1
00:00:00,000 --> 00:00:03,521
[MUSIC]
Welcome back we're now going to zero in on

2
00:00:03,521 --> 00:00:08,362
the important things that you need
to know to build a chat bot using

3
00:00:08,362 --> 00:00:12,238
the conversation service
that we created earlier.

4
00:00:12,238 --> 00:00:18,048
>> The first thing we should do is get a
bird's eye view of what we're building and

5
00:00:18,048 --> 00:00:21,018
what the overall ecosystem Looks like.

6
00:00:21,018 --> 00:00:26,693
We have provided you with a sample web
app that will be the client in this.

7
00:00:26,693 --> 00:00:31,952
The web app is using some Watson SDKs to
make it very easy to communicate with

8
00:00:31,952 --> 00:00:36,980
the Watson APIs available along
the Watson Developer Cloud over here.

9
00:00:36,980 --> 00:00:41,517
Users will input text into
our simplified app, but

10
00:00:41,517 --> 00:00:47,003
not that Watson can process text,
voice, and visual input.

11
00:00:47,003 --> 00:00:53,479
Our app will first pass the input data To
a new conversation service that we create.

12
00:00:53,479 --> 00:00:59,037
Each time we use a service from Watson,
we create our own instance to connect to.

13
00:00:59,037 --> 00:01:03,779
That allows us to train our unique
instance with our own custom data.

14
00:01:03,779 --> 00:01:08,444
The conversation service processes
the input using its underlying

15
00:01:08,444 --> 00:01:11,510
natural language processing technology.

16
00:01:11,510 --> 00:01:16,732
Later we'll see how to communicate
with more than just one service.

17
00:01:16,732 --> 00:01:19,342
As we go along and build this part,

18
00:01:19,342 --> 00:01:24,294
it will help to think about how it
fits into this overall picture.

19
00:01:24,294 --> 00:01:30,373
Then, now seems like a good time to
point out that IBM has a variety of And

20
00:01:30,373 --> 00:01:36,620
s available to make it easy for
you to get started on a new p[roject.

21
00:01:36,620 --> 00:01:41,600
No matter what you are working on,
the are available

22
00:01:41,600 --> 00:01:46,482
on and helpful are available on this page.

23
00:01:46,482 --> 00:01:51,680
Both of these links are available for
you in the teahers notes.

24
00:01:51,680 --> 00:01:56,669
Back in our diagram,
let's zoom into the conversation service.

25
00:01:56,669 --> 00:02:01,927
Like a regular conversation,
a conversation service with Watson has

26
00:02:01,927 --> 00:02:07,539
some key elements in the speech or
text that are needed for understanding.

27
00:02:07,539 --> 00:02:12,529
The Watson conversation service
defined these parts as intents,

28
00:02:12,529 --> 00:02:14,420
entities, and dialog.

29
00:02:14,420 --> 00:02:19,739
And they work together to deliver
a conversational response to the user.

30
00:02:19,739 --> 00:02:23,599
An intent represents
the purpose of a user's input.

31
00:02:23,599 --> 00:02:29,174
You define an intent for each type of
user request you want your application to

32
00:02:29,174 --> 00:02:35,581
support In the tool the name of an intent
is always prefixed the pound character.

33
00:02:35,581 --> 00:02:40,690
To train the workspace to recognize
your intents you supply lots

34
00:02:40,690 --> 00:02:45,797
of examples of user input and
indicate which intents they left.

35
00:02:45,797 --> 00:02:51,493
>> An entity represents a term or object
that is relevant to your intents And

36
00:02:51,493 --> 00:02:54,130
that provides a specific context for
an intent.

37
00:02:54,130 --> 00:02:58,118
For example, an entity might represent
a city where the user wants to find

38
00:02:58,118 --> 00:03:01,076
a business location or
the amount of the bill payment.

39
00:03:01,076 --> 00:03:04,932
In the tool the name of an entity is
always prefix with the @ character.

40
00:03:04,932 --> 00:03:09,372
To train the workspace to recognize your
entities you list the possible values for

41
00:03:09,372 --> 00:03:12,120
each entity and
synonyms that users might enter.

42
00:03:12,120 --> 00:03:17,091
>> A dialog is a brancing
converstaion flow that defines

43
00:03:17,091 --> 00:03:21,619
responses to the defined intents and
entities.

44
00:03:21,619 --> 00:03:26,037
You use the dialog building
inthe tool to create

45
00:03:26,037 --> 00:03:30,690
conversations with users
to provide responses.