CN109710805B - Video interaction method and device based on interest cluster - Google Patents
Video interaction method and device based on interest cluster Download PDFInfo
- Publication number
- CN109710805B CN109710805B CN201811525722.3A CN201811525722A CN109710805B CN 109710805 B CN109710805 B CN 109710805B CN 201811525722 A CN201811525722 A CN 201811525722A CN 109710805 B CN109710805 B CN 109710805B
- Authority
- CN
- China
- Prior art keywords
- interest
- video
- user
- cluster
- root
- 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
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application provides a video interaction method and device based on an interest cluster, wherein the method comprises the following steps: establishing an interest cluster of a user; establishing a plurality of candidate video queues according to interest labels in the interest clusters; selecting a target video queue from a plurality of candidate video queues and acquiring a historical playing sequence of a user; and processing the target video queue and the historical playing sequence through a preset generation model to generate a recommended video sequence and provide the recommended video sequence for the user. Therefore, the video sequence with predictable content can be recommended to the user, the user requirements are met, and the user experience is improved.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a video interaction method and apparatus based on an interest cluster.
Background
Generally, personalized recommendation is to perform personalized calculation by researching interest and preference of a user on the basis of big data analysis and an artificial intelligence algorithm, so as to provide high-quality personalized content for the user, solve the problem of information overload, and better meet the requirements of the user.
In the related art, a video recommendation algorithm obtains a recommendation sequence by fusing recall results of different recommendation sources, and the recommendation algorithm is non-interactive, that is, a user can only passively accept the recommendation video sequence and is unpredictable for the content of the recommendation video.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, the application provides a video interaction method and device based on an interest cluster, which are used for solving the technical problem that in the prior art, the video recommendation efficiency is low because a user cannot expect the recommended video content.
In order to achieve the above object, an embodiment of a first aspect of the present application provides a video interaction method based on an interest cluster, including:
establishing an interest cluster of a user;
establishing a plurality of candidate video queues according to the interest labels in the interest clusters;
selecting a target video queue from the candidate video queues and acquiring a historical playing sequence of the user;
and processing the target video queue and the historical playing sequence through a preset generation model to generate a recommended video sequence and provide the recommended video sequence for the user.
According to the video interaction method based on the interest clusters, the interest clusters of the user are established, the candidate video queues are established according to the interest labels in the interest clusters, the target video queue is selected from the candidate video queues, the historical playing sequence of the user is obtained, and finally the target video queue and the historical playing sequence are processed through the preset generation model to generate the recommended video sequence which is provided for the user. Therefore, the video sequence with predictable content can be recommended to the user, the user requirements are met, and the user experience is improved.
In order to achieve the above object, a second aspect of the present application provides an apparatus for video interaction based on a cluster of interest, including:
the first establishing module is used for establishing an interest cluster of a user;
the second establishing module is used for establishing a plurality of candidate video queues according to the interest labels in the interest clusters;
the acquisition module is used for selecting a target video queue from the candidate video queues and acquiring a historical playing sequence of the user;
and the processing module is used for processing the target video queue and the historical playing sequence through a preset generation model to generate a recommended video sequence and provide the recommended video sequence for the user.
According to the video interaction device based on the interest cluster, the interest cluster of the user is established, the candidate video queues are established according to the interest labels in the interest cluster, the target video queue is selected from the candidate video queues, the historical playing sequence of the user is obtained, and finally the target video queue and the historical playing sequence are processed through the preset generation model to generate the recommended video sequence to be provided for the user. Therefore, the video sequence with predictable content can be recommended to the user, the user requirements are met, and the user experience is improved.
To achieve the above object, a third aspect of the present application provides a computer device, including: a processor and a memory; wherein the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the video interaction method based on the interest cluster according to the embodiment of the first aspect.
To achieve the above object, a fourth aspect of the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a video interaction method based on a cluster of interest as described in the first aspect of the present application.
