Contextualize Trusted Data with MECBot’s Smart Knowledge Graph

The term Knowledge Graph is making heads turn in the data science and business fraternities today. But, most of us are already using the Knowledge Graph without realizing it. The world’s no. 1 search engine, Google, for example, has been using graph-based knowledge mapping to organize, rank, and interlink search results for several years now. The increasing relevance and accuracy of Google’s search results owe it all Knowledge Graphs.

We, at FORMCEPT, are one of the first big data analytics companies to deploy Knowledge Graphs to store, retrieve, and update data. This article demystifies Knowledge Graphs, demonstrates their usage in MECBot, and helps to visualize the unique advantages that MECBot’s Knowledge Graph imparts to businesses.

Companies like Airbnb and LinkedIn Are Benefiting from Knowledge Graph. With MECBot, Now Every Enterprise Can Do It.

Let us consider a few examples to understand the benefits offered by Knowledge Graphs to businesses. Airbnb, for instance, is a global leader in shared accommodation across travel destinations that uses a graph structure to encode information about the world and the business inventory. This Knowledge Graph is made up of a hierarchical taxonomy wherein concepts (for example, ‘surfing’ or ‘sport’ under adventure activities for tourists), are represented as nodes. Relationships between the concepts (for example, ‘surfing is a sport’) are represented as edges. Thus, Airbnb tags its inventory of ‘Homes’, ‘Experiences’, and ‘Places’ with concepts from this taxonomy. The Knowledge Graph is built within the Airbnb service framework. The benefits of such a system are multifold – the Knowledge Graph helps users to find specific places, homes, and even experiences that they might be looking for. Thus, the Knowledge Graph contributes to the overall flow of travel booking through deep insights and actionable intelligence. It also helps improve guest and host experiences at Airbnb.

For LinkedIn, the social media network for global professionals, the Knowledge Graph is made up of entities such as ‘members’, ‘jobs’, ‘titles’, ‘skills’, ‘companies’, ‘geographical locations’, ‘schools’, and so on. The relationships between these entities form the basis on which LinkedIn’s knowledge graph operates. Relationships exist among more than 467 million members, 290 million jobs, and 9 million organizations. There are two types of entities. The first type is made up of organic entities, which are generated and maintained by users, for example, ‘members’, ‘premium jobs’, and so on. The second type is made up of auto-created entities which are made by mapping member entities. There are tens of thousands of ‘skills’, ‘titles’, ‘companies’, ‘certificates’, and so on which can be mapped on to existing and new member entities. The knowledge graph is beneficial to members on LinkedIn in that it brings more value to members, for example, by suggesting skills, groups, and connections that will benefit their profiles, even to the extent of 3rd-degree member connections and profile recommendations. Another way in which it brings value to LinkedIn is by auto-generating a personalized professional summary based on entities and recommends it to users who do not have a standardized profile. This is extremely helpful in cases of job search or job recommendations.

Thus, Knowledge Graphs are extremely valuable to support the decision and process augmentation based on linked data. This is also made evident through the fact that Knowledge Graphs have been identified by Gartner as new key technologies in their Hype Cycle for Emerging Technologies in 2018.

But is Knowledge Graph only for Tech-Savvy Companies with Deep Pockets? NO - Enter MECBot. 

MECBot overcomes the key challenges of traditional databases by deploying Knowledge Graphs, and making the entire unified analytics solution affordable to all enterprises anytime, anywhere for collaborative big data analytics within the enterprise team. The inside of a traditional database is absolute chaos. Even if relationships between some data points are known, much of the data is not part of an overarching relationship web. This leads to two major problems:

  1. Insights generated from traditional databases are obtained in a siloed manner, giving only a partial picture. In most cases, crucial data points are lost because relationships are not identified, and therefore, the partial picture tends to be inaccurate, leading to erroneous decision-making.
  2. Data points and relationships in traditional databases are not updated in real-time. Therefore, with long data-to-decision cycles, the insights generated are already obsolete by the time a decision is made and put into effect.

