1 00:00:29,960 --> 00:00:47,240 [Paul Campbell] Good afternoon, everyone. Welcome  to our webinar for Equidox AI, which is a fully   2 00:00:47,240 --> 00:00:53,560 automated PDF remediation solution. We are very  excited about this cutting-edge technology that   3 00:00:53,560 --> 00:01:00,480 is solving PDF remediation challenges at scale. By  way of introduction, my name is Paul Campbell and   4 00:01:00,480 --> 00:01:06,640 I will be joined today by Dan Tuleta for the next  30 minutes. Quick logistics, if you have questions   5 00:01:06,640 --> 00:01:13,800 during the webinar please drop them in the Q&A  chat button at the bottom of the screen and we'll   6 00:01:13,800 --> 00:01:18,680 get back to you with an answer. Additionally,  this webinar will be recorded and will be sent   7 00:01:18,680 --> 00:01:24,680 after the meeting in addition to the slide deck  and also a short survey, which we'd appreciate   8 00:01:24,680 --> 00:01:29,920 you filling out. We're also happy to do a more  direct interactive session with you and other   9 00:01:29,920 --> 00:01:37,600 team members if they were not available to join  and further our conversations as to how Equidox AI   10 00:01:37,600 --> 00:01:44,680 may be a fit for your organization specifically.  Overview of the agenda today: first we're going to   11 00:01:44,680 --> 00:01:50,680 talk about who is Equidox Software Company, where  we have been and where we are going, challenges   12 00:01:50,680 --> 00:01:55,800 we have seen in the market, and our solution to  the problem. Then, Dan is going to talk about why   13 00:01:55,800 --> 00:02:03,120 we make PDFs accessible, what's driving this, why  should people make PDF accessible, followed by an   14 00:02:03,120 --> 00:02:11,280 overview of Equidox AI how it works, and finally,  a demonstration of our new bleeding-edge, powerful   15 00:02:11,280 --> 00:02:20,760 technology. So a little bit about Equidox: we've  been around in existence for nearly a decade. Way   16 00:02:20,760 --> 00:02:26,880 back when, a Canadian citizen was trying to apply  for a government job posting on the internet but   17 00:02:26,880 --> 00:02:33,000 she was unfortunately unable to do so because of  her visual disability. She sued the government and   18 00:02:33,000 --> 00:02:40,080 won her case. The government sought out a solution  at that point but they couldn't find one so they   19 00:02:40,080 --> 00:02:46,160 asked the marketplace to respond and that's hence  why we as Equidox started to build a solution. And   20 00:02:46,160 --> 00:02:53,000 we really haven't stopped innovating since. We  created a robust software as a service solution   21 00:02:53,000 --> 00:02:59,880 and now hundreds of customers currently use our  SaaS product. The solution is world class and is   22 00:02:59,880 --> 00:03:05,120 adding tremendous value to the marketplace  of digital accessibility for Enterprise   23 00:03:05,120 --> 00:03:11,640 organizations, government organizations, and  educational institutions. Our customers love   24 00:03:11,640 --> 00:03:16,880 the product, evidenced by the fact that nearly  100% of our customers renew their subscription   25 00:03:16,880 --> 00:03:24,560 every year. That is all well and good, however,  we started hearing from organizations in the last   26 00:03:24,560 --> 00:03:30,000 couple years that had tens of thousands, hundreds  of thousands, or even millions of documents that   27 00:03:30,000 --> 00:03:36,240 needed to be remediated and there simply wasn't  an automated solution for that daunting need. The   28 00:03:36,240 --> 00:03:42,400 traditional service providers were sending the  documents to India and other countries but there   29 00:03:42,400 --> 00:03:51,240 was no efficient way to scale so companies,  unfortunately, were forced to settle for a   30 00:03:51,240 --> 00:03:58,120 solution that is time consuming, expensive, and  doesn't truly mitigate the risk of a lawsuit from   31 00:03:58,120 --> 00:04:05,000 what we found. So enter Equidox AI and why  we figured we wanted to solve this problem   32 00:04:05,000 --> 00:04:13,920 in the market. Equidox AI is a fully automated PDF  remediation solution that removes the traditional,   33 00:04:13,920 --> 00:04:19,760 manual remediation methods and auto-tagging  methods while increasing quality, accuracy,   34 00:04:19,760 --> 00:04:28,600 and compliance. Equidox AI is utilized for use  cases where there are templated, recurring,   35 00:04:28,600 --> 00:04:32,720 large volumes of documents where manual  remediation methods are just too cumbersome   36 00:04:32,720 --> 00:04:40,240 and daunting to address. There are three main  challenges when it comes to PDF remediation   37 00:04:40,240 --> 00:04:49,560 that we have found. Number one: costs. Companies  have multiple vendors. Outsource providers and   38 00:04:49,560 --> 00:04:54,720 the and the investment internally for personnel  is very costly can really be a runaway train of   39 00:04:54,720 --> 00:05:01,360 cost because of the industry standard price per  page can be exponential and the manual work to   40 00:05:01,360 --> 00:05:07,400 this capacity and scale is extremely expensive.  