Method and device for assessing quality of multimedia resource
The present disclosure provides a method and device for assessing quality of multimedia resource, wherein the method includes the steps of: determining a cumulative distribution vector of the multimedia resource according to indicator data for describing user behavior on the multimedia resource; determining an upper boundary vector and a lower boundary vector of the multimedia resource according to the cumulative distribution vector; and determining a quality score of the multimedia resource according to the cumulative distribution vector, the upper boundary vector, and the lower boundary vector. The present disclosure can better describe the quality of multimedia resource, and has a great operability. Moreover, after the quality of multimedia resource is assessed by using the quality assessment method of multimedia resource in the examples of the present disclosure, the feedback of online behaviors can be reflected on the final dynamic and optimized ranking and recommendation of the multimedia resource.
1. A method for assessing quality of a multimedia resource, comprising:
maintaining a log storing information about user behavior associated with a plurality of multimedia resources provided to terminal devices, the information about user behavior including information that indicates percentages associated with different instances of user behavior on each multimedia resource, and the information stored in the log including indicator data for describing user behavior on the multimedia resource;
determining a cumulative distribution vector of the multimedia resource according to the indicator data;
determining an upper boundary vector and a lower boundary vector of the multimedia resource according to the cumulative distribution vector;
determining a quality score of the multimedia resource according to the cumulative distribution vector, the upper boundary vector, and the lower boundary vector; and
outputting dynamic ranking of the plurality of multimedia resources provided to the terminal devices based at least in part on the quality assessment of the multimedia resource among the plurality of multimedia resources based on the determined quality score.
2. The method according to claim 1 , wherein determining the cumulative distribution vector of the multimedia resource according to the indicator data comprises:
dividing the indicator data of one type of user behaviors into multiple groups;
counting a number of the indicator data of the one type of user behaviors included in each group; and
determining a vector formed by the counted numbers for the multiple groups as the cumulative distribution vector of the multimedia resource for the one type of user behaviors.
3. The method according to claim 2 , wherein dividing the indicator data of the one type of user behaviors into the multiple groups comprises:
obtaining a maximum value max(D) and a minimum value min(D) of the indicator data D of the one type of user behaviors;
determining
max
(
D
)
-
min
(
D
)
n
as a dividing interval, wherein n is the number of the multiple groups; and
dividing the section max(D)−min(D) into n groups.
4. The method according to claim 1 , wherein determining the quality score of the multimedia resource according to the cumulative distribution vector, the upper boundary vector, and the lower boundary vector comprises:
calculating the quality score by using Formula 1 below,
Score
=
1
-
DistanceTOTOP
DistanceBetween
,
(
Formula
1
)
wherein Score is the quality score, DistanceTOTOP is a distance from the cumulative distribution vector to the upper boundary vector, and DistanceBetween is a distance from the upper boundary vector to the lower boundary vector.
5. A device for assessing quality of a multimedia resource, comprising:
memory for maintaining a log storing information about user behavior associated with a plurality of multimedia resources provided to terminal devices, the information about user behavior including information that indicates percentages associated with different instances of user behavior on each multimedia resource, and the information stored in the log including indicator data for describing user behavior on the multimedia resource;
a first determining unit configured to determine a cumulative distribution vector of the multimedia resource according to the indicator data;
a second determining unit connected to the first determining unit and configured to determine an upper boundary vector and a lower boundary vector of the multimedia resource according to the cumulative distribution vector;
a third determining unit connected to the first and second determining units and configured to determine a quality score of the multimedia resource according to the cumulative distribution vector, the upper boundary vector, and the lower boundary vector; and
a communication interface for outputting dynamic ranking of the plurality of multimedia resources provided to the terminal devices based at least in part on the quality assessment of the multimedia resource among the plurality of multimedia resources based on the determined quality score.
6. The device according to claim 5 , wherein the first determining unit comprises:
a dividing subunit configured to divide the indicator data of one type of user behaviors into multiple groups;
a counting subunit connected to the dividing subunit and configured to count a number of the indicator data of the one type of user behaviors included in each group; and
a determining subunit connected to the counting subunit and configured to determine a vector formed by the counted numbers for the multiple groups as the cumulative distribution vector of the multimedia resource for the one type of user behaviors.
7. The device according to claim 6 , wherein the dividing subunit comprises:
an obtaining module configured to obtain a maximum value max(D) and a minimum value min(D) of the indicator data D of the one type of user behaviors;
a determining module connected to the obtaining module and configured to determine
max
(
D
)
-
min
(
D
)
n
as a dividing interval, wherein n is the number of the multiple groups; and
a dividing module connected to the determining module and configured to divide the section max(D)−min(D) into n groups.
8. The device according to claim 5 , wherein the third determining unit is configured to calculate the quality score by using Formula 1 below,
Score
=
1
-
DistanceTOTOP
DistanceBetween
,
(
Formula
1
)
wherein Score is the quality score, DistanceTOTOP is a distance from the cumulative distribution vector to the upper boundary vector, and DistanceBetween is a distance from the upper boundary vector to the lower boundary vector.