INEXTURE Solutions

Real-world damage detection from videos/photographs of vehicles being in an accident. Insurance companies have to deal with a lot many claims daily & have to employ surveyors to deal with estimations of cost. Which in the result is prone to human error & may result in some discrepancies. To avoid such cases, we were tasked to handle the damage detection part for 4 wheelers.

AI-based attendance system allowing employees to come & go without any delay. Manual entry or fingerprint scanning takes some time when it comes to a bigger organization with more than 500 staff in a premise. We had to develop an attendance system which can take photos of employees from surveillance cameras to mark them present.

The crowdfunding platform is an excellent model for a gifting program. This platform helps people fund their projects in which you receive donations for your personal needs, like medical expenses, bills, paying off debts, etc. The platform is automated to handle the people going through the boards placing people on the boards and keeping track of who is next to get gifted.

The platform has an E-Wallet for each person to hold money. The platform provides a feature to users to cash out the money to their private bank or money solution of choice.

This is a B2C(Business-to-Consumer) platform where the primary goal is to sell goods online. The platform provides users with a catalog of different products available for purchase like - impressive kit, bells, and bristles for many North America, Europe & Asia Pacific countries.

In order to facilitate online purchases, a shopping cart is provided to the user with discount facilities. The order platform provides all features, which any standard eCommerce website has like - add/modify/cancel products, apply discount/coupons, return products, processing refunds, etc. The System is implemented with a 3-tier approach, with a backend database, a middle tier of Microsoft Internet Information Services(IIS) and Python, and a web browser as a frontend client.

To develop a platform that converts natural language to SQL queries, the client wants a platform where we can add databases as data sources and for retrieving the data instead of using complex queries in SQL we can simply ask questions in plain English, and the platform will provide all answers needed. The problem is widely popular in the Natural Language Processing domain as a “Text-to-Code” conversion. We Created the Hybrid approach to tackle the problem where we are using statistical as well as deep learning to solve it.

• Natural language processing to solve the Text-to-code problem
• Deep learning-based as well as statistical models aka Hybrid approach
• Google Bigquery for warehousing the data sources
• Django APIs for easy interaction with the platform
• Google IAM authentication in GCP

Planogram compliance for detecting missing or misplaced items. A retail store frequently has to cope up with demand & much larger stores need to employ staff just to check up on inventory, products placed on the shelves & get items in place misplaced by customers, a very frequent occurrence & annoyance for storekeepers. With that taken into account, we have a solution to get instant updates on if a shelf is empty, the item is missing & our end-to-end system gets real-time updates from inventory linked to the database & assigns someone instantly to fix the situation.

Crelto is a cloud-based management system that gives users precious time again so that you can focus on the quality of service and the growth of your company again. Crelto provides lots of functionality to its customers to improve their business.

This is an eLearning platform, which provides educators with opportunities to implement a range of new teaching and learning practices, which redefine the 'classroom' term. A learning experience where the learner must contribute to activity is called active engagement, while learning experience where the learner is mainly a recipient of the information is called passive engagement. When a form of engagement is engrossed by a learning activity, the learner is focused and attentive and becomes captured and committed to the task at hand.

This project is about getting aggregate data from which we can identify the matrices like how many shoppers were in a day on a DMA or a region or in a DMA and a region, or national from raw and very granular data about car shoppers. So, The process which involved to get this result we use ETL, in general terms, we have data about car shoppers each record represents a shopper and for each shopper, we have lots of information like region and DMA, the region/DMA where the shopper was made.

Meetwo is the latest, hottest, and  FREE online dating app in town that finds your true match. Take a unique love quiz and get matched with singles nearby. Search for single men and women around you. Filter by distance and age. Disable your profile visibility when you’ve found the one! Meet new people with Meetwo and enjoy free online dating.

Our client is the UK based largest marketing company responsible for organizing events for all of their clients, These events and campaigns run for days or months. At the end of each month, they need to apply Taxes for all the events held and there are so many rules depending on each client, event types and durations.

These report files are being generated from their Admin panel and saved in AWS S3. We created Lambda functions to execute Python scripts that make all these Tax applications automated depending on a lot of rules. And after applying these rules saves these files again in s3 bucket with proper folder structure.

• → Automation scripts are written in Python3
• → S3 bucket to store files, AWS Lambda to execute scripts based on triggers
• → Optimized logic as they have thousands of report sheets coming in from all over the world with lots and lots of data in CSVs.

MakeMyDocs is an educational website platform where the primary goal is to create a custom document based on user requirements with different payment modes. The platform provides users a simple UI interface where users can simply drag and drop templates to create documents quickly and easily. You don’t have to be an IT guru to use this tool–no technical knowledge or special required.

The application provides to easily create thousands of secure documents within minutes via CSV document with payment modes for users or organizations. The application platform provides other features like - Add/Modify/delete the uploaded templates, custom templates to generate multi/bulk documents with the same template. No minimums plans/No hidden fees, You pay for what you create and then download and use that document over and over again, etc. The application provides a client-server system with a robust and optimized backend with AWS lambda.

The main requirement was to gather the data of online teaching platforms, what courses do they offer, how many and which authors are there on each e-learning platform and also the metadata for each course like the categories, course details, and co-authors, schedule, etc.

