How is Reinforcement Learning changing the Prior Art Searching?

Machine Learning is now being used in most search platforms, including many patent searching tools. One subset of ML (Machine Learning) that has recently gained traction is ‘Reinforcement Learning.’ The basic idea of reinforcement learning is quite simple, use feedback to reinforce (hence strengthen) positive outcomes.

It is a feedback-based ML technique in which a system learns to behave in an environment by performing the actions and seeing the results of actions. For each good action, the system gets positive feedback, and for each bad action, the system gets negative feedback or a penalty. In this process, the system learns automatically using feedback.

Reinforcement Learning optimizes searching technology by bringing it closer to the goal of quickly ranking search results according to human feedback.

How Does XLSCOUT Incorporate Reinforcement Learning?

XLSCOUT put the use of reinforcement learning to its AI-based Novelty Checker tool to get quality prior art search reports in just 10 minutes. The Novelty Checker uses reinforcement learning to filter the noise from the prior art by pulling up the relevant results on top of the list. To be precise, it assists in conducting a novelty search to help you ensure that your innovation is unique. By selecting a few relevant and non-relevant results, users can apply it to the result set. The system takes the user’s feedback and then learns from it. Then it re-ranks the results by bringing the quality results to the top and sending the noise to the bottom.

Without reinforcement learning, users go through hundreds of results manually. By applying this process, users can skip going through the non-relevant results. Reinforcement can also be applied multiple times to a result set according to users’ different requirements/criteria. Users can then view the Top-10 or Top-20 results for each criterion to perform a prior-art analysis for idea validation.

Users can quickly generate an automated novelty and patentability search report by selecting these Top-10 or 20 results. The Novelty Checker prior art search reports include a list of results along with relevant text mapping with the key features of the invention for enabling quick decision making.