Hi everyone. I can find a bunch of references online telling me what KPIs I should measure for my chatbot, and they have all been helpful; but does anyone know where I can find benchmarks? I understand that for a lot of these, I’ll be looking for trends, but are there any standards out there that I should be aiming for? I am looking at the following KPIs: – Confusion Rate – Missed Utterances – Interaction Rate – Retention Rate – Goal Completion Rate – Human Takeover Rate – Total Number of Users Thanks.
Nuacem AI Helps you to Choose Which AI Messenger Fits Your Marketing needs?
AI Chatbots are programmed with artificial intelligence to provide information or services.
AI chatbots are the next stage in the evolution of phone chat agents. They can handle more customer queries with fewer mistakes and free up employees for other tasks. They also provide customers with better service by not having the same limitations as people do since they can work 24/7 and don’t get tired.
AI chatbot assistants are good for businesses because they cost less than traditional customer service, which means that companies can offer more features to their customers without increasing their prices.
We recently talked about flipped classrooms, which refers to changing the classroom setting from an instruction-based learning environment to one that’s discussion-based.
Today, we’ll be exploring flipped learning. Although the two sound similar, there are some key differences that you should know.
This year’s Chatbot Conference will be the begging of something new!
Chatbot Conference in the Metaverse
We have very exciting news!
It’s that time of year, where we start to actively plan our next Chatbot & AI Conference and we’re planning on hosting it in the Metaverse!
Metaverse will allow us to connect online in a more embodied experience. You will be able to virtually walk around, meet people, talk to the speakers and even have a happy hour!
So, we are very excited!
To make matters even more interesting, we will explore the topic of how Converstional AI Avatars are coming into the Metaverse!
As you may know, Ilya Gelfenbeyn, the previous co-founder of Dialoglfow (originally Api.ai) has founded a new startup, Inworld AI, that focuses on this.
Inworld AI provides a developer platform for creating AI-powered virtual characters to populate immersive realities including the metaverse, VR/AR, games, and virtual worlds.
Virtual Avatars
What we are seeing is the beginning stages of technological convergence as AI, AR/VR, Crypto are begging to merge into the Metaverse.
So this year’s event looks to be very unique and quite special and this is just the beginning of what we are planning.
Here is how we are planning on using NFTs at the conference…
An NFT for your Identity
In our everyday lives, when we meet someone for the first time, we can instantly get a read on what type of person we are talking with. By the way they dress, move, speak they communicate their identity and who they are shows. However, we can’t really do this online.
We created the Personality NFT to help people instantly share their personality with others and find people like minded people online and in our community.
The Personality NFT is based on the most complete Psychometrics Test which includes your Big 5 personality traits, value systems, and identity. After you take the test, you will get your cards and be able to share it with others.
Personality NFT
These cards are very powerful. They can be used to learn about yourself, to learn about others, to find friends, to find business partners, and to achieve your goals in life.
They also have multiple use cases for businesses, and can be used at events, like our conference!
How to use Personality NFT at our Conference
The Personality NFT cards will help you discover the best ways to work with others by leveraging the strengths of your personality and theirs. You can think of it as a MAP that can show you how to connect with others on a deeper level.
We are very exciting about this project and our upcoming conference and hope to see your there!
I am currently working on my thesis and the topic of the thesis is “chatbot user friendliness for online businesses”. We currently are exploring the idea to have a chatbot implemented on a website where the user can choose a DMN model (basically a flowchart). Based on the chose model, the chatbot will ask questions to the user to provide the optimal output/solution given the inputs from the user.
This was actually already done by a previous thesis, but it was only locally and used Telegram chatbots with a Python back-end. I was wondering if any of you have a good idea how we can implement this further into a website? Are there any existing platforms where we can make our own chatbot and implement it into a website? Look forward to hear from you guys!
In this growing competitive world, we always tend to be the best among others. We want the system and work done to be perfect with no human errors. As said, making this happen is quite difficult. Firstly, getting human resources is one challenging task, and acquiring 100% skilled and experienced employees is nearly impossible.
