CN111083534A

CN111083534A - Method and equipment for providing recommended video list

Info

Publication number: CN111083534A
Application number: CN201911401514.7A
Authority: CN
Inventors: 方玮俊; 屠小英; 阴志亮
Original assignee: Shanghai Zhangmen Science and Technology Co Ltd
Current assignee: Nanjing Shangwang Network Technology Co ltd
Priority date: 2019-12-30
Filing date: 2019-12-30
Publication date: 2020-04-28
Anticipated expiration: 2039-12-30
Also published as: CN111083534B

Abstract

The application aims to provide a method and equipment for providing a recommended video list, and the method comprises the following steps: determining recommendation time point information corresponding to an on-air video on user equipment and a recommendation video list corresponding to the on-air video under the recommendation time point information; sending the recommended video list to the user equipment so that the recommended video list is presented above the on-air video. According to the method and the device, the recommended video list is pushed to the user, so that the user can spend more time on watching the video, and the viscosity of the user is improved.

Description

Method and equipment for providing recommended video list

Technical Field

The present application relates to the field of communications, and in particular, to a technique for providing a recommended video list.

Background

With the rapid development of the internet and the popularization of smart phones, mobile application programs distribute users, and mobile phone users increase rapidly, which becomes the first source of the growth of netizens. APP is consumed by many classes of APP as the most popular form of application for mobile terminals. In addition to social and game APP download leaders, video APPs are also ascending in mobile devices as important portals. The video APP is widely used by users due to the richness of video resources and the portability of the video-on-demand, and the users can watch other videos related to the current video in the video APP.

Disclosure of Invention

An object of the present application is to provide a method and apparatus for providing a recommended video list.

According to an aspect of the present application, there is provided a method for providing a recommended video list on a network device side, the method including:

determining recommendation time point information corresponding to an on-air video on user equipment and a recommendation video list corresponding to the on-air video under the recommendation time point information;

sending the recommended video list to the user equipment so that the recommended video list is presented above the on-air video.

According to another aspect of the present application, there is provided a method for providing a recommended video list on a user equipment side, the method including:

acquiring a playing video in the target application and presenting the playing video, wherein the playing video is presented in a full-screen playing mode;

receiving a recommended video list corresponding to the on-air video under the corresponding recommended time point information determined by the network equipment and returned by the network equipment;

presenting the list of recommended videos over the on-air video.

According to still another aspect of the present application, there is provided a method for providing a recommended video list, the method including:

the user equipment acquires a playing video in the target application and presents the playing video, wherein the playing video is presented in a full-screen playing mode;

the network equipment determines recommendation time point information corresponding to the on-air video and a recommendation video list corresponding to the on-air video under the recommendation time point information, and sends the recommendation video list to the user equipment;

the user equipment receives the recommended video list and presents the recommended video list above the on-air video.

According to an aspect of the present application, there is provided a network apparatus for providing a recommended video list, the apparatus including:

the system comprises a one-to-one module, a video playing module and a video playing module, wherein the one-to-one module is used for determining recommendation time point information corresponding to an on-play video on user equipment and a recommendation video list corresponding to the on-play video under the recommendation time point information;

a second module for sending the recommended video list to the user device such that the recommended video list is presented above the on-air video.

According to another aspect of the present application, there is provided a user equipment for providing a recommended video list, the apparatus including:

the second module is used for acquiring a playing video in the target application and presenting the playing video, wherein the playing video is presented in a full-screen playing mode;

a second module, configured to receive a recommended video list corresponding to the recommendation time point information corresponding to the on-demand video determined by the network device and returned by the network device;

and a second and third module for presenting the recommended video list above the on-air video.

According to an aspect of the present invention, there is provided an apparatus for providing a recommended video list, wherein the apparatus includes:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the operations of any of the methods described above.

According to another aspect of the invention, there is provided a computer readable medium storing instructions that, when executed, cause a system to perform the operations of any of the methods described above.

Compared with the prior art, the network equipment determines the recommendation time point information corresponding to the video on the user equipment and the recommendation video list corresponding to the video on the user equipment under the recommendation time point information; and sending the recommended video list to the user equipment. The method and the device automatically confirm the appropriate recommendation time point information about the recommended video list through the network equipment, so that the time point of issuing the recommended video list is more suitable for the requirements of the current user or the user sees more interesting video content before leaving the current video playing, the user can spend more time on the basis of the recommended video list, the stickiness of the user to products is improved to retain the user, the user equipment can automatically insert the recommended video list above a full-screen playing interface of the video playing after acquiring the recommended video information, the recommended video list can be acquired without manually clicking by the user, the operation of the user is simplified, meanwhile, the difference of the recommended video information can be personalized video information recommendation for the user, the experience of the user in watching the video is improved, and on the basis, more exposure and clicking are performed through related videos (such as the recommended video list), and analyzing the operation behavior and the preference of the user and making better data support for subsequent recommendation.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 illustrates a system topology according to the present application;

FIG. 2 illustrates a system method diagram for providing a recommended video list according to one embodiment of the present application;

fig. 3 shows a flowchart of a method for providing a recommended video list at a network device according to another embodiment of the present application;

FIG. 4 shows a flowchart of a method for providing a recommended video list at a user equipment according to another embodiment of the present application;

FIG. 5 illustrates a schematic diagram for providing a recommended video list according to yet another embodiment of the present application;

FIG. 6 illustrates an apparatus diagram of a network device for providing a recommended video list according to one embodiment of the present application;

FIG. 7 shows an apparatus diagram of a user device for providing a recommended video list according to one embodiment of the present application;

FIG. 8 shows a device diagram of a system for providing a recommended video list according to one embodiment of the present application;

FIG. 9 illustrates an exemplary system that can be used to implement the various embodiments described in this disclosure.

The same or similar reference numbers in the drawings identify the same or similar elements.

Detailed Description

The present application is described in further detail below with reference to the attached figures.

In a typical configuration of the present application, the terminal, the device serving the network, and the trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

The device referred to in this application includes, but is not limited to, a user device, a network device, or a device formed by integrating a user device and a network device through a network. The user equipment includes, but is not limited to, any mobile electronic product, such as a smart phone, a tablet computer, etc., capable of performing human-computer interaction with a user (e.g., human-computer interaction through a touch panel), and the mobile electronic product may employ any operating system, such as an android operating system, an iOS operating system, etc. The network device includes an electronic device capable of automatically performing numerical calculation and information processing according to a preset or stored instruction, and hardware thereof includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like. The network device includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud of a plurality of servers; here, the Cloud is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, one virtual supercomputer consisting of a collection of loosely coupled computers. Including, but not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless Ad Hoc network (Ad Hoc network), etc. Preferably, the device may also be a program running on the user device, the network device, or a device formed by integrating the user device and the network device, the touch terminal, or the network device and the touch terminal through a network.

Of course, those skilled in the art will appreciate that the foregoing is by way of example only, and that other existing or future devices, which may be suitable for use in the present application, are also encompassed within the scope of the present application and are hereby incorporated by reference.

In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.

