If you are following the Oracle Autonomous Mobile and Chatbot Platform announcements you would have now realised that we have announced the availability of the Oracle Digital Assistant platform as a new SKU under the PaaS offerings.
In this post, I will delve deeper into the Oracle Digital Assistant offering and answer what I anticipate will be common questions about the changes.
Building a Multi-Lingual Bot on the Oracle Chatbot Platform
First things first, if you are new to building Chatbot using the Oracle Cloud Platform, here are some quick videos to get you started on the platform and its capabilities. There is also an online MOOC (Massive Open Online Course) available on how to build your first BOT using the Oracle Platform and access the Bot through Facebook Channel.
Now that we understand how to build a bot let’s turn the Bot that can recognise the input from the end user conversing in his/her own language and respond accordingly.
The Bot platform allows you to bring your own translation keys (Google / Bing) and the Bot can be configured to detect the language. The bot further converts the user input to English, intent recognition by the NLP engine kicks off, based on the dialogue flow the bot structures the response in English which is again translated back into the language in which the question was asked by the user.
The latest VBCS 2.0 release makes developing Mobile Applications faster using a declarative drag and drop approach while giving the flexibility to the developer to inspect the code and inject any additional code that the tool doesn’t provide out of the box. You can build your app from the browser itself without the need for any code editor.
“Your call is important to us. Please continue to hold” Does this sound familiar? Imagine the frustration at the other end of the line your customers have to go through while the query might be as simple as “what is my credit score ”?
In this new digital world if a customer has to wait for 15–30 mins to speak to an agent there is something fundamentally wrong with the way an Enterprise operates. Throwing more agents to respond to queries or moving your call center to a developing country is definitely not the way you want to scale and reduce your call time to few seconds. How do we solve this problem? We need an intelligent virtual assistant or a chatbot that can understand the natural language, process the query, talk to one or more systems in the background, aggregate the information from these systems and provide a response instantly so that the customer can easily digest.
In the previous article, I mentioned how we can Dockerise a progressive framework based application (Vue). I have made few improvements to the application where I am now able to perform CRUD operations on the client side using AXIOS, based on API’s available from the server side. I wanted to test these incremental features added to the application and imagine executing those docker commands everytime you make a new component/feature available. This is quite a task. So I was looking at ways to automate the task where every time I commit/push the code to GitHub the build happens automatically so that the latest container is ready for deployment. This is where Docker Hub comes to our rescue. Here are the steps for the automated build process:
Most organisations have to the deal with several kinds of digital artefacts that need publishing on various channels like Web, Mobile, TV, Social, Kiosks, Print, etc. And it is no brainer that organisations need a “Digital Artifacts” repository that can help them to store these digital assets in a centralised repository. Also, it helps them to distribute very quickly on those channels as mentioned earlier to maintain brand consistency and ensure the rights asset displays on the right channel at the right time. However, most often the digital artefacts are produced in partnership with several teams internally and externally (Primarily design agencies). So the Digital Artifact repository is not only a storage container, but also needs to behave like a collaboration platform to engage with all the stakeholders internal and external to the same platform in real-time. To make it bit more complicated imagine the teams producing the digital assets (aka contributors) need to get all the necessary approvals before the artefacts are published or even consumed by different individuals. Given the nature of the organisations, business approvals can come in various shapes. For example, a Digital Artifact that needs to go out on TV for advertising needs a Product Team, a Branding Team, and Legal Team. The product team is responsible for the design of the digital artefact. The branding team ensures the assets produced are consistent with organisations marketing themes. The legal team task is to ensure the teams have done their due diligence and advise the product teams of the Risk level associated with the activities. So a single digital artefact has got its life-cycle, and there are various touch points before it lands on different social or mobile channels. Your Digital Artifact repository that needs to behave like a collaboration platform should also ensure it provides the capability for digital lifecycle management and manages approvals. Fortunately, the Oracle Content and Experience, and Process Cloud platform addresses the exact above needs in a simple, configurable manner. I don’t need to mention the beauty of having such a platform in the cloud as it allows us to just focus on the problem we have at hand than worrying about installation, what kind O/S server/containers, technology skills, scalability, upgrades, etc. You can read more about Content & Experience and Process Cloud platform that fulfils the requirements for Digital Artifact repository, collaboration, and workflow automation. Now that we have the context let’s focus on one of the problems at hand, how do we make the Digital Artifact go through an approval process using these platforms?