CN113190758B - Server and media asset recommendation method - Google Patents
Server and media asset recommendation method Download PDFInfo
- Publication number
- CN113190758B CN113190758B CN202110557930.7A CN202110557930A CN113190758B CN 113190758 B CN113190758 B CN 113190758B CN 202110557930 A CN202110557930 A CN 202110557930A CN 113190758 B CN113190758 B CN 113190758B
- Authority
- CN
- China
- Prior art keywords
- media asset
- assets
- media
- asset
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/74—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0482—Interaction with lists of selectable items, e.g. menus
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a server and a medium resource recommendation method, wherein the server is configured to determine a medium resource recommendation list corresponding to a user portrait of a target terminal after receiving a medium resource recommendation request of the target terminal; the first N media assets are issued to a target terminal; receiving a media asset refreshing request of a target terminal; if click information representing that a user clicks the media assets is received before the media asset refreshing request is received, reordering the issuing sequence of the non-issued media assets in the media asset recommendation list according to the content attributes of the clicked media assets and the content attributes of the non-issued media assets in the media asset recommendation list, and issuing the first M media assets in the reordered media asset recommendation list to a target terminal; and if not, issuing the first M undelivered media assets in the media asset recommendation list to the target terminal. According to the method and the device, the accuracy of media asset recommendation is improved, and the user experience of media asset recommendation is improved.
Description
Technical Field
The application relates to the technical field of media asset recommendation, in particular to a server and a media asset recommendation method.
Background
The intelligent television is an important display device for people to watch media assets such as TV dramas, movies and the like. In order to enable people to watch favorite media assets, a server of the smart television generally analyzes the media assets which are possibly interested by people through some media asset recommendation algorithms, and then displays the media assets which are possibly interested by people on some media asset recommendation pages of the smart television, so that users can request the media assets.
In the related technology, in order to improve the accuracy of recommending the media assets, a media asset recommending algorithm can recommend the media assets according to historical watching records on an intelligent television. However, on a home smart television or a smart television used by multiple users, there may be multiple historical viewing records, so that a media asset recommendation list generated by a media asset recommendation algorithm according to the multiple historical viewing records contains media assets interested by multiple users, the media assets interested by the current user may be scattered at the head, the middle and the tail of the media asset recommendation list, and if the media assets are scattered at the middle and the tail of the media asset recommendation list, the media assets not interested by the current user are all seen by the current user on the first few pages of the media asset recommendation page, so that the interest of the media asset recommendation list is lost, and an application scene is switched.
Disclosure of Invention
In order to solve the technical problem that medium asset recommendation is inaccurate, the application provides a server and a medium asset recommendation method.
In a first aspect, the present application provides a server configured to:
after a media asset recommendation request of a target terminal is received, determining a media asset recommendation list of a user portrait corresponding to the target terminal;
issuing the first N media assets in the media asset recommendation list to the target terminal, wherein the number of the media assets in the media asset recommendation list is more than or equal to N +2, and N is more than or equal to 1;
receiving a media asset refreshing request of the target terminal;
if click information representing that a user clicks the media assets is received before the media asset refreshing request is received, reordering the issuing sequence of the media assets which are not issued in the media asset recommendation list according to the content attributes of the clicked media assets and the content attributes of the media assets which are not issued in the media asset recommendation list, and issuing the first M media assets in the rearranged media asset recommendation list to the target terminal so that the media assets which are close to the content attributes of the clicked media assets in the media asset recommendation list are issued to the target terminal preferentially;
and if click information representing that a user clicks the media assets is not received before the media asset refreshing request is received, issuing the first M undelivered media assets in the media asset recommendation list to the target terminal, wherein M is more than or equal to 2 and less than or equal to N.
In a second aspect, the present application provides a method for recommending media assets, including:
after a media asset recommendation request of a target terminal is received, determining a media asset recommendation list corresponding to a user portrait of the target terminal;
issuing the first N media assets in the media asset recommendation list to the target terminal, wherein the number of the media assets in the media asset recommendation list is more than or equal to N +2, and N is more than or equal to 1;
receiving a media asset refreshing request of the target terminal;
if click information representing that a user clicks the media assets is received before the media asset refreshing request is received, reordering the issuing sequence of the media assets which are not issued in the media asset recommendation list according to the content attributes of the clicked media assets and the content attributes of the media assets which are not issued in the media asset recommendation list, and issuing the first M media assets in the rearranged media asset recommendation list to the target terminal so that the media assets which are close to the content attributes of the clicked media assets in the media asset recommendation list are issued to the target terminal preferentially;
and if click information representing that a user clicks the media assets is not received before the media asset refreshing request is received, issuing the first M undelivered media assets in the media asset recommendation list to the target terminal, wherein M is more than or equal to 2 and less than or equal to N.
The server and the medium resource recommendation method provided by the application have the beneficial effects that:
according to the method and the device, historical watching records of multiple users on the same display device are analyzed, and association rules among media assets are mined, so that when media asset recommendation is performed on the current user, the issuing sequence of the media assets is adjusted in time according to the real-time media asset on-demand records of the current user and the association rules among the media assets, the current user can see interesting media assets at the position arranged ahead, accurate media asset recommendation is achieved, and user experience is improved.
Drawings
In order to more clearly describe the technical solution of the present application, the drawings required to be used in the embodiments will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive labor.
Fig. 1 is a schematic diagram illustrating an operational scenario between a display device and a control apparatus according to some embodiments;
FIG. 2 illustrates a home schematic of a display device according to some embodiments;
FIG. 3 is a diagram illustrating a timing of generation of association rules, according to some embodiments;
FIG. 4 is a diagram illustrating interaction timing in a media asset recommendation process, according to some embodiments;
FIG. 5 illustrates a home schematic of a display device according to some embodiments;
a top page schematic of a display device according to some embodiments is illustrated in fig. 6.
Detailed Description
To make the purpose and embodiments of the present application clearer, the following will clearly and completely describe the exemplary embodiments of the present application with reference to the attached drawings in the exemplary embodiments of the present application, and it is obvious that the described exemplary embodiments are only a part of the embodiments of the present application, and not all the embodiments.
