1
00:00:04,480 --> 00:00:12,280
Speaker 1: Welcome to tech Stuff, a production from iHeartRadio. Hey they're

2
00:00:12,360 --> 00:00:16,000
Speaker 1: tech Stuff fans. This is Jonathan Strickland speaking. I've got

3
00:00:16,000 --> 00:00:19,920
Speaker 1: something special for y'all today. What follows is an episode

4
00:00:20,000 --> 00:00:24,720
Speaker 1: from season two of our podcast technically Speaking. This particular

5
00:00:24,800 --> 00:00:28,880
Speaker 1: episode is about digital twins, which I thought was a

6
00:00:28,920 --> 00:00:32,280
Speaker 1: really fascinating topic. It was one that I wasn't actually

7
00:00:32,320 --> 00:00:36,000
Speaker 1: really familiar with, and I learned a lot and I

8
00:00:36,000 --> 00:00:39,520
Speaker 1: hope you will too. So check this out, and if

9
00:00:39,560 --> 00:00:42,599
Speaker 1: you enjoy it, make sure you go and subscribe to

10
00:00:42,800 --> 00:00:48,040
Speaker 1: technically Speaking. You've got two seasons of really cool material

11
00:00:48,360 --> 00:00:51,560
Speaker 1: in those episodes, so check that out. And I hope

12
00:00:51,560 --> 00:00:53,120
Speaker 1: you enjoy this episode.

13
00:00:55,040 --> 00:00:58,320
Speaker 2: Where do world changing ideas get This start at Intel.

14
00:00:58,400 --> 00:01:01,440
Speaker 2: It starts with real solutions, and real solutions start with

15
00:01:01,560 --> 00:01:06,560
Speaker 2: exceptional engineering, the quantum computing revolution, the next generation of

16
00:01:06,600 --> 00:01:10,640
Speaker 2: AI experts, the renewable energy grid, liquid cooling, data centers,

17
00:01:10,720 --> 00:01:14,800
Speaker 2: early diagnosis for cancer, water restoration, and even farmland protection.

18
00:01:15,160 --> 00:01:18,440
Speaker 2: The examples are countless, the impacts are endless, but the

19
00:01:18,520 --> 00:01:22,200
Speaker 2: foundation is always the same. It starts with Intel. Join

20
00:01:22,319 --> 00:01:25,120
Speaker 2: us in redefining what's achievable through the power of AI.

21
00:01:25,680 --> 00:01:34,160
Speaker 2: Learn more at Intel Dot com slash stories. Workplaces like

22
00:01:34,240 --> 00:01:37,920
Speaker 2: factories or fulfillment centers are filled with many moving parts

23
00:01:38,120 --> 00:01:43,480
Speaker 2: and require constant supervision and alertness to ensure worker safety.

24
00:01:44,920 --> 00:01:48,440
Speaker 2: But what happens when errors or accidents happen unexpectedly On

25
00:01:48,520 --> 00:01:51,840
Speaker 2: the simplest level, it creates chaos and can impact productivity.

26
00:01:52,240 --> 00:01:55,520
Speaker 2: On a larger scale, can create a dangerous environment for employees.

27
00:01:56,240 --> 00:01:59,480
Speaker 2: How can technology like AI and the creation of a

28
00:01:59,520 --> 00:02:03,800
Speaker 2: digital twe in help quickly correct errors and prevent accidents

29
00:02:04,080 --> 00:02:07,640
Speaker 2: before they occur? And could these virtual replications of a

30
00:02:07,640 --> 00:02:11,400
Speaker 2: physical space ensure workers go home to their families safe

31
00:02:11,400 --> 00:02:14,680
Speaker 2: and sound. Join us as we learn more about the

32
00:02:14,720 --> 00:02:17,840
Speaker 2: world of digital twins and the many ways they can

33
00:02:17,880 --> 00:02:25,240
Speaker 2: not only improve workplace safety, but also public safety. Welcome

34
00:02:25,280 --> 00:02:28,960
Speaker 2: to Technically Speaking, an Intel podcast, the show that brings

35
00:02:29,000 --> 00:02:32,720
Speaker 2: you the stories and insights of AI, presented by iHeartMedia's

36
00:02:32,840 --> 00:02:38,239
Speaker 2: Ruby Studio and Intel. Hey then, I'm gram class. Today,

37
00:02:38,360 --> 00:02:42,160
Speaker 2: we're exploring the spaces and places replicated by digital twins.

38
00:02:42,800 --> 00:02:46,400
Speaker 2: For starters, what is a digital twin? We're going to

39
00:02:46,440 --> 00:02:50,040
Speaker 2: be examining digital spaces that represent an actual physical space

40
00:02:50,200 --> 00:02:53,520
Speaker 2: in our world. To discuss the topic further, We're joined

41
00:02:53,560 --> 00:02:59,360
Speaker 2: by Tony Franklin. Tony Franklin is the general manager of

42
00:02:59,400 --> 00:03:03,800
Speaker 2: the Federal and Aerospace Markets, which includes military, aerospace, and

43
00:03:03,840 --> 00:03:06,480
Speaker 2: government within the Network and Edge Group. He has more

44
00:03:06,520 --> 00:03:10,960
Speaker 2: than twenty years of corporate entrepreneurial, business development and management experience,

45
00:03:11,560 --> 00:03:15,120
Speaker 2: focusing on starting and growing multiple businesses that apply to

46
00:03:15,320 --> 00:03:21,000
Speaker 2: the Internet of Things, intelligence systems, and communications technologies. Intel's

47
00:03:21,000 --> 00:03:23,960
Speaker 2: Network and Edge Group provide solutions that lead the industry

48
00:03:23,960 --> 00:03:27,120
Speaker 2: and transforming businesses and the way we live. Are making

49
00:03:27,160 --> 00:03:30,080
Speaker 2: it simple to create exciting new diet solutions.

50
00:03:30,800 --> 00:03:35,040
Speaker 3: Welcome to the show, Tony, Thank you, thank you, glad

51
00:03:35,040 --> 00:03:35,560
Speaker 3: to be here.

52
00:03:35,840 --> 00:03:39,040
Speaker 2: We've seen a lot of science fiction depictions of digital

53
00:03:39,040 --> 00:03:41,760
Speaker 2: twins over the years and movies and films. The one

54
00:03:41,760 --> 00:03:44,400
Speaker 2: that comes to mind is the Matrix, where the entire

55
00:03:44,440 --> 00:03:48,200
Speaker 2: world is the digital twin. Although it's a useful sinister motives,

56
00:03:48,960 --> 00:03:51,040
Speaker 2: I'd like to get your definition of what a digital

57
00:03:51,040 --> 00:03:51,480
Speaker 2: twin is.

58
00:03:52,080 --> 00:03:54,040
Speaker 3: Yeah. Sure, it's interesting you said the matrix.

59
00:03:54,080 --> 00:03:56,200
Speaker 4: I had to laugh because of all the examples we've

60
00:03:56,280 --> 00:03:58,680
Speaker 4: joked about, that's one that hasn't come up, and it's

61
00:03:58,760 --> 00:04:01,360
Speaker 4: so obvious when you said, I'll start to use that

62
00:04:02,280 --> 00:04:04,600
Speaker 4: in its simplest form for me, a digital twin is

63
00:04:04,760 --> 00:04:07,240
Speaker 4: the digital replica of the real world.

64
00:04:07,920 --> 00:04:11,360
Speaker 2: And in terms of the technologies that are out there

65
00:04:11,920 --> 00:04:16,000
Speaker 2: needed for digital twining, maybe you could describe a little

66
00:04:16,000 --> 00:04:20,160
Speaker 2: bit of how those sorts of systems are put together

67
00:04:20,279 --> 00:04:24,160
Speaker 2: and what are some of the technology that Intel has

68
00:04:24,279 --> 00:04:25,200
Speaker 2: that can help that.

69
00:04:25,920 --> 00:04:26,200
Speaker 3: Yeah.

