Facebook PixelAI-powered estimated waiting time for better scheduling of customer appointments
Create newCreate new

AI-powered estimated waiting time for better scheduling of customer appointments

Image credit: Martha Dominguez de Gouveia

Darko Savic
Darko Savic Jul 21, 2021
Please leave the feedback on this idea

Is it original or innovative?


Is it feasible?


Is it targeting an unsolved problem?


Is it concisely described?

Bounty for the best solution

Provide a bounty for the best solution

Bounties attract serious brainpower to the challenge.

Currency *
Who gets the Bounty *
Any business where customers come in via appointments at a specific time needs to be good at predicting how much time each appointment will take before the next person should be scheduled. If people come in for an appointment but then have to wait they get frustrated and might consider going to competition next time.

The idea is to have an AI algorithm watch your scheduling predictions and gradually become better at it than you are. Eventually, the algorithm could manage the time-slots and keep adjusting them based on the latest experience.

This software could be coupled with hardware (camera) that counts people or a button/pedal that the receptionist clicks whenever a new customer enters or exits. Turnkey solutions could be sold to private medical practices and any other business where customers come in via appointments.

Less queuing = fewer unhappy customers.
Creative contributions

Better inputs for AI for more precision

Shubhankar Kulkarni
Shubhankar Kulkarni Jul 22, 2021
I like the idea, @Darko!

If the AI counts the number of people going in and coming out, the only information it would be able to extract is the average time a client takes in a meeting. For more precision, how about recognizing the clients and categorizing them. For example, if you could categorize them by age and then calculate the average time spent by an age class in the meeting, you could (slightly more) precisely determine how much time an appointment with a future person of the same age class might take.

Also, if there is a microphone that recognizes the voices in the meeting, it could be able to divide the time of the meeting into that spoken by the client vs the officer. If the conversation is highly confidential, a simple wavelength sensor could be installed that cannot identify the words but can identify who is speaking. The time of the meeting is noted. When the same client books another appointment, the time of the meeting could be more precisely predicted.

The meetings could be further categorized by the reason of the meeting. Some reasons might take more time than others. For example, "meeting a new client to listen to their terms" might take more time than a "casual in-office lunch with a friend".

If an important client, whom we do not want to lose, is consistently late for the meetings, that client's meetings could be scheduled 15 minutes or half an hour early (depending upon how late the client usually is), overlapping with the previous client, thus, saving time.

Also, all these inputs when used together could lead to another level of precision. Using these inputs, finer categories could be made, for example, "a 40-year-old male coming for a casual meeting" or "a 30-year-old woman coming with a business proposal". Based on the "appointment time" history of these categories and the personal history of each client, the future appointment time could be precisely predicted.
Please leave the feedback on this idea
Povilas S
Povilas S3 years ago
I might be wrong, but I think something along those lines is already used, especially in business sector almost certainly, cause as Darko Savic said - their success depends on that. I'll take healthcare sector as an example (I initially thought the session is about that). From my experience, if it's a good enough hospital/clinic (even a public one) and not a total mess, the waiting times are more or less accurate, meaning you don't have to wait long if you come on time. It seems logical that they should be using some kind of system to calculate this, otherwise it would be a disaster, if you'd just approximate the waiting time and assume everyone is taking 20 mins on average, this wouldn't work, for it to be more precise, they have to take into account additional factors. The majority of clinics are probably not using an AI for this, but some general system taking a few factors into account is most likely used as my guess. But of course, there's room for improvement.
Please leave the feedback on this idea
Shubhankar Kulkarni
Shubhankar Kulkarni3 years ago
Povilas S You might be right, but I have not experienced any such scheduling method. I think they consider the average time a client/ patient spends. It is accepted that when you visit a clinic or a hospital, you have to wait your turn. Even if you have an appointment, you reach there on time or a couple of minutes early and wait till the person inside leaves, which may be later than the time you were given. People sit outside the main office and a receptionist or a nurse calls you in when it's time. They probably call such areas "waiting rooms" for a reason 😂 .
Please leave the feedback on this idea
Povilas S
Povilas S3 years ago
Shubhankar Kulkarni Yes, but if you think from a wider perspective - they make schedules well in advance, so let's say you have to make a schedule for all day's patients visits - you assume one person will take 20 minutes (based on the averaged time), then someone takes 40 min instead of twenty, if you have three such people, the person coming in the evening will have an hour delay, so will have to wait for an hour even if coming on his/her designated time.

Hopefully, some people will take less and the time will balance out, but on a "bad day" the people at the end of the row could end up waiting for a few hours (you can fit 20-30 patients or more in a day, depending on clinic's working hours, so the delay might become huge). So I'm not sure if counting only on average visit's time wouldn't turn the whole process into a total mess.
Please leave the feedback on this idea

Easier estimation of waiting time using AI-mediated pre-doctor questionnaires

jnikola Oct 17, 2022
Each patient could be questioned by an AI doctor through a chat on the web platform or an app. The questions would be designed by following the question routine of many doctors over some time. The questions would be at first general and then more and more specific and would mimic the questions asked by the doctor almost perfectly.
The doctor would then get the chat history to quickly roam through the chat and invite the patient in to ask him additional questions and give him an opinion or prescription. The chats could even be interpreted by an AI and a summary could be delivered to a doctor to speed things up.
  • Most of the time people spend at hospitals is waiting
  • The second longest procedure is the questioning of the patient
  • The shortest one is the doctors comment and writing prescriptions
  • AI-chats could be very precise and extract the most relevant info from any patient
  • reduction of the doctors mistakes in questioning due to speed and tiredness
  • reduction of waiting time since patients would spend less time in the doctor's office
Please leave the feedback on this idea

Add your creative contribution

0 / 200

Added via the text editor

Sign up or


Guest sign up

* Indicates a required field

By using this platform you agree to our terms of service and privacy policy.

General comments