To achieve the above object, an embodiment of a fifth aspect of the present application proposes a computer program product, wherein instructions of the computer program product, when executed by a processor, implement the method for video interaction based on a cluster of interest as described in the embodiment of the first aspect.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a video interaction method based on an interest cluster according to an embodiment of the present application;
FIGS. 2A-2C are exemplary diagrams of video interactions based on clusters of interest;
FIG. 3 is an exemplary diagram of an interest cluster;
FIG. 4 is a flowchart illustrating another method for video interaction based on interest clusters according to an embodiment of the present disclosure;
FIG. 5 is an exemplary diagram of establishing clusters of interest;
FIG. 6 is an exemplary diagram of generating a recommended video sequence;
fig. 7 is a flowchart illustrating a video interaction method based on an interest cluster according to an embodiment of the present application;
FIG. 8 is an exemplary diagram of obtaining play durations for different topic video queues
Fig. 9 is a schematic structural diagram of a video interaction apparatus based on an interest cluster according to an embodiment of the present application;
FIG. 10 is a schematic structural diagram of another video interaction apparatus based on a cluster of interest according to an embodiment of the present application; and
fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The video interaction method and apparatus based on interest clusters according to the embodiments of the present application are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a video interaction method based on an interest cluster according to an embodiment of the present disclosure.
As shown in fig. 1, the video interaction method based on interest clusters may include the following steps:
In practical applications, a recommended video sequence can be obtained by fusing recall results of different recommendation sources and provided to a user, for example, as shown in fig. 2A, it can be seen that the user cannot generate a clear expectation for the recommended video sequence, and in addition, the user cannot influence generation of a subsequent video sequence by expressing whether the user is interested in the current video, and even if the user is not interested in the current video, the user cannot immediately feed back to a recommendation algorithm.
It can also be understood that, as shown in fig. 2B, the video is divided into different topic queues based on the tags contained in the video, and the user can freely switch between the sequences of different topics, however, the video resource of the same tag may be insufficient, resulting in the lack of continuous immersion capability, and furthermore, as the video queue is constructed based on tags, it is easy to jump to videos of other similar topics (tags) when switching topics.
The application provides a video interaction method based on an interest cluster, as shown in fig. 2C, a user interest cluster is established first, then a plurality of candidate video queues are established based on the interest cluster, a target video queue is selected through a recommendation algorithm based on content, a recommendation algorithm based on collaborative filtering and other algorithms, and finally a recommended video sequence is generated based on a play history sequence and provided for a user.
First, an interest cluster of a user is established, that is, interest points with similar semantics are aggregated into a cluster, and finally, the range of content covered by each cluster is equivalent, for example, as shown in fig. 3, the coverage content of an original interest point is compared with the coverage content of the interest cluster, the original interest point is shown on the left side of fig. 3, the desired interest cluster is shown on the right side of fig. 3, and the size of each circle is proportional to the number of the coverage content.
Specifically, the interest clusters can be established based on the user interest points recorded by the user model, and the construction of the interest clusters mainly depends on semantic similarity among the interest points. As a possible implementation, as shown in fig. 4:
Specifically, for example, according to a repeated playing operation, a pause operation, a fast playing operation, and the like of a user clicking a related video, the user may also view operation information of related news, and the like, and obtain a plurality of points of interest of the user from the operation record information. As an example, a user's point of interest is determined to be entertainment based on a record that the user browses entertainment news each morning.
And step 204, forming an interest cluster by the plurality of root interest sets.
It can be understood that a plurality of interest points of the user may be obtained, in order to combine the interest points with close semantic similarity into one piece, any one of the interest points may be determined as a root interest point, and a root interest set corresponding to the root interest point is generated, so that as long as the semantic similarity is similar to the root interest point, the root interest set is added to the root interest set, and finally the plurality of root interest sets form an interest cluster.
The similarity calculation can obtain word vector representation of each interest point through word2vec algorithm training, and then the cosine similarity between the word vectors is used as similarity measurement to calculate the similarity.
The preset threshold value can be selected and set according to the actual application requirement. If each interest point is represented as a point in space in the form of a word vector, the construction process of the interest cluster can be represented by fig. 5. In fig. 5, there are user interest points, non-user interest points, and interest points obtained based on interest cluster expansion, and the right side of fig. 5 is a plurality of interest clusters constructed based on the left graph.
