Difference between revisions of "Blog/Boost document findability with tags in O365"

From DIQA-Homepage
Line 131: Line 131:
 
<div class="row funktionen-row">
 
<div class="row funktionen-row">
 
<!-- --><div class="col-md-6 col-md-border funktionen" style="text-align: justify; ">
 
<!-- --><div class="col-md-6 col-md-border funktionen" style="text-align: justify; ">
=== 5. Create a "Learn Tags" perdictor and let it learn from your examples ===
+
=== 5. Launch the "Learning Wizard" in your library ===
# After you have created a connection to the IDAS Evaluation service you can setup a predictor which learns to tag documents from your examples.
+
# After you have created a connection to the IDAS Evaluation service you can launch the "Learning Wizard" which will guide you through the process to learn from your examples and to tag your documents.
# In the (now empty) list of predictors click on the link: "Click to create new item".
+
# Return to your library and open the "Library Settings" ribbon.
# In the selection dialog, select the "Learn Tags" predictor.
+
# Click on the "Learning Wizard" icon which launches the wizard in a dialog.
# The configuration form for the new "Learn Tags" predictor opens.
+
# Go through the three steps:
# Enter the name of the predictor, e.g. "Document types"
+
## Click on "Click to start the wizard"
# In the field "Learn from documents in this library": select the library that contains your documents.
+
## Step 1: select the language that is used in most of the documents of the library. If you documents in other languages: just select english.
# In the field "Encode with": select the entry "Glove English subset 100k words".
+
## Step 1: in the field "Learn to predict tags from this managed metadata column": select the "document types" column that you created in the earlier steps
# In the field "Learn to predict tags from this managed metadata column": select the "document types" column that you created in the earlier steps
+
## Step 2: your library is analysed for sufficient examples. If you don't have enough examples: please add further examples before you continue with the wizard.
# In the field "model": select "Simple CNN model"
+
## Step 3: select the column which will receive the document type tags: just keep the selection.
# Keep the default values of the subsequent fields.
+
## Step 3: click on the link "Start Learning and Tagging".
# Click on "Start training" to initiate the training process.
+
# The learning and tagging processes are running in the background.
# You can inspect the progress of the training process in the status bar of the predictor.
+
# You can inspect the progress in the library ribbon "Predictors + Taggers"
<!-- --></div>
 
<!-- --><div class="col-md-6 col-md-border funktionen imageExpand" style="text-align: justify; >[[File:Create_perdictor2.jpeg|center|middle]]</div>
 
</div>
 
 
<div class="row funktionen-row">
 
<div class="row funktionen-row">
 
<!-- --><div class="col-md-6 col-md-border funktionen" style="text-align: justify; ">
 
<!-- --><div class="col-md-6 col-md-border funktionen" style="text-align: justify; ">
=== 6. Create a tagger that automatically creates tags for all documents (and future documents) ===
+
=== 6. Important: re-index your document library ===
# As soon as the training of the predictor has completed, you can enable the predictor by clicking on the "enable" action link
 
# Click on "OK" in the prompt that asks you if you want to create a tagger.
 
# The "Create a tagger" form opens.
 
# You can keep all default settings in the form.
 
# Tick off the "Tagging Schedule" box if you don't want to have this tagger to automatically process new documents per a schedule.
 
# Click on "Store changes" to create the new tagger.
 
<!-- --></div>
 
<!-- --><div class="col-md-6 col-md-border funktionen imageExpand" style="text-align: justify; >[[File:Create_tagger.JPG|center|middle]]</div>
 
</div>
 
<div class="row funktionen-row">
 
<!-- --><div class="col-md-6 col-md-border funktionen" style="text-align: justify; ">
 
=== 7. Automatically tag all documents that have no tag yet ===
 
# In the list of taggers: click on the "START" action link to initiate the tagging process of all documents.
 
# Before the tagger is launched, a dialog opens: select the option "include documents that have not been modified or created since the last tagger run". This will make sure that your existing documents that have no tags yet, will be tagged now.
 
# Click on "Start tagging now"
 
# After the tagging has completed you can inspect the tagging log of the tagger (action link "open the tagging log")
 
<!-- --></div>
 
<!-- --><div class="col-md-6 col-md-border funktionen imageExpand" style="text-align: justify; >[[File:Start_tagging_2.JPG|center|middle]]</div>
 
</div>
 
<div class="row funktionen-row">
 
<!-- --><div class="col-md-6 col-md-border funktionen" style="text-align: justify; ">
 
=== 8. Important: re-index your document library ===
 
 
# Opent the settings of your library
 
# Opent the settings of your library
 
# Click on "re-index document library"
 
# Click on "re-index document library"

Revision as of 14:03, 4 November 2020

Main Page > Der DIQA Blog > Blog/Boost document findability with tags in O365
Blog

O365: Boost document findability with autotagging (September 1, 2020)


Finding documents in Sharepoint online/Office 365 can be tedious. If you want to restrict your search to certain document types (like: reports, inquiries, CVs, sales orders, invoices) you either end up with too many irrelevant search hits or relevant documents don't show up because they don't include the search term. If you rely on Sharepoint's fulltext search capabilities only, then your users will be frustrated and spend too much time to find the right documents.

You can provide your users with a better search experience if you use search refiners. Users can further refine their search result by clicking on the refiner values, e.g. to retrieve "sales orders" or "invoices", only. Before you are able to create meaningful search refiners, you have to arrange for a couple of pre-requisites which include tagging documents with tags. This guide shows you how to automatically tag documents with their type (e.g. invoice, sales order, cv, inquiry) and how to provide search refiners that contain these document types.

Frustrating search experience without meaningful refiners:

Tagcloud

Entering the search term "order" returns a lot of irrelevant documents (e.g. a CV) and even misses some sales order documents.

Better: filter documents by type, language, etc:

Tagcloud

If you provide search refiners, then the users will be able to precicely filter for all "sales order" documents, for instance.

The following steps assume that you have Sharepoint Online/Office 365 and a library that contains at least dozens of documents or scanned documents (pdf or image formats). If you are familiar with certain configuration aspects of Sharepoint then you will need 30 minutes to go them through in your tenant. If you require assistance then we are happy to help!