The IBM Watson cognitive system is being improved. The specialists of the corporation significantly updated the “emotion recognition module”, providing the system with the ability to recognize the emotional state of a person. Based on the analysis data, the system can respond to the person accordingly, knowing what he feels.
Now three APIs are added at once (while beta versions):
Tone Analyzer ,
Emotion Analysis and
Visual Recognition . The
Text to Speech (TTS) service has been updated to provide new opportunities for emotions, as well as access to the
Expressive TTS speech module API. All this significantly expands the boundaries of the interaction of man and machine, and the car was taught to empathize with human emotions, adding empathy.
“We continue to improve the capabilities of the IBM Watson platform, providing the developer community with the ability to create dynamic applications and services based on artificial intelligence,” said David Kenny, head of IBM Watson. “We also simplify the platform, making the process of creating, training and implementing developments based on IBM Watson more understandable and rational,” he adds.
')
IBM introduces new tools and improves the Watson interface for working with SDK
Node ,
Java ,
Python , as well as the recently introduced
iOS Swift and
Unity , included in the Watson portfolio. Developers have at their disposal
Application Starter Kits , which allows developers to accelerate the development of applications and services based on Watson. All APIs are available on the IBM Watson Developer Cloud Bluemix platform.
Tone Analyzer, Emotion Analysis and Visual Recognition
IBM Watson Tone Analyzer helps to set the overall tone of text communication. This is one of the latest add-ins for the Watson Developer Cloud API and SDK, which is available on Bluemix.
Emotional coloring . The emotions of people described in literature and known to us from childhood include anger, fear, expectation, surprise, joy, sadness, trust, and others. Service developers have created a model for evaluating emotions in the text. Tone Analyzer divides all emotions into three categories: positive emotions, negative and anger. Positive emotions include joy, optimism, inspiration, happiness, satisfaction. Negative - fear, disgust, denial, humiliation, guilt, despair. Anger is a type of negative emotions with such components as aggression, rage, frustration, irritation, hostility.
Social component . There is also a division according to three types: openness, expression of consent, honesty (integrity). Openness is the readiness of a person for a new experience; expression of consent - the tendency to find compromise and cooperation; honesty, good faith - the desire to act accordingly.
The style of presentation . And here there are three categories: analytics, confidence and caution. Analytical style of presentation shows the desire of the author to analyze, understanding the essence of things. Confidence reflects a person’s degree of confidence in something. And caution - the desire for a gradual development of events.
Emotion Analysis was added by IBM to the AlchemyLanguage API package. It uses deep processing and analysis of the language in order to help the developer better understand the emotions of other people. Developers can now identify positive and negative emotions, as well as produce a wider range of emotions, including joy, sadness, fear, disgust and anger. All this can be used, for example, to analyze user feedback, posts on social networks and regular comments. Companies can quickly determine the attitude of buyers to their products, assessing the ratio of positive and negative reviews. Accordingly, you can highlight the main emotions of users and respond by changing the product or service.
Visual Recognition provides the ability to recognize and classify images. Before using technology in any field of Visual Recognition, you can provide “training material”, on the basis of which the module will recognize images later.
Other companies have analogs, but there are also significant differences. Here, the main goal of IBM is to give developers a tool that can be used for various tasks and train it on their own material, creating a customized image classifier. For example, a retailer can teach Visual Recognition to recognize the clothes of its own production in pictures on social networks by analyzing the size of its audience.
Expressive Text to Speech
Work on this technology has been conducted for more than 12 years. Now it has become available to everyone in the form of the Watson TTS API. The cognitive system recognizes speech to a degree that was previously unavailable to machines. This includes the “understanding” by the computer of the tone, context and emotional coloring of speech. Based on this analysis, the computer can respond accordingly.
Previously, computers in such situations acted on the basis of a predefined set of words. The appearance of one or several words from the “control set” triggered the trigger of one of the algorithms, and the computer “responded”. Now the system of “text-based analysis” not only analyzes individual words, but also determines the emotional orientation of speech, its tone and semantic component. Based on the Watson TTS API, developers can create their own applications and services, simplifying and improving the principle of human-computer interaction.
Currently, the IBM Watson platform already has
several dozen different services available on the
IBM Watson Developer Cloud Bluemix platform. The cognitive system community includes more than 80,000 developers, students, entrepreneurs, engineers and technologists.