Looking for consultant to analyze large 17,000 page pdf file

[CREG_HB]

To whom it may concern:

We are looking for a solution to analyze the contents of an Adobe PDF file that is part of a discovery that contains 17,155 pages with a wide range of documents.  We would like a solution that does the following:

1.            It should look for payments to anyone, on behalf or or to settle the bill of anyone and organize by payee and payor, providing date, amount, and reason for payment;
2.            It should identify the page numbers HMS..." and also page # in the PDF;
3.            There should be a number of lists, e.g., by document page #, by date, by any o the classifications set out in this email or discovered by AI.
4.            There are headings, see e.g. document page #s 1. 17, 70, 115, 443, 1658, etc. It should provide a table of contents by headings.
5.            If there are documents with a title, they should be identified and the page range provided.
6.            If there are communications, it should identify by sender, recipient, date, topic.
7.            Documents should be identified by type, such as check, email.
8.            If a document is attached to another document, it should be identified as an attachment and should follow the document.
9.            If it is a billing, identify date, from, to, amount . account #, and what was billed for.
10.         It should be in a format that we can have a column for costs and payments to Steve Keh or others and then I can go in and spread the costs, billings, income etc. Or the program should be able to do it.
11.         Checks should identify by account name, account #, date, and amount, whether or not voided.
12.         If there are summaries or schedules with lists of billings, payments etc. they should be identified. See e.g. p. Document page #s 45 - 69; 633, 780 - 783;
13.         Separate out all documents dealing with (criteria to be provided)
14.         All documents relating to any important individual such as (names to be provided as well as all the attys and advisors).
15.         It should know that (address to be provided) is Havasu Springs and classify those docs as Havasu Springs.
16.         Separate out any document with a dollar amount over $100,000.

The file in question can be sent to you for review to see if you’re able to provide a solution.  The file should be considered confidential and when it is no longer needed, all copies in your possession should be destroyed.  It should not be distributed to any person who is not involved in the determination if your firm can provide a solution.

Bruce 

brucek@capitalregroup.com

[try67]

I'm happy to take a look... I will send you an email.