Quality, number two. Because of the cumbersome,   41 00:05:07,400 --> 00:05:14,480 manual processes discussed, auto-tagging mishaps  and and other issues multiplied by the volumes of   42 00:05:14,480 --> 00:05:20,400 pages in scope and complexity leaves organizations  exposed to non-compliance and potential lawsuits   43 00:05:20,400 --> 00:05:25,520 because of these elements. And the last one  is speed. Because of the demanding legal   44 00:05:25,520 --> 00:05:31,400 requirements and quick turnaround times to get  accessible information to customers or employees   45 00:05:31,400 --> 00:05:37,160 consistently, it's not realistic to accommodate  with traditional, manual processes and the   46 00:05:37,160 --> 00:05:42,600 traditional auto tagging methods because of the  sheer volumes to manage when coupled with that 47 00:05:42,600 --> 00:05:54,400 quality. So we obviously wanted to create a better  way to solve for these challenges, and we have.   48 00:05:54,400 --> 00:06:00,480 Our experts have found a way to truly automate  the PDF accessibility process for many use cases   49 00:06:00,480 --> 00:06:07,840 involving high volumes of documentation in a  reoccurring way. Equidox AI automation allows,   50 00:06:07,840 --> 00:06:14,080 number one, for good quality usability and  compliance every time because of our unique model   51 00:06:14,080 --> 00:06:20,080 creation using machine learning and artificial  intelligence. However, we don't autotag, or cut   52 00:06:20,080 --> 00:06:26,920 corners, or rely on any human element to get the  process done and not only will pass a checker but   53 00:06:26,920 --> 00:06:34,040 will be fully usable and accessible to anyone with  a screen reader, which is very near and dear to   54 00:06:34,040 --> 00:06:42,080 our hearts as a remediation organization.  Equidox AI automation also accommodates   55 00:06:42,080 --> 00:06:47,760 aggressive timelines. Because we're relying on the  technology, we can dictate how fast the solution   56 00:06:47,760 --> 00:06:53,320 runs and turn the dial up and down, so to speak,  to accommodate timelines that may be required   57 00:06:53,320 --> 00:06:58,680 because we have flexibility in the infrastructure  and the compute that we apply to to satisfy those   58 00:06:58,680 --> 00:07:05,800 timelines. And then lastly, Equidox AI automation  allows for lower costs and process improvements   59 00:07:05,800 --> 00:07:13,040 and vendor consolidation where you don't have to  rely on multiple vendors doing a common task. You   60 00:07:13,040 --> 00:07:18,760 can kind of have one organization to produce  this automated solution for your high volume,   61 00:07:18,760 --> 00:07:24,480 templates, templated documents. So with that said,  now I'm going to turn it over to my colleague,   62 00:07:24,480 --> 00:07:29,880 Dan, to talk about why it's important to  make PDFs accessible and how Equidox AI   63 00:07:29,880 --> 00:07:35,960 really works and, finally, a demonstration. Dan? [Dan Tuleta] Great, thank you, Paul. Hi, everyone.   64 00:07:35,960 --> 00:07:43,080 So yeah, let's talk a little bit about why we  are making PDFs accessible. So I assume that most   65 00:07:43,080 --> 00:07:49,000 people on this call are at least somewhat familiar  with accessibility laws like the Americans   66 00:07:49,000 --> 00:07:56,240 with Disabilities Act or Section 508 of The  Rehabilitation Act. I am not a lawyer so I'm not   67 00:07:56,240 --> 00:08:02,000 going to go into the details of all of these laws  but just at a high level, there are requirements   68 00:08:02,000 --> 00:08:08,400 for organizations to provide physical access like  wheelchair ramps, elevator, or elevators, Braille   69 00:08:08,400 --> 00:08:13,520 signage, and organizations need to ensure that  their public facing digital content, including   70 00:08:13,520 --> 00:08:18,600 PDFs, is accessible to everyone just the same as  they are to make sure that there's physical access   71 00:08:18,600 --> 00:08:25,360 to their buildings and facilities. So ignoring  the accessibility of your digital content opens   72 00:08:25,360 --> 00:08:30,920 up your organization to legal risks. There have  been thousands of organizations who learn this the   73 00:08:30,920 --> 00:08:37,000 hard way when they've been sued for exactly this  type of problem, and there are thousands more who   74 00:08:37,000 --> 00:08:43,480 quietly pay large settlements kind of quietly  and then they still have to ultimately go back   75 00:08:43,480 --> 00:08:50,160 and fix their accessibility deficiencies. So long  story short, we live in a very digital world and   76 00:08:50,160 --> 00:08:55,880 we rely so heavily on digital information.  