Video recommendation method and device, equipment and medium

Abstract

The invention provides a video recommendation method and device, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of recommendation. According to the implementation scheme, at least two candidate videos are determined from a video library, the video library comprises at least two video sets, and each video set comprises at least two videos; based on the historical operation features of the target user, first features of the candidate videos are obtained, and the first features comprise the probability that the target user watches other videos in a video set to which the corresponding candidate videos belong; determining a to-be-recommended video from candidate videos based on the first feature; and recommending the to-be-recommended video and the to-be-recommended video set to which the to-be-recommended video belongs to the target user.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of recommendation technology, and specifically to a video recommendation method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] Artificial intelligence (AI) is the study of how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily encompass computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graphs.

[0003] With the development of computer technology and big data technology, people's consumption, entertainment, learning, travel and other behaviors in life are closely related to big data. In the operation of video websites, it is usually necessary to actively recommend videos to users to increase video playback volume and user satisfaction.

[0004] The approaches described in this section are not necessarily approaches that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any approach described in this section is prior art simply by virtue of its inclusion in this section. Similarly, unless otherwise indicated, the issues raised in this section should not be considered as having been recognized in any prior art. Summary of the Invention

[0005] The present disclosure provides a video recommendation method, apparatus, electronic device, computer-readable storage medium, and computer program product.

[0006] According to one aspect of the present disclosure, a video recommendation method is provided, comprising: determining at least two candidate videos from a video library, wherein the video library includes at least two video collections, and each video collection includes at least two videos; obtaining a first feature of the candidate video based on a historical operation feature of a target user, wherein the first feature includes a probability that the target user watches other videos in the video collection to which the corresponding candidate video belongs; determining a video to be recommended from the candidate videos based on the first feature; and recommending the video to be recommended and the video collection to which the video to be recommended belongs to the video to be recommended to the target user.

[0007] According to another aspect of the present disclosure, a video recommendation device is provided, comprising: a first determination unit configured to determine at least two candidate videos from a video library, wherein the video library includes at least two video collections, and each video collection includes at least two videos; a second determination unit configured to obtain a first feature of the candidate video based on a historical operation feature of a target user, wherein the first feature includes a probability that the target user watches other videos in the video collection to which the corresponding candidate video belongs; a third determination unit configured to determine a video to be recommended from the candidate videos based on the first feature; and a recommendation unit configured to recommend the video to be recommended and the video collection to which the video to be recommended belongs to the video to be recommended to the target user.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned video recommendation method.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned video recommendation method.

[0010] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program can implement the above-mentioned video recommendation method when executed by a processor.

[0011] According to one or more embodiments of the present disclosure, the amount of video collections viewed by users can be increased, and the accuracy of video recommendations can be improved.

[0012] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings illustrate exemplary embodiments and constitute a part of the specification. Together with the description of the specification, they serve to explain exemplary implementation of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals designate similar, but not necessarily identical, elements.

[0014] Figure 1 A schematic diagram illustrating an exemplary system in which the various methods described herein may be implemented according to exemplary embodiments of the present disclosure;

[0015] Figure 2 A flowchart of a video recommendation method according to an exemplary embodiment of the present disclosure is shown;

[0016] Figure 3 shows a schematic structural diagram of a first prediction model according to an exemplary embodiment of the present disclosure;

[0017] Figure 4 A structural block diagram of a video recommendation device according to an exemplary embodiment of the present disclosure is shown;

[0018] Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0019] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0020] In this disclosure, unless otherwise specified, the use of terms such as "first" and "second" to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements. Such terms are only used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, while in some cases, based on the context of the description, they may also refer to different instances.

[0021] The terms used in the descriptions of the various examples described in this disclosure are for the purpose of describing specific examples only and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element may be one or more. In addition, the term "and / or" used in this disclosure encompasses any one and all possible combinations of the listed items.

[0022] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 FIG2 is a schematic diagram of an exemplary system 100 in which the various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1, the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 can be configured to execute one or more applications.

