Video recommendation method and device, electronic equipment and medium

Abstract

The invention provides a video recommendation method and device, electronic equipment and a medium, and relates to the technical field of computers, in particular to the technical field of data processing. According to the implementation scheme, the method comprises the steps that duration preference characteristics of a user are obtained, and the duration preference characteristics indicate a video duration range in which the user is interested; recent interest features and long-term interest features of the user are obtained, the recent interest features indicate video content interested by the user in a first time period, and the long-term interest features indicate video content interested by the user in a second time period; the starting time of the second time period is earlier than the starting time of the first time period; and determining at least one target video recommended to the user by using a video recommendation model according to the duration preference feature, the recent interest feature and the long-term interest feature.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and more particularly to the field of data processing technologies. Specifically, the present disclosure relates to a video recommendation method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] The processing process of a video recommendation system can be regarded as a funnel process, and its link includes: (1) a recall stage, where a large number of videos to be recommended are recalled from a video database; (2) a rough ranking stage, where a relatively small machine learning model is used to score each of the recalled videos to be recommended one by one, so as to retain a certain number of videos to be recommended according to the score for entering the fine ranking stage; and (3) a fine ranking stage, where a relatively large neural network model is used to score each of the videos to be recommended retained in the rough ranking stage one by one, so as to reflect the degree of interest of the user in each video to be recommended through the fine ranking score and determine the final recommended videos.

[0003] However, video recommendation systems often have the problem of historical interest forgetting, that is, video recommendation systems tend to recommend similar videos according to the user's recent interests, resulting in the user gradually falling into an information cocoon during use. Currently, video recommendations can be made by combining the user's recent interests and long-term interests in the video recommendation system at the same time to help the user break out of the information cocoon.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or adopted. Unless otherwise specified, any method described in this section should not be considered to be prior art merely because it is included in this section. Similarly, unless otherwise specified, the problems mentioned in this section should not be considered to have been recognized in any prior art. Summary of the Invention

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

[0006] According to one aspect of the present disclosure, there is provided a video recommendation method, including: obtaining a duration preference feature of a user, where the duration preference feature indicates a range of video durations that the user is interested in; obtaining a recent interest feature and a long-term interest feature of the user, where the recent interest feature indicates video content that the user is interested in within a first time period, and the long-term interest feature indicates video content that the user is interested in within a second time period, and a starting time of the second time period is earlier than a starting time of the first time period; and determining at least one target video recommended for the user using a video recommendation model according to the duration preference feature, the recent interest feature, and the long-term interest feature.

[0007] According to another aspect of the present disclosure, there is provided a video recommendation device, including: a first module configured to obtain the duration preference feature of a user, where the duration preference feature indicates the range of video durations that the user is interested in; a second module configured to obtain the recent interest feature and the long-term interest feature of the user, where the recent interest feature indicates the video content that the user is interested in within a first time period, and the long-term interest feature indicates the video content that the user is interested in within a second time period, and the start time of the second time period is earlier than the start time of the first time period; and a third module configured to use a video recommendation model to determine at least one target video recommended for the user according to the duration preference feature, the recent interest feature, and the long-term interest feature.

[0008] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; where 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 execute the above method.

[0009] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause the computer to execute the above method.

[0010] According to another aspect of the present disclosure, there is provided a computer program product including a computer program, where the computer program implements the above method when executed by a processor.

[0011] According to one or more embodiments of the present disclosure, there is provided a video recommendation method. By simultaneously introducing the user's recent interest feature, long-term interest feature, and duration preference feature of watching videos during the video recommendation process, it is possible to increase the possibility of recommending associated videos that are not the user's recent interests to break the information cocoon, and at the same time effectively combine the user's video viewing habits, avoiding the situation where the user is interested in the video content of a certain video but gives negative feedback because the video duration does not meet their viewing habits. Thus, it is possible to more accurately determine the user's preferences and help the user better break the information cocoon.

