This blog article is part of our RPA (Robotic Process Automation) blog series and deals with the underlying opportunities of AI (Artificial Intelligence) enabled RPA in an ERP ecosystem. Learn how to overcome the boundaries and boost the capabilities of RPA, how a Chatbot automates master data management, and how to implement a Chatbot in an RPA and ERP system.
Chatbots, simulate and automate human conversation through voice commands, text chats or both. They can be used through messaging applications or web pages and are naturally deployed in dialog systems for various application fields (e.g. customer service). The boom of AI enables smarter Chatbots understanding unstructured human input by applying natural language processing (NLP).
How to further increase the potential and overcome the limits of RPA?
In the recent years, RPA has been one of the most impactful technologies in process automation in all kind of organizations. Most of the RPA systems rely on structured data, static rules, and a recurrence of events. They capture structured data based on the rules engine to perform the pre-defined workflows. However, the static setup does not allow processing of unstructured data. AI is the needed game changer and adds an intelligence layer on top of RPA systems so that they can handle unstructured data thanks to their dynamic rule set. Then RPA will be able to manage exceptions, and the system improves itself after further training. AI can derive sense out of unstructured data and deliver the now structured data to the existing RPA systems. Algorithmisation is the process cycle of gathering of information out of (unlabeled) data for Machine Learning (to derive the meaning out of it) and creates new processes plus data for further processing again. Chatbots integrated into existing RPA & ERP ecosystems can provide structured data out of the human conversation for the processing of the back-end systems.
How can Chatbots support in Master Data Management?
Let’s see how Chatbots can further optimize the master data management processes. Often the employee needs to manually structure the unstructured customer input (e.g., email, phone) before it can be automatically processed by RPA. A Chatbot would offer a natural way for the customer to directly change his master data without the need to find the right account settings or form. It also facilitates back-office employees and they can focus on exception handling or more value-adding tasks. The single automated communication channel saves time for both.
Possible use cases are ranging from simple ones such as an update of the name, postal or email address, phone number etc. to more complex ones where more data needs to be analyzed by the AI. For instance, the change of order details, contract data, authentication method or the request of the FAQ. A text Chatbot should be implemented before a Voicebot since it needs the same underlying logic system and voice integration is more complicated. All mentioned use cases have several benefits in common:
- Direct Plug-in between different systems (same front-end)
- Scalable AI and RPA capabilities (from simple to complex use case)
- Best of both: Combining strength of AI (unstructured data) and rule-based RPA
- No human interaction required in the whole process
From the customer front-end in the beginning to the update in the back-end systems, everything is automated from end-to-end.How can a Chatbot with RPA and ERP integration be set up?
Within eight weeks we developed a tangible AI MVP (minimum viable product) for automatic master data updates starting with the chat as an input channel and the customer’s wish to change the postal address. We utilized IBM Watson and its conversation as services for the NLP capabilities of the Chatbot. It is entirely integrated into an existing UiPath and SAP system, but could also work with other RPA/ ERP software.
Successful execution requires an end-to-end expertise due to the various tasks. Capgemini as a Group is delivering the Chatbot MVP as a team of experts from multiple fields:
Consulting Services (Capgemini Invent):
- Leading overall agenda and bringing in experience in RPA, ERP, and digital customer journeys
- Use case creation, functional and business specifications, setup of UiPath and SAP workflow, and agile project management
Technology Services (Capgemini – IBM Watson Team):
- The Capgemini APPS – IBM Watson Team is responsible for the Development of the AI conversational service, core application, and the front-end development
Business Services (Capgemini):
- Focus on combining RPA and AI and the seamless integration of the interfaces
Experience Design Services (Idean):
- UI design and visualization of the Chatbot characteristics
Further competencies with additional complimentary 3rd party software partner, Capgemini Consulting or the client are working with, can be brought in depending on the specific requirements and client setup.
Based on our experience we suggest four months to implement a Chatbot into a live environment. Our MVP took us two months, but integration into a live back-end system and the training of the NLP capabilities would require two additional months.
Starting from a hands-on and easy to realize use case more feature-rich ones are in our pipeline. For example, Chatbots for customer complaint management (including predictive analytics), Machine Learning for customer credit assessment or Deep Learning enabled image analysis and knowledge engineering for automatic handling of customer order entry.
What are the main points of adding AI to RPA?
- Direct integration of Chatbots into existing RPA & ERP systems offers additional customer value besides organizational benefits
- AI is the new UI: Chatbot is the new user interface (UI) for people to interact in a faster and natural way with their corporate provider. The shown use case is only the beginning, and with more added features the convenience, but also complexity will rise
- To maximize the value of smart automation, a holistic approach to process automation and an end-to-end expertise is required. Only including experts with the right variety of skill sets and knowledge ranging from business, technology to data science can guarantee success
Take the chance to add an intelligence layer on your existing RPA and ERP systems for a smart end-to-end automation and break through the boundaries of unstructured data. Start the journey from digitization to algorithmisation!
This article was written by Julia Keller.
Find out more about this topic:
- Part 1: Center of Excellence & Operating Models: Why RPA is more than just a software
- Part 2: Value for money with RPA. Lessons learned from RPA audits.
- Part 3: The robot user-ID: handling RPA within existing rights & permissions structures
- Part 5: Next Generation KYC: Why RPA constitutes a crucial success factor for financial institutions’ KYC digitization