We did this by storing the sitemap of all these sites in the cloud in a customized JSON format and then triggering an SQL stored procedure which compares the already existing data with the new files update the existing courses if there are any changes or add new data.

→ Creating a common architecture that generalizes scrapping all sitemaps and gathers common data from different sites like Udemy, Udacity, Coursera, etc.
→ Upload large content of scrapped data to Azure cloud and dump the data in the warehouse in Azure.
→SQL procedures to check and update only non-existing data in the warehouse.

Document classification based on legal types of cases for internal usage by certain law firm. Due to the huge workload & manual work being done to separate case files based on their content into physical areas has been cumbersome. Many law firms have switched to online containers for their storage which is convenient but still needs some manual work to be done. To avoid reading the details & being billed many hours for it, we proposed an alternative to this & implemented ML model which based on documents will classify it.

Compiling virtual databases of business cards for an online verification firm. Business cards come in many forms & formats & nowadays taking your business online means opening a huge market for your product. And lots of business owners daily apply for verification & getting information from images manually is time consuming. For that we were tasked to implement a deep learning model which can be used for any background & any color of card to extract information from it.

ConversationalAI for detecting mental state of users for a research institute. With the increase in the number of people spending time online, the need to get insights on their mental state has become effective. We were tasked to assess & identify certain mental conditions based on how they interact with the bot.

Conversational AI to find out various options of wine with the help of text conversation. Customers will get wine options in conversation format and get easy payment options.

This is a Financial/Insurance procedure automation platform where the primary goal is to Crawl 11 different websites related to insurance of different types to automate the Login process with OTP verification (2-Factor Authentication) enabled. The platform provides save report files to Amazon AWS s3 and Bypass Captcha, Recaptcha Verification, and security with Advanced Proxy settings.

The System is implemented custom Logging architecture for Failure cases and reporting in the dashboard via APIs. It is Flask based REST APIs to initiate crawlers which is triggered by Laravel Admin Panel on which Agents can work.

Information like name, amount, contract type, organization & many more were to be extracted from any given contract by leading global CMS’s users. It may happen that contract type for every organization may differ with differences in their structure as well. So to extract information from the uploaded contract we were tasked to implement AI & DL to work our way through with extraction with accuracy in comparison with leading cloud AI service providers.

Natural Language processing custom built deep learning algorithms to generate mathematical equations from Math word problem statements without human interference. During this pandemic we saw a sudden rise of internet education & need to have tutors for children when they have doubts. So a startup allowed us to build an app where Students or parents can find out equations for the problem they enter within the app itself.

Real world damage detection from videos/photographs of Infrastructure undergoing construction or structural strength survey or maintenance survey. Manual surveys are prone to corruption & human error which has resulted in huge losses. With much accurate & faster eyes of computer & advancements in devices help us get more detailed data & in a result generate better predictions with better accuracy.

The DVE offers the opportunity to analyze and to instructively visualize data, by breaking down scenarios and solutions into comprehensive steps. Here, technology serves as an interface between science and society, where scientists and stakeholders can jointly find innovative solutions for sustainability challenges. It represents the synthesis of research results and the technology for interactive data analysis and presentation.

The Rajput Yuva Entrepreneur Club is the central hub & a big leap to revolutionize the Rajput Business Community. The search engine for the Rajputs to find fellow businessmen. 

Ryuva Club app provides the ease of managing your business from the mobile and communicating with prospective customers.

HelpUBaby is a web platform for booking babysitters for childcare & childhood. Their In-home services are available in Greater LA, Orange County, Santa Barbara, Ventura, The San Francisco Bay, Seattle, Chicago and NYC.

GTPL is a leading cable TV Distribution Company reaching an estimated 8 million households in over 169 cities across 10 states in India. We partnered with GTPL to develop the mobile application that allows users to manage plans, submit a support ticket, payment and billing history, and more.

GrouperDeal is the online platform that allows the property seeker or a property seller to connect and communicate. Users can search any property or property-dealers across the country, filter the results by location, price, amenities, and everything else. The whole search process is powered by the Apache Solr search engine and works efficiently. The portal is built on the PHP Laravel platform and Apache Solr 6.4.1.

Fonefix is one of the leading mobile reparation shops in Denmark. Fonefix offers an advanced mobile, tablet reparation booking system for over 1000+ parts from over 200+ products from 20 different brands. Besides, Fonefix also includes an online eCommerce shop for mobile phones, tablets, accessories, and more.

Anibrain is VFX & creative studio. It is one of the fastest-growing creative studios in India, that specializes in creating stunning visuals for film, TV, Apps & mobiles. They have created some unique VFX for popular films, like The Guardian of the Galaxy, Pompi, Ghost Rider, and much more. They always show your story through breathtaking visuals that dazzle audiences from all over the world. We partnered with Anibrain to develop an internal portal to manage ongoing projects, employees, events as well as leave management.

ProTeen is an online platform to guide teens for their academics and careers. The project captures student’s interests and recommends academics and career paths suitable to their interests. The whole interest capturing and career recommendation process is done with Apache Solr. The Apache Solr search engine plays an important role in recommending user’s interest-based academics and career paths.