WEBVTT

00:00:06.070 --> 00:00:07.120
Hi, my name's John.

00:00:07.510 --> 00:00:09.880
I lead the search and machine
learning teams at Google.

00:00:12.130 --> 00:00:14.230
I think it's amazingly inspiring

00:00:14.230 --> 00:00:16.214
that people all over the world

00:00:16.215 --> 00:00:19.240
turn to search engines to
ask trivial questions

00:00:19.240 --> 00:00:20.530
and incredibly important questions.

00:00:20.560 --> 00:00:23.290
So it's a huge
responsibility to give them

00:00:23.290 --> 00:00:24.594
the best answers that we can.

00:00:26.710 --> 00:00:30.610
Hi, my name's Akshaya and 
I work on the Bing search team.

00:00:31.090 --> 00:00:33.190
There are many times where
we will start looking

00:00:33.190 --> 00:00:35.800
into artificial intelligence
and machine learning,

00:00:35.830 --> 00:00:39.010
but we have to address how are
the users going to use this,

00:00:39.140 --> 00:00:42.220
because at the end of the day,
we want to make an impact to society.

00:00:43.780 --> 00:00:45.400
Let's ask a simple question.

00:00:45.820 --> 00:00:48.070
How long does it take to travel to Mars?

00:00:49.330 --> 00:00:50.950
Where did these results come from

00:00:51.370 --> 00:00:54.100
and why was this listed
before the other one?

00:00:55.700 --> 00:00:58.150
Okay, let's dive in and
see how the search engine

00:00:58.150 --> 00:00:59.860
turned your request into a result.

00:01:01.090 --> 00:01:03.310
The first thing you need to
know is when you do a search,

00:01:03.430 --> 00:01:06.310
the search engine isn't actually
going out to the World Wide Web

00:01:06.310 --> 00:01:07.840
to run your search in real time.

00:01:08.520 --> 00:01:10.450
And that's because there's
over a billion websites

00:01:10.450 --> 00:01:13.780
on the internet and hundreds more are
being created every single minute.

00:01:14.680 --> 00:01:16.210
So if the search engine
had to look through

00:01:16.240 --> 00:01:18.220
every single site to
find the one you wanted,

00:01:18.510 --> 00:01:19.390
it would just take forever.

00:01:20.500 --> 00:01:21.940
So to make your search faster,

00:01:21.970 --> 00:01:24.940
search engines are constantly
scanning the web in advance

00:01:25.420 --> 00:01:28.140
to record the information that might
help with your search later.

00:01:28.930 --> 00:01:31.270
That way, when you search
about travel to Mars,

00:01:31.630 --> 00:01:33.700
the search engine
already has what it needs

00:01:33.700 --> 00:01:35.230
to give you an answer in real time.

00:01:36.250 --> 00:01:37.540
Here's how it works.

00:01:37.900 --> 00:01:42.010
The internet is a web of pages
connected to each other by hyperlinks.

00:01:42.400 --> 00:01:44.680
Search engines are
constantly running a program

00:01:44.680 --> 00:01:47.380
called a Spider that cross
through these web pages

00:01:47.380 --> 00:01:49.040
to collect information about them.

00:01:49.780 --> 00:01:51.550
Each time it finds a hyperlink,

00:01:52.090 --> 00:01:55.000
it follows it until it
has visited every page

00:01:55.030 --> 00:01:57.240
it can find on the entire
internet.

00:01:57.335 --> 00:01:59.170
For each page the spider visits,

00:01:59.200 --> 00:02:02.320
it records any information
it might need for a search

00:02:02.500 --> 00:02:05.650
by adding it to a special
database called a search index.

00:02:07.520 --> 00:02:09.530
Now, let's go back to
that search from earlier

00:02:09.590 --> 00:02:11.720
and see if we can figure
out how the search engine

00:02:11.750 --> 00:02:13.093
came up with the results.

00:02:13.640 --> 00:02:16.460
When you ask how long does
it take to travel to Mars,

00:02:16.640 --> 00:02:18.860
the search engine looks
in each of those words

00:02:18.920 --> 00:02:21.410
in the search index to
immediately get a list

00:02:21.410 --> 00:02:24.500
of all the pages on the
internet containing those words.

00:02:25.130 --> 00:02:26.870
But just looking for these search terms

00:02:26.870 --> 00:02:28.760
could return millions of pages,

00:02:29.060 --> 00:02:30.980
so the search engine needs
to be able to determine

00:02:30.980 --> 00:02:32.990
the best matches to show you first.