So digital accessibility is not a fad and   77 00:08:55,880 --> 00:09:01,080 it's not going away, so it's always good to be  aware of it and and address it in a proactive 78 00:09:01,080 --> 00:09:09,440 way. So for anyone who is unsure of why any of  this digital accessibility stuff matters in the   79 00:09:09,440 --> 00:09:15,720 real world, people with disabilities use various  types of assistive technologies to interact with   80 00:09:15,720 --> 00:09:23,040 digital content like PDFs. A very common type of  assistive technology is called a screen reader,   81 00:09:23,040 --> 00:09:27,840 which is capable of reading digital  content like websites, applications,   82 00:09:27,840 --> 00:09:35,080 and documents. Screen readers use digital  tags to navigate documents, and these tags   83 00:09:35,080 --> 00:09:41,000 need to be properly encoded into the document  to organize the content and make it compatible   84 00:09:41,000 --> 00:09:46,760 with the screen reader. So think of the tags as a  framework of the document which gives the screen   85 00:09:46,760 --> 00:09:54,760 reader the ability to navigate and interact with  all of the various elements in the PDF. Equidox,   86 00:09:54,760 --> 00:10:01,080 in cooperation with the National Federation  of the Blind, surveyed about 250 blind or low   87 00:10:01,080 --> 00:10:08,040 vision individuals who rely on screen readers to  interact with their PDFs on a daily basis. Based   88 00:10:08,040 --> 00:10:13,520 on this survey, we found that at least two-thirds  of PDF documents are inaccessible to people with   89 00:10:13,520 --> 00:10:19,240 disabilities. So if you put yourself in the shoes  of a blind person, you can quickly imagine how   90 00:10:19,240 --> 00:10:24,600 frustrated you would be if you could not read  two-thirds of the documents that you came into   91 00:10:24,600 --> 00:10:31,920 contact with on a daily basis. On top of that,  imagine the potential privacy issues that there   92 00:10:31,920 --> 00:10:37,800 would be if you had to ask your neighbor or  your friend to help you read private documents   93 00:10:37,800 --> 00:10:44,960 like banking or investment statements, an  invoice, a pay stub, or insurance policy 94 00:10:44,960 --> 00:10:52,840 documents. So just to further emphasize  the points that I was making a couple of   95 00:10:52,840 --> 00:10:57,040 slides back, here is just some additional  information about the volume and types   96 00:10:57,040 --> 00:11:02,480 of lawsuits that organizations have faced  and will continue to face moving forward,   97 00:11:02,480 --> 00:11:08,080 and just to reiterate the digital accessibility  requirements that organizations must adhere to.   98 00:11:08,080 --> 00:11:12,960 They are not going away and there will continue  to be an increase in the attention that is paid   99 00:11:12,960 --> 00:11:18,920 to it by state and federal mandates, the  Department of Justice, disability advocacy   100 00:11:18,920 --> 00:11:23,640 groups, and individuals who simply want  to just be able to access their critical 101 00:11:23,640 --> 00:11:33,880 information. So one of the main challenges around  PDF accessibility is that PDF documents, each one   102 00:11:33,880 --> 00:11:41,600 of them, is unique. We have heard a lot of empty  promises over the years of fully automating PDF   103 00:11:41,600 --> 00:11:48,320 accessibility, but there are so many things about  PDFs that require human interpretation to decide   104 00:11:48,320 --> 00:11:55,160 how to tag specific elements within the content. I  have been working in the PDF accessibility market   105 00:11:55,160 --> 00:12:01,200 for over seven years and I have seen a lot of  organizations assume that they have accessible   106 00:12:01,200 --> 00:12:06,280 documents because their documents have some  tags in them. But they quickly learn that   107 00:12:06,280 --> 00:12:13,000 they are not usable, nor are they compliant,  and they are still open to litigation. So I   108 00:12:13,000 --> 00:12:19,400 always tell people to beware of quote unquote  auto tagging technology masked as a solution to   109 00:12:19,400 --> 00:12:24,800 fully automate PDF accessibility. These auto  taggers that are floating around out there,   110 00:12:24,800 --> 00:12:30,800 they're capable of putting tags on the page but  there will always be accuracy issues and the   111 00:12:30,800 --> 00:12:35,680 inaccuracy of these tags will lead to a lot of  confusion and frustration for the screen reader   112 00:12:35,680 --> 00:12:42,720 user. Additionally, auto taggers can and