Automated response to delivery status requests without tracking link
A manufacturer of gaming products with direct sales to end customers is affected by seasonal fluctuations in business. During peak periods (e.g. Black Friday, Christmas sales, discount campaigns, etc.), a large proportion of annual revenue is generated through new or repeat orders. This increased number of orders leads to an increase in downstream customer inquiries in Customer Care. During these peak periods, customer service staff increasingly reach the limits of their capacity. This results in some customer inquiries not being answered or being processed multiple times.
Inquiries are passed manually between agents, which affects the first contact resolution rate (FCRR), response time and ultimately customer satisfaction. In the past, this has repeatedly led to orders being canceled due to long response times.
Industry: Manufacturer of gaming products | Period: 2 weeks | Team size: 1 consultant
Status quo: semi-manual process - complex, slow, error-prone
- Recording: Customer inquiries are sent to the internal CRM system via the website (contact form) with a category or by e-mail without a category.
- Categorization: The ticket created is opened manually by a Customer Care Agent, interpreted and assigned to the appropriate reason for the request.
- Assignment: The ticket must also be manually assigned to the corresponding customer.
- Information procurement: Information (e.g. from ERP, shipping service provider systems, production planning, etc.) must be extracted manually from various peripheral systems.
- Editing: The customer response is written manually using text modules and individually adapted to the respective application.
- Finalization: Finally, the ticket is checked and closed.
“A simple thematic clustering of customer inquiries based on keywords is not enough to differentiate between standard and complex inquiries.”
Automated systems that categorize requests according to keywords quickly reach their limits. A word like “invoice” can mean a simple copy request or a complex complaint. Without context, there is a risk that complex requests will be processed incorrectly or routed to self-service processes, leading to inefficient workflows and frustration.
Instead of pure keyword recognition, intelligent systems are needed that understand formulations in context and automatically differentiate between standard and complex inquiries. This is the only way to make customer service efficient and customer-oriented.
Customer care automation with communications mining
A typical example from the retail sector. In this case, the customer expresses two concerns: a service request (“reset password”) and an information request (“order status”).
With classic routing engines, this email would either be pre-classified exclusively as “reset password” or as “order status”. To overcome this challenge, an artificial intelligence (communications mining) must be able to analyze the text, recognize the customer’s intention and mood and ideally send automated feedback to the customer describing the next steps.
In order to automatically process unstructured customer inquiries that are received via contact forms or emails, these inquiries must be structured and pre-classified according to the reason for the inquiry. So-called mixed orders can arise, particularly in the case of inquiries that allow free text.
Receive request and recognize customer intent
Automated clustering for a deeper understanding of requests
Communications Mining is either connected directly to the exchange server in Customer Care or filled with historical data. Once the data connection has been set up, an algorithm based on artificial intelligence (unattended learning algorithm, optimized for end customer communication) is launched. This algorithm forms clusters that group repetitive processes, requirements, problems or moods, for example. The result is an AI-supported analysis of the emails, clustered according to the reason for the request. Mixed requests are assigned to several categories and can be identified in the analyses, for example by overlaps in a treemap.
From data overload to efficiency - automation with a system
It is not possible for Customer Care to manually read, understand, classify and process emails in real time in order to use this data as a basis for decision-making. Example: Without communications mining, it is difficult to recognize that an increased volume of inquiries may be due to an error on the customer website. The enormous amount of data in Customer Care can neither be effectively classified nor processed in interactive dashboards without technical support. With communications mining, however, the division is able to use the data efficiently, implement specific automation solutions for individual reasons for inquiries or make well-founded decisions for day-to-day business, such as resource planning.
A robot process can be started for each category or mixed category. The information extracted from the emails – such as customer numbers, order numbers or email addresses – is transferred directly to the robot to continue processing automatically. The selection of a suitable process for automation is based on various criteria, such as the complexity of the request, variations in processing, development effort and processing frequency. With communications mining, statistical data such as the frequency of a specific request, processing times and response times can be used to identify the most promising automation candidates.
Methods such as process interviews, workshops and shadowing are also used to assess process complexity. The result of this procedure is a prioritized, weighted list of customer inquiries that are best suited for automation.
Low-code automation with UiPath robots
Robots are configured for the identified request reasons using the UiPath low-code automation platform, which take over the manual activities of the service employees. In this project, the missing delivery status due to invalid tracking information in the confirmation email to the customer was prioritized as the most important reason for the request.
To provide a precise response to a tracking request, the robot uses the information extracted from the emails to search for the required data in the relevant peripheral systems. Using the combination of email address and customer number, the robot can retrieve the original order information via an API in the ERP system. The production and delivery information is identified there. This automated process ensures that customer inquiries are processed efficiently and error-free, while reducing the workload on service staff.
The robot determines the current production status of the order. If there are bottlenecks in the production process, it uses a predefined text module, supplements it with customer-specific information and sends a corresponding response email.
Once production is complete, the robot retrieves the delivery information. Using the graphical user interface of the delivery service (e.g. DHL), it logs in with the retailer account, searches for the shipment and extracts the current tracking information. This information is used to inform the customer of the status of their delivery and provide a tracking link for self-service.
Modules used from the UiPath platform
UiPath Robot
Robot that follows a predefined script for the automatic execution of business processes and can interact with various peripheral systems via interfaces or the user interface. This robot is operated on a virtual machine or physical machine at the customer’s site and is to be regarded as a virtual employee.
UiPath Studio
Low-code development environment for the robot with numerous out-of-the-box connectors to peripheral systems such as SAP, O365, Zendesk, Celonis and many more, as well as the option of integrating the results from the UiPath platform into the robot
UiPath Document Understandig
Module for classifying and understanding documents with artificial intelligence. By training the documents, an AI model is created for a specific document category. This model is able to recognize tables with different numbers of lines, for example, and read the content correctly. A combination of OCR and AI is used to recognize characters and information.
Your advantages at a glance
Automation significantly reduces processing times for complaints, allowing your customer service team to respond to customer concerns more quickly.
The use of automated systems minimizes the susceptibility to errors when entering and assigning complaint data, which leads to more reliable problem solving.
The automation process pays for itself quickly and leads to noticeable cost savings in the operating budget, maximizing the return on investment.
Employees have more time to deal with complex customer inquiries or strategic tasks instead of dealing with routine complaints processes.
The solution is adaptable and scalable so that future process changes or increasing numbers of complaints can be easily covered.
The automatic assignment and processing of complaint cases in your existing SAP system ensures efficient internal communication and documentation.
The low-code technology enables rapid implementation and adaptation, so that your team benefits from optimized processes more quickly.
Contact us now without obligation and request a personal demo appointment
- Understanding the solution: Learn more about the functions and possibilities
- Discover added value: Identify benefits specific to your business.
- Live insights: Experience the solution in action.
- Clarify questions: Discuss your requirements with our experts.
TISAX and ISO certification for the Munich office only
