Normalization Stay organized with collections Save and categorize content based on your preferences.
For many specific supported fields, Document AI also returns anentity.normalizedValuein addition to the raw extracted field obtained through thetextAnchor of eachentity. It normalize the literal text. Normalization often breaks the text valueup into sub-fields.
This contain the data in a standardized format to reduce post processing, andenable conversion to whatever format is selected. ThementionText, representingwhat is literally on the document, is never changed by normalization.
Normalized fields belong to one of the following categories.
Normalized values in the console
In the Google Cloud console, the normalized fields are annotated withG. For example:
Sample normalized field shown in the web application.
Supported processors
Here are the processors and fields that support entity enrichment and normalization:
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2026-02-19 UTC."],[],[]]
