Abstract: The present disclosure relates to a content recommendation method, device and system. The method includes: recommending a content in a content set to a user based on an average recommendation probability; collecting feedback information on the recommended content from the user's client, wherein the feedback information includes display information and click information, the display information including displaying times and displaying timing of the recommended content on the client, and the click information including clicking times and clicking timing of the recommended content on the client; and determining a sequence of preferred contents from the contents in the content set according to the feedback information, so as to recommend a content to the user based on the sequence of preferred contents.

Abstract: 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.

Abstract: 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.

Abstract: The present disclosure relates to a content recommendation method, device and system. The method includes: recommending a content in a content set to a user based on an average recommendation probability; collecting feedback information on the recommended content from the user's client, wherein the feedback information includes display information and click information, the display information including displaying times and displaying timing of the recommended content on the client, and the click information including clicking times and clicking timing of the recommended content on the client; and determining a sequence of preferred contents from the contents in the content set according to the feedback information, so as to recommend a content to the user based on the sequence of preferred contents.

Abstract: Disclosed herein is a method and system for providing a personalized search list, which comprises: recording a viewing log of a user based on the user's viewing activities of network videos; analyzing the recorded viewing log at a cloud server to generate a list of network videos that the user may like, wherein the list of network videos the user may like comprises a list of network videos based on the user information, or a list of network videos based on the contents of network videos viewed by the user, or a list of network videos based on a degree of viewing similarity between the user and other users, or combination thereof. After a list of search results are generated in response to a user-entered search term, an intersection between the list of search results and the list of network videos that the user may like is calculated to provide the personalized search list.

Abstract: Disclosed herein is a method and system for sorting network videos as a result of an online search. Under the present invention, the system obtains a final sorting factor by calculating weight values of different dimensions, including the release time of a network video, the amount of playbacks of the network video, the classification of the network video and a probability j indicating how often the network video occurs in a collection V. By presenting the videos more needed by the user on the top of a web page, the present invention provides a more accurate display of the search results, thereby improving the user viewing experience.