Video recall method, device, equipment, computer readable medium and program product

Abstract

The embodiment of the invention discloses a video recall method, device and equipment, a computer readable medium and a program product. A specific embodiment of the method comprises the following steps: for each user in a user set, generating user dimension information of the user according to video browsing information corresponding to the user; for each video in the video set, executing the following steps: generating user behavior dimension information of the video according to a user behavior information set of the video corresponding to the user set and the generated user dimension information; generating video dimension information of the video according to the user behavior dimension information; and according to the video dimension information corresponding to each video in the video set, selecting a video meeting a preset recall condition from the video set as a recalled video, and obtaining each recalled video. The embodiment is related to video recall, and the quality of recalled videos is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a video recall method, apparatus, device, computer-readable medium, and program product. Background Art

[0002] High-trending video recall refers to using a recall algorithm to help find videos with high popularity. Currently, when recalling high-trending videos, the common method is to build a video recall index based on all user behaviors on the video, which is then used to recall the video.

[0003] However, when the above method is adopted, the following technical problems often occur: only user behavior is used to construct the recall index, and in fact there will be some worthless users and worthless behaviors among the users and behaviors (for example, a user has taken actions on too many videos, which means that this user basically does not select videos, and videos of any quality will be accepted and taken actions by this user, so the quality of the video cannot be judged from the user's behavior), resulting in poor accuracy of the recall index and poor quality of the recalled videos.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0005] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0006] Some embodiments of the present disclosure provide a video recall method, apparatus, device, computer-readable medium, and program product to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a video recall method, which includes: for each user in a user set, generating user dimension information of the user based on the video browsing information corresponding to the user; for each video in a video set, performing the following steps: generating user behavior dimension information of the video based on the user behavior information set corresponding to the video in the user set and the generated user dimension information; generating video dimension information of the video based on the user behavior dimension information; and selecting videos that meet preset recall conditions from the video set as recalled videos based on the video dimension information corresponding to each video in the video set, thereby obtaining each recalled video.

[0008] Optionally, the above-mentioned generating user dimension information of the above-mentioned user based on the video browsing information corresponding to the above-mentioned user includes: selecting video browsing behavior information that meets a preset browsing time condition from each video browsing behavior information included in the above-mentioned video browsing information, wherein each video browsing behavior information corresponds to a video, and each video browsing behavior information includes a browsing time; determining the number of each video corresponding to each selected video browsing behavior information as the number of valid videos; and generating the user dimension information of the above-mentioned user based on the above-mentioned number of valid videos.

[0009] Optionally, the above-mentioned user behavior information set corresponding to the above-mentioned video and the generated user dimension information according to the above-mentioned user set, generates the user behavior dimension information of the above-mentioned video, including: for each user behavior type in the preset user behavior type set, performing the following steps: for each user in the above-mentioned user set, performing the following steps: based on the user behavior information corresponding to the above-mentioned user in the above-mentioned user behavior information set, generating first behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video; based on the above-mentioned first behavior information and the user dimension information corresponding to the above-mentioned user, generating second behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video; determining the sum of the obtained respective second behavior information as the weighted behavior information corresponding to the above-mentioned user behavior type and the above-mentioned video; and determining the determined respective weighted behavior information as the user behavior dimension information corresponding to the above-mentioned video.

[0010] Optionally, the above-mentioned generating the first behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video based on the user behavior information corresponding to the above-mentioned user in the above-mentioned user behavior information set includes: determining whether the above-mentioned user behavior information meets the preset user behavior condition corresponding to the above-mentioned user behavior type; in response to determining that the above-mentioned user behavior information meets the above-mentioned preset user behavior condition, determining a first preset value as the first behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video; in response to determining that the above-mentioned user behavior information does not meet the above-mentioned preset user behavior condition, determining a second preset value as the first behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video, wherein the above-mentioned second preset value is smaller than the above-mentioned first preset value.

[0011] Optionally, the above-mentioned generation of video dimension information of the above-mentioned video based on the above-mentioned user behavior dimension information includes: generating first floating space information corresponding to the above-mentioned video based on the above-mentioned user behavior dimension information and the effective playback number of the above-mentioned video; generating adjusted user behavior dimension information based on the above-mentioned first floating space information and the above-mentioned user behavior dimension information; generating an effective playback time ratio based on the effective playback time and video time corresponding to the above-mentioned video; generating second floating space information corresponding to the above-mentioned video based on the above-mentioned effective playback time ratio and the above-mentioned effective playback number; generating an adjusted effective playback time ratio based on the above-mentioned effective playback time ratio and the above-mentioned second floating space information; generating video dimension information of the above-mentioned video based on the above-mentioned adjusted user behavior dimension information and the above-mentioned adjusted effective playback time ratio.

[0012] Optionally, the above-mentioned user behavior dimension information includes each weighted behavior information corresponding to a preset user behavior type set; and the above-mentioned generating the first floating space information corresponding to the above-mentioned video based on the above-mentioned user behavior dimension information and the effective playback number of the above-mentioned video includes: for each user behavior type in the preset user behavior type set, performing the following steps: based on the target user behavior type, normalizing the weighted behavior information of the above-mentioned user behavior type in the above-mentioned each weighted behavior information to obtain a normalized behavior dimension value; generating the first floating space value corresponding to the above-mentioned user behavior type and the above-mentioned video based on the above-mentioned normalized behavior dimension value and the above-mentioned effective playback number; and determining each generated first floating space value as the first floating space information corresponding to the above-mentioned video.

