Method of and system for recommending media objects

1. A computer-implemented method for selecting recommended media objects, the method executable by a server, the method comprising:

acquiring, by the server, a set of indications of media objects, each indication of the set of indications being associated with a respective media object, the respective media object having at least one respective user interaction parameter, the respective user interaction parameter being indicative of a level of interaction of at least one user with the respective media object;

acquiring, by the server, at least one tag associated with each respective media object, the at least one tag being representative of a content of the respective media object;

receiving, by the server from a client device, a request for a media object recommendation, the request for the media object recommendation having been triggered by a user having interacted with a media object via the client device;

acquiring, by the server, at least one tag and at least one user interaction parameter associated with the media object;

determining, by the server, potential recommended media object candidates based on at least one tag of the media object overlapping with tags associated with the respective media objects;

determining, by the server, for each potential recommended media object candidate, a number of overlapping tags with the media object;

generating, by the server, for each potential recommended media object candidate, a respective correspondence parameter based on the number of overlapping tags and the respective user interaction parameter of the potential recommended media object candidate and the media object, the correspondence parameter being indicative of a level of similarity between the potential recommended object candidate and the media object, the generating of the respective correspondence parameter for each potential recommended media object candidate comprising:

summing, by the server, the respective user interaction parameter of the potential recommended media object candidate and the media object to obtain a respective sum; and

assigning the respective sum to each of the overlapping tags;

adding up the respective sums of all overlapping tags for the given potential recommended media object candidate to obtain the respective correspondence parameter;

selecting, by the server, at least one recommended media object from the potential recommended media object candidates, the at least one recommended media object being associated with a predetermined value of the correspondence parameter.

2. The method of claim 1 , wherein the generating the respective correspondence parameter for each potential recommended media object candidate comprises:

summing, by the server, the respective user interaction parameter of the potential recommended media object candidate and the media object to obtain a respective sum; and

multiplying, by the server, for each potential recommended media object, the respective sum by the number of overlapping tags to obtain the respective correspondence parameter.

3. The method of claim 1 , wherein the generating the respective correspondence parameter for each potential recommended media object candidate comprises:

summing, by the server, the respective user interaction parameter of the potential recommended media object candidate and the media object to obtain a respective sum; and

summing, by the server, the respective sum for each overlapping tag between the potential recommended media object candidate and the media object to obtain the respective correspondence parameter.

4. The method of claim 1 , further comprising:

transmitting, by the server to the client device, an indication of the at least one recommended media object.

5. The method of claim 4 , wherein each respective media object is associated with a respective identifier.

6. The method of claim 5 , wherein prior to selecting the at least one recommended media object, the method further comprises:

ranking the potential recommended media object candidates according to their respective correspondence parameters.

7. The method of claim 6 , wherein the media object is a video.

8. The method of claim 1 , wherein the predetermined value of the correspondence parameter comprises a predetermined number of top-ranked respective correspondence parameters.

9. The method of claim 1 , wherein the at least one tag is at least one of: a category, a title, a performer, a subject, a description, a language, a related performer, a rating, a director, a text and a location.

10. The method of claim 9 , wherein the at least one tag associated with each respective media object is acquired from a second server.

11. The method of claim 10 , wherein the at least one tag was generated from a textual context associated with each respective media object on the second server.

12. The method of claim 1 , wherein the user interaction parameter is one of: a view time, a view count, a play rate, an engagement rate, a social sharing rate, a click-through rate (CTR) and a conversion rate.

13. A system for selecting recommended media objects, the system comprising:

a processor;

a non-transitory computer-readable medium comprising instructions;

the processor, upon executing the instructions, being configured to:

acquire a set of indications of media objects, each indication of the set of indications being associated with a respective media object, the respective media object having at least one respective user interaction parameter, the respective user interaction parameter being indicative of a level of interaction of at least one user with the respective media object;

acquire at least one tag associated with each respective media object, the at least one tag being representative of a content of the respective media object;

receive, from a client device, a request for a media object recommendation, the request for the media object recommendation having been triggered by a user having interacted with a media object via the client device;

acquire at least one tag and at least one user interaction parameter associated with the media object;

determine potential recommended media object candidates based on at least one tag of the media object overlapping with tags associated with the respective media objects;

determine, for each potential recommended media object candidate, a number of overlapping tags with the media object;

generate for each potential recommended media object candidate, a respective correspondence parameter based on the number of overlapping tags and the respective user interaction parameter of the potential recommended media object candidate and the media object, the correspondence parameter being indicative of a level of similarity between the potential recommended object candidate and the media object, the generating of the respective correspondence parameter for each potential recommended media object candidate comprising:

summing, by the server, the respective user interaction parameter of the potential recommended media object candidate and the media object to obtain a respective sum; and

assigning the respective sum to each of the overlapping tags;

adding up the respective sums of all overlapping tags for the given potential recommended media object candidate to obtain the respective correspondence parameter;

select at least one recommended media object from the potential recommended media object candidates, the at least one recommended media object being associated with a predetermined value of the correspondence parameter.

14. The system of claim 13 , wherein to generate the respective correspondence parameter for each potential recommended media object candidate, the processor is configured to:

sum the respective user interaction parameter of the potential recommended media object candidate and the media object to obtain a respective sum; and

multiply for each potential recommended media object, the respective sum by the number of overlapping tags to obtain the respective correspondence parameter.

15. The system of claim 13 , wherein to generate the respective correspondence parameter for each potential recommended media object candidate, the processor is configured to:

sum the respective user interaction parameter of the potential recommended media object candidate and the media object to obtain a respective sum; and

sum the respective sum for each overlapping tag between the potential recommended media object candidate and the media object to obtain the respective correspondence parameter.

16. The system of claim 13 , wherein the processor is further configured to:

transmit, to the client device, an indication of the at least one recommended media object.

17. The system of claim 16 , wherein each respective media object is associated with a respective identifier.

18. The system of claim 17 , wherein prior to selecting the at least one recommended media object, the system is configured to:

rank the potential recommended media object candidates according to their respective correspondence parameters.

19. The system of claim 18 , wherein the media object is a video.

20. The system of claim 13 , wherein the predetermined value of the correspondence parameter comprises a predetermined number of top-ranked respective correspondence parameters.