70
00:04:26,240 --> 00:04:30,400
Speaker 4: Sure, it's really been an evolution of technologies that some

71
00:04:30,480 --> 00:04:32,679
Speaker 4: of them were all used to using, and some of them,

72
00:04:32,800 --> 00:04:34,279
Speaker 4: you know, if you're not in the field, maybe not

73
00:04:34,360 --> 00:04:37,800
Speaker 4: so much. And so Gartner, one of the well known analysts,

74
00:04:37,839 --> 00:04:42,239
Speaker 4: has this Emerging Technologies trending chart they do every year,

75
00:04:42,800 --> 00:04:46,360
Speaker 4: and they talk about edge AI, so artificial intelligence at

76
00:04:46,400 --> 00:04:49,080
Speaker 4: the edge, you know, the place where data is actually

77
00:04:49,120 --> 00:04:51,320
Speaker 4: being generated more so than in say the cloud or

78
00:04:51,400 --> 00:04:55,400
Speaker 4: data centers. That's happening, It continues to evolve, it's growing

79
00:04:55,440 --> 00:04:57,760
Speaker 4: more and more. We're pushing more and more intelligence to

80
00:04:57,880 --> 00:04:59,520
Speaker 4: the edge. And by the edge, it could be everything

81
00:04:59,520 --> 00:05:01,479
Speaker 4: from a self phone or refrigerator or a car.

82
00:05:01,640 --> 00:05:04,000
Speaker 3: Again, where is the data actually being generated?

83
00:05:04,760 --> 00:05:07,640
Speaker 4: And then they talk about digital twins being sort of

84
00:05:07,680 --> 00:05:10,240
Speaker 4: the now to three years. I think one of their

85
00:05:10,400 --> 00:05:14,400
Speaker 4: data points was something like forty percent of businesses large

86
00:05:14,400 --> 00:05:17,120
Speaker 4: businesses in particular plan to use digital twins over the

87
00:05:17,160 --> 00:05:19,600
Speaker 4: next two to three years to actually generate revenue, So

88
00:05:19,640 --> 00:05:22,479
Speaker 4: that's happening now, and then lastly over the next maybe

89
00:05:22,560 --> 00:05:25,000
Speaker 4: six plus years, they talk about the metaverse. Now, while

90
00:05:25,000 --> 00:05:27,680
Speaker 4: we don't generally talk about the metaverse as much, the

91
00:05:27,800 --> 00:05:30,000
Speaker 4: name means different things to different people, but it's the

92
00:05:30,040 --> 00:05:33,720
Speaker 4: full extent of how it was. Commerce and any other

93
00:05:33,800 --> 00:05:38,520
Speaker 4: business really leverage a fully digital space that has interaction

94
00:05:38,800 --> 00:05:42,040
Speaker 4: with the real world. So there's this spectrum that has

95
00:05:42,080 --> 00:05:45,800
Speaker 4: been happening between sensors, with cameras being the most obvious

96
00:05:46,000 --> 00:05:49,560
Speaker 4: because we're all using cameras today. Our phones have so

97
00:05:49,600 --> 00:05:52,640
Speaker 4: many censers we take them for granted, but all the sensors.

98
00:05:52,640 --> 00:05:56,039
Speaker 4: One of the key technologies that are needed an ability

99
00:05:56,080 --> 00:06:00,280
Speaker 4: to replicate if you're doing visual digital twins, so an

100
00:06:00,320 --> 00:06:03,520
Speaker 4: ability to replicate the real world, and of course physics

101
00:06:03,520 --> 00:06:05,960
Speaker 4: modeling if you're really doing analysis and you need to

102
00:06:06,000 --> 00:06:10,600
Speaker 4: replicate the physical asset in a digital world, So computing

103
00:06:10,760 --> 00:06:15,560
Speaker 4: capability to be able to replicate the behavior of the object,

104
00:06:16,120 --> 00:06:19,040
Speaker 4: with AI being a critical component to now actually apply

105
00:06:19,360 --> 00:06:23,240
Speaker 4: intelligence and analysis to the twin. So when you think

106
00:06:23,240 --> 00:06:25,880
Speaker 4: about those different areas well. Intel, we don't make sensors.

107
00:06:26,000 --> 00:06:28,839
Speaker 4: Everything else along the way is where we tend to

108
00:06:28,839 --> 00:06:32,800
Speaker 4: play clearly, computing technology, the ability to apply AI, so

109
00:06:33,080 --> 00:06:36,880
Speaker 4: both from the software side and the various different computing

110
00:06:36,960 --> 00:06:42,400
Speaker 4: technologies that enable AI, whether it's processors or GPUs, are

111
00:06:42,880 --> 00:06:46,080
Speaker 4: AI accelerators, et cetera. And then of course we have

112
00:06:46,160 --> 00:06:50,880
Speaker 4: a very broad, really world class partnership and ecosystem that

113
00:06:50,960 --> 00:06:53,240
Speaker 4: we work with to enable the different industries.

114
00:06:54,000 --> 00:06:56,240
Speaker 2: Okay, and in terms of trying to get like a

115
00:06:56,320 --> 00:07:00,640
Speaker 2: visual kind of representation of what this would clients say, say,

116
00:07:00,680 --> 00:07:03,960
Speaker 2: if you're walking in a warehouse, for example, and you're

117
00:07:03,960 --> 00:07:05,880
Speaker 2: looking at the shelves around you, you might see some

118
00:07:05,920 --> 00:07:10,200
Speaker 2: conveyor belts. How would it actually look in a digital twin.

119
00:07:10,960 --> 00:07:15,280
Speaker 2: It depends on the use case. The simplest version i'd

120
00:07:15,360 --> 00:07:17,920
Speaker 2: use that many people should be able to relate to Obviously,

121
00:07:17,920 --> 00:07:21,040
Speaker 2: many people can relate to matrix. But from an application standpoint,

122
00:07:21,560 --> 00:07:25,640
Speaker 2: I would say think about Google Earth or Google Maps.

123
00:07:25,720 --> 00:07:30,120
Speaker 2: Even that is a type of model right. Another example

124
00:07:30,200 --> 00:07:35,000
Speaker 2: is many of the retail applications allow you to basically

125
00:07:35,400 --> 00:07:40,400
Speaker 2: embed their items that are for sale into the digital

126
00:07:40,440 --> 00:07:44,600
Speaker 2: replication of your particular space. So it's a real world

127
00:07:45,000 --> 00:07:47,440
Speaker 2: and digital combination. That's always the key.

128
00:07:47,720 --> 00:07:51,080
Speaker 4: So those are very basic, simple applications that people use

129
00:07:51,280 --> 00:07:53,160
Speaker 4: and don't even realize. They don't think about them as

130
00:07:53,160 --> 00:07:56,440
Speaker 4: digital twins, but they're already getting used to this relationship

131
00:07:56,480 --> 00:07:59,120
Speaker 4: between the real world and the digital world.

132
00:07:59,640 --> 00:08:00,320
Speaker 3: Yes, I saw.

133
00:08:00,360 --> 00:08:03,480
Speaker 2: Intel has a software platform called Scenescape that can transform

134
00:08:03,560 --> 00:08:06,240
Speaker 2: data from this world of senses to create a real

135
00:08:06,280 --> 00:08:09,160
Speaker 2: time digital twin of your physical space. Can you tell

136
00:08:09,200 --> 00:08:11,320
Speaker 2: me a little bit more of how that works? So

137
00:08:11,320 --> 00:08:14,560
Speaker 2: there's really three basic steps. One is mapping your space.

138
00:08:15,080 --> 00:08:18,520
Speaker 2: The key though in the type of real time digital

139
00:08:18,560 --> 00:08:23,720
Speaker 2: twinning that we pursue is it is a coordinate, accurate space,

140
00:08:23,920 --> 00:08:26,280
Speaker 2: so it's not just taking a random space. We know

141
00:08:26,400 --> 00:08:28,520
Speaker 2: that that room is twenty feet by twenty five feet,

142
00:08:28,520 --> 00:08:31,960
Speaker 2: and we also know that the cameras are six feet

143
00:08:32,040 --> 00:08:35,840
Speaker 2: up on the wall. We know the actual XYZ of

144
00:08:35,880 --> 00:08:38,640
Speaker 2: the space, So that's the first step. Second step is

145
00:08:39,120 --> 00:08:42,360
Speaker 2: calibrate the space. So calibrate meaning I have the space,

146
00:08:42,800 --> 00:08:45,560
Speaker 2: where are my sensors? So my sensor is ten feet up,

147
00:08:45,600 --> 00:08:48,440
Speaker 2: four feet over in that corner, et cetera. Now you

148
00:08:48,520 --> 00:08:52,000
Speaker 2: turn on your sensors and you ingest that into scenescape.