[0013] Optionally, the above-mentioned generating adjusted user behavior dimension information based on the above-mentioned first floating space information and the above-mentioned user behavior dimension information includes: for each user behavior type in the above-mentioned user behavior type set, performing the following steps: determining the first floating space value corresponding to the above-mentioned user behavior type and the above-mentioned video; determining the normalized behavior dimension value corresponding to the above-mentioned user behavior type and the above-mentioned video; generating an adjusted behavior dimension value corresponding to the above-mentioned user behavior type based on the above-mentioned first floating space value and the above-mentioned normalized behavior dimension value; and determining each generated adjusted behavior dimension value as the adjusted user behavior dimension information.

[0014] Optionally, the video dimension information of the video is generated based on the adjusted user behavior dimension information and the adjusted effective playback time ratio, including: weighting each adjusted behavior dimension value included in the adjusted user behavior dimension information and the adjusted effective playback time ratio to obtain the video dimension information corresponding to the video.

[0015] Optionally, the method further includes: matching recommended videos from the above-mentioned recalled videos according to user information of the target user to obtain a recommended video set; and pushing each recommended video in the above-mentioned recommended video set to a recommended video pool corresponding to the above-mentioned target user.

[0016] In a second aspect, some embodiments of the present disclosure provide a video recall device, which includes: a generation unit, configured to generate user dimension information of the user for each user in a user set based on video browsing information corresponding to the user; an execution unit, configured to perform the following steps for each video in a video set: generating user behavior dimension information of the video based on a user behavior information set corresponding to the video in the user set and each generated user dimension information; generating video dimension information of the video based on the user behavior dimension information; a selection unit, configured to select videos that meet preset recall conditions from the video set as recalled videos based on the video dimension information corresponding to each video in the video set, thereby obtaining each recalled video.

[0017] Optionally, the generation unit is further configured to: select video browsing behavior information that meets a preset browsing time condition from each video browsing behavior information included in the above-mentioned video browsing information, wherein each video browsing behavior information corresponds to a video, and each video browsing behavior information includes a browsing time; determine the number of each video corresponding to each selected video browsing behavior information as the number of valid videos; and generate user dimension information of the above-mentioned user based on the above-mentioned number of valid videos.

[0018] Optionally, the execution unit is further configured to: for each user behavior type in a preset user behavior type set, perform the following steps: for each user in the above user set, perform the following steps: based on the user behavior information corresponding to the above user in the above user behavior information set, generate first behavior information corresponding to the above user behavior type, the above user and the above video; based on the above first behavior information and the user dimension information corresponding to the above user, generate second behavior information corresponding to the above user behavior type, the above user and the above video; determine the sum of the obtained second behavior information as the weighted behavior information corresponding to the above user behavior type and the above video; determine the determined weighted behavior information as the user behavior dimension information corresponding to the above video.

[0019] Optionally, the execution unit is further configured to: determine whether the above-mentioned user behavior information satisfies the preset user behavior conditions corresponding to the above-mentioned user behavior type; in response to determining that the above-mentioned user behavior information satisfies the above-mentioned preset user behavior conditions, determine the first preset value as the first behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video; in response to determining that the above-mentioned user behavior information does not satisfy the above-mentioned preset user behavior conditions, determine the second preset value as the first behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video, wherein the above-mentioned second preset value is less than the above-mentioned first preset value.

[0020] Optionally, the execution unit is further configured to: generate first floating space information corresponding to the above-mentioned video based on the above-mentioned user behavior dimension information and the effective playback number of the above-mentioned video; generate adjusted user behavior dimension information based on the above-mentioned first floating space information and the above-mentioned user behavior dimension information; generate an effective playback time ratio based on the effective playback time and video time corresponding to the above-mentioned video; generate second floating space information corresponding to the above-mentioned video based on the above-mentioned effective playback time ratio and the above-mentioned effective playback number; generate an adjusted effective playback time ratio based on the above-mentioned effective playback time ratio and the above-mentioned second floating space information; generate video dimension information of the above-mentioned video based on the above-mentioned adjusted user behavior dimension information and the above-mentioned adjusted effective playback time ratio.

[0021] Optionally, the above-mentioned user behavior dimension information includes each weighted behavior information corresponding to a preset user behavior type set.

[0022] Optionally, the execution unit is further configured to: for each user behavior type in a preset user behavior type set, perform the following steps: based on the target user behavior type, normalize the weighted behavior information of the above-mentioned user behavior type in the above-mentioned weighted behavior information to obtain a normalized behavior dimension value; based on the above-mentioned normalized behavior dimension value and the above-mentioned effective playback number, generate a first floating space value corresponding to the above-mentioned user behavior type and the above-mentioned video; and determine the generated each first floating space value as the first floating space information corresponding to the above-mentioned video.

[0023] Optionally, the execution unit is further configured to: for each user behavior type in the above-mentioned user behavior type set, perform the following steps: determine a first floating space value corresponding to the above-mentioned user behavior type and the above-mentioned video; determine a normalized behavior dimension value corresponding to the above-mentioned user behavior type and the above-mentioned video; generate an adjusted behavior dimension value corresponding to the above-mentioned user behavior type based on the above-mentioned first floating space value and the above-mentioned normalized behavior dimension value; and determine each generated adjusted behavior dimension value as adjusted user behavior dimension information.

