Skip to content

Welcome to Project Cloud Conversations™

Overview

Logo TIBCO Project Cloud™ Conversations by TIBCO LABS™ offers a new way of exploring data in conjunction with a 'chatbot' conversational interface for querying enterprise knowledge. By leveraging the power of graph databases to represent data and relationships, one can find answers to unanticipated questions and discover previously "hidden" knowledge by having a conversation with your enterprise data.Project Cloud Conversations’ goal is to provide enterprise users with a simple-to-use tool for querying enterprise knowledge.

Business use case
More and more employees in the enterprise are required to analyse data as part of their job. Employees often have to obtain “responses” from existing data, and they even have to be “curious” and dig into different data sets to find the information required. These “curious” people or roles can include marketing, sales reps, C-level executives, business analysts, and business leaders.

For example, with the knowledge one has in Salesforce about deals, sales reps, customers, and products, a C-level executive may wonder which customers are part of the top ten deals in the first quarter and where they have been closed.

What are the options for people to exercise their curiosity, navigate the data, and find responses to their questions? Today, they are often asked to use fixed or rigid applications where hopefully some menu will drive them to the correct information or access to a prepared report.

In both cases, it is a painful process and there is little chance of success to really get the answers to their questions. In a fixed application, one needs to know the application logic and where to click in the various menus. At the end, the application is probably not covering all the data it needs, as it typically covers only a small silo of enterprise activity. In the case of reports, if a company dashboard has not been created, it could take time to get the answer; even if a dashboard exists among the hundreds already created, one still has to spend time finding the correct one!

This brings about the problems and considerations associated with “cognitive load” (what an employee has to know and learn even before starting to work at getting information) and “affordance” (how ‘natural’ it is to do your task).

At TIBCO LABS, we think that a conversational user interface can reduce cognitive load and augment affordance for those use cases where an employee is looking for a response to a particular question.

These questions can include ones like the following:

    - How many deals over 100k have been signed in EMEA last quarter?

- Per business unit?
- How does it compare to last year?

TIBCO LABS started the project by simply assuming that the best way to find the response was to allow a user to ask simple questions:



 
    - How many deals over 100k have been signed in EMEA last quarter?

- Per business unit?
- How does it compare to last year ?

Looks very similar to the sample questions. And this is done without navigating complex menus or searching in a myriad of reports.

Proposed Solution

Using a conversational UI, a simple query such as "show me the top ten deals in the first quarter per region" will display a response. The internal model of knowledge emphasizes the relations between data so the user can easily navigate the information.

In our example, clicking on one region will display a list of deals; each deal has information about the sales rep, product, and more that can be accessed in just one click. A manager could ask "list the sales reps with less than five opportunities" or query "show me the opportunities above 100k per industry".

Not a single report has to be prepared and all interactions are done in natural language.

Key components

The solution is based on four core components:

- Graph Database: Used for storing the knowledge graph as related nodes and edges.
- Ontology Builder: A tool used to describe what the knowledge is about.
- Graph Mapper: A tool used to synchronize the existing data and map it to graph storage.
- A conversational user interface (“ConvUI”): that allows anyone to search for information in the knowledge domain.

Logo

The Knowledge Graph

We assume that an employee asking for information is working on a specific business domain. For example, “sales and marketing” in sales, “flight operations” for an airline company, or “well operations” in oil and gas.

We leverage the efficiency of a graph database to store this information. A graph database stores information in the form of properties on entities ('nodes') and relations ('edges'). Not precisely a new idea, as entity–relationship (ER) modeling was developed for database design in the 1970s.

Entities/relations (nodes/edges) is a natural and effective way to model a knowledge domain. The key point here is that a graph database does not translate an ER model into a relational database management system (RDBMS) where the relations are stored in the data themselves (in the RDBMS, relations are kind of lost in translation), but directly uses a graph structure and treats relationships as first-class information.

The data is stored differently from a RDBMS but most importantly, data can be foraged and retrieved efficiently in many more useful ways, allowing queries and analytics of associative and contextual nature.


Ontology builder

Business people know the vocabulary used in the company and understand how all the notions fit together. As part of Cloud Conversations, there is a specific tool to help build the vocabulary and the description of the relations.

Graph Mapper

The graph mapper offers a way to connect to existing data sources (e.g. CSV, relational data), retrieve the data, and populate our knowledge graph.

ConvUI

The visible component of the solution is a simple AngularJS application hosted on the cloud. It sends the queries expressed in natural language to a backend implemented as serverless functions in cloud architecture. After analyzing the question using an English grammar and the domain ontology, the system translates it to a query into the graph database. It then decides on the best way to display the result. Some questions will result in a number or simple text while others may lead to visual responses like bar graphs or maps.

Logo

The components of the solutions in action:

Logo

NLP

The trendy approach to NLP involves machine learning (ML). ML solutions are offered by AWS, IBM, Microsoft, and others but suffers from some limitations:

- Training: ML needs a tedious learning process with samples of possible sentences or utterances you are expecting.

- Lack of deterministic result: How can you be sure of the correct "understanding" of a query? This is not critical for responses that you can correlate with the question. For example, if you ask, "When was the Internet invented?" and the response is "1600", you may think that the system did not correctly 'match' the sentence with an intent and thus did not provide the right answer. But if you ask, "What was the total revenue of license last quarter in EMEA?", one needs to trust the understanding in order to trust the response number.

- Privacy: Current offerings are usually SaaS and use the input to "improve" the ML model. We have customers using natural language for C-level types of questions in an operation control room. They don't want their queries to be shared via text with a third party in the cloud!

Project Cloud Conversations uses English grammar to understand the structure of the question and then rely on the ontology to verify the nouns used as well as the relations. Relations could be expressed in different ways in natural language:

    - Who is John’s boss?

-How many deals were created last quarter?
- Show me the flights from Boston to San Francisco.

In these sentences one can see relations expressed as a noun (“boss”), past tense verb (“created”), and with prepositions (“from / to”).

We found that the usage of the grammar analysis, extractions of entities and relations, and verification in the ontology is a very powerful way to “understand” the question with no ambiguities. The entity/relation type of intent we are creating maps very well to a graph database query.

Conclusion

So as you can see, with Project Cloud Conversations, the answer is in the conversation. This simple-to-use tool queries your enterprise data so you can discover previously hidden knowledge and have a conversation with your data. Leverage all it can offer to find out the answers you need to make better, faster decisions.

Next Steps

To start using Project Cloud Conversations™ today, follow the next steps:
1. Sign up for a TIBCO Cloud Account here
2. Check your email and activate your account
3. Log into TIBCO Cloud
4. Once you are in, navigate to the Solutions area on the right side of the landing page
Logo
5. Select the TIBCO Cloud Conversations™ project and click on the Launch button
Logo
6. Enjoy it

Logo