1
00:00:05,792 --> 00:00:11,240
[Paul Campbell] Hello everyone, welcome 
to our webinar today for Equidox AI,  

2
00:00:11,240 --> 00:00:16,720
which is a fully automated PDF remediation 
solution. We're very excited about this  

3
00:00:16,720 --> 00:00:20,840
cutting-edge technology that is solving 
for challenges within the healthcare  

4
00:00:20,840 --> 00:00:25,760
and healthcare insurance provider 
industries. By way of introduction,  

5
00:00:25,760 --> 00:00:32,240
today my name is Paul Campbell, and I will be 
joined by Dan Tuleta for the next 30 minutes.

6
00:00:32,240 --> 00:00:36,480
Some quick logistics: if you have questions 
during the webinar, please feel free to drop  

7
00:00:36,480 --> 00:00:41,600
them in the Q&A chat button at the bottom of 
your screen and we will get back to you with  

8
00:00:41,600 --> 00:00:47,640
an answer. Additionally, you know, this webinar 
will be recorded and will be sent to you after  

9
00:00:47,640 --> 00:00:53,400
the meeting in addition to the slide deck and 
a short survey. We're happy to do a more direct  

10
00:00:53,400 --> 00:00:57,800
interactive session with you and your other 
team members if they're not available to join,  

11
00:00:57,800 --> 00:01:02,120
and obviously, further our conversations 
as to whether Equidox AI may be a fit for  

12
00:01:02,120 --> 00:01:07,440
your organization specifically 
after you review here today.

13
00:01:07,440 --> 00:01:11,760
As far as the agenda today: first of all, 
I'm going to, you know, go through who is  

14
00:01:11,760 --> 00:01:18,600
Equidox Software Company and, you know, where 
have we been and where are we going. Second,  

15
00:01:18,600 --> 00:01:22,800
you know, the challenges that we've seen in the 
healthcare market as it relates to remediation  

16
00:01:22,800 --> 00:01:29,560
of PDF documents and our solution to that 
problem. I'm going to hand it over to Dan,  

17
00:01:29,560 --> 00:01:34,440
my colleague, to talk about why do we 
make PDFs accessible and, you know,  

18
00:01:34,440 --> 00:01:39,160
what's driving this. This will be followed 
by an overview of Equidox AI, how it works,  

19
00:01:39,160 --> 00:01:46,920
and finally, a demonstration for the last 15 
minutes of the half-hour we have here today.

20
00:01:46,920 --> 00:01:53,280
So who is Equidox? Equidox has been in existence 
for nearly a decade now. Way back when,  

21
00:01:53,280 --> 00:01:59,960
a Canadian citizen was trying to apply for a 
government job posting on the internet but,  

22
00:01:59,960 --> 00:02:05,800
unfortunately, was unable to do so because of 
her visual disability. She sued the government  

23
00:02:05,800 --> 00:02:12,480
and won her case, and the government of Canada 
sought out a solution to accommodate, you know,  

24
00:02:12,480 --> 00:02:15,600
this use case in the future. But they 
couldn't find one, and there was no one  

25
00:02:15,600 --> 00:02:20,240
really addressing it in the market, so they 
asked the marketplace to respond. Hence why,  

26
00:02:20,240 --> 00:02:27,680
you know, we started building our remediation 
solution and haven't stopped innovating since.

27
00:02:27,680 --> 00:02:34,640
So originally we created a software-as-a-service 
solution, you know, way back, and now, you know,  

28
00:02:34,640 --> 00:02:40,760
hundreds of customers currently use our SaaS 
product. This solution is a world-class, you know,  

29
00:02:40,760 --> 00:02:46,080
solution and is adding tremendous value to the 
marketplace of digital accessibility for not  

30
00:02:46,080 --> 00:02:51,840
only enterprise organizations but, you know, 
mid-level organizations, small businesses,  

31
00:02:51,840 --> 00:02:57,320
governments, and educational institutions as 
well. You know, our customers love the product,  

32
00:02:57,320 --> 00:03:03,080
evidenced by the fact that nearly 100% of our 
customers renew their subscription every year.