Fig. 1 shows a typical scenario of the present application, where a user holds a user device, a video-class application is installed in the user device, in response to a click operation of the user in the video application, the user device sends a play request about a target video to a network device, the network device returns the video to the user device, the user device plays the video in a full-screen play mode, and the network device determines recommendation time point information corresponding to an on-play video on the user device and a recommended video list corresponding to the on-play video under the recommendation time point information, and then sends the recommended video list to the user device, where the user device includes, but is not limited to, a computing device with a touch screen, such as a mobile phone, a tablet, and a computer.

Referring to the system shown in fig. 1, fig. 2 illustrates a system method for providing recommended video information according to an embodiment of the present application, the method including:

the network equipment determines recommendation time point information corresponding to the on-demand video and a recommendation video list corresponding to the on-demand video under the recommendation time point information, and sends the recommendation video list to the user equipment, so that the recommendation video list is presented above the on-demand video;

Fig. 3 shows a method for providing a recommended video list at a network device according to an embodiment of the present application, where the method includes step S101 and step S102.

Specifically, in step S101, the network device determines recommendation time point information corresponding to a video on the user equipment and a recommendation video list corresponding to the video on the user equipment under the recommendation time point information. In some embodiments, step S101 includes step S1013 (not shown), or includes step S1011 (not shown) and step S1012 (not shown), in step S1013, the network device queries a query database for the recommended time point information and the recommended video list matching the on-air video, where the database stores on-air videos, correspondence between the recommended time point information and the recommended video list; or, in step S1011, the network device determines recommendation time point information corresponding to the video playing on the user equipment; in step S1012, the network device determines a recommended video list corresponding to the on-air video in the recommended time point information. For example, the database stores the on-air videos, the corresponding relationship between the recommendation time point information and the recommendation video list, and the network device queries the database according to the video ID of the on-air video to obtain the corresponding recommendation time point information and the recommendation video list, or, when the network device first determines the recommendation time point information corresponding to the on-air video on the user device, provides a basis for subsequently determining the corresponding recommendation video list according to the video frame of the on-air video corresponding to the recommendation time point information. In some embodiments, in step S1011, the network device performs a matching query in the recommended time point database according to the video identification information of the on-air video on the user equipment, so as to obtain recommended time point information corresponding to the on-air video; or inputting the description vector information of the on-demand video into a recommended time point model to obtain recommended time point information corresponding to the on-demand video, wherein the recommended time point model is obtained based on a large number of recommended time point samples, and each recommended time point sample comprises sample description vector information of a video sample and one or more pieces of recommended time point sample information in the video sample; alternatively, the first and second electrodes may be,

identifying in real time according to the video attribute information of the on-air video to obtain the recommendation time point information corresponding to the on-air video, wherein the video attribute information includes at least any one of the following items:

1) background music of the on-air video;

2) the picture style of the on-air video;

3) texture of the on-air video. For example, the recommended time point database stores a plurality of records, each record includes a video and recommended time point information corresponding to the video, and the recommended time point information in the record is obtained in a manner including, but not limited to:

1) performing plot analysis on the content of the on-air video, and recording the end point or the starting point of a plot section as the recommendation time point information of the video;

2) counting the playing log information of the video playing, obtaining a plurality of playing ending time points corresponding to the video and the proportion of each playing ending time point in the total playing amount, taking the first N time points with the highest proportion as the recommended time point information of the video, wherein the value of N is positively correlated with the complete playing time length of the video. In some embodiments, the network device merges two adjacent playing end time points separated by a distance less than a certain duration (e.g., 5 seconds) into one playing time point, for example, taking a median of the two end time points, or performing weighted average according to respective proportions;

3) analyzing video attribute information of the on-air video content, for example, the video attribute information includes background music of the on-air video, the network device takes a combination point of an end point of one of the background music and a start point of a next background music as recommendation time point information, for example, the video attribute information includes a picture style of the on-air video, the network device takes a combination point of an end point of one of the picture styles and a start point of a next different picture style as recommendation time point information, for example, the video attribute information includes textures of the on-air video, and the network device takes a combination point of an end point of one of the textures and a start point of a next different texture as recommendation time point information.

Or for example, the network device obtains the video attribute information of the on-air video in real time and identifies the video attribute information in real time, so that the recommendation time point information corresponding to the on-air video is dynamically determined when the video attribute information changes.

Or for example, the network device stores a recommended time point model in advance, where the recommended time point model is learned based on a large number of recommended time point samples, each recommended time point sample includes sample description vector information of a video sample and one or more pieces of recommended time point sample information in the video sample, and the network device obtains the description vector information of the on-air video, where the description vector information includes a vector formed by a plurality of keywords, where each keyword forms a component of the vector to describe feature information of the video in one aspect (e.g., the on-air video is of a comedy type, is a lion lead actor, and is a vector formed by a plurality of keywords in which a main scene in the video is located at a place, etc.). In some embodiments, the recommended point-in-time model includes one or more recommended point-in-time sample information of video information obtained based on model training, where a ratio of the user exiting the video is higher on the one or more recommended point-in-time sample information. And on the basis of determining the recommendation time point information, providing a basis for subsequently determining a recommendation video list corresponding to the on-air video under the recommendation time point information.

In some embodiments, in step S1012, the network device determines, according to the user feedback information in the recommendation time point information, a recommended video list corresponding to the on-air video in the recommendation time point information. For example, the user feedback information includes but is not limited to behavior information such as comments, praise, forward, and exit from a currently on-air video playing interface, which are issued by the user at a time point corresponding to the recommendation time point information. And determining a corresponding recommended video list according to the user feedback information, giving the recommended videos of the same type as the currently played video to the user when the user feedback information is positive evaluation so as to attract the user, increasing the watching time of the user so as to improve the viscosity of the user, and providing other recommended videos which are irrelevant to the currently played video to the user when the user feedback information is negative evaluation so as to leave the user on a video interface. In some embodiments, in step S1012, when the user feedback information under the recommended time point information includes negative direction information, the network device resets or inverts at least one component information in the description vector information of the on-air video to obtain rectification description vector information corresponding to the on-air video, and determines a recommended video list corresponding to the on-air video under the recommended time point information according to the rectification description vector information, where the recommended video list matches with the rectification description vector information; otherwise, determining a recommended video list corresponding to the on-air video under the recommended time point information according to the description vector information of the on-air video, wherein the recommended video list is matched with the description vector information. For example, the negative information includes that the user finishes playing or stops playing the video at the time point corresponding to the recommended time point information, or the user negatively evaluates the video, and the like. If the user feedback information under the recommended time point information contains negative information, the network equipment resets or inverts at least one component information in the description vector information of the video-on-air to obtain correction description vector information corresponding to the video-on-air, wherein the resetting operation comprises resetting the assignment of the component, the inverting operation comprises taking the negative value of the component, the network equipment obtains the correction description vector by carrying out certain correction processing on the original description vector of the video, and obtains a matched recommended video list according to the correction description vector, so that the recommended video list has a certain matching degree and a certain discrimination degree with the video-on-air, the recommended video which meets the requirements of the user is recommended for the user when the user wants to leave the video-on-air, and the service life of the user is effectively prolonged. For example, the on-air video comprises description vector information composed of a plurality of keywords such as a comedy type, a lion lead actor, a main scene in the video located at a place, and the like, the network device determines corresponding rectification description vector information of the on-air video (for example, rectification description vector information composed of a plurality of keywords such as a tragedy type, a lion lead actor, a main scene in the video located at a place, and the like), and determines a corresponding recommended video list of the on-air video under the recommended time point information according to the rectification description vector information. In some embodiments, the resetting or inverting at least one component information in the description vector information of the on-air video to obtain the corresponding rectification description vector information of the on-air video includes: when the user feedback information under the recommendation time point information contains negative information, resetting or negating at least one component information in the description vector information of the video in broadcasting according to the measurement information of the negative information to obtain the correction description vector information corresponding to the video in broadcasting. For example, the measurement information of the negative-going information includes the number of the negative-going information in the user feedback information under the recommendation time point information, and if the number of the negative-going information is larger, more component information in the description vector information of the on-air video is reset or inverted, so as to recommend a recommended video more meeting the requirement of the user.