We can agree that 60% of day-to-day activities rely on machines or automatic AI. Without having them, we can’t imagine our lives today. AI is known for its perfection in its work, and it is not new to us that we depend on it every day. Introducing conversational AI in many places has brought us good results.
They have not only made our jobs easier but far more effective compared to previous methods. As humans, we tend to make mistakes unknowingly that can lead to unforeseen risky events. However, with conversational AI, we can eliminate all such events from our workflow.
Introducing CX Automation using conversation AI in the field of NBFC (Non-Banking Financial Company) has been a game-changing plan. Also, it has benefited us in various ways.
Let us know more about CX automation, Conversation AI, and their benefits for NBFC in detail.
What is CX Automation with Conversational AI?
CX Automation is nothing but Customer experience or review on any product or technology that helps users to carry on with their day-to-day activities. This also includes replacing humans with AI for work done by us. Automated customer experience helps developers to upgrade and introduce technology or products at a new level.
Conversational AI refers to a set of technologies or programming software that helps humans to have human-like interactions with computers and also assists with speech-enabled applications. They are pre-programmed on the basis of options available to provide suitable answers or solutions for queries that arise from the same.
How does it work?
Customer Experience Automation is mainly used in the field of IT and also other industrial fields. It uses modern technology to improve certain aspects of customer service resulting in inefficient outcomes, reliable products, customer satisfaction, etc. It can be implemented in any stage of customer service to increase the level of retention of users.
With the help of ASR (Automatic speech recognition), NLP (Natural Language Processing), ADM (Advanced Dialog Management), and Machine Learning (ML), conversational AI understands human speech and reacts and learns from every interaction.
How does CX Automation using Conversation AI work in the field of NBFC?
As the name suggests, NBFC does not fall under the banking financial sector but plays a very important role in lending loans, mutual funds, holding shares, insurance companies, etc. that are 80% of banking activities. These industries can grow limitlessly and have to have enormous support from AI in their growing days.
Launching CX Automation with conversational AI has been a boon to all NBFC companies to carry out their work effortlessly. Many companies have saved huge amounts of money by knowing how to automate customer communications as they do not have to establish any private unit to conduct this task.
Working Of Conversation AI in NBFC
These days customers do not have much time to talk and sort out problems with customer care. Hence, conversational AI for banks has been introduced.
It receives input from clients based on any queries such as loan amount, mutual funds, shares, etc. Inputs can be either text or speech. If a user opts to speak, then a speech recognition program senses words and converts them into computer language.
The computer uses various software to understand spoken words and forms a response in its language at its side. Dialog management software converts into a human understanding language and displays or speaks the same as a reply to our problems or queries. CX Automation plays an important role here.
In every query, lies a different answer which has to be answered based on the situation or the stage the user is in. CX Automation helps the system to learn and improve over time on its own. This is done purely on situations experienced by machines or AI. If necessary, with help of CX Automation, conversational AI corrects itself in areas it needs to.
Isn’t all this exciting, as we speak to AI every day just like we speak to other humans? Want to know more? Then, stay tuned while we look into other Banking AI Solutions in detail.
The conversational Banking sector is very essential to running a successful company and chatbots in the banking industry have made it easier. These days customers do not want to wait in a call queue to get answers but need instant solutions. Thus, AI chatbots for banking were introduced
Chatbots for banking act just like a banking employee sitting at another end, understanding your questions and answering them immediately. However, in this case, intelligent chatbots for banks do work for you. The same procedure is applied in the chatbox, where it converts human language into its own, answers a query, and replies to the same, converting them to our language in a fraction of seconds.
Some Banking Chatbot examples are here below.
Eno, Capital One’s chatbot
Balance watch by Erica
ATB Financial Chatbot
Amy, HSBC’s chatbot
Wells Fargo chatbot and so on
These AI chatbots for banking have their own unique way of responding to users with very minimal cost consumption resulting in benefiting the industry. Some benefits include,
Improves customer service
Personalize customer experience
Reduce waiting time in calls
Decrease costs
Help employees do their job better
Conclusion
CX Automation using conversation AI for NBFC sectors has many advantages or benefits for both customers and companies. Every growing banking sector has to implement the same in order to achieve its goal effectively. Chatbots in the banking industry have proved to be most efficient and helpful in achieving 100% client satisfaction compared to any other method.
