Абстрактный

Efficient Approach of Patent Search Paradigm

Haritha.V, Dr. A.Senthil Kumar, Dijith.M.S

As an important action of finding existing relevant patents and validating or invalidating new patent application, patent search attracts much attention from both industrial and academiccommunities. But most of the users have limited knowledge about the underlying patents and they have to repeatedly issue different queries and check answers, which is a very time consuming and boring process. To overcome this problem, we propose an efficient approach of user friendly patent search paradigm, which improves the user search experience by helping the user in finding the relevant patents more easily. Automatic error correction, topicbased query suggestion, and query expansion, are the three effective techniques that we have proposed to improve the usability of patent search. We also focus on how to efficiently find relevant patents from a large collection of patents. First, partition the patents into small partitions based on their topic and classes. Then for a given query, we find the highly relevant partitions and answer the query in each of such pertinent partitions. Finally, we combine the answers of each partition and generate top-k answers of the patent-search query. Thus it produces more pertinent answers through sophisticated graphical user interaction.