In step S102, the network device sends the recommended video list to the user device, so that the recommended video list is presented above the on-air video. And providing a basis for presenting the recommended video list when the video is played in a full screen mode by the subsequent user equipment. In some embodiments, in step S102, the network device sends the recommended video list and the recovery duration threshold information corresponding to the recommended video list to the user device, so that the recommended video list is presented above the on-air video. For example, the recovery duration threshold may be configured by the user equipment, or may be a basis for the network equipment to send to the user equipment, and providing a basis for automatically canceling presentation of the recommended video list after the time for presenting the recommended video list by the subsequent user equipment reaches the recovery duration threshold. In some embodiments, the method further includes step S105 (not shown), in step S105, the network device determines, according to the recommendation quantity information included in the recommended video list, recovery duration threshold information corresponding to the recommended video list; or inputting the on-air videos into a recovery duration threshold model to determine recovery duration threshold information corresponding to the recommended video list, wherein the recovery duration threshold model is learned based on a large number of recovery duration samples of the recommended video list in the on-air videos, and each recovery duration sample comprises recovery duration counted by historical click recovery operations of other users on the recommended video list in the process of watching the on-air videos; or inputting the information of the user into a recovery duration threshold model to determine recovery duration threshold information corresponding to the recommended video list, wherein the recovery duration threshold model is obtained based on a large number of recovery duration samples, and each recovery duration sample comprises the recovery duration counted by the historical click recovery operation of the recommended video list corresponding to the historical videos in the process that the user watches the historical videos; in step S102, the network device sends the recommended video list and the recovery duration threshold information to the user device, so that the recommended video list is presented above the on-air video. For example, if the recommended number of videos included in the recommended video list is larger, the network device determines that the recycling duration threshold is also higher, so as to give the user enough time to browse the recommended content when the recommended video list is larger. Or for example, the network device stores a recovery duration threshold model in advance, wherein the recovery duration threshold model is learned based on a large number of recovery duration samples of the recommended video list in the broadcast video, and for example, the model counts historical recovery duration records of the recommended video list of the broadcast video by acquiring historical click recovery operations of other users on the recommended video list in the broadcast video (for example, manually recovering the recommended video list through the historical click recovery operations). The network equipment determines the recovery duration threshold information of the on-air video based on the recovery duration threshold model, and more accurate recovery duration threshold information can be obtained. Or for example, the network device stores a recovery duration threshold model in advance, where the recovery duration threshold model is obtained based on the recovery time counted by the user through historical click recovery operations on the recommended video category when the user watches videos in the past, and the network device determines the recovery duration threshold corresponding to the user according to the relevant information of the user, for example, the user usually clicks to recover the recommended video list immediately as soon as the recommended video list appears in the on-air video, and determines that the recovery duration information better meets the requirements of the user according to the historical records of the user, thereby improving the video watching experience of the user.

For example, a user holds a user device, a video application is installed in the user device, in response to a click operation of the user in the video application, the user device sends a play request about a target video to a network device, the network device returns the video to the user device, the user device plays the video in a full-screen play mode, meanwhile, the network device determines the recommendation time point information corresponding to the video-on-play on the user equipment (for example, 10% and 90% of the playing progress of the video-on-play is taken as the recommendation time point information), and recommended video information corresponding to the on-air video under the recommended time point information (for example, a recommended video list related to people in the on-air video is determined at 10% of the playing progress of the on-air video), and then the recommended video information is sent to the user equipment, and the user equipment displays the recommended video list related to people when the on-air video is played to the recommended time point information in a full screen mode.

In some embodiments, the method further includes, before step S101, step S103 (not shown), in step S103, the network device receives a recommended video acquisition request about the on-air video, which is sent by the user device, where the recommended video acquisition request includes video identification information of the on-air video; in step S101, the network device determines, according to the video identification information of the on-air video, recommendation time point information corresponding to the on-air video, and a recommendation video list corresponding to the on-air video under the recommendation time point information. For example, the user equipment downloads a video to be watched by the user in advance, and in response to a playing operation of the user on the video in the user equipment, the user equipment plays the current video offline, and in this case, the network equipment cannot acquire video information currently played in real time. The user equipment sends a recommended video acquisition request about the on-demand video to the network equipment, wherein the recommended video acquisition request comprises video identification information of the on-demand video, and the network equipment determines recommended time point information corresponding to the on-demand video based on the video identification information, for example, the recommended time point information comprises a time point (for example, at 10% or 90% of the playing progress of the on-demand video) suitable for presenting a recommended video list in the on-demand video determined based on big data, and a key video frame (for example, at a key episode in the on-demand video) of the on-demand video determined according to model training. And the network equipment determines a corresponding recommended video list according to the recommended time point information. For example, taking a recommended time point information as an example, at the time point, the network device determines the character information in the on-air video corresponding to the time point, and the network device determines a recommended video list related to the character information according to the character information (for example, a variety video, a tv show, or a video introducing the character, referred to by the character); or the network device determines the item information corresponding to the on-air video at the time point, and the network device determines a recommended video list related to the item information according to the item information (for example, the on-air video is a national treasure appreciation type video, a certain cultural relic is corresponding to the time point, and the network device may determine a video introducing the cultural relic as the recommended video list based on the cultural relic); the network device determines event information corresponding to the on-air video at the time point, and determines a recommended video list related to the event information according to the event information (for example, the on-air video includes history-type related videos, the time point corresponding to the recommended time point information is played for a certain history time, and the network device determines, based on the history event, a video introducing the history event as the recommended video list). Under the condition that the user equipment plays the current video offline, the recommended video list is presented based on the request of the user equipment, more video watching selections are given to the user, and the video watching experience of the user is improved. In some embodiments, the recommended video acquisition request further includes background music of the on-air video, where similarity information between the background music corresponding to one or more videos in the recommended video list and the background music of the on-air video is less than or equal to a predetermined similarity threshold. For example, in the case that the on-air video is played offline, the user equipment sends the background music of the on-air video to the network equipment, the network equipment acquires the background music fingerprint information of the on-air video through an audio fingerprint extraction algorithm, and queries in a database according to the background music fingerprint information to acquire a corresponding recommended video list, wherein the database stores a corresponding relationship between the background music fingerprint information and the recommended video list, and the similarity information between the background music corresponding to one or more videos in the recommended video list and the background music of the on-air video is less than or equal to a predetermined similarity threshold. In this case, a recommended video list with high similarity to the background sound of the on-air video is recommended to the user, so that the user is given a good push receiving experience. In some embodiments, the recommended video acquisition request further includes play progress information of the on-air video; in step S101, the network device determines one or more candidate recommendation time point information corresponding to the on-air video according to the video identification information of the on-air video; selecting and determining recommendation time point information corresponding to the on-demand video from the one or more candidate recommendation time point information according to the playing progress information, wherein the recommendation time point information is later than the playing progress information; and determining a recommended video list corresponding to the on-air video under the recommended time point information. For example, after the user equipment caches a video selected by the user, the user equipment plays the video in a full-screen form, and the user equipment sends a recommended video acquisition request about the on-air video to the network equipment, wherein the recommended video acquisition request includes video identification information (for example, a video ID) of the on-air video and playing progress information of the on-air video (for example, a ratio of the currently playing time of the on-air video to the total time of the video, or a time point of the currently playing video). For example, a video library of the network device stores a mapping relationship between a relevant video (e.g., a video ID) and one or more pieces of recommendation time point information corresponding to the relevant video, the network device determines one or more pieces of candidate recommendation time point information corresponding to the on-air video according to video identification information of the on-air video, and then, the network device selects, as the recommendation time point information, candidate recommendation time point information whose candidate recommendation time point information is later than the play progress information from the one or more pieces of candidate recommendation time point information according to the play progress information of the on-air video. Under the condition that the recommendation time point information is later than the playing progress information, the network equipment does not need to consider a recommendation video list corresponding to the time point information of which the recommendation time point information is earlier than the playing progress information, so that resources are saved, and the efficiency of the network equipment in determining the recommendation video list is improved.

