Managing shared inboxes, like support@yourcompany.com, or inquiries@yourdepartment.com, can be errorprone and time consuming: a group of persons are scanning incoming emails from the inbox, and forwarding them to their email inbox before they reply to the customer, colleague, or other external stakeholder. This approach requires that the persons regularily go through all emails in the shared inbox, read and understand if they should reply to an specific email.
You can improve this process if you teach the Easy Tagging App to assign emails to a set of classes, like: job applications, inquiries, issues, invocies etc. In a second step, the App scans a shared inbox periodically for new emails, classifies them and forwards them to the recipient who is assigned to a class. This allows you to automate the process and each email is directed to a responsible person in a timely manner.
The following steps assume that you have Sharepoint Online/Office 365 and a shared inbox that contains a couple of emails. Further you should be able to assign each email to a specific set of classes, like invoices, job applications etc. After you have completed these steps, your shared inbox will be scanned periodically for new emails, which will be analysed, categorized and forwarded to the recipient who is associated to the class.
Watch the steps in the video:
Step 1: Prepare a library of example emails
1. Create a termset for your classes of emails
- Open the termstore manager (from the site settings)
- Create a new termset, named "email categories"
- Create a term for each email class that is kept in your shared inbox, like: e.g. inquiry, invoice, sales order, resume
2. Create a document library that will contain the emails used for the teach-in
- Open the site contents of your site
- Add a library, e.g. "Examples for emails"
3. Create a column for your emails library that contains the class of each example email
- Open the document library
- Open the library advanced settings
- Click on "create column"
- Enter the name of the new library column, e.g. "email category"
- Select "managed metadata" as type
- In the term set settings: select the termset "email categories" (from the step above)
- Click on "Save" to close the form
4. Copy example emails from the shared inbox to the library
- Open the shared inbox in a Outlook client and copy the emails into the library (you will receive better classification results with more examples).
- Tag each example by assigning a term to it.
- As soon as you have provided each example email with a tag, you can initiate the training.
Step 2: Teach-in the Easy Tagging App
1. Install the Easy Tagging App from the App Source (free evaluation!)
- Open the site settings and click on "Add an App"
- Click on "Sharepoint Store"
- In the Sharepoint Store: enter "diqa" as search term
- Click on the "Easy Tagging" card to initiate the installation.
- Direct link to the Microsoft App Store:
▶ Got to Microsoft AppSource
2. Launch the app and grant it the requested permissions
- Open the site contents again where you should find the newly installed Easy Tagging App
- Click on the App and grant it the requested permissions.
- The configuration page of the app opens in a new tab.
3. Connect the Easy Tagging App with the IDAS service (1/2)
- In the configuration page of the Easy Tagging App: click on the "Predictors & Taggers" tab
- Click on the link "Click here to connect to IDAS"
4. Connect the Easy Tagging App with the IDAS service (2/2)
- In the connection dialog: select the "IDAS Evaluation Service" tab
- Click on "I accept the terms of use" tick box
- If the service status says "IDAS evaluation service is available", then click on the "connect" button. If the status says something different: click on "refresh status".
- The dialog closes and you can setup a predictor.
5. Launch the "Learning Wizard" in your library
- 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.
- Return to your library and open the "Library Settings" ribbon.
- Click on the "Learning Wizard" icon which launches the wizard in a dialog.
- Go through the three steps:
- Click on "Click to start the wizard"
- 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.
- 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
- 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.
- Step 3: select the column which will receive the document type tags: just keep the selection.
- Step 3: click on the link "Start Learning and Tagging".
- The learning and tagging processes are running in the background.
- You can inspect the progress in the library ribbon "Predictors + Taggers"
Step 3: Create an "Email Dispatcher Task" and process the shared inbox automatically
1. Create an Email Dispatcher task
- Open the Easy Tagging App default page, activate the "predictors and taggers"-tab.
- Create a Mail Dispatcher task which uses the Predictor to classify new emails in your shared inbox.
- Associate each classification term with a recipient mail address.
- You can set a schedule which launches the Dispatcher regularily, for example each hour or once a day.
- You can launch the dispatcher at any time manually by clicking on "start".
2. Launch the Mail Dispatcher task manually
- Click on the "START" action link to launch the Mail Dispatcher task.
- The dispatcher scans the shared inbox for new emails, performs an analysis and a classification, and forwards each email to the recipient associated with a class.
- After a dispatcher run you can inspect the dispatcher log.
What's next?
- Create predictors that process your document libraries automatically, e.g.:
- The Easy Tagging App has a built-in predictor that detects the language that is used in documents. You can simply use that predictor in a tagger to tag all your documents with the language. Similar to the steps in section 3 you would simply create another refiner that allows users to restrict their search results to certain languages.
- The Easy Tagging App is able to identify important words from documents and store them in the termstore as a new termset. If you let the tagger tag your documents with them, then your users can use them to filter their search results.
Questions?