Searching and ranking personalized videos
A method for searching and ranking personalized videos includes receiving a user request via a communication chat between a user and another user. The user request includes a phrase. The method performs, based on the phrase, a search in a first pool of pre-rendered videos to determine a first subset of relevant videos ranked according to first rankings. The pre-rendered videos include pre-rendered text messages. The method performs a search in a second pool of customized videos to determine a second subset of relevant videos ranked according to second rankings. The customized videos include text messages modified by the user. The method generates a set of videos. The set of videos includes a first number of pre-rendered videos from the first subset of relevant videos and a second number of customized videos from the second subset of relevant videos. The method presents the set of videos via the communication chat.
1. A method for searching and ranking videos, the method comprising:
receiving, by a computing device, a user request via a communication chat between a user of the computing device and a further user of a further computing device, the user request including a phrase;
performing, by the computing device and based on the phrase, a search in:
a first pool of pre-rendered videos to determine a first subset of relevant videos ranked according to first rankings, wherein the pre-rendered videos include pre-rendered text messages, wherein the first rankings are determined based on a group the user belongs to; and
a second pool of customized videos to determine a second subset of relevant videos ranked according to second rankings, wherein the customized videos include text messages modified by the user;
generating, by the computing device, a set of videos, wherein the set of videos includes a first number of pre-rendered videos from the first subset of relevant videos and a second number of customized videos from the second subset of relevant videos, wherein the second subset of relevant videos includes a pre-determined number of customized videos ranked according to the second rankings, wherein the second rankings are independent of the group the user belongs to; and
presenting, by the computing device, the set of videos via the communication chat.
2. The method of claim 1 , wherein the second pool of customized videos includes a pre-rendered video from the first pool with a pre-rendered text message, wherein the pre-rendered text message has been modified by the user.
3. The method of claim 1 , further comprising, prior to presenting the set of videos:
determining that the set of videos includes a pre-rendered video and a customized video, wherein the customized video is the pre-rendered video with a pre-rendered text message modified by the user;
determining that the pre-rendered video includes a pre-rendered text message matching the phrase in the user request with a pre-determined level of accuracy; and
in response to the determination, removing the customized video from the set of videos.
4. The method of claim 1 , wherein the set of videos includes N best ranked pre-rendered videos from the first subset of relevant videos followed by M best ranked customized videos from the second subset of relevant videos followed by L-M-N ranked pre-rendered videos from rest of pre-rendered videos from the first subset of relevant videos, wherein L is a predetermined size of the set of videos.
5. The method of claim 1 , wherein the group includes one of the following: an age group and a gender group.
6. The method of claim 1 , wherein the first rankings are determined based on a performance metric of the relevant videos in the first subset.
7. The method of claim 6 , wherein the performance metric includes a share rate of the relevant videos.
8. The method of claim 1 , wherein the second subset of relevant videos includes a further pre-determined number of customized videos ranked according to the second rankings, the second rankings depending on a category of the customized videos and the group the user belongs to.
9. The method of claim 8 , wherein the category is based on one of the following: an emotional state associated with the text messages of the customized videos and a time a customized video was shared.
10. A system for searching and ranking videos, the system comprising at least one processor and a memory storing processor-executable codes, wherein the at least one processor is configured to implement the following operations upon executing the processor-executable codes:
receiving, by a computing device, a user request via a communication chat between a user of the computing device and a further user of a further computing device, the user request including a phrase;
performing, by the computing device and based on the phrase, a search in:
a first pool of pre-rendered videos to determine a first subset of relevant videos ranked according to first rankings, wherein the pre-rendered videos include pre-rendered text messages, wherein the first rankings are determined based on a group the user belongs to; and
a second pool of customized videos to determine a second subset of relevant videos ranked according to second rankings, wherein the customized videos include text messages modified by the user;
generating, by the computing device, a set of videos, wherein the set of videos includes a first number of pre-rendered videos from the first subset of relevant videos and a second number of customized videos from the second subset of relevant videos, wherein the second subset of relevant videos includes a pre-determined number of customized videos ranked according to the second rankings, wherein the second rankings are independent of the group the user belongs to; and
presenting, by the computing device, the set of videos via the communication chat.
11. The system of claim 10 , wherein the second pool of customized videos includes a pre-rendered video from the first pool with a pre-rendered text message, wherein the pre-rendered text message has been modified by the user.
12. The system of claim 10 , wherein the at least one processor is configured to implement the following operations prior to presenting the set of videos:
determining that the set of videos includes a pre-rendered video and a customized video, wherein the customized video is the pre-rendered video with a pre-rendered text message modified by the user;
determining that the pre-rendered video includes a pre-rendered text message matching the phrase in the user request with a pre-determined level of accuracy; and
in response to the determination, removing the customized video from the set of videos.
13. The system of claim 10 , wherein the set of videos includes N best ranked pre-rendered videos from the first subset of relevant videos followed by M best ranked customized videos from the second subset of relevant videos followed by L-M-N ranked pre-rendered videos from rest of pre-rendered videos from the first subset of relevant videos, wherein L is a predetermined size of the set of videos.
14. The system of claim 10 , wherein the group includes one of the following: an age group and a gender group.
15. The system of claim 10 , wherein the first rankings are determined based on a performance metric of the relevant videos in the first subset.
16. The system of claim 15 , wherein the performance metric includes a share rate of the relevant videos.
17. The system of claim 10 , wherein the second subset of relevant videos includes a further pre-determined number of customized videos ranked according to the second rankings, the second rankings depending on a category of the customized videos and the group the user belongs to.
18. A non-transitory processor-readable medium having instructions stored thereon, which when executed by one or more processors, cause the one or more processors to implement a method for searching and ranking videos, the method comprising:
receiving, by a computing device, a user request via a communication chat between a user of the computing device and a further user of a further computing device, the user request including a phrase;
performing, by the computing device and based on the phrase, a search in:
a first pool of pre-rendered videos to determine a first subset of relevant videos ranked according to first rankings, wherein the pre-rendered videos include pre-rendered text messages, wherein the first rankings are determined based on a group the user belongs to; and
a second pool of customized videos to determine a second subset of relevant videos ranked according to second rankings, wherein the customized videos include text messages modified by the user;
generating, by the computing device, a set of videos, wherein the set of videos includes a first number of pre-rendered videos from the first subset of relevant videos and a second number of customized videos from the second subset of relevant videos, wherein the second subset of relevant videos includes a pre-determined number of customized videos ranked according to the second rankings, wherein the second rankings are independent of the group the user belongs to; and
presenting, by the computing device, the set of videos via the communication chat.
19. The non-transitory processor-readable medium of claim 18 , wherein the second pool of customized videos includes a pre-rendered video from the first pool with a pre-rendered text message, wherein the pre-rendered text message has been modified by the user.
20. The non-transitory processor-readable medium of claim 18 , wherein the set of videos includes N best ranked pre-rendered videos from the first subset of relevant videos followed by M best ranked customized videos from the second subset of relevant videos followed by L-M-N ranked pre-rendered videos from rest of pre-rendered videos from the first subset of relevant videos, wherein L is a predetermined size of the set of videos.