In some embodiments, in step S102, the network device sends the recommended video list and the recommended time point information to the user device in real time, so that the recommended video list is presented above the on-air video. And under the condition that the network equipment sends the recommended video list and the recommended time point information to the user equipment in real time, providing a basis for presenting the recommended video list when the on-air video is played to the push time point subsequently.

In some embodiments, in step S102, step S102 includes step S1021 (not shown) and step S1022 (not shown), in step S1021, the network device sets a delayed sending timer, wherein a timing duration of the delayed sending timer is less than or equal to a time interval between the recommended time point information and the playing progress information; in step S1022, when the delayed sending timer expires, the network device sends the recommended video list to the user equipment, so that the recommended video list is presented above the on-air video. For example, in the case that the network device determines the recommendation time point information and the current playing progress information corresponding to the video playing, the network device sets a delayed sending timer, wherein the timing duration of the delayed sending timer is less than or equal to the time interval between the recommended time point information and the playing progress information, when the time delay sending timer expires, the network equipment sends the recommended video list to the user equipment as response information of the recommended video acquisition request, wherein the recommended video list is presented at the recommended time point information or at any time point between the playing progress information and the recommended time point information, which is different from the recommended video list being issued to the user equipment in real time, in this case, channel blockage can be mitigated while the recommended video information can be presented at an appropriate point in time. In some embodiments, in step S1022, when the delayed sending timer expires and the user equipment is still playing the on-air video, the network equipment sends the recommended video list to the user equipment, so that the recommended video list is presented above the on-air video. For example, the network device detects whether the user device is still playing the video through a heartbeat algorithm, and sends the recommended video list to the user device when the network device determines that the user device is still playing the video, so as to prevent the situation that the pushed video list is not matched with the currently played video after the user quits playing the video.

In some embodiments, none of the one or more candidate recommendation time point information is located between the play progress information and the recommendation time point information. For example, the recommendation time point information determined by the network device is later than the playing progress information, and the time points corresponding to other candidate time point information in the one or more candidate recommendation time point information corresponding to the on-air video are after the time points corresponding to the recommendation time point information, so that the recommendation time point information is ensured to be the time point closest to the playing progress information, and the recommended video lists corresponding to the other subsequent recommendation time point information are ensured to be sequentially presented.

In some embodiments, the method further includes, before step S101, step S104 (not shown), in step S104, the network device sends video stream information of the on-air video to the user device in response to a video playing request sent by the user device about the on-air video; in step S102, when the on-air video is played to the recommended time point information in the user equipment, the network equipment sends the recommended video list to the user equipment, so that the recommended video list is presented above the on-air video. For example, a user device sends a video playing request about current video information to a network device in real time, the network device sends video stream information of an on-air video to the user device in real time based on the video playing request, and in a case that the user device plays the current video information online, the network device may obtain playing progress information of the on-air video on the user device in real time (for example, the network device determines the current playing progress information of the on-air video on the user device by viewing a video stream of the on-air video sent to the user device) and a video ID of the on-air video, so as to determine recommendation time point information corresponding to the on-air video according to the video ID of the on-air video, and a recommendation video list corresponding to the on-air video under the recommendation time point information. And when the playing progress information reaches or approaches to the recommendation time point information, sending the recommended video list to the user equipment, and under the condition that the user watches videos online, sending the recommended video information by the network equipment in real time to enable the recommended video list to be displayed above the on-demand videos, so that the user is given more video watching choices.

Fig. 4 shows a method for providing a recommended video list at a user equipment according to an embodiment of the present application, where the method includes step S201, step S202, and step S203.

Specifically, in step S201, the user equipment acquires a playing video in the target application and presents the playing video, where the playing video is presented in a full-screen playing manner. For example, a user holds user equipment, the user equipment is provided with a target application, and the user equipment displays a currently played video in a full screen mode through the target application.

