Natural Language Processing of Patents and Technical Documentation

Abstract

Abstract. Natural Language Processing techniques for text-mining and information retrieval are finding application in the analysis of many kinds of documentation, from technical documentation to World Wide Web. Particularly, Functional Analysis techniques are based on the extraction of the interactions between the entities described in the document: these interactions are expressed as Subject-Action-Object (SAO) triples (obtainable using a suitable syntactic parser) which represent a concept in its most synthesizing form. In this work, the techniques developed for a functional analysis of patents and their implementation in the PAT-Analyzer tool are presented. The same technique has been properly tailored and applied to the analysis of software requirements documents. Current work in the direction of the development of a SAO-based Content Analysis of technical documentation is presented.

A Function-Based Knowledge Base for Technology Intelligence

“…However, the activity of proposing competitive products or technologies tends to be limited by psychological inertia on one hand and by lack of knowledge on the other (Cascini et al, 2004). Although, for these reasons, methodological approaches for technology intelligence processes haven suggested, few studies have dealt with the construction of a knowledge base that can act as a basis for the practical implementation of these approaches.…”

“…An SAO structure is a syntactically ordered sentence comprising a subject (noun phrase), an action (verb phrase), and an object (noun phrase), and it represents the clear relationship between a subject and an object using an action (Yoon and Kim, 2011). In an SAO structure, S and O may refer to components of the system, and A may refer to functions performed by and on the components (Cascini et al, 2004). For example, given an SAO structure of "soap cleans hands," then "soap" is the S, "clean" is the A, and "hand" is the O.…”

“…Although approaches exist that employ keywordbased techniques mainly based on statistics, i.e., counting term frequencies and identifying specific terms, their main limitation is that they cannot distinguish the role of a component in a technical system (Cascini et al, 2004). In contrast to those keyword approaches, functions can provide more technical information than keyword can, as mentioned above.…”

“…In order to represent the structure of a system in the composition of SAO structures, Cascini et al (2004) developed a system called PAT Analyzer, which applied natural language processing (NLP) to technical documents in order to extract SAO structures. PAT Analyzer enables a functional search for "key concepts" instead of "keywords."…”

SAO-Based Semantic Mining of Patents for Semi-Automatic Construction of a Customer Job Map

“…A Job Map represents the steps for a customer to use a product or service; the customer follows those behaviors in the form [action-object] (AO). This representation form is similar to using a [subject-action-object] (SAO) structure form in theory of solving inventive problem (Transliterated Russian acronym TRIZ) and in the function analysis research fields for abstraction of key concepts [12,13]. The SAO analysis is a method of abstracting and expressing SAO-type structure to effectively organize and express various and large amounts of document data [14,15].…”