149
00:08:52,200 --> 00:08:56,280
Speaker 2: Notice I haven't actually visualized necessarily anything. So the key

150
00:08:56,400 --> 00:08:59,400
Speaker 2: for people to realize in real time digital twinning. There

151
00:08:59,400 --> 00:09:01,800
Speaker 2: are some applications where someone's not actually going to be

152
00:09:01,800 --> 00:09:05,440
Speaker 2: sitting there watching the digital twin of the store. They

153
00:09:05,440 --> 00:09:09,280
Speaker 2: don't need to do that real time. The AI and

154
00:09:09,600 --> 00:09:13,520
Speaker 2: computing obviously, the AI tools and the actual AI models,

155
00:09:13,920 --> 00:09:18,719
Speaker 2: the inferencing capability of scenescape is doing the work. You

156
00:09:18,760 --> 00:09:22,320
Speaker 2: are configuring it so you could add things like heat

157
00:09:22,400 --> 00:09:25,880
Speaker 2: maps or trip wise so that you can actually have

158
00:09:26,200 --> 00:09:30,640
Speaker 2: events based on whatever policy you want to implement, so

159
00:09:30,760 --> 00:09:33,760
Speaker 2: that you don't have to actually monitor. So I'll know

160
00:09:33,880 --> 00:09:37,319
Speaker 2: that over in this area of the meat department, if

161
00:09:37,320 --> 00:09:40,320
Speaker 2: there's more than twenty people for twenty seconds, there's something

162
00:09:40,320 --> 00:09:43,160
Speaker 2: that happens. I don't even have to watch anything for that.

163
00:09:43,480 --> 00:09:47,480
Speaker 2: The intelligence is making it happen now. If what I

164
00:09:47,520 --> 00:09:51,320
Speaker 2: want to do later is now hit the rewind button.

165
00:09:51,480 --> 00:09:54,200
Speaker 2: The founder and creator for this particular product, he has

166
00:09:54,200 --> 00:09:57,120
Speaker 2: a phrase I'd love to use. It's called the DVR

167
00:09:57,240 --> 00:10:00,840
Speaker 2: for the real world. AI is happening real time, but

168
00:10:00,920 --> 00:10:04,520
Speaker 2: if you want additional analysis afterwards, you have that capability.

169
00:10:05,120 --> 00:10:07,679
Speaker 2: I can imagine there's a lot of challenges trying to

170
00:10:07,920 --> 00:10:10,760
Speaker 2: come up with these digital twins. What are some of

171
00:10:10,840 --> 00:10:14,839
Speaker 2: the top challenges or issues that people who are looking

172
00:10:14,880 --> 00:10:17,760
Speaker 2: to try and deploy these sorts of systems would have

173
00:10:17,840 --> 00:10:18,400
Speaker 2: to consider.

174
00:10:19,160 --> 00:10:23,440
Speaker 4: The most prominent one, to be honest with you, is

175
00:10:23,600 --> 00:10:27,920
Speaker 4: the mindset more than anything technical. You think about some

176
00:10:28,040 --> 00:10:31,559
Speaker 4: of the technology that's growing in our own home, siy

177
00:10:31,880 --> 00:10:36,880
Speaker 4: alexa are cars. There's so much technology, and most people

178
00:10:36,920 --> 00:10:40,920
Speaker 4: really don't understand you're already using AI. In many cases,

179
00:10:40,920 --> 00:10:44,000
Speaker 4: you're already using some sort of digital twin technology. There

180
00:10:44,040 --> 00:10:46,520
Speaker 4: was one demo we had for Scenescape and the executive

181
00:10:46,600 --> 00:10:48,640
Speaker 4: loved it. It's like, this is amazing. I can do

182
00:10:48,720 --> 00:10:51,280
Speaker 4: motion tracking. I see where people are. I can have

183
00:10:51,400 --> 00:10:55,800
Speaker 4: multiple cameras monitoring the same asset, our person or object,

184
00:10:55,800 --> 00:10:58,559
Speaker 4: but I only see one, so it deduplicates the person.

185
00:10:59,160 --> 00:11:01,800
Speaker 4: I can track with somebody's been in a space. Maybe

186
00:11:01,800 --> 00:11:04,600
Speaker 4: I have a radiation sensor and I can actually track

187
00:11:04,679 --> 00:11:06,720
Speaker 4: how long that person has been in the space, and

188
00:11:06,760 --> 00:11:09,520
Speaker 4: I can set triggers. There's so much he saw that

189
00:11:09,559 --> 00:11:12,800
Speaker 4: can be done, and he was so excited and he said,

190
00:11:12,800 --> 00:11:15,680
Speaker 4: where's the AI, right, Well, it's the AI that's doing

191
00:11:15,720 --> 00:11:19,440
Speaker 4: everything you just described. That's right, you just and it

192
00:11:19,520 --> 00:11:21,920
Speaker 4: actually set us back for a second. We're like, well, clearly,

193
00:11:22,520 --> 00:11:24,600
Speaker 4: we need to make sure we understand where people are

194
00:11:24,679 --> 00:11:28,040
Speaker 4: starting from. We can't assume they already know there's a

195
00:11:28,120 --> 00:11:31,959
Speaker 4: level of technology and integration of their technology.

196
00:11:33,440 --> 00:11:35,400
Speaker 2: And that's one of the biggest challenges when it comes

197
00:11:35,440 --> 00:11:39,559
Speaker 2: to understanding digital twin technology. It's the messaging some of

198
00:11:39,600 --> 00:11:42,360
Speaker 2: the very tools that you're accustomed to right now, like

199
00:11:42,520 --> 00:11:44,719
Speaker 2: the cell phone or the smart speaker that you are

200
00:11:44,800 --> 00:11:48,320
Speaker 2: listening to this podcast with essential when we consider the

201
00:11:48,320 --> 00:11:50,800
Speaker 2: future of digital twining. So when it comes to a

202
00:11:50,840 --> 00:11:54,800
Speaker 2: future that incorporates AI into our daily lives, we've actually

203
00:11:54,920 --> 00:12:00,199
Speaker 2: already taken the first steps down that path. One of

204
00:12:00,240 --> 00:12:03,720
Speaker 2: the things I like to examine is the way that

205
00:12:04,200 --> 00:12:08,319
Speaker 2: technology actually helps democratize. And maybe you have some sense

206
00:12:08,360 --> 00:12:12,400
Speaker 2: of the type of customers. Are they sort of large enterprises,

207
00:12:12,440 --> 00:12:15,160
Speaker 2: because I'm really keen to see this sort of technology

208
00:12:15,240 --> 00:12:18,840
Speaker 2: really get pushed down to the smaller businesses, you know,

209
00:12:19,000 --> 00:12:21,400
Speaker 2: and make it affordable for them to adopt and use.

210
00:12:21,840 --> 00:12:24,120
Speaker 2: Do you have any thoughts about that particular trend.

211
00:12:24,440 --> 00:12:29,760
Speaker 4: Yeah, absolutely, I'd say they're all generally larger enterprises, but

212
00:12:29,840 --> 00:12:33,200
Speaker 4: they may be larger enterprises with smaller facilities, so they

213
00:12:33,240 --> 00:12:36,120
Speaker 4: have to think about the implementation at the store level,

214
00:12:36,480 --> 00:12:38,400
Speaker 4: and then they can step back and look at it

215
00:12:38,440 --> 00:12:41,480
Speaker 4: at an operational level for the entire business that they're

216
00:12:41,480 --> 00:12:44,960
Speaker 4: trying to run. When you think about physical security, well,

217
00:12:45,000 --> 00:12:47,560
Speaker 4: physical security can happen on a construction site, it can

218
00:12:47,640 --> 00:12:50,440
Speaker 4: happen in an office space, it can happen anywhere. But

219
00:12:50,520 --> 00:12:53,400
Speaker 4: the companies we're dealing with are generally the companies that

220
00:12:53,920 --> 00:12:56,520
Speaker 4: one have the actual technology, so they may be the

221
00:12:56,520 --> 00:12:59,920
Speaker 4: camera vendors, et cetera. But whereas actually being implemented the

222
00:13:00,200 --> 00:13:04,160
Speaker 4: targeting a broad range in particular segments like I mentioned,

223
00:13:04,559 --> 00:13:07,199
Speaker 4: but the actual implementation may happen at a different level.

