Smart Conversations Overview

Smart Conversations is a collection of add-on features for Conversation API that passes received messages to the Sinch proprietary Machine Learning (ML) API engine. Each of these features collects and analyzes information present in the message. These results are then delivered via the SMART_CONVERSATION and MESSAGE_INBOUND_SMART_CONVERSATION_REDACTION webhooks.

Through these webhooks, Smart Conversations delivers vital information that can help you automate processes, respond to feedback, simplify data entry, and solve other problems to help streamline your business operations.

The features that are currently available, along with a description of each, are listed below:

Feature	Description	Description	Information and sample requirements	More information
Sentiment Analysis	Provides an assessment of the likelihood that the emotional tone of a message is positive, negative, or neutral.	Provides an assessment of the likelihood that the emotional tone of a message is positive, negative, or neutral. For information on how this analysis is represented in a callback, see the description of the ml_sentiment_result array.	There is no minimum sample set requirement.
Natural Language Understanding (NLU)	Provides an assessment of the likelihood that the message corresponds with a specific set of intents. For example, the likelihood that a message is a greeting, a request for information, or an expression of satisfaction or dissatisfaction.	Provides an assessment of the likelihood that the message corresponds with a specific set of intents. For example, the likelihood that a message is a greeting, a request for information, or an expression of satisfaction or dissatisfaction. For information on how this analysis is represented in a callback, see the description of the ml_nlu_result array.	There is no minimum sample set requirement. However, we recommended you have at least 50 samples of expressions for each intent to achieve accurate results.	More contextual information regarding Natural Language Understanding can be found on our Community site.
Image Comprehension Engine	Provides an analysis of images included in the received message. This includes the identification of probable document types in the image, optical character extraction, and the assignment of values to probable fields identified on the image.	Provides an analysis of images included in the received message. This includes the identification of probable document types in the image, optical character extraction, and the assignment of values to probable fields identified on the image. For information on how this analysis is represented in a callback, see the description of the ml_image_recognition_result array	For Document Image Classification (DIC), a data set of at least 100 images for each document class is required. For Document Field Classification (DFC), the regex patterns for each field to be extracted must be provided. For more information, click here.	More contextual information regarding the Image Comprehension Engine, which is also called IRIS, can be found on our Community site.
PII Masking	Provides an analysis of content included in the received message to identify and mask sections of text that correspond to any representation of information that discloses the identity of an individual. Name, phone number, national ID, email, and other sensitive pieces of information are considered Personal Identifiable Information (PII) and will be masked.	Provides an analysis of content included in the received message to identify and mask sections of text that correspond to any representation of information that discloses the identity of an individual. Name, phone number, national ID, email, and other sensitive pieces of information are considered Personal Identifiable Information (PII) and will be masked. For information on how this analysis is represented in a callback, see the description of the ml_pii_result array	There is no minimum sample set requirement. By default, the following common PII are supported/recognized. You can enable/disable each one to configure how PII should be identified during redaction. Recognized PII: `AMOUNT_OF_MONEY`: Any monetary value. Example: $5.99 `CARD_NUMBER`: Credit/Debit card number. Example: 1234-5678-9123-4567 `DATE:` Any date written in common formats. Example: 01/01/1990 `DRIVER_NUMBER`: Driver's license number. Example: AB123456 `EMAIL`: Email addresses. Example: bob.sinch@example.com `GENDER`: A person's gender. Example: Male `NATIONAL_ID`: Common national IDs for different countries, such as SSNs in the USA and CPF in Brazil. Example: 000-00-0000 `ORDINAL`: Ordinal number. Example: 3rd `PASSPORT_NUMBER`: Passport number. `PHONE_NUMBER`: MSISDN or phone/mobile number. Example: (123) 456 7899 `TIME`: Any time written in a standard format. Example: 10:00 `URL`: Uniform Resource Locator. Example: www.bobsinch.com `VISA_NUMBER`: The visa permits number, also known as the visa foil number of the visa document. `ZIPCODE`: The Zone information postal (Zip) code. Example: 473121-829 `NUMBER`: Any number that is different from previous patterns. Example: 5 `PERSON`: Full name, first name, or last name. Example: Bob Sinch `LOCATION`: Home address, country, state, or city. Example: USA
Offensive Content Analysis	Provides an assessment of the likelihood that the analyzed text or image message contains offensive content (for example, explicit images, hate speech, offensive language, etc.).	Provides an assessment of the likelihood that the analyzed text or image message contains offensive content (for example, explicit images, hate speech, offensive language, etc.). For information on how this analysis is represented in a callback, see the description of the ml_offensive_analysis_result array	There is no minimum sample set requirement.

Click here to get started with Smart Conversations.