will  leave organizations open to further litigation   113 00:12:42,720 --> 00:12:48,120 because there is no guarantee of compliance with  WCAG standards. So even paying to outsource your   114 00:12:48,120 --> 00:12:54,160 huge batches of documents to auto taggers, you're  still not mitigating your risk of litigation   115 00:12:54,160 --> 00:13:00,360 because auto-tagging falls well short of true  compliance with accessibility standards. And then,   116 00:13:00,360 --> 00:13:04,560 of course, the alternative of outsourcing  the remediation work to third parties   117 00:13:04,560 --> 00:13:11,160 who are almost exclusively located overseas  introduces a mountain of data privacy issues,   118 00:13:11,160 --> 00:13:16,520 and even if you can work around that with your use  case, the sheer volume is impossible to keep up   119 00:13:16,520 --> 00:13:23,040 with. These outsourced remediation providers will  cut corners to do the bare minimum of work that   120 00:13:23,040 --> 00:13:27,520 they need to make a document pass an automated  checker, but they're not actually making the   121 00:13:27,520 --> 00:13:34,720 document compliant because it simply takes too  long to meet the deadlines at that type of volume.   122 00:13:34,720 --> 00:13:42,400 So incorporating artificial intelligence, more  specifically computer vision and machine learning,   123 00:13:42,400 --> 00:13:49,480 into high volume PDF remediation, this allows  our accessibility experts to train AI models to   124 00:13:49,480 --> 00:13:56,360 accurately identify and tag all of the elements in  the document template. The use of AI developed by   125 00:13:56,360 --> 00:14:02,800 our data scientists paired with the human element  of our trained accessibility experts allows for   126 00:14:02,800 --> 00:14:08,600 incredibly accurate usable and compliant PDFs to  be returned to the customer in a fraction of the   127 00:14:08,600 --> 00:14:15,920 time because AI works exponentially faster than  humans manually tagging each page. AI doesn't need   128 00:14:15,920 --> 00:14:23,640 to take vacations. AI can work 24/7/365 without  breaks, and AI doesn't need to cut corners to   129 00:14:23,640 --> 00:14:32,520 meet a deadline. It can just do it the right way.  So how does AI work? Our accessibility experts   130 00:14:32,520 --> 00:14:38,680 use example documents of customer templates  to properly identify the various elements on   131 00:14:38,680 --> 00:14:45,800 the page. These elements might include text and  paragraph structure, various levels of headings,   132 00:14:45,800 --> 00:14:51,320 lists and tables, graphs and images, and of  course, the very important reading order of the   133 00:14:51,320 --> 00:14:58,600 content. This training data that we accumulate  is then fed to the AI models to apply what it   134 00:14:58,600 --> 00:15:04,640 has learned en masse to many thousands or even  millions of pages that have similar templates and 135 00:15:04,640 --> 00:15:16,640 formatting. Although the mechanics of how AI  technology works is rather abstract and more   136 00:15:16,640 --> 00:15:21,480 complex than what I'm capable of showing  you here in a simple PowerPoint slide.   137 00:15:21,480 --> 00:15:27,520 But here are a few examples of how we can  visualize the AI at work. So for example,   138 00:15:27,520 --> 00:15:33,200 in this scatter plot each each of the green  dots represents a page in a PDF. They are   139 00:15:33,200 --> 00:15:39,360 grouped together by the AI based on similarities  that the computer vision finds. So this cluster   140 00:15:39,360 --> 00:15:45,760 will contain all of the pages that contain  pie charts, for example. In this example,   141 00:15:45,760 --> 00:15:50,360 you can see there are different multicolumn  text layouts that the AI will use to recognize   142 00:15:50,360 --> 00:15:54,320 different pages and group them together  appropriately so that it can apply the   143 00:15:54,320 --> 00:16:01,840 correct tag structure. The AI will pick up on font  styles, sizes, and colors to help it establish the   144 00:16:01,840 --> 00:16:11,000 tags on the page. We can even train AI models to  identify the many potential variations in tables,   145 00:16:11,000 --> 00:16:16,200 such as the numbers of columns and  rows, table headers versus table data,   146 00:16:16,200 --> 00:16:21,120 and even tables of different sizes that might  span across multiple pages. We'll talk a little   147 00:16:21,120 --> 00:16:28,360 bit about this when we get into the demo as well.  