224
00:13:07,320 --> 00:13:11,560
Speaker 4: So it's the companies that apply technology across specific segments

225
00:13:11,880 --> 00:13:15,520
Speaker 4: and then they actually tear those down. Cities can be

226
00:13:15,640 --> 00:13:18,840
Speaker 4: large or they can be smaller, but you're implementing generally

227
00:13:19,160 --> 00:13:22,760
Speaker 4: starting at an intersection level, so that could be maybe

228
00:13:22,840 --> 00:13:26,880
Speaker 4: four cameras max. But now I've got a thousand intersections,

229
00:13:27,320 --> 00:13:30,120
Speaker 4: so it grows in scales, and what we're seeing back

230
00:13:30,120 --> 00:13:32,600
Speaker 4: to that early adopter, we see the big picture.

231
00:13:32,679 --> 00:13:33,120
Speaker 3: Let's start with.

232
00:13:33,160 --> 00:13:36,960
Speaker 4: Three intersections, and let's see and understand where technology can

233
00:13:37,000 --> 00:13:39,480
Speaker 4: be applied there. Because one of the ways I like

234
00:13:39,520 --> 00:13:43,120
Speaker 4: to explain to people, you need to understand the environment

235
00:13:43,200 --> 00:13:45,640
Speaker 4: the scene. That's what it's called scenes. Gape the scene,

236
00:13:46,200 --> 00:13:48,960
Speaker 4: the area, your environment better. That's one way to think

237
00:13:49,000 --> 00:13:50,800
Speaker 4: about digital twin being able to enable that.

238
00:13:54,120 --> 00:13:58,720
Speaker 2: Coming out next on Technically Speaking and Intel podcast, I.

239
00:13:58,640 --> 00:14:01,040
Speaker 4: Am the ultimate digital twin that I watch. I don't

240
00:14:01,040 --> 00:14:03,840
Speaker 4: care about an avatar that's fun and fancy. I was

241
00:14:03,840 --> 00:14:05,920
Speaker 4: something that helps improuse my quality of light.

242
00:14:07,240 --> 00:14:09,320
Speaker 2: We'll be right back after a brief message from our

243
00:14:09,360 --> 00:14:21,560
Speaker 2: partners at Intel. Where do world changing ideas get their start?

244
00:14:22,280 --> 00:14:25,840
Speaker 2: At Intel? It starts with real solutions, and real solutions

245
00:14:25,840 --> 00:14:30,080
Speaker 2: start with exceptional engineering. Empowering those with disabilities starts with

246
00:14:30,160 --> 00:14:34,280
Speaker 2: assistive AI, and stopping crop loss from infestation starts with

247
00:14:34,360 --> 00:14:38,760
Speaker 2: thermal imaging and open technology, while artificial intelligence that predicts

248
00:14:38,760 --> 00:14:43,040
Speaker 2: depression starts with educational programs like Intel's AI for Youth.

249
00:14:43,840 --> 00:14:48,680
Speaker 2: And that's just the start the quantum computing revolution. The

250
00:14:48,720 --> 00:14:54,080
Speaker 2: next generation of AI experts the renewable energy grid, liquid cooling,

251
00:14:54,160 --> 00:14:59,800
Speaker 2: data centers, radiation exposure prevention in space, water restoration, and

252
00:15:00,000 --> 00:15:04,880
Speaker 2: early cancer detection. The examples are countless, the impacts are endless,

253
00:15:05,400 --> 00:15:09,520
Speaker 2: but the foundation is always the same. It starts with Intel.

254
00:15:10,720 --> 00:15:20,240
Speaker 2: Learn more at Intel dot com, Forward Slash Stories. Welcome

255
00:15:20,280 --> 00:15:23,600
Speaker 2: back to Technically Speaking, an Intel podcast. I'm here now

256
00:15:23,680 --> 00:15:29,360
Speaker 2: with Intel's own Tony Franklin. Do you have any other

257
00:15:29,400 --> 00:15:34,120
Speaker 2: examples of benefits that your customers have seen, whether it

258
00:15:34,120 --> 00:15:36,960
Speaker 2: be productivity, increase, revenue, better, safety.

259
00:15:37,640 --> 00:15:40,080
Speaker 4: Yeah, I'll go on reverse since you said safety last,

260
00:15:40,080 --> 00:15:43,640
Speaker 4: because that's one that is so common yep to people.

261
00:15:43,680 --> 00:15:45,960
Speaker 4: In fact, I think it was the university in Texas

262
00:15:46,760 --> 00:15:50,200
Speaker 4: that has doing some pilots with the cities and with

263
00:15:50,360 --> 00:15:54,000
Speaker 4: smart vehicles. And it's a device called a roadside unit. Again,

264
00:15:54,000 --> 00:15:55,800
Speaker 4: most people don't even realize that you pull up to

265
00:15:55,800 --> 00:15:59,160
Speaker 4: an intersection, there's normally a smaller box on the side.

266
00:15:59,320 --> 00:16:02,920
Speaker 4: You already have the box that controls the lights, etc. Well,

267
00:16:02,960 --> 00:16:04,960
Speaker 4: I want to do more so you can make that

268
00:16:05,080 --> 00:16:07,960
Speaker 4: unit more intelligent. You can actually allow that roadside unit

269
00:16:08,040 --> 00:16:10,920
Speaker 4: to communicate with cars. As cars become more intelligent, they

270
00:16:10,920 --> 00:16:13,720
Speaker 4: have five G, they have wireless communications. So they implemented

271
00:16:13,760 --> 00:16:16,760
Speaker 4: a pilot where there was a particular intersection, so as

272
00:16:16,760 --> 00:16:19,960
Speaker 4: the car pulls up. Imagine an alley off to the left,

273
00:16:20,280 --> 00:16:23,800
Speaker 4: so the car can't see down the alley clearly, but

274
00:16:23,840 --> 00:16:26,000
Speaker 4: there's a pole on the right that has a camera.

275
00:16:26,120 --> 00:16:28,280
Speaker 4: The camera can see the car coming. The camera can

276
00:16:28,320 --> 00:16:30,840
Speaker 4: see down the alley. The camera has a roadside unit

277
00:16:31,080 --> 00:16:35,360
Speaker 4: with intel processing equipment. It's running scene skate again. They

278
00:16:35,360 --> 00:16:40,080
Speaker 4: don't even need to visualize this. The camera sees someone

279
00:16:40,160 --> 00:16:43,720
Speaker 4: walking down the alley, the car is coming forward. It

280
00:16:43,720 --> 00:16:46,200
Speaker 4: can communicate to the car because even the cars with

281
00:16:46,240 --> 00:16:48,920
Speaker 4: the cameras can't see around corners, so the camera can

282
00:16:48,960 --> 00:16:52,080
Speaker 4: communicate there is somebody walking. You need to slow down.

283
00:16:52,520 --> 00:16:55,360
Speaker 4: Knowing the speed of the car is great acceleration, we

284
00:16:55,440 --> 00:16:58,040
Speaker 4: understand that, but knowing where that car is at the

285
00:16:58,040 --> 00:16:59,920
Speaker 4: speed of a car coming down the highway is one thing.

286
00:17:00,120 --> 00:17:02,200
Speaker 4: The speed of a car coming down that street where

287
00:17:02,200 --> 00:17:05,440
Speaker 4: there's an alley is a totally different scenario. I need

288
00:17:05,480 --> 00:17:07,800
Speaker 4: to know the location of that car relative to the

289
00:17:07,840 --> 00:17:11,040
Speaker 4: camera and relative to the person around the corner, both

290
00:17:11,080 --> 00:17:13,680
Speaker 4: coming at the same time. So three D is also

291
00:17:13,720 --> 00:17:16,680
Speaker 4: a key aspect and value of digital twin That translates

292
00:17:16,960 --> 00:17:19,480
Speaker 4: to end benefit like you're talking about. So that's safety

293
00:17:19,560 --> 00:17:22,720
Speaker 4: right there, and that safety translates to insurance as an example.

294
00:17:23,240 --> 00:17:28,720
Speaker 2: Yeah, just fitting off that safety theme. Can technologies like

295
00:17:28,800 --> 00:17:34,120
Speaker 2: scenescape and having those sort of cameras help with worker safety,

296
00:17:34,160 --> 00:17:39,040
Speaker 2: say in a factory or warehouse, where they can detect

297
00:17:39,200 --> 00:17:41,960
Speaker 2: or even predict, you know, if something's going to go

298
00:17:42,040 --> 00:17:45,760
Speaker 2: wrong and actually warn a worker that something's going to happen.