Specifically, a plurality of candidate video teams can be established according to the interest tags in the interest clusters in a variety of ways, for example, as follows:
in a first example, videos corresponding to interest tags are obtained from a preset video resource database as a plurality of candidate video queues.
Specifically, the interest tag of the user may be determined according to the interest cluster of the user, for example, if the interest tag of the user is determined to be a mobile phone, a video corresponding to the mobile phone is obtained from a preset video resource database and is used as a plurality of candidate video queues.
In a second example, a historical playing video of a user is obtained, and a plurality of candidate video queues are determined according to interest tags and the historical playing video.
Specifically, after the interest tag of the user is determined to be the mobile phone, the historical playing video of the user, such as the camera shooting technology of the mobile phone, can be acquired, so that a plurality of candidate video queues are determined according to the mobile phone and the camera shooting technology of the mobile phone.
Therefore, by establishing the interest cluster, any one video queue will contain all resources belonging to the same interest cluster, and switching other video queues can also ensure that the difference from the original interest cluster is large. Therefore, the continuous immersion capability under the same theme and the diversity when different themes are switched can be improved.
And 104, processing the target video queue and the historical playing sequence through a preset generation model, and generating a recommended video sequence to be provided for a user.
Each of the plurality of candidate video queues only contains the candidate result of the corresponding interest cluster, that is, given a target video queue Q and a historical play sequence H, an optimal recommended video sequence can be generated.
In this embodiment, a pointing network is used to perform sequence generation (PN generation model for short), and the structure of the PN generation model is shown in fig. 6. The PN generation model encodes each input video at the embedding layer and takes it as an input to the RNN layer. In the sequence generation phase, the model scores each candidate video at each position. And finally, generating an optimal sequence based on the beacon search algorithm, and issuing video resources according to the sequence. It should be noted that the historical play sequence is also encoded based on RNN, and the output of the last hidden layer is used as the additional input of the pointer-network.
Based on the above description, it can also be understood that, as shown in fig. 7, after step 104, the method further includes:
Specifically, when the user actively switches the theme, based on the user history playing sequence and the user feedback, in combination with various factors such as the diversity of the theme and the expected immersion degree, other video queues are switched for the user. The user's next recommended video sequence will come from the video queue until the user switches the topic again. Therefore, the problem can be described as selecting an optimal video topic queue Qi given a series of video topic queues Q ═ { Q1, Q2, …, Qm } and the historical play sequence H. A neural network prediction model can be adopted to predict the expected playing time of each topic queue, and the next topic queue with the largest expected time is selected from the predicted playing time of each topic queue. The model structure is shown in fig. 8 below:
as shown in fig. 8, the preset length estimation model mainly includes three parts, where the model a is a fully connected neural network used for encoding candidate queues, and the input is the original characteristics of resource quantity, resource labels, resource quality, and the like; the model B is an RNN model and is used for encoding a historical playing sequence, and the input of an Embedding layer is the representation of each video; the model C is a duration estimation part, and the input of the model C comprises the output of the model A and the output of the model B and the original input of a part of the model.
Therefore, video sequences with predictable content can be recommended for the user, and switching to other video theme queues can be performed based on the interaction of the user. The method comprises the steps of dividing interest clusters into different topic queues according to the interest clusters, estimating the playing time of each topic queue based on a preset time estimation model, switching to the queue with the longest expected time, and generating an optimal playing sequence through a pointer-network generation model until the topics are switched again. The method has the advantages that the user can actively interact through theme switching or manual input, the generation of a subsequent video sequence is influenced, compared with the traditional non-interactive algorithm, the algorithm responds to user feedback in time, and the user experience is effectively improved.
According to the video interaction method based on the interest cluster, the interest cluster of the user is established, the candidate video queues are established according to the interest tags in the interest cluster, the target video queue is selected from the candidate video queues, the historical playing sequence of the user is obtained, and finally the target video queue and the historical playing sequence are processed through the preset generation model to generate the recommended video sequence which is provided for the user. Therefore, the video sequence with predictable content can be recommended to the user, the user requirements are met, and the user experience is improved.