In step S202, the user equipment receives a recommended video list corresponding to the recommended time point information corresponding to the on-air video determined by the network equipment and returned by the network equipment. In some embodiments, the method further includes, before step S202, step S204 (not shown), in step S204, the user equipment sends a recommended video acquisition request about the on-air video to the network device, where the recommended video acquisition request includes video identification information and play progress information of the on-air video; in step S202, the user equipment receives recommendation time point information returned by the network equipment; and receiving a recommended video list corresponding to the on-air video under the recommended time point information, which is returned by the network equipment and determined by the network equipment. For example, the user equipment sends a recommended video acquisition request about the on-air video to the network equipment, wherein the recommended video acquisition request comprises video identification information of the on-air video, the network equipment determines recommended time point information corresponding to the on-air video based on the video identification information, for example, the recommended time point information comprises a time point (for example, at 10% or 90% of the on-air video playing progress) which is determined based on big data and is suitable for presenting a recommended video list in the on-air video, and a key video frame (for example, at a key episode in the on-air video) of the on-air video determined according to model training. And the network equipment determines a corresponding recommended video list according to the recommended time point information. In some embodiments, the recommended video list is based on multi-dimensional validation, including without limitation video features, user portrayal, recall algorithms, ranking models, and the like. For example, taking a recommended time point information as an example, at the time point, the network device determines the character information in the on-air video corresponding to the time point, and the network device determines a recommended video list related to the character information according to the character information (for example, a variety video, a tv show, or a video introducing the character, referred to by the character); or the network device determines the item information corresponding to the on-air video at the time point, and the network device determines a recommended video list related to the item information according to the item information (for example, the on-air video is a national treasure appreciation type video, a certain cultural relic is corresponding to the time point, and the network device may determine a video introducing the cultural relic as the recommended video list based on the cultural relic); the network device determines event information corresponding to the on-air video at the time point, and determines a recommended video list related to the event information according to the event information (for example, the on-air video includes history-type related videos, the time point corresponding to the recommended time point information is played for a certain history time, and the network device determines, based on the history event, a video introducing the history event as the recommended video list). On the basis that the network equipment determines the recommendation time point information of the on-air video, a basis is provided for a recommendation video list corresponding to the recommendation time point information presented in the on-air video by the subsequent user equipment, and meanwhile, the different recommendation video lists can be used for personalized information recommendation of the user. In some embodiments, the method further comprises, before step S202, step S205 (not shown), in step S205, the user equipment sends a recommended video acquisition request about the on-air video to the network equipment; receiving video stream information of the on-demand video sent by the network equipment; in step S202, when the on-air video is played to the recommendation time point information in the user equipment, the user equipment receives a recommended video list corresponding to the on-air video determined by the network equipment and returned by the network equipment under the recommendation time point information. For example, a user device sends a video playing request about current video information to a network device in real time, the network device sends video stream information of an on-air video to the user device in real time based on the video playing request, and in a case that the user device plays the current video information online, the network device may obtain playing progress information of the on-air video on the user device in real time (for example, the network device determines the current playing progress information of the on-air video on the user device by viewing a video stream of the on-air video sent to the user device) and a video ID of the on-air video, so as to determine recommendation time point information corresponding to the on-air video according to the video ID of the on-air video, and a recommendation video list corresponding to the on-air video under the recommendation time point information. And when the playing progress information reaches or approaches to the recommendation time point information, sending the recommended video list to the user equipment, and under the condition that the user watches videos online, sending the recommended video information by the network equipment in real time to enable the recommended video list to be displayed above the on-demand videos, so that the user is given more video watching choices. In some embodiments, in step S202, the user equipment receives a recommended video list returned by the network equipment and the recycling duration threshold information corresponding to the recommended video list. For example, the recovery duration threshold may be configured by the user equipment, or may be a basis for the network equipment to send to the user equipment, and providing a basis for automatically canceling presentation of the recommended video list after the time for presenting the recommended video list by the subsequent user equipment reaches the recovery duration threshold. In some embodiments, the method further includes step S206 (not shown), in step S206, the user equipment receives the recycling duration threshold information corresponding to the recommended video list returned by the network equipment; and if the time of the recommended video list presented on the broadcast video is greater than or equal to the recovery duration threshold information, the user equipment hides or partially hides the recommended video list. For example, in the case that the time that the recommended video list is presented in the broadcast video is greater than or equal to the recovery duration threshold information, the user equipment cancels presentation of the recommended video list on the broadcast video, and gives a complete on-broadcast video playing interface to the user, thereby avoiding affecting the video viewing experience of the user.

In step S203, the user equipment presents the recommended video list above the on-air video. The user does not need to manually click to present the recommended video list, so that the operation of the user is simplified, and meanwhile, the difference of the recommended video list can give personalized information recommendation to the user.

Fig. 5 is a schematic diagram for providing a recommended video list according to an embodiment of the present application, where a user holds a user device, a video-class application is installed in the user device, in response to a click operation of the user in the video application, the user device sends a play request about a related video to a network device, the network device returns the video to the user device, the user device plays the video in a full-screen play mode, and the network device determines recommendation time point information corresponding to an on-air video on the user device (for example, 10% of the on-air video play progress is used as the recommendation time point information), and recommended video information corresponding to the on-air video under the recommendation time point information, for example, determines a recommended video list (for example, related video 1, related video 2, and the like) related to the video under the progress at 10% of the on-air video play progress, and then sending the recommended video information to the user equipment, and displaying a recommended video list when the user equipment plays the current video to the recommended time point information in a full screen mode.

Fig. 6 shows a network device for providing a recommended video list according to an embodiment of the present application, which includes a one-module 101 and a two-module 102.

Specifically, the one-to-one module 101 is configured to determine recommendation time point information corresponding to an on-air video on user equipment, and a recommendation video list corresponding to the on-air video in the recommendation time point information. In some embodiments, the one-to-three module 101 includes a one-to-three module 1013 (not shown), or includes a one-to-one module 1011 (not shown) and a one-to-two module 1012 (not shown), and the one-to-three module 1013 is configured to query a query database for the recommended time point information and the recommended video list corresponding to the on-demand video, where the database stores the on-demand video, the recommended time point information, and the recommended video list; or, a module 1011 is configured to determine recommended time point information corresponding to a video being played on the user equipment; a second module 1012 for determining a recommended video list corresponding to the on-air video in the recommended time point information. The operation of determining the recommendation time point information corresponding to the on-air video on the user equipment and the recommendation video list corresponding to the on-air video under the recommendation time point information in a related manner is the same as or similar to that in the embodiment shown in fig. 3, and therefore, the description is omitted, and the description is incorporated herein by reference. In some embodiments, the module 1011 is configured to perform matching query in a recommendation time point database according to video identification information of an on-air video on user equipment, so as to obtain recommendation time point information corresponding to the on-air video; or inputting the description vector information of the on-demand video into a recommended time point model to obtain recommended time point information corresponding to the on-demand video, wherein the recommended time point model is obtained based on a large number of recommended time point samples, and each recommended time point sample comprises sample description vector information of a video sample and one or more pieces of recommended time point sample information in the video sample; alternatively, the first and second electrodes may be,

1) background music of the on-air video;

2) the picture style of the on-air video;

3) texture of the on-air video. The operation of obtaining the recommended time point information corresponding to the on-air video is the same as or similar to that of the embodiment shown in fig. 3, and therefore is not repeated here, and is included herein by reference.