The results of this extensive document analysis   148 00:16:28,360 --> 00:16:34,760 and feeding the training data to the AI is we're  creating fully compliant PDF documents without   149 00:16:34,760 --> 00:16:40,600 any human remediators who are, again, expensive to  employ or outsource to, and they are, of course,   150 00:16:40,600 --> 00:16:46,880 liable to make human errors or be forced to cut  corners just to meet unattainable, unrealistic,   151 00:16:46,880 --> 00:16:53,120 deadlines due to the crazy volume demands. We are  also reaching full compliance because this is not   152 00:16:53,120 --> 00:16:59,720 auto-tagging, just sloppily throwing tags on a  page and saying that it's good enough. Beyond   153 00:16:59,720 --> 00:17:05,440 compliance and passing automated checkers, the  bonus of using AI for high volume and hyper-fast   154 00:17:05,440 --> 00:17:12,160 remediation is that it will produce incredibly  accurate and very much usable documents for people   155 00:17:12,160 --> 00:17:18,240 with disabilities. So your customers who rely on  you on assistive technology, they're not going   156 00:17:18,240 --> 00:17:24,680 to be filing complaints or lawsuits or calling  your headquarters to complain that their document   157 00:17:24,680 --> 00:17:28,920 that you've given them cannot be navigated  or understood because they're using a screen 158 00:17:28,920 --> 00:17:37,560 reader. So we are just about ready to jump into a  demo. I promise the slides will end soon so. But   159 00:17:37,560 --> 00:17:42,080 before we do I just want to make it clear that  the the underlying technology that we're talking   160 00:17:42,080 --> 00:17:49,520 about here, this can be deployed in several ways  to align with your organization's requirements. So   161 00:17:49,520 --> 00:17:54,240 first and foremost, what we're going to be seeing  during the demo is we've built an interface that   162 00:17:54,240 --> 00:17:59,080 allows us internally here, and potentially  you if it's the right type of use case,   163 00:17:59,080 --> 00:18:06,160 for this interface to run the process from start  to finish. So basically doing bulk uploads of   164 00:18:06,160 --> 00:18:12,360 documents, running the batch process, and then  downloading the finished PDF. We can also take   165 00:18:12,360 --> 00:18:18,000 the technology and use, and this is kind of like  what we ultimately envision for this technology,   166 00:18:18,000 --> 00:18:23,440 we can embed the AI models into an existing  document creation and delivery system through   167 00:18:23,440 --> 00:18:29,760 the use of APIs. So this would be probably  critical for customers needing to download their   168 00:18:29,760 --> 00:18:36,840 private documents like a monthly statement, or an  explanation of benefits, or medical test results,   169 00:18:36,840 --> 00:18:43,760 or investment portfolio type of reports and  status updates. Those types of documents that   170 00:18:43,760 --> 00:18:50,640 are produced en masse but contain private and  sensitive information. Lastly, Equidox can operate   171 00:18:50,640 --> 00:18:56,560 the entire process on your behalf as a managed  service. So we can take care of the remediation   172 00:18:56,560 --> 00:19:02,240 as well as the validation to ensure that  everything exceeds all accessibility requirements,   173 00:19:02,240 --> 00:19:07,480 and then we would deliver fully compliant, fully  compliant PDFs back to your organization to then   174 00:19:07,480 --> 00:19:12,160 be posted and distributed. So we'll talk a little  bit about that in one of the demonstrations as   175 00:19:12,160 --> 00:19:19,920 well. Just one more thing to note, Equidox  AI is tagging the PDFs at what we call the   176 00:19:19,920 --> 00:19:25,680 post-processing stage. So, and you'll see this  during the demonstration, and what I mean by that   177 00:19:25,680 --> 00:19:32,280 is these PDFs have already been created and we are  applying the accessibility as a final step before   178 00:19:32,280 --> 00:19:38,760 they are publicly distributed. The advantage of  of tagging PDFs post-processing is that we do   179 00:19:38,760 --> 00:19:44,840 not have to disrupt or completely rebuild your  document creation process, which is probably   180 00:19:44,840 --> 00:19:50,640 fully established and has been sort of vetted out  by your organization over a long period of time,   181 00:19:50,640 --> 00:19:56,120 and it wouldn't be ideal to have to completely  redo that from scratch. So your designers and   182 00:19:56,120 --> 00:20:01,720 your producers of mass documentation can continue  their process the way that they've been doing it,   183 00:20:01,720 --> 00:20:06,360 and we will handle the accessibility component  at the very end of the creation stage, but right   184 00:20:06,360 --> 00:20:13,400 before the document reaches your customer. Okay,  so what we'll do, we're going to jump into the   185 00:20:13,400 --> 00:20:18,840 demonstration and so I'm going to leave the slide  deck for just a minute and I'm going to switch   186 00:20:18,840 --> 00:20:24,120 over to our batch