Case Study

- AI Customer Service

Hunk Times - Case Study - AI Customer Service , J-- E-Commerce

2022 Nov

In this AI Customer Service project for J-- E-Commerce, the client plans to implement automatic language recognition and drive various customer service processes for J-- E-Commerce through the customer's voice input. Based on AI technology, AI Customer Service will automatically complete and provide feedback to end-users on the technical and business support they require based on end-user input.
The most important aspect of upgrading the dialogue model between customers and AI is to transform the dialogue model from a question-and-answer to a dialogue-centric, process-based interaction model, requiring the design and implementation of the underlying engine that supports the execution of the process. To meet the needs to support process-based interactions in the dialogue mode between customers and AI, the AI response interaction process needs to be supported in the AI Customer Service; to meet the needs of other process execution within the system, all existing J-- E-Commerce standard processes need to keep seamless interfacing with the AI dialogue function.

Project Information

Service Subscription: The customer is a large E-Commerce service provider, over 580 Million active online commercial buyers, 8 Million active online business buyers, over 500 K active business sellers.

Hunk Times Team Members:
Hunk Times provided full Agile software teams for this project. Includes PM, Solution Architect, Frontend developers, backend developers, UI designers, Business Analyst, etc.
This is a 14 months software projects.

Hunk Times Service Scope:
- Joint solution design with the customer.
- Software detail design
- Frontend and backend coding, QA, CI/CD, maintenance
- Business workflow design

Application Architecture

(In Archimate)

Business Value

Online AI Customer Service Robots
J-- E-Commerce online AI customer service robot is the industry's first large-scale commercial use of emotional robots in the retail, municipal, customer service, medical and other fields have created large-scale application use cases. In all the applications which are working now, J-- E-Commerce online AI customer service robot has achieved more than 90% of the user consultation by the robot to complete the reception, reduce customer service workforce costs, improve service efficiency, to provide users with 7 × 24 hours of convenient intelligent response service.
Semantic recognition and voice recognition both reach 95%+ accuracy rate.

Voice-activated customer service robots
It includes voice answering (automatic transfer) and voices outbound calling (automatic outbound) services, providing services to users with anthropomorphic voice interaction. It is now commercially available on a large scale in e-commerce, logistics, finance, and other industry scenarios.

Intelligent Workstation
We have introduced AI capabilities and upgraded the workstation for manual agents to achieve a significant increase in their efficiency.

Intelligent Dispatch
Optimal scheduling of user inquiries and service resources, reducing user waiting time, improving user experience, and optimizing call centre staff utilization.

Intelligent quality detection
Intelligent conversation analysis tool that extracts risks and business opportunities from conversation text and recordings, helping companies to improve customer service quality and monitor the risk of public opinion.

Competitive Advantage
Nearly ten years of customer service experience, the whole process of intelligent products and equipment, high emotional and intellectual machine service experience, the best practice of seamless integration of human-machine services. Powerful technical architecture supports massive customer service concurrency, hundreds of millions of calls per year 100% safe.

Functions

Overview of **process engine** functions:
1、Load process
2、Execute process
3、Process status record
4、Return execution results
5、Support process refresh

The process engine consists of a process manager and a process executor: the process manager is responsible for loading process data and calling the process executor, the process executor is responsible for executing the process and returning results.

Business Value

Online AI Customer Service Robots
J-- E-Commerce online AI customer service robot is the industry's first large-scale commercial use of emotional robots in the retail, municipal, customer service, medical and other fields have created large-scale application use cases. In all the applications which are working now, J-- E-Commerce online AI customer service robot has achieved more than 90% of the user consultation by the robot to complete the reception, reduce customer service workforce costs, improve service efficiency, to provide users with 7 × 24 hours of convenient intelligent response service.
Semantic recognition and voice recognition both reach 95%+ accuracy rate.

Voice-activated customer service robots
It includes voice answering (automatic transfer) and voices outbound calling (automatic outbound) services, providing services to users with anthropomorphic voice interaction. It is now commercially available on a large scale in e-commerce, logistics, finance, and other industry scenarios.

Intelligent Workstation
We have introduced AI capabilities and upgraded the workstation for manual agents to achieve a significant increase in their efficiency.

Intelligent Dispatch
Optimal scheduling of user inquiries and service resources, reducing user waiting time, improving user experience, and optimizing call centre staff utilization.

Intelligent quality detection
Intelligent conversation analysis tool that extracts risks and business opportunities from conversation text and recordings, helping companies to improve customer service quality and monitor the risk of public opinion.

Competitive Advantage
Nearly ten years of customer service experience, the whole process of intelligent products and equipment, high emotional and intellectual machine service experience, the best practice of seamless integration of human-machine services. Powerful technical architecture supports massive customer service concurrency, hundreds of millions of calls per year 100% safe.