The healthcare industry has been under immense pressure over the past couple of years and needs to embrace digital transformation as much as possible to scale up and provide healthcare services in a better manner. So, how do they do that? How can the healthcare sector improve customer satisfaction? The answer, to a great extent, lies in reaching patients over the app they use 23 times a day and automating conversations right there. How do they do that? By deploying WhatsApp chatbots for healthcare.
How are medical WhatsApp chatbots used in healthcare?
1. Assessing symptoms
Your patients can chat with your healthcare chatbot on WhatsApp to self-report their symptoms and get a diagnosis. This is not intended to replace doctors or healthcare professionals in any way, rather, these bots are meant to supplement them and help them work more effectively. Such assessments are meant for preliminary diagnoses, not final ones.
2. Booking appointments for your hospital or healthcare service
After assessing the patient’s symptoms and generating a preliminary diagnosis, the bot can refer the patient to departments and doctors within your hospital, share their schedules, and even help patients book appointments for consultations and check-ups. You can include your healthcare chatbot with Google Calendar to make the booking process even more convenient for your patients and reduce the effort involved.
3. Appointment reminders
Missed appointments can cost your hospital or clinic quite a bit of money. In fact, it’s so costly to the healthcare sector that the NHS loses £216 million to missed appointments on a yearly basis because 1 out of every 20 patients who make appointments just don’t show up .for them.
A lot of these misses could be avoided, quite a few of them get missed because the patients simply forget that they had an appointment in the first place. You can use your WhatsApp bots to send appointment reminders and get your patients to confirm that they’re going to show up.
4. Test results
You can use your bot to send test results over to your patients so that they don’t need to physically collect them. Your patients can even access your healthcare chatbot on WhatsApp to see which of their reports are pending and could even book tests over the bot.
With everything that they have going on in their lives, people can very easily forget to take their medicines on time. That goes for youngsters who have to worry about balancing school, extracurricular activities & their social lives, adults who spend a huge chunk of their day working and traveling, as well as senior patients whose memories might not be serving them too well.
A WhatsApp chatbot could be used to send reminders out to them whenever they have to take their medicines so that they take them on time without forgetting, thus keeping them in a healthier state and helping them recover in a faster manner from whatever ails them.
6. Making payments
Waiting in line at a hospital to book medical consultations and pay for them can be quite annoying. This is especially true when people have to come early, wait in line, and then figure out whether they want to go home and come back for their appointment or just wait at the hospital or clinic for an hour (or a few) till it’s time for their appointment.
You can ease this pain by simply allowing people to book appointments and make their payments directly over your WhatsApp chatbot. And since they would pay in advance for the appointments, the chance of them missing their appointments would be greatly reduced.
7. Providing support and relevant information
When you use a WhatsApp chatbot for healthcare, you can provide instant responses to your patients’ queries, especially the FAQs which keep coming in all the time and don’t need personal attention from medical staff. These repetitive tasks can be handled by your AI-powered chatbot, right on WhatsApp when you have access to the WhatsApp Business API.
This allows you to provide healthcare services faster, free up time for your healthcare professionals to focus on tasks that would create more value for your patients, and even improve your healthcare organization’s customer satisfaction levels in a more efficient manner.
Once again, these chatbots are not trying to replace healthcare providers, their purpose is to help automate simple patient queries that do not require the attention of a healthcare provider. If any queries need personal attention from healthcare professionals, these queries can be transferred seamlessly to them via the live chat functionality.
8. Uploading documents
Patients can use the WhatsApp chatbot to send copies of necessary documents directly over the bot instead of having to email them, upload them on the healthcare institution’s website, or carry them along for their visit, thus reducing the fear and eliminating the consequences of having left their documents at home, which leads to higher levels of customer satisfaction. Chatbot technology makes it possible for patients to upload their documents on popular messaging apps like WhatsApp, and through integrations, these documents are automatically stored in the healthcare companies’ databases.