It should be noted that the brief descriptions of the terms in the present application are only for convenience of understanding of the embodiments described below, and are not intended to limit the embodiments of the present application. These terms should be understood in their ordinary and customary meaning unless otherwise indicated.
The terms "first," "second," "third," and the like in the description and claims of this application and in the foregoing drawings are used for distinguishing between similar or analogous objects or entities and are not necessarily intended to limit the order or sequence in which they are presented unless otherwise indicated. It is to be understood that the terms so used are interchangeable under appropriate circumstances.
The terms "comprises" and "comprising," as well as any variations thereof, are intended to cover a non-exclusive inclusion, such that a product or device that comprises a list of elements is not necessarily limited to all of the elements explicitly listed, but may include other elements not expressly listed or inherent to such product or device.
The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and/or software code that is capable of performing the functionality associated with that element.
Fig. 1 is a schematic diagram of an operation scenario between a display device and a control apparatus according to an embodiment. As shown in fig. 1, a user may operate the display apparatus 200 through the smart device 300 or the control device 100.
In some embodiments, the control device 100 may be a remote controller, and the communication between the remote controller and the display device includes an infrared protocol communication or a bluetooth protocol communication, and other short-distance communication methods, and the display device 200 is controlled by a wireless or wired method. The user may input a user command through a key on a remote controller, a voice input, a control panel input, etc. to control the display apparatus 200.
In some embodiments, a smart device 300 (e.g., a mobile terminal, a tablet, a computer, a laptop, etc.) may also be used to control the display device 200. For example, the display device 200 is controlled using an application program running on the smart device.
In some embodiments, the display device 200 may also be controlled in a manner other than the control apparatus 100 and the smart device 300, for example, the voice command control of the user may be directly received by a module configured inside the display device 200 to obtain a voice command, or may be received by a voice control device provided outside the display device 200.
In some embodiments, the display device 200 is also in data communication with a server 400. The display device 200 may be allowed to be communicatively connected through a Local Area Network (LAN), a Wireless Local Area Network (WLAN), and other networks. The server 400 may provide various contents and interactions to the display apparatus 200. The server 400 may be a cluster or a plurality of clusters, and may include one or more types of servers.
In some embodiments, the display device may display a home page of the device after being activated, and an interface of the home page, as shown in fig. 2, includes at least a navigation bar and a content display area located below the navigation bar, and content displayed in the content display area changes according to a change of a selected control in the navigation bar. The programs in the application program layer can be integrated in the video-on-demand program and displayed through one control of the navigation bar, and can also be further displayed after the application control in the navigation bar is selected.
In some embodiments, the display device may directly enter a display interface of a signal source selected last time after being started, or a signal source selection interface, where the signal source may be a preset video-on-demand program, or may be at least one of an HDMI interface, a live tv interface, and the like, and after a user selects different signal sources, the display may display contents obtained from different signal sources.
In some embodiments, referring to fig. 2, the navigation bar may be provided with a plurality of controls, such as "my", "channel", "movie", "fitness", "VIP", "education", "mall", "game" and application, different navigation bar controls correspond to different interfaces, different interfaces may display different assets in the content display area, fig. 2 is an interface corresponding to the "channel" control, as shown in fig. 2, the content display area under the "channel" control may display a plurality of asset controls, respectively corresponding to assets 1 to 10, after a user clicks one asset control, a detailed page corresponding to the asset control may be entered, or a playing interface corresponding to the asset control may be entered, and the user may also turn down a page in fig. 2 by pressing a down key of the remote controller to view other asset controls.
In some embodiments, the media asset data corresponding to the media asset control is issued to the display device by the server, the server may generate a media asset recommendation list with an issuing order according to some media asset recommendation algorithms, and then send the media asset data corresponding to the media asset recommendation list to the display device according to the issuing order, so that the display device displays the corresponding media asset. The issuing sequence can be expressed as the interest degree of the user on the media assets calculated according to the media asset recommendation algorithm, the more front the issuing sequence is, the more interest the user is possibly on the media assets, and the display equipment displays the media assets at the more front position. For example, in fig. 2, the delivery sequence of the asset 1 is earlier than the delivery sequence of the asset 2, and the display device displays the asset 1 at a relatively earlier position and displays the asset 2 at a relatively later position accordingly.
The accuracy of the media asset recommendation algorithm is limited, the conformity between the issuing sequence and the user interest may not meet the expectation, at this time, the problems that some media assets which are not interested by the user are arranged relatively earlier and some media assets which are interested by the user are arranged relatively later will occur, so that the user needs to turn pages for many times in fig. 2 to find the media assets which are interested by the user, and the user experience is poor.
Of course, in addition to the top page scenario shown in fig. 2, in some other scenarios that require displaying of the assets, such as a scenario that a detailed page of the assets displays the associated assets, a problem that the arrangement order of the assets is poor in conjunction with the user interest may also occur.
In order to solve the technical problem, an embodiment of the present application provides a method for recommending media assets, where relevance of media assets is analyzed in advance, and then a server adjusts an issuing sequence of media assets to be issued in real time in combination with user feedback, so that a user can find a media asset interested in the user at a position before sorting when a page is turned, and user experience is improved.
In some embodiments, the server analyzes the relevance between the media assets according to the media asset viewing record of the user on the display device to obtain a relevance rule between media asset content attribute tags, where the media asset content attribute tags may be media asset tags set by a media asset provider, or media asset tags set by a server side of the display device, and may represent content types of the media assets or some content features of the media assets, for example, the media asset content attribute tags may be cities, stories, ancient installations, actions, and the like.
Referring to fig. 3, a schematic diagram of a generation timing sequence of association rules according to some embodiments is shown in fig. 3, where the server of the display device may include an interface server, a storage server, and an offline calculation server, where the interface server may be used to interact with the display device and interact with other servers, the storage server may be used to store data such as media data and user data, the storage server may be a codis, and the offline calculation server may be used to mine the association rules.
