Cognitive Platform Sharpens Focus on Unstructured Data
Big data platform vendors are increasingly focusing on churning through unstructured data, especially for text, audio and even security applications like insider threat analysis. Among the companies emerging in this industry segment is Digital Reasoning, a well-connected cognitive computing company that has helped the U.S. military track terrorists online while working with financial markets to spot insider trading.
The company, which recently expanded beyond the Capital Beltway to Nashville, rolled out the latest version of its Synthesys cognitive computing platform this week that combines machine learning, natural language processing, computer vision and pattern recognition. The combination is intended to boost the quality of unstructured data analysis while reducing the amount of time needed to get the desired results.
Version 4 of the Digital Reasoning platform released on Tuesday (June 21) is based on proprietary analytics tools that apply deep learning neural network techniques across text, audio and images. Synthesys 4 also incorporates behavioral analytics based on anomaly detection techniques.
The upgrade also reflects the company’s push into user and “entity” behavior analytics, a technique used to leverage machine learning in security applications such as tracking suspicious activity on enterprise networks and detecting ransomware attacks. “We are especially excited to expand into the area of entity behavior analytics, combining the analysis of structured and unstructured data into a person-centric, prioritized profile that can be used to predict employees at risk for insider threats,” Bill DiPietro, Digital Reasoning’s vice president of product management noted in a statement.
The platform’s language translation capabilities also have been expanded to include Spanish and Chinese (although the company did not specify if the latter included Mandarin, so-called “simplified” Chinese, or both). The language capabilities do come with syntactic parsing.
Targeting data scientists, the upgraded platform also integrates the ability to conduct interactive data analytics via local data exploration along with the ability to import or export results to third party databases and visualization tools.
The latest version also adds support for Elasticsearch to enable advanced indexing and data exploration across Cloudera Enterprise, HortonWorks, MapR and other Hadoop distributions, Digital Reason said. The goal is to help exploit unstructured data in real time.
The company is betting that the upgrades will help boost adoption of cognitive computing technology by demonstrating how the platform learns from context. It also cited improved tools for exploring the results of its cognitive algorithms and knowledge graphs.
The text mining and text analytics platform is billed as continually learning from context, thereby overcoming the “I-don’t-know-what-I-don’t-know” problem the company claims is common among other analytics tools.
Along with Defense Department agencies, Digital Reasoning also works with financial markets, including the Nasdaq stock exchange, on surveillance and monitoring technologies. Financial markets are increasingly turning to cognitive computing platforms to ferret out insider trading and other illegal schemes.