Abstract: Systems and methods for enhanced document analysis and identification through a reinforcement learning framework are provided. A system may employ computer based reinforcement learning to interact with large populations of documents to help users achieve a goal. To accomplish this goal, rewards, value functions, states, policies, and actions may be modeled and various tools within the system can be used to achieve the user's goal. As actions are performed, the results of these actions may be used to update state, assess rewards, and update value functions and policy functions. If the goal is not achieved, the system may make adjustments by adjusting policies, pushing the user closer to their goal by methods of reinforcement learning. Once the goal is achieved, such as a confidence that at least a certain percentage of relevant documents have been identified, relevant documents may be provided to a party desiring the documents.
Abstract: A method for converting arbitrary strings consisting of any combination of numbers, digits, or punctuation into numerical representations for comparisons at run time or any other time using a data store such as a relational database or full text search engine. The method is designed to build a numeric representation having small, fixed length values that are stored in numeric data types supported by the data store. All arbitrary string data is converted to a numeric representation using the method and placed in the data store. Queries of the data can be converted to a similar numeric representation.