33
00:03:03,080 --> 00:03:07,880
And while this is all well and good, you know, 
we started hearing from organizations that,  

34
00:03:07,880 --> 00:03:12,200
you know, had tens of thousands or hundreds 
of thousands or even millions of pages in  

35
00:03:12,200 --> 00:03:19,080
documentation that needed to be remediated, and 
there just wasn't a fully automated solution for  

36
00:03:19,080 --> 00:03:25,200
that type of daunting need. Our SaaS solution, 
you know, is still a manual solution that has,  

37
00:03:25,200 --> 00:03:31,440
you know, some automated functions but doesn't 
truly automate the full process, and you know,  

38
00:03:31,440 --> 00:03:38,200
nothing out there does with the quality. So 
you know, the traditional service providers,  

39
00:03:38,200 --> 00:03:45,640
you know, at that time, you know, were sending 
the documents to India and other countries,  

40
00:03:45,640 --> 00:03:50,200
but you know, there's really no efficient way 
to scale. So companies were forced to settle for  

41
00:03:50,200 --> 00:03:55,040
a solution that is, you know, time-consuming, 
expensive, and doesn't truly mitigate the risk  

42
00:03:55,040 --> 00:04:00,880
of a lawsuit with some of the software tools 
and some of the, you know, service provider  

43
00:04:00,880 --> 00:04:06,400
solutions that were out there at the time.
So enter Equidox AI, and you know, Equidox AI  

44
00:04:06,400 --> 00:04:13,840
is a fully automated PDF remediation solution that 
removes the traditional manual remediation methods  

45
00:04:13,840 --> 00:04:21,560
and auto-tagging methods while still increasing 
the quality, accuracy, and compliance. The Equidox  

46
00:04:21,560 --> 00:04:28,960
AI solution is utilized for use cases where 
there are templated, reoccurring large volumes  

47
00:04:28,960 --> 00:04:36,160
of documents where manual remediation methods are 
just too cumbersome and daunting to address. And,  

48
00:04:36,160 --> 00:04:40,600
you know, we've found over the past couple of 
years that the healthcare industry can really  

49
00:04:40,600 --> 00:04:46,560
get the most value out of Equidox AI, and this 
is because of Section 508 compliance mandates,  

50
00:04:46,560 --> 00:04:51,840
the large quantities of templated and reoccurring 
documents that consistently need to be accessible  

51
00:04:51,840 --> 00:04:58,200
because of these compliance requirements and 
the challenges with current processes today.

52
00:04:58,200 --> 00:05:06,080
The quality, speed, and overall vendor, you 
know, just sprawl that these customers possess,  

53
00:05:06,080 --> 00:05:12,600
you know, currently at these organizations. So 
the use cases, you know, may include but are  

54
00:05:12,600 --> 00:05:18,480
not limited to the biggest one that we've seen: 
physician directories. You know, these can be,  

55
00:05:18,480 --> 00:05:22,000
you know, documents that are updated on a 
reoccurring basis and can be very daunting  

56
00:05:22,000 --> 00:05:27,400
to remediate and complex. Additionally, 
explanation of benefits, digital ID cards,  

57
00:05:27,400 --> 00:05:32,160
invoices, statements, etc., all these are 
really great candidates for Equidox AI  

58
00:05:32,160 --> 00:05:40,240
because of the high volume, repetitive, 
and templated nature that they possess.

59
00:05:40,240 --> 00:05:45,800
So, you know, we found that there are three 
main challenges for healthcare organizations  

60
00:05:45,800 --> 00:05:52,160
when it comes to PDF remediation. Number one 
is the costs. You know, multiple vendors,  

61
00:05:52,160 --> 00:05:58,160
we've seen outsource providers, and 
also investment into internal personnel,  

62
00:05:58,160 --> 00:06:02,240
is very costly for PDF remediation. 
It can really be a runaway train of  

63
00:06:02,240 --> 00:06:07,640
cost because the industry standard price per 
page can be exponential, and the manual work  

64
00:06:07,640 --> 00:06:13,680
at this capacity and scale is obviously very 
expensive. With that is the quality, you know,  

65
00:06:13,680 --> 00:06:19,520
because of the cumbersome manual processes and 
auto-tagging mishaps and issues with quality,  

66
00:06:19,520 --> 00:06:25,320
multiplied by, you know, the volumes of pages 
and scope and complexity. It really leaves  

67
00:06:25,320 --> 00:06:30,240
these organizations exposed to non-compliance 
with Section 508 and, you know, unfortunately,  

68
00:06:31,320 --> 00:06:37,080
lawsuits in some of these cases because of 
these elements. And lastly, the speed, you  

69
00:06:37,080 --> 00:06:42,560
know, with a lot of the use cases we've seen in 
healthcare organizations, you know, the demanding  

70
00:06:42,560 --> 00:06:49,600
legal requirements do require quick turnaround 
times to get this information out to customers  

71
00:06:49,600 --> 00:06:56,920
consistently, but it's not really realistic to 
accommodate with traditional manual processes  

72
00:06:56,920 --> 00:07:04,040
and the auto-tagging methods because of the 
volume to manage when coupled with the quality.

