CN114398559A - Content item recommendation method and device, electronic equipment and storage medium - Google Patents
Content item recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114398559A CN114398559A CN202210296004.3A CN202210296004A CN114398559A CN 114398559 A CN114398559 A CN 114398559A CN 202210296004 A CN202210296004 A CN 202210296004A CN 114398559 A CN114398559 A CN 114398559A
- Authority
- CN
- China
- Prior art keywords
- content item
- resource
- target
- content
- determining
- 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.)
- Pending
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
Abstract
The method determines the content of interest of a target object by acquiring a resource tag of a media resource of the target object interacting in a target time period, and acquires a target content item matched with the resource tag by the resource tag, so that the target content item is ensured to be matched with the interest of the target object, and further, based on the target content item, the content item recommendation is carried out on the target object, and the accuracy rate of the content item recommendation can be improved.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a content item recommendation method and apparatus, an electronic device, and a storage medium.
Background
With the rapid development of computer technology and mobile internet, recommending content items related to commodities to objects in a network has become a common commodity popularization mode. Therefore, for the merchants with the demand for promotion of commodities, how to accurately recommend content items to objects becomes a problem which needs to be solved urgently.
Disclosure of Invention
The present disclosure provides a content item recommendation method, apparatus, electronic device, and storage medium, which can improve the accuracy of content item recommendation. The technical scheme of the disclosure is as follows.
According to a first aspect of embodiments of the present disclosure, there is provided a content item recommendation method, the method comprising:
determining a target media resource of a target object, wherein the target media resource is a media resource which interacts with the target object in a target time period;
acquiring a resource label of the target media resource, wherein the resource label is used for representing the content of the target media resource;
determining a target content item matched with the resource label based on the resource label of the target media resource;
based on the target content item, a content item recommendation is made to the target object.
In some embodiments, the obtaining the resource tag of the target media resource comprises:
acquiring a resource characteristic of the target media resource based on the target media resource, wherein the resource characteristic is used for expressing at least one of image information, voice information and text information of the target media resource;
and determining a label with the similarity meeting the first condition with the target media resource as the resource label based on the resource characteristics.
In some embodiments, the determining, based on the resource tag of the target media resource, the target content item that matches the resource tag comprises:
determining a plurality of second content items from the plurality of first content items that match the resource tag based on the resource tag of the target media resource;
the target content item is determined from the plurality of second content items based on the object information of the target object.
In some embodiments, the determining, from the first content items, a second content item that matches the resource tag based on the resource tag of the target media resource comprises at least one of:
determining a first content item having a content item tag that is the same as the resource tag as the second content item, the content item tag being used to represent the content of the first content item;
or;
and determining a first content item with a first association relationship between the content item label and the resource label as the second content item, wherein the first association relationship is used for indicating that the content of the first content item and the content of the target media resource have the same use scene.
In some embodiments, the determining, from the first content items, a second content item that matches the resource tag based on the resource tag of the target media resource comprises:
deleting a first content item from the plurality of first content items, wherein the content item label and the resource label have a second association relationship, and the second association relationship is used for indicating that the content of the first content item and the content of the target media resource are mutually exclusive;
the plurality of second content items is determined from the remaining plurality of first content items based on the resource tags of the target media asset.
In some embodiments, the determining the target content item from the plurality of second content items based on the object information of the target object comprises any one of:
determining a second content item matched with the object information of the target object as the target content item;
or;
and determining a second content item matching the object orientation information with the object information as the target content item, wherein the object orientation information is used for describing an object recommended by the second content item.
In some embodiments, the determining, based on the resource tag of the target media resource, the target content item that matches the resource tag comprises:
determining, based on the resource tag, a second content item from the plurality of first content items that matches the resource tag;
and determining the second content item with the click rate meeting the second condition as the target content item.
According to a second aspect of embodiments of the present disclosure, there is provided a content item recommendation apparatus comprising:
the determining unit is configured to determine a target media resource of a target object, wherein the target media resource is a media resource which interacts with the target object in a target time period;
an obtaining unit configured to perform obtaining a resource tag of the target media resource, the resource tag being used for representing the content of the target media resource;
the determining unit is configured to execute determining a target content item matching the resource label based on the resource label of the target media resource;
a recommendation unit configured to perform content item recommendation for the target object based on the target content item.