[0012] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings exemplarily illustrate embodiments and form part of the specification, and are used together with the written description of the specification to explain the exemplary implementation manners of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0014] Figure 1 is a schematic diagram showing an example system in which various methods described herein can be implemented according to an exemplary embodiment;

[0015] Figure 2 shows a flowchart of a video recommendation method according to an embodiment of the present disclosure;

[0016] Figure 3 shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure;

[0017] Figure 4 shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure;

[0018] Figure 5 shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure;

[0019] Figure 6 shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure;

[0020] Figure 7 shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure;

[0021] Figure 8 shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure;

[0022] Figure 9 shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure;

[0023] Figure 10 shows a block diagram of the structure of a video recommendation apparatus according to an embodiment of the present disclosure; and

[0024] Figure 11 shows a block diagram of the structure of an exemplary electronic device that can be used to implement the embodiments of the present disclosure. Detailed Description

[0025] The exemplary embodiments of the present disclosure will be described below in conjunction with the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist in understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.

[0026] In the present disclosure, unless otherwise specified, the terms "first", "second", etc. are used to describe various elements and are not intended to limit the positional relationship, timing 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, and in certain cases, based on the context description, they may also refer to different instances.

[0027] The terms used in the description of various examples in the present disclosure are only for the purpose of describing specific examples and are not intended to be restrictive. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in the present disclosure covers any one of the listed items and all possible combinations.

[0028] Video recommendation systems often have the problem of forgetting historical interests. That is, video recommendation systems tend to recommend similar videos based on users' recent interests, resulting in users gradually falling into an information cocoon during the use process. In the related art, video recommendations can be made by combining users' recent interests and long-term interests in the video recommendation system to help users break out of the information cocoon.

[0029] However, the related art only starts from the perspective of users' entity interests and does not consider users' viewing duration habits. It is easy to occur that when recommending videos related to long-term interests to users, although users are interested in the content of the videos, they skip them because the video duration is too long and they don't have time to watch, or they give negative feedback because the video duration is too short and there is too little effective information.

[0030] Since viewing duration and user feedback are important indicators for the video recommendation system to judge user preferences, such negative feedback will also have a negative impact on the corresponding entity interests (long-term interests) associated with the current video, resulting in the video recommendation model possibly reducing the relevant pushes of such entity interests and affecting the effect of breaking out of the information cocoon.

[0031] To solve the above problems, the present disclosure provides a video recommendation method. By simultaneously introducing the user's recent interest features, long-term interest features, and video duration preference features during the video recommendation process, it is possible to increase the likelihood of recommending associated videos that are not of the user's recent interests to break the information cocoon, while effectively combining the user's video viewing habits, and avoiding the situation where the user is interested in the video content of a certain video but gives negative feedback because the video duration does not match their viewing habits. Thus, it is possible to more accurately determine the user's preferences and help the user better break the information cocoon.

[0032] Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0033] Figure 1 FIG. shows a schematic diagram of an exemplary system 100 in which the various methods and apparatuses described herein can be implemented according to an embodiment of the present disclosure. Referring to 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 that couple 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.

[0034] In an embodiment of the present disclosure, the server 120 can run one or more services or software applications that enable the execution of the video recommendation method.

[0035] In certain embodiments, the server 120 can also provide other services or software applications that can include non-virtual environments and virtual environments. In certain embodiments, these services can be provided as web-based services or cloud services, for example, provided to users of the client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0036] In Figure 1 the configuration shown, the server 120 can include one or more components that implement the functions performed by the server 120. These components can include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating the client devices 101, 102, 103, 104, 105, and / or 106 can in turn use one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that various different system configurations are possible, which can be different from the system 100. Therefore, Figure 1 is an example of a system for implementing the methods described herein and is not intended to be limiting.

[0037] Users may use client devices 101, 102, 103, 104, 105, and / or 106 to perform the video recommendation method. The client devices may provide an interface that enables a user of the client device to interact with the client device. The client devices may also output information to the user via the interface. Although Figure 1 only six client devices are depicted, those skilled in the art will be able to understand that the present disclosure may support any number of client devices.