[0024] Optionally, the execution unit is further configured to: weight each adjusted behavior dimension value included in the above-mentioned adjusted user behavior dimension information and the above-mentioned adjusted effective playback time ratio to obtain video dimension information corresponding to the above-mentioned video.

[0025] Optionally, the video recall apparatus further includes a matching unit and a push unit. The matching unit is configured to match recommended videos from the recalled videos based on the target user's user information to obtain a recommended video set. The push unit is configured to push each recommended video in the recommended video set to a recommended video pool corresponding to the target user.

[0026] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0027] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0028] In a fifth aspect, some embodiments of the present disclosure provide a computer program product, including a computer program, which implements the method described in any implementation of the first aspect when executed by a processor.

[0029] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the video recall method of some embodiments of the present disclosure, the quality of the recalled video is improved. Specifically, the reason for the poor quality of the recalled video is that: only user behavior is used to construct the recall index. In fact, there will be a part of worthless users and worthless behaviors in the users and behaviors (for example, a user has generated behaviors on too many videos, which means that this user basically does not select videos. No matter what the quality of the video is, it will be accepted and generated by this user. Then, the quality of the video cannot be judged from the behavior of this user), resulting in poor accuracy of the recall index and poor quality of the recalled video. Based on this, the video recall method of some embodiments of the present disclosure, first, for each user in the user set, based on the video browsing information corresponding to the above user, generates user dimension information of the above user. Thus, the user can be scored from the user's own dimension based on the user's video browsing behavior. Then, for each video in the video set, perform the following steps: Step 1, based on the user behavior information set corresponding to the above video in the above user set and the generated user dimension information, generate user behavior dimension information of the above video. Thus, the score of each video under the influence of user behavior can be determined based on the user behavior of each user for each video and the user score of each user. The second step is to generate the video dimension information of the above video based on the above user behavior dimension information. Thus, the final score of each video can be comprehensively determined. The third step is to select videos that meet the preset recall conditions from the above video set as recalled videos based on the video dimension information corresponding to each video in the above video set, and obtain each recalled video. Thus, video recall can be performed based on the improved video recall index (i.e., video dimension information). Because the improved video recall index not only takes into account the impact of user behavior on the video, but also takes into account the impact of the user's own dimension score (i.e., user dimension information) on the video under user behavior, it can weaken the influence of worthless users and their worthless behavior on the accuracy of the recall index, thereby improving the accuracy of the improved video recall index, and then improving the quality of the recalled video. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0031] Figure 1 is an architectural diagram of an exemplary system in which some embodiments of the present disclosure may be applied;

[0032] Figure 2 is a flow chart of some embodiments of the video recall method according to the present disclosure;

[0033] Figure 3 is a flow chart of other embodiments of the video recall method according to the present disclosure;

[0034] Figure 4 is a schematic structural diagram of some embodiments of the video recall device according to the present disclosure;

[0035] Figure 5 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0036] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0037] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0038] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0039] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0040] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0041] With regard to the collection, storage, and use of user personal information (such as videos, video browsing information, and user information) involved in this disclosure, before performing the corresponding operations, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, fulfilling the obligation to inform the personal information subjects, and obtaining the authorization and consent of the personal information subjects in advance.

[0042] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0043] like Figure 1As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0044] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, short video applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0045] Terminal devices 101, 102, and 103 can be hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with display screens and support video browsing, including but not limited to smartphones, tablet computers, e-book readers, laptop computers, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules, for example, to provide distributed services, or as a single software or software module. No specific limitations are given here.

[0046] The server 105 may be a server that provides various services, such as a background server that supports the video displayed on the terminal devices 101, 102, and 103. The background server may analyze and process the received data such as the video request, and feed back the processing result (such as the video) to the terminal device.

[0047] It should be noted that the video recall method provided in the embodiments of the present disclosure may be executed by the server 105. Accordingly, the video recall device may be provided in the server 105.

[0048] It should be noted that the server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules, for example, to provide distributed services, or as a single software program or software module. This is not specifically limited here.

[0049] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0050] Continue to refer Figure 2 , shows a process 200 of some embodiments of the video recall method according to the present disclosure. The video recall method includes the following steps:

[0051] Step 201: For each user in the user set, user dimension information of the user is generated according to the video browsing information corresponding to the user.

[0052] In some embodiments, for each user in the user set, the execution subject of the video recall method (eg Figure 1 The server shown in the figure can generate user dimension information of the user based on the video browsing information corresponding to the user. The user set can be pre-set or can be all users. Users can be represented by user identifiers. The video browsing information can represent relevant statistical data on the user's video browsing behavior. The video browsing information can include the number of valid views. The valid view number can represent the number of non-repeated videos that the user has effectively viewed. A valid view here can mean that the viewing time for a video exceeds a preset duration. For example, the preset duration can be 4 seconds. It should be noted that, from the user dimension, some users rarely engage in behavior. Once such users engage in behavior, it can basically represent the user's preferences and the quality of the video. On the other hand, some users engage in behavior very frequently. Such users may engage in behavior on a variety of videos. Therefore, the value of such users' behavior is relatively low and cannot reflect the quality of the video. Therefore, users can be scored from the user's own dimension based on the frequency of their behavior to obtain user dimension information. In practice, for each user, the execution entity can determine the inverse of the number of valid views included in the video browsing information corresponding to the user as the user dimension information of the user.

