Using classified text or images and deep learning algorithms to identify risk of product defect and provide early warning
Deep learning is used to identify specific, potential risks to an enterprise (of which product liability is the prime example here) while such risks are still internal electronic communications. The system involves mining and using existing classifications of data (e.g., from an internal litigation database, or from external sources such as customer complaints, and/or warranty claims) to train one or more deep learning algorithms, and then examining the enterprise's internal electronic communications with the trained algorithm, to generate a scored output that will enable enterprise personnel to be alerted to risks and take action in time to prevent the risks from resulting in harm to the enterprise or others.
1. A method of using classified text and deep learning algorithms to identify product liability risk and provide early warning comprising:
creating one or more training datasets for textual data corresponding to a product liability risk classification;
training one or more deep learning algorithms using said one or more training datasets;
extracting electronic communications related to an enterprise;
applying said one or more deep learning algorithms to said electronic communications to identify and report said product liability risk;
determining if said identified product liability risk is a false positive or a true positive;
re-training said one or more deep learning algorithms if said identified product liability risk is a false positive; and
saving said electronic communications in a true positive database if said identified product liability risk is a true positive.
2. The method of claim 1 , wherein said one or more deep learning algorithms is a framework for natural language processing of text.
3. The method of claim 1 , wherein said one or more deep learning algorithms is a recurrent neural network with a multiplicity of layers and various features, including but not limited to long short-term memory or gated recurrent units.
4. The method of claim 1 , wherein the one or more deep learning algorithms have been trained with different classifiers using previously classified data sourced and provided by a subject matter expert to become models for specific threats or risks.
5. The method of claim 1 , wherein each one of said one or more deep learning algorithms has also been trained with one or more datasets unrelated to the product liability risk.
6. The method of claim 1 , wherein said electronic communications are indexed.
7. The method of claim 6 , wherein each one of said one or more deep learning algorithms scores the data for accuracy with the deep learning model classification of the data.
8. The method of claim 7 , wherein said report said product liability risk comprises providing the scores and related data to one or more designated users.
9. The method of claim 8 , wherein the report may be limited to scores which surpass a specified threshold associated with each of said one or more deep learning algorithms.
10. The method of claim 9 , wherein the report and the indexed data is exported to an existing case management system for investigation and review and possible further action.
11. The method of claim 1 , wherein said one or more training datasets is obtained by mining one or more litigation databases.
12. A method of using classified text and deep learning algorithms to identify product liability risk and provide early warning comprising:
creating one or more training datasets by mining litigation database for textual data corresponding to a product liability;
training one or more deep learning algorithms using said one or more training datasets;
extracting and indexing one or more electronic communications, wherein said electronic communications comprises internal and external communications;
applying said one or more deep learning algorithms to said one or more electronic communications to identify and report any one of said product liability risk;
determining if said identified one of said product liability risk is a false positive or a true positive;
re-training said one or more deep learning algorithms if said identified one of said product liability risk is a false positive; and
saving said electronic communications in a true positive database for evaluation if said identified one of said product liability risk is a true positive, wherein said true positive database provides early warning.
13. The method of claim 12 , wherein each one of said one or more deep learning algorithms scores the data for accuracy with the deep learning model classification of the data.
14. The method of claim 13 , wherein said report said one of said product liability risk comprises providing the scores and related data to one or more designated users.
15. The method of claim 14 , wherein the report may be limited to scores which surpass a specified threshold associated with each of said one or more deep learning algorithms.
16. The method of claim 15 , wherein the report and the indexed data is exported to an existing case management system for investigation and review and possible further action.