In some embodiments, a user may log in a user _ id (user account) on the display device, and after the login is successful, the display device may store the currently logged-in user account in the first preset storage path. The media asset control displayed on the display device can correspond to some media asset information, the media asset information can be obtained by the display device from interface data of a media asset recommendation page issued by the server, the display device can store the media asset information to a second preset storage path, wherein the media asset recommendation page can comprise a first page of the display device, and the media asset information can comprise media asset id.
In some embodiments, after the user requests the media asset on the display device, the display device may obtain the user _ id from the first preset storage path, obtain the media asset id from the second preset storage path, and generate a media asset request log. Illustratively, the asset on-demand log of a certain asset may be Ti = (user _ id, item _ Ti, length, click _ time, end _ time), where item _ Ti may be asset id, length is asset duration, click _ time is a timestamp of beginning playing of the asset, and end _ time represents a timestamp of ending playing of the asset. The display device may be configured to upload the asset-on-demand log to the interface server in real time after the asset-on-demand log is generated.
In some embodiments, after receiving the media asset on-demand log, the interface server sends the media asset on-demand log to the storage server for storage.
In some embodiments, the offline computing server may collect the media asset on-demand logs for a preset time from the storage server, for example, collecting the media asset on-demand logs for a month, such as T1, T2, T3, \ 8230;, ti, \ 8230, and then analyze the media asset on-demand logs. These asset on-demand logs may be recorded as historical asset on-demand logs.
In some embodiments, for multiple media asset on-demand logs corresponding to one user id, the multiple media asset on-demand logs may be generated by the same person watching media assets, for example, only children watch television in a family, or multiple persons watch media assets, for example, dad, mom and children watch television in the family, the media asset on-demand log corresponding to dad may be several action films, the on-demand log corresponding to mom may be several ancient dramas, and the media asset on-demand log corresponding to children may be several animation films. The media assets watched by different people may have larger difference on the media asset content attribute labels, and the media assets watched by the same person may have smaller difference on the media asset content attribute labels. In addition to the differences in the media asset content attribute tags, there may be differences in the times at which different people watch television, for example, the times at which children watch television may be after dinner, and the times at which dad and mom watch television may be after the children fall asleep. The off-line computing server can divide the media asset on-demand logs within the preset time, divide the media asset on-demand logs with the collection interval smaller than the first time into logs generated by the watching behavior of the same user, and then generate a media asset sequence according to the media assets corresponding to the logs; and judging the media asset on-demand logs with the collection interval being larger than or equal to the first time as logs generated by the watching behaviors of different users, and then generating a plurality of media asset sequences according to the media assets corresponding to the logs.
For example, for two consecutive asset on-demand logs Tn and Tn +1 corresponding to the user ids, when the time between the end _ time of Tn and the click _ time of Tn +1 is less than x minutes, default viewing behaviors of Tn and Tn +1 corresponding to the same user can be determined, and it is determined that the asset content attribute tags of assets corresponding to Tn and Tn +1 all belong to tags in which the same user is interested, where, for example, x is the first time, such as 10 minutes; when the time between the end _ time of Tn and the click _ time of Tn +1 is greater than or equal to x minutes, the watching behaviors of different users corresponding to Tn and Tn +1 can be defaulted, and the asset content attribute tags of assets corresponding to Tn and Tn +1 are judged to belong to tags in which the different users are interested.
In some embodiments, before the offline computing server divides the media asset on-demand logs, or after the media asset sequence is obtained, the offline computing server may further screen the media asset on-demand logs to remove media asset on-demand logs corresponding to media assets with short viewing time. For example, if the end _ time-click _ time/length < rate in the asset on-demand log is determined as the asset that is not interested by the current user, the asset needs to be removed from the asset sequence, where the rate is the viewing progress ratio of the asset, and may be set according to actual conditions, and exemplarily, the rate may be 0.1.
In some embodiments, after the offline computing server divides the media asset on-demand log within the preset time according to the above method, a plurality of media asset sequences can be obtained. Illustratively, two of the asset sequences may be [ item _ T1, item _ T2, item _ T4], [ item _ T5, item _ T6, item _ T9].
In some embodiments, the offline computation server may count the asset content attribute tags corresponding to each asset sequence, thereby converting the asset sequence into an asset content attribute tag set. The offline computing server can acquire the media asset content attribute labels corresponding to each media asset in the media asset sequence from the storage server.
For example, the asset content attribute tags of item _ T1 include (tag 1, tag2, tag 3), the asset content attribute tags of item _ T2 include (tag 3, tag5, tag 7), and the asset content attribute tags of item _ T4 include (tag 2, tag 5), so that the set of asset content attribute tags corresponding to the asset sequence [ item _ T1, item _ T2, item _ T4] is (tag 1, tag2, tag3, tag5, tag 7), and these five asset content attribute tags can be determined as the tag set of interest of the same user.
In some embodiments, the offline server may further set a weight for the asset content attribute tag, and store the asset content attribute tag in a data structure of a dictionary, for example, a set of asset content attribute tags corresponding to [ item _ T1, item _ T2, item _ T4] may be set as { tag1:1, tag 2. Along with the increase of the media assets requested by the user, the media asset content attribute label set is also increased, and the labels with too low weight in the media asset content attribute label set can be removed, so that only the relevance between the head labels with high weight is analyzed subsequently, the error relevance of the labels with low weight can be avoided, and the effectiveness and the reliability of the relevance rule can be improved.
In some embodiments, after obtaining a plurality of sets of media asset content attribute tags corresponding to the media asset on-demand log within a period of time, the offline server may calculate a correlation degree between two media asset content attribute tags according to the number of times that the two media asset content attribute tags appear in the media asset sequence within the preset time, and set an association rule between the two media asset content attribute tags whose correlation degree exceeds a preset threshold.
In some embodiments, the relevancy includes three indexes, i.e., support degree, confidence degree and boost degree, each index may be provided with a threshold, and when the three indexes between two media asset content attribute tags exceed respective thresholds, an association rule may be set between the two media asset content attribute tags.
For example, if one association rule is: the label (swordsman) > label (speech), if the user likes the media assets with the swordsman label, the user probably likes the media assets with the speech label, and accordingly, the associated media asset recommendation can be performed.