[0038] 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 laptop computers), 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 WindowsMobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smartphones, tablets, 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 devices are capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0039] Network 110 may be any type of network known to those skilled in the art, which may support data communication using any one of a variety of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.). By way of example only, one or more networks 110 may be a local area network (LAN), an Ethernet-based network, token ring, wide area network (WAN), the Internet, virtual network, virtual private network (VPN), intranet, extranet, public switched telephone network (PSTN), infrared network, wireless network (such as Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0040] Server 120 may include one or more general-purpose computers, dedicated server computers (such as PC (Personal Computer) servers, UNIX servers, midrange servers), blade servers, mainframes, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (such as one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices of the server). In various embodiments, server 120 may run one or more services or software applications that provide the functions described below.

[0041] The computing units in server 120 may run one or more operating systems including any of the above operating systems as well as any commercially available server operating systems. Server 120 may also run any one of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0042] In some embodiments, server 120 may include one or more applications to analyze and merge 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 data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0043] In some embodiments, server 120 may be a server of a distributed system, or a server combined with a blockchain. Server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system, which solves the defects of difficult management and weak business scalability existing in traditional physical hosts and virtual private server (VPS, Virtual Private Server) services.

[0044] System 100 may also include one or more databases 130. In certain embodiments, these databases can be used to store data and other information. For example, one or more of the databases 130 can be used to store information such as audio files and video files. The databases 130 can reside in various locations. For example, the database used by the server 120 can be local to the server 120, or can be remote from the server 120 and can communicate with the server 120 via a network-based or dedicated connection. The databases 130 can be of different types. In certain embodiments, the database used by the server 120 can be, for example, a relational database. One or more of these databases can store, update, and retrieve data to and from the database in response to commands.

[0045] In certain embodiments, one or more of the databases 130 can also be used by an application to store application data. The database used by the application can be a different type of database, such as a key-value store, an object store, or a conventional store supported by a file system.

[0046] Figure 1 The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatuses described according to the present disclosure.

[0047] Figure 2 A flowchart of a video recommendation method according to an embodiment of the present disclosure is shown.

[0048] As Figure 2 shown, the video recommendation method 200 includes:

[0049] Step 210, obtaining the duration preference feature of the user, where the duration preference feature indicates the range of video durations that the user is interested in;

[0050] Step 220, obtaining the recent interest feature and the long-term interest feature of the user, where the recent interest feature indicates the video content that the user is interested in within a first time period, and the long-term interest feature indicates the video content that the user is interested in within a second time period, and the start time of the second time period is earlier than the start time of the first time period; and

[0051] Step 230, using a video recommendation model to determine at least one target video recommended for the user according to the duration preference feature, the recent interest feature, and the long-term interest feature.

[0052] Based on this, by simultaneously introducing the user's recent interest features, long-term interest features, and video duration preference features during the video recommendation process, it is possible to increase the likelihood of recommending associated videos that are not the user's recent interests to break the information cocoon, while effectively combining the user's video viewing habits, and avoiding the situation where the user is interested in the video content of a certain video but gives negative feedback because the video duration does not match their viewing habits. Thus, it is possible to more accurately determine the user's preferences and help the user better break the information cocoon.

[0053] In step 210, the video duration is usually closely related to the amount of information in the video. Generally, the longer the video duration, the greater the amount of information it contains. Exemplarily, for users with a fast-paced life, they may be more inclined to videos with relatively short durations to quickly obtain the information they need; while for users with a slow-paced life, they are more inclined to videos with relatively long durations to obtain sufficient detailed information.

[0054] In the example, videos can be classified according to their durations. For example, videos with a duration within 1 minute can be regarded as micro-videos, videos with a duration between 1 minute and 3 minutes can be regarded as medium-length videos, and videos with a duration over 3 minutes can be regarded as extra-long videos. It can be understood that the above classification is only for illustrative purposes and is not limited thereto.