In some embodiments, the one-to-two module 1012 is configured to determine, according to the user feedback information in the recommendation time point information, a recommended video list corresponding to the on-air video in the recommendation time point information. The operation of determining the recommended video list corresponding to the on-air video under the recommended time point information is the same as or similar to that of the embodiment shown in fig. 3, and therefore, the description is omitted, and the description is incorporated herein by reference. In some embodiments, the one-to-two module 1012 is configured to, when the user feedback information under the recommended time point information includes negative direction information, reset or invert at least one component information in the description vector information of the on-air video to obtain rectification description vector information corresponding to the on-air video, and determine a recommended video list corresponding to the on-air video under the recommended time point information according to the rectification description vector information, where the recommended video list matches the rectification description vector information; otherwise, determining a recommended video list corresponding to the on-air video under the recommended time point information according to the description vector information of the on-air video, wherein the recommended video list is matched with the description vector information. The operation of the user feedback information including the negative information related to the recommended time point information is the same as or similar to that in the embodiment shown in fig. 3, and therefore, the description is omitted, and the operation is included herein by reference. In some embodiments, the resetting or inverting at least one component information in the description vector information of the on-air video to obtain the corresponding rectification description vector information of the on-air video includes: when the user feedback information under the recommendation time point information contains negative information, resetting or negating at least one component information in the description vector information of the video in broadcasting according to the measurement information of the negative information to obtain the correction description vector information corresponding to the video in broadcasting. The operation of resetting or inverting at least one component information in the descriptor vector information of the on-air video to obtain the corresponding correction descriptor vector information of the on-air video is the same as or similar to the embodiment shown in fig. 3, and therefore, the description is omitted, and the description is incorporated herein by reference.

A second module 102, configured to send the recommended video list to the user equipment, so that the recommended video list is presented above the on-air video. And providing a basis for presenting the recommended video list when the video is played in a full screen mode by the subsequent user equipment. In some embodiments, a second module 102 is configured to send the recommended video list and the recovery duration threshold information corresponding to the recommended video list to the user equipment, so that the recommended video list is presented above the on-air video. The operation of sending the recommended video list and the recovery duration threshold information corresponding to the recommended video list to the user equipment is the same as or similar to that in the embodiment shown in fig. 3, and therefore, the description is omitted, and the description is incorporated herein by reference. In some embodiments, the network device further includes a fifth module 105 (not shown), where the fifth module 105 is configured to determine, according to the recommendation quantity information included in the recommended video list, the recovery duration threshold information corresponding to the recommended video list; or inputting the on-air videos into a recovery duration threshold model to determine recovery duration threshold information corresponding to the recommended video list, wherein the recovery duration threshold model is learned based on a large number of recovery duration samples of the recommended video list in the on-air videos, and each recovery duration sample comprises recovery duration counted by historical click recovery operations of other users on the recommended video list in the process of watching the on-air videos; or inputting the information of the user into a recovery duration threshold model to determine recovery duration threshold information corresponding to the recommended video list, wherein the recovery duration threshold model is obtained based on a large number of recovery duration samples, and each recovery duration sample comprises the recovery duration counted by the historical click recovery operation of the recommended video list corresponding to the historical videos in the process that the user watches the historical videos; a secondary module 102, configured to send the recommended video list and the recovery duration threshold information to the user equipment, so that the recommended video list is presented above the on-air video. The specific implementation manner of the fifth module 105 is the same as or similar to the embodiment of the step S105, and therefore, the detailed description is omitted, and the detailed implementation manner is included herein by reference.

Here, the specific implementation of the above one-module 101 and two-module 102 is the same as or similar to the embodiment of the steps S101 and S102 in fig. 3, and therefore, the detailed description is omitted, and the specific implementation is incorporated herein by reference.

In some embodiments, the network device further includes a third module 103 (not shown) before the first module 101, the third module 103 being configured to receive a recommended video acquisition request about the on-air video sent by the user device, where the recommended video acquisition request includes video identification information of the on-air video; a one-to-one module 101, configured to determine, according to the video identification information of the on-demand video, recommendation time point information corresponding to the on-demand video, and a recommendation video list corresponding to the on-demand video in the recommendation time point information. The specific implementation manner of the three modules 103 is the same as or similar to the embodiment of the step S103, and therefore, the detailed description is omitted, and the detailed implementation manner is included herein by reference. In some embodiments, the recommended video acquisition request further includes background music of the on-air video, where similarity information between the background music corresponding to one or more videos in the recommended video list and the background music of the on-air video is less than or equal to a predetermined similarity threshold. The operation of the related background music is the same as or similar to that of the embodiment shown in fig. 3, and therefore is not described herein again, and is incorporated herein by reference. In some embodiments, the recommended video acquisition request further includes play progress information of the on-air video; a one-to-one module 101, configured to determine, according to the video identification information of the on-air video, one or more candidate recommendation time point information corresponding to the on-air video; selecting and determining recommendation time point information corresponding to the on-demand video from the one or more candidate recommendation time point information according to the playing progress information, wherein the recommendation time point information is later than the playing progress information; and determining a recommended video list corresponding to the on-air video under the recommended time point information. The operation that the relevant recommended video acquisition request further includes the playing progress information of the on-air video is the same as or similar to the embodiment shown in fig. 3, and therefore, the description is omitted, and the operation is incorporated herein by reference.

In some embodiments, a second module 102 is configured to send the recommended video list and the recommended time point information to the user equipment in real time, so that the recommended video list is presented above the on-air video. The operation of sending the recommended video list and the recommended time point information to the user equipment in real time is the same as or similar to that in the embodiment shown in fig. 3, and therefore, the description is omitted, and the description is incorporated herein by reference.

In some embodiments, the second module 102 includes a second module 1021 (not shown) and a second module 1022 (not shown), the second module 1021, and the second module 1021, configured to set a delayed sending timer, where a timing duration of the delayed sending timer is less than or equal to a time interval between the recommended time point information and the playing progress information; a second module 1022, configured to send the recommended video list to the user equipment when the delayed sending timer expires, so that the recommended video list is presented above the on-air video. The operation of the related delay transmission timer is the same as or similar to that of the embodiment shown in fig. 3, and therefore, the description thereof is omitted, and the description thereof is incorporated herein by reference. In some embodiments, a second module 1022 is configured to send the recommended video list to the user equipment when the delayed sending timer expires and the user equipment is still playing the on-air video, so that the recommended video list is presented above the on-air video. The operation when the delayed sending timer expires is the same as or similar to that of the embodiment shown in fig. 3, and therefore, the detailed description is omitted, and the operation is incorporated herein by reference.

In some embodiments, none of the one or more candidate recommendation time point information is located between the play progress information and the recommendation time point information. The operation that the candidate recommendation time point information does not exist in the one or more pieces of candidate recommendation time point information and is located between the playing progress information and the recommendation time point information is the same as or similar to the embodiment shown in fig. 3, and therefore, the description is omitted, and the description is incorporated herein by reference.

In some embodiments, the network device further comprises a fourth module 104 (not shown) before the first module 101, the fourth module 104 being configured to send video stream information of the on-air video to the user device in response to a video playing request sent by the user device about the on-air video; a second module 102, configured to send the recommended video list to the user equipment when the on-air video is played to the recommended time point information in the user equipment, so that the recommended video list is presented above the on-air video. The specific implementation manner of the four modules 104 is the same as or similar to the embodiment of the step S104, and therefore, the detailed description is omitted, and the detailed implementation manner is included herein by reference.

Fig. 7 shows a user equipment for providing a recommended video list according to an embodiment of the present application, which includes a two-to-one module 201, a two-to-two module 202, and a two-to-three module 203.

