1 00:00:03,480 --> 00:00:07,440 Speaker 1: Workplaces like factories or fulfillment centers are filled with many 2 00:00:07,480 --> 00:00:11,319 Speaker 1: moving parts and require constant supervision and alertness to ensure 3 00:00:11,400 --> 00:00:17,120 Speaker 1: worker safety. But what happens when errors or accidents happen 4 00:00:17,239 --> 00:00:21,079 Speaker 1: unexpectedly On the simplest level, it creates chaos and can 5 00:00:21,120 --> 00:00:24,520 Speaker 1: impact productivity. On a larger scale, can create a dangerous 6 00:00:24,600 --> 00:00:29,200 Speaker 1: environment for employees. How can technology like AI and the 7 00:00:29,240 --> 00:00:32,879 Speaker 1: creation of a digital twin help quickly correct errors and 8 00:00:33,000 --> 00:00:37,760 Speaker 1: prevent accidents before they occur? And could these virtual replications 9 00:00:37,760 --> 00:00:40,639 Speaker 1: of a physical space ensure workers go home to their 10 00:00:40,640 --> 00:00:44,599 Speaker 1: families safe and sound. Join us as we learn more 11 00:00:44,600 --> 00:00:47,680 Speaker 1: about the world of digital twins and the many ways 12 00:00:47,800 --> 00:00:53,920 Speaker 1: they can not only improve workplace safety, but also public safety. 13 00:00:55,160 --> 00:00:58,960 Speaker 1: Welcome to Technically Speaking, an Intel podcast, the show that 14 00:00:58,960 --> 00:01:02,160 Speaker 1: brings you the stories and insights of AI, presented by 15 00:01:02,200 --> 00:01:08,560 Speaker 1: iHeartMedia's Ruby Studio and Intel. Hey there, I'm gram class. Today, 16 00:01:08,640 --> 00:01:12,480 Speaker 1: we're exploring the spaces and places replicated by digital twins 17 00:01:13,080 --> 00:01:16,720 Speaker 1: for starters, what is a digital twin? We're going to 18 00:01:16,760 --> 00:01:20,319 Speaker 1: be examining digital spaces that represent an actual physical space 19 00:01:20,520 --> 00:01:23,839 Speaker 1: in our world. To discuss the topic further, We're joined 20 00:01:23,840 --> 00:01:29,640 Speaker 1: by Tony Franklin. Tony Franklin is the general manager of 21 00:01:29,680 --> 00:01:34,080 Speaker 1: the Federal and Aerospace Markets, which includes military, aerospace, and 22 00:01:34,120 --> 00:01:36,760 Speaker 1: Government within the Network and Edge Group. He has more 23 00:01:36,800 --> 00:01:41,240 Speaker 1: than twenty years of corporate entrepreneurial, business development and management experience, 24 00:01:41,840 --> 00:01:45,399 Speaker 1: focusing on starting and growing multiple businesses that apply to 25 00:01:45,600 --> 00:01:51,280 Speaker 1: the Internet of Things, intelligence systems, and communications technologies. Intel's 26 00:01:51,280 --> 00:01:54,200 Speaker 1: Network and Edge Group provide solutions that lead the industry 27 00:01:54,240 --> 00:01:57,400 Speaker 1: and transforming businesses and the way we live are making 28 00:01:57,440 --> 00:02:02,040 Speaker 1: it simple to create exciting new buyetis Welcome to the show. 29 00:02:01,840 --> 00:02:05,840 Speaker 2: Tony, Thank you, Thank you, glad to be here. 30 00:02:06,120 --> 00:02:09,320 Speaker 1: We've seen a lot of science fiction depictions of digital 31 00:02:09,320 --> 00:02:12,040 Speaker 1: twins over the years and movies and films. The one 32 00:02:12,080 --> 00:02:14,679 Speaker 1: that comes to mind is the matrix. But the entire 33 00:02:14,720 --> 00:02:18,520 Speaker 1: world is a digital twin. Although it's a useful sinister motives. 34 00:02:19,240 --> 00:02:21,320 Speaker 1: I'd like to get your definition of what a digital 35 00:02:21,360 --> 00:02:21,760 Speaker 1: twin is. 36 00:02:22,360 --> 00:02:24,360 Speaker 2: Yeah. Sure, it's interesting you said the matrix. 37 00:02:24,360 --> 00:02:26,519 Speaker 3: I had to laugh because of all the examples we've 38 00:02:26,600 --> 00:02:28,960 Speaker 3: joked about, that's one that hasn't come up, and it's 39 00:02:29,040 --> 00:02:31,480 Speaker 3: so obvious when you said it. I'll start to use 40 00:02:31,560 --> 00:02:34,720 Speaker 3: that in its simplest form from me a digital twin 41 00:02:34,840 --> 00:02:37,520 Speaker 3: is the digital replica of the real world. 42 00:02:38,200 --> 00:02:41,680 Speaker 1: And in terms of the technologies that are out there 43 00:02:42,200 --> 00:02:46,280 Speaker 1: needed for digital twining, maybe you could describe a little 44 00:02:46,280 --> 00:02:50,480 Speaker 1: bit of how those sorts of systems are put together 45 00:02:50,560 --> 00:02:54,440 Speaker 1: and what are some of the technology that Intel has 46 00:02:54,560 --> 00:02:55,520 Speaker 1: that can help that. 47 00:02:56,200 --> 00:02:56,480 Speaker 2: Yeah. 48 00:02:56,520 --> 00:03:00,720 Speaker 3: Sure, it's really been an evolution of technologies that some 49 00:03:00,800 --> 00:03:02,920 Speaker 3: of them were all used to using, and some of them, 50 00:03:03,080 --> 00:03:04,560 Speaker 3: you know, if you're not in the field, maybe not 51 00:03:04,639 --> 00:03:08,079 Speaker 3: so much. And so Gartner, one of the well known analysts, 52 00:03:08,120 --> 00:03:12,520 Speaker 3: has this Emerging Technologies trending chart they do every year, 53 00:03:13,080 --> 00:03:16,600 Speaker 3: and they talk about edge AI, so artificial intelligence at 54 00:03:16,680 --> 00:03:19,400 Speaker 3: the edge, you know, the place where data is actually 55 00:03:19,400 --> 00:03:21,600 Speaker 3: being generated more so than in say the cloud or 56 00:03:21,680 --> 00:03:25,720 Speaker 3: data centers. That's happening, It continues to evolve, it's growing 57 00:03:25,760 --> 00:03:28,040 Speaker 3: more and more. We're pushing more and more intelligence to 58 00:03:28,200 --> 00:03:29,840 Speaker 3: the edge. And by the edge, it could be everything 59 00:03:29,880 --> 00:03:32,160 Speaker 3: from a cell phone or refrigerator or a car. Again, 60 00:03:32,200 --> 00:03:35,680 Speaker 3: where is the data actually being generated. And then they 61 00:03:35,720 --> 00:03:38,840 Speaker 3: talk about digital twins being sort of the now to 62 00:03:39,000 --> 00:03:41,400 Speaker 3: three years. I think one of their data points was 63 00:03:41,400 --> 00:03:45,680 Speaker 3: something like forty percent of businesses, large businesses in particular 64 00:03:45,840 --> 00:03:47,920 Speaker 3: plan to use digital twins over the next two to 65 00:03:47,960 --> 00:03:50,680 Speaker 3: three years to actually generate revenue. So that's happening now, 66 00:03:51,120 --> 00:03:53,720 Speaker 3: and then lastly over the next maybe six plus years, 67 00:03:53,720 --> 00:03:55,960 Speaker 3: they talk about the metaverse. Now, while we don't generally 68 00:03:55,960 --> 00:03:58,880 Speaker 3: talk about the metaverse as much, the name means different 69 00:03:58,920 --> 00:04:01,240 Speaker 3: things to different people, but it's the full extent of 70 00:04:01,560 --> 00:04:05,280 Speaker 3: how it does. Commerce and any other business really leverage 71 00:04:05,280 --> 00:04:10,680 Speaker 3: a fully digital space that has interaction with the real world. 