[0024] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable the video recommendation method to be performed.

[0025] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0026] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may, in turn, utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0027] The user can use client devices 101, 102, 103, 104, 105 and / or 106 to send a video recommendation request and transmit the user's historical operation characteristics. The client device can provide an interface that enables the user of the client device to interact with the client device. The client device can also output information to the user via the interface. Although Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure can support any number of client devices.

[0028] Client devices 101, 102, 103, 104, 105, and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux, or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include cellular phones, smartphones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, internet-enabled gaming devices, etc. The client device is capable of executing various different applications, such as various Internet-related applications, communication applications (eg, email applications), Short Message Service (SMS) applications, and may use various communication protocols.

[0029] The network 110 may be any type of network known to those skilled in the art that can support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0030] Server 120 may include one or more general-purpose computers, specialized server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0031] The computing units in the server 120 may run one or more operating systems including any of the operating systems described above as well as any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.

[0032] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display the data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0033] In some embodiments, server 120 may be a distributed system server or a server integrated with blockchain. Server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host equipped with artificial intelligence technology. A cloud server is a host product within the cloud computing service system that addresses the management difficulties and poor scalability of traditional physical hosts and virtual private servers (VPS) services.

[0034] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in a variety of locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different types. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0035] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0036] Figure 1The system 100 may be configured and operated in various ways to enable application of the various methods and apparatuses described in accordance with the present disclosure.

[0037] With the development of internet technology, the way people access information and entertainment has undergone tremendous changes. The rise of video streaming platforms, and in particular the popularity of short videos, has provided users with a way to quickly consume information and entertainment. In this context, video compilations have become an emerging form of video content promotion, effectively attracting users and boosting video platforms' business metrics (video views, video engagement, etc.).

[0038] In related technologies, when recommending videos to target users, recommendations are usually made based only on the target user's user characteristics and the characteristics of the candidate videos themselves (such as video content, video popularity, etc.), without considering the impact of the recommended videos on the viewing volume of the video collection.

[0039] Based on this, the present disclosure provides a video recommendation method, which uses the first feature of the candidate video to express whether the user will continue to watch the corresponding video collection after receiving the recommendation for a candidate video, and determines the video to be recommended based on this, so as to increase the user's viewing volume of the video collection and improve the video recommendation effect.

[0040] Figure 2 FIG. 2 shows a flow chart of a video recommendation method 200 according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the method 200 includes:

[0041] Step S201: Determine at least two candidate videos from a video library, wherein the video library includes at least two video collections, and each video collection includes at least two videos;

[0042] Step S202: Based on the historical operation characteristics of the target user, a first feature of the candidate video is obtained, wherein the first feature includes a probability that the target user has watched other videos in the video collection to which the corresponding candidate video belongs;

[0043] Step S203: determining a video to be recommended from the candidate videos based on the first feature; and

[0044] Step S204: recommend the video to be recommended and the collection of videos to be recommended to which the video to be recommended belongs to the target user.

[0045] By applying the above-mentioned video recommendation method 200, the first feature of the candidate video can be used to express the influence of the candidate video on the viewing rate of the video collection, that is, it can represent whether the user will continue to watch the corresponding video collection after receiving the recommendation for the candidate video, and based on this, the video to be recommended is determined, and then the user's viewing volume of the video collection is increased by actively pushing recommended videos to the user, thereby improving the accuracy of video recommendation.

[0046] In some examples, the multiple video collections in the video library can be multiple TV series, and the multiple videos included in each video collection can be multiple episodes of the TV series. In this case, by recommending episode videos that are more likely to attract users to pay attention to the entire TV series (for example, to encourage users to follow the TV series), the playback volume and attention of the TV series can be increased, thereby improving the recommendation effect.

[0047] According to some embodiments, the first feature includes the predicted number or predicted duration of viewing of other videos within the video collection to which the candidate video belongs by the target user. By predicting the user's viewing probability, viewing step, and viewing duration for a candidate video, the impact of the candidate video on the video collection's playback volume can be accurately assessed, facilitating more precise adjustment of recommendation targets and achieving more accurate recommendations.