In some embodiments, the obtaining unit is configured to perform obtaining, based on the target media resource, a resource feature of the target media resource, where the resource feature is used to represent at least one of image information, voice information, and text information of the target media resource; and determining a label with the similarity meeting the first condition with the target media resource as the resource label based on the resource characteristics.
In some embodiments, the determining unit comprises:
a first determining subunit configured to perform determining, based on the resource tag of the target media resource, a plurality of second content items matching the resource tag from among the plurality of first content items;
a second determining subunit configured to perform determining the target content item from the plurality of second content items based on the object information of the target object.
In some embodiments, the first determining subunit is configured to perform at least one of:
determining a first content item having a content item tag that is the same as the resource tag as the second content item, the content item tag being used to represent the content of the first content item;
or;
and determining a first content item with a first association relationship between the content item label and the resource label as the second content item, wherein the first association relationship is used for indicating that the content of the first content item and the content of the target media resource have the same use scene.
In some embodiments, the first determining subunit is configured to perform deleting, from the plurality of first content items, a first content item having a second association relationship between the content item tag and the resource tag, the second association relationship being used to indicate that the content of the first content item and the content of the target media resource are mutually exclusive; the plurality of second content items is determined from the remaining plurality of first content items based on the resource tags of the target media asset.
In some embodiments, the second determining subunit is configured to perform any one of:
determining a second content item matched with the object information of the target object as the target content item;
or;
and determining a second content item matching the object orientation information with the object information as the target content item, wherein the object orientation information is used for describing an object recommended by the second content item.
In some embodiments, the determining unit is configured to perform determining, based on the resource tag, a second content item from the plurality of first content items that matches the resource tag; and determining the second content item with the click rate meeting the second condition as the target content item.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
one or more processors;
a memory for storing the processor executable program code;
wherein the processor is configured to execute the program code to implement the content item recommendation method described above.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium including: the program code in the computer readable storage medium, when executed by a processor of an electronic device, enables the electronic device to perform the content item recommendation method described above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the content item recommendation method described above.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a schematic illustration of an implementation environment for a method of content item recommendation, according to an example embodiment;
FIG. 2 is a flow diagram illustrating a method of content item recommendation, according to an example embodiment;
FIG. 3 is a flow diagram illustrating a method of content item recommendation, according to an example embodiment;
FIG. 4 is a flow diagram illustrating a method of content item recommendation, according to an example embodiment;
FIG. 5 is a block diagram illustrating a content item recommendation device, according to an example embodiment;
FIG. 6 is a block diagram illustrating a server in accordance with an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The data to which the present disclosure relates may be data authorized by the subject or sufficiently authorized by the parties.
Fig. 1 is a schematic diagram of an implementation environment of a content item recommendation method provided in an embodiment of the present disclosure, referring to fig. 1, where the implementation environment includes: a terminal 101 and a server 102. The terminal 101 and the server 102 can be connected directly or indirectly by wire or wirelessly.
The terminal 101 may be at least one of a smart phone, a smart watch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, a laptop computer, and the like, the terminal 101 has a communication function and can access the internet, and the terminal 101 may be generally referred to as one of a plurality of terminals, which is only exemplified by the terminal 101 in this embodiment. Those skilled in the art will appreciate that the number of the above-mentioned terminals 101 may be more or less, and the embodiment of the present application is not limited thereto. The terminal 101 may be running applications that support content item presentation and recommendation functions, such as video applications, music applications, e-commerce applications, and the like.
The server 102 may be an independent physical server, a server cluster or a distributed file system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like. The server 102 is configured to provide background services for the application program executed by the terminal 101. Alternatively, the number of the servers 102 may be more or less, and the embodiment of the present application is not limited thereto. Of course, the server 102 may also include other functional servers to provide more comprehensive and diverse services.
Fig. 2 is a flow chart illustrating a method of content item recommendation, as illustrated in fig. 2, performed by a server, comprising the following steps 201 to 204, according to an exemplary embodiment.
In step 201, the server determines a target media resource of a target object, where the target media resource is a media resource that interacts with the target object in a target time period.
The target object is an object which is currently logged in by the terminal, the terminal runs a target application program, the target application program provides a media resource display function and a content item display and recommendation function, the target object can interact with the media resource through the target application program, and the server can determine the target media resource of the target object in the process that the terminal runs the target application program, so that the content item related to the content of the target media resource is recommended for the target object.
The target media resource may be a video, an image, or an audio, and the form of the target media resource is not limited in the embodiments of the present application. The content item is used for promoting an article, and the content item may be a video, an image, an audio, or the like, for example, the content item is a promotion video or a promotion poster of a certain commodity, and the embodiment of the present application is not limited by this way.
In some embodiments, the media resource that interacts with the target object in the target time period refers to a media resource that the target object is browsing or clicking, such as a video that the target object is watching, or a media resource that the target object has paid attention to, commented on, or shared at the previous time. Therefore, in the subsequent steps, the target content item recommended to the target object is obtained based on the target media resource, so that the target content item can meet the current interest of the object, and the purpose of improving the accuracy of the recommended content item is achieved.
Of course, the target object can also interact with the media resource in other forms, which is not limited in this embodiment of the present application.
In step 202, the server obtains a resource tag of the target media resource, where the resource tag is used to represent the content of the target media resource.
In some embodiments, the resource tag includes multiple types, with different types of resource tags being used to represent the content of the target media resource from different aspects. For example, the industry tag is used for representing industries related to the content of the target media resource, such as clothing, electronic information, sports and the like, the category tag is used for representing the type of interaction of the content of the target media resource on an article, such as introduction, use, evaluation, sharing and the like, the theme tag is used for representing the content theme of the target media resource, such as vehicle knowledge, makeup teaching and the like, and the article tag is used for representing the type of the article related to the content of the target media resource, such as leather shoes, lipstick and the like.
Optionally, the number of the resource tags of the target media resource is at least one, which is not limited in this embodiment of the present application.
In step 203, the server determines a target content item matching the resource tag based on the resource tag of the target media resource.
The target content item matched with the resource label is obtained, so that the content item related to the content of the target media resource is obtained, and the target media resource is the media resource interacted by the target user in the target time period, so that the obtained target content item can be matched with the interest of the target object, the target content item is recommended to the target object, and the accuracy of recommending the content item can be improved.
In step 204, the server makes a content item recommendation to the target object based on the target content item.
The content item recommendation of the target object means that the server sends the target content item to the terminal, and the terminal displays the target content item in a currently browsed page of the target object.
According to the technical scheme provided by the embodiment of the disclosure, the interesting content of the target object is determined by acquiring the resource label of the media resource interacted with the target object in the target time period, and the target content item matched with the resource label is acquired through the resource label, so that the interest of the target content item matched with the target object is ensured, and the content item recommendation is performed on the target object based on the target content item, so that the accuracy of the content item recommendation can be improved.
The above embodiment of fig. 2 is only a brief description of the content item recommendation method proposed in the present application, and the method is described in detail below with reference to fig. 3. Fig. 3 is a flow chart illustrating a method of content item recommendation, according to an exemplary embodiment, as shown in fig. 3, comprising the following steps 301 to 307.
In step 301, the terminal determines a target media resource of a target object, and sends a content item acquisition request to the server, where the target media resource is a media resource interacting with the target object in a target time period, and the content item acquisition request is used to indicate to return a content item related to the target media resource.
In some embodiments, the terminal responds to the starting operation of the target application program, starts the target application program, displays a target page, the target page comprises a plurality of display positions, each display position is used for displaying a media resource or a content item, and the target object can interact with the media resource of any display position in the target page through clicking, sliding and other operations. As shown in 401 in fig. 4, in response to that a target object interacts with any media resource in the target page, the terminal determines the media resource as a target media resource, and sends the content item acquisition request to the server, where the content item acquisition request carries a resource identifier of the target media resource.
Optionally, the terminal sends the content item acquisition request and the target media resource to the server, which is not limited in this embodiment of the present application.
In step 302, the server receives the content item acquisition request, and determines a target media resource of the target object based on the content item acquisition request.
In some embodiments, the server is associated with a resource database for storing a plurality of media resources uploaded by the object and corresponding resource identifications. The server receives the content item acquisition request, acquires the resource identifier carried in the content item acquisition request, and queries the media resource corresponding to the resource identifier in a resource database to determine the target media resource of the target object.
Optionally, the server receives the content item acquisition request and the target media resource of the terminal, thereby determining the target media resource of the target object.
In step 303, the server obtains a resource tag of the target media resource, where the resource tag is used to indicate the content of the target media resource.
In some embodiments, the server is pre-provisioned with a plurality of tags from which the server determines a resource tag for the target media resource. Correspondingly, the server acquires the target media resource from a resource database, performs feature extraction on the target media resource, acquires resource features, and determines a label, the similarity of which to the target media resource meets a first condition, as a resource label of the target media resource based on the resource features, wherein the resource features are used for representing at least one of image information, voice information and text information of the target media resource. Optionally, the first condition is that the similarity is greater than a first threshold.
Illustratively, the server is capable of determining a resource tag for the target media resource from the plurality of tags through a media resource classification model. For example, the media resource classification model includes a convolutional layer and a full-link layer, the server inputs the target media resource into the media resource classification model, performs feature extraction on the target media resource based on the convolutional layer to obtain resource features, maps the resource features to classification spaces of a plurality of labels respectively based on the full-link layer to obtain similarity between the target media resource and the plurality of labels, and determines the label with the similarity meeting a first condition as the resource label of the target media resource.
It should be noted that the above process is a process in which the server acquires the resource tag in real time in response to receiving the content item acquisition request from the terminal. In some embodiments, as shown in 402 and 403 in fig. 4, the server can obtain resource tags of multiple media resources in a resource database in advance based on a method similar to that described above, correspondingly store the obtained resource tags in the resource database, and in response to receiving a content item obtaining request from the terminal, obtain corresponding resource tags from the resource database based on a resource identifier of a target media resource carried in the content item obtaining request.
In step 304, the server determines a plurality of second content items from the plurality of first content items that match the resource tag based on the resource tag of the target media resource.
In some embodiments, as shown at 404 in fig. 4, the server is further associated with a content item database, the content item database is configured to store a plurality of first content items uploaded by the object and corresponding content item tags, the content item tags are configured to represent content of the first content items, and the server is configured to determine the plurality of second content items by at least one of the following methods based on the resource tags and the plurality of content item tags.
In one implementation, the server compares the resource tag of the target media resource with the content item tags of a plurality of first content items in the content item database, and determines the first content item with the same content item tag and resource tag as the second content item.
In another implementation manner, the content item database further stores a first association relationship between the content item tag and the resource tag, and the server queries, based on the resource tag of the target media resource, a plurality of first association relationships in the content item database, and determines, as the second content item, a first content item in which the content item tag and the resource tag have the first association relationship. Wherein the first association is used to indicate that the content of the first content item and the content of the target media resource have the same usage scenario. For example, if the target media resource is a putting-on teaching video and the first content item is a promotion video of clothes, the content item tag of the first content item and the resource tag of the target media resource have a first association relationship. For another example, if the target media resource is a milk powder assessment video and the first content item is a promotion video of a diaper, the content item tag of the first content item and the resource tag of the target media resource have a first association relationship.
By obtaining the plurality of second content items, the content items with the content related to the content of the target media resource or the same using scene are obtained, so that the second content items are ensured to be matched with the current interest of the target object, and in the subsequent steps, the content item recommendation is carried out based on the second content items, so that the accuracy of the content item recommendation can be improved.
In some embodiments, the content item database further stores a second association of the content item tag and the resource tag, the second association being used to indicate that the content of the first content item is mutually exclusive with the content of the target media resource, and the server is capable of deleting the first content item, the content of which is mutually exclusive with the content of the target media resource, from the plurality of first content items and then determining the second content item from the remaining first content items. Accordingly, this step 304 can be replaced by: the server deletes the first content item having the second association relationship between the content item tag and the resource tag from the plurality of first content items, and determines the plurality of second content items from the remaining plurality of first content items based on the resource tag of the target media resource.
Wherein, the content of the first content item and the content of the target media resource are mutually exclusive, that the content of the first content item and the content of the target media resource relate to different articles of the same type, or the content of the first content item includes negative information of the content of the target media resource. For example, if the target media asset is an introduction video of lipstick a and the first content item is a promotional video of lipstick B, the content of the first content item is mutually exclusive from the content of the target media asset. For another example, if the target media resource is a shared video of a commodity and the first content item is a negative advertisement video of the commodity, that is, if the content of the first content item includes a negative evaluation of the commodity, the content of the first content item and the content of the target media resource are mutually exclusive.
By deleting the first content item with mutually exclusive content and the content of the target media resource, the promotion content of the same type of goods being browsed can be prevented from being recommended for the target object, the negative promotion content of the goods being browsed can also be prevented from being recommended for the target object, the object experience is improved, and the purpose of improving the content item recommendation accuracy is also achieved.
In step 305, the server determines the target content item from the plurality of second content items based on the object information of the target object.
The object information includes an interest and basic attributes of the target object, and optionally, the basic attributes include a gender, an age, a region, a scholarship, and the like of the target object.
In some embodiments, the server obtains object information for the target object, and determines the target content item based on the object information by any one of the following methods.
In one implementation, the server determines the second content item matching the object information of the target object as the target content item.
In another implementation, the server obtains object targeting information of each second content item from the content item database, where the object targeting information is used to describe an object recommended by the second content item, and determines the second content item whose object targeting information matches the object information as the target content item. Optionally, the object targeting information comprises at least one of gender, age, territory and academic calendar of the object recommended by the second content item.
The acquired target content item can be more matched with the interest of the target object through the object information of the target object, and in the subsequent steps, the content item recommendation is carried out on the target object based on the target content item, so that the accuracy of recommending the content item can be improved.
In some embodiments, the object information of the target object further includes content items that the target object has interacted with in a historical period of time, and the server is capable of obtaining click through rates of a plurality of second content items based on the object information, and determining the target content item based on the click through rates of the plurality of second content items. Accordingly, this step 305 can be replaced by: the server obtains click rates of a plurality of second content items based on the object information of the target object and the plurality of second content items, and determines the second content items with the click rates meeting a second condition as the target content items. Optionally, the second condition is that the click rate is greater than a second threshold, or the click rate is ranked first by N bits in descending order, where N is an integer greater than 0 and less than the second number of content items. By obtaining the click rate of the plurality of second content items, the content items with higher click rate can be recommended to the target object, so that the accuracy of recommending the content items is improved.
In some embodiments, as shown in 405 and 406 in fig. 4, the server first determines a plurality of third content items from the plurality of second content items based on the object information of the target object, and then determines a third content item having a click through rate meeting a second condition as the target content item according to the click through rate of the plurality of third content items. And secondary screening is carried out on the second content item through the object information and the click rate, so that the content item with higher click rate can be recommended to the target object under the condition of ensuring that the content item accords with the interest of the target object, and the accuracy rate of recommending the content item is further improved.
In addition, the above step 305 is described by taking as an example that the server can acquire the object information of the target object, and in some embodiments, when the server cannot acquire the object information of the target object, the server does not execute the step 305 and sets the acquired second content item as the target content item.
In step 306, the server sends the target content item to the terminal.
In some embodiments, as shown at 407 in fig. 4, the server sends the target content item and a content item acquisition response to the terminal, the content item acquisition response indicating that the target content item is to be exposed to the target object; or the server sends the content item acquisition response to the terminal, wherein the content item acquisition response carries the target content item.
In step 307, the terminal receives the target content item and presents the target content item to the target object.
In some embodiments, the terminal receives the target content item, determines a target presentation position in the target page that is next to the presentation position of the target media asset of the target object, and presents the target content item in the target presentation position, as shown at 408 in fig. 4, thereby completing the content item recommendation for the target object. Optionally, the next presentation position of the target media resource refers to a presentation position located at the right side of the presentation position of the target media resource, or a presentation position located below the presentation position of the target media resource. Optionally, the process of presenting the target content item is also referred to as target content item exposure.
In addition, in the embodiment of the present application, a server recommends a content item related to the content of a target media resource for a target object based on the target media resource of the target object as an example. In some embodiments, the server determines a plurality of media resources shown in the target page, and based on the method similar to the foregoing steps 303 to 305, obtains content items related to the content of the plurality of media resources, respectively, sends the content items corresponding to the plurality of media resources to the terminal, and the terminal recommends the content items corresponding to the media resources to the target object in response to the target object interacting with any media resource in the target page.
According to the technical scheme provided by the embodiment of the disclosure, the interesting content of the target object is determined by acquiring the resource label of the media resource interacted with the target object in the target time period, and the target content item matched with the resource label is acquired through the resource label, so that the interest of the target content item matched with the target object is ensured, and the content item recommendation is performed on the target object based on the target content item, so that the accuracy of the content item recommendation can be improved.
FIG. 5 is a block diagram illustrating a content item recommendation device according to an example embodiment. As shown in fig. 5, the apparatus includes a determining unit 501, an obtaining unit 502, and a recommending unit 503:
a determining unit 501, configured to perform determining a target media resource of a target object, where the target media resource is a media resource that interacts with the target object in a target time period;
an obtaining unit 502 configured to perform obtaining a resource tag of the target media resource, where the resource tag is used to represent the content of the target media resource;
the determining unit 501 is configured to perform determining a target content item matching the resource label based on the resource label of the target media resource;
a recommending unit 503 configured to perform content item recommendation for the target object based on the target content item.
In some embodiments, the obtaining unit is configured to perform obtaining, based on the target media resource, a resource feature of the target media resource, where the resource feature is used to represent at least one of image information, voice information, and text information of the target media resource; and determining a label with the similarity meeting the first condition with the target media resource as the resource label based on the resource characteristics.
In some embodiments, the determining unit 501 includes:
a first determining subunit configured to perform determining, based on the resource tag of the target media resource, a plurality of second content items matching the resource tag from among the plurality of first content items;
a second determining subunit configured to perform determining the target content item from the plurality of second content items based on the object information of the target object.
In some embodiments, the first determining subunit is configured to perform at least one of:
determining a first content item having a content item tag that is the same as the resource tag as the second content item, the content item tag being used to represent the content of the first content item;
or;
and determining a first content item with a first association relationship between the content item label and the resource label as the second content item, wherein the first association relationship is used for indicating that the content of the first content item and the content of the target media resource have the same use scene.
In some embodiments, the first determining subunit is configured to perform deleting, from the plurality of first content items, a first content item having a second association relationship between the content item tag and the resource tag, the second association relationship being used to indicate that the content of the first content item and the content of the target media resource are mutually exclusive; the plurality of second content items is determined from the remaining plurality of first content items based on the resource tags of the target media asset.
In some embodiments, the second determining subunit is configured to perform any one of:
determining a second content item matched with the object information of the target object as the target content item;
or;
and determining a second content item matching the object orientation information with the object information as the target content item, wherein the object orientation information is used for describing an object recommended by the second content item.
In some embodiments, the determining unit 501 is configured to perform determining, based on the resource tag, a second content item matching the resource tag from the plurality of first content items; and determining the second content item with the click rate meeting the second condition as the target content item.
It should be noted that: the content item recommendation apparatus provided in the foregoing embodiment only exemplifies the division of the functional modules when recommending a content item, and in practical applications, the functions may be distributed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the content item recommendation apparatus and the content item recommendation method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.
Embodiments of the present application further provide an electronic device for performing the above content item recommendation method, which in some embodiments is provided as a server. Fig. 6 is a block diagram of a server according to an exemplary embodiment, where the server 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 601 and one or more memories 602, where at least one program code is stored in the one or more memories 602, and the at least one program code is loaded and executed by the one or more processors 601 to implement the processes executed by the server in the content item recommendation method provided by the above-mentioned method embodiments. Of course, the server 600 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 600 may also include other components for implementing the functions of the device, which is not described herein again.
In an exemplary embodiment, a computer readable storage medium comprising program code, such as a memory 602 comprising program code, executable by a processor 601 of the server 600 to perform the content item recommendation method described above is also provided. Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a Random Access Memory (RAM), a compact-disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product is also provided, comprising a computer program which, when executed by a processor, implements the content item recommendation method described above.
In some embodiments, the computer program according to the embodiments of the present application may be deployed to be executed on one computer device or on multiple computer devices located at one site, or may be executed on multiple computer devices distributed at multiple sites and interconnected by a communication network, and the multiple computer devices distributed at the multiple sites and interconnected by the communication network may constitute a block chain system.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (13)
1. A method of content item recommendation, the method comprising:
determining a target media resource of a target object, wherein the target media resource is a media resource which interacts with the target object in a target time period;
acquiring a resource label of the target media resource, wherein the resource label is used for representing the content of the target media resource;
determining a target content item matching the resource tag based on the resource tag of the target media resource;
and recommending the content item to the target object based on the target content item.
2. The content item recommendation method of claim 1, wherein said obtaining a resource tag for the target media resource comprises:
acquiring a resource characteristic of the target media resource based on the target media resource, wherein the resource characteristic is used for representing at least one of image information, voice information and text information of the target media resource;
and determining a label with the similarity meeting a first condition with the target media resource as the resource label based on the resource characteristics.
3. The content item recommendation method of claim 1, wherein determining the target content item matching the resource tag based on the resource tag of the target media resource comprises:
determining, from a plurality of first content items, a plurality of second content items that match the resource tag based on the resource tag of the target media resource;
determining the target content item from the plurality of second content items based on object information of the target object.
4. The content item recommendation method according to claim 3, wherein determining, from the plurality of first content items, a plurality of second content items matching the resource tag based on the resource tag of the target media resource comprises at least one of:
determining a first content item having a content item tag that is the same as the resource tag as the second content item, the content item tag being used to represent the content of the first content item;
or;
determining a first content item with a first association relationship between the content item tag and the resource tag as the second content item, wherein the first association relationship is used for indicating that the content of the first content item and the content of the target media resource have the same use scene.
5. The content item recommendation method according to claim 3, wherein determining, from among the first content items, the second content items matching the resource tag based on the resource tag of the target media resource comprises:
deleting a first content item from the plurality of first content items, wherein the content item label and the resource label have a second association relationship, and the second association relationship is used for indicating that the content of the first content item and the content of the target media resource are mutually exclusive;
determining the plurality of second content items from the remaining plurality of first content items based on the resource tags of the target media asset.
6. The content item recommendation method according to claim 3, wherein the determining the target content item from the plurality of second content items based on the object information of the target object includes any one of:
determining a second content item matched with the object information of the target object as the target content item;
or;
and determining a second content item with object orientation information matched with the object information as the target content item, wherein the object orientation information is used for describing an object recommended by the second content item.
7. The content item recommendation method of claim 1, wherein determining the target content item matching the resource tag based on the resource tag of the target media resource comprises:
determining, based on the resource tag, a second content item from the plurality of first content items that matches the resource tag;
and determining a second content item with the click rate meeting a second condition as the target content item.
8. An apparatus for recommending content items, the apparatus comprising:
the determining unit is configured to determine a target media resource of a target object, wherein the target media resource is a media resource which interacts with the target object in a target time period;
an obtaining unit configured to perform obtaining a resource tag of the target media resource, the resource tag being used for representing the content of the target media resource;
the determining unit is configured to determine a target content item matching the resource label based on the resource label of the target media resource;
a recommendation unit configured to perform content item recommendation for the target object based on the target content item.
9. The content item recommendation device according to claim 8, wherein the obtaining unit is configured to perform obtaining a resource feature of the target media resource based on the target media resource, the resource feature being used to represent at least one of image information, voice information and text information of the target media resource; and determining a label with the similarity meeting a first condition with the target media resource as the resource label based on the resource characteristics.
10. The content item recommendation device according to claim 8, wherein said determining unit comprises:
a first determining subunit configured to perform determining, from a plurality of first content items, a plurality of second content items matching the resource tag based on the resource tag of the target media resource;
a second determining subunit configured to perform determining the target content item from the plurality of second content items based on object information of the target object.
11. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory for storing the processor executable program code;
wherein the processor is configured to execute the program code to implement the content item recommendation method of any one of claims 1 to 7.
12. A computer-readable storage medium, wherein program code in the computer-readable storage medium, when executed by a processor of an electronic device, enables the electronic device to perform a content item recommendation method according to any one of claims 1-7.
13. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the content item recommendation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210296004.3A CN114398559A (en) | 2022-03-24 | 2022-03-24 | Content item recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210296004.3A CN114398559A (en) | 2022-03-24 | 2022-03-24 | Content item recommendation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114398559A true CN114398559A (en) | 2022-04-26 |
Family
ID=81233932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210296004.3A Pending CN114398559A (en) | 2022-03-24 | 2022-03-24 | Content item recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114398559A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10136191B1 (en) * | 2016-12-12 | 2018-11-20 | Google Llc | Methods, systems, and media for recommending media content based on attribute grouped viewing sessions |
| CN109213933A (en) * | 2018-08-14 | 2019-01-15 | 腾讯科技（深圳）有限公司 | Content item recommendation method, apparatus, equipment and storage medium |
| CN110209921A (en) * | 2018-05-10 | 2019-09-06 | 腾讯科技（深圳）有限公司 | The method for pushing and device and storage medium and electronic device of media resource |
| CN111708901A (en) * | 2020-06-19 | 2020-09-25 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
| CN113034168A (en) * | 2019-12-25 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Content item delivery method and device, computer equipment and storage medium |
| CN113792212A (en) * | 2021-08-31 | 2021-12-14 | 北京百度网讯科技有限公司 | Multimedia resource recommendation method, device, equipment and storage medium |
| CN113901244A (en) * | 2021-10-12 | 2022-01-07 | 北京达佳互联信息技术有限公司 | Label construction method and device for multimedia resource, electronic equipment and storage medium |
-
2022
- 2022-03-24 CN CN202210296004.3A patent/CN114398559A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10136191B1 (en) * | 2016-12-12 | 2018-11-20 | Google Llc | Methods, systems, and media for recommending media content based on attribute grouped viewing sessions |
| CN110209921A (en) * | 2018-05-10 | 2019-09-06 | 腾讯科技（深圳）有限公司 | The method for pushing and device and storage medium and electronic device of media resource |
| CN109213933A (en) * | 2018-08-14 | 2019-01-15 | 腾讯科技（深圳）有限公司 | Content item recommendation method, apparatus, equipment and storage medium |
| CN113034168A (en) * | 2019-12-25 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Content item delivery method and device, computer equipment and storage medium |
| CN111708901A (en) * | 2020-06-19 | 2020-09-25 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
| CN113792212A (en) * | 2021-08-31 | 2021-12-14 | 北京百度网讯科技有限公司 | Multimedia resource recommendation method, device, equipment and storage medium |
| CN113901244A (en) * | 2021-10-12 | 2022-01-07 | 北京达佳互联信息技术有限公司 | Label construction method and device for multimedia resource, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107203894B (en) | Information pushing method and device | |
| CN107426328B (en) | Information pushing method and device | |
| CN110009401A (en) | Advertisement placement method, device and storage medium based on user's portrait | |
| CN110020188A (en) | Recommended based on the Global Vector of implicit interactions and profile data | |
| US11132703B2 (en) | Platform for providing augmented reality based advertisements | |
| CN111242748B (en) | Method, apparatus, and storage medium for recommending items to a user | |
| CN105718184A (en) | Data processing method and apparatus | |
| CN108805594A (en) | Information-pushing method and device | |
| CN104428805A (en) | Search-powered connection targeting | |
| CN108243219B (en) | Information pushing method and device | |
| CN110059256B (en) | System, method and device for displaying information | |
| CN110298716A (en) | Information-pushing method and device | |
| CN110363604A (en) | Page generation method and device | |
| CN113592535B (en) | Advertisement recommendation method and device, electronic equipment and storage medium | |
| CN109859006A (en) | For determining method, system, electronic equipment and the computer-readable medium of user interest profile | |
| CN112396456A (en) | Advertisement pushing method and device, storage medium and terminal | |
| CN111552835A (en) | File recommendation method and device and server | |
| CN114245165B (en) | Live broadcast recommendation method and device, electronic equipment and storage medium | |
| CN112749323A (en) | Method and device for constructing user portrait | |
| CN112784103A (en) | Information pushing method and device | |
| CN110020108B (en) | Network resource recommendation method, device, computer equipment and storage medium | |
| CN113379449A (en) | Multimedia resource recall method and device, electronic equipment and storage medium | |
| CN112288461A (en) | Advertisement information pushing method, device, medium and electronic equipment | |
| CN111782850A (en) | Object searching method and device based on hand drawing | |
| CN114398559A (en) | Content item recommendation method and device, electronic equipment and 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 |