Biogen Chooses Lexalytics to Improve Customer Care with New AI-Based Text Analytics System

Lexalytics, a provider of “words-first” machine learning and artificial intelligence, announced that it is working with Biogen Japan LTD. to create a system to respond faster and more accurately to questions it receives from patients, the media, physicians, and other constituents at its Medical Information Department (MID). The semi-custom application leverages the Lexalytics Pharmaceutical Industry Pack and combines machine learning (ML) and artificial intelligence (AI) with natural language processing (NLP) to immediately understand what conditions, drugs, ailments or issues a constituent is calling about and deliver a proper response.

When a Biogen constituent calls into the MID, an operator is expected to provide a timely and accurate response. To achieve this goal under the current system, the operator has access to a database of frequently asked questions (FAQs), as well as product information brochures and other resources. If the operator is not able to answer the caller within one minute, the call is escalated to a Medical Director, which is costly for Biogen and frustrating for the caller. By combining machine learning and keyword search in a unified platform, the Lexalytics system is designed to reduce average call time without sacrificing quality of responses, reduce the number of calls that need to be referred to a Medical Director and consolidate the institutional knowledge located in disparate sources and databases, making it available across the organization. 

The new Lexalytics system has been trained using proprietary data from Biogen Japan LTD., including transcripts from call logs, product information brochures and internal FAQ documents. While the system is currently being tested in a call center-type environment, Biogen believes that it shows promise for use at all constituent touchpoints, whether email, social media, chatbots or even a physician’s desk. The initial prototype system represents a transcontinental collaboration which took approximately a month to develop and is expected to be in full production by early 2020. Given the complexity of the Japanese language, Biogen and Lexalytics are confident the success of this pilot can be replicated for other languages and geographies. 

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues
Related Articles

69% Find It ‘Creepy’ When They Receive Ads from Voice Assistants Based on Unprompted Conversations

Global Connected Consumer Index highlights need for marketers to strike a relevancy balance to deliver personalization and brand value without alienating consumers.

Inference Solutions Enables Conversational AI for Cisco’s On-Premise Platforms

Enterprises using Cisco's UC and CC offerings can upgrade their IVRs to Intelligent Virtual Agents without "ripping and replacing" existing software and equipment.

SyncWords Integrates Automated Subtitling and Captioning with Microsoft Azure

SyncWords, a cloud-based video accessibility platform provider for automated captioning and subtitling tools, announced that its solution is now available on Microsoft Azure and uses Azure Cognitive services.

McDonald's to Acquire Apprente, a Provider of Voice Technology

McDonald's buys Apprente--a provider of voice-based, conversational technology--in a move that will integrate new teams with advanced technology skill sets into the McDonald's business.

Sensory Unveils Custom Voice Assistant Platform with Biometrics and Voice Analytics

Sensory's new custom voice assistant platform is a modular, edge- or cloud-based virtual assistant platform that offers companies everything they need to deliver a branded voice assistant ordering experience to customers.