Fig 7 - uploaded by Gaetano Cascini
Content may be subject to copyright.
Source publication
Patents are gaining a growing importance as a complementary source of technical information, since the information they disclose is not accessible in scientific and technical literature. Text mining technologies are emerging as a possible solution to increase the efficiency of patent analysis activities; besides, most of the existing systems are de...
Similar publications
Background
Various monitoring approaches have shown that urban areas and their energy systems are major contributors to climate change. Corresponding observations have mostly been based on physical data. However, text data is an untapped source of information that can be analyzed by text mining methods. Taking the example of the German Energy Trans...
Citations
... A cooccurrence graph is a powerful technique to represent semantic relations. Hence it is used to identify relevant technical parameters for a certain domain by comparing thesauri automatically extracted from patents (Cascini et al., 2011). A more generalized semantic network TechNet is specifically trained on larger technology related data sources compared to WordNet and ConceptNet, which are more broad based and lesser engineering centric (Sarica and Luo, 2021). ...
Representation of design information using causal ontologies is very effective for creative ideation in product design. Hence researchers created databases with models of engineering and biological systems using causal ontologies. Manually building many models using technical documents requires significant effort by specialists. Researchers worked on the automatic extraction of design information leveraging the computational techniques of Machine Learning. But these methods are data intensive, have manual touch points and have not yet reported the end-to-end performance of the process. In this paper, we present the results of a new method inspired by the cognitive process followed by specialists. This method uses the Knowledge Graph with Rule based reasoning for information extraction for the SAPPhIRE causality model from natural language texts. Unlike the supervised learning methods, this new method does not require data intensive modelling. We report the performance of the end-to-end information extraction process, which is found to be a promising alternative.
... A co-occurrence graph is a powerful technique to represent semantic relations. Hence it is used to identify relevant technical parameters for a certain domain by comparing thesauri automatically extracted from patents (Cascini et al., 2011). A more generalized semantic network TechNet is specifically trained on larger technology related data sources compared to WordNet and ConceptNet, which are more broad based and lesser engineering centric (Sarica and Luo, 2021). ...
A Knowledge Graph and Rule based Reasoning Method for Extracting SAPPhRE Information from Text
Representation of design information using causal ontologies is very effective for creative ideation in product design. Hence researchers created databases with models of engineering and biological systems using causal ontologies. Manually building many models using technical documents requires significant effort by specialists. Researchers worked on the automatic extraction of design information leveraging the computational techniques of Machine Learning. But these methods are data intensive, have manual touch points and have not yet reported the end-to-end process's performance. In this paper, we present the results of a new method that uses the Knowledge Graph with Rule based reasoning for information extraction for the SAPPhIRE causality model from natural language texts. Unlike the supervised learning methods, this new method is not data intensive. We report the performance of the end-to-end information extraction process, which is found to be a promising alternative.
... The achieved structured information represents an index about the complexity of the patent and the pertaining degree of inventiveness in the perspective of identifying the possible evolution patterns of the studied technical systems. The objective of assessing the evolution trajectories is strengthened by the automated building and confrontation of thesauri concerning different technical fields [17]; this kind of algorithm also allows to build ontologies with entities and related relationships and map key problems of the investigated field. ...
The growing complexity of technical solutions, which encompass knowledge from different scientific fields, makes necessary, also for multi-disciplinary working teams, the consultation of information sources. Indeed, tacit knowledge is essential, but often not sufficient to achieve a proficient problem solving process. Besides, the most comprehensive tool of the TRIZ body of knowledge, i.e. ARIZ, requires, more or less explicitly, the retrieval of new knowledge in order to entirely exploit its potential to drive towards valuable solutions. A multitude of contributions from the literature support various common tasks encountered when using TRIZ and requiring additional information; most of them hold the objective of speeding up the generation of inventive solutions thanks to the capabilities of text mining techniques. Nevertheless, no global study has been conducted to fully disclose the effective knowledge requirements of ARIZ. With respect to this deficiency, the present paper illustrates an analysis of the algorithm with the specific objective of identifying the different types of information needs that can be satisfied by patents. The results of the investigation lay bare the most significant gaps of the research in the field. Further on, an initial proposal is advanced to structure the retrieval of relevant information from patent sources currently not supported by existing methodologies and software applications, so as to exploit the vast amount of technical knowledge contained in there. An illustrative experiment sheds light on the relevance of control parameters as input terms for the definition of search queries aimed at retrieving patents sharing the same physical contradiction of the problem to be treated.