73
00:07:04,040 --> 00:07:08,840
So, we, you know, obviously wanted to create 
a better way to solve for these challenges,  

74
00:07:08,840 --> 00:07:13,760
and we did as mentioned with our, you know, 
solution Equidox AI. Our experts have found  

75
00:07:13,760 --> 00:07:19,760
a way to truly automate the PDF accessibility 
process for many of these healthcare use cases  

76
00:07:19,760 --> 00:07:26,400
involving high volumes. Equidox AI automation 
allows good quality, usability, and compliance  

77
00:07:26,400 --> 00:07:32,680
every single time because of our unique model 
creation. We don't auto-tag or cut corners or rely  

78
00:07:32,680 --> 00:07:40,240
on human elements to get the process done, you 
know, training these models with our developers,  

79
00:07:40,240 --> 00:07:48,680
our data scientists, and our accessibility experts 
to ensure that quality is key to the solution.

80
00:07:48,680 --> 00:07:52,760
You know, our Equidox AI automation also 
accommodates aggressive timelines because  

81
00:07:52,760 --> 00:07:57,880
we're relying on technology. We can dictate 
how fast the solution runs and turn the dial  

82
00:07:57,880 --> 00:08:04,320
up or down, so to speak, to accommodate these 
timelines that may be required. And lastly,  

83
00:08:04,320 --> 00:08:10,480
Equidox AI automation allows for lower costs, 
which everybody's looking for. You know,  

84
00:08:10,480 --> 00:08:16,680
to the bottom line to, you know, efficiently 
ensure that they're compliant, efficiently,  

85
00:08:16,680 --> 00:08:23,960
you know, make the documents accessible but while 
keeping costs down. And you know, we increase the  

86
00:08:23,960 --> 00:08:29,440
process improvements because of this and are 
also able to consolidate, you know, vendor  

87
00:08:30,120 --> 00:08:33,800
relationships because of this automation.

88
00:08:33,800 --> 00:08:38,440
So with that introduction, I'm going to 
pass it over to my colleague Dan Tuleta,  

89
00:08:38,440 --> 00:08:42,680
who is going to talk about, you know, why 
it's important to make PDFs accessible and  

90
00:08:42,680 --> 00:08:44,960
a little background about that, and then you know,  

91
00:08:44,960 --> 00:08:51,067
just how our Equidox AI works in more 
detail with a demonstration. Thank you. Dan?

92
00:08:51,067 --> 00:08:56,320
[Dan Tuleta] All right, thank you, Paul. So, hi 
everyone. I assume that most people on this call  

93
00:08:56,320 --> 00:09:04,760
are familiar with accessibility laws such as 
the ADA or Section 508 or the WCAG guidelines.  

94
00:09:04,760 --> 00:09:10,240
Since I'm not a lawyer, I'm not going to go 
into the details and the legal of these laws,  

95
00:09:10,240 --> 00:09:15,720
but at a high level, just like there are 
requirements to provide physical access,  

96
00:09:15,720 --> 00:09:21,320
like wheelchair ramps or elevators or Braille 
signage, organizations also need to ensure that  

97
00:09:21,320 --> 00:09:27,160
their public-facing digital content, including 
their PDF documents, is accessible to everyone,  

98
00:09:27,160 --> 00:09:32,720
including people with disabilities. Ignoring the 
accessibility of your digital content opens up  

99
00:09:32,720 --> 00:09:37,960
your organization to legal risks, and there have 
been thousands of organizations who learned this  

100
00:09:37,960 --> 00:09:43,000
the hard way when they were sued for exactly 
this type of problem, and there are thousands  

101
00:09:43,000 --> 00:09:49,120
more who quietly pay out large settlements, and 
yet they still have to circle back and fix their  

102
00:09:49,120 --> 00:09:55,200
accessibility deficiencies after that payout. 
Long story short, we live in a very digital world,  

103
00:09:55,200 --> 00:10:01,080
and we rely so heavily on digital information, 
so digital accessibility is not a fad,  

104
00:10:01,080 --> 00:10:09,920
and it's not going away, so it is always good to 
be aware of it and address it in a proactive way.

