Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:00,530 --> 00:00:00,780
All right.
2
00:00:00,800 --> 00:00:06,440
So as you probably know over the past year or so Microsoft has been making some pretty incredible strides
3
00:00:06,890 --> 00:00:11,490
integrating artificial intelligence into tools like power by now.
4
00:00:11,510 --> 00:00:18,320
Some of these tools like Azure machine learning models or sentiment analysis or text analytics are currently
5
00:00:18,320 --> 00:00:22,260
only available to enterprise or premium capacity users.
6
00:00:22,310 --> 00:00:28,280
But the good news is that there are some great A.I. tools that are accessible to free or pro users as
7
00:00:28,280 --> 00:00:28,640
well.
8
00:00:29,060 --> 00:00:34,160
So what I want to do here is cover some of the A.I. driven visuals that were recently introduced to
9
00:00:34,220 --> 00:00:35,820
provide desktop.
10
00:00:35,820 --> 00:00:41,510
Now important note what you're looking at here is the December 20 19 release.
11
00:00:41,510 --> 00:00:46,520
Make sure you've got a current version of power b ice that you see these new visuals if you're not sure
12
00:00:46,910 --> 00:00:48,630
head to the upper left corner.
13
00:00:48,680 --> 00:00:56,250
Jump in to help about and you should see the version number so I'm on to 7 6 which is the December 20
14
00:00:56,270 --> 00:00:58,220
19 release.
15
00:00:58,280 --> 00:01:04,250
Now the first A.I. visual I want to talk about is the Q and A VISUAL which looks like a little callout
16
00:01:04,280 --> 00:01:06,020
box or text box here.
17
00:01:06,050 --> 00:01:08,920
We'll see a little light bulb in the lower right corner.
18
00:01:08,990 --> 00:01:13,850
There are three visuals here that I'm showing with that light bulb that indicates that it's an A.I.
19
00:01:13,970 --> 00:01:15,080
visual.
20
00:01:15,080 --> 00:01:19,090
So we're going to use our venture works report here that we've built throughout the course.
21
00:01:19,160 --> 00:01:21,840
Let's go ahead and clear this filter on our fields.
22
00:01:21,960 --> 00:01:25,520
Just want to work with a data model that we're already comfortable and familiar with.
23
00:01:25,970 --> 00:01:33,260
So first things first we're going to add a new tab or page let's call it Q and A nothing fancy.
24
00:01:33,260 --> 00:01:33,920
And here we go.
25
00:01:33,920 --> 00:01:35,420
Got our blank canvas.
26
00:01:35,420 --> 00:01:41,330
There are two ways we can insert a Q and A visual and click the button just like any other chart or
27
00:01:41,330 --> 00:01:47,690
if you go to the Home Menu you'll see an ask a question option which does the exact same thing and delete
28
00:01:47,690 --> 00:01:49,040
that duplicate.
29
00:01:49,190 --> 00:01:50,680
You can drag this out.
30
00:01:50,720 --> 00:01:53,180
This is the only thing we're gonna be showing here.
31
00:01:53,180 --> 00:01:59,170
And the first thing you'll probably notice is that we have a question bar here and some suggestions
32
00:01:59,180 --> 00:02:00,520
to get started.
33
00:02:00,560 --> 00:02:06,620
So Microsoft is looking at our data model and offering some suggestions things I might want to look
34
00:02:06,620 --> 00:02:06,830
at.
35
00:02:07,100 --> 00:02:14,330
So total cost by SKU category total revenue by SKU category top genders by year to date can show some
36
00:02:14,330 --> 00:02:16,350
more kind of get a full list.
37
00:02:16,400 --> 00:02:22,370
Now listen I'm going to be honest with you guys I very rarely will use these suggestions that kind of
38
00:02:22,370 --> 00:02:24,150
feel like a shot in the dark.
39
00:02:24,350 --> 00:02:26,290
Sometimes we'll get some interesting suggestions.
40
00:02:26,300 --> 00:02:30,770
But in this case you know we're not that interested in the SKU category.