72 00:04:10,800 --> 00:04:14,080 Speaker 3: So there's this spectrum that has been happening between sensors, 73 00:04:14,360 --> 00:04:17,400 Speaker 3: with cameras being the most obvious because we're all using 74 00:04:17,960 --> 00:04:20,800 Speaker 3: cameras today. Our phones have so many sensors, we take 75 00:04:20,839 --> 00:04:23,200 Speaker 3: them for granted. But all the sensors, one of the 76 00:04:23,240 --> 00:04:27,840 Speaker 3: key technologies that are needed an ability to replicate if 77 00:04:27,920 --> 00:04:32,120 Speaker 3: you're doing visual digital twins, so an ability to replicate 78 00:04:32,200 --> 00:04:34,600 Speaker 3: the real world, and of course physics modeling if you're 79 00:04:34,640 --> 00:04:37,680 Speaker 3: really doing analysis and you need to replicate the physical 80 00:04:37,760 --> 00:04:41,960 Speaker 3: asset in a digital world, So computing capability to be 81 00:04:42,000 --> 00:04:46,919 Speaker 3: able to replicate the behavior of the object, with AI 82 00:04:47,000 --> 00:04:50,479 Speaker 3: being a critical component to now actually apply intelligence and 83 00:04:50,560 --> 00:04:53,920 Speaker 3: analysis to the twin. So when you think about those 84 00:04:53,920 --> 00:04:56,880 Speaker 3: different areas well, intel, we don't make sensors. Everything else 85 00:04:56,920 --> 00:04:59,800 Speaker 3: along the way is where we tend to play clearly 86 00:05:00,040 --> 00:05:03,800 Speaker 3: muting technology the ability to apply AI, so both from 87 00:05:03,800 --> 00:05:08,160 Speaker 3: the software side and the various different computing technologies that 88 00:05:08,400 --> 00:05:14,440 Speaker 3: enable AI, whether it's processors or GPUs, are AI accelerators, 89 00:05:14,560 --> 00:05:17,440 Speaker 3: et cetera. And then of course we have a very broad, 90 00:05:17,920 --> 00:05:21,840 Speaker 3: really world class partnership and ecosystem that we work with 91 00:05:21,920 --> 00:05:23,560 Speaker 3: to enable the different industries. 92 00:05:24,279 --> 00:05:26,520 Speaker 1: Okay, and in terms of trying to get like a 93 00:05:26,600 --> 00:05:30,520 Speaker 1: visual kind of representation of what this would look like. 94 00:05:30,600 --> 00:05:33,720 Speaker 1: So say if you're walking in a warehouse, for example, 95 00:05:33,960 --> 00:05:35,840 Speaker 1: and you're looking at the shelves around you, you might 96 00:05:35,880 --> 00:05:39,599 Speaker 1: see some conveyor belts. How would it actually look in 97 00:05:39,640 --> 00:05:43,520 Speaker 1: a digital twin? It depends on the use case. The 98 00:05:44,000 --> 00:05:47,360 Speaker 1: simplest version i'd use that many people should be able 99 00:05:47,400 --> 00:05:49,560 Speaker 1: to relate to. Obviously many people can relate to matrix. 100 00:05:49,600 --> 00:05:53,120 Speaker 1: But from an application standpoint, I would say think about 101 00:05:53,360 --> 00:05:58,279 Speaker 1: Google Earth or Google Maps. Even that is a type 102 00:05:58,320 --> 00:06:01,560 Speaker 1: of model right. Another example is many of the retail 103 00:06:01,600 --> 00:06:08,080 Speaker 1: applications allow you to basically embed their items that are 104 00:06:08,080 --> 00:06:13,440 Speaker 1: for sale into the digital replication of your particular space, 105 00:06:13,640 --> 00:06:17,320 Speaker 1: so it's a real world and digital combination. That's always 106 00:06:17,360 --> 00:06:17,720 Speaker 1: the key. 107 00:06:18,000 --> 00:06:21,360 Speaker 3: So those are very basic, simple applications that people use 108 00:06:21,560 --> 00:06:23,440 Speaker 3: and don't even realize. They don't think about them as 109 00:06:23,480 --> 00:06:26,760 Speaker 3: digital twins, but they're already getting used to this relationship 110 00:06:26,760 --> 00:06:29,480 Speaker 3: between the real world and the digital world. 111 00:06:29,960 --> 00:06:30,560 Speaker 2: Yes, I saw. 112 00:06:30,600 --> 00:06:33,760 Speaker 1: Intel has a software platform called Scenscape that can transform 113 00:06:33,839 --> 00:06:36,520 Speaker 1: data from this world of senses to create a real 114 00:06:36,560 --> 00:06:39,480 Speaker 1: time digital twin of your physical space. Can you tell 115 00:06:39,480 --> 00:06:41,000 Speaker 1: me a little bit more of how that works? 116 00:06:41,560 --> 00:06:44,840 Speaker 3: So there's really three basic steps. One is mapping your space. 117 00:06:45,360 --> 00:06:48,800 Speaker 3: The key though in the type of real time digital 118 00:06:48,839 --> 00:06:54,000 Speaker 3: twinning that we pursue is it is a coordinate, accurate space, 119 00:06:54,200 --> 00:06:56,560 Speaker 3: So it's not just taking a random space. We know 120 00:06:56,680 --> 00:06:58,800 Speaker 3: that that room is twenty feet by twenty five feet, 121 00:06:58,800 --> 00:07:02,240 Speaker 3: and we also know that the cameras are six feet 122 00:07:02,320 --> 00:07:06,120 Speaker 3: up on the wall. We know the actual XYZ of 123 00:07:06,160 --> 00:07:08,920 Speaker 3: the space, So that's the first step. Second step is 124 00:07:09,400 --> 00:07:12,680 Speaker 3: calibrate the space. So calibrate meaning I have the space, 125 00:07:13,080 --> 00:07:15,880 Speaker 3: where are my sensors? So my sensor is ten feet up, 126 00:07:15,920 --> 00:07:19,040 Speaker 3: four feet over in that corner, etc. Now you turn 127 00:07:19,080 --> 00:07:22,760 Speaker 3: on your sensors and you ingest that into scenescape. Notice 128 00:07:22,800 --> 00:07:26,800 Speaker 3: I haven't actually visualized necessarily anything. So the key for 129 00:07:26,840 --> 00:07:29,840 Speaker 3: people to realize in real time digital twinning. There are 130 00:07:29,840 --> 00:07:32,360 Speaker 3: some applications where someone's not actually going to be sitting 131 00:07:32,400 --> 00:07:35,920 Speaker 3: there watching the digital twin of the store. They don't 132 00:07:35,960 --> 00:07:40,680 Speaker 3: need to do that real time. The AI and computing obviously, 133 00:07:40,720 --> 00:07:45,080 Speaker 3: the AI tools and the actual AI models, the inferencing 134 00:07:45,160 --> 00:07:50,520 Speaker 3: capability of scenescape is doing the work. You are configuring 135 00:07:50,560 --> 00:07:53,160 Speaker 3: it so you could add things like heat maps or 136 00:07:53,200 --> 00:07:57,960 Speaker 3: trip wise so that you can actually have events based 137 00:07:58,000 --> 00:08:01,880 Speaker 3: on whatever policy you want to implement, so that you 138 00:08:01,920 --> 00:08:04,720 Speaker 3: don't have to actually monitor. So I'll know that over 139 00:08:04,760 --> 00:08:08,040 Speaker 3: in this area of the meat department, if there's more 140 00:08:08,080 --> 00:08:11,360 Speaker 3: than twenty people for twenty seconds, there's something that happens. 