105
00:10:09,920 --> 00:10:14,760
For anyone who is unsure of why this 
digital accessibility stuff matters,  

106
00:10:14,760 --> 00:10:20,400
people with disabilities use various types of 
assistive technologies to interact with digital  

107
00:10:20,400 --> 00:10:27,680
content, like PDF documents. A very common type 
of assistive technology is called a screen reader,  

108
00:10:27,680 --> 00:10:32,400
which is capable of reading digital 
content like websites, applications,  

109
00:10:32,400 --> 00:10:39,800
and documents. Screen readers use what are called 
digital tags to navigate documents. The tags need  

110
00:10:39,800 --> 00:10:45,560
to be properly encoded into a document to organize 
the content and make it compatible with the screen  

111
00:10:45,560 --> 00:10:51,680
reader. Think of the tags as a framework of the 
document, which gives the screen reader user  

112
00:10:51,680 --> 00:10:59,480
the ability to navigate and interact with all of 
the various elements within that PDF. Equidox, in  

113
00:10:59,480 --> 00:11:06,040
cooperation with the National Federation of the 
Blind, surveyed about 250 blind and low-vision  

114
00:11:06,040 --> 00:11:12,760
individuals who rely on screen readers to interact 
with PDFs every day. Based on this survey,  

115
00:11:12,760 --> 00:11:17,600
we found that at least two-thirds of PDF 
documents are inaccessible to people with  

116
00:11:17,600 --> 00:11:22,640
disabilities. So if you just take a moment to 
put yourself in the shoes of a blind person,  

117
00:11:22,640 --> 00:11:27,000
you can quickly imagine how frustrated 
you would become if you could not read  

118
00:11:27,000 --> 00:11:32,680
two-thirds of the documents that you came into 
contact with on a daily basis. On top of that,  

119
00:11:32,680 --> 00:11:37,920
imagine the privacy issues if you have 
to go and ask your neighbor or a friend  

120
00:11:37,920 --> 00:11:44,040
to help you read private documents like a 
banking or investment statement, an invoice,  

121
00:11:44,040 --> 00:11:51,080
a pay stub, or health insurance policy documents 
or medical test results. It could be embarrassing,  

122
00:11:51,080 --> 00:11:59,280
and it's just a breach of privacy that 
no one should have to live through.

123
00:11:59,280 --> 00:12:02,760
To further emphasize the points I 
was making a couple of slides ago,  

124
00:12:02,760 --> 00:12:06,360
here's some additional information about 
the volumes and the types of lawsuits that  

125
00:12:06,360 --> 00:12:11,720
organizations have faced and will continue 
to face moving forward. Just to reiterate,  

126
00:12:11,720 --> 00:12:16,960
the digital accessibility requirements that 
organizations must adhere to are not going away,  

127
00:12:16,960 --> 00:12:21,200
and there will continue to be an increase 
in the attention that is paid to it by state  

128
00:12:21,200 --> 00:12:26,720
and federal mandates. The DOJ, disability 
advocacy groups, and individuals who simply  

129
00:12:26,720 --> 00:12:30,920
want to be able to access their critical 
information are going to continuously put  

130
00:12:30,920 --> 00:12:39,120
more and more pressure on organizations to 
adhere to these accessibility standards.

131
00:12:39,120 --> 00:12:46,040
One of the main challenges with PDF accessibility 
is that each PDF document is unique. We have heard  

132
00:12:46,040 --> 00:12:52,560
a lot of empty promises of fully automating PDF 
accessibility, but there are so many things about  

133
00:12:52,560 --> 00:12:59,120
PDFs that require human interpretation to decide 
how to tag specific elements within the content.  

134
00:13:00,080 --> 00:13:05,040
I have been working in the PDF accessibility 
market for over seven years now, and I've  

135
00:13:05,040 --> 00:13:09,680
seen a lot of organizations who come to us, but 
they assume that they have accessible documents  

136
00:13:09,680 --> 00:13:16,600
because their documents have some tags, but they 
quickly learn that these tags are not necessarily  

137
00:13:16,600 --> 00:13:24,120
usable or compliant, and they are still open to 
litigation. So please be aware of this concept of  

138
00:13:24,120 --> 00:13:30,160
autotagging. Auto-tagging technology is really 
just masking or masking a solution to fully  

139
00:13:30,160 --> 00:13:37,280
automate PDF accessibility, but these auto-taggers 
are capable of putting tags on a page,  

140
00:13:37,280 --> 00:13:42,360
but there's always going to be accuracy issues 
with them, and the inaccuracy of those tags can  

141
00:13:42,360 --> 00:13:48,160
lead to a ton of confusion and frustration 
for a screen reader user. Additionally,  

142
00:13:48,160 --> 00:13:53,760
auto-taggers can and will leave organizations 
open to further litigation because there is no  

143
00:13:53,760 --> 00:13:59,240
guarantee of compliance with WCAG standards. 
So even paying to outsource your huge batch  

144
00:13:59,240 --> 00:14:05,120
of documents to companies who auto-tag them, you 
are not mitigating your risk of litigation because  

145
00:14:05,120 --> 00:14:12,040
auto-tagging simply falls short of true compliance 
with accessibility standards. Oh, excuse me,  

146
00:14:12,040 --> 00:14:18,240
I hit the wrong button. The alternative of 
outsourcing the remediation work to third parties  