In some embodiments, an association rule may also correspond to multiple tags, for example, if an association rule is a tag (immortal) - > tag (sentiment) - > tag (ancient dress), then indexes of support, confidence and promotion need to be achieved between every two tags in the association rule, and the association rule is established.
In some embodiments, the support degree is a ratio of the number of times that the tag1 and the tag2 of the content attribute of the media asset appear in one tag set of the content attribute of the media asset to the number of the tag sets of the content attribute of the media asset, and when the support degree is greater than a first threshold value, it can be determined that the tag1 and the tag2 have a certain correlation, and a frequent item set including the tag1 and the tag2 is generated, thereby excluding the contingency that the tag1 and the tag2 appear in one tag set of the content attribute of the media asset at the same time. The calculation formula of the support degree support is as follows:
in the above equation, freq represents a probability. And N is the number of the media asset content attribute label sets.
In some embodiments, the confidence level refers to a conditional probability that when the asset content attribute tag1 exists in one asset sequence, the asset content attribute tag1 also exists in the same asset sequence, which may indicate that in a case where the user is interested in tag1, the user is also interested in tag 2. The confidence coefficient can be used for determining the strength of the association rules between tag1- > tag2, the offline server can respectively calculate the confidence coefficient of each frequent item set, and the association rules with the confidence coefficients larger than the minimum threshold value are reserved. The calculation formula of the confidence is as follows:
in some embodiments, the promotion degree may be used to verify whether the association rule determined according to the support degree and the confidence degree is valid, that is, after tag1- > tag2 is selected as the association rule, whether the total number of times that the tag1 and tag2 of the asset content appear in the same asset content attribute tag set is higher than the product of the number of times that the two tags appear in one asset content attribute tag set individually. And if the ratio of the total times to the product is greater than 1, determining that the association rule is valid, and if the ratio is less than 1, determining that the association rule is invalid. The calculation formula of the Lift is as follows:
in some embodiments, according to the calculation of the correlation degree, after obtaining the plurality of association rules, the offline server may store the association rules in the storage server.
In some embodiments, the association rule may be applied to sort the plurality of assets according to the user interests, for example, when the user browses the assets on the display device, the interface server may call the association rule to reorder the assets to be delivered. Referring to fig. 4, which is a schematic diagram of an interaction timing sequence in a media asset recommendation process, as shown in fig. 4, in a media asset recommendation scene, which is a home page of a display device, the display device may interact with an interface server, and the interface server may interact with a storage server respectively to obtain association rules stored by the storage server, and interact with a recommendation algorithm server to obtain media asset recommendation data.
In some embodiments, after the user starts the display device, the display device may send a home page request to the interface server, where the home page request may include the user id the display device is currently logged in. After receiving the home page request, the interface server generates a media asset recommendation request according to a media asset recommendation bit set in preset home page data, wherein the media asset recommendation request can include the user id. And the interface server sends the medium resource recommendation request to the recommendation algorithm server.
In some embodiments, after receiving the medium resource recommendation request, the recommendation algorithm server may calculate the medium resource recommendation data of the user id according to a recommendation algorithm, where the medium resource recommendation data may include a medium resource recommendation list of the user portrait corresponding to the user id.
In some embodiments, the user representation may be obtained based on user behaviors of all users of the user id, the user behaviors may include operations of media asset on demand, media asset collection and the like, and the user behaviors may be obtained through log-type data such as a media asset on demand log and a media asset collection log. The recommendation algorithm server generates a user-interested media asset label according to user behavior, wherein the media asset label is not limited to a media asset content attribute label, but also comprises other labels, such as a media asset duration label and the like, the media asset labels are determined as user figures, then media assets conforming to the labels are searched in a media asset library, and a media asset recommendation list with a plurality of media asset ids is generated according to the degree of engagement between the searched media assets and the user figures, wherein the degree of engagement can comprise the overlapping number of the labels, or different labels can have different weights, and the degree of engagement can be a numerical value calculated by combining the overlapped labels and the weights. The arrangement sequence of the medium asset id in the medium asset recommendation list can be a default issuing sequence, and the higher the fit between the medium asset corresponding to the medium asset id and the portrait of the user is, the more the issuing sequence of the medium asset id is advanced. Illustratively, the asset recommendation list may include asset ids for 100 assets.
In some embodiments, the recommendation algorithm server may send the media asset recommendation data to the interface server and the storage server after generating the media asset recommendation data. The interface server can acquire the media asset ids of the first quantity of media assets in the front sequence from the media asset recommendation list, then acquire the media asset data corresponding to the media asset ids from the storage server, pack the media asset data into the first page data and send the first page data to the display device, wherein the first page data can also include some arrangement data besides the media asset data, such as the position and size of the recommendation control.
In some embodiments, the recommendation algorithm server may also send only the media asset recommendation data to the storage server after generating the media asset recommendation data. The interface server can acquire the media asset recommendation list from the storage server, then acquire the media asset data corresponding to the media asset id of the first quantity of media assets in the front sequence from the storage server, package the media asset data into the first page data and send the first page data to the display device.
In some embodiments, after receiving the top page data, the display device may display the first number of assets on the top page, where the first number may be N, N is greater than or equal to 1, as shown in fig. 2, the first number may be 10, and the display device may display 10 assets, namely, assets 1-10, on the top page. Of course, the first number may be other values, such as 15, and if the first number is 15, the display device may display assets 1-15 on the top page.
In some embodiments, after the display device displays a first amount of assets, there may be assets that are interesting to the user in the assets, and the user may select one or more of the assets to watch, where each time the user requests one asset, the display device may send a media asset request log to the interface server, where the media asset request log may be recorded as a first media asset request log representing a user request log after the interface server issues media asset recommendation data for the first time, and includes click information representing that the user clicks the assets, such as request time, exit time, and the like.
In some embodiments, after the user broadcasts several pieces of assets in fig. 2, the user may not be interested in the remaining assets on the top page, the user may press a down key of the remote controller to turn pages to refresh the asset recommendation page, the display device generates an asset refresh request according to a trigger signal received from the down key and a current display interface as a top page interface, and then sends the asset refresh request to the interface server, where the asset refresh request may include a user id.