In order to implement the above embodiments, the present application further provides a video interaction device based on an interest cluster.
Fig. 9 is a schematic structural diagram of a video interaction apparatus based on an interest cluster according to an embodiment of the present application.
As shown in fig. 9, the video interaction apparatus based on interest clusters may include: a first establishing module 10, a second establishing module 20, an obtaining module 30 and a processing module 40. Wherein the content of the first and second substances,
a first establishing module 10, configured to establish a user interest cluster.
And a second establishing module 20, configured to establish a plurality of candidate video queues according to the interest tags in the interest clusters.
The obtaining module 30 is configured to select a target video queue from the plurality of candidate video queues and obtain a historical playing sequence of the user.
And the processing module 40 is configured to process the target video queue and the historical play sequence through a preset generation model, and generate a recommended video sequence to be provided to the user.
In a possible implementation manner of the embodiment of the present application, the first establishing module 10 is specifically configured to: acquiring operation record information of a user, and acquiring a plurality of interest points of the user from the operation record information; determining root interest points and generating a root interest set corresponding to the root interest points; obtaining semantic similarity between any interest point in the interest points and a root interest point, and adding any interest point into a root interest set when the semantic similarity is greater than a preset threshold value; forming a plurality of root interest sets into an interest cluster.
In a possible implementation manner of the embodiment of the present application, the second establishing module 20 is specifically configured to: and acquiring videos corresponding to the interest tags from a preset video resource database to serve as a plurality of candidate video queues.
In a possible implementation manner of the embodiment of the present application, the second establishing module 20 is specifically configured to: acquiring a historical playing video of the user; and determining the candidate video queues according to the interest tags and the historical playing videos.
In a possible implementation manner of the embodiment of the present application, as shown in fig. 10, on the basis of the embodiment shown in fig. 9, the video interaction apparatus based on an interest cluster further includes: a receiving module 50 and a switching module 60.
The receiving module 50 is configured to obtain playing durations of video queues with different topics based on a preset duration estimation model after receiving a video topic switching operation input by a user.
And the switching module 60 is configured to sort the playing durations according to time, and use the theme video queue corresponding to the first playing duration as the switched video playing sequence.
It should be noted that the foregoing explanation of the embodiment of the video interaction method based on interest clusters is also applicable to the video interaction apparatus based on interest clusters of this embodiment, and the implementation principle thereof is similar, and is not repeated here.
According to the video interaction device based on the interest cluster, the interest cluster of the user is established, the candidate video queues are established according to the interest labels in the interest cluster, the target video queue is selected from the candidate video queues, the historical playing sequence of the user is obtained, and finally the target video queue and the historical playing sequence are processed through the preset generation model to generate the recommended video sequence to be provided for the user. Therefore, the video sequence with predictable content can be recommended to the user, the user requirements are met, and the user experience is improved.
By in order to implement the above embodiments, the present application also provides a computer device, including: a processor and a memory. Wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the video interaction method based on the interest cluster as described in the foregoing embodiment.
FIG. 11 is a block diagram of a computer device provided in an embodiment of the present application, illustrating an exemplary computer device 90 suitable for use in implementing embodiments of the present application. The computer device 90 shown in fig. 11 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present application.
As shown in fig. 11, the computer device 90 is in the form of a general purpose computer device. The components of computer device 90 may include, but are not limited to: one or more processors or processing units 906, a system memory 910, and a bus 908 that couples the various system components (including the system memory 910 and the processing unit 906).
The system Memory 910 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 911 and/or cache Memory 912. The computer device 90 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 913 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 11, and commonly referred to as a "hard disk drive"). Although not shown in FIG. 11, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 908 by one or more data media interfaces. System memory 910 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
Program/utility 914 having a set (at least one) of program modules 9140 may be stored, for example, in system memory 910, such program modules 9140 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination of these examples may comprise an implementation of a network environment. Program modules 9140 generally perform the functions and/or methods of embodiments described herein.