41
00:02:30,950 --> 00:02:37,090
Some of these are just a little weird like Day of Week over time that really doesn't make much sense.
42
00:02:37,520 --> 00:02:40,440
But if you click on one you can see kind of how this visual works.
43
00:02:40,440 --> 00:02:40,680
Right.
44
00:02:40,680 --> 00:02:44,990
It populates the query turns that query into a visual.
45
00:02:44,990 --> 00:02:50,450
And because this is an A.I. visual you're not going to get the same chart type every time powered by
46
00:02:50,450 --> 00:02:54,440
is going to look at your query it's going to interpret what you're asking and what you're looking for
47
00:02:54,890 --> 00:02:58,990
and it's going to render the most appropriate visual to answer that question.
48
00:02:59,460 --> 00:03:05,180
So here we're looking at SKU category with total profit as our values.
49
00:03:05,180 --> 00:03:09,000
So let's go ahead and clear that out and ask a question of our own.
50
00:03:09,020 --> 00:03:14,420
Now what's important here is that we want to be able to ask a question the same way that we would speak
51
00:03:14,420 --> 00:03:15,770
to a friend right.
52
00:03:15,830 --> 00:03:22,520
This visual wouldn't be very powerful or useful if we had to type the same way that we create a tax
53
00:03:22,520 --> 00:03:23,780
measure for instance.
54
00:03:23,780 --> 00:03:28,750
Right things like a W. underscore sales bracket.
55
00:03:28,880 --> 00:03:30,910
That's not natural language.
56
00:03:31,020 --> 00:03:32,770
That's not a natural query.
57
00:03:32,780 --> 00:03:35,980
So what we can do here is type the same way that we would speak.
58
00:03:35,980 --> 00:03:36,250
All right.
59
00:03:36,260 --> 00:03:43,220
So maybe want something like revenue by category presenter.
60
00:03:43,260 --> 00:03:44,410
We got a result.
61
00:03:44,430 --> 00:03:51,720
Granted it's maybe not the one that we want but power by recognized keywords in the query which it underlined
62
00:03:51,720 --> 00:03:56,400
in blue and it took a stab at rendering what it thinks we're looking for.
63
00:03:56,400 --> 00:04:03,210
So skew category and I can see what the tool tip that it is showing adjusted revenue not quite what
64
00:04:03,210 --> 00:04:03,970
we want here.
65
00:04:03,970 --> 00:04:08,490
The good news is we can click on that keyword and we can use a different suggestion.
66
00:04:08,520 --> 00:04:15,400
So in this case we want total revenue and instead of skew category we want the product category name.
67
00:04:15,630 --> 00:04:17,970
There we go and now we get something a little bit more reasonable.
68
00:04:17,970 --> 00:04:18,180
Right.
69
00:04:18,180 --> 00:04:21,470
We get bikes accessories clothing and based on the tool tip.
70
00:04:21,480 --> 00:04:24,180
We're looking at that total revenue measure.
71
00:04:24,180 --> 00:04:25,640
So that looks great.
72
00:04:25,990 --> 00:04:29,470
Now powered by pretty smart when it comes this visual.
73
00:04:29,580 --> 00:04:35,130
So let's say that I was typing very quickly and I did something like this
74
00:04:37,900 --> 00:04:40,340
revenue by category name.
75
00:04:40,630 --> 00:04:42,880
Well it gave me the correct results.
76
00:04:42,880 --> 00:04:44,530
Same to you that we just showed.
77
00:04:44,560 --> 00:04:49,030
And now what it's done is underlined that first term revenue in red.
78
00:04:49,030 --> 00:04:53,570
And it's saying hey you know we think you're probably trying to type revenue here.
79
00:04:53,830 --> 00:04:58,930
So we're going to show you the results for revenue by category name just like Google does.
80
00:04:58,930 --> 00:05:06,010
You know the auto correct tool powered by AIS driven by obviously a behind the scenes and as part of
81
00:05:06,010 --> 00:05:11,260
that A.I. and understands synonyms and corrections just like the one we're looking at here.
