Skip to the content

Machine learning digital assistant (chatbot)

RS Components – Chatbot

RS Components, the number one high-service distributor of electronics and maintenance products across Europe and Asia Pacific.

RS Components, the number one high-service distributor of electronics and maintenance products across Europe and Asia Pacific.

Task

Create a foundation on which disruptive new customer interfaces could be build, therefore contributing to RS Components’ long-term strategic goal to be the market leader in customer experience.

How we did it

H&C partnered our machine learning experts with the in-house innovation department, customer service specialist team and sales team to form a comprehensive taskforce.

Collaboration

We held a workshop for the entire taskforce and discussed different approaches. After reaching a collaborative consensus, we established initial user stories to guide the development process.

Build

We build the prototype chatbot framework, which was tested by users. From this we went through iterative stages to hone and improve, all the while building on user feedback. A staged rollout to the market gathered early market feedback.

Tech

The main technical challenge of this project was the creation of an intelligent chat system. Unlike conventional software, this challenge needed a two-stage development approach of training followed by runtime-operation.

To solve the intelligent chat challenge, we used Diagflow and machine learning to create a chatbot harness, which used annotated chat templates and transcripts from real-life user interactions with customer service. This allowed us to develop a solution capable of maintaining context throughout multiple interactions. It can also clarify user information and answer customer requests by leveraging upstream systems.

Increased capability and accuracy of the intelligent chat system will be achieved using a self-learning system. This uses each and every interaction to expand its training set, making the system smarter and more resilient as more customers use it.

Impact

The chatbot aims to increase customer satisfaction by providing faster responses, constant 24/7 availability and lower overall support costs when compared to human agents.

Methodology RS_2 Created with Sketch. Learning Improvements Dialog Flow & Machine UX Improvements CONTINUOUS DELIVERY Chatbot MVP Framework RS – Digital Assistant Layer RS Data Processing ALPHA Hack and Craft RS Team Team members PROJECT ROADMAP 3. Scale 2. Development 1. Ideation
Dev RS_2 Created with Sketch. RS CHATBOT AI & MACHINE LEARNING TRANSCRIPTS SERVICE INTERACTIONS USER – CUSTOMER INFORMATION PRICE, STOCK AND ORDER INFORMATION PRODUCT RS Components

All case studies

Close

Outro

Science and technology are the principal drivers of human progress. The creation of technology is hindered by many problems including cost, access to expertise, counter productive attitudes to risk, and lack of iterative multi-disciplinary collaboration. We believe that the failure of technology to properly empower organisations is due to a misunderstanding of the nature of the software creation process, and a mismatch between that process and the organisational structures that often surround it.