[0055] In the example, for some videos with opening and closing credits such as TV series, since the effective information content of their opening and closing credits is relatively low, when determining their video durations, their opening and closing credits can be skipped, and the duration of the effective content in the middle can be used as the video duration to more accurately determine the user's duration preference features.

[0056] Figure 3 Shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure.

[0057] According to some embodiments, as Figure 3 shown, step 210 includes:

[0058] Step 310, obtaining a plurality of first historical videos watched by the user; and

[0059] Step 320, determining the duration preference feature according to the video duration of each first historical video among the plurality of first historical videos.

[0060] Thus, based on the user's historical video viewing records, the video duration that the user overall prefers can be determined, thereby determining their preferences.

[0061] Figure 4 Shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure.

[0062] According to some embodiments, the duration preference feature further indicates the range of video durations that the user is interested in at the current moment, such as Figure 4 As shown, step 320 includes:

[0063] Step 410, according to the time points when the user watches each first historical video, screen out at least one second historical video from the multiple first historical videos, wherein the time points when the user watches each second historical video in the at least one second historical video fall within a target time period of the day that includes the current moment; and

[0064] Step 420, determine the duration preference feature according to the video duration of each second historical video.

[0065] The user's duration preference feature is not static. At different moments of the day, the user is likely to prefer videos of different durations. For example, during the free time after work, the user may prefer videos with longer durations; while during the fragmented time on the commute, the user may prefer videos with shorter durations. Based on this, the user's activity pattern during the day can be further predicted according to the user's historical viewing records, so as to better recommend videos of corresponding durations to the user at the current moment.

[0066] Exemplarily, the duration preference feature of the user at the current moment can also be determined based on the user's geographical location and network environment, etc. For example, whether the user is at home may affect the user's preference for video duration, or whether the user uses wireless network or mobile data may also affect the user's preference for video duration.

[0067] In step 220, the first time period may partially or entirely fall within the second time period, or the first time period may not overlap with the second time period, for example.

[0068] Exemplarily, the user's long-term interest feature can, for example, indicate the video content that the user has been interested in in the past 3 years, while the user's short-term interest feature can, for example, indicate the video content that the user has been interested in in the past 3 months. Exemplarily, the user's long-term interest feature can, for example, indicate the video content that the user has been interested in from January to March this year, while the user's short-term interest feature can, for example, indicate the video content that the user has been interested in from April to June this year.

[0069] In step 230, according to some embodiments, each target video in the at least one target video is associated with the duration preference feature and the long-term interest feature, and each target video is not associated with the short-term interest feature. Thus, it is possible to effectively screen out videos that are not associated with the user's short-term interests for recommendation, thereby breaking the user's information cocoon.

[0070] It can be understood that when recommending to the user, in addition to the above at least one target video, videos associated with the user's short-term interests will also be recommended accordingly.

[0071] Figure 5 Shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure.

[0072] According to some embodiments, the video recommendation model includes a recall model and a ranking model. As Figure 5 shown, step 230 includes:

[0073] Step 510, according to the duration preference feature, recent interest feature, and long-term interest feature, use the recall model to recall and score and rank multiple recalled videos to generate a recall ranking result;

[0074] Step 520, according to the duration preference feature, recent interest feature, and long-term interest feature, use the ranking model to process the recall ranking result to obtain a target ranking result; and

[0075] Step 530, determine at least one target video according to the target ranking result.

[0076] For the funnel-shaped video recommendation model, by introducing the duration preference feature, recent interest feature, and long-term interest feature simultaneously at each stage of the video recommendation model link, the consistency of the underlying link (recall model) and the upper-layer link (ranking model) of the video recommendation model is ensured, maximizing the video recommendation effect and improving the user experience.

[0077] Figure 6 Shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure.

[0078] According to some embodiments, as Figure 6 shown, step 510 includes:

[0079] Step 610, set a first recall channel for the recall model according to the recent interest feature;

[0080] Step 620, set a second recall channel for the recall model according to the long-term interest feature; and

[0081] Step 630, perform recall ranking on the first recall channel and the second recall channel based on the duration preference feature to obtain a recall ranking result.

