Implementing a Chatbot for Improved Customer Service

Implementing a Chatbot for Improved Customer Service

This project aims to improve the customer service of a call center by developing a chatbot that can handle frequently asked questions from clients. The Google dialogue flow technology and Python will be used to create the chatbot. The objective is to shorten the time clients spend talking to representatives and boost call centre productivity, which will improve customer happiness and boost the company’s profitability.

Business Challenge:
For a website of a call center due to huge number of client queries resulting in high engaging time which was a big problem where many clients had to wait for their turn. This resulted in poor customer support system.

Solution:
By developing a chatbot that would be capable of catering to frequently asked questions by the clients, the problem at hand could be resolved. Moreover, this would improve the efficiency of the call center.

AI Engine Results:
Chatbot engine will first try to capture the user’s intent from the query and respond accordingly.

Results:
By implementing this chatbot, the engaging time would decrease plus more clients would be dealt with in less time. Resulting in improved customer service.

Client Success:
The organization would become more profitable and this would result in an increase in their customer satisfaction.

Technology Stack:
Language: Python
Technologies: Google dialogue flow

Detecting and Tracking Athletes in Marathon

Detecting and Tracking Athletes in Marathon

We developed a solution to detect and track athletes in marathon videos using face and bib number recognition. The system runs on a simple intel i7 machine without a GPU and achieves near real-time performance at 7 fps. Our AI engine resulted in a 97% detection and tracking accuracy, leading to the creation of personalized video clips for registered participants. The client’s productivity increased by 300% with this solution. The technology stack includes Python, Yolo, OpenCV, and deep learning models.

Business Challenge:
The client installs his cameras at various location of the marathon track and records video. A few participants registers with the client. The use case is to detect and track automatically the registered athletes from the marathon’s complete race videos and clip out personalized short videos at each spot the camera is installed.

Solution:
We developed and optimized a solution that performed the automatic detection and tracking of athletes by face and their bib number both available on front of the shirt. The system is deployed on a simple intel i7 machine with out GPU that performs the said task in near real time at 7 fps.

AI Engine Results:
We achieved 97% detection and tracking results to clip out small videos of athletes.

Results:
An app that churns out the personalized video clips of the registered participants in the marathon.

Client Success:
The automatic personalized video extraction increased the productivity of the client by 300%.

Technology Stack:
Language: Python
Technologies: Yolo, OpenCV, Deep Learning Models

Photo Courtesy: olympics.com

News Recommendation System

News Recommendation System

Our AI-powered system generates personalized news suggestions using a probabilistic prediction model created by analyzing reader behavior, holding their attention for longer and saving time. As a result, website traffic rises by 5 to 8%, and the material is improved based on reader preferences. Deep learning and NLP models were used in the Python-based system, which was then saved on Apache Cassandra.

Business Challenge:
News websites aim to increase their readers and traffic on their websites. However, they fail at captivating their reader’s attention and interest for longer time span.

Solution:
A probabilistic prediction model can be generated by studying the liking, disliking and digital footprints data gathered from records of previous readers.

AI Engine Results:
By using the results of probabilistic prediction model the liking and disliking of the readers can be predicted and with the aid of those predictions recommendations can be made to readers according to their interest.

Results:
Readers interest can be captivated for longer time span. It will save their time in searching for news and there would be fewer chances for them to miss on news of their interest.

Client Success:
The web traffic over the website would increase by 5-8%. The client would have more systemized data depending on liking and disliking of readers, and this can aid in improving the content of the website.

Technology Stack:
Language: Python
Models: Deep Learning Models, Natural Language Processing
Storage: Apache Cassandra

Sports Analytics for Android/IOS

Sports Analytics for Android/IOS

We developed a sports analytics solution that works with both Android and iOS mobile devices. Our approach uses a YOLO and DeepSort-based model tuned on Tensorflow-lite to conduct real-time pose estimation of players and ball identification and tracking in baseball and golf. Our AI engine results in two Tensorflow lite models running on high-end Android and IOS devices. Without employing pricey hardware, the client was able to launch a first-of-its-kind, cost-effective sports analytics tool. The project’s technology stack consists of Yolo, DeepSort, Deep Learning Models, and OpenCV.

Business Challenge:
Every sport has introduced the field of Analytics. We worked on the analytics of two sports, Baseball and Golf. There were three major challenges. The first challenge was to detect the pose of the player. The second challenge was to detect and track the ball moving at around 160 km/h in near real-time. The third challenge was to implement the solution on both Android and IOS devices.

Solution:
We developed and optimized a solution that performed the pose estimation of the player. Furthermore, we optimized and implemented a YOLO and Deepsort-based model that detects and tracks the ball. Finally, the model was optimized on Tensorflow-lite to run on Android and IOS devices.

AI Engine Results:
We developed two Tensorflow lite models that runs on high-end Android and IOS devices. The first model detects and tracks of the ball in near real time, whereas the second model detects the player’s pose .

Results:
An app that performs the pose estimation, and ball detection and tracking in real time.

Client Success:
The client was able to introduce a first of its kind mobile app that performs a reasonable analytics of the two sports like baseball and Golf without using specialized and expensive hardware that may cost as high as $20000.

Technology Stack:
Language: Python
Technologies: Yolo, DeepSort, Deep Learning Models, OpenCV

Photo Courtesy: Tech Bullion