Skip to main content

How do I build AI-enabled apps with OutSystems?

OutSystems

How do I use cognitive services to create AI-enabled Apps?

Cognitive services solve business problems from unstructured data that regular development algorithms cannot  via AI and machine learning. They are built of top of already known and tested models that provide best-in-class accuracy. Text, speech, and image analysis are generic, enabling the use of many data sets to train and test the models. Some can be trained with specific data sets to enable services like image recognition to detect a certain object or pattern. Cognitive services can be split in categories:

  • Vision services related to image and video processing

  • Speech services for speech recognition, intent recognition, transcription and synthesization

  • Text services for content and sentiment analysis

  • Knowledge services that provide more complex content analysis, automatically creating Q&A from a given content.

Vision Services

  1. Azure Vision Services

  2. Google Vision Services

  3. IBM Vision Services

  4. AWS Rekognition

With vision services, image-processing algorithms smartly identify, caption, index, and moderate pictures and videos. It’s possible to understand the content of an image, classify it, detect individual objects and faces within images, and read printed words in the images (OCR). In this section we look at the vision services from Microsoft, Google, IBM, and AWS and how you can use them in OutSystems.

Azure Vision Services

Microsoft Azure Vision Services offer:

  • Image analysis: Returns information about visual content found in an image, identifying content and labeling it with confidence. It detects objects and potential adult content and retrieves their location from an image. It also identifies image types and color schemes.

  • Recognition of text in image (handwritten or printed): Uses optical character recognition (OCR) to detect text in an image and then  pulls any recognizable words into a stream of characters that are machine-readable.

  • Recognition of celebrities and landmarks: Spots famous people from business, politics, sports, and entertainment from images, as well as natural and manmade landmarks from all over the globe.

  • Generate a thumbnail: Produces a thumbnail based on any image, and modifies images to best suit the needs for size, shape, and style. Smart cropping generates thumbnails that differ from the aspect ratio of your original image while preserving the part that’s of interest.

  • Face verification: Checks if two faces belong to the same person and assigns a confidence score for how likely it is that the two faces belong to the same person.

  • Face detection: Finds human faces in an image, using face rectangles to show the location of a face or faces in the image, along attributes such as age, emotion, and gender..

  • Emotion recognition: Analyzes facial expressions and returns a confidence score for the likelihood of emotions, such as anger, contempt, disgust, fear, happiness, neutral, sadness, and surprise.

  • Custom model for image recognition: Trains the image recognition model with custom images and custom tags for a specific use cases.

Through the OutSystems strategic partnership with Microsoft, the OutSystems platform supports and integrates the components for all Azure Vision Services. Developers can use these capabilities in the OutSystems IDE and using the OutSystems visual language.

ai_page_graphics_02.png

The Forge component that should be used for these vision services is the Azure Cognitive Services Connector.

Google Vision Services

Google Cloud Vision offers these services:

  • Extract text: Uses OCR to detect text  in images and automatically identifies language.

  • Identify text in image: Uses object localization to create a list of all the text objects in an image and identifies the area of the image where text was detected.

  • Get specific data types in image: Uses specified regular expressions to pull  text from an image, which is useful for emails or dates.

A reviewed component for the Google Cloud Vision allows developers to use these capabilities in the OutSystems IDE and using the OutSystems visual language.

ai_page_graphics_03.png

The Forge component for these vision services is Google Cloud Vision OCR.

IBM Watson Vision Services

The IBM Watson Visual Recognition Services offer:

  • Facial analysis: Analyzes faces in images and identifies  estimated age, gender, and names of celebrities.

  • Image recognition: Tags and classes objects in images, and can be trained to use custom classes

A reviewed component for IBM Watson Vision Services allows developers to use these capabilities in the OutSystems IDE and using the OutSystems visual language.

ai_page_graphics_4.png

The Forge component that should be used for these vision services is IBM Watson Services.

This component will be updated to support a new Watson authentication requirement.

AWS Rekognition

AWS Rekognition offers:

  • Face matching: Allows the application to create collections of faces. These collections can then be "searched" to see if they match a sample image.

  • Add face to collections: Adds a new facial image to the specified collection.

A reviewed component for Amazon Rekognition Face Matching allows developers to use these capabilities in the OutSystems IDE and using the OutSystems Visual Language.

ai_page_graphics_5.png

The Forge component that should be used for these vision services is Amazon Rekognition Face Matching.