147
00:14:18,240 --> 00:14:25,320
who are almost exclusively located overseas also 
introduces a mountain of data privacy issues,  

148
00:14:25,320 --> 00:14:30,280
and even if you can work around that, the sheer 
volume is impossible to keep up with. These  

149
00:14:30,280 --> 00:14:36,080
outsourced remediation providers will cut corners 
and do the absolute bare minimum amount of work  

150
00:14:36,080 --> 00:14:41,560
to make the document pass an automated checker, 
but they are not actually making the documents  

151
00:14:41,560 --> 00:14:46,440
compliant because it simply takes too long to meet 
the deadlines when you're dealing with that type  

152
00:14:46,440 --> 00:14:52,920
of volume. Incorporating artificial intelligence, 
more specifically computer vision and machine  

153
00:14:52,920 --> 00:14:59,440
learning, into high-volume PDF remediation 
allows our Equidox accessibility expert  

154
00:14:59,440 --> 00:15:07,120
to train an AI model to accurately identify and 
tag all of the elements in the document template,  

155
00:15:07,120 --> 00:15:11,040
and the use of AI developed by our data 
scientists paired with that human element  

156
00:15:11,040 --> 00:15:17,040
of our trained accessibility experts allows for 
incredibly accurate, usable, and compliant PDFs  

157
00:15:17,040 --> 00:15:23,280
to be returned to the customer in a fraction 
of the time because AI works exponentially  

158
00:15:23,280 --> 00:15:29,000
faster than humans manually tagging each 
page. AI doesn't need to take vacations,  

159
00:15:29,000 --> 00:15:35,960
it can work 24/7, 365 without breaks, and 
also AI doesn't need to cut corners to meet  

160
00:15:35,960 --> 00:15:45,680
a deadline. And of course, we're going well 
beyond just a simple autotagging process.

161
00:15:45,680 --> 00:15:53,120
So, how does any of this work? Well, our 
accessibility experts use example documents  

162
00:15:53,120 --> 00:15:59,920
of customer templates to properly identify the 
various elements on the page. These elements might  

163
00:15:59,920 --> 00:16:06,560
include text or paragraph structure, various 
levels of headings, lists and tables, graphs,  

164
00:16:06,560 --> 00:16:12,960
and images, in the reading order of the content, 
which is very, very important. This training data  

165
00:16:12,960 --> 00:16:19,520
is then fed to an AI model to apply what it has 
learned en masse to many thousands or millions of  

166
00:16:19,520 --> 00:16:30,360
pages that have similar templates and formatting. 
Although the mechanics of how this AI technology  

167
00:16:30,360 --> 00:16:35,160
works is a little bit abstract and much more 
complicated than what I'm capable of showing  

168
00:16:35,160 --> 00:16:41,720
you on a simple PowerPoint slide, here are just 
a few high-level examples of how we can visualize  

169
00:16:41,720 --> 00:16:49,440
the AI at work. In this scatter plot, each of the 
green dots represents a page in a PDF document. If  

170
00:16:49,440 --> 00:16:54,720
you can see, they are grouped together based on 
similarities that the computer vision finds. So,  

171
00:16:54,720 --> 00:16:58,840
for example, this cluster will contain 
all of the pages containing pie charts.  

172
00:17:01,640 --> 00:17:06,640
In this example, you can see there are different 
multicolumn text layouts that the AI will also  

173
00:17:06,640 --> 00:17:12,160
use to recognize different pages and group 
them together appropriately. The AI will also  

174
00:17:12,160 --> 00:17:17,840
pick up on font styles, sizes, and colors 
to help it establish accurate tags on a  

175
00:17:17,840 --> 00:17:25,480
page. We can even train the AI to identify 
the many potential variations in tables,  

176
00:17:25,480 --> 00:17:31,440
which are extremely complicated to tag accurately, 
so the different numbers of rows and columns,  

177
00:17:31,440 --> 00:17:37,680
table headers versus table data, and even tables 
of varying sizes that might span across multiple  

178
00:17:37,680 --> 00:17:44,800
pages. All of this can be handled through the 
AI. The result of all of this extensive document  

179
00:17:44,800 --> 00:17:51,320
analysis and training of the model, and feeding 
the data to the AI, is creating a fully compliant  

180
00:17:51,320 --> 00:17:58,120
PDF document without any human remediators, who 
are both expensive to employ or outsource to,  

181
00:17:58,120 --> 00:18:02,920
and they are also, of course, liable to make 
errors or be forced to cut corners just to be  

182
00:18:02,920 --> 00:18:08,920
able to meet an unattainable deadline due to 
the volume demands. We are also reaching full  

