Idea

Marco Burato avatar image
Marco Burato suggested

Custom Skills without invocation name

The idea with voice control and virtual assistants is to be able to do certain things using a natural language, like if we were talking to another person. That's the power of it.

The problem with Custom Skills is that an "invocation name" is required to route the intent to a specific skill. This doesn't feel natural at all. For instance, if we had a real personal assistant, we would ask him/her to check our appointments, find a flight, etc and we would definitely not use phrases such as: "Check if I have any appointment for tomorrow from Fantastical" "Find me a flight from XXX to XXX for next Saturday using Sky Planner"

The "standard" intents to switch lights ON/OFF, set temperature, lock doors, etc. are an example of common sentences that are much more convenient to use now than before, when the user had to "manually" specify the skill to make it happen. Amazon is adding new "standardised" APIs for these common sentences, and that's better than nothing. However, this only happens as a reaction ("uh, many people are saying this, we probably want to make that easier"). As a Developer, I believe this is a turnoff: voice-controlled devices really need the freedom of natural language to explore new possibilities and experiment new features.

With all of that being said, I reckon that the problem here is to understand which Skill to use to handle a specific user request.

My proposal is to: 1. when the user says something that Alexa doesn't know how to process, the Skills are checked for one which supports the request 2a. If a Skill is matched, Alexa passes the intent to it 2b. If multiple Skills can handle the request, Alexa can ask which Skill to use among them and, the first time, ask if that Skill should always use that one for the future or keep asking. ... and that's is really. The current intent schemas and sample utterances could already contain all the needed info.

alexa skills kitvoice-user interface
10 |3000 characters needed characters left characters exceeded

Up to 2 attachments (including images) can be used with a maximum of 512.0 KiB each and 1.0 MiB total.

newuser-1adb3d04-1f99-42b1-acb8-89c825dd9bc7 avatar image
newuser-1adb3d04-1f99-42b1-acb8-89c825dd9bc7 commented

I think of a second possibility to control Alexa over a table.The first column contains the spoken text and the second column contains the text interpreted by Alexa as order.

e.g. Logitech Harmony.

speak: Alexa make louder

the order send to Alexa: make TV louder with Harmony.

So it is easier to define specific commands which can be better implemented by alexa.
10 |3000 characters needed characters left characters exceeded

Up to 2 attachments (including images) can be used with a maximum of 512.0 KiB each and 1.0 MiB total.

newuser-c80a13a9-837f-4b67-830e-21d794e54883 avatar image
newuser-c80a13a9-837f-4b67-830e-21d794e54883 commented

Every "Alexa" user should be able to simply link any "text" .. e.g. "ask aquarium to turn pump" to a "pseudo skill" .. in this case "pump" . He or she could then simply say "alexa pump on" and it would be translated to "[alexa ask aquarium to turn pump] [on]". This would open a whole new world of possibilities were people link the skills they like or use most to make the invocation much more convenient and realistic.

10 |3000 characters needed characters left characters exceeded

Up to 2 attachments (including images) can be used with a maximum of 512.0 KiB each and 1.0 MiB total.

Write a Comment

Up to 2 attachments (including images) can be used with a maximum of 512.0 KiB each and 1.0 MiB total.

Your Opinion Counts

Share your great idea, or help out by voting for other people's ideas.