[0082] By separately adding recall channels with different interest dimensions to the network structure of the basic recall model and recalling videos that meet the user's duration preference for each interest dimension channel, the recall ranking result can be made more in line with the user's preferences.

[0083] In an example, the rough ranking model in the subsequent ranking model can be introduced into the recall model to achieve self-ranking of the recall model, and a certain number of videos ranked at the top in the self-ranking are intercepted and passed to the ranking model in the subsequent link, thereby further improving the link consistency of the video recommendation model.

[0084] Figure 7 FIG. shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure.

[0085] According to some embodiments, the ranking model includes a rough ranking model and a fine ranking model. As Figure 7 shown, step 520 includes:

[0086] Step 710, according to the duration preference feature, recent interest feature, and long-term interest feature, use the rough ranking model to process the recall ranking result to screen out the first number of recalled videos associated with the duration preference feature and recent interest feature, and the second number of recalled videos associated with the duration preference feature and long-term interest feature, where the second number is an integer greater than zero; and

[0087] Step 720, use the fine ranking model to score and rank the recalled videos in the fine ranking candidate queue to obtain the target ranking result.

[0088] Exemplarily, the rough ranking model combines the duration preference feature, sets corresponding feature buckets for the long-term interest dimension and recent interest dimension respectively for rough ranking scoring, and ensures that a certain number of videos in the long-term interest feature bucket enter the subsequent fine ranking stage to effectively avoid videos related to the long-term interest feature being excluded in the rough ranking stage and ultimately unable to enter the video list recommended to the user.

[0089] Figure 8 FIG. shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure.

[0090] According to some embodiments, as Figure 8 shown, the second number in step 710 is determined by the following operations:

[0091] Step 810, obtain the historical data set of the user, where the first data set includes a plurality of historical data pairs, and each historical data pair in the plurality of historical data pairs includes the first data indicating the video content and video duration of the third historical video watched by the user, and each historical data pair further includes the second data indicating the viewing satisfaction of the user for the corresponding third historical video; and

[0092] Step 820, use the deep learning model to process the historical data set to determine the second number.

[0093] Thus, based on the user's historical consumption satisfaction, the video content and video duration preferred by the user can be determined to determine the number of videos entering the refined ranking within the corresponding bucket interval segments of each long-term interest type, thereby ensuring that the duration of the long-term interest-related videos recommended to the user subsequently conforms to the user's viewing habits.

[0094] Exemplarily, different priorities can also be set for different long-term interest types to increase their weights and improve their final rankings in the sorting results.

[0095] Figure 9 Shows a partial flowchart of another video recommendation method according to an embodiment of the present disclosure.

[0096] According to some embodiments, as Figure 9 shown, in addition to the above steps 210 to 230, method 200 further includes:

[0097] Step 910, obtaining the potential interest features of the user, where the potential interest features indicate the video content that sample users with a feature similarity greater than the similarity threshold to the user are interested in; and

[0098] Step 920, using a video recommendation model to determine at least one target video recommended for the user according to the potential interest features, duration preference features, recent interest features, and long-term interest features.

[0099] Potential interest is an interest type that the user has not given feedback on liking or disliking in the past but similar users like. Thus, by further introducing the user's potential interest, it can better help the user break the information cocoon.

[0100] In step 910, the feature similarity can, for example, indicate the feature similarities such as age, occupation, and region between the user and the sample user. Exemplarily, the feature similarity can also, for example, indicate that the user and the sample user have a common topic of interest.

[0101] Exemplarily, in addition to the above potential interest features, the user's long-tail interest features can also be further introduced during video recommendation to help the user break the information cocoon. Specifically, the long-tail interest features indicate the video content that the user is interested in, but this type of video content is relatively niche, and the base number of such videos in the database is small, so the probability of their being recalled by the video recommendation model is also small.