82
00:05:11,260 --> 00:05:17,140
So again I can click in and I can say you know what I want total revenue by category name and boom we're
83
00:05:17,140 --> 00:05:18,260
off and running.
84
00:05:18,520 --> 00:05:22,900
Now this is really just scratching the surface of what this visual is capable of.
85
00:05:22,920 --> 00:05:29,850
You know this is a simple query one measure one column or dimension name get a little bit more sophisticated
86
00:05:29,850 --> 00:05:39,890
in this and we could do something like total revenue for red bikes.
87
00:05:40,740 --> 00:05:48,090
And because this query is designed to aggregate values to a single result power RBI has displayed the
88
00:05:48,090 --> 00:05:50,940
answer or the result in the form of card one value.
89
00:05:50,940 --> 00:05:53,460
Four point eighty seven million.
90
00:05:53,460 --> 00:05:57,330
If you're not sure if you don't trust that that's right we can go ahead and test that.
91
00:05:57,330 --> 00:06:00,110
We can add a card ourselves.
92
00:06:00,120 --> 00:06:07,030
Let's expand our filters and in this card we want to show that total revenue measure.
93
00:06:07,530 --> 00:06:14,480
And we want to filter it down for the bike category.
94
00:06:14,520 --> 00:06:15,730
There we go.
95
00:06:15,780 --> 00:06:23,800
And for the color product color red four point eight seven million.
96
00:06:23,800 --> 00:06:24,490
Boom.
97
00:06:24,490 --> 00:06:25,440
There we go.
98
00:06:25,480 --> 00:06:26,350
The Q and A VISUAL.
99
00:06:26,350 --> 00:06:32,410
Did its job it return the proper result which is actually pretty impressive when you consider the complexity
100
00:06:32,410 --> 00:06:33,560
of this query.
101
00:06:33,610 --> 00:06:41,740
We're looking for a measure aggregated values based on an attribute read which has a value in a dimension
102
00:06:41,740 --> 00:06:49,090
from one table the product table and also category equals bikes which is a dimension from a second table.
103
00:06:49,130 --> 00:06:50,840
The product category table.
104
00:06:51,160 --> 00:06:58,000
So the fact that Part B I was able to interpret that instantly and render the proper result is actually
105
00:06:58,240 --> 00:06:59,660
pretty incredible.
106
00:06:59,680 --> 00:07:01,590
Now we can take this a step further.
107
00:07:01,690 --> 00:07:07,120
Beauty of of AI and machine learning is that you can train these models and train these tools to get
108
00:07:07,120 --> 00:07:08,820
smarter over time.
109
00:07:08,860 --> 00:07:10,580
So let me show you what that looks like.
110
00:07:10,600 --> 00:07:15,160
Going to click this gear icon here this is going to open up this menu.
111
00:07:15,160 --> 00:07:17,020
Granted this is a brand new visual.
112
00:07:17,050 --> 00:07:22,630
Things are changing and evolving so you might not see this exact view but basically I've got three options
113
00:07:22,630 --> 00:07:28,570
here I can review questions that have been asked in this visual I can teach the Q and A VISUAL to get
114
00:07:28,570 --> 00:07:35,560
smarter and understand new synonyms and I can manage any custom terms or synonyms that I've defined.
115
00:07:35,590 --> 00:07:39,820
If you click this link here you'll go to the official Microsoft documentation if you want to dig a little
116
00:07:39,820 --> 00:07:40,890
bit deeper.
117
00:07:41,080 --> 00:07:43,070
But let me show you how this works.
118
00:07:43,120 --> 00:07:49,100
Now if I click review questions I'm going to see a list of questions that I've been asked in this visual.
119
00:07:49,360 --> 00:07:51,970
Now you won't see any questions here.
120
00:07:52,120 --> 00:07:57,490
If you've only interacted with the visual in power b I desktop in order for this to work you have to
121
00:07:57,490 --> 00:08:03,400
publish this to a workspace in the power be a service environment which we do cover in a separate course
122
00:08:03,640 --> 00:08:05,450
publishing it Power by Service.
