AI Agent ROI Calculator
Free training: Chatbot crash course
Whitepaper: The acceptance of chatbots
Entity
--> to the BOTwiki - The Chatbot Wiki
Entities are used to extract user information from natural language.
A distinction is usually made between System Entities and custom entities. System entities are entities already contained in the system for addresses, times and numbers, for example.
Custom entities, on the other hand, can be defined by the user and contain, for example, product information or a staff directory, depending on the use case.
Entities in NLP Services
The Entity Recognition is already integrated in the current NLP Services [1][2][3] and is, besides the Intent Matching, the main component of the Natural Language Processing for chatbots.
Example for an Entity Extraction
I would like to order a small Pizza Margherita to Berliner Straße 1.
Entities:
small (Custom Entity pizza_size)
Margherita (Custom Entity pizza_type)
Berliner Straße 1 (System Entity street_address)
> Back to BOTwiki - The Chatbot Wiki
Sources
[1] https://dialogflow.com/docs/intents
[2] https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-utterance
[3] https://cloud.ibm.com/docs/services/assistant?topic=assistant-intents
Confidence Score / Confidence Level
--> to the BOTwiki - The Chatbot Wiki
The Confidence Score, or Classification Threshhold, indicates how sure the NLP service / machine learning model is that the respective intent was correctly assigned. The score can have a value between 0 and 1 , depending on how the neural networks work. In general, a score for each intent is calculated for each user input and the one with the highest value is returned as the result. If the confidence level falls below a predefined limit, a fallback intent is issued.
An example for the calculation of the Confidence Score at Google Dialogflow:
The following four training phrases were entered for the intent "Burger_order". Training phrases have been added:
"Burger Order",
"Order burger",
"I would like to place an order for a burger",
"I want to order a burger"
Dialogflow calculated a confidence score of 0.8 for the user input of "I would like to order a burger from you" . The NLP service Dialogflow is therefore 80% sure that the response issued from the intent "Order_a_burger" was correct. Based on this data and previously defined rules, no fallback intent is issued.
> Back to BOTwiki - The Chatbot Wiki
BOTwiki - The Chatbot Wiki
A
AI Task
AI Workflows
Aleph Alpha
Artificial General Intelligence (AGI)
C
Channel Connector
Chatbot
Clustering
Collected Data
Confidence Score / Confidence Level
Contact Center AI (CCAI)
AI Context
Contextual Awareness
Conversational AI Platform
Conversational Analytics
Conversational Copywriting
Conversational Design
Conversational Map / Conversational Flow
Conversational Office
Conversational Testing
Custom GPT
Custom Voice
E
F
(Default) Fallback Intent
FAQ Bot
G
Generative AI
Guided Communication
H
AI hallucinations
Happy Path
Human Handover
Human in the Loop
Hybrid Human Chatbot
I
L
LangChain
LangSmith
AI Latency
M
Machine Learning
Markdown Prompts
Messenger Services
Model Context Protocol (MCP)
N
Natural Language Generation
Natural Language Processing
Natural Language Understanding (NLU)
O
On Premise Chatbots
Chatbot Operations
P
Filler
Pre-built models
Prompt Engineering
Prompt Jailbreaks
R
RAG (Retrieval-Augmented Generation)
RCS - Rich Communication Services
Reasoning
S
Semantic Search
Sentiment Analysis
System Entities
T
AI Temperature
Tone of Voice
AI Tokens
Chatbot Training
Training phrases / utterances
U
Trainings Phrases / UtterancesV
Voice Bot / AssistantW
Wizard of Oz Experiment
Didn't find what you were looking for? You may find the answer you need in our webinars.
Wizard of Oz Experiment
--> to the BOTwiki - The Chatbot Wiki
In the field of human-computer interaction, the Wizard of Oz method refers to a research experiment in which subjects interact with a computer system that is considered autonomous by the subjects but is actually operated or partially operated by an unseen human.[1]
Chatbots and Wizard of Oz
Chatbots are enormously suitable for the Wizard of Oz experiment. In this way, a use case can already be examined for its"chatbot suitability" before implementation. The findings can then be used to iteratively expand existing flows and define new communication strands. In addition, the collected data, such as utterances, can be used directly for the Chatbot Training be used. A mature human handover tool is even able to automatically convert the tested data into a chatbot.
Recommended procedure
- Define different chatbot flows
- Integration of a live chat or an empty chatbot that only triggers a human handover.
- Manual response to user queries
- Derive chatbot flows
- Answering the queries based on the chatbot flows
- Iterative revision and expansion of the chatbot flows
- Manual or automated transfer of the flows into a chatbot builder
> Back to BOTwiki - The Chatbot Wiki
Sources
[1] Kelley, J. F., "An empirical methodology for writing user-friendly natural language computer applications". Proceedings of ACM SIG-CHI '83 Human Factors in Computing systems (Boston, 12-15 December 1983), New York, ACM, pp. 193-196
RCS - Rich Communication Services
--> to the BOTwiki - The Chatbot Wiki
Rich Communication Services (RCS) is a protocol of mobile operators and is promoted by the GSMA, the industry association of international mobile operators.[1]
RCS and Chatbots
RCS Business Messaging is the evolution of mobile messaging that increases and improves communication between people and businesses. It offers businesses the opportunity to increase customer engagement by using business messaging through chatbots and artificial intelligence (AI). No longer is it necessary to download multiple apps, users are given direct access to a range of brands and services within the messaging app itself, allowing them to work with virtual assistants to book flights, buy clothes, make restaurant reservations and more.[2]
Rich Messaging Chatbot via "SMS"
Simplified, RCS can be seen as the successor to SMS and MMS. Only with rich messaging content such as buttons and videos. RCS is integrated by Google and Apple into the already pre-installed Android Messages[3] app and iMessage [4] app. Thus, every Android and iOS user theoretically has access to RCS.
RBM and ABC
From Android, the system is called RBM (Rich Business Messaging)[5]. Apple calls its service ABC (Apple Business Chat)[6]. To use the systems, however, the transmission protocol RCS must be supported by the respective carrier.
> Back to BOTwiki - The Chatbot Wiki
Sources
[1] https://www.gsma.com/futurenetworks/rcs/
[2] https://www.gsma.com/futurenetworks/rcs/rcs-business-messaging/
[3] https://messages.google.com/web/authentication
[4] https://support.apple.com/explore/messages
[5] https://jibe.google.com/business-messaging/
[6] https://www.apple.com/ios/business-chat/