[0048] In some examples, when video collection A includes four candidate videos A1, A2, A3, and A4, it is possible to predict for each candidate video whether the user will watch other videos in video collection A (i.e., viewing probability). It is also possible to predict the number of videos the user will watch in video collection A (e.g., watching 2 videos, i.e., a viewing step of 2) or the predicted duration of the videos the user will watch in video collection A (e.g., watching 10 minutes of video in video collection A, i.e., a viewing duration of 10 minutes).

[0049] In some examples, the first feature of each candidate video can also include more content. Specifically, it can be a prediction of more behavioral content of the target user on the video collection. For example, it can predict whether the target user will pay attention to the video collection corresponding to the candidate video, thereby facilitating more precise adjustment of the recommendation target and achieving more accurate recommendations.

[0050] In some examples, the at least two candidate videos determined in step S201 may be all the candidate videos in the video library, or may be some of the candidate videos in the video library. In some examples, the candidate videos may be screened from the video library according to the needs of the actual business scenario. For example, when it is necessary to recommend short videos whose video length is not greater than a certain threshold to the user, the videos may be screened from the video library based on the video length. For another example, other methods may be applied to determine the target user's preferences for video features (such as video content, video popularity), and then multiple candidate videos may be screened from the video library based on the user's preferences, and then the method 200 provided in the present disclosure may be applied to determine the video to be recommended from the candidate videos.

[0051] According to some embodiments, in step S202, obtaining the first feature of the candidate video based on the historical operation feature of the target user includes: for each candidate video, determining the first feature based on the historical operation feature and the second features of at least two videos included in the video collection to which the candidate video belongs, wherein the second feature includes at least one of the following: the probability of the target user watching the corresponding video, the historical playback information of the corresponding video, and the historical feedback information of the corresponding video. Thus, the second features of multiple videos in each video collection (such as the predicted viewing rate, historical playback volume, historical praise rate, etc. of the video) can be used to express the characteristics of the video collection, thereby more accurately determining the probability of the user watching other videos in the video collection (i.e., the first feature) to improve the recommendation accuracy.

[0052] In some examples, step S202 can also combine more content related to the candidate video to determine the first feature, such as the video content features and video popularity (such as the number of video views and likes), so as to more accurately determine the first feature of each candidate video to improve the recommendation accuracy.

[0053] In some examples, step S202 may also combine more features related to the target user to determine the first feature, such as user preference information. In one example, user preference information may be determined based on information such as the user's historical viewing history and liked content, thereby more accurately determining the first feature of each candidate video to improve recommendation accuracy.

[0054] It should be noted that the technical solutions disclosed herein involve the collection, storage, use, processing, desensitization, transmission, provision and disclosure of information such as the user's historical operation characteristics, of which the users are aware and authorized, and in compliance with relevant laws and regulations.

[0055] According to some embodiments, determining the first feature for each candidate video based on the historical operational feature and the second features of at least two videos included in the video collection to which the candidate video belongs includes: for each candidate video, inputting the historical operational feature and the corresponding second feature into a first prediction model to obtain the first feature output by the first prediction model, wherein the first prediction model is trained using sample data annotated with reference to the first feature. By using the first prediction model to obtain the first feature of the candidate video, the first feature of each candidate video can be determined more simply and accurately, thereby improving the efficiency and accuracy of recommendations.

[0056] In some examples, the sample data used to train the first prediction model can be constructed based on the user's real historical behavior data. For example, when the historical recommendation sequence for the sample user includes video A1 and video A2 in video collection A, and video B1 and video B2 in video collection B, four sets of sample data can be constructed based on the video features of video A1, video A2, video B1, and video B2, as well as the historical operation features of the sample user, and the real interaction information that can indicate whether the sample user watched the video collection described by each video is used as annotation information, and then the loss value can be calculated based on the prediction results of the first prediction model and the annotation information to tune and train the first prediction model, thereby obtaining a first prediction model with higher prediction accuracy.

[0057] In some examples, other methods may also be used to determine the first feature of a candidate video. For example, the user's historical interaction information may be analyzed to record whether the user continues to watch the video collection to which the historically recommended video belongs after watching it. The first feature of each candidate video may then be determined based on the similarity between each candidate video and the historically recommended videos that the target user has watched. For example, when a candidate video has a high similarity to a historically recommended video in the video collection that the target user has historically watched, it can be determined that there is a high probability that the target user will continue to watch the video collection to which the candidate video belongs after watching it, thereby obtaining the first feature of the candidate video.

[0058] According to some embodiments, the second feature includes a probability of the target user viewing the corresponding video. Method 200 further includes: inputting the historical operation feature and the video feature of the corresponding video into a second prediction model, and obtaining the probability of the target user viewing the corresponding video output by the second prediction model, wherein the second prediction model is trained using sample data labeled with reference probabilities. Thus, the independent second prediction model can be used to predict the viewing rate of a single video, that is, the second feature of each candidate video can be determined more simply and accurately, thereby improving recommendation efficiency and accuracy.

[0059] It can be understood that the sample data construction process and supervised training process of the second prediction model are similar to the sample data construction process and supervised training process of the first prediction model described above, and will not be repeated here.

[0060] According to some embodiments, determining the video to be recommended from the candidate videos based on the first feature in step S203 includes: determining the video to be recommended from the candidate videos based on the first feature and a third feature of the candidate videos, wherein the third feature includes a probability of the target user viewing the corresponding candidate video. In this way, the video to be recommended can be determined by combining the view rate prediction results at the video collection level and the view rate prediction results at the individual video level, thereby achieving more accurate recommendations.

[0061] In some examples, the third feature of a candidate video can be determined using an existing video recommendation algorithm. For example, the method described above can be used to construct sample data based on real historical user behavior data and perform supervised training on a video recommendation model. The trained video recommendation model can then be used to determine the third feature of each candidate video.

[0062] In some examples, the strength of each of the first and third features of the candidate video can be adjusted in step S202 based on the needs of the actual application scenario. For example, if the recommendation goal is to maximize the number of views of the video collection, the strength (weight) of the first feature of the candidate video can be increased in step S202 to meet the needs of the recommendation business.

[0063] According to some embodiments, the historical operation feature includes the target user's historical interaction information for the video collection to which the historical recommended video belongs, and the determining the video to be recommended from the candidate videos based on the first feature and the third feature of the candidate video includes: determining the video to be recommended based on the product between the first feature and the first feature weight of the target user, and the third feature, wherein the first feature weight of the target user is determined based on the historical interaction information. Thus, the strength of the first feature (first feature weight) can be determined based on the target user's historical interaction information. It can be understood that when the target user's historical interaction information is relatively rich (for example, it contains a large amount of target user viewing data for the historically recommended video collection), the first feature determined based on this has a higher accuracy, while when the target user's historical interaction information is relatively scarce (for example, there is only a small amount of target user viewing data for the historically recommended video collection), the first feature of the candidate video determined based on this may not accurately indicate the target user's viewing probability of the recommended video collection. By determining the confidence of the first feature based on the target user's corresponding historical interaction information, it is possible to avoid inaccurate first feature prediction results affecting the recommendation results, thereby improving the accuracy of video recommendations.

[0064] According to some embodiments, the historical interaction information includes at least one of the following: historical viewing volume; historical feedback frequency; and the number of historical recommended videos recommended to the target user. Thus, when the historical interaction information includes explicit viewing volume (e.g., the target user's historical viewing volume for the video collection to which the historical recommended video belongs), feedback volume (e.g., the target user's historical feedback frequency for the video collection to which the historical recommended video belongs), and recommendation volume, the confidence level of the first feature can be determined based on the quantitative information.

[0065] In some examples, the historical interaction information of the target user includes the number of historical recommended videos recommended to the target user (historical distribution volume) and the target user's satisfaction rate of playing the historical recommended videos. In this case, the first feature weight corresponding to the target user can be determined based on the following formula:

[0066] Ratio=a×[1+(xb) d ] c×y

[0067] Where Ratio is the first feature weight, x is the target user's satisfaction rate for historically recommended videos, y is the historical distribution volume for the target user, and a, b, c, and d are constants.

[0068] Figure 3 FIG. 3 shows a schematic diagram of the structure of the first prediction model 300 according to an exemplary embodiment of the present disclosure. Figure 3As shown, the first prediction model 300 includes feature encoding layers 311, 312, and 313, which are used to encode user-side historical operation features, video features, and recommendation requests, respectively. In this example, the recommendation request can be a video search request input by the user or a recommendation request transmitted by the recommendation service platform. After the input features are encoded by the feature encoding layer, the user-side information and video-side information are processed by expert networks 321 and 322, respectively, and further processed by fully connected layers 331 and 322.

[0069] In this example, the first features of a candidate video include: the probability that the target user has watched other videos in the video collection to which the candidate video belongs, the predicted number of other videos in the video collection to which the candidate video belongs that the target user has watched, and the predicted duration of time the target user has spent watching other videos in the video collection to which the candidate video belongs. Figure 3 As shown, the first prediction model 300 can apply the viewing rate prediction network 341, the step length prediction network 342 and the duration prediction network 343 to obtain three sets of prediction results respectively, and the predicted viewing rate can be multiplied by the output results of the step length prediction network 342 and the duration prediction network 343 respectively to obtain the final predicted compensation and predicted duration.

[0070] As described above, the sample data used to train the model can be constructed based on the user's real historical behavior data, and the historical operation features can also include the user's real historical interaction information. In actual application scenarios, since the video platform may conduct exploratory distribution to users (that is, the recommended content is not determined by the calculation of the recommendation system), it will cause the user's consumption data of the recommended content (such as viewing rate, like rate, feedback frequency, attention and other business indicators) to be negatively pulled down. In order to eliminate the interaction data offset caused by exploratory distribution, the user interaction data corresponding to the exploratory distribution behavior can be given a low weight to improve the accuracy of the model prediction results, thereby improving the recommendation accuracy.

[0071] In some examples, the video features input into the model include real user interaction data for the video, such as video playback volume and video popularity. When a candidate video has a cold start phenomenon, the video features of the cold start video can also be determined based on the interaction data of other candidate videos in the same video collection to avoid the cold start phenomenon affecting the accuracy of the model prediction, thereby improving the recommendation accuracy.

[0072] According to one aspect of the present disclosure, a video recommendation device is also provided. Figure 4 FIG. 4 shows a structural block diagram of a video recommendation apparatus 400 according to an exemplary embodiment of the present disclosure. Figure 4 As shown, the apparatus 400 includes:

[0073] A first determining unit 401 is configured to determine at least two candidate videos from a video library, wherein the video library includes at least two video collections, and each video collection includes at least two videos;

[0074] The second determining unit 402 is configured to obtain a first feature of the candidate video based on the historical operation feature of the target user, wherein the first feature includes a probability that the target user has watched other videos in the video collection to which the corresponding candidate video belongs;

[0075] A second determining unit 403 is configured to determine a video to be recommended from the candidate videos based on the first feature; and

[0076] The recommendation unit 404 is configured to recommend the video to be recommended and the video collection to be recommended to which the video to be recommended belongs to to the target user.

[0077] According to some embodiments, the second determination unit 402 is configured to: determine the first feature for each candidate video based on the historical operation feature and the second feature of at least two videos included in the video collection to which the candidate video belongs, wherein the second feature includes at least one of the following items: the probability of the target user watching the corresponding video, the historical playback information of the corresponding video, and the historical feedback information of the corresponding video.

[0078] According to some embodiments, the second determination unit 402 is configured to: for each candidate video, input the historical operation feature and the corresponding second feature into a first prediction model to obtain the first feature output by the first prediction model, wherein the first prediction model is trained using sample data labeled with a reference to the first feature.