interface. So again, this is  an interface that we have built pretty much just   187 00:20:24,120 --> 00:20:29,080 for demonstrations to help people visualize like  what the technology is actually doing. But again,   188 00:20:29,080 --> 00:20:34,640 this technology can be deployed in a number of  ways to kind of align with your specific use case   189 00:20:34,640 --> 00:20:40,960 and any internal requirements like around security  or integration that your that your company or your   190 00:20:40,960 --> 00:20:46,480 organization would have. So what we'll do to get  started is I'm going to go to the upload documents   191 00:20:46,480 --> 00:20:51,480 tab here on the interface and then I'm just  going to open up the folders on my hard drive.   192 00:20:51,480 --> 00:20:58,040 What I'm going to do first is I'm going to grab  a batch of financial statements. So this is just   193 00:20:58,040 --> 00:21:03,800 a simple .zip folder that contains, I can't even  remember, 20 or 30 sample financial statements.   194 00:21:03,800 --> 00:21:08,720 So we're just going to use this for sort of a  small scale example. If I drag and drop that   195 00:21:08,720 --> 00:21:13,440 batch of documents into this, I can then press the  upload button. So I'm just going to give it a few   196 00:21:13,440 --> 00:21:18,720 seconds to upload and once it uploads, it's going  to be available to have the AI models be applied   197 00:21:18,720 --> 00:21:25,520 to those various documents. So if I now go to the  Create and Run Batch tab, I have a dropdown menu   198 00:21:25,520 --> 00:21:30,720 to select. I have some different models that are  kind of pre loaded here into my own little private   199 00:21:30,720 --> 00:21:36,400 demo account. So one of the models is called  “Example Statement” so we're going to use this   200 00:21:36,400 --> 00:21:42,640 model to apply to those documents. Now I just have  to select the .zip radio button, and I'm going to   201 00:21:42,640 --> 00:21:49,200 choose the financial statement .zip folder that  I just uploaded, and then I just press Run Batch.   202 00:21:49,200 --> 00:21:54,520 Now this is going to kick off an automated process  where Equidox is going to first unpack that .zip   203 00:21:54,520 --> 00:22:00,800 folder and it's going to identify all the various  elements within these different statements. Now   204 00:22:00,800 --> 00:22:06,280 these statements are all relatively similar  to each other but they can have quite a few   205 00:22:06,280 --> 00:22:11,440 variances. So just think about, like, what your  credit card bill might look like. You might have a   206 00:22:11,440 --> 00:22:16,360 credit card bill one month that has just a single  page because you only used it a couple of times,   207 00:22:16,360 --> 00:22:21,480 you only have a couple of charges. Then you  might have another month where maybe it's holiday   208 00:22:21,480 --> 00:22:26,920 shopping season and you have 200 charges on that  credit card over the course of the month, and then   209 00:22:26,920 --> 00:22:31,760 suddenly your bank statement or your credit card  bill is a lot different looking. It's got three,   210 00:22:31,760 --> 00:22:37,720 four, five pages breaking down every single one  of those charges, usually in a table format.   211 00:22:37,720 --> 00:22:42,640 So these are just some of the examples of like  where you can have differences even though the   212 00:22:42,640 --> 00:22:48,680 documents are similar and are coming from really  the same source. So while I was talking there you   213 00:22:48,680 --> 00:22:54,040 might have noticed these green lights just kind  of lighting up across the screen. Equidox, after   214 00:22:54,040 --> 00:22:59,920 it unpacks the .zip folder, it will start applying  the machine learning zones based on what it knows   215 00:22:59,920 --> 00:23:05,640 about this template. Once it finishes with the ML  zones, it's going to run this export process and   216 00:23:05,640 --> 00:23:10,200 we can see these green status bars again lighting  up. And then once the documents are finished,   217 00:23:10,200 --> 00:23:16,400 we get a Job Finish and a Job Success green light  and all of these documents are again available for   218 00:23:16,400 --> 00:23:23,480 download. I can also I see some basic information  up here, like how much time was elapsed for that   219 00:23:23,480 --> 00:23:29,280 process to run, how many documents ran, how many  total pages. We're not too concerned about that   220 00:23:29,280 --> 00:23:34,880 right now, but we're really just going to look at  kind of the resulting PDF. So if, before we get   221 00:23:34,880 --> 00:23:40,080 into the completed one, if I just like unzip this  for a second and let's just look at one of these   222 00:23:40,080 --> 00:23:46,440 documents that we started with. These documents  were completely untagged so there's no tag   223 00:23:46,440 --> 00:23:51,960 structure at all. This would be just a completely  useless page to someone who was blind. They would   224 00:23:51,960 --> 00:23:56,800 not be able to read any of this information. They  would not be able to understand their deposits and   225 00:23:56,800 --> 00:24:02,800 credits and withdrawals. All of this information  would be completely lost on them because this   226 00:24:02,800 --> 00:24:08,320 document is not tagged at all, or if it were  tagged it was probably not tagged properly.   227 00:24:08,320 --> 00:24:12,800 So what we do through that AI process is, if we  just take a look at one of these documents that   228 00:24:12,800 --> 00:24:22,000 came out of the batch, and I'll download this and  I will put this on my desktop just so we know it's   229 00:24:22,000 --> 00:24:30,480 the different one, and I'll open up my document  that I just created. Now this document here,   230 00:24:30,480 --> 00:24:35,960 if you can tell underneath the accessibility  tags tab, this is completely different. We   231 00:24:35,960 --> 00:24:41,120 have all of the elements accounted for on the  page. But not only are they accounted for, they   232 00:24:41,120 --> 00:24:46,880 are accounted for correctly. So we have your bank  name and your customer name information up here,   233 00:24:46,880 --> 00:24:52,760 we have a figure which would be, like, let's just  say the logo of the bank in this in this example   234 00:24:52,760 --> 00:24:57,680 that we're using. So we can navigate through all  of the different content. We have our heading   235 00:24:57,680 --> 00:25:03,080 structure, we have an H2, we have a table. The  table is properly tagged, and if you're not too   236 00:25:03,080 --> 00:25:08,960 familiar with what the tag structures look like in  accessible PDFs, this is kind of the whole point,   237 00:25:08,960 --> 00:25:14,840 that it is pretty complicated and it's very slow  and manual to set this up document by document.   238 00:25:14,840 --> 00:25:20,560 So the use of automation and AI dramatically  simplifies this process and it totally takes   239 00:25:20,560 --> 00:25:26,080 humans out of the equation. So because of that  training work that we did on templates like this,   240 00:25:26,080 --> 00:25:31,760 our AI is able to fully understand and recognize  the differences between these different elements   241 00:25:31,760 --> 00:25:38,640 and account for them in the tag tree in a fully  automated way. Another use case that I can quickly   242 00:25:38,640 --> 00:25:44,520 explain would be a document. It's going to be  a totally different document. Let's go here and   243 00:25:44,520 --> 00:25:51,840 I'll use this document. If I upload this one, this  document here, if we'll take a quick peek at it,   244 00:25:51,840 --> 00:25:55,320 this is a totally different use case. So  we were just looking at a bank statement,   245 00:25:55,320 --> 00:26:02,640 which is kind of applicable to invoices or a  pay stub or test results from on the healthcare   246 00:26:02,640 --> 00:26:06,600 side of things. There's a lot of different use  cases that would use things like statements,   247 00:26:06,600 --> 00:26:14,560 but this is an example here where we have what's  a a listing of a physicians directory. These are   248 00:26:14,560 --> 00:26:20,760 thousands of pages long and they go on and on  and on and they are consistently updated. So   249 00:26:20,760 --> 00:26:28,080 they're updated on a regular basis and that would  require the user to go back to the the document   250 00:26:28,080 --> 00:26:34,920 and re-remediate it month after month, or quarter  after quarter, or year after year. On top of that,   251 00:26:34,920 --> 00:26:41,360 those documents are also created in many different  languages, so depending on the market that that   252 00:26:41,360 --> 00:26:46,440 the the physician's directory is located in,  they're typically being produced in multiple   253 00:26:46,440 --> 00:26:52,600 languages. At least English and Spanish, sometimes  Chinese, sometimes Arabic, it just depends on the   254 00:26:52,600 --> 00:26:57,920 the region of the country. But those physician’s  directories, the volume of them is impossible to   255 00:26:57,920 --> 00:27:02,840 deal with, and they're actually quite complicated  documents. You have very complicated heading   256 00:27:02,840 --> 00:27:11,720 structures throughout, you need to of course  make pages like this, and there's all kinds of   257 00:27:11,720 --> 00:27:16,000 different things that span across multiple pages  that needs to be accounted for. There's just   258 00:27:16,000 --> 00:27:21,600 simply no way for humans to be able to remediate  these at the volume of literally thousands and   259 00:27:21,600 --> 00:27:27,080 thousands of pages that are constantly being  updated on a monthly basis. So this is a use   260 00:27:27,080 --> 00:27:33,120 case that we're currently solving for. We have  customers that are dealing with, like I said,   261 00:27:33,840 --> 00:27:39,520 literally millions of pages just like that across  their across their different networks. And so we   262 00:27:39,520 --> 00:27:44,920 have to, we're accounting for that through the  use of AI because they're dissatisfied with the   263 00:27:44,920 --> 00:27:50,880 results they were seeing from both auto-taggers as  well as outsourced human remediators. The accuracy   264 00:27:50,880 --> 00:27:56,200 was terrible, the speed was too slow, and it  simply just wasn't good enough for what they   265 00:27:56,200 --> 00:28:02,440 needed. So we're letting the machine learning kind  of do its thing here. This is a long document and   266 00:28:02,440 --> 00:28:07,840 there's a lot of tags for it to kind of interpret  and apply. But what we'll see when we export the   267 00:28:07,840 --> 00:28:14,160 document is very similar to what we saw when we  exported the bank statement. We are going to have   268 00:28:14,160 --> 00:28:19,200 accurate tags where it's properly accounting  for the reading order, properly accounting for   269 00:28:19,200 --> 00:28:25,120 the heading structure, all of the different text  elements are going to be identified. My little   270 00:28:25,120 --> 00:28:29,760 private environment seems to be a little  bit sluggish today but we'll get there. 271 00:28:42,120 --> 00:28:45,360 Once it gets into the export  it should go rather quickly. 272 00:28:55,120 --> 00:29:01,200 Okay, so with that said, just in the interest  of time I realized that we're at 2:30 and   273 00:29:01,200 --> 00:29:05,880 people might have to be dropping off. So while  while we're waiting for that, oh, there we go.   274 00:29:05,880 --> 00:29:10,640 Perfect timing. It just finished. So if I open up  this document now, and again I'll open it up in   275 00:29:10,640 --> 00:29:15,160 Adobe Acrobat, we remember that the original was  not tagged at all. But I just wanted to show you   276 00:29:15,160 --> 00:29:20,600 that this one is properly tagged. So when you open  up the tag structure you can see that all of these   277 00:29:20,600 --> 00:29:25,320 different elements are accounted for and they're  accounted for an accurate way, which is critical   278 00:29:25,320 --> 00:29:30,840 because this is an extremely difficult document  to use if you're blind and these elements are   279 00:29:30,840 --> 00:29:35,280 not tagged correctly. Just imagine if it reads  left to right across the three columns you would   280 00:29:35,280 --> 00:29:40,320 have no idea what any of these doctors are, where  they're located, would be impossible to use this.   281 00:29:40,320 --> 00:29:45,320 So that's what Equidox solves for. Now with that  said, I'm going to jump out of the demonstration   282 00:29:45,320 --> 00:29:50,440 and we'll go back into the slide deck just to wrap  things up. We do have some articles that will be   283 00:29:50,440 --> 00:29:54,560 listed in the slide deck, so when we share the  slide deck out if you'd like to learn a little   284 00:29:54,560 --> 00:29:59,840 bit more about PDF accessibility please feel free  to browse through them or visit our website. And   285 00:29:59,840 --> 00:30:05,080 just in conclusion, I just want to say thank you  to everyone for joining us here today. So we hope   286 00:30:05,080 --> 00:30:09,920 you see the value and the capabilities of the new  technology. Please do not hesitate to reach out to   287 00:30:09,920 --> 00:30:16,200 one of us for more of a one-on-one consultation so  that we can discuss your organization's unique use   288 00:30:16,200 --> 00:30:23,720 cases and how Equidox AI can be applied to them.  And again we will be sending out the recording   289 00:30:23,720 --> 00:30:28,560 of this webinar so please feel free to share  this with anyone in your organization. We will   290 00:30:28,560 --> 00:30:33,320 include a link to the slide deck and for anyone  who asked a question during the Q&A feature,   291 00:30:33,320 --> 00:30:37,680 we will get back to you as soon as possible.  And again there will be a short survey so if   292 00:30:37,680 --> 00:30:41,720 you don't mind just taking a moment to fill that  out we would greatly appreciate it. So thank you   293 00:30:41,720 --> 00:30:47,280 again everyone for joining and have a great  rest of your day. For more information about   294 00:30:47,280 --> 00:30:55,040 how Equidox Software Company can help you with PDF  accessibility, email us at EquidoxSales@equidox.co   295 00:30:55,040 --> 00:31:03,840 or give us a call at 216-529-3030 or  visit our website at www.Equidox.co.