183
00:18:08,920 --> 00:18:14,320
compliance because this is not autotaggers 
throwing sloppy tags on a page and saying  

184
00:18:14,320 --> 00:18:21,080
"quote-unquote good enough." And then, of course, 
beyond compliance and passing automated checkers,  

185
00:18:21,080 --> 00:18:25,680
the bonus of using AI for high-volume, 
hyper-fast remediation is that it will  

186
00:18:25,680 --> 00:18:30,560
produce incredibly accurate and very usable 
documents for people with disabilities,  

187
00:18:30,560 --> 00:18:36,920
so your customers who rely on assistive technology 
will not be filing complaints or lawsuits or  

188
00:18:36,920 --> 00:18:44,200
calling your headquarters to complain about 
documents that they can't navigate or understand.

189
00:18:44,200 --> 00:18:49,440
So we're just about ready to jump into 
a demonstration of this AI technology,  

190
00:18:49,440 --> 00:18:54,680
but before we do, I just want to make it clear 
that this underlying technology can be deployed in  

191
00:18:54,680 --> 00:19:01,160
several ways to align with your organization's 
requirements. We have built an interface,  

192
00:19:01,160 --> 00:19:06,600
which you will see during the demonstration, that 
could allow theoretically your employees to run  

193
00:19:06,600 --> 00:19:14,240
this process from start to finish with just a few 
clicks by uploading the document or documents,  

194
00:19:14,240 --> 00:19:21,160
running the batch, and then downloading the 
finished PDF or multiple PDFs. We can also embed  

195
00:19:21,160 --> 00:19:28,720
the AI models into an existing document creation 
and delivery system through the use of APIs.  

196
00:19:29,240 --> 00:19:34,400
This could be critical for customers needing 
to download private documents, like a monthly  

197
00:19:34,400 --> 00:19:39,440
statement or an explanation of benefits or 
medical test results or something along those  

198
00:19:39,440 --> 00:19:47,840
lines. Lastly, Equidox can operate the entire 
process on your behalf as a managed service,  

199
00:19:47,840 --> 00:19:53,960
so we can take care of the remediation as well 
as the validation of that remediation to ensure  

200
00:19:53,960 --> 00:19:58,840
that everything exceeds all accessibility 
requirements, and then also deliver that  

201
00:19:58,840 --> 00:20:07,360
fully compliant PDF back to your 
organization to be posted and distributed.

202
00:20:07,360 --> 00:20:15,800
Just one more thing to note: Equidox AI is tagging 
the PDFs at the post-processing stage, which you  

203
00:20:15,800 --> 00:20:21,600
will see during the demonstration, and what I mean 
by that is that these PDFs are already created,  

204
00:20:21,600 --> 00:20:26,080
and we are applying the accessibility 
as a final step before they are publicly  

205
00:20:26,080 --> 00:20:32,800
distributed. The advantage of tagging PDFs at 
the post-processing stage is that we do not have  

206
00:20:32,800 --> 00:20:40,400
to disrupt or completely rebuild your document 
creation process. Your designers and producers  

207
00:20:40,400 --> 00:20:45,960
of mass documentation can continue their process, 
and we will handle the accessibility component at  

208
00:20:45,960 --> 00:20:53,000
the very end of the creation stage, but right 
before that document reaches your customer.

209
00:20:58,960 --> 00:21:02,960
switch over to the Equidox batch 
interface. We're going to do a  

210
00:21:02,960 --> 00:21:07,040
little demonstration of how this technology works.

211
00:21:07,040 --> 00:21:13,960
So, as I said, we do have this small interface 
built for demonstration purposes. But in theory,  

212
00:21:13,960 --> 00:21:20,480
this type of technology could be deployed 
to users within your own organization,  

213
00:21:20,480 --> 00:21:25,040
who would be able to use an interface like 
this, perhaps slightly customized for you,  

214
00:21:25,040 --> 00:21:32,040
to manage this workflow internally. We can, of 
course, also do this as a managed service for you.

215
00:21:32,040 --> 00:21:36,640
Now, what I'm going to do to get started is I'm 
going to go to the 'Upload Documents' tab. This  

216
00:21:36,640 --> 00:21:41,360
will take me to this view here, where I can 
then open up the folders on my hard drive.  

217
00:21:41,360 --> 00:21:45,280
I'm going to just grab this document that 
we want to run through the process today.  

218
00:21:45,280 --> 00:21:50,160
When I drag and drop that document into this 
rectangle, a blue 'Upload' button will appear.  

219
00:21:50,160 --> 00:21:54,240
I'm just going to give this document a 
few seconds to upload. When it uploads,  

220
00:21:54,240 --> 00:21:59,640
it'll then be ready. It's going to be in the 
system, ready to go for the batch process.

