Leveraging Object-Oriented Approach For An Efficient Chatbot Design

With the proliferation of AI, chatbots are evolving as a mandatory enterprise tool. However, it is imperative that they qualify on some “must-have” design requirements e.g. always-on, security etc. This paper presents an architectural approach for an efficient chatbot design which can fully meet these tenets by the use of proxy patterns, based on the OOAD methodology for design, and explains in depth the reasons and advantages of this pattern over others.

Businesses now increasingly focus on enhancing user experience and agile decision making with users being at the core of all business strategies. The user-enterprise relationship has inverted and enterprise boundaries are evaporating.

In order to fulfil these requirements, enterprises need a smart and intelligent virtual assistant or a chatbot. A human-like virtual assistant allows people and websites/mobile devices to engage in intelligent conversations via any interactive channel and in multiple languages. These digital virtual agents are highly contextual, allowing them to adopt any physical appearance or personality.

In principle, chatbots need to embody all the attributes of a next generation smart application such as:

Client-Aware - Adapts to device capabilities (mobile, browser, SKYPE etc.), is responsive to form factors, behaves native and also provides consistent experiences across all channels
Context-Aware - Is aware of user context as well as extreme user personalization
Intelligent - Leverages ML, NLP etc. for human-like conversations with highly contextual response generation
Always On - Works 24/7,365 days a year, while dynamically scaling up/down with user additions or deletions, is auto-scalable and elastic, self-configurable etc.
Security - Has the right security framework to shield sensitive business information since chatbots interact with multiple users like employees, customers and vendors.

So, what should the right architectural approach be - one that encapsulates all of the above? We explore OOAD-based design as a strong candidate for chatbot architecture. Object-oriented design is an old paradigm in enterprise architecture. This can be applied successfully to build a chatbot.

Let’s consider a simple basic use case where a user interacts with a chatbot and the following interaction ensues:

User query is ambiguous and needs more probing from the bot
User ask is understood via query classification and associated intent
User is looking for some information which is available in the back-end systems. Bot needs to invoke cognitive search and provide a contextual response to the user

In an enterprise scenario, cognitive chat capabilities could be built leveraging a homegrown AI stack, or the more prevalent approach of customizing APIs offered by the likes of Wipro HOLMES, IBM Watson, Google, Amazon, etc. An organization may start with a vendor but subsequently move to another. The main reason for this migration could be availability of better AI features, pricing etc. Hence, the chatbot design should use the right architectural pattern to support this migration with minimal or zero disruption in an already established operation. Proxy pattern- a software design pattern, is a solution that is a subset of the larger broker pattern and is highly recommended for a chatbot design.

Proxy pattern: This pattern decouples server from client by the use of an intermediate proxy. Clients (UI) can initiate requests that the proxy can marshal to the server object that renders the cognitive services. The main benefit of this is that since the server can physically reside remotely in other address spaces, apart from the client’s server, this pattern is, by default, suitable for a distributed computing. Another advantage is that the proxy pattern helps to provide a security by shielding the server storing the organization's critical data.

The above scenarios can easily be modelled as a simple sequence diagram to illustrate the types of objects needed to build a chat and their interaction.

Leveraging Object-Oriented Approach For An Efficient Chatbot Design

Figure 1: Chatbot Sequence Diagram

As shown above, the solution needs mainly 5 objects viz. UI, proxy, conversation engine, cognitive search and back end databases. Such object orientation provides a good decoupling between system components. Object internal behaviors can also be modelled assuming they can consume various cognitive services. For example, the below-stated machine is an example of the “Conversation Engine” object shown above. Likewise, another object’s behavior can also be easily captured in a similar way.

Figure 2: Cognitive State Diagram

Benefits of OO design or Proxy pattern for a chatbot:

OOAD is predominantly an event-driven architecture so it always shows the chatbot in an "On" mode. Chatbots can be in different states based on various events.
In any business, the number of users can go up or down. Scalability can be dynamically achieved by object instantiation concept.
Decoupling of cognitive services –Some companies choose to invest in specific AI technologies and customize according to their requirements. Of late, however, we are also seeing enterprises' preferences to select the right partner who can then enable them to make technology decisions best-suited to their landscape. As previously referred in this article, switching from one technology to another is also a reality clients and technology providers must smoothly adapt to. For these reasons, AI vendors should provide API-based cognitive services to ensure modularity and flexibility. Object-driven architecture insulates the architecture from AI services. AI-related APIs are part of individual objects, hence any alteration in the API requires a change in the object’s internal part while the overall architecture remains decoupled from this.
Security - A proxy object acts as a gatekeeper to internal enterprise systems and makes it possible to enforce an organization’s security and authentication policies in one place.
A chatbot is not a standalone entity. It needs to connect to various other sub-systems of an enterprise. For example, a business needs a strong analytics capability of conversations over time or there could be governance-related requirements like security, logging, audit etc. OO-driven architecture allows dynamically adding or deleting objects and each object in turn could represent a sub-system service.
Ease of testing and debugging – A chatbot is built based on various scenarios of user interactions. It is often time-consuming to test and re-design any hierarchical architecture. OO design supports model-driven development and hence it is possible to model the user scenarios and test them as well in simulated mode. It helps to reduce issues associated with deployment too.

Proxy design pattern is easy as well as simple to understand and implement. It is very popular for designing any distributed computing architecture specially as demanded by chatbot requirements. Proxy design pattern plays an important role in helping a software architect in taking decisions in solution design of any kind of chatbot and is a key enterprise tool that no business can afford to ignore.

References:

[1] http://cci.drexel.edu/seniordesign/2016_2017/DrexelChatbot/DrexelChatbotDD.pdf

[2] https://chatbotsmagazine.com/design-framework-for-chatbots-aa27060c4ea3

[3] https://chatbotslife.com/two-ways-to-design-chatbots-1deccd2448df

[4] https://repository.genmymodel.com/beyhosni/chatbot

[5] https://repository.genmymodel.com/suryasingh217/chatbot

About the Author

Manish Okhade -Solution Architect and Pre-sales Lead for the Automation Ecosystem HOLMES™.

With more than fifteen years of experience in engineering services and 4+ years in Artificial Intelligence, Manish has been associated with HOLMES since its inception in the CTO’s office and is instrumental in building complex AI solutions in the Health, Communications and other verticals.

Service Offerings

Client Themes

Service Offerings

Client Themes

Our Global Presence Global Site

Our Global Presence Global Site

Our Showcase Pages Locations

Leveraging Object-Oriented Approach

For An Efficient Chatbot Design

About the Author

Service Offerings

Industries

Digital

HOLMES

Innovation

Contact Us

About Wipro

Location

Leadership

Investors

News and Events

Blogs

Analyst Speak

Partner Ecosystem

Careers

Sustainability

Contact Wipro