In some embodiments, after the user requests all the first amount of assets displayed on the home page, the display device may also generate an asset refresh request according to the generated first amount of asset request logs, so as to request the interface server to update the assets of the home page interface. The asset refresh request is a first asset refresh request.
In some embodiments, after the user browses the first amount of assets on the home page, the user is not interested in the first amount of assets, at this time, the user can press a down key of the remote controller to turn pages, so as to generate a media asset refreshing request, and because the user does not request the media assets, the interface server does not receive a media asset request log before receiving the media asset refreshing request.
In some embodiments, after receiving the media asset refresh request, if the media asset on-demand log is not received, the interface server may directly issue a first second number of media assets, which are not issued in the media asset recommendation list, to the display device, where the second number may be M, M is greater than or equal to 2, before issuing, when the number of media assets, which are not issued in the media asset recommendation list, is greater than or equal to N, M may be equal to N, and when the number of media assets, which are not issued in the media asset recommendation list, is less than N, M may be less than N.
In some embodiments, after receiving the media asset refreshing request, if the media asset on-demand log is received, the interface server may obtain the association rule stored by the offline server from the storage server, and then reorder, in combination with the first media asset on-demand log of the user, the non-delivered media assets in the media asset recommendation list, where the non-delivered media assets may be the media asset data of the (N + 1) th media asset in the media asset recommendation list and the subsequent media asset data of the media asset.
In some embodiments, the interface server performs the reordering as follows:
firstly, an interface server obtains a media asset content attribute tag corresponding to a media asset id in a first media asset on-demand log, wherein the media asset corresponding to the media asset id in the first media asset on-demand log can be marked as a first on-demand media asset, and the media asset content attribute tag of the first on-demand media asset can be determined as a first tag.
And secondly, the interface server can acquire other media asset content attribute tags associated with the first tags according to the association rules, and determine the associated tags as second tags.
And thirdly, determining the first label and the second label as target labels, generating a set containing the target labels, and determining the set as a user interest label set.
And determining a content attribute tag of the undelivered media asset as a third tag, matching tags in the user interest tag set with the third tag to obtain the matching degree of the undelivered media asset, and determining a matching degree sequence for each undelivered media asset according to the matching degree, wherein the matching degree can be the superposition number of the user interest tag set and the third tag of the undelivered media asset, and the higher the superposition number is, the higher the matching degree is.
And finally, determining a new issuing sequence of the undelivered medium assets according to the matching degree sequence.
For example, one media asset recommendation List is List1, list1= [ item1, item2, item3,.. And item100], and after determining that the user clicks on item1 according to the first media asset ordering log, the current user may be considered to be interested in the content attribute tag [ tag1, tag2, tag5] of item 1. If the association rules tag1- > tag4, tag2- > tag4, tag2- > tag5 exist, comparing the content attribute tags of the media assets which are not issued in the media asset recommendation list with the user interest tag sets (tag 1, tag2, tag4 and tag 5), wherein the higher the matching degree is, the greater the probability of the current user interest is, and therefore the media asset recommendation list can be reordered according to the matching degree. If the content attribute tags of the media asset item13 are (tag 3, tag5, tag 6), the number of the media asset item13 overlapping with the media asset item1 is 1, and by analogy, the matching degree sequence can be calculated to generate a matching degree sequence table. Taking item11-item20 in the media asset recommendation list as an example, the matching degree order table can be seen in table 1.
TABLE 1
According to table 1, after reordering, each asset has two orderings, one is a sequence number in an issuing sequence in the asset recommendation list generated by the recommendation algorithm, the issuing sequence can be recorded as an original sequence, the sequence number of the original sequence can be represented by an order _ origin, the other is a sequence number in a matching degree sequence calculated according to the user interest content attribute tag set, and the sequence number of the matching degree sequence can be represented by an order _ match.
In some embodiments, the interface server may directly issue the media asset data of the second number of media assets to the display device according to the matching degree sequence, so that the display device refreshes the top page to display the second number of media assets. If the matching degree sequence of the two pieces of media resources is the same, the media resource data of the media resources with the former original sequence can be preferentially issued. For example, in table 1, the matching degree sequence of item11 and item20 is 2, and item11 is preferentially issued according to the earlier original sequence of item11.
In some embodiments, in order to avoid overruling, the interface server may also weight the original order and the matching degree order to obtain a compromise order, then store the media asset recommendation list with the delivery order being the compromise order into the storage server, and deliver the media asset data of the first M media assets after the nth media asset to the display device according to the compromise order, where the sequence number of the compromise order may be represented by order _ new, and the interface server may deliver the media asset data of the second number of media assets according to the compromise order. The calculation formula of the compromise order may be:
X(order_new)＝w1*X(order_origin)+w2*X(order_match)
wherein, X represents the sequence, w1 is the weight of the original sequence of the non-delivered assets in the asset recommendation list, the weight can be recorded as a first weight, w2 is the weight of the matching degree sequence, the weight can be recorded as a second weight, the sum of w1 and w2 is 1, and w1 and w2 are both greater than or equal to 0.
In some embodiments, when the interface server performs reordering, the label weight of each label in the user interest label set may be further obtained from a dictionary generated by the offline server, and if there is a label overlapping with a label with a higher label weight in a non-delivered medium asset, the matching degree of the medium asset is higher. For example, in table 1, if there is a tag that overlaps both item13 and item18 with the user interest tag set, item13 is preferentially issued according to the higher the tag weight of the tag that overlaps item13.
In some embodiments, the display device may refresh a top page of the display device to display the second amount of assets after receiving the asset data of the second amount of assets.
Referring to fig. 5, which is a schematic view of a home interface of a display device according to some embodiments, as shown in fig. 5, a second amount of top-ranked media assets obtained by an interface server after reordering are media asset 12, media asset 34, media asset 16, media asset 11, media asset 25, media asset 42, media asset 14, media asset 56, media asset 19, and media asset 30, and before reordering, a second amount of media assets after media asset 1-media asset 10 are respectively media asset 11-media asset 20.