221
00:21:59,640 --> 00:22:04,520
My next step is I'm going to go to the 
'Create and Run Batch' tab. From this view,  

222
00:22:04,520 --> 00:22:09,520
we have this dropdown menu where I can 
select a model that I want to apply for  

223
00:22:09,520 --> 00:22:16,040
this batch. I'm going to select this model 
right here. Once I select that model,  

224
00:22:17,120 --> 00:22:21,440
another set of options appears, and this 
is the document that I just uploaded. So,  

225
00:22:21,440 --> 00:22:26,240
I'm going to select this document, and 
I'm simply going to hit 'Run Batch.' Now,  

226
00:22:26,240 --> 00:22:31,320
when I hit 'Run Batch,' it's going to populate 
in this list, and we see some different dots  

227
00:22:31,320 --> 00:22:36,760
here to kind of indicate which stage it is in 
during the process. We have some other details  

228
00:22:36,760 --> 00:22:44,560
about the document right up here, showing 
us like how many pages, how many documents,  

229
00:22:44,560 --> 00:22:50,720
how much time it's taking, and so on. Down 
here, the different stages of the remediation.

230
00:22:50,720 --> 00:22:55,800
Right now, Equidox is analyzing the 
document and applying the ML zones.  

231
00:22:55,800 --> 00:23:00,640
The computer vision and machine learning 
are working in the background to analyze  

232
00:23:00,640 --> 00:23:06,760
all of these various pages and accurately tag 
the content. Once it finishes getting tagged,  

233
00:23:06,760 --> 00:23:11,800
it will then go to the export engine. We're 
basically going to rebuild the PDF and create  

234
00:23:11,800 --> 00:23:18,000
an exact replica version of that document with 
all of the tags properly organized and applied  

235
00:23:18,000 --> 00:23:23,320
to the content. Once it finishes exporting, 
I'll be able to download that completed file,  

236
00:23:23,320 --> 00:23:28,600
and that document will be fully tagged, fully 
compliant, fully usable for screen reader users.

237
00:23:28,600 --> 00:23:32,600
Now, while that is running, I'm going to 
open up the document that we just uploaded  

238
00:23:32,600 --> 00:23:38,000
just so we can take a look at it. If I look at 
this document in my default PDF viewer here,  

239
00:23:38,000 --> 00:23:45,000
Adobe Acrobat, this document is completely 
untagged. There's no tag structure at all.  

240
00:23:45,000 --> 00:23:48,880
If we were to run accessibility 
checkers across this document,  

241
00:23:49,920 --> 00:23:54,840
virtually everything would light up as an error, 
because there are no tags for an accessibility  

242
00:23:54,840 --> 00:23:58,440
checker to check for, so it assumes that 
everything is wrong because it is wrong.  

243
00:23:58,960 --> 00:24:04,800
You cannot have an untagged document. This is 
completely unusable to a screen reader user.

244
00:24:04,800 --> 00:24:08,480
If we just take a quick look at some 
of the content in this document,  

245
00:24:08,480 --> 00:24:14,440
this document is a 100-page 
excerpt of a much larger document,  

246
00:24:14,440 --> 00:24:20,720
but it is a physician's directory. This 
would be for a healthcare insurance type  

247
00:24:20,720 --> 00:24:27,640
of company that is going to provide a PDF 
document with all of the hospitals, doctors,  

248
00:24:28,440 --> 00:24:34,920
physicians, physical therapists, dentists, 
and everyone in their network that you can  

249
00:24:34,920 --> 00:24:40,960
use as part of your healthcare coverage. These 
healthcare providers must provide this in a PDF  

250
00:24:40,960 --> 00:24:47,640
format—it's the law—but the challenge is that 
these documents are constantly being updated,  

251
00:24:47,640 --> 00:24:57,160
often being updated every single month. They are 
typically upwards of 1,000 to 5,000 pages long.  

252
00:24:58,640 --> 00:25:04,560
Another challenge is that many providers are in 
markets where they have to provide this document  

253
00:25:04,560 --> 00:25:11,840
in multiple languages, not just English but 
also Spanish, Mandarin Chinese, or Vietnamese.

254
00:25:13,680 --> 00:25:24,480
Given the complexity and frequency of updates, 
any team of humans would struggle to keep up  

255
00:25:24,480 --> 00:25:29,640
with the volume demand and the constant flow 
of these documents as they get updated monthly.  

256
00:25:33,120 --> 00:25:34,800
Auto-tagging technology is not reliable 
for these complex documents, as there is  

257
00:25:34,800 --> 00:25:45,920
a very specific heading structure, reading 
order, and variances across these pages.  

