Deep learning solution for improved conversational data analysis for distributed customer facing teams

无论业务的部门或规模如何，每天都会通过企业与其客户之间的交互以及内部通信生成大量的对话数据。尽管这些数据具有改善客户体验、业务活动和竞争力的潜在价值，但真正分析内部和外部客户沟通产生的大量电话、电子邮件、网上聊天所产生的复杂互动内容的能力，在目前依赖人工口译进行这一活动的情况下，远远谈不上是最佳的。由于内容差异很大，自动提取沟通含义和意图的能力是一项高度复杂的任务，通过当前的呼叫分析产品或基于人工智能的解决方案(依赖于特定的元数据、关键短语或情绪分析)是不可能的。虽然这种需求早已被认识到，但随着公司寻找新的机会来推动销售，以便在团队/客户之间的传统沟通方式中断和销售团队不同的工作实践中生存，尤其是在B2B环境中，这种需求已显著复杂化。尽管放宽了封锁措施，但许多员工(和部门)继续远程操作，比以往通过数字渠道和电话交付的任务更多，以取代物理交互/面对面销售会议，并且随着大多数行业面临具有挑战性的市场条件，更好地了解客户的需求和更快地响应不断变化的市场机会的需求变得更加关键。通过部署第一个自动对话意图识别系统，该系统能够解释来自任何形式的通信的非结构化通信数据并将其从自然语言转换为结构化数据，而不需要软件专业知识或额外的编码输入，Reiner在这一领域克服了手动实践和新兴的基于人工智能的解决方案的限制。虽然自动解释通信数据的能力现在已经被Reinfer证明了，但在远程工作的销售和客户服务团队中快速传播这一能力还没有。该拟议项目寻求提供的正是这种能力，探索集成到现有CRM系统和通信平台的潜力，例如，跨更广泛的通信渠道提供松散和扩展的功能。如果成功，该解决方案将能够在多个部门产生重大的社会经济影响，支持提高销售和运营效率，并作为不同工作团队的宝贵支持工具。该解决方案可以在支持英国业务复苏和未来增长方面发挥关键作用，并帮助为潜在的“新世界”做准备，在这个新世界中，虚拟客户参与越来越多地取代传统的面对面会议。

Regardless of sector or size of operation, significant volumes of conversational data are generated daily through the interaction between a business and its customers as well as through internal communications. Despite the potential value of this data to improve its customer experience, operational activity and competitiveness, the ability to truly analyse the content of complex interactions generated by the large volume of phone calls, emails, on-website chat generated by internal and external customer communication is far from optimal with a current reliance on manual interpretation to perform this activity. With significant variations in content, the ability to automatically extract both the meaning of a communication as well as the intent is a highly complex task which is not possible through current call analytics products or AI based solutions which on rely specific metadata, key phrases or sentiment analysis.Whilst this need has long been recognised, it has been significantly compounded as a result of the COVID pandemic as companies seek new opportunities to drive sales in order to survive with a disruption to the traditional ways of communicating amongst teams/customers and disparate working practices of sales teams particularly in an B2B environment. Despite the easing of easing of lockdown measures, many employees (and departments) continue to operate remotely with more tasks than ever being delivered by digital channels and phone calls as a replacement for physical interactions/in-person sales meetings, and with the majority of sectors facing challenging market conditions, the need to better understand a client's needs and more quickly respond to evolving market opportunities has become even more critical.Through the deployment of the first automated conversational intent recognition system capable of interpreting unstructured communications data from any form of communication and converting this from natural language to structured data, without the need for software expertise or additional coding input, Reinfer overcomes the limitations of both manual practice and emerging AI based solutions in this space. Whilst the ability to automate the interpretation of communication data has now been proven by Reinfer -- the ability to rapidly disseminate this across remote working sales and customer service teams has not. It is this capability that the proposed project seeks to deliver exploring the potential to be integrated into existing CRM systems and communication platforms e.g. slack and expanding functionality across wider communication channels.If successful, the solution has the ability to deliver significant socioeconomic impact across multiple sectors supporting increased sales, operational efficiencies and as a valuable support tool for disparate working teams. The solution can play a critical role in supporting both the recovery of UK business and future growth as well as help prepare for a potential 'new world' where virtual customer engagement increasingly replaces traditional face-to-face meetings.