Method and apparatus for a ranking engine
View Patent ↗A computer-implemented method is provided for ranking files from an Internet search. In one embodiment, the method comprises assigning a score to each file based on at least one of the following factors: recency, editorial popularity, clickthru popularity, favorites metadata, or favorites collaborative filtering. The file may be organized based on the assigned scores to provide users with more accurate search results.
1. A computer-implemented method for organizing a collection of files from an Internet search, the method comprising:
by at least one computer:
assigning a score to each file based on at least the following factors: recency, editorial popularity, clickthru popularity, favorites metadata, and favorites collaborative filtering;
organizing the files based on the assigned scores; and
displaying the files as organized;
wherein the clickthru popularity for each file is based on an aggregation of at least:
a first clicks-per-minute value for each file;
a second clicks-per-hour value for each file; and
a third clicks-per-day value for each file.
2. The method of claim 1 wherein the score is RT and is determined using the following formula:
R
T
=
W
r
R
r
Term
1
+
W
e
R
e
Term
2
+
W
c
R
c
Term
3
+
W
md
R
md
Term
4
+
W
cf
R
cf
Term
5
where
:
0
<
R
i
<
1
and
:
1
=
W
r
+
W
e
+
W
c
+
W
md
+
W
cf
⇒
0
<
R
T
<
1.
3. The method of claim 2 wherein recency is weighted based on the following formula for Rr:
R
r
{
1
-
1
t
e
(
d
c
-
d
F
)
,
For
(
d
c
-
d
F
)
<
t
e
0
,
For
(
d
c
-
d
F
)
>
t
e
t e =expiration time (perhaps ˜30 days)
d c =current date
d F =date found.
4. The method of claim 2 wherein editorial popularity is weighted between 1 and 0 and is based on at least one of the following: Neilsen ratings, known brand names, website popularity (e.g. Alexa ranking), or the judgment of a professional or corporation with expertise in online media.
5. The method of claim 1 wherein weighting of favorites metadata is R md =0 if no matches are found or 1 if a keyword field in the metadata of the file matches any favorite titles in a user's favorite titles file, any favorite people in a user's favorite people file, or any keyword in a user's favorite keywords file.
6. The method of claim 1 wherein weighting of collaborative filtering favorites metadata is R cf
R cf,l =W sim ( S max,l )+(1− W sim ) P 1 ,
where:
W
sim
=
similarity
weighting
factor
=
C
ma
x
sim
(
1
-
1
1
+
n
i
)
,
where:
0≦C max sim ≦1.
7. The method of claim 6 wherein R cf is a weighted sum of the maximum user similarity for an item l and the popularity of item l among K-Nearest Neighbors such that 0≦R cf ≦1.
8. A computer-implemented method for organizing a collection of files from an Internet search, the method comprising:
by at least one computer:
assigning a score to each file based on favorites collaborative filtering W cf R cf and at least the following factors: recency W r R r , editorial popularity W e R e , clickthru popularity; W c R c , and favorites metadata W md R md ;
organizing the files based on the assigned scores; and
displaying the files as organized;
wherein the clickthru popularity for each file is based on an aggregation of at least:
a first clicks-per-minute value for each file that is multiplied by a first weight;
a second clicks-per-hour value for each file that is multiplied by a second weight; and
a third clicks-per-day value for each file that is multiplied by a third weight;
wherein the multiplication of the first, second and third weights is configured to affect a relative impact of the first clicks-per-minute value, the second clicks-per-hour value, and the third clicks-per-day value.
9. The method of claim 8 wherein the score is R T and is determined using the following formula:
R
T
=
W
r
R
r
Term
1
+
W
e
R
e
Term
2
+
W
c
R
c
Term
3
+
W
md
R
md
Term
4
+
W
cf
R
cf
Term
5
where
:
0
<
R
i
<
1
and
:
1
=
W
r
+
W
e
+
W
c
+
W
md
+
W
cf
⇒
0
<
R
T
<
1.
10. The method of claim 9 wherein recency is weighted based on the following formula for R r :
R
r
{
1
-
1
t
e
(
d
c
-
d
F
)
,
For
(
d
c
-
d
F
)
<
t
e
0
,
For
(
d
c
-
d
F
)
>
t
e
t e =expiration time (perhaps ˜30 days)
d c =current date
d F =date found.
11. The method of claim 9 wherein editorial popularity is weighted between 1 and 0 and is based on at least one of the following: Neilsen ratings, known brand names, website popularity (e.g. Alexa ranking), or the judgment of a professional or corporation with expertise in online media.
12. The method of claim 8 wherein weighting of favorites metadata is R md =0 if no matches are found or 1 if a keyword field in the metadata of the file matches any favorite titles in a user's favorite titles file, any favorite people in a user's favorite people file, or any keyword in a user's favorite keywords file.
13. The method of claim 8 wherein weighting of collaborative filtering favorites metadata is R cf
R cf,l =W sim ( S max,l )+(1− W sim ) P l ,
where:
W
sim
=
similarity
weighting
factor
=
C
m
ax
sim
(
1
-
1
1
+
n
i
)
,
where:
0≦C max sim ≦1.
14. The method of claim 13 wherein R cf is a weighted sum of the maximum user similarity for an item l and the popularity of item l among K-Nearest Neighbors such that 0≦R cf ≦1.
15. A system comprising:
a computer including a ranking engine having programming code for sorting results of a search query based on scores;
wherein the scores for files found in the search are based on clickthru popularity; and
wherein the clickthru popularity for each file is based on at least:
a clicks-per-minute value for each file that is multiplied by a first weight;
a clicks-per-hour value for each file that is multiplied by a second weight; and
a clicks-per-day value for each file that is multiplied by a third weight;
wherein the multiplication of the first, second and third weights is configured to affect a relative impact of the clicks-per-minute value, the clicks-per-hour value, and the clicks-per-day value.