Organizations that deal with digital assets increasingly use taxonomy-controlled vocabulary in asset metadata. Essentially, it includes a list of keywords that employees, partners, and customers commonly use to refer to and search for digital assets of a particular class. Tagging assets with taxonomy-controlled vocabulary ensures that they can be easily identified and retrieved by tag-based searches.
Compared to natural language vocabularies, tagging digital assets based on business taxonomy helps align them with a company’s business and ensures that the most relevant assets appear in searches.
For example, a car manufacturer can tag car images with model names so only relevant images appear when images of various models are searched to design a promotion campaign.
For the Smart Content Service to apply the right tags, you must train it to recognize your taxonomy. To train the service, first curate a set of assets and tags that best describe these assets. Apply these tags on the assets and run a training workflow to help the service learn.
Once a tag is trained and ready, the service can now apply these tags on assets through a tagging workflow.
In the background, the Smart Content Service uses the AI framework of Adobe Sensei to train its image recognition algorithm on your tag structure and business taxonomy. This content intelligence is then used to apply relevant tags on a different set of assets.
Smart Content Service is a cloud service that is hosted on Adobe I/O. To use it in Adobe Experience Manager (AEM), the system administrator must integrate your AEM instance with Adobe I/O.
In summary, here are the main steps to use the Smart Content Service:
Before you can use the Smart Content Service, ensure the following to create an integration on Adobe I/O:
The Smart Content Service is available for purchase as an add-on to AEM. After you purchase, an email is sent to the administrator of your organization with a link to Adobe I/O.
The administrator can follow the link to integrate the Smart Content Service with AEM. To integrate the service with AEM Assets, see Configure Smart Tags.
The onboarding process is complete when the administrator configures the service and adds users in AEM.
If you are using AEM 6.3 or earlier version and require automatic tagging service for your assets, see Smart Tags. Smart Tags do not use the AI capabilities and are less accurate than the Enhanced Smart Tagging capability.
After you are onboarded, the first thing you want to do is identify a set of tags that best describe these images in the context of your business.
Next, review images to identify a set of images that best represent your product for a particular business requirement. Ensure that the assets in your curated set conform to Smart Content Service training guidelines.
Add the assets to a folder and apply the tags to each asset from the properties page. Then, run the training workflow on this folder. The curated set of assets enables the Smart Content Service to effectively train more assets using your taxonomy definitions.
For the Smart Content Service to recognize your business taxonomy, run it on a set of assets that already include tags that are relevant to your business. After training, the service can apply the same taxonomy on a similar set of assets.
You can train the service multiple times to improve its ability to apply relevant tags. After each training cycle, run a tagging workflow and check whether your assets are tagged appropriately.
You can train the Smart Content Service periodically or on requirement basis.
The training workflow runs on folders only.
You can enable the Smart Content Service to train periodically on the assets and associated tags within a folder. Open the properties page of your asset folder, select Enable Smart Tags under the Details tab, and save the changes.
Once this option is selected for a folder, AEM runs a training workflow automatically to train the Smart Content Service on the folder assets and their tags. By default, the training workflow runs on a weekly basis at 12:30 AM on Saturdays.
You can train the Smart Content Service whenever required from the Workflow console.
Tap/click the AEM logo, and go to Tools > Workflow > Models.
From the Workflow Models page, select the Smart Tags Training workflow and then tap/click Start Workflow from the toolbar.
In the Run Workflow dialog, browse to the payload folder that includes the tagged assets for training the service.
Specify a title for the workflow and a add a comment. Then, tap/click Run. The assets and tags are submitted for training.
Once the assets in a folder are processed for training, only the modified assets are processed in subsequent training cycles.
To check whether the Smart Content Service is trained on your tags in the training set of assets, review the training workflow report from the Reports console.
Tap/click the AEM logo, and go to Tools > Assets > Reports.
In the Asset Reports page, tap/click Create.
Select the Smart Tags Training report, and then tap/click Next from the toolbar.
Specify a title and description for the report. Under Schedule Report, leave the Now option selected. If you want to schedule the report for later, select Later and specify a date and time. Then, tap/click Create from the toolbar.
In the Asset Reports page, select the report you generated. To view the report, tap/click the View icon from the toolbar.
Review the details of the report.
The report displays the training status for the tags you trained. The green color in the Training Status column indicates that the Smart Content Service is trained for the tag. Yellow color indicates that the service is not completely trained for a particular tag. In this case, add more images with the particular tag and run the training workflow to train the service completely on the tag.
If you do not see your tags in this report, run the training workflow again for these tags.
To download the report, select it from the list, and tap/click the Download icon from the toolbar. The report downloads as an Excel file.
After you have trained the Smart Content Service, you can trigger the tagging workflow to automatically apply appropriate tags on a different set of similar assets.
You can run the tagging workflow periodically or whenever required.
The tagging workflow runs on both assets and folders.
You can enable the Smart Content Service to periodically tag assets within a folder. Open the properties page of your asset folder, select Enable Smart Tags under the Details tab, and save the changes.
Once this option is selected for a folder, the Smart Content Service automatically tags the assets within the folder. By default, the tagging workflow runs every day at 12:00 AM.
You can trigger the tagging workflow from the following to instantly tag your assets:
If you run the tagging workflow from the timeline, you can apply tags on a maximum of 15 assets at a time.
Tap/click the AEM logo, and go to Tools > Workflow > Models.
From the Workflow Models page, select the DAM Smart Tags Assets workflow and then tap/click Start Workflow from the toolbar.
In the Run Workflow dialog, browse to the payload folder containing assets on which you want to apply your tags automatically.
Specify a title for the workflow and an optional comment. Then, tap/click Run.
Navigate to the asset folder and review the tags to verify whether the Smart Content Service tagged your assets properly. For details, see Managing Smart Tags.
From the Assets user interface, select the folder containing assets or specific assets to which you want to apply smart tags.
Tap/click the GlobalNav icon and open the timeline.
Tap/click the arrow at the bottom, and then tap/click Start Workflow.
Select the DAM Smart Tag Assets workflow, and specify a title for the workflow.
Tap/click Start. The workflow applies your tags on assets. Navigate to the asset folder and review the tags to verify whether the Smart Content Service tagged your assets properly. For details, see Managing Smart Tags.
In the subsequent tagging cycles, only the modified assets are tagged again with newly-trained tags.
However, even unaltered assets are tagged if the gap between the last and current tagging cycles for the tagging workflow exceeds 24 hours.
For periodic tagging workflows, unaltered assets are tagged when the gap exceeds 6 months.