00:02:33.860 --> 00:02:35.810
This is where it gets tricky
because the search engine

00:02:35.840 --> 00:02:37.610
may need to guess what
you're looking for.

00:02:38.930 --> 00:02:41.360
Each search engine
uses its own algorithm

00:02:41.360 --> 00:02:44.230
to rank the pages based on
what it thinks you want.

00:02:44.930 --> 00:02:47.660
The search engine's ranking
algorithm might check

00:02:47.990 --> 00:02:50.360
if your search term shows
up in the page title,

00:02:51.040 --> 00:02:53.660
it might check if all of the
words show up next to each other,

00:02:54.520 --> 00:02:57.020
or any number of other calculations

00:02:57.020 --> 00:02:58.610
that help it better determine

00:02:58.670 --> 00:03:01.420
which pages you'll want
to see and which you won't.

00:03:03.280 --> 00:03:04.960
Google invented the most 
famous algorithm

00:03:04.960 --> 00:03:08.530
for choosing the most relevant results
for a search by taking into account

00:03:08.560 --> 00:03:11.230
how many other Web pages
linked to a given page.

00:03:11.830 --> 00:03:14.140
The idea is that if
lots of websites think

00:03:14.140 --> 00:03:15.400
that a web page is interesting,

00:03:15.660 --> 00:03:17.170
then it's probably the one 
you're looking for.

00:03:18.190 --> 00:03:20.020
This algorithm is called page rank,

00:03:20.590 --> 00:03:22.330
not because it ranks web pages,

00:03:22.570 --> 00:03:25.210
but because it was named after
its inventor, Larry Page,

00:03:25.480 --> 00:03:27.023
who's one of the founders of Google.

00:03:27.940 --> 00:03:30.520
Because a website often makes
money when you visit it,

00:03:30.820 --> 00:03:32.950
spammers are constantly
trying to find ways

00:03:32.950 --> 00:03:35.741
to game the search algorithm 
so that their pages

00:03:35.742 --> 00:03:37.931
are listed higher in the results.

00:03:38.260 --> 00:03:40.750
Search engines regularly
update their algorithms

00:03:40.750 --> 00:03:44.296
to prevent fake or untrustworthy
sites from reaching the top.

00:03:44.680 --> 00:03:47.350
Ultimately, it's up to you 
to keep an eye out

00:03:47.500 --> 00:03:49.450
for these pages that are untrustworthy

00:03:49.690 --> 00:03:52.990
by looking at the web address and
making sure it's a reliable source.

00:03:53.680 --> 00:03:55.390
Search programs are always evolving

00:03:55.420 --> 00:03:58.420
to improve the algorithms 
wo they return better results,

00:03:58.540 --> 00:04:00.460
faster results than their competitors.

00:04:01.000 --> 00:04:03.100
Today's search engines
even use information

00:04:03.100 --> 00:04:06.310
that you haven't explicitly provided
to help you narrow down your search.

00:04:07.150 --> 00:04:10.120
So, for example,
if you did a search for dog parks,

00:04:10.510 --> 00:04:12.190
many search engines
would give you results

00:04:12.190 --> 00:04:13.840
for all the dog parks nearby,

00:04:14.080 --> 00:04:15.880
even though you didn't
type in your location.

00:04:17.800 --> 00:04:20.530
Modern search engines
also understand more

00:04:20.530 --> 00:04:22.060
than just the words on a page,

00:04:22.300 --> 00:04:24.970
but what they actually mean
in order to find the best one

00:04:24.970 --> 00:04:26.560
that matches what you're looking for.

00:04:27.130 --> 00:04:29.980
For example, if you search 
for fast pitcher,

00:04:30.280 --> 00:04:32.000
it will know you're
looking for an athlete.

00:04:32.500 --> 00:04:34.180
But if you search for large pitcher,

00:04:34.450 --> 00:04:36.730
it will find you options
for your kitchen.

00:04:38.810 --> 00:04:40.000
To understand the words better,

00:04:40.000 --> 00:04:41.440
we use something called
machine learning,

00:04:41.800 --> 00:04:43.390
a type of artificial intelligence.

00:04:43.760 --> 00:04:46.050
It enables search
algorithms to search out

00:04:46.090 --> 00:04:48.190
not just individual letters
or words in the page,

00:04:48.400 --> 00:04:51.280
but understand the underlying
meaning of the words.

00:04:53.690 --> 00:04:55.850
The internet is growing exponentially,

00:04:56.210 --> 00:04:59.810
but if the teams that design
search engines do our jobs right,

00:05:00.080 --> 00:05:04.090
the information you want should
always be just a few keystrokes away.