Decipher

 View Only
last person joined: 2 days ago 

A community for Blue Prism Decipher users.

  • 1.  Handling unstructured data - Decipher 1.2

    Posted 09-16-2021 05:17

    Here with I have attached  image(source data) , image2 as

    expected result is as shown in table

    I have colored the values in the image  with same colors of below table , for better understanding.

    I have trained  around 30 + docs and results are not satisfactory.

    1. The columns L1,L2 L3 comes exactly across even for multiple pages
    2. But L5and L6 lines are not coming properly almost for all lines
    3. The data in the image, you can observe that it is more unstructured data ,
    4. Coz L5 and L6 column values present in the image in different rows
    5. I have added key words which present for L5 and L6 values in the image still result is not good.

    My Questions

    1. Can I enable NLPN to manage this kid of unstructured data
    2. As it  use Graphic card , is any performance related will arise.
    3. Or you suggest any other method to achieve  good result

     



    ------------------------------
    Krishna Elapavuluri RPA Solution Lead
    TEchnology Consultant
    DXC.technology
    Asia/Kolkata
    ------------------------------


  • 2.  RE: Handling unstructured data - Decipher 1.2

    Posted 09-16-2021 08:27
    Hi Krishna,

    1. NLP is not intended for structured or semi-structured documents, and while I appreciate this may seem "unstructured" it would fall in one of the first 2 categories. This is because the information is laid out in a consistent structure and not unstructured like a contract or agreement.
    2. The GPU requirement is to speed up the processing as the NLP model uses a neural network and a regular CPU would take far too long to process the data.
    3. Without anchors (e.g. sample headers) near the respective data, it will be very difficult to train consistently. Your best bet is to try using Format Expressions (Regex) for each of the fields. Sometimes you may need to gather more data than needed and format it later in Blue Prism. e.g. get the number 10 and KPL, then remove KPL later.

    Thanks

    ------------------------------
    Ben Lyons
    Product Consultant
    Blue Prism
    UK
    ------------------------------



  • 3.  RE: Handling unstructured data - Decipher 1.2

    Posted 09-16-2021 13:46
    Hi Ben ,
    as you said in #3 , I am doing lot of enrichment in BP process. But here problem is the expected value  position line is keep changing  (mean​ that it present 4 or 6 ot 9 row of specific order line) .
    This is causing for Decipher to get wrong value as it  remember last trained row position . to pore precise
    Assume I trained D1 and picked the data from 4th (sample header as VALMISTAJAN TUOTENUMERO) row of an order line (say for 30 line).
    for next order D2 assume same header present in 6th row  , it won't read 6th row data  still it read 4th line data
    Hope i explained clearly  :)


    ------------------------------
    Krishna Elapavuluri RPA Solution Lead
    TEchnology Consultant
    DXC.technology
    Asia/Kolkata
    ------------------------------



  • 4.  RE: Handling unstructured data - Decipher 1.2

    Posted 09-17-2021 09:52
    Hi Krishna,

    You might be better off reading the entire section of text, then using formulas/functions in Blue Prism to extract the specific data.

    Regards

    ------------------------------
    Ben Lyons
    Product Consultant
    Blue Prism
    UK
    ------------------------------



Welcome to the Blue Prism Decipher Community

Blue Prism Decipher IDP is Intelligent Document Processing for Blue Prism RPA. This is a community for Decipher users to get support and discuss the implementation and usage of product.

This community has been set up so that we continue to work closely with our Decipher users, both new and established. As our members join, we will be using this community to share information, and also hope this will allow all members to discuss ideas and issues around Decipher.

Decipher IDP Resources

Download DecipherProduct HelpBrochureOne-Sheet

FAQs

Decipher IDP is a Blue Prism product for Intelligent Document Processing. It allows organizations to easily extract, analyse and understand data from a range of documents whether these are PDFs, email attachements, or even scanned paperwork.
Decipher IDP is currently available without additional cost to Blue Prism customers with Production or Business-Critical support.
Please contact your Blue Prism Account Manager or Customer Success Director for information on accessing Decipher. They will be able to request a license key which is required to be able to install Decipher IDP.
Yes, a trial version is available for Blue Prism customers. Please contact your Blue Prism Account Manager or Customer Success Director for information on accessing Decipher. We are planning to offer a trial version available for download from our DX later this year.
All documentation for Decipher IDP is available online on BP DOCS.
An extended FAQ can be found here.
Decipher IDP is currently available for Blue Prism Enterprise customer for on-premise installation.