displayed on a page.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image data mining, in particular to a remote sensing image recommendation device based on frequent item mining. Background technique [0002] With the rapid development of the Internet, the data has also ushered in explosive growth. Whether it is user data, product data or the number of websites, etc., there is an exponential growth trend. There are two main problems. One is How to store massive data, the current common technical solution is to store massive data in a distributed manner based on Hadoop clusters, and increase the overall storage capacity by dynamically expanding the number of clusters, and the distributed storage guarantees data through a unique backup mechanism Storage security. The second problem is how to retrieve massive amounts of data efficiently. Due to the huge increase in the amount, the speed of generation has far exceeded the speed that users can obtain, and user...

AI Technical Summary

Problems solved by technology

The second problem is how to efficiently retrieve massive data. Due to the large increase in the number, the speed of generation has far exceeded the speed that users can obtain. Users will be at a loss when faced with massive data sets.

[0003] In the field of remote sensing data, the nature of remote sensing data is different from that of general commodities. The main points are as follows: 1. Remote sensing data are generally large, and the original data is generally around 1Gb. If the amount of data increases, the stand-alone storage can basically not meet the requirements

2. Remote sensing data involves spatial attributes, each piece of data corresponds to an actual area, and general commodities do not have this feature

4. The volume of remote sensing data transactions is limited, and the time span may be large, so the problem of insufficient data volume needs to be solved

Since the user may have multiple cities, whether it is a full-text search or a two-dimensional image check search, the user can only rely on the user to independently select the target result in the returned result set. Once the number of returned results is too large, the time spent by the user will increase The longer it will be, it will greatly affect the user's efficiency and experience, and the returned result is a single area, and users often need a combination of several areas