cognitive-services

WHAT ARE COGNITIVE SERVICES?

Cognitive Services are a set of machine learning algorithms that Microsoft has developed to solve problems in the field of Artificial Intelligence (AI). It is a simulation of human thought process in a computerized model, also known as cognitive computing.

The main goal of cognitive computing is to create an Automated IT System that should be capable of solving problem/providing solution without human assistance. It uses machine learning algorithms. And such algorithms are the ones which are so profoundly used by many of the giant companies, like Google, in their websites. If one were to cast a quick glance over this page, they’d understand how eCommerce businesses inculcate these algorithms. 

Web and Universal Windows Platform developers can consume these algorithms through standard REST calls over the Internet to the Cognitive Services APIs.

They work across devices and platforms such as iOS, Android, and Windows. Also, they are easy to set up.

DOMAINS OF COGNITIVE SERVICES APIS

Cognitive Services APIs around five domains:

  • Vision
  • Speech
  • Language
  • Knowledge
  • Search

VISION

Vision API provides image processing algorithms related to vision, face recognition and emotions. Image Recognition can interpret real time images from multiple formats. An image can be recognized as a collection of objects and the actions. Image Recognition can identify and assess the collective emotions and ages of people in an image. It can recognize the environment of the image and name the elements displayed. It can detect text in the image, such as a sign, and understands it. Image Captioning brings this all together. It allows a simple and complete story to be told about the image.

  1. Face API: The Face API helps to detect, analyze, and organize the faces in a given image. We can also tag faces in any given photo. It provides the most mature face algorithms to work with applications.
  2. Emotion API: The Emotion API creates apps that respond to moods, recognize feelings, and get personal with users. Using facial expressions,it detect happiness, neutrality, sadness, contempt, anger, disgust, fear, and surprise. The artificial intelligence algorithms detect these emotions based on universal facial expressions, functioning even cross-culturally.
  3. Computer Vision API: The Computer Vision API,extracts rich information from the images to categorize and process visual data and protect your users from unwanted content.

It can:

  • Analyze an image.
  • Generate thumbnails.
  • Read text in the images.
  1.   Content Moderator: Content Moderator, protects your brand and users with automated image, text, and video moderation services and human review tools.It automatically filters out offensive content in images, text, and video across platforms and includes human review tools for more nuanced cases.

It offers:

  • Image moderation API
  • Text moderation API
  • Video moderation API

SPEECH

Speech API allows the developers to implement speech processing in their apps. Speech Recognition has progressed to the point digital assistants and switchboard IVR replacements can understand realistic human speech. Applications using cognitive services understand naturally spoken language: context, meaning, slang, jargon, and even local accents.

  1. Translator Speech API: The Translator Speech API,, is a cloud-based automatic translation service. It enables developers to add end-to-end, real-time, speech translations to their applications or services.
  2. Speaker Recognition API: The Speaker Recognition API, uses speech to identify and authenticate the individual speakers. It gives your app the ability to know who is talking.

LANGUAGE

Language API allows the developers to implement natural language and sentiments processing in their apps. Text can be converted to speech for automatic verbal responses. Speech can be transcribed as text and piped as input to the APIs.

  1. Language Understanding Intelligent Service (LUIS): LUIS helps an application understand commands from users. The LUIS API, is designed to provide you with an easy way to create models, which allows your applications to understand user commands.
  2. Text Analytics API: This API evaluates sentiment and topics to understand a user’s commands.It is designed to detect sentiment, key phrases, topics, and language from your text. It is a suite of text analytics web services built with Azure Machine Learning. It uses advanced natural language processing techniques to deliver class predictions.
  3. Bing Spell Check API: The Bing Spell Check API, as described by Microsoft, helps users correct spelling errors, recognize the differences among names, brand names, and slang, and understand homophones as they type. Also, it detects and corrects spelling mistakes within your app.

KNOWLEDGE

Knowledge API provides the functionality related to the recommendations and semantic searches.

  1. Recommendations API: Recommendations API is designed to provide personalized product recommendations for your customers and improve sales in your store.
  2. Academic Knowledge API: The Academic Knowledge API, explores relationships among academic papers, journals, and authors.

SEARCH

Search API allows the developers to implement Bing Search APIs to build smart and more engaging apps.

  1. Bing Web Search API – It includes web pages and related types, such as images, videos, news, related searches, spelling corrections, etc.
  2. Bing News Search API – It provides news items relevant to user’s query. It also provides news for specific categories, such as health, sports, etc., and news trending at any point in time.
  3. Bing Video Search API – It returns relevant videos. It also provides endpoints for similar videos and trending videos.
  4. Bing Image Search API – It has 3 endpoints: image search, similar images, and trending images.

           Below is the example for Text Analytic API.

Here, text is analyzing for home rent prediction. The input values from user will be Flat and Area, and the service calculate the average rent for given input, which is highlighted in red box.

References:

  1. https://dzone.com/articles/a-look-at-cognitive-services