In some embodiments, after the display device displays the second amount of the media assets, the user may select one or more media assets from the media assets for watching, where each time the user requests one media asset, the display device may send a media asset request log to the interface server, where the media asset request log may be recorded as a second media asset request log indicating a user request log after the interface server issues the media asset recommendation data for the second time.
In some embodiments, after the user broadcasts several assets in fig. 5, the user may press a down key of the remote controller to turn pages to refresh the asset recommendation page again, the display device generates an asset refresh request according to the trigger signal received from the down key and the current display interface as a top page interface, and then sends the asset refresh request to the interface server, where the asset refresh request may include a user id.
In some embodiments, after the user requests all the second amount of assets shown in fig. 5, the display device may also generate an asset refresh request according to the second amount of second asset request logs generated, so as to request the interface server to update the assets of the home interface. The asset refresh request is a second asset refresh request.
In some embodiments, after receiving the media asset refreshing request, the interface server may dynamically adjust an issuing sequence of non-issued media assets according to the second media asset on-demand log, where the non-issued media assets may be the media asset data of the (N + M + 1) th media asset in the media asset recommendation list and the subsequent media asset data of the media asset. The adjusting method comprises the following steps:
the interface server can preset N indexes for expressing the quality of user feedback, and the initial value of N is 0; acquiring a media asset id of a media asset in a second media asset on-demand log, then acquiring a sequence number of an original sequence of the media asset id and a reordered sequence number, if the reordered sequence number is smaller than the sequence number of the original sequence, increasing the value of N, if the value of N is increased by 1, taking the value of N as a primary correction positive feedback, otherwise, decreasing the value of N, and taking the value of N as a primary correction negative feedback; according to the second media asset on-demand logs, multiple user feedbacks can be obtained, and then the following calculation is carried out: j = N/P, J E [ -1,1], J can be used as an index of the weight effectiveness of the current matching degree sequence, the more the J is smaller than 0 and closer to-1, the weight of the matching degree sequence can be reduced when the weight of the current matching degree sequence is too large, the more the J is larger than 0 and closer to 1, the weight of the matching degree sequence can be increased continuously when the weight of the current matching degree is effective.
In some embodiments, after the weight of the matching degree sequence is adjusted according to the feedback of the user, the compromise sequence can be recalculated according to the new weight to obtain a new issuing sequence, then the media asset recommendation list with the issuing sequence being the new issuing sequence is stored in the storage server, and the media asset data of the first third number of media assets after the N + M number of media assets are issued according to the new issuing sequence are sent to the display device, wherein the third number can be P, before issuing, if the number of the media assets which are not issued in the media asset recommendation list is greater than or equal to N, P can be equal to N, and when the number of the media assets which are not issued in the media asset recommendation list is less than N, P can be less than N.
In some embodiments, after receiving the asset data of the third amount of assets, the display device may refresh a top page of the display device to display the third amount of assets.
Referring to fig. 6, which is a schematic view of a home interface of a display device according to some embodiments, as shown in fig. 6, a third quantity of top-ranked assets obtained by the interface server after performing dynamic adjustment are asset 15, asset 21, asset 27, asset 18, asset 36, asset 20, asset 67, asset 31, asset 58, and asset 17.
In some embodiments, the user may play some media assets for viewing in fig. 6, and each time a media asset is played, the display device may send a media asset play log to the interface server, where the media asset play log may be recorded as a third media asset play log to indicate a user play log after the interface server issues media asset recommendation data for the third time, and so on.
According to the embodiment, the historical watching records of multiple users on the same display device are analyzed, and the association rules among the media assets are mined, so that when the media asset recommendation is performed on the current user, the issuing sequence of the media assets is timely adjusted according to the real-time media asset on-demand records of the current user and the association rules among the media assets, the current user can see the interested media assets at the position arranged ahead, accurate media asset recommendation is achieved, and user experience is improved.
Since the above embodiments are all described by referring to and combining with other embodiments, the same portions are provided between different embodiments, and the same and similar portions between the various embodiments in this specification may be referred to each other. And will not be described in detail herein.
It is noted that, in this specification, relational terms such as "first" and "second," and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such circuit structure, article, or apparatus. Without further limitation, the phrases "comprising a" \8230; "defining an element do not exclude the presence of additional like elements in circuit structures, articles, or devices comprising the element.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
The above embodiments of the present application do not limit the scope of the present application.
Claims (9)
1. A server, wherein the server is configured to:
after a media asset recommendation request of a target terminal is received, determining a media asset recommendation list of a user portrait corresponding to the target terminal;
issuing the first N media assets in the media asset recommendation list to the target terminal, wherein the number of the media assets in the media asset recommendation list is more than or equal to N +2, and N is more than or equal to 1;
receiving a media asset refreshing request of the target terminal;
if click information representing that a user clicks the assets is received before the assets refreshing request is received, determining a first label and a second label associated with the first label according to the content attributes of the clicked assets, determining the first label and the second label as target labels, determining a third label according to the content attributes of the assets which are not delivered, obtaining the matching degree sequence of the assets which are not delivered according to the matching degree of the third label and the target label, re-sequencing the delivery sequence of the assets which are not delivered in the assets recommendation list according to the matching degree sequence, and delivering the first M assets in the re-sequenced assets recommendation list to the target terminal so that the assets which are close to the content attributes of the clicked assets in the assets recommendation list are preferentially delivered to the target terminal, wherein M is greater than or equal to 2 and less than or equal to N;
and if click information representing that a user clicks the media assets is not received before the media asset refreshing request is received, issuing the first M undelivered media assets in the media asset recommendation list to the target terminal.
2. The server of claim 1, wherein determining a first tag and a second tag associated with the first tag according to the content attribute of the clicked-on asset comprises:
determining a first label according to the content attribute of the clicked medium asset;
and determining a second label associated with the first label according to an association rule, wherein the association rule is obtained according to a historical media asset on-demand log of the target terminal within a preset time.
3. The server according to claim 1, wherein the association rule is obtained according to a historical media asset on-demand log of the target terminal within a preset time, and includes:
generating a medium resource sequence by the historical medium resource on-demand log according to the historical medium resource on-demand log of the acquisition interval in the first time;
acquiring a media asset content attribute label corresponding to each media asset sequence within the preset time;
calculating the correlation degree between the two media asset content attribute labels according to the occurrence times of the two media asset content attribute labels in all the media asset sequences;
and setting an association rule between the two media asset content attribute labels with the correlation degree exceeding a preset threshold value.
4. The server according to claim 3, wherein the obtaining of the media asset content attribute tag corresponding to each media asset sequence within the preset time comprises:
and acquiring the media asset content attribute labels of which the coincidence times corresponding to each media asset sequence in the preset time exceed a preset threshold.
5. The server of claim 3, wherein calculating the correlation between two asset content attribute tags according to the number of occurrences of the two asset content attribute tags in the entire asset sequence comprises:
obtaining the support degree of the two media asset content attribute labels according to the proportion of the number of times that the two media asset content attribute labels simultaneously appear in one media asset sequence to the number of all media asset sequences in the preset time;
obtaining the confidence degrees of two media asset content attribute labels according to the conditional probability that when one media asset content attribute label exists in one media asset sequence, the other media asset content attribute label also exists in the same media asset sequence;
calculating the total times of the two media asset content attribute tags existing in one media asset sequence at the same time, and calculating the product of the times of the two media asset content attribute tags existing in one media asset sequence independently to obtain the promotion degrees of the two media asset content attribute tags;
the relevance includes the support degree, the confidence degree and the promotion degree.
6. The server of claim 1, wherein adjusting the distribution sequence of the undelivered assets in the asset recommendation list according to the matching degree sequence comprises:
setting an original sequence of the undelivered media assets in the media asset recommendation list as a first weight, wherein the original sequence is a distribution sequence determined by the recommendation algorithm;
setting the matching degree sequence as a second weight;
and calculating the issuing sequence of the undelivered medium resources in the medium resource recommendation list according to the first weight and the second weight.
7. The server of claim 6, wherein the server is further configured to:
after issuing the reordered media assets to the target terminal, receiving a media asset refreshing request of the target terminal again;
if click information representing that the user clicks the reordered assets is received before the asset refreshing request is received again, the first weight and the second weight are adjusted according to the sequence of the clicked reordered assets before reordering and the sequence of the reordered assets, so as to obtain a new issuing sequence of undelivered assets, and the assets in the asset recommendation list are issued to the target terminal according to the new issuing sequence.
8. The server of claim 7, wherein the adjusting the first weight and the second weight according to the order of the clicked re-ordered assets before the re-shooting order and the order of the clicked re-ordered assets after the re-shooting order to obtain a newly issued sequential asset recommendation list of the non-issued assets comprises:
if the order of the clicked reordered media assets after the re-shooting is smaller than the order of the media assets before the re-ordering, increasing a second weight;
if the order of the clicked reordered media assets after the order is re-shot is larger than or equal to the order of the media assets before the order is re-ordered, reducing the second weight;
and calculating a new issuing sequence of the undelivered media assets in the media asset recommendation list according to the adjusted second weight.
9. A method for recommending media assets is characterized by comprising the following steps:
after a media asset recommendation request of a target terminal is received, determining a media asset recommendation list of a user portrait corresponding to the target terminal;
issuing the first N media assets in the media asset recommendation list to the target terminal, wherein the number of the media assets in the media asset recommendation list is more than or equal to N +2, and N is more than or equal to 1;
receiving a media asset refreshing request of the target terminal;
if click information representing that a user clicks the medium resources is received before the medium resource refreshing request is received, determining a first tag and a second tag related to the first tag according to the content attributes of the clicked medium resources, determining the first tag and the second tag as target tags, determining a third tag according to the content attributes of the medium resources which are not issued, obtaining the matching degree sequence of the medium resources which are not issued according to the matching degree of the third tag and the target tags, reordering the issuing sequence of the medium resources which are not issued in the medium resource recommending list according to the matching degree sequence, and issuing the first M medium resources in the reordered medium resource recommending list to the target terminal so that the medium resources which are close to the content attributes of the clicked medium resources in the medium resource recommending list are issued to the target terminal preferentially;
and if click information representing that a user clicks the media assets is not received before the media asset refreshing request is received, issuing the first M undelivered media assets in the media asset recommendation list to the target terminal, wherein M is more than or equal to 2 and less than or equal to N.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110557930.7A CN113190758B (en) | 2021-05-21 | 2021-05-21 | Server and media asset recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110557930.7A CN113190758B (en) | 2021-05-21 | 2021-05-21 | Server and media asset recommendation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113190758A CN113190758A (en) | 2021-07-30 |
| CN113190758B true CN113190758B (en) | 2023-01-20 |
Family
ID=76984776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110557930.7A Active CN113190758B (en) | 2021-05-21 | 2021-05-21 | Server and media asset recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113190758B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113986575A (en) * | 2021-10-25 | 2022-01-28 | 聚好看科技股份有限公司 | Server and processing method of multi-level data |