[0079] According to some embodiments, the second feature includes the probability of the target user watching the corresponding video; the device 400 also includes: a fourth determination unit, configured to input the historical operation feature and the video feature of the video into a second prediction model to obtain the probability of the target user watching the video output by the second prediction model, wherein the second prediction model is trained using sample data marked with reference probabilities.

[0080] According to some embodiments, the third determination unit 403 is configured to: determine the video to be recommended from the candidate videos based on the first feature and the third feature of the candidate video, wherein the third feature includes the probability of the target user watching the corresponding candidate video.

[0081] According to some embodiments, the historical operation feature includes historical interaction information of the target user for the video collection to which the historical recommended video belongs; the third determination unit 403 is configured to: determine the video to be recommended based on the product of the first feature and the first feature weight of the target user, and the third feature, wherein the first feature weight of the target user is determined based on the historical interaction information.

[0082] According to some embodiments, the historical interaction information includes at least one of the following: historical viewing volume; historical feedback frequency; and the number of historical recommended videos recommended to the target user.

[0083] According to some embodiments, the first feature of each candidate video includes: the predicted number or predicted duration of viewing by the target user of other videos in the video collection to which the candidate video belongs.

[0084] It should be understood that Figure 4 The operations of the various units of the video recommendation apparatus 400 shown in FIG. 4 can be compared with Figure 2 The steps in the video recommendation method 200 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 200 are also applicable to the apparatus 400 and the various units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0085] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0086] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned video recommendation method.

[0087] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned video recommendation method.

[0088] According to another aspect of the present disclosure, a computer program product is further provided, including a computer program, wherein the computer program implements the above-mentioned video recommendation method when executed by a processor.

[0089] refer to Figure 5, a block diagram of an electronic device 500 that can serve as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0090] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 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.

[0091] Multiple components within device 500 are connected to I / O interface 505, including an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. Input unit 506 can be any device capable of inputting information into device 500. Input unit 506 can receive input numeric or character information and generate key signal input related to user settings and / or function control of the electronic device. It can include, but is not limited to, a mouse, keyboard, touch screen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 507 can be any device capable of presenting information and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 508 can include, but is not limited to, a magnetic disk or an optical disk. Communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks. It can include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0092] The computing unit 501 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the video recommendation method. For example, in some embodiments, the video recommendation method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the video recommendation method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the video recommendation method by any other appropriate means (e.g., by means of firmware).

[0093] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0094] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0095] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can 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.

[0096] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0097] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by 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), the Internet, and a blockchain network.

[0098] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0099] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0100] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but is only limited by the claims after authorization and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. In addition, the steps may be performed in an order different from that described in this disclosure. Further, the various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after this disclosure.

Claims

1. A video recommendation method, comprising: Determine at least two candidate videos from a video library, wherein the video library includes at least two video collections, and each of the video collections includes at least two videos; Based on the historical operation characteristics of the target user, obtaining a first characteristic of the candidate video, wherein the first characteristic includes a probability that the target user watches other videos in the video collection to which the corresponding candidate video belongs; Based on the first feature, determining a video to be recommended from the candidate videos; and The video to be recommended and the collection of videos to be recommended to which the video to be recommended belongs are recommended to the target user.

2. The method of claim 1, wherein: The acquiring the first feature of the candidate video based on the historical operation feature of the target user includes: For each of the candidate videos, the first feature is determined based on the historical operation feature and the second feature of at least two videos included in the video collection to which the candidate video belongs, wherein the second feature includes at least one of the following items: the probability of the target user watching the corresponding video, the historical playback information of the corresponding video, and the historical feedback information of the corresponding video.

3. The method of claim 2, wherein: The determining, for each of the candidate videos, based on the historical operation feature and the second features of at least two videos included in the video collection to which the candidate video belongs, of the first feature comprises: For each candidate video, the historical operation feature and the corresponding second feature are input into a first prediction model to obtain the first feature output by the first prediction model, wherein the first prediction model is trained using sample data annotated with reference to the first feature.