299
00:17:46,280 --> 00:17:47,080
Speaker 3: Yeah. Absolutely.

300
00:17:47,200 --> 00:17:50,639
Speaker 4: Robot interaction is a common one also, so think about

301
00:17:50,840 --> 00:17:54,720
Speaker 4: robots with cameras and the cameras and sensors that are

302
00:17:54,760 --> 00:17:58,320
Speaker 4: around Mobile World Congress is going on right now, and

303
00:17:58,400 --> 00:18:00,520
Speaker 4: I think it was last year. We did a escape

304
00:18:00,520 --> 00:18:03,080
Speaker 4: demo there and it was purely an industrial We had

305
00:18:03,119 --> 00:18:06,720
Speaker 4: the robotic arms that were moving and they were building something.

306
00:18:07,119 --> 00:18:09,080
Speaker 4: And then you have a sensor doesn't even need to

307
00:18:09,080 --> 00:18:11,640
Speaker 4: be a camera that has a digital n scen escape

308
00:18:11,640 --> 00:18:14,880
Speaker 4: the trip wire, so we know if somebody crosses this point,

309
00:18:15,440 --> 00:18:17,400
Speaker 4: then it's a trip wire. So that was the actual demo.

310
00:18:17,720 --> 00:18:19,600
Speaker 4: So there was a safety zone and then there was

311
00:18:19,680 --> 00:18:22,160
Speaker 4: crossing the safety zone. So if you enter the safety zone,

312
00:18:22,200 --> 00:18:23,560
Speaker 4: there could be a warning light to go off. You

313
00:18:23,560 --> 00:18:25,800
Speaker 4: don't have to stop anything, but I know someone's in

314
00:18:25,840 --> 00:18:27,840
Speaker 4: the safety zone, I know how long they've been in

315
00:18:27,880 --> 00:18:30,520
Speaker 4: the safety zone and if they cross past that, then

316
00:18:30,560 --> 00:18:32,960
Speaker 4: I know I can start to shut down automatically equipment

317
00:18:33,160 --> 00:18:36,479
Speaker 4: if that's the policy that that particular site chooses to use.

318
00:18:36,480 --> 00:18:39,800
Speaker 4: So I think can execute another one in a more

319
00:18:40,000 --> 00:18:44,960
Speaker 4: constrained environment warehouse that we've seen is where there's actually

320
00:18:45,359 --> 00:18:50,119
Speaker 4: a controlled space, so radiation. Actually, the earlier example I

321
00:18:50,160 --> 00:18:52,959
Speaker 4: talked about is a real example where there's an area

322
00:18:53,040 --> 00:18:55,960
Speaker 4: that it needs to be climate controlled and it literally

323
00:18:56,000 --> 00:18:58,640
Speaker 4: has radiations. So they have a radiation sensor both inside

324
00:18:58,640 --> 00:19:01,200
Speaker 4: outside and commodity or do you have the equipment on

325
00:19:01,720 --> 00:19:04,760
Speaker 4: how long has a person been in this particular space,

326
00:19:05,119 --> 00:19:07,520
Speaker 4: and I could set timers and triggers so I know

327
00:19:07,600 --> 00:19:09,600
Speaker 4: that they can only be in for so long, and

328
00:19:09,640 --> 00:19:12,760
Speaker 4: I can also track that. So that's real time action

329
00:19:12,880 --> 00:19:15,480
Speaker 4: and control, and I can also use that for later

330
00:19:15,600 --> 00:19:18,480
Speaker 4: analysis and prediction. Maybe I need to change the configuration

331
00:19:18,520 --> 00:19:20,360
Speaker 4: of the room, maybe I need to put more signs up,

332
00:19:20,640 --> 00:19:23,479
Speaker 4: But you can have real time action and decisions and

333
00:19:23,600 --> 00:19:25,040
Speaker 4: also post analysis.

334
00:19:25,640 --> 00:19:28,879
Speaker 2: Yeah, what you said there about the simulation is quite

335
00:19:29,080 --> 00:19:32,119
Speaker 2: interesting because you know, as you're talking else, you know

336
00:19:32,359 --> 00:19:35,320
Speaker 2: it came back to the gaming side of things, playing

337
00:19:35,359 --> 00:19:39,240
Speaker 2: SimCity or roller coaster tycoon being able to sort of

338
00:19:39,280 --> 00:19:41,720
Speaker 2: simulate you know, if I put this thing here, is

339
00:19:41,760 --> 00:19:42,560
Speaker 2: it going to be dangerous?

340
00:19:42,600 --> 00:19:45,000
Speaker 3: If I put that over there? Does that help the workers?

341
00:19:45,040 --> 00:19:46,320
Speaker 3: Does it help with productivity?

342
00:19:46,840 --> 00:19:50,760
Speaker 2: Maybe talk a little bit of some examples of using

343
00:19:50,800 --> 00:19:54,440
Speaker 2: real world data to kind of do what if analysis

344
00:19:54,520 --> 00:19:59,760
Speaker 2: of various scenarios that management and workers together can can

345
00:19:59,760 --> 00:20:02,840
Speaker 2: see mille and potentially improve the workplace.

346
00:20:03,720 --> 00:20:06,280
Speaker 4: So let's take something like a gaming site, I mean

347
00:20:06,320 --> 00:20:11,400
Speaker 4: like a football or soccer So clearly those are massive

348
00:20:11,480 --> 00:20:14,440
Speaker 4: events with a lot of people, a lot of insurances,

349
00:20:14,520 --> 00:20:19,200
Speaker 4: there's safety concerns, there's access to medical professionals that need

350
00:20:19,240 --> 00:20:22,680
Speaker 4: to get in and out. So can I take existing

351
00:20:22,920 --> 00:20:27,159
Speaker 4: data that has already been captured using existing cameras and

352
00:20:27,200 --> 00:20:29,680
Speaker 4: I can actually run simulations on that. I could also

353
00:20:30,400 --> 00:20:32,280
Speaker 4: ideally what I want and I need it. If I'm

354
00:20:32,280 --> 00:20:33,960
Speaker 4: going to do a digital twin, I need some sort

355
00:20:34,000 --> 00:20:37,040
Speaker 4: of digital twin of the environment. The level of depth

356
00:20:37,119 --> 00:20:39,280
Speaker 4: is just depending upon the level of analysis that you

357
00:20:39,320 --> 00:20:42,320
Speaker 4: want to conduct. Now, what I need is what's the

358
00:20:42,440 --> 00:20:44,760
Speaker 4: data that I've been able to collect, because most of

359
00:20:44,800 --> 00:20:46,840
Speaker 4: these places they're already going to have some data, even

360
00:20:46,880 --> 00:20:49,360
Speaker 4: if it's just camera feed data. I could take that

361
00:20:49,760 --> 00:20:52,600
Speaker 4: and actually start to run models on Okay, where are

362
00:20:52,600 --> 00:20:56,399
Speaker 4: people congregating? I can actually post camera feed and apply

363
00:20:56,600 --> 00:20:59,680
Speaker 4: inference data to that, so I can use the AI

364
00:20:59,760 --> 00:21:03,000
Speaker 4: to it. Andy, well, that's a person, and that's an animal.

365
00:21:03,119 --> 00:21:05,160
Speaker 4: That's a car over there, And now I can start

366
00:21:05,200 --> 00:21:07,760
Speaker 4: to look at Okay, how often are they in these spaces?

367
00:21:07,800 --> 00:21:10,520
Speaker 4: Where am I getting congregation? Where am I getting long

368
00:21:10,640 --> 00:21:14,360
Speaker 4: killing live? So I can do analysis all on existing data.

369
00:21:14,680 --> 00:21:17,480
Speaker 4: Now I can start to reconfigure whatever actions need to

370
00:21:17,480 --> 00:21:20,720
Speaker 4: be taken, so all of that can happen before I've

371
00:21:20,720 --> 00:21:22,159
Speaker 4: shown up physically at the space.