The computer device 90 may also communicate with one or more external devices 10 (e.g., keyboard, pointing device, display 100, etc.), with one or more devices that enable a user to interact with the terminal device 90, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 90 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 902. Moreover, computer device 90 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via Network adapter 900. As shown in FIG. 11, network adapter 900 communicates with the other modules of computer device 90 via bus 908. It should be appreciated that although not shown in FIG. 11, other hardware and/or software modules may be used in conjunction with computer device 90, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 906 executes various functional applications and data processing by executing programs stored in the system memory 910, for example, implementing the video interaction method based on the interest cluster mentioned in the foregoing embodiments.
In order to implement the foregoing embodiments, the present application further proposes a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the video interaction method based on the interest cluster as described in the foregoing embodiments.
In order to implement the foregoing embodiments, the present application further proposes a computer program product, wherein when the instructions in the computer program product are executed by a processor, the video interaction method based on the interest cluster as described in the foregoing embodiments is implemented.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A video interaction method based on interest clusters is characterized by comprising the following steps:
constructing an interest cluster of the user according to semantic similarity among the interest points of the user; the interest clusters comprise interest labels with similar semantics, and the interest labels are determined according to the interest clusters of the user;
establishing a plurality of candidate video queues according to the interest labels in the interest clusters; any candidate video queue comprises all video resources belonging to the same interest cluster;
selecting a target video queue from the candidate video queues and acquiring a historical playing sequence of the user;
processing the target video queue and the historical playing sequence through a preset generation model to generate a recommended video sequence and provide the recommended video sequence for the user;
and each video queue in the candidate video queues only comprises the candidate results of the corresponding interest cluster.
2. The method of claim 1, wherein the constructing the interest cluster of the user comprises:
acquiring operation record information of the user, and acquiring a plurality of interest points of the user from the operation record information;
determining a root interest point and generating a root interest set corresponding to the root interest point;
obtaining semantic similarity between any interest point of the interest points and the root interest point, and adding the interest point into the root interest set when the semantic similarity is greater than a preset threshold;
forming a plurality of root interest sets into the interest cluster.
3. The method of claim 1, wherein said building a plurality of candidate video queues according to interest tags in said interest cluster comprises:
and acquiring videos corresponding to the interest tags from a preset video resource database to serve as the candidate video queues.
4. The method of claim 1, wherein said building a plurality of candidate video queues according to interest tags in said interest cluster comprises:
acquiring a historical playing video of the user;
and determining the candidate video queues according to the interest tags and the historical playing videos.
5. The method of claim 1, wherein after the generating the recommended video sequence is provided to the user, further comprising:
after receiving video theme switching operation input by the user, acquiring playing time lengths of different theme video queues based on a preset time length estimation model;
and sequencing the playing time lengths according to the time, and taking the subject video queue corresponding to the first playing time length as a switched video playing sequence.
6. A video interaction device based on interest clusters, comprising:
the first establishing module is used for establishing an interest cluster of the user according to semantic similarity among interest points of the user; the interest clusters comprise interest labels with similar semantics, and the interest labels are determined according to the interest clusters of the user;
the second establishing module is used for establishing a plurality of candidate video queues according to the interest labels in the interest clusters; any candidate video queue comprises all video resources belonging to the same interest cluster;
the acquisition module is used for selecting a target video queue from the candidate video queues and acquiring a historical playing sequence of the user;
the processing module is used for processing the target video queue and the historical playing sequence through a preset generation model to generate a recommended video sequence and provide the recommended video sequence for the user;
and each video queue in the candidate video queues only comprises the candidate results of the corresponding interest cluster.
7. The apparatus of claim 6, wherein the first establishing module is specifically configured to:
acquiring operation record information of the user, and acquiring a plurality of interest points of the user from the operation record information;
determining a root interest point and generating a root interest set corresponding to the root interest point;
obtaining semantic similarity between any interest point of the interest points and the root interest point, and adding the interest point into the root interest set when the semantic similarity is greater than a preset threshold;
forming a plurality of root interest sets into the interest cluster.
8. The apparatus according to claim 6, wherein the second establishing module is specifically configured to:
and acquiring videos corresponding to the interest tags from a preset video resource database to serve as the candidate video queues.
9. A computer device comprising a processor and a memory;
wherein the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, for implementing the cluster-of-interest-based video interaction method according to any one of claims 1 to 5.
10. A non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor implements the cluster-of-interest based video interaction method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811525722.3A CN109710805B (en) | 2018-12-13 | 2018-12-13 | Video interaction method and device based on interest cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811525722.3A CN109710805B (en) | 2018-12-13 | 2018-12-13 | Video interaction method and device based on interest cluster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109710805A CN109710805A (en) | 2019-05-03 |
| CN109710805B true CN109710805B (en) | 2022-03-04 |
Family
ID=66255767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811525722.3A Active CN109710805B (en) | 2018-12-13 | 2018-12-13 | Video interaction method and device based on interest cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109710805B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096523B (en) * | 2019-05-16 | 2021-07-02 | 广州方硅信息技术有限公司 | Method and equipment for generating unordered question queue |
| CN110334245B (en) * | 2019-05-20 | 2023-04-07 | 山东大学 | Short video analysis method and device of graph neural network based on time sequence attribute |
| CN110381364A (en) * | 2019-06-13 | 2019-10-25 | 北京奇艺世纪科技有限公司 | Video data handling procedure, device, computer equipment and storage medium |
| CN110413885A (en) * | 2019-07-17 | 2019-11-05 | 咪咕互动娱乐有限公司 | A kind of exchange method and relevant device |
| CN110516153B (en) * | 2019-08-28 | 2023-05-30 | 腾讯科技（深圳）有限公司 | Intelligent video pushing method and device, storage medium and electronic device |
| CN111010592B (en) * | 2019-12-19 | 2022-09-30 | 上海众源网络有限公司 | Video recommendation method and device, electronic equipment and storage medium |
| CN111182332B (en) * | 2019-12-31 | 2022-03-22 | 广州方硅信息技术有限公司 | Video processing method, device, server and storage medium |
| CN112423134B (en) * | 2020-07-06 | 2022-03-29 | 上海哔哩哔哩科技有限公司 | Video content recommendation method and device, computer equipment and storage medium |
| CN111918104A (en) * | 2020-07-29 | 2020-11-10 | 有半岛(北京)信息科技有限公司 | Video data recall method and device, computer equipment and storage medium |
| CN112528071A (en) * | 2020-10-30 | 2021-03-19 | 百果园技术(新加坡)有限公司 | Video data sorting method and device, computer equipment and storage medium |
| CN113011919B (en) * | 2021-03-10 | 2024-02-02 | 腾讯科技（深圳）有限公司 | Method and device for identifying object of interest, recommendation method, medium and electronic equipment |
| CN112862007B (en) * | 2021-03-29 | 2022-12-13 | 山东大学 | Commodity sequence recommendation method and system based on user interest editing |
| CN113095884B (en) * | 2021-04-21 | 2022-12-06 | 山东大学 | Television member user recommendation method and system based on user feedback |
| CN113127684B (en) * | 2021-06-16 | 2021-08-27 | 北京视连通科技有限公司 | Short video generation method based on user interest and interactive behavior |
| CN113704510B (en) * | 2021-07-30 | 2024-02-06 | 北京达佳互联信息技术有限公司 | Media content recommendation method and device, electronic equipment and storage medium |
| CN113630631A (en) * | 2021-08-23 | 2021-11-09 | 南京金智视讯技术有限公司 | HLS caching method and system based on collaborative filtering recommendation algorithm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6845374B1 (en) * | 2000-11-27 | 2005-01-18 | Mailfrontier, Inc | System and method for adaptive text recommendation |
| CN103136275A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术（上海）有限公司 | System and method for recommending personalized video |
| CN104376058A (en) * | 2014-11-07 | 2015-02-25 | 华为技术有限公司 | User interest model updating method and device |
| CN107645667A (en) * | 2017-09-21 | 2018-01-30 | 广州华多网络科技有限公司 | Video recommendation method, system and server apparatus |
| CN107846629A (en) * | 2017-10-11 | 2018-03-27 | 五八有限公司 | Recommend the method, apparatus and server of video to user |
| CN108197327A (en) * | 2018-02-07 | 2018-06-22 | 腾讯音乐娱乐（深圳）有限公司 | Song recommendations method, apparatus and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8019766B2 (en) * | 2007-03-30 | 2011-09-13 | Amazon Technologies, Inc. | Processes for calculating item distances and performing item clustering |
| US20090013347A1 (en) * | 2007-06-11 | 2009-01-08 | Gulrukh Ahanger | Systems and methods for reporting usage of dynamically inserted and delivered ads |
| JP2012128765A (en) * | 2010-12-17 | 2012-07-05 | Mitsubishi Electric Corp | Video display device, video display method, video display control program, and recording medium |
| US8713004B1 (en) * | 2011-08-26 | 2014-04-29 | Google Inc. | Method and system for prioritizing points of interest for display in a map using category score |
| US8645366B1 (en) * | 2011-12-30 | 2014-02-04 | Google Inc. | Generating recommendations of points of interest |
| US9080885B2 (en) * | 2012-06-05 | 2015-07-14 | Apple Inc. | Determining to display designations of points of interest within a map view |
| US20160132513A1 (en) * | 2014-02-05 | 2016-05-12 | Sk Planet Co., Ltd. | Device and method for providing poi information using poi grouping |
-
2018
- 2018-12-13 CN CN201811525722.3A patent/CN109710805B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6845374B1 (en) * | 2000-11-27 | 2005-01-18 | Mailfrontier, Inc | System and method for adaptive text recommendation |
| CN103136275A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术（上海）有限公司 | System and method for recommending personalized video |
| CN104376058A (en) * | 2014-11-07 | 2015-02-25 | 华为技术有限公司 | User interest model updating method and device |
| CN107645667A (en) * | 2017-09-21 | 2018-01-30 | 广州华多网络科技有限公司 | Video recommendation method, system and server apparatus |
| CN107846629A (en) * | 2017-10-11 | 2018-03-27 | 五八有限公司 | Recommend the method, apparatus and server of video to user |
| CN108197327A (en) * | 2018-02-07 | 2018-06-22 | 腾讯音乐娱乐（深圳）有限公司 | Song recommendations method, apparatus and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109710805A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109710805B (en) | Video interaction method and device based on interest cluster | |
| CN109670029B (en) | Method, apparatus, computer device and storage medium for determining answers to questions | |
| CN108882020B (en) | Video information processing method, device and system | |
| US11995556B2 (en) | Video retrieval method, and method and apparatus for generating video retrieval mapping relationship | |
| CN109376267B (en) | Method and apparatus for generating a model | |
| CN108491540B (en) | Text information pushing method and device and intelligent terminal | |
| CN109300179B (en) | Animation production method, device, terminal and medium | |
| CN112511854B (en) | Live video highlight generation method, device, medium and equipment | |
| CN109947993B (en) | Plot skipping method and device based on voice recognition and computer equipment | |
| CN110730387B (en) | Video playing control method and device, storage medium and electronic device | |
| CN109348254B (en) | Message pushing method, device, computer equipment and storage medium | |
| CN109086439A (en) | Information recommendation method and device | |
| CN111046286A (en) | Object recommendation method and device and computer storage medium | |
| US20220248096A1 (en) | Automatic trailer detection in multimedia content | |
| CN111708941A (en) | Content recommendation method and device, computer equipment and storage medium | |
| CN109961041B (en) | Video identification method and device and storage medium | |
| CN110402445A (en) | Use recurrent neural network processing sequence data | |
| CN113965751B (en) | Screen content coding method, device, equipment and storage medium | |
| CN111680517A (en) | Method, apparatus, device and storage medium for training a model | |
| CN112804558B (en) | Video splitting method, device and equipment | |
| CN109255070B (en) | Recommendation information processing method and device, computer equipment and storage medium | |
| CN114040216B (en) | Live broadcast room recommendation method, medium, device and computing equipment | |
| CN115801980A (en) | Video generation method and device | |
| CN112182281B (en) | Audio recommendation method, device and storage medium | |
| CN113923472A (en) | Video content analysis 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |