I'm using IBM Watson Assistant and I have built a very good and functional chatbot and I want to make even better.
I'm trying for a while to find a dataset to import entities and intents for IBM Watson Assistant. I have already found some data from datasearch google and other sites but I'm searching for booking system and customer support data. Is there any site that I can find the right format for Watson or any data from the above.
Usually the trained intents and entities are customized within each company for its use-cases, and it will be hard to find a ready plug and play intents that fits your usecase 100%. But you can get the data to start training Watson assistant yourself using examples from datasets available on Kaggle.
Related
I have been asked to develope integrations solution for Sage People application which is a HRMS tool build on Salesforce platform. Integration capabilities of Sage People are poorly documentation and limited to file based integrations only . Sage people objects are showed as managed objects in Salesforce. I just want to confirm the possiibility of whether I will be able to use Salesforce Apex functionality to receive Data from external API and change records in Sage People.
Even in the manage packages, it is possible to change the records. Apart from that, it is also possible to change the fields on the manage package objects. To use in the API you may write custom API or use the standard API
Does the IBM Watson question answering system that won the Jeopardy game in 2011, support dialogue with users in its new versions?
I think you are referring to Watson Assistant, which is the 4th generation Q&A / Dialog / Conversation / Assistant service.
You can find a demo at the bottom of the page at
https://www.ibm.com/cloud/watson-assistant/features/
and getting started instructions at
https://cloud.ibm.com/docs/services/assistant?topic=assistant-getting-started#getting-started
If you opt for the plus or premium price plan then you can make use of search skill, which cribbed from the documentation -
When Watson Assistant doesn't have an explicit solution to a problem,
it routes the user question to a search skill to find an answer from
across your disparate sources of self-service content. The search
skill interacts with the IBM Watson™ Discovery service to extract this
information from a configured data collection.
If you already use the Discovery service, you can mine your existing
data collections for source material that you can share with customers
to address their questions.
However, you do not need to have a Discovery service instance. If you
choose to create a search skill, a free instance of Discovery is
provisioned for you. You can then create a collection from a data
source and configure your search skill to search this collection to
find answers to customer queries.
If you don't have a plus or premium plan then its still possible to craft in the Discovery search into your application using either your own orchestration or a cloud function.
We look forward to maximise the use of Watson in our project. For this purpose we have to educate waston with all project documents, User manuals etc and use the Watson Conversation API possibly. But this seems a manual process of creating entities, intents and then dialogues. Is there a way Watson can identify potential entities and intents on its own? Or some way of automating or fast tracking the process of identifying entities, intents and creation of dialogues.
Can RPA (Robotic process automation) tools such as WinAuto or BluePrism be combined to use for this purpose ? Please suggest.
Thanks.
Depending on what you're seeking to do, Watson Conversation Service may not be the right answer for your use case.
What I read, looks more like a case for Watson Discovery Service, possibly combined with Watson Knowledge Studio.
You can read more about it here: https://www.ibm.com/blogs/watson/2016/12/watson-discovery-service-understand-data-scale-less-effort/?spMailingID=27478889&spUserID=MTY4Mzc0OTEyOTIxS0&spJobID=960800840&spReportId=OTYwODAwODQwS0
And secondly on the integration:
https://www.ibm.com/watson/developercloud/doc/wks/wks_mapublish.shtml
In the API documentation it states that methods are available to create all artefacts (workspaces, entities, intents, dialognodes etc..)
https://www.ibm.com/watson/developercloud/conversation/api/v1/?curl#update_workspace
But the SDK's don't support it yet (at least the Java SDK)
Are there any cloud hosting solutions for geospatial data? I am currently writing a directory style app where businesses can sign up and then users can find nearby ones.
I am considering Google App Engine for this, but from what I can tell the GeoModel code is quite expensive (up to tens of thousands of dollars a year) to run since Google updated the pricing of App Engine. It doesn't seem like App Engine's database is really suited to this kind of query (though the SQL solution may be an answer).
I was hoping to find a service where I could send off a HTTP request to add data (a business' id, name and icon url) to a database, and then another one to find a list of businesses that are nearby to a given point. A service is preferable as this is work done for a client and we would like the solution to be managed with as little interaction from us or the client needed as possible.
EDIT:
I just found cartodb.com which uses PostgreSQL and is reasonably priced. Are the any other alternatives?
The App Engine Search API (currently in Experimental) supports GeoPoints and geosearch, and is great for exactly the kind of query that you describe.
See the Google Developers Academy (GDA) App Engine Search API classes for a bit more info and an example as well.
http://www.iriscouch.com/ is a cloud-based host for CouchDB and they support the geocouch extensions for CouchDB to store geoJSON data and perform spatial queries.
We have decided to go with cartodb.com because it looks like they have a good price to ease of use ratio.
You mentioned going with CartoDB, which is a good choice with a nice UI.
Just adding, if you were just looking for a scalable backend, you could use StormDB. It is a cloud hosted SQL database with geospatial extensions. You data is automatically distributed amongst multiple nodes for write, read, and parallel query scalability.
In my CS course project this fall, we have to build a little eCommerce app (like Amazon, eBay, etc). We are free to build any type of eCommerce/store app. Since I don't have a preference for what app to build, perhaps it may be easier to decide based on freely available sample data for the store. So is there some freely available dataset available that represents a set of products, like groceries, movies, books, cars, apps, electronics, weapons, library, etc? It doesn't have to be real but as long as it can save me a few hours of entering data, it will be worthwhile. An open data format for the dataset would be useful, a MySQL database would be great.
Perhaps I should use the Northwind database from MSSQL?
Is there a "Northwind" type database available for MySQL?
I haven't looked at all the reference in this post but it looks promising: Where can I find sample databases with common formatted data that I can use in multiple database engines?
Any suggestions eCommerce sample datasets?
At this link you can find some e-commerce datasets in Comma-Separated Values format, namely some snapshots of Amazon, Google Products, ABT and Buy.
http://dbs.uni-leipzig.de/en/research/projects/object_matching/fever/benchmark_datasets_for_entity_resolution
You can try the nopCommerce sample data. Download from http://nopcommerce.codeplex.com. During installation, tick the "create sample data" box. You can then use the data within your own application. The schema is pretty easy to understand.