372
00:21:24,240 --> 00:21:28,280
Speaker 2: Just think about all the personal identifiable information involved in

373
00:21:28,320 --> 00:21:30,600
Speaker 2: some of the tasks we're talking about today. Well, the

374
00:21:30,640 --> 00:21:32,920
Speaker 2: sheer amount of streaming data coming in from a host

375
00:21:32,920 --> 00:21:36,480
Speaker 2: of senses required to implement digital twining, keeping that data

376
00:21:36,520 --> 00:21:41,080
Speaker 2: secure is paramount to the future of this industry. I

377
00:21:41,240 --> 00:21:44,080
Speaker 2: like to get your thoughts around the whole privacy side

378
00:21:44,119 --> 00:21:46,159
Speaker 2: of things, and you know what can be done to

379
00:21:46,280 --> 00:21:49,639
Speaker 2: make sure that as individuals we don't feel like where

380
00:21:50,240 --> 00:21:51,680
Speaker 2: our privacy is getting invaded.

381
00:21:52,320 --> 00:21:54,040
Speaker 4: That's a very good topic and we thought about that

382
00:21:54,240 --> 00:21:57,760
Speaker 4: from the beginning. So one of the ways that we've

383
00:21:57,760 --> 00:22:00,760
Speaker 4: defined scenescaper is we primarily work on meta data, and

384
00:22:00,800 --> 00:22:03,600
Speaker 4: what metadata simply means is, for instance, we don't do

385
00:22:03,600 --> 00:22:06,359
Speaker 4: any facial recognition. I need to know that that's a

386
00:22:06,359 --> 00:22:07,959
Speaker 4: person or I need to know In fact, we had

387
00:22:07,960 --> 00:22:10,680
Speaker 4: an actual scenario where a customer had a particular area

388
00:22:11,040 --> 00:22:13,240
Speaker 4: and they knew people were around, but at night there

389
00:22:13,240 --> 00:22:14,959
Speaker 4: were objects and they didn't know what it was. They

390
00:22:14,960 --> 00:22:17,480
Speaker 4: were animals, and the model hadn't been trained for animals.

391
00:22:17,560 --> 00:22:19,879
Speaker 4: So the model can say, hey, there's something there. I

392
00:22:19,920 --> 00:22:23,159
Speaker 4: can't say that it's a deer versus or whatever, but

393
00:22:23,320 --> 00:22:28,320
Speaker 4: it's not a human, you know. And so think about

394
00:22:28,359 --> 00:22:30,240
Speaker 4: the simplicity of that. Now, I don't have to transmit

395
00:22:30,920 --> 00:22:35,800
Speaker 4: every movement, every aspect. I'm only transmitting what's critical to

396
00:22:35,920 --> 00:22:38,919
Speaker 4: make the decisions that are needed real time and for

397
00:22:38,960 --> 00:22:39,920
Speaker 4: post analysis.

398
00:22:40,359 --> 00:22:44,159
Speaker 2: We talked a little bit about fulfillment centers and warehouses.

399
00:22:44,960 --> 00:22:48,880
Speaker 2: I like everyone else's ecomma sites like Amazon Prime. I'm

400
00:22:48,920 --> 00:22:51,439
Speaker 2: just wondering if you could maybe paint a picture of

401
00:22:51,560 --> 00:22:54,000
Speaker 2: how from the time that I hit that buy now,

402
00:22:54,040 --> 00:22:56,639
Speaker 2: but to the time that I get my pair of

403
00:22:56,680 --> 00:23:02,719
Speaker 2: socks at my doorstep, take me through how digital twins

404
00:23:02,720 --> 00:23:07,719
Speaker 2: could be used. How would a system help that process,

405
00:23:08,080 --> 00:23:11,159
Speaker 2: both as an in consumer and also for the business.

406
00:23:11,440 --> 00:23:13,520
Speaker 4: Actually to be honest, One of the first examples that

407
00:23:13,560 --> 00:23:17,400
Speaker 4: came to mind is the delivery truck and why location

408
00:23:17,680 --> 00:23:21,800
Speaker 4: intelligence is so important. All of us use location based

409
00:23:21,840 --> 00:23:24,720
Speaker 4: services today. There was a study I read I think

410
00:23:24,760 --> 00:23:28,240
Speaker 4: it was UPS is saving a lot of money per

411
00:23:28,280 --> 00:23:33,120
Speaker 4: truck because they realized that location intelligence they were getting more.

412
00:23:33,119 --> 00:23:35,719
Speaker 4: Particularly this was when hotels were putting in their address

413
00:23:35,920 --> 00:23:39,560
Speaker 4: because they use Amazon Prime to and they're getting these

414
00:23:39,600 --> 00:23:44,480
Speaker 4: packages shipped to them. The location data of that hotel

415
00:23:44,680 --> 00:23:47,160
Speaker 4: relative to where the truck is coming from, and then

416
00:23:47,240 --> 00:23:50,879
Speaker 4: mapping the route were not good routes, so it was

417
00:23:51,040 --> 00:23:55,400
Speaker 4: costing the company so much money to get from point

418
00:23:55,400 --> 00:23:57,240
Speaker 4: A to point B. So now I can start to

419
00:23:57,280 --> 00:23:59,760
Speaker 4: identify where are the hotel. And they discovered this and

420
00:23:59,800 --> 00:24:02,480
Speaker 4: they started taking copies which they have.

421
00:24:02,600 --> 00:24:03,040
Speaker 3: This would go.

422
00:24:03,080 --> 00:24:05,360
Speaker 4: We can take copies of the maps, I can start

423
00:24:05,400 --> 00:24:07,639
Speaker 4: to locate where am I going. I can start to

424
00:24:07,680 --> 00:24:11,199
Speaker 4: figure out the routes. So they're using the twin of

425
00:24:11,280 --> 00:24:14,480
Speaker 4: the maps and the data they already have. Think about

426
00:24:14,560 --> 00:24:16,760
Speaker 4: they have tons of data on their routes and the

427
00:24:16,960 --> 00:24:19,800
Speaker 4: locations and where are they normally congregating, and which truck

428
00:24:19,800 --> 00:24:22,640
Speaker 4: should they send, what time should they be They did

429
00:24:22,680 --> 00:24:25,520
Speaker 4: all of that analysis to figure out just on the

430
00:24:25,600 --> 00:24:28,400
Speaker 4: back end of when I actually dropped the packets off

431
00:24:28,400 --> 00:24:30,919
Speaker 4: to you and what makes sense that's saving money for

432
00:24:31,000 --> 00:24:34,600
Speaker 4: them completely and again it's location based yep.

433
00:24:34,880 --> 00:24:37,000
Speaker 2: And can you give me an example of how digital

434
00:24:37,000 --> 00:24:39,840
Speaker 2: twinning might already be in use for the consumer on

435
00:24:39,840 --> 00:24:43,240
Speaker 2: one of these sites such as Amazon Prime all similar.

436
00:24:43,400 --> 00:24:45,639
Speaker 4: I have a chair behind me I just bought, so

437
00:24:45,760 --> 00:24:49,159
Speaker 4: now I can use digital twining right now to figure

438
00:24:49,160 --> 00:24:52,119
Speaker 4: out exactly where I want this, how does it look?

439
00:24:52,600 --> 00:24:55,800
Speaker 4: And they also have those clothing services which are digital twining.

440
00:24:55,840 --> 00:24:58,320
Speaker 4: You're the real person, and they have the digital where

441
00:24:58,359 --> 00:25:01,000
Speaker 4: you can apply the clothes to you. Yes, I mean again,

442
00:25:01,040 --> 00:25:03,320
Speaker 4: these are services that people are using today. But back

443
00:25:03,359 --> 00:25:06,880
Speaker 4: to my earlier comment, you're not actually thinking about the technology.

444
00:25:07,359 --> 00:25:10,400
Speaker 4: Are taking that now back to work, to your day job. Oh,

445
00:25:10,440 --> 00:25:12,280
Speaker 4: I do all of this at home. I should be

446
00:25:12,320 --> 00:25:15,520
Speaker 4: applying this to my business and saving money and getting

447
00:25:15,520 --> 00:25:18,280
Speaker 4: greater insights of my scene and of my environment. So

448
00:25:18,280 --> 00:25:20,359
Speaker 4: those are a couple of examples. Can I give you

449
00:25:20,359 --> 00:25:25,240
Speaker 4: a different example. Most people have some sort of ring

450
00:25:25,320 --> 00:25:27,320
Speaker 4: doorbell or type of it could be ring, it could

451
00:25:27,320 --> 00:25:28,480
Speaker 4: be simply safe whatever.

