Mining Ideas from Text

Fraunhofer INT

Application

The identification of technological solution ideas is important for the technological development process and the identification of new product ideas from consumers is important for new product development process in a company. Idea mining is defined as the process of extracting these new and useful ideas from unstructured texts. Unstructured texts come in many shapes and sizes: internet web sites, articles, reports, newsletters, blogs etc.

Problem: The manual extraction of ideas from texts is time and cost consuming because of the huge amount of textual information.

Solution: We introduce a (semi-) automated idea mining approach for finding new ideas in unstructured texts. Our approach follows the statements of technique philosophy. Therefore a new idea, invention or innovation represents not only a new mean, but a new purpose and mean combination. By systematic analysis of the purpose and mean combinations in new texts compared to specialized reference collections, an automatic collection of new ideas and inventions can be realized.

Case Study

Approaches and case studies are published in

Thorleuchter, D., Van den Poel, D.: Web Mining based Extraction of Problem Solution Ideas. Expert Systems with Applications, 40 (10), 2013, 3961-3969.

Thorleuchter, D., Van den Poel, D., Prinzie, A.: Mining Ideas from Textual Information. Expert Systems with Applications 37 (10), 2010, 7182-7188.

Thorleuchter, D., Herberz, S. and Van den Poel, D.: Mining Social Behavior Ideas of Przewalski Horses. In: Yanwen Wu (Ed.) Advances in Computer, Communication, Control and Automation. Lecture Notes in Electrical Engineering 121, Springer, Berlin, pp. 649-656, 2012.

Thorleuchter, D., Van den Poel, D.: Extraction of Ideas from Microsystems Technology. In: David Jin, Sally Lin (Eds.) Advances in Computer Science and Information Engineering. Advances in Intelligent and Soft Computing 168, Springer, Berlin, pp. 563-568, 2012.

Thorleuchter, D., Van den Poel, D.: Using NMF for Analyzing War Logs. In: N. Aschenbruck et al. (Eds.): Future Security 2012, Communications in Computer and Information Science, 318, Springer, Berlin, pp. 73-76, 2012.

Thorleuchter, D., Van den Poel, D. and Prinzie, A.: Extracting Consumers Needs for New Products. In: Proceedings of WKDD 2010, IEEE Computer Society, Los Alamitos, CA, pp. 440-443, 2010.

Thorleuchter, D.: Finding technological ideas and inventions with text mining and technique philosophy. In: Schmidt-Thieme, L. (editor): Data Analysis, Machine Learning, and Applications. Springer, Berlin-Heidelberg-New York, pp. 413-420, 2008.

Contact us if you would like to identify new ideas for your company.

Idea Mining Tools

Here we demonstrate our "Technological Idea Miner" application. Ideas can be identified from provided texts.

"Technological Idea Miner"


Here we demonstrate our "Idea Web Miner" application. Ideas can be identified from the internet.

"Idea Web Miner"


Here we demonstrate our "Idea Patent Miner" application. Ideas can be identified from patent data.

"Idea Patent Miner"


Here we demonstrate our "Idea News Miner" application. Ideas can be identified from internet news articles.

"Idea News Miner"


Here we demonstrate our "Product Idea Web Log Miner" application. Ideas can be identified from internet blogs.

"Product Idea Web Log Miner"