Guide FloatChat

Floatchat- User Guid

Tabular input

1. Introduction #

Smart conversational bots have revolutionized user engagement, allowing users to interact with their desired products or brands anytime, anywhere. These bots handle complex use cases by extensively training on FAQs and adding entity sets, making it easier to manage conversation context and handle multiple queries with less effort. Floatchat provides the functionality to add a data source that maps entity sets, reducing the need to write queries for each set of information.

1.1 Availability #

The ability to add a data source is available to all Floatchat customers. You can add a data source to your bot by clicking on the Train tab in the left panel and selecting Tabular Input.

Tabular input

1.2 Terms and Definitions #

Terms 

Definitions 

FAQ

Frequently Asked Questions (FAQs) are standard queries relevant to a product or service.

Intent 

It refers to the intention or purpose of the user in the conversational flow.

Entity

It is a data point or value that can be extracted from a conversation/user query, allowing for customization of the collected information.

NLP

Natural Language Processing is the ability of a computer program to understand human language as it is spoken.

2. Creating a Data Source #

To begin, ensure that your data table is ready in a file with a specific structure. Each row should represent one entity from the set for which the chatbot will provide details, and each column should represent various aspects that users may query the chatbot about.

Tabular input
  • Click on the Train tab and select Tabular Input.
Tabular input
  • Upload the file containing the tabular data for entities and their information. Supported file formats include .xls, .xlsx, and .csv. You can refer to the sample file provided for reference.
Tabular input
  • Name the data source and the entity to be used for these custom values.

3. Post Upload Processing #

After uploading the data sheet, an internal entity of type “Custom Values” is created to track the various values of the defined objects. The first column entries are treated as different values of this custom entity. These entities can be used in FAQs and in Request User Data.

Tabular input
  • Multiple intents are created, with each intent associated with a specific column/attribute. Variations can be added to each intent to enhance bot training.
  • The responses for these intents are generated and set as reference values associated with the corresponding cells.
  • The dynamic identifier is used to reference the values. For example, {{context.CourseName.Start_Date}}, where CourseName is the entity name and Start_Date refers to the value in the Start Date column.
  • These intents are associated with the data source, and their life cycles are tied together. If a data source is deleted, the corresponding linked intents are also cleaned up.
Tabular input
What are your feelings
Scroll to Top