Tutorials | Bragisoft

Input patterns

A technical description of the pattern matcher language that is used by the system. Statics, variables, thesaurus variables, operators and sub topics/rules are all covered.

Off line Chatting with a chatbot can be done through the viewer or editor application. Both can be started from the windows-start menu. The software package works like a standard windows app: before you can begin, you need to open a project. For this tutorial, lets use one of the demo projects ‘Name & age’ (located in {my documents}\NND\Demos. After loading, you should see something like the next image: Lets focus on the chatbot window for this tutorial. It contains a toolbar at the top, to the left, an input box and a conversation...

Getting started: creating bots

You can create your own bots from scratch, you can build upon an already existing bot or you can compose a new bot from exported sections of other bots (like a collage). A bot usually consists of the following parts or sections: The chatbot’s properties This can be opened from the menu (view/chatbot properties) or from the toolbar on the project tool-page (first button). In the properties, you can specify some global settings, specific to the current project. This includes some preferences like your and the bot’s name, birthday and gender....

The different file types

The chatbot designer uses a number of different file types to accomplish different tasks. Here’s a short overview of all possible files (and sometimes directories): Projects A project contains the entire neural network (in binary form) together with a bunch of configuration files in a directory. This directory is accompanied by the main project file. Both have the same name. When moving around a project, make certain you have both file and directory. When opening and saving projects, you only need to worry about the file, the directory...

Creating your own characters

It’s possible to create your own characters for the chatbot designer app. The process consists out of 2 parts: first you need to create a set of images, once that’s done, you need to make a ccs file that combines all the images.

Using a bot’s memory

A bot has 2 types of memory at it’s disposal: short and long term memory, but with some tricks, a mid term memory function can also be simulated. Short term memory Or also called ‘volatile’ as it’s content is lost in time, can be accessed through the use of variables in the patterns. Input patterns support 2 types of variables: regular variables, which can collect any type of content and thesaurus variables, which can only collect words that are equal to or are children of the thesaurus item referenced by the variable (in other...

Numbers, time, dates, durations

Besides text, a chatbot should also be able to handle other types of basic data, like numbers, date-time and time-spans. This tutorial takes an in-depth tour on all the features available to your for working with these types of values.

Why? because! :Invert

In this tutorial, different approaches are presented to handle 'because' statements and 'why' questions. The tutorial also presents a technique for inverting sentences (I vs you), which is commonly used in many types of reply statements.

Scraping the Internet

Getting information from the internet into a chatbot’s output can be very useful at some times. Not only to show continuously changing values, like weather information, but it can potentially also be used for learning, although the latter is obviously a little trickier. Retrieving, or scraping info from the internet can be done remarkably easy with the chatbot designer. This tutorial uses the google weather api to guide you into the details of internet scraping.

Questions, answers and redirections

When a bot asks a question, it needs to know that a response is expected and, when an incorrect response is given, the bot should also know how to react. Furthermore, to correctly process an answer, memory and context often play an important role. Finally, the content of the questions that are asked (the topic) should also be controllable. In this post I’ll try to present a way to approach these issues using the chatbot designer.