141 00:08:11,800 --> 00:08:13,920 Speaker 3: I don't even have to watch anything for that. The 142 00:08:13,960 --> 00:08:15,800 Speaker 3: intelligence is making it happen. 143 00:08:15,840 --> 00:08:16,320 Speaker 2: Gotcha. 144 00:08:16,440 --> 00:08:20,200 Speaker 3: Now, if what I want to do later is now 145 00:08:20,440 --> 00:08:23,520 Speaker 3: hit the rewind button. The founder and creator for this 146 00:08:23,520 --> 00:08:25,520 Speaker 3: particular product, he has a phrase I'd love to use. 147 00:08:25,560 --> 00:08:29,200 Speaker 3: It's called the DVR for the real world. AI is 148 00:08:29,240 --> 00:08:33,520 Speaker 3: happening real time, but if you want additional analysis afterwards, 149 00:08:33,600 --> 00:08:34,800 Speaker 3: you have that capability. 150 00:08:35,400 --> 00:08:38,000 Speaker 1: I can imagine there's a lot of challenges trying to 151 00:08:38,200 --> 00:08:41,120 Speaker 1: come up with these digital twins. What are some of 152 00:08:41,120 --> 00:08:45,160 Speaker 1: the top challenges or issues that people who are looking 153 00:08:45,200 --> 00:08:48,080 Speaker 1: to try and deploy these sorts of systems would have 154 00:08:48,120 --> 00:08:48,680 Speaker 1: to consider. 155 00:08:49,440 --> 00:08:53,720 Speaker 3: The most prominent one, to be honest with you, is 156 00:08:53,880 --> 00:08:58,200 Speaker 3: the mindset more than anything technical. You think about some 157 00:08:58,320 --> 00:09:02,760 Speaker 3: of the technology that's growing in our own home, Siri, Alexa, 158 00:09:03,440 --> 00:09:07,440 Speaker 3: are cars. There's so much technology and most people really 159 00:09:07,440 --> 00:09:11,360 Speaker 3: don't understand you're already using AI. In many cases, you're 160 00:09:11,360 --> 00:09:14,360 Speaker 3: already using some sort of digital twin technology. There was 161 00:09:14,400 --> 00:09:16,800 Speaker 3: one demo we had for Sea Escape and the executive 162 00:09:16,880 --> 00:09:18,920 Speaker 3: loved it. It's like, this is amazing. I can do 163 00:09:19,000 --> 00:09:21,600 Speaker 3: motion tracking. I see where people are. I can have 164 00:09:21,720 --> 00:09:26,079 Speaker 3: multiple cameras monitoring the same asset, our person or object, 165 00:09:26,080 --> 00:09:28,840 Speaker 3: but I only see one, so it deduplicates the person. 166 00:09:29,440 --> 00:09:32,080 Speaker 3: I can track withf somebody's been in a space. Maybe 167 00:09:32,120 --> 00:09:34,920 Speaker 3: I have a radiation sensor and I can actually track 168 00:09:35,000 --> 00:09:37,000 Speaker 3: how long that person has been in the space, and 169 00:09:37,040 --> 00:09:39,800 Speaker 3: I can set triggers. There's so much he saw that 170 00:09:39,880 --> 00:09:43,080 Speaker 3: can be done, and he was so excited and he said, 171 00:09:43,080 --> 00:09:46,000 Speaker 3: where's the AI, right, Well, it's the AI that's doing 172 00:09:46,000 --> 00:09:49,600 Speaker 3: everything you just described. That's right, you just like and 173 00:09:49,640 --> 00:09:52,240 Speaker 3: it actually set us back for a second. We're like, well, clearly, 174 00:09:52,800 --> 00:09:54,920 Speaker 3: we need to make sure we understand where people are 175 00:09:54,960 --> 00:09:58,319 Speaker 3: starting from. We can't assume they already know there's a 176 00:09:58,400 --> 00:10:02,280 Speaker 3: level of technology and integration of their technology. 177 00:10:03,760 --> 00:10:05,720 Speaker 1: And that's one of the biggest challenges when it comes 178 00:10:05,720 --> 00:10:09,880 Speaker 1: to understanding digital twin technology. It's the messaging some of 179 00:10:09,880 --> 00:10:12,640 Speaker 1: the very tools that you're accustomed to right now, like 180 00:10:12,800 --> 00:10:15,000 Speaker 1: the cell phone or the smart speaker that you or 181 00:10:15,080 --> 00:10:18,600 Speaker 1: listening to this podcast with essential when we consider the 182 00:10:18,640 --> 00:10:21,120 Speaker 1: future of digital twinning. So when it comes to a 183 00:10:21,160 --> 00:10:25,079 Speaker 1: future that incorporates AI into our daily lives, we've actually 184 00:10:25,200 --> 00:10:30,480 Speaker 1: already taken the first steps down that path. One of 185 00:10:30,480 --> 00:10:34,000 Speaker 1: the things I like to examine is the way that 186 00:10:34,480 --> 00:10:38,600 Speaker 1: technology actually helps democratize. And maybe you have some sense 187 00:10:38,640 --> 00:10:42,640 Speaker 1: of the type of customers. Are they sort of large enterprises, 188 00:10:42,760 --> 00:10:45,440 Speaker 1: because I'm really keen to see this sorts of technology 189 00:10:45,520 --> 00:10:49,640 Speaker 1: really get pushed down to the smaller businesses and make 190 00:10:49,679 --> 00:10:52,320 Speaker 1: it affordable for them to adopt and use. Do you 191 00:10:52,320 --> 00:10:54,400 Speaker 1: have any thoughts about that particular trend? 192 00:10:54,720 --> 00:10:54,960 Speaker 2: Yeah? 193 00:10:55,000 --> 00:11:00,319 Speaker 3: Absolutely, I'd say they're all generally larger enterprises, but they 194 00:11:00,360 --> 00:11:03,600 Speaker 3: may be larger enterprises with smaller facilities, so they have 195 00:11:03,679 --> 00:11:06,880 Speaker 3: to think about the implementation at the store level, and 196 00:11:06,920 --> 00:11:08,880 Speaker 3: then they can step back and look at it at 197 00:11:08,920 --> 00:11:12,079 Speaker 3: an operational level for the entire business that they're trying 198 00:11:12,120 --> 00:11:15,679 Speaker 3: to run. When you think about physical security, well, physical 199 00:11:15,679 --> 00:11:18,199 Speaker 3: security can happen on a construction site, it can happen 200 00:11:18,200 --> 00:11:20,880 Speaker 3: in an office space, it can happen anywhere. But the 201 00:11:20,880 --> 00:11:24,480 Speaker 3: companies we're dealing with are generally the companies that one 202 00:11:24,720 --> 00:11:27,560 Speaker 3: have the actual technology, so they may be the camera vendors, 203 00:11:27,600 --> 00:11:31,000 Speaker 3: et cetera, but whereas actually being implemented. They're targeting a 204 00:11:31,120 --> 00:11:35,080 Speaker 3: broad range in particular segments like I mentioned, but the 205 00:11:35,120 --> 00:11:37,920 Speaker 3: actual implementation may happen at a different level. So it's 206 00:11:37,960 --> 00:11:42,520 Speaker 3: the companies that apply technology across specific segments and then 207 00:11:42,600 --> 00:11:46,400 Speaker 3: they actually tear those down. Cities can be large or 208 00:11:46,400 --> 00:11:50,080 Speaker 3: they can be smaller, but you're implementing generally starting at 209 00:11:50,160 --> 00:11:54,280 Speaker 3: an intersection level, so that could be maybe four cameras max. 210 00:11:54,920 --> 00:11:58,600 Speaker 3: But now I've got a thousand intersections, so it grows 211 00:11:58,679 --> 00:12:00,600 Speaker 3: in scales. And what we're saying, being back to that 212 00:12:00,679 --> 00:12:03,400 Speaker 3: early adopter, we see the big picture. Let's start with 213 00:12:03,440 --> 00:12:07,240 Speaker 3: three intersections and let's see and understand where technology can 214 00:12:07,280 --> 00:12:09,760 Speaker 3: be applied there. Because one of the ways I like 215 00:12:09,840 --> 00:12:13,400 Speaker 3: to explain to people, you need to understand the environment 216 00:12:13,480 --> 00:12:17,160 Speaker 3: the scene. That's what it's called scenescape the scene, the area, 217 00:12:17,240 --> 00:12:19,920 Speaker 3: your environment better. That's one way to think about digital 218 00:12:19,920 --> 00:12:21,079 Speaker 3: twin being able to enable that. 219 00:12:24,400 --> 00:12:27,960 Speaker 1: Coming out next on Technically Speaking and Intel podcast. 220 00:12:28,760 --> 00:12:31,120 Speaker 3: I am the ultimate digital twin that I want. I 221 00:12:31,120 --> 00:12:33,880 Speaker 3: don't care about an avatar that's fun and fancy. I 222 00:12:34,040 --> 00:12:36,880 Speaker 3: was something that helps improve my quality of life. 223 00:12:37,520 --> 00:12:39,920 Speaker 1: We'll be right back after a brief message from our partner. 224 00:12:39,960 --> 00:12:52,880 Speaker 1: Is that Intel? Welcome back to Technically Speaking an Intel Podcast. 225 00:12:53,160 --> 00:12:58,840 Speaker 1: I'm here now with the Intel's own Tony Fenklin. Do 226 00:12:58,880 --> 00:13:02,640 Speaker 1: you have any other example of benefits that your customers 227 00:13:02,679 --> 00:13:07,120 Speaker 1: have seen, whether it be productivity, increase, revenue, better, safety. 228 00:13:07,800 --> 00:13:09,160 Speaker 2: Yeah, I'll go on reverse ands. 229 00:13:09,200 --> 00:13:11,880 Speaker 3: You said safety last, because that's one that is so 230 00:13:12,160 --> 00:13:14,720 Speaker 3: common yep to people. In fact one, I think it 231 00:13:14,760 --> 00:13:18,520 Speaker 3: was the university in Texas that is doing some pilots 232 00:13:18,600 --> 00:13:22,120 Speaker 3: with the cities and with smart vehicles, and it's a 233 00:13:22,200 --> 00:13:24,959 Speaker 3: device called a roadside unit. Again, most people don't even 234 00:13:25,000 --> 00:13:27,480 Speaker 3: realize that you pull up to an intersection there's normally 235 00:13:27,559 --> 00:13:30,280 Speaker 3: a smaller box on the side. You already have the 236 00:13:30,400 --> 00:13:33,440 Speaker 3: box that controls the lights, et cetera. Well, I want 237 00:13:33,440 --> 00:13:36,240 Speaker 3: to do more so you can make that unit more intelligent. 238 00:13:36,280 --> 00:13:39,480 Speaker 3: You can actually allow that roadside unit to communicate with cars. 239 00:13:39,480 --> 00:13:41,800 Speaker 3: As cars become more intelligent, they have five G they 240 00:13:41,800 --> 00:13:45,400 Speaker 3: have wireless communications. So they implemented a pilot where there 241 00:13:45,440 --> 00:13:47,760 Speaker 3: was a particular intersection. So as the car pulls up, 242 00:13:47,800 --> 00:13:51,680 Speaker 3: imagine an alley off to the left, so the car 243 00:13:51,760 --> 00:13:54,679 Speaker 3: can't see down the alley clearly, but there's a poll 244 00:13:54,840 --> 00:13:56,920 Speaker 3: on the right that has a camera. The camera can 245 00:13:56,960 --> 00:13:59,360 Speaker 3: see the car coming. The camera can see down the alley. 246 00:13:59,360 --> 00:14:03,200 Speaker 3: The camera has roadside unit with Intel processing equipment. It's 247 00:14:03,240 --> 00:14:07,080 Speaker 3: running scenescape. Again, they don't even need to visualize this. 248 00:14:08,080 --> 00:14:12,400 Speaker 3: The camera sees someone walking down the alley, the car 249 00:14:12,480 --> 00:14:15,600 Speaker 3: is coming forward. It can communicate to the car because 250 00:14:15,640 --> 00:14:18,240 Speaker 3: even the cars with the cameras can't see around corners, 251 00:14:18,360 --> 00:14:21,400 Speaker 3: so the camera can communicate there's somebody walking. You need 252 00:14:21,520 --> 00:14:23,960 Speaker 3: to slow down. Knowing the speed of the car is 253 00:14:24,000 --> 00:14:27,760 Speaker 3: great acceleration, we understand that, but knowing where that car 254 00:14:27,840 --> 00:14:29,240 Speaker 3: is at the speed of a car coming down the 255 00:14:29,320 --> 00:14:31,400 Speaker 3: highway is one thing. The speed of a car coming 256 00:14:31,440 --> 00:14:34,480 Speaker 3: down that street where there's an alley is a totally 257 00:14:34,520 --> 00:14:36,920 Speaker 3: different scenario. I need to know the location of that 258 00:14:37,000 --> 00:14:39,880 Speaker 3: car relative to the camera and relative to the person 259 00:14:39,920 --> 00:14:42,800 Speaker 3: around the corner, both coming at the same time. So 260 00:14:42,920 --> 00:14:45,200 Speaker 3: three D is also a key aspect and value of 261 00:14:45,240 --> 00:14:48,840 Speaker 3: digital twin that translates to end benefit like you're talking about. 262 00:14:48,880 --> 00:14:51,280 Speaker 3: So that's safety right there, and that safety translates to 263 00:14:51,440 --> 00:14:52,840 Speaker 3: insurance as an example. 264 00:14:53,400 --> 00:14:58,880 Speaker 1: Yeah, just feeding off that safety theme, can technologies like 265 00:14:58,960 --> 00:15:04,240 Speaker 1: scenescape and having those sort of cameras help with worker safety, 266 00:15:04,320 --> 00:15:09,200 Speaker 1: say in a factory or warehouse, where they can detect 267 00:15:09,320 --> 00:15:12,120 Speaker 1: or even predict, you know, if something's going to go 268 00:15:12,200 --> 00:15:15,920 Speaker 1: wrong and actually warn a worker that something's going to happen. 269 00:15:16,440 --> 00:15:17,239 Speaker 2: Yeah. Absolutely. 270 00:15:17,320 --> 00:15:20,760 Speaker 3: Robot interaction is a common one also, so think about 271 00:15:20,960 --> 00:15:24,840 Speaker 3: robots with cameras and the cameras and sensors that are 272 00:15:24,920 --> 00:15:28,480 Speaker 3: around Mobile World Congress is going on right now, and 273 00:15:28,520 --> 00:15:30,680 Speaker 3: I think it was last year we did a Scenescape 274 00:15:30,680 --> 00:15:33,280 Speaker 3: demo there and it was purely an industrial We had 275 00:15:33,280 --> 00:15:36,880 Speaker 3: the robotic arms that were moving and they were building something, 276 00:15:37,280 --> 00:15:39,200 Speaker 3: and then you have a sensor doesn't even need to 277 00:15:39,240 --> 00:15:42,400 Speaker 3: be a camera that has a digital n scenescape to tripwire, 278 00:15:42,640 --> 00:15:45,920 Speaker 3: so we know if somebody crosses this point, then it's 279 00:15:45,920 --> 00:15:48,160 Speaker 3: a tripwire. So that was the actual demo. So there 280 00:15:48,160 --> 00:15:50,320 Speaker 3: was a safety zone and then there was crossing the 281 00:15:50,360 --> 00:15:52,480 Speaker 3: safety zone. So if you enter the safety zone, there 282 00:15:52,480 --> 00:15:53,920 Speaker 3: could be a warning light to go off. You don't 283 00:15:53,920 --> 00:15:56,040 Speaker 3: have to stop anything, but I know someone's in the 284 00:15:56,080 --> 00:15:58,080 Speaker 3: safety zone, I know how long they've been in the 285 00:15:58,120 --> 00:16:00,800 Speaker 3: safety zone, and if they cross past that, then I 286 00:16:00,840 --> 00:16:03,480 Speaker 3: know I can start to shut down automatically equipment if 287 00:16:03,480 --> 00:16:06,640 Speaker 3: that's the policy that that particular site chooses to use, 288 00:16:06,640 --> 00:16:11,280 Speaker 3: so they can execute another one in a more constrained environment. 289 00:16:11,440 --> 00:16:16,840 Speaker 3: Warehouse that we've seen is where there's actually a controlled space, 290 00:16:17,480 --> 00:16:21,000 Speaker 3: so radiation. Actually, the earlier example I talked about is 291 00:16:21,040 --> 00:16:24,080 Speaker 3: a real example where there's an area that it needs 292 00:16:24,080 --> 00:16:26,920 Speaker 3: to be climate controlled and it literally has radiation. So 293 00:16:26,960 --> 00:16:30,280 Speaker 3: they have a radiation sensor both inside outside and commnitor. 294 00:16:30,360 --> 00:16:32,760 Speaker 3: Do you have the equipment on how long has a 295 00:16:32,760 --> 00:16:35,920 Speaker 3: person been in this particular space, and I could set 296 00:16:35,960 --> 00:16:38,400 Speaker 3: timers and triggers so I know that they can only 297 00:16:38,440 --> 00:16:40,640 Speaker 3: be in for so long, and I can also track 298 00:16:40,720 --> 00:16:43,920 Speaker 3: that so that's real time action and control, and I 299 00:16:43,920 --> 00:16:47,280 Speaker 3: can also use that for later analysis and prediction. Maybe 300 00:16:47,280 --> 00:16:49,240 Speaker 3: I need to change the configuration of the room, maybe 301 00:16:49,240 --> 00:16:51,280 Speaker 3: I need to put more signs up. But you can 302 00:16:51,320 --> 00:16:55,200 Speaker 3: have real time action and decisions and also post analysis. 303 00:16:55,800 --> 00:16:59,040 Speaker 1: Yeah, what you said there about the simulation is quite 304 00:16:59,240 --> 00:17:02,280 Speaker 1: interesting because you know, as you're talking else, you know, 305 00:17:02,520 --> 00:17:05,480 Speaker 1: it came back to the gaming side of things, playing 306 00:17:05,480 --> 00:17:09,399 Speaker 1: SimCity or roller Coaster Tycoon, being able to sort of 307 00:17:09,440 --> 00:17:11,879 Speaker 1: simulate you know, if I put this thing here, is 308 00:17:11,920 --> 00:17:13,680 Speaker 1: it going to be dangerous? If I put that over there? 309 00:17:13,760 --> 00:17:16,480 Speaker 2: Does that help the workers? Does it help with productivity? 310 00:17:16,960 --> 00:17:20,920 Speaker 1: Maybe talk a little bit of some examples of using 311 00:17:20,960 --> 00:17:24,600 Speaker 1: real world data to kind of do what if analysis 312 00:17:24,640 --> 00:17:30,000 Speaker 1: of various scenarios that management and workers together can can 313 00:17:30,040 --> 00:17:33,000 Speaker 1: simulate and potentially improve the workplace. 314 00:17:33,920 --> 00:17:36,399 Speaker 3: So let's take something like a gaming site, I mean 315 00:17:36,480 --> 00:17:41,600 Speaker 3: like a football or soccer So clearly those are massive 316 00:17:41,640 --> 00:17:44,600 Speaker 3: events with a lot of people, a lot of insurances, 317 00:17:44,680 --> 00:17:49,360 Speaker 3: there's safety concerns, there's access to medical professionals that need 318 00:17:49,400 --> 00:17:52,840 Speaker 3: to get in and out. So can I take existing 319 00:17:53,080 --> 00:17:57,280 Speaker 3: data that has already been captured using existing cameras and 320 00:17:57,359 --> 00:17:59,760 Speaker 3: I can actually run simulations on that, I could also 321 00:18:00,560 --> 00:18:02,440 Speaker 3: ideally what I want and I need it. If I'm 322 00:18:02,440 --> 00:18:04,160 Speaker 3: going to do a digital twin, I need some sort 323 00:18:04,160 --> 00:18:07,200 Speaker 3: of digital twin of the environment. The level of depth 324 00:18:07,280 --> 00:18:09,439 Speaker 3: is just depending upon the level of analysis that you 325 00:18:09,480 --> 00:18:12,480 Speaker 3: want to conduct. Now, what I need is what's the 326 00:18:12,560 --> 00:18:14,920 Speaker 3: data that I've been able to collect, Because most of 327 00:18:14,960 --> 00:18:17,000 Speaker 3: these places they're already going to have some data, even 328 00:18:17,000 --> 00:18:19,520 Speaker 3: if it's just camera feed data. I could take that 329 00:18:19,920 --> 00:18:22,760 Speaker 3: and actually start to run models on Okay, where are 330 00:18:22,760 --> 00:18:26,560 Speaker 3: people congregating. I can actually post camera feed and apply 331 00:18:26,760 --> 00:18:29,840 Speaker 3: inference data to that, so I can use the AI 332 00:18:29,920 --> 00:18:33,160 Speaker 3: to identify, well, that's a person, and that's an animal, 333 00:18:33,280 --> 00:18:35,320 Speaker 3: that's a car over there. And now I can start 334 00:18:35,359 --> 00:18:37,919 Speaker 3: to look at, okay, how often are they in these spaces? 335 00:18:37,920 --> 00:18:40,680 Speaker 3: Where am I getting congregation? Where am I getting long 336 00:18:40,760 --> 00:18:44,520 Speaker 3: kelling lies? So I can do analysis all on existing data. 337 00:18:44,840 --> 00:18:47,600 Speaker 3: Now I can start to reconfigure whatever actions need to 338 00:18:47,640 --> 00:18:50,880 Speaker 3: be taken, so all of that can happen before I've 339 00:18:50,920 --> 00:18:52,320 Speaker 3: shown up physically at the space. 340 00:18:54,400 --> 00:18:58,439 Speaker 1: Just think about all the personal identifiable information involved in 341 00:18:58,480 --> 00:19:00,760 Speaker 1: some of the tasks we're talking about today. Well, the 342 00:19:00,800 --> 00:19:03,080 Speaker 1: sheer amount of streaming data coming in from a host 343 00:19:03,080 --> 00:19:06,640 Speaker 1: of senses required to implement digital twining. Keeping that data 344 00:19:06,640 --> 00:19:11,320 Speaker 1: secure is paramount to the future of this industry. I'd 345 00:19:11,400 --> 00:19:14,240 Speaker 1: like to get your thoughts around the whole privacy side 346 00:19:14,280 --> 00:19:16,320 Speaker 1: of things, and you know, what can be done to 347 00:19:16,440 --> 00:19:19,720 Speaker 1: make sure that as individuals we don't feel like we're 348 00:19:20,400 --> 00:19:21,800 Speaker 1: our privacy is getting invaded. 349 00:19:22,480 --> 00:19:24,280 Speaker 3: It's a very good topic and we thought about that 350 00:19:24,400 --> 00:19:27,920 Speaker 3: from the beginning. So one of the ways that we've 351 00:19:27,920 --> 00:19:31,080 Speaker 3: defined scenescape is we primarily work on metadata. And what 352 00:19:31,119 --> 00:19:33,920 Speaker 3: metadata simply means is, for instance, we don't do any 353 00:19:33,960 --> 00:19:36,879 Speaker 3: facial recognition. I need to know that that's a person, 354 00:19:37,080 --> 00:19:38,199 Speaker 3: or I need to know. In fact, we had an 355 00:19:38,240 --> 00:19:41,639 Speaker 3: actual scenario where customer had a particular area and they 356 00:19:41,680 --> 00:19:43,960 Speaker 3: knew people were around, but at night there were objects 357 00:19:44,000 --> 00:19:45,720 Speaker 3: and they didn't know what it was. They were animals, 358 00:19:46,000 --> 00:19:47,919 Speaker 3: and the model hadn't been trained for animals. So the 359 00:19:47,920 --> 00:19:50,600 Speaker 3: model can say, hey, there's something there. I can't say 360 00:19:50,680 --> 00:19:53,760 Speaker 3: that it's a deer versus or whatever, but it's not 361 00:19:53,800 --> 00:19:59,080 Speaker 3: a human, you know, And so think about the simplicity 362 00:19:59,080 --> 00:20:01,920 Speaker 3: of that. Now, I don't have to try trans every movement, 363 00:20:02,160 --> 00:20:06,359 Speaker 3: every aspect. I'm only transmitting what's critical to make the 364 00:20:06,440 --> 00:20:10,040 Speaker 3: decisions that are needed real time and for post analysis. 365 00:20:10,520 --> 00:20:15,199 Speaker 1: We talked a little bit about fulfillment centers and warehouses. I, 366 00:20:15,400 --> 00:20:19,040 Speaker 1: like everyone else, use ecommace sites like Amazon Prime. I'm 367 00:20:19,080 --> 00:20:21,600 Speaker 1: just wondering if you could maybe paint a picture of 368 00:20:21,720 --> 00:20:24,160 Speaker 1: how from the time that I hit that buy now 369 00:20:24,200 --> 00:20:26,800 Speaker 1: button to the time that I get my pair of 370 00:20:26,840 --> 00:20:32,479 Speaker 1: socks at my doorstep. Perhaps take me through how digital 371 00:20:32,520 --> 00:20:37,879 Speaker 1: twins could be used. How would a system help that process, 372 00:20:38,240 --> 00:20:41,320 Speaker 1: both as an in consumer and also for the business. 373 00:20:41,600 --> 00:20:43,679 Speaker 3: Actually to be honest, One of the first examples that 374 00:20:43,680 --> 00:20:47,560 Speaker 3: came to mind is the delivery truck and why location 375 00:20:47,800 --> 00:20:51,960 Speaker 3: intelligence is so important. All of us use location based 376 00:20:52,000 --> 00:20:54,880 Speaker 3: services today. There was a study I read I think 377 00:20:54,920 --> 00:20:58,400 Speaker 3: it was UPS is saving a lot of money per 378 00:20:58,440 --> 00:21:03,760 Speaker 3: truck because they realize the location intelligence they were getting more. Particularly, 379 00:21:03,760 --> 00:21:06,439 Speaker 3: this was when hotels were putting in their addresss because 380 00:21:06,560 --> 00:21:10,280 Speaker 3: they use Amazon Prime to and they're getting these packages 381 00:21:10,320 --> 00:21:15,320 Speaker 3: shipped to them. The location data of that hotel relative 382 00:21:15,359 --> 00:21:17,800 Speaker 3: to where the truck is coming from, and then mapping 383 00:21:17,840 --> 00:21:21,640 Speaker 3: the route were not good routes, so it was costing 384 00:21:21,720 --> 00:21:25,639 Speaker 3: the company so much money to get from point A 385 00:21:25,680 --> 00:21:28,000 Speaker 3: to point B. So now I can start to identify 386 00:21:28,040 --> 00:21:29,960 Speaker 3: where are the hotel. And if they discovered this and 387 00:21:30,000 --> 00:21:33,199 Speaker 3: they started taking copies which they have, this would go. 388 00:21:33,240 --> 00:21:35,520 Speaker 3: We can take copies of the maps, I can start 389 00:21:35,560 --> 00:21:37,800 Speaker 3: to locate where am I going. I can start to 390 00:21:37,840 --> 00:21:41,359 Speaker 3: figure out the routes. So they're using the twin of 391 00:21:41,440 --> 00:21:44,680 Speaker 3: the maps and the data they already have. Think about 392 00:21:44,720 --> 00:21:47,719 Speaker 3: they have tons of data on their routes and the locations, 393 00:21:47,720 --> 00:21:50,240 Speaker 3: and where are they normally congregating, and which truck should 394 00:21:50,240 --> 00:21:53,000 Speaker 3: they send, what time should they be. They did all 395 00:21:53,040 --> 00:21:55,960 Speaker 3: of that analysis to figure out just on the back 396 00:21:56,080 --> 00:21:58,639 Speaker 3: end of when I actually dropped the packets off to 397 00:21:58,680 --> 00:22:01,840 Speaker 3: you and what makes sense. That's saving money for them 398 00:22:01,960 --> 00:22:04,080 Speaker 3: completely and again it's location based. 399 00:22:04,560 --> 00:22:06,720 Speaker 1: Yeah, and can you give me an example of how 400 00:22:06,760 --> 00:22:09,480 Speaker 1: digital twinning might already be in use for the consumer 401 00:22:09,840 --> 00:22:12,960 Speaker 1: on one of these sites such as Amazon Prime all similar. 402 00:22:13,560 --> 00:22:15,800 Speaker 3: I have a chair behind me I just bought, so 403 00:22:15,920 --> 00:22:19,320 Speaker 3: now I can use digital twining right now to figure 404 00:22:19,320 --> 00:22:22,280 Speaker 3: out exactly where I want this, how does it look? 405 00:22:22,760 --> 00:22:25,960 Speaker 3: And they also have those clothing services which are digital twintying. 406 00:22:26,000 --> 00:22:28,480 Speaker 3: You're the real person and they have the digital where 407 00:22:28,480 --> 00:22:31,160 Speaker 3: you can apply the clothes to you. Yes, I mean again, 408 00:22:31,200 --> 00:22:33,480 Speaker 3: these are services that people are using today. But back 409 00:22:33,520 --> 00:22:37,000 Speaker 3: to my earlier comment, you're not actually thinking about the technology. 410 00:22:37,520 --> 00:22:40,560 Speaker 3: Are taking that now back to work, to your day job. Oh, 411 00:22:40,600 --> 00:22:42,480 Speaker 3: I do all of this at home. I should be 412 00:22:42,480 --> 00:22:45,639 Speaker 3: applying this to my business and saving money and getting 413 00:22:45,680 --> 00:22:48,439 Speaker 3: greater insights of my scene and of my environment. So 414 00:22:48,440 --> 00:22:50,480 Speaker 3: those are a couple of examples. Can I give you 415 00:22:50,520 --> 00:22:55,399 Speaker 3: a different example. Most people have some sort of ring 416 00:22:55,480 --> 00:22:57,480 Speaker 3: doorbell or type of It could be ring, it could 417 00:22:57,480 --> 00:22:58,400 Speaker 3: be simply safe whatever. 418 00:22:58,480 --> 00:22:59,320 Speaker 1: Yeah, I'll have that. 419 00:22:59,400 --> 00:22:59,840 Speaker 2: There you go. 420 00:23:01,160 --> 00:23:04,480 Speaker 3: One of the ways we've gone to market is to 421 00:23:04,560 --> 00:23:07,520 Speaker 3: make sure what we're doing is standard based and open, 422 00:23:07,600 --> 00:23:11,040 Speaker 3: you know, maximum scalability and flexibility. So I have a ring. 423 00:23:11,400 --> 00:23:14,359 Speaker 3: One of my family members has simply safe. The challenge 424 00:23:14,400 --> 00:23:17,080 Speaker 3: is I have the ring camera at the door, I 425 00:23:17,119 --> 00:23:20,360 Speaker 3: have another ring camera. I can connect them. I can 426 00:23:20,400 --> 00:23:23,680 Speaker 3: see if something's walking by. That's great. It's not very open. 427 00:23:23,720 --> 00:23:27,480 Speaker 3: I'm somewhat siloed. What we've had someone do with scenescape 428 00:23:27,520 --> 00:23:29,760 Speaker 3: is they use scenescape. First of all, you don't need 429 00:23:29,760 --> 00:23:32,000 Speaker 3: to go to the cloud, so they're not paying anybody. Okay, 430 00:23:32,040 --> 00:23:33,479 Speaker 3: if you want to use the cloud, you can, but 431 00:23:33,520 --> 00:23:35,360 Speaker 3: you do not have to use the cloud. Everything can 432 00:23:35,400 --> 00:23:37,359 Speaker 3: be edge based. And by edge based, think about the 433 00:23:37,440 --> 00:23:39,640 Speaker 3: edge again at home, where's the data generated. 434 00:23:39,960 --> 00:23:42,159 Speaker 2: That's my edge. So in this case, your edge is 435 00:23:42,160 --> 00:23:44,160 Speaker 2: your home. So my home. 436 00:23:44,480 --> 00:23:46,960 Speaker 3: I already have a computer, and I already have one 437 00:23:47,040 --> 00:23:49,520 Speaker 3: or two cameras. But there's a particular type of camera 438 00:23:49,560 --> 00:23:51,480 Speaker 3: I want for the front yard, which is totally different 439 00:23:51,520 --> 00:23:53,400 Speaker 3: than the camera I want indoors, which is totally different 440 00:23:53,400 --> 00:23:55,439 Speaker 3: than the camera I want. But so three totally different brands. 441 00:23:55,840 --> 00:23:58,280 Speaker 3: Well it's called multi camera, multi brand from that sense. 442 00:23:58,320 --> 00:24:01,359 Speaker 3: So and by the way, I want a heat sensor 443 00:24:01,440 --> 00:24:03,719 Speaker 3: or something like in a particularly air in the backyard 444 00:24:03,760 --> 00:24:06,199 Speaker 3: because I don't know if there's something overheating. So now 445 00:24:06,240 --> 00:24:08,280 Speaker 3: I can add all different type of brand sensors and 446 00:24:08,320 --> 00:24:12,200 Speaker 3: I can connect that into scenescape. And now Scenescape party 447 00:24:12,200 --> 00:24:15,479 Speaker 3: has AI. So I've used different brands. I've used my 448 00:24:15,520 --> 00:24:19,120 Speaker 3: own computer, so I have standard based connectivity. And because 449 00:24:19,119 --> 00:24:21,199 Speaker 3: of standard based connectivity, I can connect it to my 450 00:24:21,240 --> 00:24:23,879 Speaker 3: phone every phone app. Now it's very easy to connect 451 00:24:23,920 --> 00:24:26,440 Speaker 3: to it and get alerts. So now I can start 452 00:24:26,480 --> 00:24:30,320 Speaker 3: to use the existing AI tools that are in scenescape, 453 00:24:30,400 --> 00:24:33,400 Speaker 3: but there are so many applications out there. With scenescape, 454 00:24:33,440 --> 00:24:36,520 Speaker 3: you can integrate it with other applications. So there was 455 00:24:36,560 --> 00:24:39,399 Speaker 3: one person that used it to identify the difference between 456 00:24:39,400 --> 00:24:43,600 Speaker 3: a car coming in the driveway versus a postal truck 457 00:24:43,680 --> 00:24:46,359 Speaker 3: that goes by and stops, and they set an alert. 458 00:24:46,440 --> 00:24:48,720 Speaker 3: So whenever the postal truck comes and stops for a 459 00:24:48,760 --> 00:24:50,680 Speaker 3: few minutes, the alert goes on the phone. He never 460 00:24:50,680 --> 00:24:52,560 Speaker 3: has to look at a camera. He knows when he 461 00:24:52,600 --> 00:24:55,640 Speaker 3: gets that alert. Mails here. You can't do that with ring, 462 00:24:55,680 --> 00:24:58,840 Speaker 3: you can't do that with these other applications. So that's 463 00:24:58,840 --> 00:25:02,159 Speaker 3: a common use use case that people know today where 464 00:25:02,320 --> 00:25:08,600 Speaker 3: standard digital twinning technology with AI, standard based communication, and 465 00:25:08,920 --> 00:25:12,800 Speaker 3: standard computing technologies can all be used to enable use 466 00:25:12,840 --> 00:25:14,120 Speaker 3: cases that we use every day. 467 00:25:14,760 --> 00:25:18,879 Speaker 1: Yeah, we just have time for one more question. I 468 00:25:18,880 --> 00:25:23,800 Speaker 1: would like to get your number one. I guess area 469 00:25:23,840 --> 00:25:29,040 Speaker 1: of excitement for digital twins for me is healthcare. What 470 00:25:29,160 --> 00:25:31,159 Speaker 1: I want to see in my lifetime and we have 471 00:25:31,240 --> 00:25:32,840 Speaker 1: the technology to do it. In fact, we've have a 472 00:25:32,880 --> 00:25:34,879 Speaker 1: few use cases with scene skates where we're working with 473 00:25:34,880 --> 00:25:37,399 Speaker 1: the medical community. I want the digital twin of my 474 00:25:37,600 --> 00:25:42,680 Speaker 1: health I want for me the person all think about 475 00:25:42,760 --> 00:25:44,679 Speaker 1: all the data, all the medical records. First of all, 476 00:25:44,680 --> 00:25:46,359 Speaker 1: it's hard enough keeping all your medical records together. 477 00:25:46,640 --> 00:25:50,879 Speaker 3: So not only my medical records, but the medications I've taken, 478 00:25:51,080 --> 00:25:53,719 Speaker 3: any reactions I've had. You have so much data from 479 00:25:53,840 --> 00:26:00,000 Speaker 3: blood work and positive reactions, negative reactions to medications, exercise 480 00:26:00,040 --> 00:26:03,000 Speaker 3: since I've done that may have improved weight or blood pressure. 481 00:26:03,520 --> 00:26:06,320 Speaker 3: So as I grow, and as all of us grow 482 00:26:07,119 --> 00:26:10,439 Speaker 3: an age, I should say, yes, I want all of 483 00:26:10,480 --> 00:26:15,480 Speaker 3: that history to follow my DNA, my person to maximize healthcare. 484 00:26:15,800 --> 00:26:18,159 Speaker 3: I am the ultimate digital twin that I want. I 485 00:26:18,160 --> 00:26:20,960 Speaker 3: don't care about an avatar that's fun and fancy. I 486 00:26:21,080 --> 00:26:24,040 Speaker 3: was something that helps improve my quality of life. That's 487 00:26:24,040 --> 00:26:24,600 Speaker 3: what I want. 488 00:26:25,119 --> 00:26:28,719 Speaker 1: Out of interest, have you seen any companies or businesses 489 00:26:29,000 --> 00:26:29,760 Speaker 1: looking into this. 490 00:26:30,400 --> 00:26:32,560 Speaker 3: I did meet a company or CEO of a company 491 00:26:32,560 --> 00:26:35,280 Speaker 3: that's working on the medical record side YEP, where they're 492 00:26:35,280 --> 00:26:38,600 Speaker 3: trying to tie all of that to the person so 493 00:26:38,640 --> 00:26:41,720 Speaker 3: that can follow them, so that now physicians and healthcare 494 00:26:41,840 --> 00:26:44,879 Speaker 3: workers can have all that. So it's a startup. It 495 00:26:44,960 --> 00:26:47,200 Speaker 3: seems to be much more challenging to get this done 496 00:26:47,200 --> 00:26:50,280 Speaker 3: than you think it would be. But we've engaged with 497 00:26:50,400 --> 00:26:53,399 Speaker 3: some companies and hospitals that are making their hospital smart. 498 00:26:53,400 --> 00:26:56,560 Speaker 3: You can see some areas called the smart operating room. 499 00:26:57,240 --> 00:27:00,480 Speaker 3: That's a particular area in a hospital that's obviously critical. 500 00:27:00,520 --> 00:27:03,120 Speaker 3: I mean, you think about something as basic as we're 501 00:27:03,160 --> 00:27:06,360 Speaker 3: in the operating room, we're starting the operation. I have 502 00:27:06,720 --> 00:27:11,560 Speaker 3: twelve high value instruments on my right. Those twelve high 503 00:27:11,640 --> 00:27:14,000 Speaker 3: value instruments need to be there when I finished, because 504 00:27:14,000 --> 00:27:16,359 Speaker 3: if they're not there, there's a very bad place they 505 00:27:16,359 --> 00:27:18,720 Speaker 3: could be. Yeah, that's right, And that is a real 506 00:27:18,760 --> 00:27:21,160 Speaker 3: example that I know personally somebody like that that's happened 507 00:27:21,200 --> 00:27:23,119 Speaker 3: to and they've had to go back and get one 508 00:27:23,160 --> 00:27:27,080 Speaker 3: of those instruments. So when you think about the seriousness 509 00:27:27,119 --> 00:27:29,200 Speaker 3: of the operating room, and that's before you even get 510 00:27:29,240 --> 00:27:32,320 Speaker 3: into intrusive sensors and I mean, you know, what's the 511 00:27:32,320 --> 00:27:35,040 Speaker 3: blood pressure and et cetera. Yes, you never go to 512 00:27:35,080 --> 00:27:37,720 Speaker 3: a hospital, are to a healthcare professional and they take 513 00:27:37,720 --> 00:27:39,360 Speaker 3: your blood pressure and that's it and you're good. 514 00:27:39,400 --> 00:27:40,680 Speaker 2: Then they start talking to you. 515 00:27:40,720 --> 00:27:42,359 Speaker 3: No, we don't even think about the fact that we 516 00:27:42,359 --> 00:27:46,480 Speaker 3: take blood pressure, we take temperature, we take weight, sometimes 517 00:27:46,480 --> 00:27:51,080 Speaker 3: we take blood. So we're already experiencing a multi modal environment. 518 00:27:51,440 --> 00:27:54,000 Speaker 3: To maximize our health, but we don't always think about 519 00:27:54,000 --> 00:27:55,359 Speaker 3: that when we bring that to work. So now I 520 00:27:55,359 --> 00:27:57,680 Speaker 3: need a temperature sensor, I need light, I need lie dar, 521 00:27:57,800 --> 00:28:00,840 Speaker 3: I need cameras, I need different brands. I need to 522 00:28:00,840 --> 00:28:03,760 Speaker 3: apply intelligence to that. So now I can perceive my 523 00:28:03,880 --> 00:28:07,199 Speaker 3: space and my environment, I can understand it with analysis 524 00:28:07,240 --> 00:28:09,719 Speaker 3: and AI and makes sense of it to make decisions. 525 00:28:09,800 --> 00:28:12,280 Speaker 3: And then I can also do prediction based on that. 526 00:28:12,359 --> 00:28:13,600 Speaker 3: So what should happen in the future. 527 00:28:14,119 --> 00:28:17,120 Speaker 1: That's great, Tony. I think we'll leave it on that note. 528 00:28:17,240 --> 00:28:18,160 Speaker 1: Thanks so much. 529 00:28:18,280 --> 00:28:20,560 Speaker 2: Now, thank you. This was fun, really enjoyed it. 530 00:28:22,680 --> 00:28:25,840 Speaker 1: My deepest thanks to Tony Franklin for sharing his equities 531 00:28:25,840 --> 00:28:30,240 Speaker 1: with us. Today's chat about digital twins really opened my 532 00:28:30,359 --> 00:28:33,679 Speaker 1: eyes to the incredible potential. It's like stepping into a 533 00:28:33,720 --> 00:28:37,640 Speaker 1: simulation game where you can tweak maintenance schedules, production lines, 534 00:28:38,000 --> 00:28:40,480 Speaker 1: and even play around with the interaction between workers and 535 00:28:40,560 --> 00:28:44,520 Speaker 1: machinery using real world data. Yes, I'm letting my inner 536 00:28:44,560 --> 00:28:46,640 Speaker 1: geek shine through here, but the idea of managing a 537 00:28:46,680 --> 00:28:50,200 Speaker 1: supply chain with the ears of playing SimCity seems pretty 538 00:28:50,240 --> 00:28:53,720 Speaker 1: cool to me. Tony's closing thoughts on the future of 539 00:28:53,760 --> 00:28:56,800 Speaker 1: healthcare and the possibility of creating a human digital twin. 540 00:28:57,360 --> 00:29:01,680 Speaker 1: We're particularly striking. Imagine having clone of yourself in a sense. 541 00:29:02,280 --> 00:29:05,480 Speaker 1: I mean, we're already wearing watches that monitor heart rate, 542 00:29:05,720 --> 00:29:10,120 Speaker 1: physical activity, sleep quality, plus a range of other biometric data. 543 00:29:10,760 --> 00:29:13,040 Speaker 1: It's not too far fetched to dream about a future 544 00:29:13,040 --> 00:29:16,440 Speaker 1: where digital twins can forecast our health outcomes based on 545 00:29:16,480 --> 00:29:20,840 Speaker 1: our DNA, diet and exercise. It's an interesting idea and 546 00:29:20,880 --> 00:29:23,640 Speaker 1: I'm looking forward to seeing where this technology takes us, 547 00:29:25,800 --> 00:29:28,200 Speaker 1: and lucky for us, we'll get a chance to explore 548 00:29:28,200 --> 00:29:31,640 Speaker 1: this further on our next episode Tuesday, April twenty third, 549 00:29:31,960 --> 00:29:35,800 Speaker 1: on Technically Speaking and Intel Podcast, We'll be learning about 550 00:29:35,840 --> 00:29:39,280 Speaker 1: some of the revolutionary implementations of AI in the healthcare 551 00:29:39,280 --> 00:29:43,040 Speaker 1: space with team members from Intel and Siemens Health and 552 00:29:43,120 --> 00:29:52,760 Speaker 1: Ears See You then. Technically Speaking was produced by Ruby 553 00:29:52,800 --> 00:29:56,880 Speaker 1: Studio from iHeartRadio in partnership with Intel and hosted by 554 00:29:56,920 --> 00:30:01,520 Speaker 1: me Graham Class. Our Executive producer is my our EP 555 00:30:01,640 --> 00:30:05,480 Speaker 1: of Post production is James Foster, and our Supervising producer 556 00:30:05,720 --> 00:30:09,800 Speaker 1: is Nika Swinton. This episode was edited by Sierra Spreen 557 00:30:10,120 --> 00:30:14,600 Speaker 1: and was written by Molly Sosher and Nick Firshaw.