Both these shortcomings are effectively removed when enterprise information is organized and contextualized as per the business domain or ontology and a Knowledge Graph is created. Knowledge Graph demonstrates, analyzes, and mines every facet of the data and helps unravel the most useful and accurate insights, and therefore, is invaluable to organizations in decision-making. If the information within a traditional database does not relate to the business entities, it is incomplete, inaccurate, and leads to time-lags and poor decisions. To find the most important and relevant information effectively in real-time within the right context is where Knowledge Graphs come in. It preserves its lineage through versioning, maps relationships, and ontologies, and refreshes these data and relationships in real-time by updating the graph.

In MECBot’s Knowledge Graph, data takes the back-seat, while relationships between the data arefirst-class citizens.” The value generated in a Knowledge Graph, therefore, is by linking information to generate coherent insights. Also, since graphs are highly versatile and flexible formal data structures, all the available data formats can be easily converted into graphs using standard tools. In MECBot, these tools are embedded into an automated functionality that underlies the data ingestion process and converts all ingested data instantly into graph format without any coding by the user.

MECBot’s Augmented Data Fabric Uses Knowledge Graph to Answer the Burning Questions in Business Decision-Making


MECBot Data Fabric

  • How can businesses attain cost leadership through improved productivity, higher efficiency, and reduced cost-to-serve?
  • How best can enterprises improve the quality of their products and services, while reducing the time-to-market?
  • How can businesses create and distribute highly personalized communication and marketing campaigns?
  • How can marketers and product managers target the right product for the right customer?
  • What steps should marketers and CXOs take to maximize brand loyalty and boost customer lifetime value (CLV) manifolds?

Explore our use-case on how MECBot powered a Fortune 500 company to optimize cash management in ATMs using semantically enriched Knowledge Graphs.

The Journey from Meaningless Data to Contextualized Information with MECBot

One of the most impressive characteristics of Knowledge Graphs is the constant churning of meaning. Knowledge Graphs are semantically enriched - i.e. they can augment data by connecting with its domain of origin and enhance its meaning by extracting the implications of this domain. Domains can also be user-defined, making Knowledge Graphs incredibly powerful in understanding user-generated inputs and queries.

Contextualization is a key component in the analysis of unstructured data. Let us take an example: if a page of unstructured text data is given to an analytics platform on the topic ‘Taj Mahal’, the platform has to be able to mimic human reasoning to identify whether that page of content is talking about ‘Taj Mahal’ - the historical monument or ‘Taj Mahal’ - the premium brand of tea. While this is a very basic example, without deep contextualization any analytics performed on unstructured data is meaningless.

Read our use case on smart EVSE management by MECBot by deploying industry-scale Knowledge Graph at one of the world’s largest networks of EV charging stations.

Ink is a unique feature of MECBot geared to clean, analyze, contextualize, and unify unstructured data with structured data in a seamless manner in real-time. Powered by a state-of-the-art Knowledge Base that is based on the concepts of Linked Data, MECBot Ink can understand various domains and semantics across industries by enhancing the existing Universal Knowledge Base with Domain and Tribal Knowledge. MECBot’s real-time Annotation Engine detects contextual keywords/phrases in unstructured content at blazing speed and fosters deep knowledge of annotated keywords and phrases, backed by Deep Context hierarchy for on-the-fly disambiguation. With its easy-to-use and intuitive interface, annotations at scale can be explored and structured as per the business model anytime, anywhere.

From Static Data Mining to Dynamic, Actionable Intelligence - Bridging the Time Gap with MECBot

Let’s face it: historical data is like stale food - it has minimal nutritive value for enterprises and decision-making. Knowledge Graphs beat time-lags by staying hydrated with new data and insights seamlessly. They allow performing cutting-edge graph-computing algorithms like bi-directional search or shortest path analysis which keep the stored data relevant by augmenting it with fresh layers of actionable intelligence in real-time. They are also highly extensible as they are independent of the underlying schema or databases, and are used to identify the context as well as enrich the content with deep contextualization. 

MECBot’s Knowledge Graph keeps updating itself with new inputs from the environment as well as from within itself. Knowledge Graphs also come in handy in managing and annotating powerful meta-data at scale. This leads to cool features like provenance, versioning, and data governance. 