[0053] In some optional implementations of some embodiments, the execution entity may generate user dimension information of the user according to the video browsing information corresponding to the user through the following steps:

[0054] The first step is to select video browsing behavior information that meets a preset browsing duration condition from each piece of video browsing behavior information included in the video browsing information. Each piece of video browsing behavior information corresponds to a video. The video browsing behavior information may be information related to a user's browsing behavior for a video. Each piece of video browsing behavior information may include a browsing duration. The browsing duration may indicate the length of time the user viewed the video. The preset browsing duration condition may be that the browsing duration included in the video browsing behavior information is greater than or equal to a preset duration.

[0055] In the second step, the number of videos corresponding to the selected video browsing behavior information is determined as the number of valid videos. The number of valid videos can represent the number of videos whose browsing time by the user meets the preset browsing time condition.

[0056] The third step is to generate the user dimension information of the user based on the number of valid videos. In practice, the execution entity may determine the first value as the user dimension information of the user in response to determining that the number of valid videos is greater than a preset number. For example, the preset number may be 30. Secondly, in response to determining that the number of valid videos is less than or equal to the preset number, the second value may be determined as the user dimension information of the user. The first value is less than the second value. For example, the first value may be 0, and the second value may be 1. Thus, valuable users may be assigned higher scores and worthless users may be assigned lower scores through a binary classification method.

[0057] Step 202: For each video in the video collection, perform the following steps:

[0058] Step 2021: Generate user behavior dimension information of the video based on the user behavior information set of the video corresponding to the user set and the generated user dimension information.

[0059] In some embodiments, the execution entity may generate user behavior dimension information for the video based on the user behavior information set corresponding to the video and the generated user dimension information. Each piece of user behavior information in the user behavior information set corresponds to a user in the user set. The user behavior information may be information related to the user's actions performed on the video. For example, the video may be a short video. The user's actions that can be performed on the video may include, but are not limited to, at least one of the following: play, like, forward, and comment. The user behavior information may include the user's actions performed on the video. In practice, for each executable action and each user in the user set, the execution entity may, in response to determining that the user behavior information corresponding to the user includes the executable action, determine the user dimension information corresponding to the user as a component of the executable action and the user's user behavior dimension value. The sum of the resulting user behavior dimension value components corresponding to the executable action and each user may be determined as the user behavior dimension value corresponding to the executable action. Finally, the resulting user behavior dimension value corresponding to each executable action may be determined as the user behavior dimension information for the video.

[0060] In some optional implementations of some embodiments, the execution entity may generate user behavior dimension information of the video according to the user behavior information set corresponding to the video and the generated user dimension information by the following steps:

[0061] In the first step, for each user behavior type in the preset user behavior type set, perform the following steps:

[0062] First, for each user in the above user set, perform the following steps:

[0063] First, based on the user behavior information corresponding to the user in the user behavior information set, first behavior information corresponding to the user behavior type, the user, and the video is generated. The preset user behavior type set may include, but is not limited to, at least one of the following: play, like, forward, and comment.

[0064] Secondly, based on the first behavior information and the user dimension information corresponding to the user, second behavior information corresponding to the user behavior type, the user, and the video is generated. In practice, the execution entity may determine the second behavior information corresponding to the user behavior type, the user, and the video by multiplying the first behavior information and the user dimension information.

[0065] Second, the sum of each obtained second behavior information is determined as weighted behavior information corresponding to the user behavior type and the video.

[0066] In the second step, the weighted behavior information is determined as the user behavior dimension information corresponding to the video, thereby performing weighted voting on the video based on user behavior.

[0067] In some optional implementations of some embodiments, the execution entity may generate first behavior information corresponding to the user behavior type, the user, and the video based on the user behavior information corresponding to the user in the user behavior information set through the following steps:

[0068] The first step is to determine whether the above user behavior information meets the preset user behavior conditions corresponding to the above user behavior type.

[0069] In a second step, in response to determining that the user behavior information satisfies the preset user behavior condition, a first preset value is determined as the first behavior information corresponding to the user behavior type, the user, and the video. The preset user behavior condition may be that the user behavior information includes the user behavior type. The first preset value may be 1.

[0070] In a third step, in response to determining that the user behavior information does not meet the preset user behavior condition, a second preset value is determined as the first behavior information corresponding to the user behavior type, the user, and the video. The second preset value is less than the first preset value. The second preset value may be 0.

[0071] Step 2022: Generate video dimension information of the video based on the user behavior dimension information.

[0072] In some embodiments, the execution entity may generate video dimension information for the video based on the user behavior dimension information. In practice, the execution entity may determine the video dimension information for the video by taking the weighted sum of the user behavior dimension values included in the user behavior dimension information. The weighting coefficients corresponding to the user behavior dimension values may be set based on the importance of the executable behavior, and are not specifically limited here.

[0073] Step 203 : Based on the video dimension information corresponding to each video in the video set, select videos that meet the preset recall conditions from the video set as recalled videos to obtain each recalled video.

[0074] In some embodiments, the execution entity may select videos that meet preset recall conditions from the video set as recalled videos based on the video dimension information corresponding to each video in the video set, thereby obtaining each recalled video. The preset recall condition may be a TopK ranking of the video dimension information corresponding to the video. In practice, the execution entity may sort the videos in descending order of the video dimension information corresponding to each video in the video set to obtain a video sequence. Then, the top K videos may be selected from the video sequence as each recalled video. The specific setting of K is not limited here.

[0075] Optionally, the execution entity may also match recommended videos from the recalled videos based on the target user's user information to obtain a recommended video set. The target user may be any user to whom videos are to be recommended. The user information may include various user attribute-related information. For example, user information may include, but is not limited to, at least one of the following: username, age, gender, login location, and topics of interest. In practice, the execution entity may use a recommendation algorithm to match recommended videos from the recalled videos to obtain a recommended video set. Recommendation algorithms may include, but are not limited to, content-based recommendation algorithms and collaborative filtering recommendation algorithms. Each recommended video in the recommended video set may then be pushed to a recommended video pool corresponding to the target user. The recommended video pool may be used to store videos to be recommended to the user. After logging in to the terminal, the user can retrieve each recommended video from the recommended video pool and play them sequentially for viewing. In this way, videos can be recommended to the user from popular videos and pre-stored in the recommended video pool corresponding to the user for viewing after logging in.

[0076] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the video recall method of some embodiments of the present disclosure, the quality of the recalled video is improved. Specifically, the reason for the poor quality of the recalled video is that: only user behavior is used to construct the recall index. In fact, there will be a part of worthless users and worthless behaviors in the users and behaviors (for example, a user has generated behaviors on too many videos, which means that this user basically does not select videos. No matter what the quality of the video is, it will be accepted and generated by this user. Then, the quality of the video cannot be judged from the behavior of this user), resulting in poor accuracy of the recall index and poor quality of the recalled video. Based on this, the video recall method of some embodiments of the present disclosure, first, for each user in the user set, based on the video browsing information corresponding to the above user, generates user dimension information of the above user. Thus, the user can be scored from the user's own dimension based on the user's video browsing behavior. Then, for each video in the video set, perform the following steps: Step 1, based on the user behavior information set corresponding to the above video in the above user set and the generated user dimension information, generate user behavior dimension information of the above video. Thus, the score of each video under the influence of user behavior can be determined based on the user behavior of each user for each video and the user score of each user. The second step is to generate the video dimension information of the above video based on the above user behavior dimension information. Thus, the final score of each video can be comprehensively determined. The third step is to select videos that meet the preset recall conditions from the above video set as recalled videos based on the video dimension information corresponding to each video in the above video set, and obtain each recalled video. Thus, video recall can be performed based on the improved video recall index (i.e., video dimension information). Because the improved video recall index not only takes into account the impact of user behavior on the video, but also takes into account the impact of the user's own dimension score (i.e., user dimension information) on the video under user behavior, it can weaken the influence of worthless users and their worthless behavior on the accuracy of the recall index, thereby improving the accuracy of the improved video recall index, and then improving the quality of the recalled video.

[0077] Further references Figure 3 , which shows a process 300 of another embodiment of a video recall method. The process 300 of the video recall method includes the following steps:

[0078] Step 301: For each user in the user set, user dimension information of the user is generated according to the video browsing information corresponding to the user.

[0079] Step 302: For each video in the video collection, perform the following steps:

[0080] Step 3021: Generate user behavior dimension information of the video based on the user behavior information set of the video corresponding to the user set and the generated user dimension information.

[0081] In some embodiments, the specific implementation of steps 301-3021 and the resulting technical effects can be referred to Figure 2 The corresponding steps 201-2021 in the embodiments are not repeated here.

[0082] Step 3022: Generate first floating space information corresponding to the video based on the user behavior dimension information and the number of valid video playbacks.

[0083] In some embodiments, the execution subject of the video recall method (eg Figure 1 The server shown in the figure) can generate the first floating space information corresponding to the above video based on the above user behavior dimension information and the effective playback number of the above video. The above user behavior dimension information may include each weighted behavior information corresponding to a preset set of user behavior types. The above effective playback number can be the number of times the playback time of the above video exceeds the preset playback time. In practice, the above execution entity can generate the first floating space information corresponding to the above video based on the above user behavior dimension information and the effective playback number of the above video through the following steps:

[0084] In the first step, for each user behavior type in the preset user behavior type set, perform the following steps:

[0085] First, based on the target user behavior type, the weighted behavior information of the above-mentioned user behavior type in the above-mentioned various weighted behavior information is normalized to obtain a normalized behavior dimension value. Among them, the above-mentioned preset user behavior type set may include each user behavior type in the above-mentioned user behavior type set except the above-mentioned target user behavior type. The above-mentioned target user behavior type may be a basic user behavior. For example, the target user behavior type may be playback. Other user behaviors are all executed after playback. In practice, the above-mentioned execution entity may determine the weighted behavior information corresponding to the above-mentioned target user behavior type as the target weighted behavior information. Then, the ratio of the above-mentioned weighted behavior information to the above-mentioned target weighted behavior information may be determined as the normalized behavior dimension value.

[0086] Second, based on the normalized behavior dimension value and the number of valid plays, a first floating space value corresponding to the user behavior type and the video is generated. In practice, the execution entity may generate the first floating space value corresponding to the user behavior type and the video using the following formula:

[0087]

[0088] Wherein, offset may represent the first floating space value. s may represent the normalized behavior dimension value. N may represent the effective playback number. p It can represent the interval value when the confidence level is p under the standard normal distribution. Here, p can be 0.95, z p It can be 1.96.

[0089] The second step is to determine each generated first floating space value as the first floating space information corresponding to the video. Thus, each first floating space value provides a floating space for the video's score under various user behavior types. This floating space decreases as the number of views increases, ultimately stabilizing the video score. Furthermore, when multiple videos have the same score, the introduction of floating space tends to prioritize videos with lower views, thereby rapidly increasing the views of those videos and accelerating the iteration of the hot queue.

[0090] Step 3023: Generate adjusted user behavior dimension information based on the first floating space information and the user behavior dimension information.

[0091] In some embodiments, the execution entity may generate adjusted user behavior dimension information based on the first floating space information and the user behavior dimension information. In practice, for each user behavior type in the user behavior type set, the execution entity may perform the following steps:

[0092] The first step is to determine a first floating space value corresponding to the user behavior type and the video.

[0093] The second step is to determine the normalized behavior dimension value corresponding to the above user behavior type and the above video.

[0094] The third step is to generate an adjusted behavior dimension value corresponding to the user behavior type based on the first floating space value and the normalized behavior dimension value. In practice, the execution entity can determine the difference between the first floating space value and the normalized behavior dimension value. Then, the product of the difference and the preset floating weight can be determined. Finally, the sum of the normalized behavior dimension value and the product can be determined as the adjusted behavior dimension value. In this way, the floating space can be used to adjust the video score under each user behavior.

[0095] Finally, the generated adjusted behavior dimension values may be determined as adjusted user behavior dimension information.

[0096] Step 3024: Generate an effective playback duration ratio based on the effective playback duration and video duration of the video.

[0097] In some embodiments, the above-mentioned execution entity may generate an effective playback time ratio based on the effective playback time and video duration corresponding to the above-mentioned video. The above-mentioned effective playback time may be the average of the effective browsing time of all valuable users on the above-mentioned video. The valuable user may be a user whose corresponding number of valid videos is greater than a preset number. The effective browsing time may be the browsing time of watching the above-mentioned video that is greater than a preset time. The above-mentioned video duration may be the total video duration of the above-mentioned video. The above-mentioned execution entity may determine the ratio of the above-mentioned effective playback time to the above-mentioned video duration as the effective playback time ratio.

[0098] Step 3025: Generate second floating space information of the corresponding video based on the effective playback time ratio and the effective playback number.

[0099] In some embodiments, the execution entity may generate second floating space information corresponding to the video based on the effective play time percentage and the effective play count. In practice, the execution entity may generate the second floating space information corresponding to the video using a formula that generates the first floating space value. The "s" in the formula may also represent the effective play time percentage. The "offset" in the formula may also represent the second floating space information.

[0100] Step 3026: Generate an adjusted effective playback time ratio based on the effective playback time ratio and the second floating space information.

[0101] In some embodiments, the execution entity may generate an adjusted effective playback time ratio based on the effective playback time ratio and the second floating space information. In practice, the execution entity may determine the difference between the second floating space information and the effective playback time ratio as a first difference. Then, the product of the first difference and a preset floating weight may be determined as a first product. Finally, the sum of the effective playback time ratio and the first product may be determined as the adjusted effective playback time ratio. Thus, the floating space may be used to adjust the video score under the effective playback time ratio.

[0102] Step 3027: Generate video dimension information of the video based on the adjusted user behavior dimension information and the adjusted effective playback time ratio.

[0103] In some embodiments, the above-mentioned execution entity can generate the video dimension information of the above-mentioned video based on the above-mentioned adjusted user behavior dimension information and the above-mentioned adjusted effective playback time ratio. In practice, the above-mentioned execution entity can weight the various adjusted behavior dimension values and the above-mentioned adjusted effective playback time ratio included in the above-mentioned adjusted user behavior dimension information to obtain the video dimension information corresponding to the above-mentioned video. Here, each weighting coefficient can be pre-set. Considering the time cost of the behavior, a lower weight can be given to behavioral indicators that are easy to falsify and increase the number of counts. For example, the various adjusted behavior dimension values corresponding to likes, comments, shares and effective playback time ratio and the various weights of the above-mentioned adjusted effective playback time ratio can be: 0.1, 0.2, 0.15, 0.2 respectively.

[0104] Step 303 : According to the video dimension information corresponding to each video in the video set, videos that meet the preset recall conditions are selected from the video set as recalled videos to obtain each recalled video.

[0105] In some embodiments, the specific implementation of step 303 and the resulting technical effects can be referred to Figure 2 The corresponding step 203 in the embodiments will not be described in detail here.

[0106] from Figure 3 It can be seen that Figure 2 Compared with the description of some corresponding embodiments, Figure 3 Process 300 of the video recall method in some corresponding embodiments embodies an expanded step for determining video dimension information using a floating range. Thus, the schemes described in these embodiments can provide a floating range for video scores. This floating range decreases as the number of views increases, ultimately stabilizing the video scores. Furthermore, when multiple videos have the same score, the introduction of a floating range tends to prioritize videos with low views, thereby rapidly increasing the views of low-view videos and accelerating iterations of the popular queue.

[0107] Further references Figure 4 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a video recall device. These device embodiments are similar to Figure 2 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0108] like Figure 4As shown, the video recall device 400 of some embodiments includes: a generating unit 401, an executing unit 402, and a selecting unit 403. The generating unit 401 is configured to generate user dimension information of each user in the user set according to the video browsing information corresponding to the user; the executing unit 402 is configured to perform the following steps for each video in the video set: generating user behavior dimension information of the video according to the user behavior information set corresponding to the video in the user set and the generated user dimension information; generating video dimension information of the video according to the user behavior dimension information; the selecting unit 403 is configured to select videos that meet the preset recall conditions from the video set as recalled videos according to the video dimension information corresponding to each video in the video set, thereby obtaining each recalled video.