123
00:08:05,530 --> 00:08:11,820
So as a test what I've done is upload or or publish this report to a workspace in the service environment.
124
00:08:11,830 --> 00:08:16,690
I asked a bunch of questions inside of this visual and they populated right here.
125
00:08:16,900 --> 00:08:24,250
So the important thing to note on this tab or this view is that any query that has a red underline or
126
00:08:24,280 --> 00:08:30,000
a keyword that power b I didn't understand has this pencil icon where it says fixed needed.
127
00:08:30,000 --> 00:08:35,790
And when I click that icon takes me to the teach Q and A tab it populates that query.
128
00:08:35,920 --> 00:08:41,530
And when I hit submit what it's going to do is show me a preview of what the Q and A VISUAL would return
129
00:08:41,530 --> 00:08:42,970
here on the right side.
130
00:08:42,970 --> 00:08:46,990
So in this case a card with the value twenty four point nine one million.
131
00:08:47,110 --> 00:08:53,560
And it also lets me define the term and read the term that power be I wasn't able to interpret.
132
00:08:53,590 --> 00:08:59,470
So in this case you know I'm looking for product type which isn't actually a column name or field in
133
00:08:59,470 --> 00:09:06,680
my model but I know that this user because it was me is actually looking for the category right bikes
134
00:09:06,760 --> 00:09:08,190
clothing accessories.
135
00:09:08,230 --> 00:09:14,080
So what I can do is tell power b I hate whenever you see someone type product type what they really
136
00:09:14,080 --> 00:09:18,030
mean is category name.
137
00:09:18,030 --> 00:09:22,720
OK so I've just defined a new synonym and watch this preview update.
138
00:09:22,920 --> 00:09:23,240
Boom.
139
00:09:23,240 --> 00:09:23,640
There you go.
140
00:09:23,640 --> 00:09:28,830
So now instead of the card it's showing that bar chart with the breakdown by category name.
141
00:09:28,830 --> 00:09:36,840
So when I save that synonym I've now made this visual smarter and I can manage any terms that I've created
142
00:09:37,140 --> 00:09:39,130
right here in that last tab.
143
00:09:39,150 --> 00:09:45,930
So pretty cool stuff if I close out of that dialog box now and I head into our model tab you'll see
144
00:09:45,930 --> 00:09:50,730
this kind of populate one other place which is in the properties tab.
145
00:09:50,730 --> 00:09:57,500
So if we look at the category name inside of our category lookup table there's this box called synonyms.
146
00:09:57,630 --> 00:10:04,410
Check it out category name category name no space category and product type which is the one that we
147
00:10:04,410 --> 00:10:07,540
just defined in the Q and A VISUAL.
148
00:10:07,560 --> 00:10:10,070
So pretty cool stuff pretty user friendly.
149
00:10:10,080 --> 00:10:12,070
One last query that I want to show you.
150
00:10:12,090 --> 00:10:18,660
Let's say we do something like orders by order quantity.
151
00:10:18,910 --> 00:10:25,930
In this case power b I interpreted this as a line chart but really we're not showing anything in a time
152
00:10:25,930 --> 00:10:26,350
series.
153
00:10:26,350 --> 00:10:28,440
We don't really want a line chart here.
154
00:10:28,450 --> 00:10:31,970
I think a bar column chart would be a little bit more appropriate.
155
00:10:32,050 --> 00:10:38,350
So what we can do is convert this to a visual using this button here just turns it right into a line
156
00:10:38,350 --> 00:10:43,860
chart and all we need to do is click and we can modify it change the chart type.
157
00:10:43,870 --> 00:10:47,140
We can format this we can filter it any way that we like.
158
00:10:47,140 --> 00:10:48,760
Just like any other visual.
159
00:10:48,850 --> 00:10:51,370
So there you have it pretty powerful stuff.
160
00:10:51,370 --> 00:10:54,010
That's the A.I. driven q and a visual.
16226
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.