I want to develop one robot using watson conversation, this robot can answer some frequently asked question about my application. Here is my thinking, every question has its own intent, and the answer will be returned by response. but I have over 50 questions, that means I need to define over 50 intents, but watson conversation limited 25 intents for one workspace. Does anyone have any idea about how to resolve it? Thanks.
There are two options for you
Purchase Standard plan ($0.0025 USD/API call)Includes upto Up to 2000 Intents.Check out more on pricing here
Link similar questions together and try to reduce the questions.For example, take two questions regarding Bank withdrawals and Bank deposits could be asked in one intent as Bank transaction and then put type of transactions as entities(dialogue box condition as entities).
And besides that limit, there is another one: max 1000 API queries/month. It if fine for a proof of concept or to development phase. If you intend to go to production, you should purchase a plan. https://www.ibm.com/watson/developercloud/conversation.html
Related
I am working on a research project based on the six degrees of separation theory (based on the works of Stanley Milgram 1967 and later, Duncan Watts 2001). I just wanted to plot the connections of every user part of the study.
I wanted to show a users connections list, from LinkedIn. I read that there was something like a peoples API which could be used, but I think it is deprecated now. Is there any way of getting a users list of connections, even if we take the users permission?
I also read that there is something like a LinkedIn partners program, I cannot find much information about how I can apply for it.
I have been playing around with One Signal & Firebase Push Notification.
I am almost sure One Signal cannot help me and am starting to feel Firebase might also not be able to help me.
We have a web app that allows regular authors to post articles. It also allows users to comment on the article using Firebase synced realtime database.
I want to create functionality where users can get a push notification for article-specific comment treads. The room ID will be the article ID. If both allow push notification generally from our app and has commented on an article, they subscribe to this article comment tread solely. They can also click a button at this specific article comment thread and unsubscribe to this article comment thread if they want.
So we may have thousands of articles and hundreds of comments in each article, to put it lightly.
I quickly moved away from One Signal when I didn't feel like I could have a separate "Segment" for each article, I wasn't certain this is allowed? Thoughts there?
Throughout my exploration of Firebase I just came across this comment in their documentation in relation to groups (Which I was hoping could be my article room).
"The maximum number of members allowed for a notification key is 20" found here. A key is a group key from my understanding. This won't work because what if there are more than 20 users in a comment thread. I looked up the most popular commented threads ever to find numbers like 500. This means my system would have to be able to support large numbers of users per article tread.
Additionally One Signal Tags and Social activities look like could be investigated, but my general question is not specific, its more a wider general question. I am hoping someone with experience can give some guidance and good tips on best way to approach this problem. Are Push notification even allowed on such a scale I am wondering?
A scaling examples
1000 Articles with 100s of different users commenting on each article. A user may only receive a push notification on articles which he has commented in only.
(Assuming he has allowed push notification site-wide first and not blocked us or unsubscribed from the site entirely. Subscribing to the site doesn't automatically subscribe you to anything specific, just means you willing to be subscribed to something and have control which things easily)
Ok thanks for reading and looking forward to hearing from someone with this experience and share their experience.
Daniel Gadd # GaddBox
Maybe it's a bit late.
You have to use topics.
FCM topic messaging allows you to send a message to multiple devices that have opted in to a particular topic. You compose topic messages as needed, and FCM handles routing and delivering the message reliably to the right devices.
In your case, every Article is a topic.
I have defined an intent in Watson Assistant using the following training examples:
adieu
au revoir
bye
bye now
ciao
cu
cya
exit
farewell
good bye
have a nice day
I'm leaving
later
quit
see you
so long
stop
we are done
A user inputs the word "again". Watson returns a match to this intent with a confidence level of about .9
The word "again" does appear in a training example for a completely different intent, namely "I'm looking forward to working with you again! :)". It does not appear in any other training example.
What is the reasoning used by Watson Assistant to arrive at this match and with such a high level of confidence?
There is a whole load of factors that determine why an intent is picked over the other.
Intents do not work properly if you have <= 2 intents.
Any entities you have created that are referenced in the example questions can also impact what is picked.
Contextual entities will also add weight to the POS of those entities.
Number of intents and how frequently the word is used across those intents can also impact the scoring.
Watson Assistant always tries to get meaning from the term where it can.
When trying to determine why it picked one intent over another, you need to look at both. The intent you mention may not even be the second one picked.
With just one intent shown above it's hard to say the 'Why', so this is just an educated guess as to what may be happening.
"again" is a single word and by itself has no context to determine an intent. The closest in the list would be "later".
It couldn't find any meaning whatsoever in a single word, so looked at the intent with the most single word examples, as possible reason to pick it.
That aside, you should try not to answer real 1-2 keyword based questions. There is almost never any context that a person could answer, so it's unlikely WA will be able to either.
Was wondering if anyone has crossed upon this problem:
Using MSFT Cognitive Services Face API to persist Person Groups, Persons and Person Faces
Am sending an image to the Face-Identify API and receiving a candidate list that includes "phantom" personIds that are not persisted by me and are not listed in the person group used for identification.
When I run List Persons in a Person Group API I don't receive that personID.
Overall everything is working but for some images I get these invalid responses.
Any clue would be appreciated.
Hello from Microsoft Cognitive Service Face Team,
And really sorry for the inconvenience cause by our current training strategy. AFAIK, it is still computation/time cost to train a person group, that is why we make it as an asynchronous call and need training again after the person group is modified.
If you have any further problem, please feel free to update.
I need to understand the accounting entries that are created in Oracle ebs. For example, when we talk about a standard P2P cycle, there are certain accounting entries created right from the moment a purchase order is created, approved and received.
I have basic knowledge of debit and credit entries. But when it comes to making debit and credit entries in Oracle apps, when I look at the accounts being used, I can not apply the basic dr cr entry rules to the accounts.
Please advise on this. Kindly also suggest some resources from where I can obtain this information.
This isn't a simple answer as the DR and CR entries are all driven by the accounting setup. To use your example, when a PO is created, very little accounting is done. It isn't until the line is received and Create Accounting is run that debits and credits are really applied based on how the accounting rules are set. If you were to open a PO, click "All Distributions", select a line and then click Tools > View Accounting Events, you'll see the detailed debits and credits that the accounting setup has created.
I'm not sure what your role is (developer, analyst, accountant etc.) or your experience level, but I would suggest you familiarize yourself with the accounting setup of your organization to be able to truly understand it. My suggestion is to get a Financial Super User responsibility in your development environment and ask one of your Financial Analysts to show you the basics of your account setup.
If you really want a deep dive, login to your My Oracle Support account and start looking at the documentation (Doc 1597048.1). The user guides are exhaustive but very helpful when you get the right one.
The debit and credit depends on the accounting rule setup.
In simple terms:
Inv Validated:___Dr-------Cr
Inv Exp...............100
Liability...........................100
Inv Paid:________Dr-------Cr
Liability........100
Cash................................100
There can be several steps in between depending on the Accounting rules, like Encumbrance accounting.