I am new proyxsg and dlp user. Please tell me how to solve below questoin.
I have a proxysg(version 6.7) and DLP(15.5). When I intergrate with both, then health check, the proysg shows “health check has failed”. Can anyone help me what should I do for successful integration. Thanks.
I am just wondering if we could block one specific google document url https://drive.google.com/file/d/xxxxxxxxxxxxxxxxxxxxxxx/view?usp=drive_web
I do not want to block the whole domain but only that google document url.
I have tried:
Those didn’t work.
Machine learning (ML) and emerging artificial intelligence (AI) are empowering “data-driven digital ecosystems” that can analyze vast volumes of data for insight to improve outcomes—and to get continually smarter and smarter at doing so.
As part of our own digital transformation in Services, we are using these techniques to pioneer new and better ways to serve customers. Our data science teams have identified the enormous potential of AI/ML in multiple business areas. We utilize it in our proactive, predictive support capabilities and it’s playing a significant role in our supply chain. Jeff Clarke predicted that supply chains will get stronger and smarter in 2019 and the Global Service Parts team is delivering on that vision, taking advantage of AI/ML to deliver a better customer repair experience.
Applying Predictive, ML, AI and Operational Research Methodologies to Unlock New Insights
Dell EMC Services has been collecting and analyzing data from our service parts supply chain for years. Today, our Global Service Parts organization manages procurement, inventory, repair, and the recycling of parts for 100+ million products at customer sites under warranty or service agreement in 160+ countries around the world.
Massive amounts of historical and near real-time service parts data―tracking the lifecycle of parts as they move in and out of our 800+ warehouses and to and from customer sites―provides a rich trove of data for unlocking new insights.
So what type of actions can we take based on the insights we extract from all that data?
To continue innovation and evolution of our supply chain, we applied predictive, ML, AI and operational research methodologies in two areas for:
Let’s take a look at what each of these means to our business, and most importantly, to our customers.
Sharper Forecasting, with Less Human Effort
The unpredictability of immediate, short- and long-term demand for repair parts makes accurate forecasting an ongoing challenge. To tackle this, our experienced parts planners and data scientists worked together to develop and supervise a data-driven digital ecosystem that uses machine learning to identify and prioritize variables, build predictive models, and generate plans to more precisely pre-position inventory across the globe.
Today, about 35% of our planning is generated autonomously, without human input, greatly reducing the amount of time our expert resources spend on the front end of this process. Once plans are generated, our parts planners have only to review and adjust them before they are approved. We are confident that as the planning tool continues to “learn” from planner modifications and usage patterns, and as AI continues to evolve, we will be able to rely on a fully autonomous planning tool in the next few years, freeing our planners to focus on more complex issues and additional tool development.
Smarter Repair, with Reverse Supply Chain Data
When a repair is needed, of course, we want to make the process as quick and efficient as possible so we are using data science techniques in this area as well.
We use reverse supply chain data―data that comes from built-in system diagnostics, tech support workflow, hands-on diagnostics, defective part evaluations, and other sources. It informs predictive analytics that help us identify the likelihood of failures and helps accelerate repair times.
Our new predictive repair engine combines relevant data and identifies patterns to recommend what parts will be needed before a unit arrives at the repair depot, so a swap-out can be quickly completed. In an initial pilot, we achieved 80% accuracy in identifying the correct part, reducing the movement of parts by 15%, and cutting time-to-repair by 20 minutes. Efficiencies continue to improve, as the technology learns from confirmation of accurate recommendations and correction of inaccurate ones. The repair engine also learns from extensive, post-event failure analysis of parts at the repair depot, improving diagnoses and providing valuable information to product engineers working on next-generation systems.
This predictive repair engine is also making our supply chain greener and more efficient, by helping to reduce waste and shipping, and the need to manufacture and manage as many parts in the first place.
Better and Better Service Experience for Our Customers
Emerging AI technologies, machine learning and other innovative techniques are helping us get smarter and smarter so we can minimize disruption and inconvenience, prevent issues or resolve them faster, and make technology simpler for all of us.
|Update your feed preferences|