Patent mining to predict class using decision tree and naïve bayes algorithm

Abstract

The number of patents that are being filed across the world is increasing day by day. With the increase in patents being filed the process of segregating the patents based on their class becomes even more difficult. There is no prior work that has been done to increase the efficiency of this process, therefore patent mining is done. There are a set of features that are extracted from the dataset that is previously present. The features that are being extracted will vary for each document and based on the feature that is extracted the following steps are carried out. After the feature extraction is done there are two steps that need to be carried out, namely: Classification and prediction. For this purpose, decision tree algorithm is used which makes use of the most prominent feature and classification is done using those features. Therefore, for classification a hierarchical decision tree algorithm is used along with the probability of patent conversion. Based on the classification that is done a model will be created and whenever a new entity is brought it is compared with the model file that was created using the available datasets and is predicted as a particular class. Thus, both classification of existing dataset and the prediction for any new dataset based on previous inputs can be achieved thereby facilitating the patent mining process.