258
00:25:45,920 --> 00:25:51,000
This makes it impossible to rely solely on 
auto-tagging technology to do this accurately.

259
00:25:51,720 --> 00:25:58,360
So, when we go back to the batch interface and 
see that the process has completed, we'll open  

260
00:25:58,360 --> 00:26:04,240
up that new document and see a dramatic change—the 
document will visually look the same, but all of  

261
00:26:04,240 --> 00:26:14,240
the content will be tagged accurately. This new 
document is completed and ready to download.

262
00:26:14,240 --> 00:26:21,440
If I just hit the 'Completed File Download' 
button, I'll download this one, put it on my  

263
00:26:21,440 --> 00:26:33,920
desktop, and then open it in our app. Here's 
the new version of the document. If I go to  

264
00:26:33,920 --> 00:26:41,480
my tab for the accessibility tags, you can 
see the big difference. All of this content  

265
00:26:41,480 --> 00:26:46,880
is now tagged. If you start to tab through it, 
you'll see that we have the heading level one,  

266
00:26:47,760 --> 00:26:51,720
then the heading level two, heading 
level three, heading level four,  

267
00:26:51,720 --> 00:26:58,080
and heading level five, with the subsequent 
information about that specific area of Iowa.

268
00:26:58,080 --> 00:27:01,960
As you tab through, you can see that 
all of the content is grouped together  

269
00:27:01,960 --> 00:27:10,400
appropriately and read in the way 
it should be. This is critical for  

270
00:27:10,400 --> 00:27:15,880
the usability of this document. I could, of 
course, tab through all 100 pages of this,  

271
00:27:15,880 --> 00:27:20,960
but what you'll see is more of the same 
accurate, consistent tag structure being  

272
00:27:20,960 --> 00:27:26,560
applied to many pages without a single human 
being having to be involved in the process.

273
00:27:26,560 --> 00:27:32,000
This would allow this particular healthcare 
company to manage literally hundreds of thousands,  

274
00:27:32,000 --> 00:27:37,080
if not millions, of pages of documents just 
like this throughout the course of the year,  

275
00:27:37,080 --> 00:27:43,320
without having to outsource it or 
rely on auto-tagging technology.

276
00:27:44,160 --> 00:27:49,960
This technology can be deployed in a number 
of ways: It can be inserted into your document  

277
00:27:49,960 --> 00:27:54,800
creation process, we can run it for you as 
a managed service, or potentially you could  

278
00:27:54,800 --> 00:28:00,600
deploy an application like this using this type 
of interface to manage the service yourself.

279
00:28:00,600 --> 00:28:04,680
Just keep that in mind. Now I'm going 
to jump back to the slide deck here,  

280
00:28:04,680 --> 00:28:09,640
just to wrap things up, because we're 
just about out of time. As Paul said,  

281
00:28:09,640 --> 00:28:15,640
this is being recorded, and we will insert 
all of the information about that demo,  

282
00:28:17,080 --> 00:28:23,360
as well as the slide deck to be shared with 
you. Here are some links if you'd like to  

283
00:28:23,360 --> 00:28:28,120
learn more about digital accessibility 
and how it relates to your PDF documents.

284
00:28:30,680 --> 00:28:35,360
In conclusion, I just want to thank everyone for 
joining us here today. We hope that you can see  

285
00:28:35,360 --> 00:28:41,160
the value and capabilities of this new technology. 
Please do not hesitate to reach out to us for more  

286
00:28:41,160 --> 00:28:46,440
of a one-on-one type of consultation, so that 
we can discuss your organization's unique use  

287
00:28:46,440 --> 00:28:53,320
case and how Equidox AI can be applied to 
them. Also, we will be sending a recording,  

288
00:28:53,320 --> 00:28:58,240
so feel free to share this with anyone in 
your organization who might benefit from it,  

289
00:28:58,240 --> 00:29:03,240
along with a link to the deck. If anyone 
asked a question using the Q&A feature,  

290
00:29:03,240 --> 00:29:06,640
we will get back to them with 
a response as soon as possible.

291
00:29:06,640 --> 00:29:09,800
Lastly, there's going to be a short survey 
sent out, so if you don't mind just taking  

292
00:29:09,800 --> 00:29:15,920
a moment to fill it out, we would greatly 
appreciate it. Thank you again for joining,  

293
00:29:15,920 --> 00:29:22,600
and have a great rest of your day. For more 
information about how Equidox Software Company  

294
00:29:22,600 --> 00:29:28,040
can help you with PDF accessibility, 
email us at EquidoxSales@Equidox.co  

295
00:29:28,800 --> 00:29:37,600
or give us a call at 216-529-3030, or 
visit our website at www.Equidox.co.