Currently, business users identify a problem, and then the data team creates bespoke data pipelines and models to solve the problem. Then, once the problem at hand is solved, they begin to worry about data governance. This means that businesses take the necessary measures to ensure that data comes from the right sources (and that it is not managed/manipulated in between) only at the fag end of the analytics lifecycle. As a result, creating logs of authorized and unauthorized access comes into the picture only after the data model is already in place and ready for execution. Such an approach leads to high inefficiencies, poor data governance, and unchecked mishandling of data that ultimately adversely impact the decision-making outcomes.

MECBot inverts the entire process. Starting with the data source, it applies checks and balances to each stage of the data pipeline such that all the data that MECBot touches are pre-checked to be trusted, clean, and fully traceable. This way, even if some or all of the data were uneven, inconsistent, messy, or untrusted at some point in their life-cycle, by the time they get stored in MECBot in graph form and are analytics-ready, they have all been automatically transformed into a trusted data-store by MECBot. This also ensures that there exists only a single source of truth for all data users. This is achieved by applying the following features at the data sourcing and pipeline creation stages:

1) Data Lineage - Verify the source from where the data is being ingested - Is it trusted? When the data pipeline was run, did anyone change the pipeline? If so, when? What changes were made to the pipeline? What types of relationships exist between the data points at the source? How do those interrelationships change across the pipeline? How do they change over time?

2) Data Security and Privacy - Transparent security to ensure that well-defined user access is a top priority - Which users can access which data modules? With whom can they share those modules? What are the sharing permissions available to users within and outside a user group? In the case of a data breach, what kinds of fail-safe are in place? How quickly and easily can previous versions of the data be rolled back by authorized users?

3) Data Cataloging - MECBot creates an organized inventory of all the data assets and ensures seamless and systematic access using powerful metadata management, smart data discovery, and data governance.

By making the data fundamentally trustworthy, MECBot makes the data models trusted and explainable through its secure data pipeline. This means that along with gleaning results and insights from the data model, it is also possible to discover ‘why’ the certain results or insights have been the outcomes of such models. This way, MECBot enables the extraction of high-quality, governed insights using AI.

Dive deep into MECBot’s use case in Cricket Analytics and explore how our omniscient Knowledge Graph creates 360o player performance analysis in real-time. 

Why MECBot: Knowledge Graph is at the Heart of Our Award-winning Product

Our flagship product MECBot is the #1 Augmented Data Management Platform for Real-Time Analytics at Scale. MECBot puts the business first by adopting the Entity Domain Model approach, which operates without any dependency on the underlying databases or the structure of the data. It comes bundled with a self-service, intuitive interface and takes care of all the data management and analytics requirements in a centralized manner, including scalable deployment.

Simply put, MECBot automates the entire data unification process envisaging all forms of data at scale, and delivers unprecedented business results. To accomplish this, MECBot first structures the unstructured data contextually using domain-specific business ontologies and marries it with structured transactional data in near real-time. This creates a comprehensive Smart Data Graph for an enterprise (Smart Enterprise Knowledge Graph).

This Smart Enterprise Knowledge Graph is accessible through “Free Form Vertical Search”, APIs, SparkSQL, and Graph QL. MECBot’s unique value propositions include:

  • Simplicity: Sets up the application with just a few clicks. Gives results from day 1.
  • Speed: Matches the pace of decision-making with the speed of the original data generation.
  • Scale: Performs elastic scaling based on business needs with dynamic clustering.
  • Security: Offers banking grade security and role-specific access to the platform.

MECBot saves more than 80% of pre-processing time & cost and delivers highly actionable insights to boost business ROI manifolds. It is the only platform that puts the business first, not data. Its unique, built-in capabilities drastically reduce the burden on IT infrastructure and empower business decisions with powerful business intelligence in real-time through augmented data management.


MECBot Central Data Management

Interested to know more about how MECBot can boost enterprise RoI manifolds with Smart Enterprise Knowledge Graphs and Augmented Data Management? Visit To know about the state-of-the-art technologies we use, check out our platform architecture here:

Wish to take a deep dive into what MECBot can do for your business? Request a demo here: