Hi everyone. This is Kar Kti man from Frisco, Texas. I'm an SAP project manager, having long one years of experience in SAP and almost la 14 years of experience as a project manager. In last seven, eight years, I did almost less seven s 400 implementations. And how experience of working with the different industries like manufacturing, healthcare agriculture, pharma and chemical industries, and also food and beverage industries. Today I'm going to talk about SAPA, transfer me to power technical insight and industry specific applications. We all know that SAP is an ERP system and also now the world. AI is sticking over the, all the technologies. So let's see how SAP and AI is integrated together for this ERP business. For multiple industries, SAP artificial intelligence capabilities are izing multiple industries through tailored intelligent application built on the business technology platform, BTP. That is one of the package from SAP. SAP AI seamlessly integrates with existing enterprise systems while providing sophisticated machine learning, natural language processing, and VE and capabilities. These presentation explores how SAP AI leverage is multi-layered architecture to address industry specific challenges across retail healthcare. Supply chain energy and agriculture sectors. Let's see the detailed presentations. SAP, business Technology Platform, SAP, ai, core Architectures. Let's see how business technology platforms and the service are integrated with the ASAP AI core architecture, business technology platforms integration layer, API management and data orchestration capabilities that form the foundation of SAP ai. Solutions. And also SAP says that machine learning services classifications regression clustering and an MLA detection algorithm that power intelligent applications, natural language processing, entity extraction, sentiment analysis and document understanding capability, work and structured data, computer vision object detection, defect identification, visual inspection technologies for image analysis. Let's see. So SAP and e-commerce applications working together to help the retail and e-commerce applications recommendation engines. SAP AI recommends system employ collaborative filter algorithms combined with content based filtering to create hybrid models. Text the Select personalization. These models analyze customer interaction, purchase history, browsing patterns to generate relevant product suggestions. The implementation in Cooperates Metric Federation techniques for identifying data and futures and deep learning neural networks for processing and structured data means. SAP is helping to model, analyze the customer interactions and also sure, also, gather the purchase histories, the browsing patterns, and generate relevant product suggestions. And let's see, demand forecasting for inventory optimization. SAP integrate times and series analysis. External factors such as market trends, seasonal variations, and social media sentiment. Dark picture includes LSTM Network to capture long term dependencies in time series data. The systems typically employ and symbol methods. Combining LLST and networks with traditional RMI models achieving high forecast accuracy rates for short term and medium term projections, demand forecasting and SAP is playing a crucial role, the help of AI in this ERP World Extra Healthcare application. How it's helping care applications with the AI optimization patient admission prediction. SAP healthcare AI solution utilize multi-variate regression models and classification algorithms to predict admission rates with remarkable accuracy. These systems analyze historical admission data. Seasonal illness patterns, local event calendar, population demography, and current facility utilization rates. It clearly says that it is collecting the illness patterns and also the local event calendars with the helping patient admission predictions to the hospitals. And next care enhancement early. This is a detection, leverages natural language processing to mine un unstructured clinical notes alongside structured patient data. The system employs transfer based models for text analysis, anomaly detection algorithm to identify clear inpatient metrics and secure data processing that maintains the HIPAA compliances. It's also helping the hospitals to make sure they're following the HIPAA compliance processes by. Following patterns which I provided with the help of SAP clinical impact facilities employing advanced NLP for a clinical nurse analysis report. Early introduction, increase for high risk condition, corresponding reductions in acute admission per monitor condition, translating to average cost reduction per patient. It is like also helping in the cost reduction and high risk introductions eye finding acute admissions. Okay, now let's see. SAP integration with ai. Applications for manufacturing company data collections. LOD sensor Gather equipment, elementary and operational data in the real time pattern analysis algorithm, identify, anomaly and predict. Potential failures. Maintenance planning systems schedules optimal interaction before failures occur. Performance optimization, continuous learning, improves prediction accuracy over time. Manufacturing facilitates employing advance and predict to maintenance show unplanned downtime reductions up to 50%. And maintenance cost decrease of what, 10 to 40% compared to traditional scheduled maintenance approaches. These systems typically monitor thousands of sensor per facility with edge computing, noise processing, terabytes of equipment, elementary data daily. Here we can clearly see that SAP integration with AI is helping good data collection, pattern analysis, maintenance planning, performance, or optimization, which is like helping the manufacturing industries to get an advanced prediction maintenance. Which is which shows like it'll also helping to unplanned downtime duction up to 50%. Next quality with computer vision image capture. Analysis defect classification, product integration, image capture, high resolution camera capture, detailed image of product on the production line. AI analysis, conventional natural network analysis, images, defects with the precision exceeding human inspection defect classification system categorized defects by type and CVRT. Enabling target process implements means. The quality of the images increased and also AI is going to analyze the neural network analysis images, detect defects. If you see any precision exceeding human inspection, production integration, real-time feedback to manufacturing system enables immediate process adjustments. CN based inspection system detect up to 99% of surface defects and structural cy compared to 80 to 90% per traditional machine vision systems and human inspectors. The economic impact translate to documented disease in customer reported quality issues and assert variant claim reduction. So it is also helping to reduce the claim reductions and decrease in the customer reported quality issues. Finance and banking applications. So finance and banking are the most important. And let's see, the fraud detection, the document understanding explainable AI financial processing. Nowadays we are seeing like most of the financial institutes that using, aI platforms are AI apps. So instead of talking to the human, the AI will provide all the informations and it is the banks and everyone is saying that is an accurate information. Let's see how it is going to detect the fraud graph neural networks model relationship between the entities to identify suspicions. Pattern means it's also detect the fraud if any unauthorized persons are trying to use your accounts. P transforms. Explainable AI shop and line framework generate transparent decision and rationals financial forecasting reinforcement learning, optimiz prediction across it. Also forecast for some of the apps, it forecast the financials so that you can plan accordingly. For example, if you take in stock markets, it'll give the predictions and based on that, you can invest on your stocks. SAP's fraud detection capabilities employs adaptive graphic neural networks with optimized message passing mechanism. That analysis system's ability to identify abnormal patterns with complex financial network demonstrating market improved meant over traditional rule-based systems means it is overall, it is helping the financial industries on the market based and traditional rule based systems, supply chain. Let's see how supply chain is integrated with SAP AI and how it is helping the supply chain departments route optimization. Multi objective, visionary algorithms, balance, cost, time, and environmental impact while respecting real world constraints. Early warning systems and simple methods. Monitor diverse data streams to identify potential disruptions before the impact operations. Digital supply chain twins. Virtual representation enable scenario planning through sophisticated simulation capabilities. Dynamic rerouting automatic response to emerging constraints without requiring manual intervention means it is taking optimization, is giving early warning systems and also a digital supply chain with the dynamic routing with the automatic response. Energy and utility management. Consumption optimization, balancing multiple objectives in the cost. Demanding grid capability means it, it also give you the grid capability means like when you open your energy, app, which you are using for your home. It gives all the information renewable energy forecasting, hybrid models, combining physics based and machine learning approaches not only for your home based apps. It is for entire industry, for utility industries. And also for any manufacturing industry any industries which are using energy storage optimization, determining optimal charging and discharging cycles for diverse technologies, microgrid management, enabling reason and power delivery through sophisticated balancing systems. SAP AI implements competency energy management solutions that leverage reinforcement learning techniques to optimize conception patterns across complex utility. Networks implementation study demonstrate these approaches deliver substantial improvements in key energy management metrics, including e load reduction, overall consumption efficiency, renewable energy utilization rates. So here you can clearly see that the bottom, it says that it is really helping the energy and utility management industry saying that low reduction consumption efficiencies and renewable energy rates. Agriculture decision support satellite energy analysis means it analysis the computer vision algorithm extract actionable insights from multi-spectral data, enabling earlier interaction for developing issues including moisture stress, new newly deficiency and pesty fixations. So environmental mon monitoring field levels, sensor networks, providing granular data on soil conditions. Micro variation, crop development, creating a multi-dimensional view of agriculture operations. Yield prediction gradient. Booster edition trees captures non-linear relations between environmental conditions, management practice, and crop genetic to predict production outcomes with high accuracy. It's helping satellite imaging analysis, environment monitoring and yield production. Technical benefits of SAPI implementations a hundred percent enterprise integration, seamless connectivity with existing S-R-P-S-A-P-E-R-P and business systems. 99.9% system availability, high reliability across mutual deployments, and thousand extra query performance faster than traditional database architectures. And 24 by seven continuous learning. Self BR system that adapt to changing conditions. So these A EA solutions deliver substantial technical advantages through an architectural approach that emphasizes enterprise integration, scalability, continuous improvement, and security. This compromise approach to enterprise AI represents a fundamental advance beyond isolated machine learning projects, transforming the theoretical into practical business. Through integration with operational realities. Thank you. This is my today's presentation. Hope you all like it. Thank you once again. Thank you very much.