Download as pdf or txt
Download as pdf or txt
You are on page 1of 7

Department of Computer Engineering

(NBA Accredited)
Academic Year 2022-23

Name: Atharv Darekar Roll No: 23

Div: A Batch: A1

Subject: CCL Moodle Id: 21102036

SageMaker Q&A Assistant: Mercedes-Benz Case

INTRODUCTION:

Amazon SageMaker is a fully managed machine learning service provided by Amazon


Web Services (AWS) that enables developers and data scientists to build, train, and deploy
machine learning models at scale. It simplifies the process of building, training, and
deploying machine learning models by providing a comprehensive set of tools and
services within a single integrated platform. Here's a detailed overview of Amazon
SageMaker:
1. Features:

- Data Labelling: SageMaker offers built-in tools for data labelling, enabling users to
annotate and label datasets for supervised learning tasks.

- Model Training: Users can train machine learning models using SageMaker's managed
training infrastructure, which supports distributed training across multiple instances.

- Built-in Algorithms: SageMaker provides a library of built-in algorithms for common


machine learning tasks such as classification, regression, clustering, and
recommendation.

- Custom Algorithms: Users can also bring their own algorithms and frameworks to
SageMaker, allowing for flexibility and customization in model development.

- Model Tuning: SageMaker includes hyperparameter optimization capabilities to


automatically tune model parameters for improved performance.

- Model Hosting: Trained models can be deployed to SageMaker's managed hosting


infrastructure, making it easy to serve predictions at scale.

- Real-Time and Batch Inference: SageMaker supports both real-time and batch
inference, allowing users to generate predictions on individual data points or large
datasets.

- Automatic Model Deployment: SageMaker offers automated model deployment


options, including rolling updates and canary deployments, to streamline the deployment
process.

2. Workflow:

The typical workflow for using Amazon SageMaker involves the following steps:

- Data Preparation: Users start by preparing their data, which may involve cleaning,
preprocessing, and splitting into training, validation, and test sets.

- Model Development: Next, users select or develop a machine learning algorithm and
train their model using SageMaker's training infrastructure. This step may involve
hyperparameter tuning to optimize model performance.

- Model Evaluation: After training, users evaluate the model's performance using
validation data to ensure it meets the desired criteria.

- Model Deployment: Once satisfied with the model's performance, users deploy it to
SageMaker's hosting infrastructure for inference. This step involves configuring
endpoints and specifying resource requirements.
- Inference: With the model deployed, users can generate predictions on new data in real-
time or in batch using SageMaker's inference capabilities.

- Monitoring and Iteration: Finally, users monitor the deployed model's performance
over time, making adjustments as needed based on feedback and changing requirements.

Overall, Amazon SageMaker provides a powerful and versatile platform for building,
training, and deploying machine learning models in the cloud, enabling organizations to
accelerate innovation and drive business value with artificial intelligence.

Mercedes Benz with AWS SageMaker:

As a trusted consulting and services provider


in the automotive domain, Mercedes-Benz
Consulting understands the critical
importance of providing efficient and effective
support to its customers. However, like many
organizations, it faces the challenge of ensuring
timely and accurate responses to the myriad
inquiries it receives daily. Whether customers
seek information about vehicle specifications,
service schedules, or brand-related queries,
the need for a streamlined and responsive support system is paramount.

To address this challenge and elevate its customer support capabilities to new heights,
Mercedes-Benz Consulting embarks on a transformative journey by embracing cutting-
edge technologies. Leveraging the power of artificial intelligence and machine learning,
Mercedes-Benz Consulting partners with Amazon Web Services (AWS) to harness the
capabilities of Amazon SageMaker, a fully managed machine learning service.

The collaboration between Mercedes-Benz Consulting and AWS represents a strategic


initiative aimed at revolutionizing customer support within the automotive industry. By
harnessing the advanced capabilities of Amazon SageMaker, Mercedes-Benz Consulting
endeavours to develop a sophisticated question-and-answer (Q&A) digital assistant
capable of understanding and responding to natural language queries in real-time. This
innovative solution promises to empower customers with instant access to accurate
information while alleviating the burden on customer support teams.
NAME AND LOCATION OF THE COMPANY

Name:
Mercedes-Benz Consulting GmbH
Location:
Mercedes-Benz Consulting GmbH
Esslinger Str. 1
70771 Leinfelden-Echterdingen
Germany

CUSTOMER SEGMENT:

Existing Mercedes-Benz customers: This segment includes individuals who have


purchased or leased vehicles from Mercedes-Benz or have engaged with the brand in
some capacity. These customers may have inquiries related to vehicle features,
maintenance, warranties, and services.

Prospective Mercedes-Benz customers: This segment comprises individuals who are


considering purchasing or leasing a Mercedes-Benz vehicle or are interested in learning
more about the brand. They may have questions about vehicle models, pricing, features,
and comparisons with other automotive brands.

Mercedes-Benz enthusiasts: This segment consists of individuals who have a strong


affinity for the Mercedes-Benz brand and may actively engage with the brand through
online forums, social media channels, and community events. They may seek
information about the latest products, brand heritage, and exclusive offers.

Mercedes-Benz owners' associations and clubs: This segment includes members of


official Mercedes-Benz owners' associations and clubs who are passionate about the
brand and its products. They may have specialized inquiries related to club activities,
events, and member benefits.

