I am trying to build a chatbot using wit.ai. I have managed to make intent and their values with different questions but i am unable to understand that where to put answer of every intent. I mean how to form a dialogue or conversation system as there is not stories tabin current wit.ai.
I saw different Tuts where stories tab (in beta format) available (to make dialogue) but in current site it is not available.
The stories feature has been deprecated.
More information here.
If you want something similar, maybe have a look at api.ai
Related
I want to build a similar post recommendation system that a user sees after performing some activity on the news feed. For example: If he/she spends more time on sports posts, giving him/her sports recommended post so I would like to get help on what kind of dataset do I need to build a post recommendation system that a user likes to see. I am confused on should I build a dataset of my own if yes how can I build these recommendation posts? Thank you in advance!!
Hello and welcome to the forum! I recommend against building a dataset of your own as real world datasets have certain properties (distribution, missing data, noise) which are quite hard to replicate artificially.
You included Kaggle in your tags. Why don't you use it? It looks perfect for the job. Here's a list of options with the #recommender-systems tag.
This one and this one are about films. This other one is about user interactions with a news platform.
If this answered your question, please don't forget to accept it by clicking on the Tick button at the left of the answer. Have fun!
I am getting frustrated with Google's Play store. My app won't appear in searches (at all). There isn't a "new this week" section where users can find new stuff from indie devs such as myself. Top results usually include hillarious reviews that smell fishy
I contacted Google and they said that I can pay them money to appear in top searches (via ads) and this way improve my "market strategy". I am just trying to share my free app so that others can use it, I have no market strategy
As a result, I am going to focus on my Apple Store version (which is performing much better). I am also exploring the option of publishing on Galaxy Store, Huawei Store, etc
I tried uploading to Galaxy Store but upon submitting the app I get the following error:
The registered binaries do not meet the category conditions for Galaxy Specials
Looking here I can see that something needs to be added in the manifest file. Is there a way to do this via build hints in CodenameOne? I also read that a "Galaxy SDK" needs to be added somewhere. Is this a prerquisite and if so, how would one add it in CodenameOne?
I haven't tried this but this might work, add the build hint:
android.xpermissions=<uses-permission android:name=”com.samsung.android.providers.context.permission.WRITE_USE_APP_FEATURE_SURVEY”/>
If the build hint already exists then just tack this string to its ending.
I have written a smart speaker app for Google Home using DialogFlow, and am now in the process of porting it over to Alexa.
One of the fundamental differences seems to be the inability to easily trigger follow-up intents. For example, I have a dialog that asks the user a series of questions, one after the other, before providing a result based on the answers provided. e.g. ({slot types})
Do you like a low maintenance or working garden? {low maintenance}{working}
Do you like a garden you can relax in? {yes/no}
Would you like to grow vegetables in your garden? {yes/no}
This is easy to achieve using DialogFlow follow-up intents, but I have no clue where to start with Alexa and there dont seem to be many examples out there. All I can find seems to focus on slot filling for a single dialog.
I am using my own API service to serve results (vs Lambda).
Can anybody recommend a way of achieving this in an Alexa Skill?
I managed to achieve this by adding a single utterance with three individual slots, one for each of the answers required:-
inspire me {InspireMaintenance} {InspireRelax} {InspireVeg}
These Slots back onto one SlotType - Custom_YesNo, which had Yes and No values + synonyms. My C# service then checks for each of these required slots and where one is missing it triggers the relevant question as a response. Once all slots are filled it provides the answer.
Not as intuitive as Dialogflow and requires code to achieve what can be done without code in DF, but at least it works :)
Apologies for posting a basic question and not a detailed programming problem! Alas, IBM send people here for BlueMix support.
We're evaluating different AI Bots, and with Watson what we want to do, I think, is use Alchemy to analyze our web site, and have a chat bot that can answer random questions using general knowledge as well as what Alchemy has learnt from our site.
But, I can't find an example of how to hook up Alchemy to a chat bot. Could any of you point me in the right direction? I'll try to come back with more difficult questions another day!
I think, is use Alchemy to analyze our web site, and have a chat bot that can answer random questions using general knowledge as well as what Alchemy has learnt from our site.
There is two ways to do this.
You can create a controller that sits in front of Alchemy API + Dialog. The user talks to the controller and it sends the information to Dialog. Dialog can then request a lookup to the controller. This option is only useful if you don't expect Dialog to be maintained at a later date (or you are using earlier versions of WEA).
The better option is to use the FUNCTION call within Dialog. This will allow you to talk to a third party system and get information back to work with.
Once you have your data returned, you can use your tags or keywords within the returned data to activate a particular process flow using SEARCH.
One thing to be aware of is that depending on the answer you need to determine how to present it.
If your corpus is stored as conversational, then you can use the content as-is. If it is stored from documentation, then you should have Dialog talk as if it is reviewing the content and coming back with an answer. The latter should be visible in a way that distinguishes it as separate from the conversation.
I want to push card into my app in the Google Glass, and not to the timeline, my app in the glass contains cards with names of friends, I want to give ability to each one of the friends sending card under the friend name.
I will be happy to know if this behavior allowed, Thanks.
It depends exactly what you mean. In general, it is best not to think about specific apps when it comes to Glass, but rather to think about actions that take place using Glass. So instead of "starting" an app that shows the names of each person, we might instead think about wanting to send a note to that person and have that person be on our contact list to get a note if we wish to send them one.
Doing it this way, your Glassware needs to create and maintain contacts and register them with the TAKE_A_NOTE action. See https://developers.google.com/glass/v1/reference/contacts for more details.
It isn't clear what you are trying to do exactly, but it sounds like you might be able to use card bundles as well. Take a look at https://developers.google.com/glass/develop/mirror/static-cards#bundling_cards to see if this scheme will work for you.
If you're not doing it either of these ways - you may need to update your initial question to clarify how you are starting and running the app itself and how you picture the entire workflow.