Heuristic Boolean Patent Search Comparative Patent Search Quality / Cost Evaluation “superboolean” vs. Legacy Boolean Search Engines
نویسنده
چکیده
This paper explores the application of an expert system to Boolean patent searching. Speci fically, it will introduce skilled researchers to the next technological evolution of search methodologies that apply Heuristic Boolean methods to reduce cost, increase efficiency, and enhance search results quality. Boolean search methodology, otherwise known as " keyword searching, " only extracts documents from a database that literally match the search query, but Boolean engines have no capability of determining which of those documents are of highest interest to the researcher. In an effort to overcome this limitation, modi fications to simple Boolean engines have emerged, including truncation, proximity searching, nested complex query capability, and wildcarding. But even with these enhancements, at best, Boolean searching remains little more than an iterative process of applying a query construct to a database in order to (a) extract a reasonable number of documents within (b) a reasonable amount of time, in order to (c) produce the most relevant documents supporting the search objective. At worst, the restrictive nature of Boolean search methods inordinately increase direct and indirect search costs, and establishes a false con fidence in search results quality that i ncrease exposure to long term legal and commercial risks. The patent documents that Boolean engines inherently miss, sometimes discovered years later by other researchers, often establish the true (high) costs attributable to Boolean searches. This paper examines how next generation Heuristic Boolean search methods can more quickly yield the most relevant documents, mitigate long-term risk associated with poor quality results, and reduce the direct, as well as hidden costs attributable to legacy keyword search engines. When the arti ficial intelligence of Heuristics is applied to Boolean patent searching, even novice researchers can quickly achieve reliable search results. A future invalidity search is the ultimate quality test of today's patentability search. Relying on the best search tools and processes today is critical. The future invalidity search performed when millions or 10s of millions of dollars are at risk, and can easily challenge and outperform the earlier patentability search because: 1) Liberal budgets for invalidity searches allow signi ficantly more investment in search labor (higher cost), and 2) Invalidity searches rely on search technology advancements which have evolved since completing the patentability search. The demands to perform a patent search that attempts to identify all of the relevant documents within the scope of available resources (time, budget, computing time, a given …
منابع مشابه
Characteristics of the Boolean Web Search Query: Estimating Success from Characteristics
Popular web search engines use Boolean queries as their main interface for users to search their information needs. The paper presents results a user survey employing volunteer web searchers to determine the effectiveness of the Boolean queries in meeting the information needs. A metric for measuring the quality of a web search query is presented. This enables us to relate attributes of the sea...
متن کاملDepth-based Local Search Heuristics for Boolean Circuit Satisfiability
We propose a structure-exploiting heuristic for the justification-based stochastic local search (SLS) method CRSat for Boolean circuit satisfiability. Experimental evaluation shows that the proposed depth-based heuristic significantly improved the performance of CRSat on structural instances arising from industrial applications. A proof of probabilistically approximate completeness (PAC) of CRS...
متن کاملLearning Boolean Queries for Article Quality Filtering
Prior research has shown that Support Vector Machine models have the ability to identify high quality content-specific articles in the domain of internal medicine. These models, though powerful, cannot be used in Boolean search engines nor can the content of the models be verified via human inspection. In this paper, we use decision trees combined with several feature selection methods to gener...
متن کاملAutomatically Detecting Boolean Operations Supported by Search Engines, Towards Search Engine Query Language Discovery
Each Web search engine provides query language through which it can communicate with its users and retrieve corresponding results to user queries. Supporting Boolean operations is a major characteristic of the query language. In this paper, we propose a novel, fully automatic, query probing based approach to identify what Boolean operations that are supported by a search engines and their corre...
متن کاملSearching for Complex Patterns over Large Stored Information Repositories
Although Information Retrieval (IR) systems, including search engines, have been effective in locating documents that contain specified patterns from large repositories, they support only keyword searches and queries/patterns that use Boolean operators. Expressive search for complex text patterns is important in many domains such as patent search, search on incoming news, and web repositories. ...
متن کامل