In a prior post, I commented on how personal digital assistants and virtual assistants in general work and how they become smart in answering questions. While virtual assistants for businesses work just the same, when choosing a platform, businesses have other aspects to consider. Typically, a business will rely on a virtual assistant platform that allows them to run the same algorithms over a different set of knowledge. Think of a technology company with 100 products and wants to provide a virtual assistant service for each product. Building and coding virtual assistants 100 times is an expensive and time-consuming process. This is where companies such as NoHold come into play with their SaaS platform. Each virtual assistant uses precisely the same NLP, navigation and inference algorithms on every product’s knowledge base. The only difference is the separation of dialog trees, structured hierarchical trees, and meta-data, with the answers available across any virtual assistant or 3rd party app. The rule-based approach, and in particular the NoHold platform, is in my opinion simpler and less costly for creating virtual assistants for businesses. It provides these benefits:
I find this approach simple and more attuned to an enterprise where adherence to processes is important. The rule-based and statistical NLP algorithm offers predictable outcomes that can be retrained easily by non-programmers.
In a way, one can conceivably build 100 Alexa virtual assistants or skills or Google virtual assistants, but the main difference for businesses lies on how you manage knowledge and use it across virtual assistants, without duplication of efforts and without creating intricate code that is difficult to maintain or complex processes to ensure consistency. The authoring console in the NoHold system requires only language and knowledge domain skills, you start with a simple dialog tree and expand it organically with use. You can even get started by importing a Word document. NoHold designed the platform from the beginning with the understanding that the system may not be 100% sure of the answer and therefore allowed for narrowing or expanding the scope of a question, through its inference algorithm. NoHold virtual assistants will give a direct answer if there is only one highly probable answer. If there are multiple equally probable answers or answers that are not highly probable, by asking a simple confirmation to the user, or two, the virtual assistant will get to the right answer. If no answers are available in the knowledge base, the interactions are easily marked so you can continuously and quickly teach the virtual assistant about new subjects or the latest issues. Alternative systems allow developers to code clarifying questions, e.g., when ordering a pizza and user doesn’t give the toppings information, the virtual assistant will ask for the toppings. But it requires developers to implement this and the reason this approach is not scalable when you have dozens or hundreds of products you want to build a virtual assistant for and the same intent could very well apply to multiple products. Disclaimer: I was at NoHold for several years and worked on the conversational assistant platform. NoHold has been carrying on their business of helping customers improve their customer service. As for the 10-point comparison list introduced earlier, here is how NoHold compares:
NoHold was founded in 1999 and launched one of the first modern (SaaS-based) virtual assistant platforms. An exciting and recent development at NoHold is Albert. It provides anyone the ability to create a virtual assistant, teach it from a simple Word document, and NoHold will take care of the rest. See here for more information: http://www.albertai.com UPDATE 12/2017: NoHold can now give your Albert a voice through Alexa or Google Assistant. Comments are closed.
|
Categories
All
Archives
January 2019
|