10%

Try : Insurtech, Application Development

Edtech(5)

Events(31)

Interviews(10)

Life@mantra(10)

Logistics(1)

Strategy(14)

Testing(7)

Android(43)

Backend(28)

Dev Ops(2)

Enterprise Solution(20)

Frontend(28)

iOS(39)

Javascript(13)

AI in Insurance(26)

Insurtech(57)

Product Innovation(34)

Solutions(13)

Augmented Reality(7)

Customer Journey(7)

Design(6)

User Experience(21)

Artificial Intelligence(95)

Bitcoin(7)

Blockchain(14)

Cognitive Computing(7)

Computer Vision(6)

Data Science(14)

FinTech(41)

Intelligent Automation(25)

Machine Learning(43)

Natural Language Processing(10)

E-health(2)

HealthTech(5)

mHealth(3)

Telehealth Care(1)

How chatbots are changing the digital Indian

3 minutes, 39 seconds read

Chatbots have come a long way – from a hyped technology under the AI umbrella to a direct-to-consumer product, that has incessantly penetrated the tech-enabled services we use today. While the adoption of chatbots is still in its infancy, the proliferation and mushroomed effect it has had so far is remarkable. Most of us, are perhaps not even aware of how seamless this transition has been – since many now interact with several bots almost everyday!

Nearly 1 in 4 customers have interacted with a brand via chatbots in the past 12 months, according to a Salesforce study published in late 2018.”

Chatbots have permeated the Indian Landscape

In India, like most countries, both businesses and consumers rely on telephone and email as the most preferred channels to conduct business, yet they are also the slowest for quick resolution. The average time-to-resolution using email interactions was reported at 39 minutes while in India it was reported at 2 hours 17 minutes. In addition, global data shows only 49% of problems are solved on the first interaction.

Most people in India (59%) however, still prefer to talk to an actual person for customer service needs. While this is true, customer service experts believe this trend will reverse in the near term. A majority (61%) of “the Digital Indian” or tech-savvy users see the benefits for chatbots in customer service.

How Chatbots are changing the Digital Indian

AI is already providing benefits to e-commerce businesses in India by improving decision making & recommendation systems using machine learning algorithms, while simplifying the product search journey for the customer. When done well, 43% feel chatbots can be almost as good as interacting with a human, revealed a study titled “Efficacy of AI” conducted by digital marketing solutions firm iCubesWire.

Bots among us

Conversant bots have augmented our ability to quickly access information, services, and support – even taking over some of our day-to-day tasks. The passage deeply signifies an unmistakable shift in our digital communication patterns. Here are some well-known instances of chatbots in use, around us.

GoHero

This AI-enabled personal travel agent assists customers in booking flights, hotels, taxis, buses etc. It integrates with messaging apps to use sophisticated algorithms to understand traveller’s preferences and is available across nine platforms such as Facebook Messenger, Telegram & Skype.

Aisha

A voice assistant (similar to Siri, Google Assistant) by Micromax performs daily tasks like initiating a google search, fetching movie reviews, making calls, reading news articles, view stalk market details and more. The Handset Speech Assistant with AI integrated into its backend is gently becoming an accepted, must-have tool for the average consumer.

Lawbot

A customer facing AI application that automates specific legal tasks that would otherwise require extensive legal research. It analyses and reviews legal documents, like contracts or agreements, and identify problems in them in seconds – saving customers valuable time and money.

FitCircle

This health and fitness chatbot offers its users personalised weight-loss workouts, yoga guides and nutrition guides. The AI empowered fitness companion, called ‘Zi’, helps the Digital Indian achieve fitness goals through custom-fit workouts and diets.

Oheyo

Formerly Prepathon, Oheyo helps students (the digital Indian of the future) prepare for exams, by connecting them to experts anywhere. It messages students the subject of the day, answers queries and additionally sends across motivational messages. They also provide a video Q&A platform through which students can find a lot of their queries answered and archived for later use.

Skedool

Skedool’s ‘Alex’ is a B2B smart assistant, that excels at automating repetitive everyday tasks for business executives, sales and recruiting professionals. It handles B2B scheduling activities and calendar management. The AI assistant uses natural language processing and machine learning supervised by humans to enable customers to communicate with the service via e­mail just as they might with a human assistant.

Hitee

A one-of-a-kind chatbot with voice, video, and multilingual features. It’s custom NLP-powered workflow builder solves a number of purposes like operations, HR, IT, logistics, and more.

While these are just a few highlighted examples, there are many more in use across the country, each with a unique use case and problem it is trying to solve. For example, Aapke Sarkar – a chatbot (developed by Haptik) launched by the Maharashtra Govt. for people to access information regarding public services in the state, in Hindi or Marathi; or the bot introduced by IRCTC called ‘AskDisha’ (Digital Interaction to Seek Help Anytime) that helps railway passengers access customer services support in multiple regional languages and even voice-enabled chat.

Bots and The Digital Indian

The Indian chatbot industry, although still in its nascent form, is a $3.1B market, according to analysts. The market, in the coming years will evolve to a point where interactive and intuitive AI will become the bare standard for customer service across a variety of sectors.

AI Chatbot in Insurance Report

AI in Insurance will value at $36B by 2026. Chatbots will occupy 40% of overall deployment, predominantly within customer service roles.
DOWNLOAD REPORT

Related Reads:

Cancel

Knowledge thats worth delivered in your inbox

Tabular Data Extraction from Invoice Documents

5 minutes, 12 seconds read

The task of extracting information from tables is a long-running problem statement in the world of machine learning and image processing. Although the latest accomplishments in the field of deep learning have seen a lot of success, tabular data extraction still remains a challenge due to the vast amount of ways in which tables are represented both visually and structurally. Below are some of the examples: 

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Invoice Documents

Many companies process their bills in the form of invoices which contain tables that hold information about the items along with their prices and quantities. This information is generally required to be stored in databases while these invoices get processed.

Traditionally, this information is required to be hand filled into a database software however, this approach has some drawbacks:

1. The whole process is time consuming.

2. Certain errors might get induced during the data entry process.

3. Extra cost of manual data entry.

 An invoice automation system can be deployed to address these shortcomings. The idea is to upload the invoice document and the system will read and generate the tabular information in the digital format making the whole process faster and more cost-effective for companies.

Fig. 6

Fig. 6 shows a sample invoice that contains some regular invoice details such as Invoice No, Invoice Date, Company details, and two tables holding transaction information. Now, our goal is to extract the information present in the two tables.

Tabular Information

The problem of extracting tables from invoices can be condensed into 2 main subtasks.

1. Table Detection

2. Tabular Structure Extraction.

 What is Table Detection?

 Table Detection is the process of identifying and locating tables that are present in a document, usually an image. There are multiple ways to detect tables in an image. Some of the approaches make use of image processing toolkits like OpenCV while some of the other approaches use statistical models on features extracted from the documents such as Text Position and Text Characteristics. Recently more deep learning approaches have been used to detect tables using trained neural networks similar to the ones used in Object Detection.

What is Table Structure Extraction?

Table Structure Extraction is the process of extracting the tabular information once the boundaries of the table are detected through Table Detection. The information within the rows and columns is then extracted and transferred to the desired format, usually CSV or Excel file.

Table Detection using Faster RCNN

Faster RCNN is a neural network model that comes from the RCNN family. It is the successor of Fast RCNN created by Ross Girshick in 2015. The name Faster RCNN is to signify an improvement over the previous model both in terms of training speed and detection speed. 

To read more about the model framework, one can access the paper Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

 There are many other object detection model architectures that are available for use today. Each model comes with certain advantages and disadvantages in terms of prediction accuracy, model parameter size, inference speed, etc.

For the task of detecting tables in invoice documents, we will select the Faster RCNN model with FPN(Feature Pyramid Network) as a feature extraction network. The model is pre-trained on the ImageNet corpus using ResNET 101 architecture. The ImageNet corpus is a public dataset that consists of more than 20,000 image categories of everyday objects.  We will therefore make use of a Pytorch framework to train and test the model.

The above mentioned model gives us a fast inference time and a high Mean Average Precision. It is preferred for cases where a quick real time detection is desired.

First, the model is to be trained using public datasets for Table Detection such as Marmot and UNLV datasets. Next, we further fine-tune the model with our custom labeled dataset. For the purpose of labeling, we will follow the COCO annotation format.

Once trained, the model displayed an accuracy close to 86% on our custom dataset. There are certain scenarios where the model fails to locate the tables such as cases containing watermarks and/or overlapping texts. Tables without borders are also missed in a few instances. However, the model has shown its ability to learn from examples and detect tables in multiple different invoice documents. 

Fig. 7

After running inference on the sample invoice from Fig 6, we can see two table boundaries being detected by the model in Fig 7. The first table gets detected with 100% accuracy and the second table is detected with 99% accuracy.

Table Structure Extraction

Once the boundaries of the table are detected by the model, an OCR (Optical Character Reader) mechanism is used to extract the text within the boundaries. The text is then processed using the information that is part of a unique table.

We were able to extract the correct structure of the table, including its headers and line items using logics derived from the invoices. The difficulty of this process depends on the type of invoice format at hand.

There are multiple challenges that one may encounter while building an algorithm to extract structure. Some of them are:

  1. The span of some table columns may overlap making it difficult to determine the boundaries between columns.
  2. The fonts and sizes present within tables may vary from one table to another. The algorithm should be able to accomodate for this variation.
  3. The tables might get split into two pages and detecting the continuation of a table might be challenging.

Certain deep learning approaches have also been published recently to determine the structure of a table. However, training them on custom datasets still remains a challenge. 

Fig 8

The final result is then stored in a CSV file and can be edited or stored according to one’s convenience as shown in Fig 8 which displays the first table information.

Conclusion

The deep learning approach to extracting information from structured documents is a step in the right direction. With high accuracy and low running time, the systems can only learn to perform better with more data. The recent and upcoming advancements in computer vision approaches have made processes such as invoice automation significantly accessible and robust.

About the author:

Prateek Sethi is a Data Scientist working at Mantra Labs. His work involves leveraging Artificial Intelligence to create data-driven solutions. Apart from his work he takes a keen interest in football and exploring the outdoors.

Further Reading:

Cancel

Knowledge thats worth delivered in your inbox

Loading More Posts ...
Go Top
bot

May i help you?

bot shadow

Our Website is
Best Experienced on
Chrome & Safari

safari icon