Sunday, January 17, 2016

Infrastructure for Global Customer Support

There’s only one affordable way to provide customer support in many languages: deploy a Multilingual Knowledge System (MKS) to access your, primarily monolingual, knowledge base and use the MKS as an information infrastructure for the process and its tools.
The requirements list for global customer support is long. Actually, a product for real global customer support still has to be built. The solution architecture below illustrates how. The chart shows the data flow, the different building blocks, and how the MKS makes them work multilingual.

Listen and Speak to your Customer

In the support section of your web site customers describe their problems, often in their mother tongue. Particularly younger customers might simply write about their issues on social media. Mobile customers want to use either voice or chat to communicate with support. No matter how the customers contacts you, they expect to be answered via the same channel in the same language.

Cross-language Semantic Search

The textual data (in case of voice gained through automatic speech recognition) must be tokenized for the following analytics into words, numbers, special characters, etc. Named entities, measurements, product names, corporate terminology, etc. need to be marked. When retrieved from social media text analytics decides how the information has to be further processed. Ideally the author and customer can be identified in the structured customer data.
The Advanced Linguistic Search (ALS) finds then the relevant information in the Knowledge Base. ALS combined with a Knowledge System searches semantically; combined with a MKS it can also search cross-language.

One Corporate Language, many Customer Languages

The Multilingual Knowledge System enables companies to retrieve knowledge from many languages. On top of Advanced Linguistic Search and MKS an analytic component can answer questions. Only ontology/taxonomy combined with advanced search provides the intelligent responses that customers and agents need. Machine Translation is used when the solution, a question, or dialogue is passed back to the customer in her language.

Support the Support Agent

In many standard case a Question & Answering System can detect that crucial information is missing. It then formulates the respective questions. A dialogue system is customized with domain and company specific templated dialogues. It can talk with the customer.
Today’s maturity level of speech technologies, natural language processing, artificial intelligence, dialogue systems, machine translation, and text analytics cannot handle all situations without human intervention. Luckily it knows when it needs help. It then simply handled the case over to a human agent. At that moment most standard stuff is already dealt with. The agent has all relevant information at hand and can focus on solving the customer’s issue.

MKS, Information Infrastructure for Customer Support

The Multilingual Knowledge System is the central information infrastructure for the global customer support solution. The product knowledge stored in the MKS is used to customize speech recognition, voice generation, NLP, text analysis, and dialogue systems. It tunes the Machine Translation. It provides the multilingual terms and knowledge for the semantic cross-language search in the Knowledge Base.

In order to enhance the company’s Knowledge Base, multilingual Text Analytics combined with the intelligence of the MKS provides quantified information about product and process defects reported in different languages on any media. This helps Product Management to prioritize features or even come up with new ones. It supports Marketing in positioning new product capabilities and understand customer use cases. For all customers, globally!

By Jochen Hummel CEO of Coreon GmbH and ESTeam AB

Tuesday, January 5, 2016

The Needs of Global Customer Support

Nowadays customers interact on many channels and expect a a great experience on each. It has to be fun and satisfying for the international customer base to engage with the company’s brand. The work of support agents has to be made easy and efficient. The systems deployed must effortlessly rise to the business needs.

Going mobile is the current trend driven partly by Social Customer Care favored by millennials. This requires a very flexible SaaS architecture. Information flow and presentation needs to be optimized for the respective channels. For example, for mobile the system needs a minimalistic UI. Hit lists must be very short and have to highlight key information. Automatic dialog systems have to support the most common chat applications. The system needs to tolerate typos and terse social media style language. Some customer might want to use voice instead of typing. Answers have to be short and precise and link to further information.


Know your Customers and Meet their Needs


Companies collect a lot of customer data. Still, customers often have to repeat everything over and over again. Instead, good customer support could sometimes even preempt issues if they would know the customer. Leveraging data stored in ERP systems and having the communication history at hand are key. For new customers social media mining or analyzing peer groups can make the customer known without bothering him with thousands of questions.


Deliver a Personal, Satisfying Self-service Experience

For most people being able to use their mother tongue is a prerequisite for a personal experience. Or simply the only way to communicate efficiently. This requires a localized UI, but also being able to access knowledge using the customers language. Ideally also answers are provided in the customers’ language, at least in a machine translated quality. FAQs should be translated in human quality.


Allow Customers to Share Ideas and Solve Issues

E-commerce wants to benefit from the sharing economy, too. And it should. Often the customers themselves are the best support agents. Companies therefore need to provide an Open Knowledge Base which can be expanded by customers. Giving kudos to contributors or implementing some sort of gamification is often incentive enough for the customer’s efforts. Most customers, though, will use their mother tongue for writing knowledge articles. Thus articles in many languages have to be revised for publication. They need to be retrievable by cross-language search through the Multilingual Knowledge System. Their content has to be machine translated into the customer’s language. Some companies want to translate every article in human revised quality into their corporate language. Articles need to be categorized. Text Analytics can extract invaluable insights.


Support your Agents Optimally

Customers can embarrass support agents, because by simple googling they often know more about the issue than the agents themselves. Therefore, the agents need the same cross-language access to the knowledge base as the customers. In addition they need to have access to the communication history and customer data from the ERP systems. A social media dashboard provides further information about the customer, about their colleagues, friends, or family members and their communication history. For known problems template answers, translated in all languages, should be available.

Don't miss next week's post for a proposed solution...