452
00:25:28,320 --> 00:25:29,160
Speaker 2: Yeah, I'll have that.

453
00:25:29,240 --> 00:25:29,720
Speaker 3: There you go.

454
00:25:31,000 --> 00:25:34,320
Speaker 4: One of the ways we've gone to market is to

455
00:25:34,400 --> 00:25:37,359
Speaker 4: make sure what we're doing is standard based and open,

456
00:25:37,440 --> 00:25:40,600
Speaker 4: you know, maximum scalability and flexibility. So I have a

457
00:25:40,680 --> 00:25:43,600
Speaker 4: ring one of my family members has simply safe. The

458
00:25:43,720 --> 00:25:46,840
Speaker 4: challenge is I have the ring camera at the door,

459
00:25:46,880 --> 00:25:50,000
Speaker 4: I have another ring camera. I can connect them. I

460
00:25:50,040 --> 00:25:52,960
Speaker 4: can see if something's walking by. That's great. It's not

461
00:25:53,119 --> 00:25:56,520
Speaker 4: very open. I'm somewhat siloed. What we've had someone do

462
00:25:56,600 --> 00:25:59,240
Speaker 4: with scenescape is they use scenescape. First of all, you

463
00:25:59,280 --> 00:26:01,840
Speaker 4: don't need to go through the so they're not paying anybody. Okay,

464
00:26:01,880 --> 00:26:03,320
Speaker 4: if you want to use the cloud, you can, but

465
00:26:03,359 --> 00:26:05,200
Speaker 4: you do not have to use the cloud. Everything can

466
00:26:05,240 --> 00:26:07,199
Speaker 4: be edge based, and by edge based, think about the

467
00:26:07,280 --> 00:26:10,720
Speaker 4: edge again. At home, where's the data generated? That's my edge.

468
00:26:10,960 --> 00:26:13,399
Speaker 4: So in this case, your edge is your home. So

469
00:26:13,520 --> 00:26:16,399
Speaker 4: my home, I already have a computer, and I already

470
00:26:16,440 --> 00:26:18,920
Speaker 4: have one or two cameras. But there's a particular type

471
00:26:18,960 --> 00:26:20,800
Speaker 4: of camera I want for the front yard, which is

472
00:26:20,800 --> 00:26:22,760
Speaker 4: totally different than the camera I want indoors, which is

473
00:26:22,800 --> 00:26:24,600
Speaker 4: totally different than the camera I want, so three totally

474
00:26:24,640 --> 00:26:27,720
Speaker 4: different brands. Well it's called multi camera multi brand from

475
00:26:27,760 --> 00:26:30,280
Speaker 4: that sense. So and by the way, maybe I want

476
00:26:30,440 --> 00:26:33,040
Speaker 4: a heat sensor or something like in a particularly air

477
00:26:33,040 --> 00:26:35,399
Speaker 4: in the backyard because I don't know if there's something overheating.

478
00:26:35,800 --> 00:26:37,639
Speaker 4: So now I can add all different type of brand

479
00:26:37,680 --> 00:26:40,879
Speaker 4: sensors and I can connect that into scenescape. And now

480
00:26:41,240 --> 00:26:44,920
Speaker 4: scenescape party has AI. So I've used different brands. I've

481
00:26:45,000 --> 00:26:48,160
Speaker 4: used my own computer, so I have standard based connectivity.

482
00:26:48,520 --> 00:26:50,800
Speaker 4: And because of standard based connectivity, I can connect it

483
00:26:50,840 --> 00:26:53,320
Speaker 4: to my phone. Every phone app now it's very easy

484
00:26:53,320 --> 00:26:55,840
Speaker 4: to connect to it and get alerts. So now I

485
00:26:55,840 --> 00:26:59,000
Speaker 4: can start to use the existing AI tools that are

486
00:26:59,040 --> 00:27:02,520
Speaker 4: in Scenescape. But there are so many applications out there.

487
00:27:02,560 --> 00:27:05,960
Speaker 4: With scenescape, you can integrate it with other applications. So

488
00:27:06,119 --> 00:27:08,439
Speaker 4: there was one person that used it to identify the

489
00:27:08,480 --> 00:27:12,200
Speaker 4: difference between a car coming in the driveway versus a

490
00:27:12,640 --> 00:27:15,720
Speaker 4: postal truck that goes by and stops, and they set

491
00:27:15,720 --> 00:27:18,479
Speaker 4: an alert. So whenever the postal truck comes and stops

492
00:27:18,480 --> 00:27:20,119
Speaker 4: for a few minutes, the alert goes on the phone.

493
00:27:20,200 --> 00:27:22,200
Speaker 4: He never has to look at a camera. He knows

494
00:27:22,200 --> 00:27:24,800
Speaker 4: when he gets that alert mails here. You can't do

495
00:27:24,880 --> 00:27:27,840
Speaker 4: that with RING, you can't do that with these other applications.

496
00:27:28,160 --> 00:27:31,240
Speaker 4: So that's a common use case that people know today

497
00:27:31,640 --> 00:27:37,760
Speaker 4: where standard digital twinting technology with AI, standard based communication,

498
00:27:38,359 --> 00:27:42,439
Speaker 4: and standard computing technologies can all be used to enable

499
00:27:42,520 --> 00:27:44,000
Speaker 4: use cases that we use every day.

500
00:27:44,640 --> 00:27:48,720
Speaker 2: Yep, we just have time for one more question. I

501
00:27:48,720 --> 00:27:53,600
Speaker 2: would like to get your number one. I guess area

502
00:27:53,680 --> 00:27:57,160
Speaker 2: of excitement for digital twins for.

503
00:27:57,160 --> 00:28:00,640
Speaker 4: Me is healthcare. What I want to see in my lifetime,

504
00:28:00,680 --> 00:28:02,280
Speaker 4: and we have the technology to do it. In fact,

505
00:28:02,280 --> 00:28:04,280
Speaker 4: we've have a few use cases with scene skates where

506
00:28:04,280 --> 00:28:06,640
Speaker 4: we're working with the medical community. I want the digital

507
00:28:06,680 --> 00:28:10,960
Speaker 4: twin of my health. I want for me the person

508
00:28:11,840 --> 00:28:14,200
Speaker 4: all think about all the data, all the medical records.

509
00:28:14,200 --> 00:28:15,640
Speaker 3: First of all, it's hard enough keeping all your medical

510
00:28:15,680 --> 00:28:16,200
Speaker 3: records together.

511
00:28:16,480 --> 00:28:20,760
Speaker 4: So not only my medical records, but the medications I've taken,

512
00:28:20,920 --> 00:28:23,600
Speaker 4: any reactions I've had. You have so much data from

513
00:28:23,680 --> 00:28:30,040
Speaker 4: blood work and positive reactions, negative reactions to medications, exercises

514
00:28:30,080 --> 00:28:32,840
Speaker 4: I've done that may have improved weight or blood pressure.

515
00:28:33,359 --> 00:28:36,159
Speaker 4: So as I grow and as all of us grow

516
00:28:36,440 --> 00:28:40,280
Speaker 4: and age, I should say yes, I want all of

517
00:28:40,320 --> 00:28:45,320
Speaker 4: that history to follow my DNA, my person to maximize healthcare.

518
00:28:45,680 --> 00:28:48,000
Speaker 4: I am the ultimate digital twin that I want. I

519
00:28:48,000 --> 00:28:50,760
Speaker 4: don't care about an avatar that's fun and fancy. I

520
00:28:50,800 --> 00:28:53,200
Speaker 4: want something that helps to improve my quality of life.

521
00:28:53,680 --> 00:28:56,040
Speaker 4: That's what I want out of interest. Have you seen

522
00:28:56,080 --> 00:29:00,800
Speaker 4: any companies or businesses looking into this. I did meet

523
00:29:00,840 --> 00:29:03,000
Speaker 4: a company or CEO of a company that's working on

524
00:29:03,040 --> 00:29:06,200
Speaker 4: the medical record side where they're trying to tie all

525
00:29:06,240 --> 00:29:09,640
Speaker 4: of that to the person so that can follow them,

526
00:29:09,720 --> 00:29:12,800
Speaker 4: so that now physicians and healthcare workers can have all that.

