Patent mining

In this research, network analysis is applied to examine smart building patents to find the most effective technologies and novel opportunities for innovation. Core–periphery structure is the main analysis method deployed to exploit the most effective patents in the core network as basic inventions in smart building technologies, and also to explore the periphery network for novel opportunities to develop new technologies.

Composting technology (CT) is a bridge between organic waste and soil carbon pool, which also a critical technology on the sustainable development of agriculture. Although some attempts have been made to address the CT assessment, technical details are not yet available; this brought difficulties in predicting the development directions. Here, patent measurement was used to analyse the structured and unstructured scripts of 11,701 composting technology patents (CTPs) in the Derwent Innovations Index database. It was discovered that the history of CT could be divided into the budding stage (1970e1989), the developing stage (1990e2006) and the expanding stage (2007e2019). Environmental policies are highly related to CT development. China authorised the most CTPs, accounting for 43.89% of the world's total. The World Intellectual Property Organization and the European Patent Office made a significant contribution to patent flow. The co-words analysis suggested that the technological aim of CT has shifted from waste disposal to organic fertiliser preparation. Cluster analysis sectored CTPs into 42.76% of which focuses on the composting device. Through the mining results and literature reviews, the subject of using mineral in compost, anaerobic fermentation, new microbial strain, straw composting and preparation of high-efficiency organic fertiliser were the potential research directions. This study investigated the history of CT and predicted possible trajectories that could be informative to eliminate repetitive and subsidiary horizontal innovations.

Patents are valuable source of knowledge and are extremely important for assisting engineers and decisions makers through the inventive process. This paper describes a new approach of automatic extraction of IDM (Inventive Design Method) related knowledge from patent documents. IDM derives from TRIZ, the theory of Inventive problem solving, which is largely based on patent's observation to theorize the act of inventing. Our method mainly consists in using natural language techniques (NLP) to match and extract knowledge relevant to IDM Ontology. The purpose of this paper is to investigate on the contribution of NLP techniques to effective knowledge extraction from patent documents.  We propose in this paper to firstly report on progress made so far in data mining before describing our approach.

Patents are increasingly of great importance to innovation performance. A patent document is an important source of technological knowledge where artifact evolves according to problems and partial solutions. This paper reports on an on-going research whose goal is to provide design engineer with an efficient patent mining tool that re-structures a patent corpus in a problem graph to better highlight state of the art of  given field of knowledge. The methodology employed to achieve such a functionality is based on a NLP method that manage both IDM-TRIZ concepts and patent corpuses contents. The paper also presents a case study in steel making industry to illustrate the methodology.

This paper presents a new approach for knowledge extraction from patent document for the use of design engineers. It is based on the Inventive Design Method (IDM) which derives from TRIZ, the theory of inventive problem solving whose goal is to theorize about the act of inventing partly on the bases of patent’s observation. The purpose of this paper is to demonstrate that it is possible to au-tomatically extract IDM concepts from patent document, using generic linguistic markers. This paper which is the continuation of a previous work, it mainly focus-es on the retrieval of parameters which characterize the main components of con-tradictions related to an artifact evolution bottlenecks.