HSBC taps Google Cloud for call centre AI
HSBC has enlisted Google Cloud to build a global call centre AI chatbot that helps employees cut down on the time they spend on manually intensive queries.
Working with the customer engineering team at Google Cloud, HSBC built Operational Resilience and Risk Application (ORRA), a FAQ and document search-enabled chatbot.
The bot performs dynamic document search and powers natural conversations with Google Cloud Dialogflow, part of the Google Cloud contact centre AI.
ORRA is accessible to all employees from the HSBC intranet and answers queries on internal policy and framework areas applicable across the bank.
Google says that Dialogflow offers a cost efficient, feature-rich solution for large scale conversational FAQ flow. HSBC created the initial knowledge base consisting of intents, utterances, and answers and used the bulk upload function to load it into the Dialogflow console.
They then worked to finesse intents, train responses, and to create synonyms and entities as well as add smalltalk to humanize the bot responses and to create a “real-world personality”.
Added to this was an inhouse document search capability so that users get direct answers to questions with the flexibility of an app using Natural Language Processing to interrogate large documents for supplementary answers in milliseconds – all through the same UI.
Gareth Butler, head, risk transformation and innovation lead, Asia Pacific, HSBC, says: “In addition to providing rapid access to information, ORRA also brings important benefits for learning and development and the embedding of policies and procedures.
“As query flow increases, the architecture uses machine learning and user feedback to determine the best response to give.”
Steve Suarez, global head, innovation, finance and risk, HSBC, adds: “People go out and use Google to answer questions every day and receive instant, precise responses. Similarly, we’re now getting information to users in a way that feels familiar to them without having to read through an entire policy document.”