Mercedes-Benz dealership personnel: This segment encompasses sales


representatives, service advisors, and other dealership staff who interact directly with
customers on behalf of Mercedes-Benz. They may require access to comprehensive
product information and support resources to assist customers effectively.

Identifying and understanding these customer segments will enable Mercedes-Benz


Consulting to tailor the Q&A digital assistant powered by Amazon SageMaker to meet
the specific needs and preferences of each segment. By providing personalized and
timely support, Mercedes-Benz Consulting can enhance customer satisfaction, drive
engagement, and foster long-term loyalty within its customer base.
INDUSTRY DOMAIN:

Consulting and Services in the Automotive Sector


The industry domain of consulting and services in the automotive sector encompasses a
wide range of activities aimed at providing specialized expertise, guidance, and support
to automotive companies, manufacturers, dealerships, and related businesses. Within
this domain, consulting firms offer strategic advice, market research, business process
optimization, and technology solutions tailored to the unique needs and challenges of the
automotive industry. Additionally, service providers offer a variety of services such as
vehicle maintenance and repair, parts distribution, logistics, and customer support. This
dynamic and rapidly evolving sector plays a crucial role in driving innovation, efficiency,
and growth across the automotive value chain, ultimately contributing to the success and
competitiveness of automotive businesses in a highly competitive global market.

EXISTING PROBLEM:

Mercedes-Benz Consulting faces challenges in providing efficient and effective


customer support due to the need for timely and accurate responses to inquiries
related to their vehicles, services, and brand.
Mercedes-Benz Consulting encounters hurdles in delivering efficient customer support,
attributed to the imperative for swift and precise responses to inquiries concerning
their vehicles, services, and brand. The necessity for timely assistance across a spectrum
of inquiries poses a challenge in maintaining a high standard of customer satisfaction.
Addressing these inquiries accurately and promptly is crucial for enhancing customer
experiences and fostering brand loyalty. However, the existing framework may lack the
agility and accuracy required to meet these demands effectively, necessitating a
strategic solution to optimize customer support processes and elevate overall service
quality.
SERVICES USED:

1. Amazon Sage Maker:


- Build, train, and deploy machine learning (ML) models for any use case with fully
managed infrastructure, tools, and workflows.

2. Amazon Glue
- Discover, prepare, and integrate all your data at any scale.

3. Amazon Professional Services

- AWS Professional Services’ offerings use a unique methodology based on Amazon’s


internal best practices to help you complete projects faster and more reliably, while
accounting for evolving expectations and dynamic team structures along the way.

4. Amazon OpenSearch Service

- Securely unlock real-time search, monitoring, and analysis of business and


operational data.

SOLUTION TO THE PROBLEM

Mercedes-Benz Consulting needed to architect a strong foundation for its data sources,
and it took a serverless-first approach. When employees ask a question of the AI solution,
the process starts with data going through the extract, transform, load process. To
automate the migration of data, Mercedes-Benz Consulting uses AWS Lambda, a
serverless, event-driven compute service. This data is then processed and cleaned
using AWS Glue, a serverless data integration service that makes it simple to discover,
prepare, move, and integrate data from multiple sources.

Another important component of the solution is the processing of natural language. Here,
text needs to be converted to numbers using embeddings. For its ML model development,
monitoring, and deployment, Mercedes-Benz Consulting uses Amazon SageMaker, a
service to build, train, and deploy ML models. The company can also use Amazon
SageMaker to integrate open-source ML models from Hugging Face while keeping control
of its data. These data embeddings are then accessed by Amazon OpenSearch Service,
which is used to securely unlock near-real-time search, monitoring, and analysis of
business and operational data. The embeddings then go through a vector search, and the
AI solution provides the answer to the initial question.

The speed and accuracy of this solution helps improve staff productivity at Mercedes-
Benz Consulting. The company’s goal is for the top three returned results of any query to
contain all the relevant information, with the first result providing the best answer to the
question. One metric for measuring accuracy is the percentage of questions with positive
user feedback from qualified users. The speed and accuracy of answers saves time and
effort for employees, especially new hires, when searching for information.

By building this AI product, the company helps drive innovation at Mercedes-Benz


Consulting. Developers can work more efficiently using the AI assistant, and searching for
information by asking questions in natural language eases workflow friction across the
company. Additionally, using AWS for this solution reduced its time to market

“Using AWS, we created a cutting-edge system that allows our company to bring our ways
of using internal knowledge to a completely new level,” says Dr. Marcel Graus, head of
data and tech at Mercedes-Benz Consulting.

CONCLUSION:

Mercedes-Benz Consulting is in the process of developing innovative solutions for


multiple internal clients using mature AI technology that is flexible, scalable, and secure.
Although
the new application is already in use within Mercedes-Benz Consulting, the company
wants to expand its solution for use in workshops and on showroom floors.

“With this AWS engagement and everything we’ve developed in the past year, we have
moved our focus from doing projects to creating products,” says Dr. Chadha. “We have
learned to build in a flexible, scalable manner so that we can incorporate user
requirements and develop our system further.”

REFERENCES:

1. https://www.simplilearn.com/tutorials/aws-tutorial/aws-sagemaker

2. https://www.mercedes-benz-consulting.de/en/cases/marie-our-digital-assistant/

3. https://aws.amazon.com/solutions/case-studies/mercedes-benz-consulting/

You might also like