[0109] Optionally, the generation unit 401 can be further configured to: select video browsing behavior information that meets a preset browsing time condition from each video browsing behavior information included in the above-mentioned video browsing information, wherein each video browsing behavior information corresponds to a video, and each video browsing behavior information includes a browsing time; determine the number of each video corresponding to each selected video browsing behavior information as the number of valid videos; and generate user dimension information of the above-mentioned user based on the above-mentioned number of valid videos.

[0110] Optionally, the execution unit 402 can be further configured to: for each user behavior type in a preset user behavior type set, perform the following steps: for each user in the above user set, perform the following steps: based on the user behavior information corresponding to the above user in the above user behavior information set, generate first behavior information corresponding to the above user behavior type, the above user and the above video; based on the above first behavior information and the user dimension information corresponding to the above user, generate second behavior information corresponding to the above user behavior type, the above user and the above video; determine the sum of the obtained second behavior information as the weighted behavior information corresponding to the above user behavior type and the above video; determine the determined weighted behavior information as the user behavior dimension information corresponding to the above video.

[0111] Optionally, the execution unit 402 can be further configured to: determine whether the above-mentioned user behavior information meets the preset user behavior conditions corresponding to the above-mentioned user behavior type; in response to determining that the above-mentioned user behavior information meets the above-mentioned preset user behavior conditions, determine the first preset value as the first behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video; in response to determining that the above-mentioned user behavior information does not meet the above-mentioned preset user behavior conditions, determine the second preset value as the first behavior information corresponding to the above-mentioned user behavior type, the above-mentioned user and the above-mentioned video, wherein the above-mentioned second preset value is smaller than the above-mentioned first preset value.

[0112] Optionally, the execution unit 402 can be further configured to: generate first floating space information corresponding to the above-mentioned video based on the above-mentioned user behavior dimension information and the effective playback number of the above-mentioned video; generate adjusted user behavior dimension information based on the above-mentioned first floating space information and the above-mentioned user behavior dimension information; generate an effective playback time ratio based on the effective playback time and video time corresponding to the above-mentioned video; generate second floating space information corresponding to the above-mentioned video based on the above-mentioned effective playback time ratio and the above-mentioned effective playback number; generate an adjusted effective playback time ratio based on the above-mentioned effective playback time ratio and the above-mentioned second floating space information; generate video dimension information of the above-mentioned video based on the above-mentioned adjusted user behavior dimension information and the above-mentioned adjusted effective playback time ratio.

[0113] Optionally, the above-mentioned user behavior dimension information includes each weighted behavior information corresponding to a preset user behavior type set.

[0114] Optionally, the execution unit 402 can be further configured to: for each user behavior type in a preset user behavior type set, perform the following steps: based on the target user behavior type, normalize the weighted behavior information of the above-mentioned user behavior type in the above-mentioned weighted behavior information to obtain a normalized behavior dimension value; based on the above-mentioned normalized behavior dimension value and the above-mentioned effective playback number, generate a first floating space value corresponding to the above-mentioned user behavior type and the above-mentioned video; and determine the generated each first floating space value as the first floating space information corresponding to the above-mentioned video.

[0115] Optionally, the execution unit 402 can be further configured to: for each user behavior type in the above-mentioned user behavior type set, perform the following steps: determine the first floating space value corresponding to the above-mentioned user behavior type and the above-mentioned video; determine the normalized behavior dimension value corresponding to the above-mentioned user behavior type and the above-mentioned video; generate an adjusted behavior dimension value corresponding to the above-mentioned user behavior type based on the above-mentioned first floating space value and the above-mentioned normalized behavior dimension value; and determine the generated adjusted behavior dimension values as adjusted user behavior dimension information.

[0116] Optionally, the execution unit 402 can be further configured to: weight each adjusted behavior dimension value included in the above-mentioned adjusted user behavior dimension information and the above-mentioned adjusted effective playback time ratio to obtain video dimension information corresponding to the above-mentioned video.

[0117] Optionally, the video recall device 400 may further include a matching unit and a push unit (not shown). The matching unit is configured to match recommended videos from the recalled videos based on the target user's user information to obtain a recommended video set. The push unit is configured to push each recommended video in the recommended video set to a recommended video pool corresponding to the target user.

[0118] It is understood that the units described in the device 400 are similar to those in the reference Figure 2 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 400 and the units included therein, and will not be repeated here.

[0119] Reference below Figure 5 , which shows an electronic device 500 (eg, Figure 1 A schematic diagram of the structure of the server in FIG. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0120] like Figure 5 As shown, the electronic device 500 may include a processing device 501 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0121] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 5 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0122] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0123] It should be noted that the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0124] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0125] The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: generates user dimension information of each user in the user set according to the video browsing information corresponding to the user; performs the following steps for each video in the video set: generates user behavior dimension information of the video according to the user behavior information set corresponding to the video in the user set and the generated user dimension information; generates video dimension information of the video according to the user behavior dimension information; selects videos that meet the preset recall conditions from the video set as recalled videos according to the video dimension information corresponding to each video in the video set, and obtains each recalled video.

[0126] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0127] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0128] The units described in some embodiments of the present disclosure may be implemented in software or in hardware. The described units may also be provided in a processor, for example, they may be described as: a processor comprising a generation unit, an execution unit, and a selection unit. The names of these units do not, in some cases, constitute a limitation on the units themselves. For example, the generation unit may also be described as "a unit that generates user dimension information of each user in a user set based on the video browsing information corresponding to the user".

