This feature is a part of the Symbl Labs. Symbl Labs is our experimental wing designed to share our bleeding edge AI research on human conversations with anyone who wants to explore its limits.
You can access the Labs features using your Symbl App Id and Secret. If you don't already have it, sign up on platform to get your credentials.
Note: The usage of data for Labs projects is stored for enhancing our research. We may continue to build, iterate, mutate or discontinue any of the below given features on the sole discretion of our team as deemed necessary.
For any queries or feedback, please contact us at firstname.lastname@example.org.
Personally Identifiable Information (PII) is any information about an individual that can be used to distinguish or trace the individual's identity, such as name, social security number, email address, phone number, etc.
Although, sensitive, they can appear in conversations such as account verification by customer care agents that requires the customer to share their name, email address or other confidential information.
Symbl provides the capability to identify and redact PII data from conversations and insights it processes. Redaction of PII is a process of concealing confidential information in messages and insights.
This feature will allow you to:
- Identify any PII such as Social Security Number, Phone Number, etc. from messages and insights. See the complete list of supported PII entities here.
- Redact PII in the messages and transcripts with a default masking redaction indicator "****".
- Mask with custom string instead of the default redaction indicator.
A list of supported PII data that Symbl can identify and redact are given in Supported PII Entities section.
Currently, the PII identification and redaction is only supported for English for the Streaming API.
To enable PII support for messages objects, provide additional payload in the request body for Streaming API.
For WebSocket request using Streaming API, add the
redaction object in the
start_request message to begin
the real-time PII identification and redaction while starting the connection to the Streaming API.
For SDK client, add payload in the
|Field Name||Data Type||Description||Required||Default vaule||Allowed values|
|Boolean||Specifies that the PII or sensitive content should be identified.||Mandatory|
|Boolean||Specifies that the PII or sensitive content should be redacted in the transcript and insights.||Mandatory|
|String||Specifies any specific string to be used to replace redacted entities.||Optional||Min length 1 character, Max length 16 characters.|
The response returned for PII Identification and Redaction will be any of the following 3 Scenarios depending on how you have set up the two mandatory parameters
- Identify Only
- Redact Only
- Identify and Redact
PII or sensitive content will be identified and will be made available in the message and insight objects, but the content of transcript and insight with not be redacted, and will still show the sensitive content.
PII or sensitive content will not be made available in the message and insight objects, but the content of transcript and insight with be redacted, and will be replaced with the redaction indicator.
PII or sensitive content will be identified and will be made available in the message and insight objects. And the content of transcript and insight with also be redacted, and will be replaced with the redaction indicator.
Given below is a sample of using PII Identification and Redaction with Get Conversation Insights call for
Response with enable redaction configuration:
Response with disable redaction configuration:
When you enable the PII identification and redaction feature, the following PII data will be supported:
|Credit/Debit Card Number||Finance||A credit or debit card number is 12 to 19 digits long, used for payment transactions.|
|Credit/Debit Card CVV Number||Finance||A 3-digit or 4-digit security code of a credit or debit card.|
|Credit/Debit Card Expiration Date||Finance||The month and year a card expires.|
|Credit/Debit Card PIN.||Finance||A security code issued by a bank or credit union for authenticating the transaction. Not to be confused with CVV code.|
|IBAN Code||Finance||An International Bank Account Number (IBAN) is an international system for identifying bank accounts across national borders. It defined under the ISO-13616:2007 standard. An IBAN consists of up to 34 alphanumeric characters.|
|SWIFT Code||Finance||A SWIFT code is a unique identification code for a particular bank. These codes are used when transferring money between banks, particularly for international wire transfers.|
|US Bank Routing Number||Finance||The American Bankers Association (ABA) Routing Number (also called the transit number) is a nine-digit code. It is used to identify the financial institution that's responsible to credit or entitled to receive credit for a check or electronic transaction.|
|US Bank Account Number||Finance||US Bank Account Number.|
|Name||Personal||A person's full name, which can include first names, middle names or initials, and last names.|
|Personal||An email address to a mailbox.|
|Age||Personal||Age measured in months or years.|
|Phone Number, Address, Date of Birth||Personal||Phone number, address and date of birth.|
|Social Security Number||National ID||A United States Social Security number (SSN) is a 9-digit number issued to US citizens, permanent residents, and temporary residents.|
|Passport Number||National ID||A passport number.|
|US Drivers License Number||National ID||A driver's license number for the United States. Format can vary depending on the issuing state.|
|Date||General||Detects date mentions, including the names of common world holidays.|
|Domain Name||General||A domain name as defined by DNS standard.|