9. Storing the patients’ health information for doctors to access it
You can integrate your WhatsApp chatbot with your database and all your systems to collect all your patients’ information and medical history in one place so that doctors can access it easily without needing to hunt through a storeroom full of files and can make well-informed decisions at a faster pace, thus serving their patients faster and better, and even saving lives because the patient’s medical history can be accessed in a speedier manner.
Integrating your chatbot with your backend systems even reduces the time spent on data entry.
10. Sharing digital copies of prescriptions and health records
If your patients need medical attention when they’re in a whole different part of the country (or even another part of the world), they’d need access to their prescriptions and health records. If they don’t have physical copies on them, you should make it possible for them to request and download digital copies of these in an easy manner. And what’s easier than sending a quick message over the app that they use the most?
Make it easy for your patients to get access to the right healthcare services wherever they are by letting them access their prescriptions and medical history directly over a WhatsApp chatbot.
11. Mental Health Counselling
Conversational chatbots making use of NLP can be used to supplement the work of mental health professionals. They aren’t going to replace licensed therapists, but rather, they’ll augment their work. These chatbots can even perform cognitive-behavioral therapy (CBT) to some extent.
WhatsApp healthcare chatbots vs COVID-19
WhatsApp chatbots can be used to find slots for vaccinations and to identify testing centers in the patient’s vicinity. COVIDAsha even uses an AI-powered chatbot deployed on WhatsApp, Facebook Messenger, and Telegram to connect citizens with suppliers of critical medicines and medical facilities. It has even been highlighted in the national news on NDTV because of the bot’s ability to serve rural India in 7 regional languages.
If you’re looking for tutorials about Swift, Kotlin, React, and more, check out our developer portal.
The Sendbird chatbot sample code may help you. For additional guidance, check out our docs. Here’s a general Sendbird chat demo and details about Sendbird chat.
Introduction
This tutorial will explain how to use the Sendbird API for Bots to receive a message from any channel, send it to Dialogflow, and respond.
Figure 1. Sendbird chatbot architecture diagram
By the end of this tutorial, you will understand how to build the entire flow in the architecture diagram above. This flow consists of the following steps:
The client sends a message to the Sendbird Bot Sync Server.
From the Sendbird Bot Sync Server, we send the message to Dialogflow using the Dialogflow APIs for NodeJS.
Dialogflow will process this message and activate Agents & Intents to give a response to the client.
The Bot Sync Server will receive this message and send it to Sendbird using Sendbird’s Bots API.
Finally, Sendbird will deliver this message to the user’s chat.
For this tutorial, you will need:
A Sendbird account with the Bot feature enabled
NodeJS (with express) to build our Bot Sync Server
A Dialogflow account
Sendbird and Dialogflow are mandatory, but you can replace NodeJS with any other server platform/language you like. In this tutorial, we have used the words ‘chatbot’ and ‘bot’ interchangeably — remember that they mean the same thing.
This tutorial assumes familiarity with NodeJS since this is what we use in our example. Remember that a good understanding of chatbot building will help you make the best use of this tutorial.
With this in mind, let’s get started.
Step 1. Dialogflow configuration
First, we need to configure Dialogflow. We will start from scratch and detail each of the steps to go through, including how to:
Log in to Dialogflow with your Google account
2. Create a new agent: a. Get your credentials b. Save your project ID c. Save your credentials d. Create a service account e. Select permission & role
You should see the following screen once you sign in:
Figure 3. Dialogflow main window
1.2. Create a new agent
An agent in Dialogflow will receive the information from the Sendbird bot. The agent will process this information and send a response back to the users in the chat. This can be complex, but for this tutorial, we will use the basic default information.
Click on the hamburger menu at the top left. Hover over APIs & Services, and then click on Credentials.
Figure 8. Accessing the Google credentialsFigure 9. Google credentials: Create new
1.2.4. Create a service account
To do this, click on the + CREATE CREDENTIALS button at the top of the screen.