[0129] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0130] Some embodiments of the present disclosure further provide a computer program product, including a computer program, which implements any of the above-mentioned video recall methods when executed by a processor.

[0131] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A video recall method, comprising: For each user in the user set, generating user dimension information of the user according to the video browsing information corresponding to the user; For each video in the video collection, perform the following steps: Generating user behavior dimension information of the video according to the user behavior information set corresponding to the video by the user set and the generated user dimension information; Based on the user behavior dimension information, video dimension information of the video is generated; based on the video dimension information corresponding to each video in the video set, videos that meet preset recall conditions are selected from the video set as recalled videos to obtain each recalled video.

2. The method according to claim 1, wherein Generating user dimension information of the user according to the video browsing information corresponding to the user includes: Selecting video browsing behavior information that meets a preset browsing duration condition from each video browsing behavior information included in the video browsing information, wherein each video browsing behavior information corresponds to a video and each video browsing behavior information includes a browsing duration; Determine the number of each video corresponding to each selected video browsing behavior information as the number of valid videos; User dimension information of the user is generated according to the number of valid videos.

3. The method according to claim 1, wherein Generating user behavior dimension information of the video according to the user behavior information set corresponding to the video by the user set and the generated user dimension information includes: For each user behavior type in the preset user behavior type set, perform the following steps: For each user in the user set, perform the following steps: generating first behavior information corresponding to the user behavior type, the user, and the video according to the user behavior information corresponding to the user in the user behavior information set; generating, based on the first behavior information and the user dimension information corresponding to the user, second behavior information corresponding to the user behavior type, the user, and the video; Determining the sum of each obtained second behavior information as weighted behavior information corresponding to the user behavior type and the video; The determined pieces of weighted behavior information are determined as user behavior dimension information corresponding to the video.

4. The method according to claim 3, wherein: The generating, based on the user behavior information corresponding to the user in the user behavior information set, first behavior information corresponding to the user behavior type, the user, and the video, includes: Determining whether the user behavior information meets a preset user behavior condition corresponding to the user behavior type; In response to determining that the user behavior information satisfies the preset user behavior condition, determining a first preset value as first behavior information corresponding to the user behavior type, the user, and the video; In response to determining that the user behavior information does not meet the preset user behavior condition, a second preset value is determined as the first behavior information corresponding to the user behavior type, the user and the video, wherein the second preset value is less than the first preset value.

5. The method according to claim 1, wherein Generating the video dimension information of the video according to the user behavior dimension information includes: Generate first floating space information corresponding to the video according to the user behavior dimension information and the effective playback number of the video; generating adjusted user behavior dimension information according to the first floating space information and the user behavior dimension information; Generate an effective playback time ratio based on the effective playback time and video time corresponding to the video; generating second floating space information corresponding to the video according to the effective playback time ratio and the effective playback quantity; generating an adjusted effective playback time ratio according to the effective playback time ratio and the second floating space information; The video dimension information of the video is generated according to the adjusted user behavior dimension information and the adjusted effective playback time ratio.

6. The method according to claim 5, wherein: The user behavior dimension information includes each weighted behavior information corresponding to a preset user behavior type set; And generating first floating space information corresponding to the video according to the user behavior dimension information and the effective playback number of the video includes: For each user behavior type in the preset user behavior type set, perform the following steps: Based on the target user behavior type, normalizing the weighted behavior information of the user behavior type in each weighted behavior information to obtain a normalized behavior dimension value; Generating a first floating space value corresponding to the user behavior type and the video according to the normalized behavior dimension value and the effective playback quantity; The generated first floating space values are determined as first floating space information corresponding to the video.

7. The method according to claim 6, wherein: Generating adjusted user behavior dimension information according to the first floating space information and the user behavior dimension information includes: For each user behavior type in the user behavior type set, perform the following steps: Determining a first floating space value corresponding to the user behavior type and the video; Determining a normalized behavior dimension value corresponding to the user behavior type and the video; generating an adjusted behavior dimension value corresponding to the user behavior type according to the first floating space value and the normalized behavior dimension value; The generated adjusted behavior dimension values are determined as adjusted user behavior dimension information.

8. The method according to claim 7, wherein: Generating the video dimension information of the video according to the adjusted user behavior dimension information and the adjusted effective playback time ratio includes: The adjusted behavior dimension values and the adjusted effective playback time ratio included in the adjusted user behavior dimension information are weighted to obtain the video dimension information corresponding to the video.

9. The method according to any one of claims 1 to 8, wherein: The method further comprises: Matching recommended videos from the recalled videos according to the user information of the target user to obtain a recommended video set; Each recommended video in the recommended video set is pushed to the recommended video pool corresponding to the target user.

10. A video recall device comprising: a generating unit configured to generate user dimension information of each user in the user set according to the video browsing information corresponding to the user; The execution unit is configured to perform the following steps for each video in the video set: generating user behavior dimension information of the video based on the user behavior information set corresponding to the video of the user set and the generated user dimension information; generating video dimension information of the video based on the user behavior dimension information; The selection unit is configured to select videos that meet preset recall conditions from the video set as recalled videos based on video dimension information corresponding to each video in the video set, thereby obtaining each recalled video.

11. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 9.

12. A computer-readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images