[0102] Exemplarily, the user's real-time feedback can be returned to the video recommendation model so that the video recommendation model can determine the interest types that need to be phased out and more accurately determine the user's preferences. For example, in response to the number of times the user gives negative feedback on "economics" videos exceeding the target threshold, the "economics" videos are used as the phased-out interest types, and videos of the corresponding type are no longer recalled, so as to reduce the processing difficulty of the video recommendation model and improve the processing efficiency.

[0103] According to another aspect of the present disclosure, a video recommendation device is provided. As Figure 10 shown, the video recommendation device 1000 includes: a first module 1010 configured to obtain the duration preference feature of a user, where the duration preference feature indicates the range of video durations that the user is interested in; a second module 1020 configured to obtain the recent interest feature and the long-term interest feature of the user, where the recent interest feature indicates the video content that the user is interested in within a first time period, and the long-term interest feature indicates the video content that the user is interested in within a second time period, and the start time of the second time period is earlier than the start time of the first time period; and a third module 1030 configured to use a video recommendation model to determine at least one target video recommended for the user according to the duration preference feature, the recent interest feature, and the long-term interest feature.

[0104] According to another aspect of the present disclosure, an electronic device is further provided, including: 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 execute the foregoing method.

[0105] 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 cause the computer to execute the foregoing method.

[0106] 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 foregoing method when executed by a processor.

[0107] As Figure 11 shown, the electronic device 1100 includes a computing unit 1101, which can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 1102 or the computer program loaded from the storage unit 1108 into the random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the electronic device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other through a bus 1104. The input / output (I / O) interface 1105 is also connected to the bus 1104.

[0108] Multiple components in the electronic device 1100 are connected to the I / O interface 1105, including: an input unit 1106, an output unit 1107, a storage unit 1108, and a communication unit 1109. The input unit 1106 can be any type of device capable of inputting information into the electronic device 1100. The input unit 1106 can receive input digital or character information, and generate key signal inputs related to the user settings and / or function controls of the electronic device, and can include but are not limited to a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone, and / or a remote control. The output unit 1107 can be any type of device capable of presenting information, and can include but are not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1108 can include but are not limited to a magnetic disk and an optical disk. The communication unit 1109 allows the electronic device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but are not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth TM device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0109] The computing unit 1101 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 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 running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 executes the various methods and processes described above, such as the GPU-based matrix calculation method. For example, in some embodiments, the GPU-based matrix calculation method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 1108. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the GPU-based matrix calculation method described above can be executed. Alternatively, in other embodiments, the computing unit 1101 can be configured to execute the GPU-based matrix calculation method in any other suitable manner (e.g., by means of firmware).

[0110] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems-on-a-chip (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 interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0111] The program code for implementing the methods 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, special purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0112] 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 connection with an instruction execution system, apparatus, or device. 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, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] To provide for 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for interaction with the user; for example, 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, speech input, or tactile input).

[0114] 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 having a graphical user interface or a web browser through which the user can interact with an implementation 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), and the Internet.

[0115] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of the client and the server is generated by computer programs that run on the respective computers and have a client-server relationship with each other. The server can be a cloud server, can also be a server of a distributed system, or a server that incorporates a blockchain.

[0116] It should be understood that various forms of the flows shown above can be used, steps can be reordered, added, or deleted. For example, the steps recited in this disclosure can be executed 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, and this is not limited herein.

[0117] Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above 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 defined by the authorized claims and their equivalent scope. Various elements in the embodiments or examples may be omitted or replaced by their equivalent elements. In addition, the steps may be executed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples may be combined in various ways. Importantly, with the evolution of technology, many of the elements described herein may be replaced by equivalent elements that emerge after the present disclosure.

Claims

1. A video recommendation method, comprising: Acquire a duration preference feature of a user, wherein the duration preference feature indicates a duration range of videos that the user is interested in; Acquire a recent interest feature and a long-term interest feature of the user, wherein the recent interest feature indicates video content that the user is interested in within a first time period, and the long-term interest feature indicates video content that the user is interested in within a second time period, and a start time of the second time period is earlier than a start time of the first time period; and At least one target video recommended for the user is determined using a video recommendation model according to the duration preference feature, the recent interest feature, and the long-term interest feature.

