These are the set of core building blocks that are shared throughout Impira.
A record holds all the information of a particular file. In the table view, each record gets a row to itself. There are four records in the image below.
A field is a piece of information that each record contains. Each field has a certain type (e.g., text, number) and that type is consistent for every record in a Collection. In the table view, each field gets a column to itself. The fields in the image below are, “Total Amt,” “Due date,” and “Customer name.”
The value is the piece of data that corresponds to a field. In the table view, each value sits within a cell. In the image below, the value for the “Due date” field in the “Demo4.pdf” record is
Wed Aug 28 2019.
Impira makes it easy to organize your files and data. There are several different organizational tools within Impira.
A Collection (i.e., a standard or manual Collection) is a feature unique to Impira. It's a folder that contains a group of files that have similar layouts and share the same schema (a set of fields you want to extract — e.g., Name, Date, Balance, etc).
However, while standard folders simply hold and organize files, Collections have a brain (i.e., a machine learning model) to actively learn how to extract data from those files. Creating a Collection is the first step before moving on to extract data from your files. Read more.
Instant Collections are useful for extracting data from common document types (e.g., 1040, ACORD 25, loss run reports, and more).
While a standard Collection is a blank canvas you customize yourself by adding your own fields and training, an Instant Collection already has fields and training built in for you.
Instant Collections are still just as flexible and customizable as a standard Collection — they just help you get going faster. Read more.
Smart Collections allow you to automatically filter new files into a group of similar files, just like you can with email filters. With Smart Collections, newly uploaded files will automatically be routed to a Collection that has been set up and trained to extract the fields you want. Read more.
Datasets are like normal databases (e.g., a spreadsheet, CSV, Airtable, etc) that you can use alongside data that you’ve extracted in Impira. Use them to reconcile, connect, and unlock data stored in outside locations to your data in Impira.
It holds a group of records where each record does not necessarily correspond to a specific file. Datasets commonly contain metadata and can be created from the contents of a spreadsheet (via CSV import) or from scratch. Read more.
A View is a page that can be created to save and manage an IQL query that needs to be used frequently. Instead of managing a series of bookmarks containing long URLs for each IQL query, you can create a View that will appear on the left hand navigation bar, allowing for easy access. Read more.
Types of fields
The ability to extract structured data from records is a core action within Impira. Machine learning fields help you automate the extraction of that information. There are several different types of machine learning fields within Impira in addition to manual fields.
Single value field
The single value field type can extract data of any length. However, this field will only return at most one value per file. If Impira isn't confident that a matching prediction is present in a file, it'll return a blank value.
A single value field can be text, number, or dates.
This type is for extracting a binary True or False value. This model works for checkboxes, radio buttons, and other marks of true or false.
This field type is for extracting data from tables, as well as repeating value, lists, and matrices that appear across multiple documents. Read more.
Types of values
An individual instance of a field is called a value. For example, a column in a spreadsheet is a field — the header is the field name and all the cells below it contain various values of that field.
Text: Text of any type and length, including letters, numbers, and symbols. This is the most flexible type but doesn't give Impira a lot of specific information.
Number: Numbers and related symbols, like “-” and currency. Choosing this will tell Impira to ignore blocks of text for these values.
Date: Single dates that contain a Day, Month, and Year in formats that are less likely to be misinterpreted, like “Jan. 1, 2022” or “2022-01-01” (if this last type causes errors, you'll have to manually enter the date in a less ambiguous way).
Checkbox: A binary true or false value. Includes radiobuttons and other yes/no indicators.
Manual field value: Values that you yourself enter in as a note or detail about a particlar file or line item. Read more.
Join: A field that links a file to files in another Collection or dataset. Read more.
Custom field value: The saved result of an IQL function for each record. Read more.
Machine learning confidence states
For machine learning fields, in addition to generating the most accurate predictions, Impira uses black, green, and red markers to communicate an estimate of certainty around those predictions.
Manual confidence: A black marker indicates a value that you've manually extracted or confirmed yourself. This indicates 100% confidence.
High confidence: A green marker indicates that Impira is highly confident in this particular prediction.
Review recommended: A red flag indicates that Impira recommends you review this prediction and either confirm or correct it. (Also called "medium confidence.")
Blank prediction: If the machine learning model is not able to identify the value in the record, the cell will be blank and either have the "high confidence" or "review recommended" indicator. Not all blank predictions are inherently incorrect, and some files may simply not contain the value in question.