Specifically, the first module 201 is configured to obtain a playing video in the target application and present the playing video, where the playing video is presented in a full-screen playing manner. For example, a user holds user equipment, the user equipment is provided with a target application, and the user equipment displays a currently played video in a full screen mode through the target application.

A second module 202, configured to receive a recommended video list corresponding to the recommendation time point information corresponding to the on-demand video determined by the network device and returned by the network device. In some embodiments, the user equipment further includes a second-fourth module 204 (not shown) before the second-second module 202, the second-fourth module 204 is configured to send a recommended video acquisition request about the on-air video to the network device, where the recommended video acquisition request includes video identification information and playing progress information of the on-air video; a second module 202, configured to receive recommendation time point information returned by the network device; and receiving a recommended video list corresponding to the on-air video under the recommended time point information, which is returned by the network equipment and determined by the network equipment. The specific implementation manner of the two or four modules 204 is the same as or similar to the embodiment of the step S204, and therefore, the detailed description is omitted, and the detailed implementation manner is incorporated herein by reference. In some embodiments, the user device further comprises a twenty-five module 205 (not shown) before the second module 202, the twenty-five module 205 is configured to send a recommended video acquisition request for the on-air video to the network device; receiving video stream information of the on-demand video sent by the network equipment; a second module 202, configured to receive, when the on-demand video is played to the recommendation time point information in the user equipment, a recommended video list corresponding to the on-demand video determined by the network equipment at the recommendation time point information and returned by the network equipment. The specific implementation manner of the twenty-five module 205 is the same as or similar to the embodiment of the step S205, and therefore, the detailed description is omitted, and the detailed implementation manner is included herein by reference. In some embodiments, the second module 202 is configured to receive a recommended video list returned by the network device and recovery duration threshold information corresponding to the recommended video list. An operation related to receiving the recommended video list returned by the network device and the recovery duration threshold information corresponding to the recommended video list is the same as or similar to that in the embodiment shown in fig. 4, and therefore, the description is omitted, and the operation is included herein by reference. In some embodiments, the user equipment further includes a twenty-six module 206 (not shown), where the twenty-six module 206 is configured to receive the recycling duration threshold information corresponding to the recommended video list returned by the network device; and if the time of the recommended video list presented on the broadcast video is greater than or equal to the recovery duration threshold information, hiding or partially hiding the recommended video list. The specific implementation manner of the twenty-six modules 206 is the same as or similar to the embodiment of the step S206, and therefore, the detailed description is omitted, and the detailed implementation manner is incorporated herein by reference.

A twenty-three module 203 for presenting the recommended video list above the on-air video. The user does not need to manually click to present the recommended video list, so that the operation of the user is simplified, and meanwhile, the difference of the recommended video list can give personalized information recommendation to the user.

Here, the examples of the specific implementation manners of the two-in-one module 201, the two-in-two module 202, and the two-in-three module 203 are the same as or similar to the embodiments of steps S201, S202, and S203 in fig. 4, and therefore, the detailed description is omitted, and the detailed description is incorporated herein by reference.

Fig. 8 shows a system apparatus for providing recommended video information according to an embodiment of the present application, the system including:

The present application also provides a computer readable storage medium having stored thereon computer code which, when executed, performs a method as in any one of the preceding.

The present application also provides a computer program product, which when executed by a computer device, performs the method of any of the preceding claims.

The present application further provides a computer device, comprising:

one or more processors;

a memory for storing one or more computer programs;

the one or more computer programs, when executed by the one or more processors, cause the one or more processors to implement the method of any preceding claim.

FIG. 9 illustrates an exemplary system that can be used to implement the various embodiments described herein;

in some embodiments, as shown in FIG. 9, the system 300 can be implemented as any of the devices in the various embodiments described. In some embodiments, system 300 may include one or more computer-readable media (e.g., system memory or NVM/storage 320) having instructions and one or more processors (e.g., processor(s) 305) coupled with the one or more computer-readable media and configured to execute the instructions to implement modules to perform the actions described herein.

For one embodiment, system control module 310 may include any suitable interface controllers to provide any suitable interface to at least one of processor(s) 305 and/or any suitable device or component in communication with system control module 310.

The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. Memory controller module 330 may be a hardware module, a software module, and/or a firmware module.

System memory 315 may be used, for example, to load and store data and/or instructions for system 300. For one embodiment, system memory 315 may include any suitable volatile memory, such as suitable DRAM. In some embodiments, the system memory 315 may include a double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

For one embodiment, system control module 310 may include one or more input/output (I/O) controllers to provide an interface to NVM/storage 320 and communication interface(s) 325.

For example, NVM/storage 320 may be used to store data and/or instructions. NVM/storage 320 may include any suitable non-volatile memory (e.g., flash memory) and/or may include any suitable non-volatile storage device(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).

NVM/storage 320 may include storage resources that are physically part of the device on which system 300 is installed or may be accessed by the device and not necessarily part of the device. For example, NVM/storage 320 may be accessible over a network via communication interface(s) 325.

Communication interface(s) 325 may provide an interface for system 300 to communicate over one or more networks and/or with any other suitable device. System 300 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and/or protocols.

For one embodiment, at least one of the processor(s) 305 may be packaged together with logic for one or more controller(s) (e.g., memory controller module 330) of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be packaged together with logic for one or more controller(s) of the system control module 310 to form a System In Package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with logic for one or more controller(s) of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with logic for one or more controller(s) of the system control module 310 to form a system on a chip (SoC).

In various embodiments, system 300 may be, but is not limited to being: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.). In various embodiments, system 300 may have more or fewer components and/or different architectures. For example, in some embodiments, system 300 includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an Application Specific Integrated Circuit (ASIC), and speakers.

It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, implemented using Application Specific Integrated Circuits (ASICs), general purpose computers or any other similar hardware devices. In one embodiment, the software programs of the present application may be executed by a processor to implement the steps or functions described above. Likewise, the software programs (including associated data structures) of the present application may be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.

In addition, some of the present application may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present application through the operation of the computer. Those skilled in the art will appreciate that the form in which the computer program instructions reside on a computer-readable medium includes, but is not limited to, source files, executable files, installation package files, and the like, and that the manner in which the computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Computer-readable media herein can be any available computer-readable storage media or communication media that can be accessed by a computer.

Communication media includes media by which communication signals, including, for example, computer readable instructions, data structures, program modules, or other data, are transmitted from one system to another. Communication media may include conductive transmission media such as cables and wires (e.g., fiber optics, coaxial, etc.) and wireless (non-conductive transmission) media capable of propagating energy waves such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied in a modulated data signal, for example, in a wireless medium such as a carrier wave or similar mechanism such as is embodied as part of spread spectrum techniques. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. The modulation may be analog, digital or hybrid modulation techniques.

By way of example, and not limitation, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory such as random access memory (RAM, DRAM, SRAM); and non-volatile memory such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic/ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disk, tape, CD, DVD); or other now known media or later developed that can store computer-readable information/data for use by a computer system.