2. The method according to claim 1, wherein: The obtaining of the user's duration preference characteristics includes: Acquire a plurality of first historical videos watched by the user; and The duration preference feature is determined according to the video duration of each first historical video in the plurality of first historical videos.

3. The method according to claim 2, wherein: The duration preference feature further indicates a video duration range that the user is interested in at the current moment, and wherein determining the duration preference feature according to the video duration of each first historical video in the at least one first video comprises: Filtering at least one second historical video from the plurality of first historical videos according to a time point when the user watches each of the first historical videos, wherein the time point when the user watches each of the at least one second historical video falls within a target time period of a day that includes the current moment; and The duration preference feature is determined according to the video duration of each second historical video.

4. The method according to any one of claims 1 to 3, wherein: The video recommendation model includes a recall model and a ranking model, and the step of determining at least one target video recommended to the user using the video recommendation model according to the duration preference feature, the recent interest feature, and the long-term interest feature includes: According to the duration preference feature, the recent interest feature, and the long-term interest feature, the recall model is used to recall multiple recall videos for scoring and ranking to generate a recall ranking result; According to the duration preference feature, the recent interest feature, and the long-term interest feature, using the sorting model to process the recall sorting result to obtain a target sorting result; and The at least one target video is determined according to the target sorting result.

5. The method according to claim 4, wherein: The step of recalling a plurality of recalled videos using the recall model for scoring and sorting based on the duration preference feature, the recent interest feature, and the long-term interest feature to generate a recall sorting result includes: Setting a first recall channel for the recall model according to the recent interest feature; Setting a second recall channel for the recall model according to the long-term interest feature; and The first recall channel and the second recall channel are recalled and sorted based on the duration preference feature to obtain the recall sorting result.

6. The method according to claim 4 or 5, wherein: The sorting model includes a rough sorting model and a fine sorting model. The sorting model is used to process the recall sorting result according to the duration preference feature, the recent interest feature and the long-term interest feature to obtain a target sorting result, including: According to the duration preference feature, the recent interest feature, and the long-term interest feature, the recall sorting result is processed using the coarse sorting model to screen out a first number of recalled videos associated with the duration preference feature and the recent interest feature, and a second number of recalled videos associated with the duration preference feature and the long-term interest feature, wherein the second number is an integer greater than zero; and The refined ranking model is used to score and sort the recalled videos in the refined ranking candidate queue to obtain the target ranking result.

7. The method according to claim 6, wherein: The second number is determined by: Acquire a historical data set of the user, wherein the first data set includes a plurality of historical data pairs, each of the plurality of historical data pairs includes first data indicating video content and video duration of a third historical video watched by the user, and each of the historical data pairs also includes second data indicating viewing satisfaction of the user with respect to the corresponding third historical video; and The historical data set is processed using a deep learning model to determine the second quantity.

8. The method according to any one of claims 1 to 7, further comprising: Acquire a potential interest feature of the user, wherein the potential interest feature indicates video content that is of interest to a sample user whose feature similarity to the user is greater than a similarity threshold; and At least one target video recommended for the user is determined using the video recommendation model according to the potential interest feature, the duration preference feature, the recent interest feature, and the long-term interest feature.

9. The method according to any one of claims 1 to 8, wherein: Each of the at least one target video is associated with the duration preference feature and the long-term interest feature, and each of the target videos is not associated with the short-term interest feature.

10. A video recommendation device, comprising: The first module is configured to obtain a duration preference feature of a user, wherein the duration preference feature indicates a duration range of videos that the user is interested in; a second module configured to obtain a recent interest feature and a long-term interest feature of the user, wherein the recent interest feature indicates video content that the user is interested in within a first time period, and the long-term interest feature indicates video content that the user is interested in within a second time period, and a start time of the second time period is earlier than a start time of the first time period; and The third module is configured to use a video recommendation model to determine at least one target video recommended for the user based on the duration preference feature, the recent interest feature, and the long-term interest feature.

11. 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 9.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

13. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images