4. The method of claim 3, wherein: The second feature includes a probability that the target user watches the corresponding video; The method further comprises: The historical operation features and the video features of the corresponding video are input into a second prediction model to obtain the probability of the target user watching the corresponding video output by the second prediction model, wherein the second prediction model is trained using sample data labeled with reference probabilities.

5. The method according to any one of claims 1 to 4, wherein: The determining of the video to be recommended from the candidate videos based on the first feature includes: Based on the first feature and the third feature of the candidate video, the video to be recommended is determined from the candidate videos, wherein the third feature includes the probability that the target user watches the corresponding candidate video.

6. The method of claim 5, wherein: The historical operation feature includes the historical interaction information of the target user with respect to the video collection to which the historical recommended video belongs; The determining the video to be recommended from the candidate videos based on the first feature and the third feature of the candidate videos comprises: The video to be recommended is determined based on the product of the first feature and the first feature weight of the target user, and the third feature, wherein the first feature weight of the target user is determined based on the historical interaction information.

7. The method of claim 6, wherein: The historical interaction information includes at least one of the following: Historical views; Historical feedback frequency; and The number of historical recommended videos recommended to the target user.

8. The method according to any one of claims 1 to 7, wherein: The first feature includes: The predicted number or predicted duration of viewing of other videos in the video collection to which the corresponding candidate video belongs by the target user.

9. A video recommendation device, comprising: A first determining unit is configured to determine at least two candidate videos from a video library, wherein the video library includes at least two video collections, and each of the video collections includes at least two videos; A second determining unit is configured to obtain a first feature of the candidate video based on a historical operation feature of the target user, wherein the first feature includes a probability that the target user watches other videos in the video collection to which the corresponding candidate video belongs; A third determining unit is configured to determine a video to be recommended from the candidate videos based on the first feature; and The recommendation unit is configured to recommend the video to be recommended and the collection of videos to be recommended to which the video to be recommended belongs to to the target user.

10. The device of claim 9, wherein: The second determining unit is configured to: For each of the candidate videos, the first feature is determined based on the historical operation feature and the second feature of at least two videos included in the video collection to which the candidate video belongs, wherein the second feature includes at least one of the following items: the probability of the target user watching the corresponding video, the historical playback information of the corresponding video, and the historical feedback information of the corresponding video.

11. The device of claim 10, wherein: The second determining unit is configured to: For each candidate video, the historical operation feature and the corresponding second feature are input into a first prediction model to obtain the first feature output by the first prediction model, wherein the first prediction model is trained using sample data annotated with reference to the first feature.

12. The device of claim 11, wherein: The second feature includes a probability that the target user watches the corresponding video; The device also includes: The fourth determination unit is configured to input the historical operation features and the video features of the video into a second prediction model to obtain the probability of the target user watching the video output by the second prediction model, wherein the second prediction model is trained using sample data labeled with reference probabilities.

13. The device according to any one of claims 9 to 12, wherein: The third determining unit is configured to: Based on the first feature and the third feature of the candidate video, the video to be recommended is determined from the candidate videos, wherein the third feature includes the probability that the target user watches the corresponding candidate video.

14. The device of claim 13, wherein: The historical operation feature includes the historical interaction information of the target user with respect to the video collection to which the historical recommended video belongs; The third determining unit is configured to: The video to be recommended is determined based on the product of the first feature and the first feature weight of the target user, and the third feature, wherein the first feature weight of the target user is determined based on the historical interaction information.

15. The device of claim 14, wherein: The historical interaction information includes at least one of the following: Historical views; Historical feedback frequency; and The number of historical recommended videos recommended to the target user.

16. The device according to any one of claims 9 to 15, wherein: The first feature includes: The predicted number or predicted duration of viewing of other videos in the video collection to which the corresponding candidate video belongs by the target user.

17. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1-8.

19. A computer program product comprising a computer program, wherein: The computer program implements the method according to any one of claims 1 to 8 when executed by a processor.

Images