527
00:29:13,160 --> 00:29:15,800
Speaker 4: So it's a startup. It seems to be much more

528
00:29:15,840 --> 00:29:18,000
Speaker 4: challenging to get this done than you think it would be.

529
00:29:18,520 --> 00:29:22,000
Speaker 4: But we've engaged with some companies and hospitals that are

530
00:29:22,000 --> 00:29:25,040
Speaker 4: making their hospital smart. You can see some areas called

531
00:29:25,080 --> 00:29:28,520
Speaker 4: the smart operating room. That's a particular area in a

532
00:29:28,560 --> 00:29:31,440
Speaker 4: hospital that's obviously critical. I mean, you think about something

533
00:29:31,480 --> 00:29:34,800
Speaker 4: as basic as we're in the operating room, we're starting

534
00:29:34,800 --> 00:29:39,720
Speaker 4: the operation. I have twelve high value instruments on my right.

535
00:29:40,560 --> 00:29:42,920
Speaker 4: Those twelve high value instruments need to be there when

536
00:29:42,960 --> 00:29:45,600
Speaker 4: I finished, because if they're not there, there's a very

537
00:29:45,640 --> 00:29:48,040
Speaker 4: bad place they could be. Ye, that's right, and that

538
00:29:48,160 --> 00:29:50,360
Speaker 4: is a real example that I know personally somebody like

539
00:29:50,360 --> 00:29:52,160
Speaker 4: that that's happened to and they've had to go back

540
00:29:52,400 --> 00:29:55,840
Speaker 4: and get one of those instruments. So when you think

541
00:29:55,840 --> 00:29:58,520
Speaker 4: about the seriousness of the operating room, and that's before

542
00:29:58,520 --> 00:30:01,840
Speaker 4: you even get into intrusive sensors and I mean, you know,

543
00:30:01,880 --> 00:30:04,560
Speaker 4: what's the blood pressure and et cetera. Yes, you never

544
00:30:04,640 --> 00:30:07,240
Speaker 4: go to a hospital, are to a healthcare professional and

545
00:30:07,280 --> 00:30:09,200
Speaker 4: they take your blood pressure and that's it and you're good.

546
00:30:09,240 --> 00:30:10,520
Speaker 3: Then they start talking to you.

547
00:30:10,560 --> 00:30:12,200
Speaker 4: No, we don't even think about the fact that we

548
00:30:12,200 --> 00:30:16,320
Speaker 4: take blood pressure, we take temperature, we take weight, sometimes

549
00:30:16,320 --> 00:30:20,320
Speaker 4: we take blood. So we're already experiencing a multi modal

550
00:30:20,520 --> 00:30:23,640
Speaker 4: environment to maximize our health, but we don't always think

551
00:30:23,640 --> 00:30:25,080
Speaker 4: about that when we bring that to work. So now

552
00:30:25,120 --> 00:30:27,080
Speaker 4: I need a temperature sensor, I need light, I need

553
00:30:27,120 --> 00:30:30,400
Speaker 4: lie dar, I need cameras, I need different brands. I

554
00:30:30,440 --> 00:30:32,840
Speaker 4: need to apply intelligence to that. So now I can

555
00:30:32,920 --> 00:30:36,200
Speaker 4: perceive my space and my environment, I can understand it

556
00:30:36,240 --> 00:30:38,640
Speaker 4: with analysis and AI and make sense of it to

557
00:30:38,720 --> 00:30:41,920
Speaker 4: make decisions, and then I can also do prediction based

558
00:30:41,920 --> 00:30:43,440
Speaker 4: on that. So what should happen in the future.

559
00:30:43,960 --> 00:30:46,080
Speaker 2: That's great, Tony. I think we will leave it on

560
00:30:46,160 --> 00:30:48,280
Speaker 2: that note. Thanks so much, No.

561
00:30:48,360 --> 00:30:50,360
Speaker 3: Thank you, this was fun, really enjoyed it.

562
00:30:52,520 --> 00:30:55,680
Speaker 2: My deepest thanks to Tony Franklin for sharing his equities

563
00:30:55,720 --> 00:31:00,600
Speaker 2: with us. Today's chat about digital twins really our eyes

564
00:31:00,720 --> 00:31:04,040
Speaker 2: to the incredible potential. It's like stepping into a simulation

565
00:31:04,160 --> 00:31:07,920
Speaker 2: game where you can tweak maintenance schedules, production lines, and

566
00:31:08,000 --> 00:31:10,960
Speaker 2: even play around with the interaction between workers and machinery

567
00:31:11,200 --> 00:31:14,640
Speaker 2: using real world data. Yes, I'm letting my inner geek

568
00:31:14,680 --> 00:31:16,840
Speaker 2: shine through here, but the idea of managing a supply

569
00:31:17,000 --> 00:31:20,240
Speaker 2: chain with the ears of playing SimCity seems pretty cool

570
00:31:20,280 --> 00:31:24,120
Speaker 2: to me. Tony's closing thoughts on the future of healthcare

571
00:31:24,320 --> 00:31:27,400
Speaker 2: and the possibility of creating a human digital twin we're

572
00:31:27,400 --> 00:31:31,520
Speaker 2: particularly striking. Imagine having a clone of yourself in a sense.

573
00:31:32,120 --> 00:31:35,360
Speaker 2: I mean, we're already wearing watches that monitor heart rate,

574
00:31:35,560 --> 00:31:39,960
Speaker 2: physical activity, sleep quality, plus a range of other biometric data.

575
00:31:40,600 --> 00:31:42,880
Speaker 2: It's not too far fetched to dream about a future

576
00:31:42,920 --> 00:31:46,280
Speaker 2: where digital twins can forecast our health outcomes based on

577
00:31:46,320 --> 00:31:50,680
Speaker 2: our DNA, diet, and exercise. It's an interesting idea and

578
00:31:50,720 --> 00:31:53,120
Speaker 2: I'm looking forward to seeing where this technology takes us,

579
00:31:55,640 --> 00:31:58,040
Speaker 2: and lucky for us, we'll get a chance to explore

580
00:31:58,080 --> 00:32:01,480
Speaker 2: this further on our next episode Tuesday, April twenty third,

581
00:32:01,800 --> 00:32:05,640
Speaker 2: on technically Speaking, an Intel podcast, we'll be learning about

582
00:32:05,680 --> 00:32:09,120
Speaker 2: some of the revolutionary implementations of AI in the healthcare

583
00:32:09,120 --> 00:32:14,200
Speaker 2: space with team members from Intel and Siemens Healthineers See

584
00:32:14,200 --> 00:32:23,440
Speaker 2: you then. Technically Speaking was produced by Ruby Studio from

585
00:32:23,520 --> 00:32:28,000
Speaker 2: iHeartRadio in partnership with Intel and hosted by me Graham Class.

586
00:32:28,360 --> 00:32:31,840
Speaker 2: Our executive producer is Molly Sosher, Our EP of Post

587
00:32:31,840 --> 00:32:36,480
Speaker 2: Production is James Foster, and our supervising producer is Nikia Swinton.

588
00:32:37,520 --> 00:32:40,560
Speaker 2: This episode was edited by Sierra Spreen and was written

589
00:32:40,560 --> 00:32:51,240
Speaker 2: by Molly Sosher and Nick Firshall. Where do world changing

590
00:32:51,280 --> 00:32:55,080
Speaker 2: ideas get their start? At Intel? It starts with real solutions,

591
00:32:55,280 --> 00:32:59,920
Speaker 2: and real solutions start with exceptional engineering, the quantum computing,

592
00:33:00,760 --> 00:33:04,240
Speaker 2: the next generation of AI experts, the renewable energy grid,

593
00:33:04,440 --> 00:33:08,520
Speaker 2: liquid cooling, data centers, early diagnosis for cancer, water restoration,

594
00:33:08,720 --> 00:33:12,520
Speaker 2: and even farmland protection. The examples are countless, the impacts

595
00:33:12,520 --> 00:33:15,400
Speaker 2: are endless, but the foundation is always the same. It

596
00:33:15,520 --> 00:33:19,520
Speaker 2: starts with Intel join us in redefining what's achievable through

597
00:33:19,520 --> 00:33:22,680
Speaker 2: the power of AI. Learn more at intel dot com.

598
00:33:22,720 --> 00:33:23,600
Speaker 2: Slash stories