Method and method for recommending data

Abstract

The invention relates to a method and system for recommending data, wherein the method comprises the steps of collecting the choice record of each user to each piece of to-be-recommended data, obtaining an average click rate of each user to the to-be-recommended data according to the choice record of each user to each piece of to-be-recommended data, obtaining an average popular degree of each piece of to-be-recommended to all users receiving recommendation, and obtaining the recommendation score of each piece of to-be-recommended according to the average popular degree or obtaining the recommendation score of each piece of to-be-recommended according to the choice record, the average click rate and the average popular degree. The method and the system are capable of automatically realizing differentiated processing on active users and non-active users, and hot videos and non-hot videos, and also capable of automatically digging out the popular statistical characteristics of data, for example, videos, and the recommendation results are not limited to the hottest data, for example, videos, so that lots of data, for example, videos, have a chance to be shown to different users.

Description

technical field

[0001] The invention relates to a data recommendation method and system. Background technique

[0002] With the explosive growth of Internet content, especially the rapid development of video sites and social networking sites, a large amount of fresh content is produced and consumed every day, and for a user, finding interesting information from a large amount of irrelevant data or content It is getting more and more difficult.

[0003] A common method of screening and recommending from a large amount of data or content is that the editors of the website manually mark high-quality content or content closely related to current affairs, and push it to the main page of the website, or notify each user. But this method is not only laborious, but also has obvious disadvantages: on the one hand, its update is slow and not timely enough; on the other hand, because users have different tastes, manual recommendation cannot meet the individual needs of users. [0004...

Examples

Embodiment 1

[0076] Such as figure 1 As shown, the present invention provides a data recommendation method, including:

[0077] Step S11, collect each user's selection records for each recommended data. Specifically, when a user visits the website, the website will display the recommended data (item) to the user (user) through different channels, such as search pages, recommended pages, browsing pages, etc. The user may click to watch, or may refuse to watch, Or bookmark the content to favorites, and after collecting the user's selection records of the content pushed by the website, it can be converted into a data structure that can be recognized and processed uniformly.

[0078] Preferably, the score of each user's selection record for each recommended data is represented by score(user, item), where user represents the user, and item represents the recommended data, including the acceptance of each recommended data for each user Record or reject the record, the score of the accepted rec...

Embodiment 2

[0107] Such as image 3 As shown, the present invention provides another data recommendation method. The difference between this embodiment and the embodiment is that the first N candidate data are obtained according to the average popularity of each recommended data to all recommended users, and then Calculating the recommendation score of each candidate data, so as to make the recommendation result more accurate, the method includes:

[0108] Step S21, collecting each user's selection records for each recommended data. Specifically, when a user visits the website, the website will display the recommended data (item) to the user (user) through different channels, such as search pages, recommended pages, browsing pages, etc. The user may click to watch, or may refuse to watch, Or bookmark the content to favorites, and after collecting the user's selection records of the content pushed by the website, it can be converted into a data structure that can be recognized and process...

Embodiment 3

[0139] Such as Figure 4 and 5 As shown, the present invention also provides another data recommendation system, including a data collection module 1 , a model generation module 2 and a result recommendation module 2 .

[0140] The data collection module 1 is used to collect each user's selection records for each recommended data. Specifically, when a user visits the website, the website will display the recommended data (item) to the user (user) through different channels, such as search pages, recommended pages, browsing pages, etc. The user may click to watch, or may refuse to watch, Or bookmark the content to favorites, and after collecting the user's selection records of the content pushed by the website, it can be converted into a data structure that can be recognized and processed uniformly.

[0141] Preferably, the score of each user's selection record for each recommended data is represented by score(user, item), where user represents the user, and item represents t...

technical field

[0001] The invention relates to a data recommendation method and system. Background technique

[0002] With the explosive growth of Internet content, especially the rapid development of video sites and social networking sites, a large amount of fresh content is produced and consumed every day, and for a user, finding interesting information from a large amount of irrelevant data or content It is getting more and more difficult.

[0003] A common method of screening and recommending from a large amount of data or content is that the editors of the website manually mark high-quality content or content closely related to current affairs, and push it to the main page of the website, or notify each user. But this method is not only laborious, but also has obvious disadvantages: on the one hand, its update is slow and not timely enough; on the other hand, because users have different tastes, manual recommendation cannot meet the individual needs of users. [0004...

Examples

Embodiment 1

[0076] Such as figure 1 As shown, the present invention provides a data recommendation method, including:

[0077] Step S11, collect each user's selection records for each recommended data. Specifically, when a user visits the website, the website will display the recommended data (item) to the user (user) through different channels, such as search pages, recommended pages, browsing pages, etc. The user may click to watch, or may refuse to watch, Or bookmark the content to favorites, and after collecting the user's selection records of the content pushed by the website, it can be converted into a data structure that can be recognized and processed uniformly.

[0078] Preferably, the score of each user's selection record for each recommended data is represented by score(user, item), where user represents the user, and item represents the recommended data, including the acceptance of each recommended data for each user Record or reject the record, the score of the accepted rec...

Embodiment 2

[0107] Such as image 3 As shown, the present invention provides another data recommendation method. The difference between this embodiment and the embodiment is that the first N candidate data are obtained according to the average popularity of each recommended data to all recommended users, and then Calculating the recommendation score of each candidate data, so as to make the recommendation result more accurate, the method includes:

[0108] Step S21, collecting each user's selection records for each recommended data. Specifically, when a user visits the website, the website will display the recommended data (item) to the user (user) through different channels, such as search pages, recommended pages, browsing pages, etc. The user may click to watch, or may refuse to watch, Or bookmark the content to favorites, and after collecting the user's selection records of the content pushed by the website, it can be converted into a data structure that can be recognized and process...

Embodiment 3

[0139] Such as Figure 4 and 5 As shown, the present invention also provides another data recommendation system, including a data collection module 1 , a model generation module 2 and a result recommendation module 2 .

[0140] The data collection module 1 is used to collect each user's selection records for each recommended data. Specifically, when a user visits the website, the website will display the recommended data (item) to the user (user) through different channels, such as search pages, recommended pages, browsing pages, etc. The user may click to watch, or may refuse to watch, Or bookmark the content to favorites, and after collecting the user's selection records of the content pushed by the website, it can be converted into a data structure that can be recognized and processed uniformly.

[0141] Preferably, the score of each user's selection record for each recommended data is represented by score(user, item), where user represents the user, and item represents t...

Images