Speech Services

  1. Azure Speech Services

  2. IBM Watson Speech Services

Speech services can convert spoken audio into text or written text into natural sounding audio, enable the use of voice for verification, or add speaker recognition to an app, allin a variety of languages and voices.

Azure Speech Services

Azure Speech Services offer:

  • Speech transcription: Converts spoken audio to text.

  • Custom speech service: Trains a the speech model with custom speech analysis for specific use cases.

  • Speaker verification: Uses the voice to verify a speaker’s claim of identity, powering applications with an intelligent verification tool.

  • Speaker identification: Determines the identity of an unknown speaker by comparing the speaker’s input audio with a group of selected speakers and returning an identity if one is found.

  • Text to speech: Converts text to audio in near real-time and plays back so applications can speak to users naturally, improving accessibility and usability.

Through the OutSystems strategic partnership with Microsoft, the OutSystems platform supports and integrates components for all of Azure’s Speech Services, allowing developers to use these capabilities in the OutSystems IDE and using the OutSystems Visual Language.

ai_page_graphics_6.png

The Forge component that should be used for these speech services is the Azure Cognitive Services Connector.

IBM Watson Speech Services

The IBM Watson Speech has one available service. The text to speech service produces human-like audio from written text in multiple languages and tones. It makes content more accessible to users with different abilities or activities, such as providing audio options to avoid distracted driving for example.

There is a reviewed component for IBM Watson Speech Services that allows developers to use these capabilities in the OutSystems IDE and using the OutSystems Visual Language.

ai_page_graphics_7.png

The Forge component that should be used for these vision services is IBM Watson Services.

Text Services

  1. Azure Text Services

  2. IBM Text Services

Text services enable apps and services to understand the meaning and recognize the intent of unstructured text, extracting information about people, places, events, and much more from documents, news articles, or blog posts. Text services also extract metadata from content such as concepts, entities, and sentiment.

Azure Text Services

Azure Text services has several available services:

  • Sentiment analysis: Uses scoring to analyze text sentiment. Scores close to 1 indicate positive sentiment, and those close to 0 indicate negative sentiment. The sentiment scores are generated using classification techniques.

  • Key phrase extraction: Pulls a list of key talking points from the input text.

  • Language detection: Uses a numeric score between 0 and 1 to indicate the certainty of detected language, with 1 being 100% certainty. One hundred and twenty  languages are supported.

  • Identify entities in your text: Detects names of organizations, people, locations, and more.

  • Translation: Enables developers to easily integrate websites, tools, or any solution requiring multi-language support into their applications, such as website localization, e-commerce, customer support, messaging applications, internal communication, social media scheduling and inbound platforms, and more.

  • Spell check: Uses Bing Spell Search API v7.

Through the OutSystems strategic partnership with Microsoft, the OutSystems platform supports and integrates components for all of Azure’s Text Services, allowing developers to use these capabilities in the OutSystems IDE and using the OutSystems Visual Language.

ai_page_graphics_8.png

The Forge component that should be used for these text services is the Azure Cognitive Services Connector.

IBM Watson Text Services

IBM Watson Text Services include:

  • Translation: Identifies the source language of text, translates it  to another specified language language, You can also use custom translation models.

  • Text analysis: Analyzes text, HTML, or a public web page for concepts, emotions, keywords, and more.

  • Personality insights: Derives human attributes such as needs, values, and habits from  content written by an author.

  • Text tone: Analyzes text or HTML input, and derives various characteristics related to tone: emotion, language, and social.

There is a reviewed component for IBM Watson Text Services that allows developers to use these capabilities in the OutSystems IDE and using the OutSystems Visual Language.

ai_page_graphics_9.png

The Forge component that should be used for these text services is IBM Watson Services.

This component will be updated to support a new Watson authentication requirement.

Knowledge Services

  1. Azure Knowledge Services

 

Currently, only Azure offers knowledge services, which is more complex content analysis that can be combined with speech and text services to create a chat bot that not only knows what the user needs, but also is able to find the right solution for a problem.

Azure Knowledge Services

The Azure Knowledge service QnA Generator pulls questions and answers from existing content to create Q&A, which is a key component of an intelligent chat bot.

Through the OutSystems strategic partnership with Microsoft, the OutSystems platform supports and integrates the components for all Azure Vision Services. Developers can use these capabilities in the OutSystems IDE and using the OutSystems visual language.

ai_page_graphics_8.png

The Forge component that should be used for these text services is the Azure Cognitive Services Connector.

  • Was this article helpful?