An embodiment according to the present application comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform a method and/or a solution according to the aforementioned embodiments of the present application.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Claims

1. A method for providing a recommended video list on a network device side, wherein the method comprises:

2. The method of claim 1, wherein before determining the recommended time point information corresponding to the on-air video on the user equipment and the recommended video list corresponding to the on-air video under the recommended time point information, the method further comprises:

receiving a recommended video acquisition request about the on-air video, which is sent by the user equipment, wherein the recommended video acquisition request comprises video identification information of the on-air video;

the determining recommendation time point information corresponding to an on-air video on user equipment and a recommendation video list corresponding to the on-air video under the recommendation time point information includes:

and determining recommendation time point information corresponding to the on-air video according to the video identification information of the on-air video and a recommendation video list corresponding to the on-air video under the recommendation time point information.

3. The method of claim 2, wherein the request for obtaining recommended videos further includes background music of the on-air video, and wherein similarity information between the background music corresponding to one or more videos in the list of recommended videos and the background music of the on-air video is less than or equal to a predetermined similarity threshold.

4. The method of claim 2, wherein the recommended video acquisition request further includes play progress information of the on-air video;

determining one or more candidate recommendation time point information corresponding to the on-air video according to the video identification information of the on-air video;

selecting and determining recommendation time point information corresponding to the on-demand video from the one or more candidate recommendation time point information according to the playing progress information, wherein the recommendation time point information is later than the playing progress information;

and determining a recommended video list corresponding to the on-air video under the recommended time point information.

5. The method of claim 4, wherein the sending the list of recommended videos to the user device to cause the list of recommended videos to be presented over the on-air video comprises:

and sending the recommended video list and the recommended time point information to the user equipment in real time so that the recommended video list is presented above the on-air video.

6. The method of claim 3, wherein the sending the list of recommended videos to the user device to cause the list of recommended videos to be presented over the on-air video comprises:

setting a delayed sending timer, wherein the timing duration of the delayed sending timer is less than or equal to the time interval between the recommended time point information and the playing progress information;

when the delayed sending timer expires, sending the recommended video list to the user equipment so that the recommended video list is presented above the on-air video.

7. The method of claim 6, wherein said transmitting the list of recommended videos to the user device when the delayed transmission timer expires such that the list of recommended videos is presented above the on-air video comprises:

when the delayed sending timer expires and the user equipment is still playing the on-air video, sending the recommended video list to the user equipment so that the recommended video list is presented above the on-air video.

8. The method of claim 1, wherein before determining the recommended time point information corresponding to the on-air video on the user equipment and the recommended video list corresponding to the on-air video under the recommended time point information, the method further comprises:

in response to a video playing request about the on-air video sent by the user equipment, sending video stream information of the on-air video to the user equipment;

the sending the recommended video list to the user equipment so that the recommended video list is presented above the on-air video includes:

and when the on-air video is played to the recommended time point information in the user equipment, sending the recommended video list to the user equipment so that the recommended video list is presented above the on-air video.

9. The method according to any one of claims 1 to 8, wherein the determining recommendation time point information corresponding to the on-air video on the user equipment and the recommended video list corresponding to the on-air video under the recommendation time point information comprises:

inquiring the recommendation time point information and the recommendation video list corresponding to the on-air video in an inquiry database, wherein the database stores the on-air video, the recommendation time point information and the recommendation video list; alternatively, the first and second electrodes may be,

determining recommendation time point information corresponding to a video played on user equipment;

10. The method of claim 9, wherein the determining recommended time point information corresponding to a video being played on a user equipment comprises:

performing matching query in a recommendation time point database according to video identification information of an on-air video on user equipment to obtain recommendation time point information corresponding to the on-air video; alternatively, the first and second electrodes may be,

inputting the description vector information of the video-on-demand to a recommended time point model to obtain recommended time point information corresponding to the video-on-demand, wherein the recommended time point model is obtained based on a large number of recommended time point samples, and each recommended time point sample comprises sample description vector information of a video sample and one or more pieces of recommended time point sample information in the video sample; alternatively, the first and second electrodes may be,

background music of the on-air video;

the picture style of the on-air video;

texture of the on-air video.

11. The method according to claim 9 or 10, wherein the determining a recommended video list corresponding to the on-air video under the recommended time point information includes:

and determining a recommended video list corresponding to the on-air video under the recommendation time point information according to the user feedback information under the recommendation time point information.

12. The method of claim 11, wherein the determining a recommended video list corresponding to the on-air video at the recommended time point information comprises:

when the user feedback information under the recommendation time point information contains negative information, resetting or negating at least one component information in the description vector information of the video-on-air to obtain correction description vector information corresponding to the video-on-air, and determining a recommendation video list corresponding to the video-on-air under the recommendation time point information according to the correction description vector information, wherein the recommendation video list is matched with the correction description vector information; if not, then,

and determining a recommended video list corresponding to the on-air video under the recommended time point information according to the description vector information of the on-air video, wherein the recommended video list is matched with the description vector information.

13. The method of claim 12, wherein the resetting or inverting at least one component information in the on-air video's description vector information to obtain the on-air video's corresponding rectification description vector information comprises:

when the user feedback information under the recommendation time point information contains negative information, resetting or negating at least one component information in the description vector information of the video in broadcasting according to the measurement information of the negative information to obtain the correction description vector information corresponding to the video in broadcasting.

14. The method of any of claims 1-13, wherein the sending the list of recommended videos to the user device to cause the list of recommended videos to be presented over the on-air video comprises:

and sending the recommended video list and the recovery duration threshold information corresponding to the recommended video list to the user equipment, so that the recommended video list is presented above the on-air video.

15. The method of claim 14, wherein the method further comprises:

determining recovery duration threshold information corresponding to the recommended video list according to the recommended quantity information contained in the recommended video list; alternatively, the first and second electrodes may be,

inputting the on-air videos into a recovery duration threshold model to determine recovery duration threshold information corresponding to the recommended video list, wherein the recovery duration threshold model is obtained based on the learning of a large number of recovery duration samples of the recommended video list in the on-air videos, and each recovery duration sample comprises the recovery duration counted by other users in the process of watching the on-air videos through historical click recovery operations on the recommended video list; alternatively, the first and second electrodes may be,

inputting the information of the user into a recovery duration threshold model to determine recovery duration threshold information corresponding to the recommended video list, wherein the recovery duration threshold model is obtained based on a large number of recovery duration samples, and each recovery duration sample comprises recovery duration counted by historical click recovery operation of the recommended video list corresponding to the historical videos in the process that the user watches the historical videos.

16. A method for providing a recommended video list on a user equipment side, wherein the method comprises:

presenting the list of recommended videos over the on-air video.

17. The method of claim 16, wherein the method further comprises:

receiving recovery duration threshold information corresponding to the recommended video list returned by the network equipment;

and if the time of the recommended video list presented on the broadcast video is greater than or equal to the recovery duration threshold information, hiding or partially hiding the recommended video list.

18. A method for providing a recommended video list, wherein the method comprises:

19. An apparatus for providing a recommended video list, the apparatus comprising:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of any of claims 1 to 17.

20. A computer-readable medium storing instructions that, when executed by a computer, cause the computer to perform operations of any of the methods of claims 1-17.