| CN114065044A (en) * | 2021-11-23 | 2022-02-18 | 聚好看科技股份有限公司 | Content recommendation optimization method and server |
| CN114897510A (en) * | 2022-05-29 | 2022-08-12 | 上海妙一生物科技有限公司 | Method and device for adapting human resources of clinical test project |
| CN115204693B (en) * | 2022-07-21 | 2023-10-17 | 中交西北投资发展有限公司 | Intelligent park management method based on artificial intelligence and cloud platform |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102685565A (en) * | 2012-05-18 | 2012-09-19 | 合一网络技术(北京)有限公司 | Click feedback type individual recommendation system |
| CN108334575A (en) * | 2018-01-23 | 2018-07-27 | 北京三快在线科技有限公司 | A kind of recommendation results sequence modification method and device, electronic equipment |
| CN108776907A (en) * | 2018-05-31 | 2018-11-09 | 康键信息技术（深圳）有限公司 | Advertisement intelligent recommends method, server and storage medium |
| CN109063104A (en) * | 2018-07-27 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Method for refreshing, device, storage medium and the terminal device of recommendation information |
| CN110598016A (en) * | 2019-09-11 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Method, device, equipment and medium for recommending multimedia information |
| CN110941740A (en) * | 2019-11-08 | 2020-03-31 | 腾讯科技（深圳）有限公司 | Video recommendation method and computer-readable storage medium |
| CN111191122A (en) * | 2019-12-20 | 2020-05-22 | 重庆邮电大学 | Learning resource recommendation system based on user portrait |
| CN111212304A (en) * | 2020-02-27 | 2020-05-29 | 青岛聚看云科技有限公司 | Video recommendation method and server |
| CN111310016A (en) * | 2018-12-11 | 2020-06-19 | 百度在线网络技术（北京）有限公司 | Label mining method, device, server and storage medium |
| CN111327955A (en) * | 2018-12-13 | 2020-06-23 | Tcl集团股份有限公司 | User portrait based on-demand method, storage medium and smart television |
| CN112131411A (en) * | 2020-09-21 | 2020-12-25 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
| CN112468852A (en) * | 2020-11-24 | 2021-03-09 | 深圳市易平方网络科技有限公司 | Method, device and system for recommending media assets and computer readable storage medium |
| CN112804567A (en) * | 2021-01-04 | 2021-05-14 | 青岛聚看云科技有限公司 | Display device, server and video recommendation method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440335B (en) * | 2013-09-06 | 2016-11-09 | 北京奇虎科技有限公司 | Video recommendation method and device |
| CN107087235B (en) * | 2017-04-21 | 2021-09-10 | 腾讯科技（深圳）有限公司 | Media content recommendation method, server and client |
| CN108763502B (en) * | 2018-05-30 | 2022-03-25 | 腾讯科技（深圳）有限公司 | Information recommendation method and system |
| CN111897861A (en) * | 2020-06-30 | 2020-11-06 | 苏宁金融科技(南京)有限公司 | Content recommendation method and device, computer equipment and storage medium |
| CN112528150A (en) * | 2020-12-17 | 2021-03-19 | Oppo广东移动通信有限公司 | Live broadcast recommendation method and device, electronic equipment and storage medium |
-
2021
- 2021-05-21 CN CN202110557930.7A patent/CN113190758B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102685565A (en) * | 2012-05-18 | 2012-09-19 | 合一网络技术(北京)有限公司 | Click feedback type individual recommendation system |
| CN108334575A (en) * | 2018-01-23 | 2018-07-27 | 北京三快在线科技有限公司 | A kind of recommendation results sequence modification method and device, electronic equipment |
| CN108776907A (en) * | 2018-05-31 | 2018-11-09 | 康键信息技术（深圳）有限公司 | Advertisement intelligent recommends method, server and storage medium |
| CN109063104A (en) * | 2018-07-27 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Method for refreshing, device, storage medium and the terminal device of recommendation information |
| CN111310016A (en) * | 2018-12-11 | 2020-06-19 | 百度在线网络技术（北京）有限公司 | Label mining method, device, server and storage medium |
| CN111327955A (en) * | 2018-12-13 | 2020-06-23 | Tcl集团股份有限公司 | User portrait based on-demand method, storage medium and smart television |
| CN110598016A (en) * | 2019-09-11 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Method, device, equipment and medium for recommending multimedia information |
| CN110941740A (en) * | 2019-11-08 | 2020-03-31 | 腾讯科技（深圳）有限公司 | Video recommendation method and computer-readable storage medium |
| CN111191122A (en) * | 2019-12-20 | 2020-05-22 | 重庆邮电大学 | Learning resource recommendation system based on user portrait |
| CN111212304A (en) * | 2020-02-27 | 2020-05-29 | 青岛聚看云科技有限公司 | Video recommendation method and server |
| CN112131411A (en) * | 2020-09-21 | 2020-12-25 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
| CN112468852A (en) * | 2020-11-24 | 2021-03-09 | 深圳市易平方网络科技有限公司 | Method, device and system for recommending media assets and computer readable storage medium |
| CN112804567A (en) * | 2021-01-04 | 2021-05-14 | 青岛聚看云科技有限公司 | Display device, server and video recommendation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113190758A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113190758B (en) | Server and media asset recommendation method | |
| US10885093B2 (en) | Global recommendation systems for overlapping media catalogs | |
| US20240202213A1 (en) | Feedback loop content recommendation | |
| AU2016277657B2 (en) | Methods and systems for identifying media assets | |
| US9032435B2 (en) | Ad selection and next video recommendation in a video streaming system exclusive of user identity-based parameter | |
| CN101828199B (en) | Method and system for generating recommendations of content items | |
| CN108040294B (en) | Method, system, and computer readable medium for recommending videos | |
| US20120317123A1 (en) | Systems and methods for providing media recommendations | |
| JP2020166887A (en) | Methods and systems for displaying contextually relevant information regarding media asset | |
| US10616299B2 (en) | Video analytics device | |
| CN111432226B (en) | Live broadcast recommendation method and device, server, terminal and storage medium | |
| CN106415644A (en) | Dynamic content item creation | |
| US10747836B2 (en) | Apparatus and methods for controlling and optimizing information distribution between users in an information exchange | |
| US20210185386A1 (en) | Video playing method and apparatus, electronic device, and storage medium | |
| CN112616064B (en) | Live broadcasting room information processing method and device, computer storage medium and electronic equipment | |
| CN106471819A (en) | System and method for improving the accuracy in media asset recommended models | |
| US20220277342A1 (en) | Method for modeling digital advertisement consumption | |
| CN111949807A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN114065044A (en) | Content recommendation optimization method and server | |
| CN110147481B (en) | Media content pushing method and device and storage medium | |
| CN113111197A (en) | Multimedia content recommendation method, device, equipment and storage medium | |
| CN117135380A (en) | Travel product live broadcast marketing system based on AIGC technology | |
| KR20210097432A (en) | Apparatus and method for recommending contents | |
| US20230254521A1 (en) | Video distribution device, video distribution method, and recording media | |
| WO2023078226A1 (en) | Recommendation method and apparatus, server and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |