|
Cloem is a French company which applies natural language processing (NLP) technologies to patents ("algorithmic patenting"). Cloem creates, then timestamps and optionally publishes, variants of patent claims, called Cloems,〔 using Natural Language Processing technologies. ==Technology== Described by the company's scientists, Cloem technology uses specialized claim parsers, proprietary algorithms to manipulate patents as well as proprietary dictionaries. A patent claim defines a technical invention. Claims define the boundaries of legal protection. A claim is one unique sentence. A parser performs the formal analysis of a sentence. According to Cloem’s approach, one or more words of "base claims" (or "seed claims") are replaced by their synonyms, hyponyms, hyperonyms, holonyms and meronyms. Cloem’s algorithms also include the injection of the definition of terms, thereby disambiguating initial patent claims. Dictionaries are derived from Wordnet, Wikipedia, claim construction dictionaries and the analysis of 70 million patent documents. Grammatical algorithms include the combinatorial permutation of clauses of a patent claim, the handling of time (e.g. causality of events), the transcoding of claim categories (e.g. method claim into system claim and vice-versa) and the creation of intermediate generalizations (by inserting combinations of hyponyms and hyperonyms).〔 Cloem’s claim general drafting model is said to follow industry “best practices” (e.g. USPTO M.P.E.P., EPO Examination Guidelines, Case Law, etc). Cloem optionally implements a proprietary implementation of TRIZ (injection of invention patterns, as identified in the general patent corpus). 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「Cloem」の詳細全文を読む スポンサード リンク
|