Figure 10. Creating credentials for your service account
Enter any value for the Service Account Name, Service Account ID, and Service Account Description. Then click the CREATE button.
Figure 11. Service account information
1.2.5. Select permission and role
Select Owner, as displayed in the following screenshot:
Figure 12. Service account: Assign permissions
Click CONTINUE and then click on DONE.
Figure 13. Service account: Finish process
Once you click on DONE, you will see your Service Account at the bottom.
Click on this Service Account. You will see a new screen:
Figure 14. Credentials created
Click on the Email field at the bottom to go to the next screen and create a new key.
Figure 15. New key
Select JSON and click on CREATE. You will be prompted to save a JSON file. This JSON file contains the information you can use later for creating a Google Session ID. We won’t use this in our NodeJS project, but knowing this could be helpful in the future.
Finally, click on the blue SAVE button to confirm all changes.
Google will ask you to download a JSON file. This file has a structure like the following:
Run the following command for Google to identify your project:
Note: Take your time. This process from Google is very tricky.
Once you run that command, a browser window will open. You need to authorize your Google account and allow the use of this service. After that, Google will create a new JSON file for you. If you don’t have this information correct, you will receive an Error 400.
Copy the value from client_secret and populate GOOGLE_SESSION_ID below in the NodeJS code.
Figure 18. Define the Dialogflow project ID and authorization token
Note: Grab your project ID from Dialogflow (taken from the Dialogflow configuration, section 1.2 2.b.)
4.4. Create a test Group Channel from the Sendbird Dashboard
Go to your Sendbird dashboard and access any of your Group Channels. We will create a new one here.
Figure 19. Create group channel from Sendbird DashboardFigure 20. Group channel created
As you can see, my new channel is called bot-channel, and its URL is bot-channel-url.
Click the bot-channel-url to enter this channel:
Figure 21. Group channel messages view
4.5. Create a new bot
The next step is to add this to create a bot. We will send a POST request to our Bot Sync Server.
Note: For all bot operations, we use the Sendbird Bot API. Check out how to create a new bot here:
Go back to the code and install all libraries:
npm i
Once all libraries are downloaded, run your Bot Sync Server:
npm run start
Once our server is running, we will send a POST request to create a bot called bot1.
You can use Postman to send POST requests. The most critical parameter is called bot_callback_url. It refers to the callback Sendbird will invoke when a message is sent to the Group Channel. This callback URL must be accessed from the Internet.
To accomplish this task, you can upload this NodeJS to any server like AWS, Heroku, Github, or any other service you are familiar with. For this example, I will use NGROK. NGROK creates https://b1b85fc97d18.ngrok.io, which points to my local server http://localhost:5500
The next step is to add this bot to your new Group Channel. To add a bot to a Group Channel, we use the Sendbird API. Check out our documentation here.
If all went well, you should have the following response:
Figure 22. Postman response
And the following message in your Sendbird dashboard:
Figure 23. Sendbird Dashboard view
Step 5. Test the full flow
It’s time to test our flow! Send a simple “Hello” message from your dashboard. This message will trigger the webhook running on your local computer with NodeJs:
Replace b1b85fc97d18 with the ID you receive from your NGROK application.
Our bot will grab this message and send it to Dialogflow. Dialogflow will respond.
Our bot will receive this response and send it back to the chat channel. The response will be displayed as a new message in the dashboard.
Figure 24. Final results
Conclusion
In-app chat is engaging for users, and it can be even more efficient with bots! The integration of the Sendbird API with 3rd-party services leads to robust implementations. In this tutorial, we learned how to automate Sendbird chat responses with Dialogflow. Note that it will work on any device, and you can choose the programming language you prefer — from Android to React, to Angular, to .Net, etc. All you need to do is send HTTP requests to your server. Check out some other examples of enabling chat messaging for Salesforce support agents and connecting an email service to chat with Mailgun. The possibilities are endless!
If you want to see a history of messages sent to Dialogflow, Google has a dedicated section that you can access from the Dialogflow console:
