Video recommendation method, device, storage medium and electronic device

Abstract

The present disclosure relates to a video recommendation method, device, storage medium and electronic device, the method comprising: obtaining a video to be recommended and extracting content features of the video to be recommended; searching a video library for K target videos whose content features are most similar to the content features of the video to be recommended according to the content features of the video to be recommended, wherein the video library stores video information for representing videos whose playback heat is greater than a preset playback heat threshold, and K is an integer greater than 0; constructing an association relationship between the video to be recommended and all the target videos, and using the association relationship as an extended feature of the video to be recommended; at least inputting the extended feature into a recommendation model to recommend the video to be recommended to a target object, thereby achieving accurate distribution of videos, improving the distribution effect of video cold start, and avoiding waste of resources.

Description

Technical Field

[0001] The present disclosure relates to the field of electronic information technology, and in particular to a video recommendation method, device, storage medium and electronic device. Background Art

[0002] The recommendation model can recommend videos that match users' interests based on certain information, thus satisfying users' needs to watch similar or related videos.

[0003] However, for some newly released videos, since such videos have not been watched or have been watched less by users, the recommendation model has not fully learned the features of such videos and the basis for recommendation is incomplete, resulting in the recommendation model being unable to accurately match which users may like such videos, resulting in poor distribution of such videos. This is the cold start problem faced by video recommendation. Poor video distribution directly leads to a waste of resources used to distribute such videos. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a video recommendation method, comprising:

[0006] Obtaining a video to be recommended, and extracting content features of the video to be recommended;

[0007] According to the content features of the video to be recommended, searching a video library for K target videos whose content features are most similar to the content features of the video to be recommended, wherein the video library stores video information representing videos whose playback popularity is greater than a preset playback popularity threshold, and K is an integer greater than 0;

[0008] Constructing an association relationship between the video to be recommended and all the target videos, and using the association relationship as an extended feature of the video to be recommended;

[0009] At least the extended features are input into a recommendation model to recommend the video to be recommended to a target object.

[0010] In a second aspect, the present disclosure provides a video recommendation device, comprising:

[0011] An acquisition module, used to acquire the video to be recommended and extract content features of the video to be recommended;

[0012] A query module, configured to query a video library for K target videos whose content features are most similar to the content features of the video to be recommended, based on the content features of the video to be recommended, wherein the video library stores video information representing videos whose playback popularity is greater than a preset playback popularity threshold, and K is an integer greater than 0;

[0013] A construction module, used to construct an association relationship between the video to be recommended and all the target videos, and use the association relationship as an extended feature of the video to be recommended;

[0014] The recommendation module is used to input at least the extended features into a recommendation model to recommend the video to be recommended to a target object.

[0015] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the first aspect when executed by a processing device.

[0016] In a fourth aspect, the present disclosure provides an electronic device, including:

[0017] a storage device having a computer program stored thereon;

[0018] A processing device is used to execute the computer program in the storage device to implement the steps of the method in the first aspect.

[0019] Through the above technical scheme, since the target video has a high playback popularity, the representation recommendation model can accurately recommend the target video to users who are interested in it, and for users watching videos, the contents of the videos they are interested in are similar. Therefore, the video to be recommended and the target video with a high playback popularity and highly similar content to the video to be recommended can be associated, and the associated relationship obtained can be input into the recommendation model as the feature of the video to be recommended, and used as the basis for the recommendation model to distribute the video to be recommended. The recommendation model can recommend the video to be recommended to the target object who is interested in the target video and is interested in the video to be recommended with similar content to the target video, thereby realizing accurate distribution of videos, improving the distribution effect of video cold start, and avoiding waste of resources.

[0020] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0022] Figure 1 The figure is a flowchart of a video recommendation method according to an exemplary embodiment of the present disclosure.

[0023] Figure 2 The diagram is a schematic diagram showing a method of establishing an association relationship according to an exemplary embodiment of the present disclosure.

[0024] Figure 3 It is a schematic diagram showing a method of obtaining fusion features according to an exemplary embodiment of the present disclosure.

[0025] Figure 4 The block diagram of a video recommendation device according to an exemplary embodiment of the present disclosure is shown.

[0026] Figure 5 It is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0029] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0034] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0035] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0036] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0037] At the same time, it is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0038] As mentioned in the background technology, for some newly released videos, since such videos have not been watched or are rarely watched by users, the recommendation model lacks the basis for distributing such videos to users who are interested in them, resulting in such videos being unable to be accurately distributed to users who are interested in such videos in the early stage of recommendation, resulting in low video distribution efficiency, poor video cold start effect, and waste of video distribution resources. In addition, for the original creators who uploaded the videos, the inaccurate distribution of the videos will also lead to a poor experience for the original creators, reducing the original creators' enthusiasm for video creation, which is also unfavorable to the video distribution platform.

[0039] In view of this, the embodiments of the present disclosure provide a video recommendation method, device, storage medium and electronic device to achieve accurate distribution of videos and improve the distribution effect of video cold start.

[0040] The present disclosure is further explained below in conjunction with the accompanying drawings.

[0041] Figure 1 1 is a flowchart of a video recommendation method according to an exemplary embodiment of the present disclosure. The video recommendation method can be applied to an electronic device, such as a mobile phone, a tablet, etc. Figure 1 , the video recommendation method may include the following steps.

[0042] Step S101, obtaining a video to be recommended and extracting content features of the video to be recommended.

[0043] The video to be recommended is a cold start video, which can be understood as a video that has not been watched or has been watched less by the user.

[0044] In some embodiments, a content extraction model may be used to extract content features of the video to be recommended. The content extraction model may extract features of the video from multiple different dimensions as the content features of the video, thereby increasing the amount of information of the content features. For example, the dimensions here may be picture dimensions, text dimensions, and sound dimensions, etc. The content extraction model may be obtained by training based on a supervised method or an unsupervised method, which is not limited in this embodiment.

[0045] Step S102, based on the content features of the video to be recommended, search the video library for K target videos whose content features are most similar to the content features of the video to be recommended, wherein the video library stores video information for representing videos whose playback popularity is greater than a preset playback popularity threshold, and K is an integer greater than 0.

[0046] The preset playback heat threshold can be set according to actual conditions. For example, the playback heat can be represented by the number of playbacks, and correspondingly, the preset playback heat threshold can be represented by the preset number of playbacks.

[0047] The similarity between videos can be determined by calculating the distance between content features, and the K target videos in the video library that are most similar to the video to be recommended in terms of content can be determined based on the similarity. It is worth noting that the shorter the distance between the content features of the videos, the higher the similarity between the videos. For example, the distance can be Euclidean distance, Manhattan distance, Chebyshev distance, Mahalanobis distance, etc.

[0048] The video information may be an identifier corresponding to the video. It is worth noting that the identifier of the video is used to determine the unique video corresponding thereto.

[0049] The video information may be content features corresponding to the video, and the content features may be extracted based on the content extraction model described above.

[0050] Step S103: construct an association relationship between the video to be recommended and all target videos, and use the association relationship as an extended feature of the video to be recommended.

[0051] In some embodiments, the storage structure of the association relationship may be a key-value pair storage structure.

[0052] In some embodiments, the storage structure of the association relationship may be a graph storage structure.

[0053] Step S104: at least input the extended features into the recommendation model to recommend the video to be recommended to the target object.

[0054] For example, the input of the recommendation model may also include the extended features of the video to be recommended and the inherent features of the video to be recommended. The inherent features of the video to be recommended are the inherent features of the video to be recommended. Generally, if the video content does not change, the inherent features of the video will not change. For example, the inherent features of the video to be recommended here may be, for example, the category features of the video to be recommended, and the category may be, for example, singing, dancing, pets, etc.

[0055] It is worth noting that the target object is an object that is interested in the target video. Since the target video has a high playback popularity, the representation recommendation model can accurately recommend the target video to users who are interested in it, and it is understandable that for users who watch videos, the content of the videos they are interested in is similar. Therefore, the video to be recommended can be associated with a target video with a high playback popularity and a content that is highly similar to the video to be recommended, and the associated relationship obtained can be input into the recommendation model as a feature of the video to be recommended, and used as the basis for the recommendation model to distribute the video to be recommended. This allows the recommendation model to recommend the video to the target object who is interested in the target video and is interested in the video to be recommended with content similar to the target video, thereby achieving accurate video distribution, improving the distribution effect of video cold start, and avoiding waste of resources.

[0056] In addition, for original creators, accurate distribution of videos can enhance their video creation experience, and at the same time, it is also beneficial to improve the video quality of the video distribution platform.

[0057] In some embodiments, Figure 1 The step S103 shown can be implemented in the following manner: construct a mapping relationship between the identifier of the video to be recommended and the identifier of each target video; combine all the constructed mapping relationships to obtain the association relationship between the video to be recommended and the target video, and use the association relationship as the extended feature of the video to be recommended.

[0058] For example, the mapping relationship can be a key-value pair relationship, and the storage structure of the corresponding association relationship is a key-value pair storage structure. Specifically, the key in the mapping relationship can be the identifier of the video to be recommended, and the value in the mapping relationship can be the identifier of the target video. The identifier of the video to be recommended and the identifier of the target video constitute a key-value pair. The following is an example to illustrate the combination of all the constructed mapping relationships, with the mapping relationship including (ID 1 , ID1), (ID 1 , ID2) and (ID 1 , ID3) as an example, where ID 1 The IDs of the videos to be recommended are represented by ID1, ID2 and ID3, which represent the IDs of different target videos. The combined association relationship can be [(ID 1 , ID1), (ID 1 , ID2) and (ID 1 , ID3)], the storage structure of this association relationship is a key-value pair storage structure.

[0059] For example, the mapping relationship can be a binary relationship with edges. The binary relationship is a relationship between two elements obtained by constructing edges, and the storage structure of the corresponding association relationship is a graph storage structure. Specifically, the elements in the mapping relationship can be the identifier of the video to be recommended and the identifier of the target video. An edge can be constructed between the identifier of the video to be recommended and the identifier of the target video. The identifier of the video to be recommended, the identifier of the target video, and the edge between the identifier of the video to be recommended and the identifier of the target video constitute a binary relationship. The following is an example to illustrate the combination of all the constructed mapping relationships, with reference to Figure 2 ,exist Figure 2 In, ID 1 The identifier of the video to be recommended ( Figure 2 ), ID1, ID2 and ID3 represent the identifiers of different target videos ( Figure 2 (indicated by a circle in the figure), Figure 2 Combining the three mapping relationships shown in the figure, we can get Figure 2 The association relationship shown in FIG. 1 is a graph storage structure.

[0060] Through the above method, through the association relationship between the above identifiers, users who are interested in the recommended video can be determined, and only the identifier corresponding to the video is used to characterize the extended features of the recommended video, ensuring that the recommendation model has a larger learning space for the features of the recommended video.

[0061] In some embodiments, Figure 1The step S103 shown can be implemented in the following manner: construct a mapping relationship between the identifier of the video to be recommended and the feature representation of each target video in the recommendation model; combine all the constructed mapping relationships to obtain the association relationship between the video to be recommended and the target video, and use the association relationship as the extended feature of the video to be recommended.

[0062] Similar to the above, the mapping relationship can be a key-value pair relationship. Specifically, the key in the mapping relationship can be the identifier of the video to be recommended, and the value in the mapping relationship can be the feature representation of the identifier of the target video in the recommendation model. The identifier of the video to be recommended and the feature representation of the identifier of the target video in the recommendation model constitute a key-value pair. In addition, the implementation method of combining all constructed mapping relationships can be found in the above-mentioned related embodiments, and this embodiment will not be described in detail here.

[0063] Similar to the above, the mapping relationship can be a binary relationship with edges. Specifically, the elements in the mapping relationship can be the feature representations of the identifier of the video to be recommended and the identifier of the target video in the recommendation model. An edge can be constructed between the identifier of the video to be recommended and the identifier of the target video in the feature representation of the recommendation model. The identifier of the video to be recommended, the identifier of the target video in the feature representation of the recommendation model, and the edges between the identifier of the video to be recommended and the identifier of the target video in the feature representation of the recommendation model constitute a binary relationship. In addition, the implementation method for combining all constructed mapping relationships can be found in the above-mentioned related embodiments, and this embodiment will not be described in detail here.

[0064] Through the above method, through the association relationship between the above identification and the feature representation, users who are interested in the recommended video can be determined, and the extended features of the video to be recommended can be directly characterized based on the feature representation of the target video by the recommendation model, which can reduce the changes to the model.

[0065] In some embodiments, Figure 1 The step S103 shown can be implemented in the following manner: fuse the target features of all target videos to obtain fused features; construct a mapping relationship between the identifier of the video to be recommended and the fused features; use the constructed mapping relationship as the association relationship between the video to be recommended and the target video, and use the association relationship as the extended feature of the video to be recommended.

[0066] The target feature is at least one of a content feature and a feature representation in a recommendation model. It is worth noting that the content feature can be extracted based on the above-mentioned content extraction model.

[0067] Reference Figure 3 ,exist Figure 3In the example, the reference video is a video whose playback times are greater than the preset playback times. The reference video is subjected to content feature extraction by the content extraction model. The extracted content feature of the reference video can be inserted into the video library and stored as video information of a video whose playback popularity is greater than the preset playback popularity threshold. The content feature of the video to be recommended is extracted by the content extraction model to obtain the content feature of the video to be recommended. Based on the content feature of the video to be recommended, the K content features most similar to the content feature of the video to be recommended are queried in the video library ( Figure 2 The K most similar content features are fused to obtain fused features, which can be used as a basis for constructing the association between the video to be recommended and all target videos, thereby obtaining the extended features of the video to be recommended. It is worth noting that the K content features here are the content features corresponding to the K target videos.

[0068] In addition, Figure 2 In the example, the feature representations of the videos corresponding to the K results in the recommendation model can be fused to obtain fused features.

[0069] In the above manner, the K results that are most similar to the video to be recommended are fused to simplify the association relationship between the constructed video to be recommended and all target videos.

[0070] In some embodiments, the method may further include: deleting video information in the video library whose storage duration exceeds a preset maximum storage duration from the video library.

[0071] Among them, the preset maximum storage time can be set according to actual conditions.

[0072] It is worth mentioning that online videos are constantly updated. Video information in the video library that has been stored for more than the preset maximum storage time can be deleted from the video library. In this way, the video library can be updated as the online videos are updated, ensuring real-time updates of highly popular videos. At the same time, it can also reduce the storage pressure of the video library.

[0073] In some embodiments, there may be multiple video libraries, and each video library is used to store video information of videos whose playback popularity is greater than different preset playback popularity thresholds. Different preset playback popularity thresholds correspond to different preset maximum storage durations, and the preset playback popularity threshold is directly proportional to the preset maximum storage duration.

[0074] For example, the playback popularity is represented by the number of playback times. The preset playback popularity threshold corresponding to video library 1 can be 1000 times, and the preset maximum storage time can be 7 days; the preset playback popularity threshold corresponding to video library 2 can be 5000 times, and the preset maximum storage time can be 30 days.

[0075] It is worth noting that, especially when the preset playback heat threshold is set to be small, the number of videos greater than the same preset playback heat threshold is large, and for two videos with the same preset playback heat threshold, the greater the difference in the playback heat of the two videos, the degree of influence on the distribution of the recommended video may be different. Therefore, multiple video information for storing videos with playback heat greater than different preset playback heat thresholds can be maintained. In this case, the association relationship between the K most similar target videos to the model to be recommended and the video to be recommended in different video libraries can be constructed to obtain different extended features of the video to be recommended, thereby increasing the amount of information of the recommendation model in distributing the video to be recommended, so that multiple extended features can be used as inputs of the recommendation model to achieve the distribution of the video to be recommended, and further improve the recommendation accuracy.

[0076] It is worth noting that the number of videos above the first preset playback heat threshold is smaller than the number of videos above the second preset playback heat threshold, wherein the first preset playback heat threshold is greater than the second preset playback heat threshold; considering the different numbers, it is unreasonable to set the same preset maximum storage time. Therefore, for different preset playback heat thresholds, different preset maximum storage times need to be set, and the preset playback heat threshold is proportional to the preset maximum storage time, that is, the higher the preset playback heat threshold, the longer the preset maximum storage time, so as to achieve targeted filtering of video information of videos with different playback heat.

[0077] Figure 4 is a block diagram of a video recommendation device according to an exemplary embodiment of the present disclosure, referring to Figure 4 , the video recommendation device 400 may include:

[0078] The acquisition module 401 is used to acquire the video to be recommended and extract the content features of the video to be recommended;

[0079] A query module 402 is used to query K target videos whose content features are most similar to the content features of the video to be recommended in a video library according to the content features of the video to be recommended, wherein the video library stores video information representing videos whose playback popularity is greater than a preset playback popularity threshold, and K is an integer greater than 0;

[0080] A construction module 403 is used to construct an association relationship between the video to be recommended and all the target videos, and use the association relationship as an extended feature of the video to be recommended;

[0081] The recommendation module 404 is configured to at least input the extended features into a recommendation model to recommend the video to be recommended to a target object.

[0082] In some embodiments, the building block 403 includes:

[0083] A first construction submodule is used to construct a mapping relationship between the identifier of the video to be recommended and the identifier of each target video;

[0084] The first determination submodule is used to combine all the constructed mapping relationships to obtain the association relationship between the video to be recommended and the target video, and use the association relationship as the extended feature of the video to be recommended.

[0085] In some embodiments, the building block 403 includes:

[0086] A second construction submodule is used to construct a mapping relationship between the identifier of the video to be recommended and the feature representation of each target video in the recommendation model;

[0087] The second determination submodule is used to combine all the constructed mapping relationships to obtain the association relationship between the video to be recommended and the target video, and use the association relationship as the extended feature of the video to be recommended.

[0088] In some embodiments, the building block 403 includes:

[0089] A fusion submodule, used for fusing target features of all the target videos to obtain fused features, wherein the target feature is at least one of a content feature and a feature representation in the recommendation model;

[0090] The third construction submodule is used to construct a mapping relationship between the identifier of the video to be recommended and the fusion feature;

[0091] The third determination submodule is used to use the constructed mapping relationship as the association relationship between the video to be recommended and the target video, and use the association relationship as the extended feature of the video to be recommended.

[0092] In some embodiments, the video recommendation device 400 further includes:

[0093] The deleting module is used to delete the video information whose storage time in the video library exceeds the preset maximum storage time from the video library.

[0094] In some embodiments, the video library includes multiple ones, each of which is used to store video information of videos whose playback popularity is greater than different preset playback popularity thresholds, different preset playback popularity thresholds correspond to different preset maximum storage durations, and the preset playback popularity threshold is proportional to the preset maximum storage duration.

[0095] In some embodiments, the storage structure of the association relationship is one of a key-value pair storage structure and a graph storage structure.

[0096] The implementation of each module in the above-mentioned device can refer to the above-mentioned method embodiment, and this embodiment will not be described in detail here.

[0097] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device 500 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0098] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0099] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0100] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable storage medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0101] It should be noted that the computer-readable storage medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable storage medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0102] In some embodiments, the electronic device can communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0103] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0104] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the video to be recommended and extracts the content features of the video to be recommended; based on the content features of the video to be recommended, searches the video library for K target videos whose content features are most similar to the content features of the video to be recommended, wherein the video library stores video information for representing videos whose playback popularity is greater than a preset playback popularity threshold, and K is an integer greater than 0; constructs an association relationship between the video to be recommended and all the target videos, and uses the association relationship as an extended feature of the video to be recommended; and at least inputs the extended feature into the recommendation model to recommend the video to be recommended to the target object.

[0105] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, an acquisition module may also be described as a "module for acquiring videos to be recommended and extracting content features of the videos to be recommended."

[0108] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0109] In the context of the present disclosure, a machine-readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable storage medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0111] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0112] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A video recommendation method, characterized in that: include: Obtaining a video to be recommended, and extracting content features of the video to be recommended; According to the content features of the video to be recommended, searching a video library for K target videos whose content features are most similar to the content features of the video to be recommended, wherein the video library stores video information representing videos whose playback popularity is greater than a preset playback popularity threshold, and K is an integer greater than 0; Constructing an association relationship between the video to be recommended and all the target videos, and using the association relationship as an extended feature of the video to be recommended; At least the extended features are input into a recommendation model to recommend the video to be recommended to a target object.

2. The method according to claim 1, characterized in that The step of constructing the association relationship between the video to be recommended and all the target videos, and using the association relationship as an extended feature of the video to be recommended, includes: Constructing a mapping relationship between the identifier of the video to be recommended and the identifier of each target video; All the constructed mapping relationships are combined to obtain the association relationship between the video to be recommended and the target video, and the association relationship is used as the extended feature of the video to be recommended.

3. The method according to claim 1, characterized in that The step of constructing the association relationship between the video to be recommended and all the target videos, and using the association relationship as an extended feature of the video to be recommended, includes: Constructing a mapping relationship between the identifier of the video to be recommended and the feature representation of each target video in the recommendation model; All the constructed mapping relationships are combined to obtain the association relationship between the video to be recommended and the target video, and the association relationship is used as the extended feature of the video to be recommended.

4. The method according to claim 3, characterized in that The step of constructing the association relationship between the video to be recommended and all the target videos, and using the association relationship as an extended feature of the video to be recommended, includes: fusing target features of all the target videos to obtain fused features, wherein the target features are at least one of content features and feature representations in the recommendation model; Constructing a mapping relationship between the identifier of the video to be recommended and the fusion feature; The constructed mapping relationship is used as the association relationship between the video to be recommended and the target video, and the association relationship is used as the extended feature of the video to be recommended.

5. The method according to claim 1, characterized in that: The method further comprises: The video information whose storage time in the video library exceeds the preset maximum storage time is deleted from the video library.

6. The method according to claim 1, characterized in that The video library includes multiple ones, each of which is used to store video information of videos whose playback heat is greater than different preset playback heat thresholds. Different preset playback heat thresholds correspond to different preset maximum storage durations, and the preset playback heat threshold is proportional to the preset maximum storage duration.

7. The method according to claim 1, characterized in that The storage structure of the association relationship is one of a key-value pair storage structure and a graph storage structure.

8. A video recommendation device, characterized in that: include: An acquisition module, used to acquire the video to be recommended and extract content features of the video to be recommended; A query module, configured to query a video library for K target videos whose content features are most similar to the content features of the video to be recommended, based on the content features of the video to be recommended, wherein the video library stores video information representing videos whose playback popularity is greater than a preset playback popularity threshold, and K is an integer greater than 0; A construction module, used to construct an association relationship between the video to be recommended and all the target videos, and use the association relationship as an extended feature of the video to be recommended; The recommendation module is used to input at least the extended features into a recommendation model to recommend the video to be recommended to a target object.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processing device, the steps of the method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 7.

Images