WO2022179481A1

WO2022179481A1 - Resource issuing method, apparatus and device, and storage medium

Info

Publication number: WO2022179481A1
Application number: PCT/CN2022/077189
Authority: WO
Inventors: 杨典; 严冰
Original assignee: 北京字跳网络技术有限公司
Priority date: 2021-02-26
Filing date: 2022-02-22
Publication date: 2022-09-01
Also published as: CN114979679A

Abstract

Provided in embodiments of the present disclosure are a resource issuing method, apparatus and device, and a storage medium. The resource issuing method comprises: on the basis of a duration prediction model, determining an estimated play duration of a resource, which is not played, in the current feed stream; and on the basis of a result of comparison between the estimated play duration and a preset duration, determining an occasion of issuing a supplementary resource.

Description

Resource delivery method, apparatus, device and storage medium

This application claims the priority of the Chinese Patent Application No. 202110220305.3 filed with the China Patent Office on February 26, 2021, the entire contents of which are incorporated herein by reference.

technical field

The embodiments of the present disclosure relate to the technical field of streaming media processing, for example, to a resource delivery method, apparatus, device, and storage medium.

Background technique

With the development of the mobile Internet and the popularization of smart terminals, the short video business has ushered in explosive growth. In the information feed stream resource scenario, the server sends resources to the user's feed stream in batches. The server sends resources to the feed stream in real time according to user preferences, tags, historical behaviors, etc. for user consumption.

In order to improve the user's viewing experience and reduce the delay and the length of the first frame, the server usually sends the next batch of resources to the user before the resources in the current feed stream are consumed. For example, if there are less than 2 unplayed resources in the current feed stream, a new batch of resources is delivered to the client. The above resource delivery method cannot dynamically adjust the timing of video resource delivery.

SUMMARY OF THE INVENTION

Embodiments of the present disclosure provide a resource delivery method, apparatus, device, and storage medium to dynamically adjust the timing of video resource delivery.

In a first aspect, an embodiment of the present disclosure provides a method for delivering resources, including:

Determine the expected playback duration of the unplayed resources in the current information feed stream based on the duration prediction model;

Based on the comparison result between the predicted playback duration and the preset duration, the timing for delivering the supplementary resource is determined.

In a second aspect, an embodiment of the present disclosure further provides a resource delivery device, including:

The playback duration prediction module is set to determine the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model;

The delivery timing determination module is configured to determine the delivery timing of the supplementary resource based on the comparison result between the estimated playback duration and the preset duration.

In a third aspect, an embodiment of the present disclosure further provides a resource delivery device, including:

one or more processors;

memory, arranged to store one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors implement the resource delivery method according to any one of the embodiments of the present disclosure.

In a fourth aspect, an embodiment of the present disclosure further provides a medium, where the medium stores a computer program, and when the computer program is executed by a processor, implements the resource delivery method according to any one of the embodiments of the present disclosure.

Description of drawings

Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

1 is a flowchart of a method for delivering resources provided by an embodiment of the present disclosure;

2 is a schematic structural diagram of a duration prediction model provided by an embodiment of the present disclosure;

3 is a flowchart of a method for delivering resources provided by an embodiment of the present disclosure;

4 is a schematic diagram of interaction between a server and a client provided by an embodiment of the present disclosure;

5 is a schematic diagram of an apparatus for delivering resources provided by an embodiment of the present disclosure;

FIG. 6 is a structural diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed ways

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for the purpose of A more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not intended to limit the protection scope of the present disclosure.

It should be understood that the multiple steps described in the method embodiments of the present disclosure may be performed in different orders and/or in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this regard.

As used herein, the term "including" and variations thereof are open-ended inclusions, ie, "including but not limited to". The term "based on" is "based at least in part on." The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below.

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

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

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

First, words appearing in the present disclosure are explained.

The “feed” in the embodiment of the present disclosure may be a content aggregator that combines several news sources actively subscribed by the user to help the user continuously obtain the latest feed content. The feed is a Really Simple Syndication (RSS) The interface used to receive the source of this information.

The feed stream in the embodiment of the present disclosure, also referred to as an information stream, is a continuously updated information stream, which can push the information in the RSS to the user.

Among them, there are many forms of presentation of feed streams, including but not limited to: timeline-based presentation form timeline, smart sorting-based presentation form rank, among which timeline is the most typical feed stream presentation method, which is updated according to the feed stream content. Time sequence, the content is displayed to the user; rank is to calculate the weight of the feed stream content according to certain factors, so as to determine the sequence of the feed stream content display.

At present, there are mainly the following forms in which the server sends the feed stream resources to the user:

In the push mode, if a user updates the dynamic information, the server will push the dynamic information to each follower who follows the user, store the pushed resources in the server's cache pool and push it to each follower If the amount of information to be pushed is relatively large, it needs to occupy a large amount of server cache resources.

In the Pull mode, when the server determines that the user requests to access its own feed stream according to the user's active request, it will push the resource requested by the user in the feed stream to the user and cache it in the server's cache pool.

Pull mode saves a lot of resources, but users need to perform feed pull operation first when accessing their own content, which makes users may need to wait for a while, which increases the delay and the length of the first frame, which affects the user experience. For this reason, the server usually delivers the next batch of videos to the client before the video resources in the current feed stream are consumed. For example, if there are less than 4 unplayed video resources in the current feed stream, a new batch of video resources is delivered to the client. The drawback of the above method is that the timing of delivering video resources cannot be dynamically adjusted. For example: the remaining 4 unplayed resources may be content that the user does not like to watch, and the user may skip it and not play it. Since the fifth resource has not been delivered, when the user requests the fifth resource to be delivered, it will be delivered Loading may cause the playback of the 5th resource to freeze.

The embodiments of the present disclosure provide a resource delivery method, device, device, and storage medium, which utilize the result of comparing the estimated playback duration of unplayed resources in the feed stream with the preset duration to determine the delivery timing of supplementary resources, thereby realizing the feed The effect of dynamically delivering stream resources. When the playback time of the remaining resources is insufficient, resources are added to the feed stream in a timely manner. By adding resources to the feed stream in advance, the supplemented resources can also be preloaded and other strategies, reducing the phenomenon of subsequent resource playback freezes. The playback experience is improved. When the remaining playback time is sufficient, the distribution of resources is suspended, and relatively more real-time user behaviors and operations are collected to achieve better recommendation effects.

The resource delivery method, apparatus, device, and storage medium provided by the embodiments of the present disclosure will be described in detail below with reference to specific embodiments.

FIG. 1 is a flowchart of a method for delivering resources provided by an embodiment of the present disclosure. This embodiment is applicable to a situation in which video resources in a feed stream are dynamically delivered. The method can be executed by a resource delivery device. The apparatus can be implemented by means of software and/or hardware. The resource delivery method is applied to computer equipment. The computer device is installed with an application program that executes the feed stream playback, for example, the resource delivery method is performed by the client side that installs the feed stream playback application program.

It should be noted that the resource distribution method provided in this embodiment can be used on computer equipment, and can be considered to be executed by a resource distribution device integrated on the computer equipment, wherein the computer equipment can specifically include processing A computer device that includes a processor, memory, input device, and output device. Such as notebook computers, desktop computers, tablet computers and smart terminals.

The resource delivery method provided by the embodiments of the present disclosure can also be applied to other smart devices having the same functions as computer devices. The embodiments of the present disclosure describe the application scenarios and application devices of the above-mentioned resource delivery, but are not limited.

As shown in FIG. 1 , the method for delivering resources provided by this embodiment mainly includes steps S11 and S12.

S11. Determine, based on the duration prediction model, the expected playback duration of the unplayed resources in the current feed stream.

Among them, the feed stream can be a list of resources that can be continuously loaded by sliding down, and each feed entry is an independent resource. The resources in the feed stream can be text, images, videos, and even actionable cards.

The current feed stream refers to the feed stream that the server has pushed to the client and the client is playing. The current feed stream mainly includes broadcast resources, current resources and unplayed resources. Played resources refer to resources that have been played by the client and have been watched by the user; current resources refer to the resources that are being played by the client and are being watched by the user; unplayed resources refer to the resources that have not yet been played by the client.

The estimated playback duration of the unplayed resources in the current feed stream refers to the possible viewing time of the unplayed resources in the current feed stream. In practical applications, the total duration of unplayed resources may be 10 minutes, but due to the user's personal preference or network freezes and other reasons, if one chooses to skip one of the resources and does not play, then the actual playback duration of the unplayed resources will be less than The total duration of unplayed resources.

In order to more accurately determine the delivery timing of the next batch of feed stream resources, it is necessary to predict the possible playback duration of the unplayed resources to obtain the estimated playback duration of the unplayed resources in the current feed stream.

In one embodiment, the duration prediction model is obtained by pre-training, and the user's historical behavior, user-defined information, type of unplayed resources, number of unplayed resources, duration of each unplayed resource, and total duration of unplayed resources are input. To the duration prediction model, the duration prediction model outputs the estimated playback duration of the unplayed resources in the current feed stream.

In one embodiment, the duration prediction model is obtained by pre-training, and the user's historical behavior, user-defined information, unplayed resource types, the number of unplayed resources, and the duration of each unplayed resource are input into the duration prediction model, and the duration The prediction model outputs the expected playback ratio of unplayed assets in the current feed stream. Based on this ratio and the total duration of the unplayed resources, calculate the estimated playback duration of the unplayed resources. For example, the product of the ratio and the total duration of the unplayed resources may be determined as the expected playing duration of the unplayed resources.

In an embodiment of the present disclosure, a training method for a duration prediction model is provided, which mainly includes the following steps: using historical user behavior, user-defined information, type of broadcasted resources, number of broadcasted resources, total duration of broadcasted resources, The neural network model is trained based on characteristics such as the type of broadcast resources, the number of unbroadcast resources, the duration of each unbroadcast resource, and the total duration of unbroadcast resources, and the duration prediction model is obtained.

When using the duration prediction model to predict the expected playback duration of the unplayed resources in the current feed stream, the input of the duration prediction model is to use the user's historical behavior, user-defined information, the type of unplayed resources, the number of unplayed resources, and the number of unplayed resources for each unplayed resource. The resource duration and the total duration of unplayed resources. The output is the estimated playback duration of the unplayed resources in the current feed stream under the current user's behavior mode.

It should be noted that, since the output results of the duration prediction models in the above two embodiments are different, it is only the model parameters set in the model training process that are different. The output results of using the duration prediction model can be consistent with the output results of its training.

FIG. 2 is a schematic structural diagram of a duration prediction model provided by an embodiment of the present disclosure. As shown in FIG. 2 , the duration prediction model mainly includes an input layer, n intermediate layers and an output layer, and the feature parameters received by the input layer mainly include: User historical behavior, user-defined information, video type, and playback duration of broadcast resources, etc. After learning and prediction by n intermediate layers, the output layer outputs the expected playback duration of unplayed resources.

S12. Determine the timing for delivering the supplementary resource based on the comparison result between the predicted playback duration and the preset duration.

In this embodiment, the preset duration refers to a reference threshold determined according to the resource delivery time, and the preset duration may be set according to parameters such as network upload and download speed. The preset duration can be 10 seconds, 30 seconds, or 1 minute, etc. The specific value of the preset duration is not specifically limited in this embodiment.

Among them, the supplementary resources refer to the resources delivered by the server to the user and supplemented to the feed stream. The delivery timing refers to the time when the server delivers supplementary resources to the feed stream. Resource delivery means that the server sends the relevant information of the resource to the user, which can be the loading address and loading method of the resource.

For example, based on the comparison result between the estimated playback duration and the preset duration, it is determined whether the server needs to deliver supplementary resources at the current moment.

For example, if the expected playback duration is less than or equal to the preset duration, it is determined that the server will deliver supplementary resources to the feed stream of the client at the current moment. By supplementing video resources to the feed stream in advance, the supplemented resources can be preloaded, etc. strategy to reduce the phenomenon of subsequent resource playback freezes and other phenomena. If the expected playback duration is greater than the preset duration, it is determined that the unplayed resources in the feed stream at the current moment can be used by the user, and the server does not need to deliver supplementary resources to the feed stream of the user.

An embodiment of the present disclosure provides a method for delivering resources, which includes: determining an expected playback duration of unplayed resources in a current feed stream based on a duration prediction model; In the technical solution of the embodiment of the present disclosure, the result of comparing the estimated playback duration of the unplayed resources in the feed stream with the preset duration is used to determine the delivery timing of the supplementary resources, thereby realizing the effect of dynamically delivering the video resources of the feed stream. When the remaining playback time is insufficient, video resources are added to the feed stream in a timely manner. By adding video resources to the feed stream in advance, the supplemented videos can also be pre-loaded and other strategies, reducing subsequent video playback freezes and other phenomena. The playback experience is improved. When the remaining playback time is sufficient, the video resources will be temporarily released, and relatively more real-time user behaviors and operations will be collected to achieve a better recommendation effect.

On the basis of the above embodiments, the embodiments of the present disclosure refine the resource delivery method. FIG. 3 is a flowchart of a resource delivery method provided by the embodiments of the present disclosure. As shown in FIG. 3 , the embodiments of the present disclosure provide The resource distribution method mainly includes the following steps:

S21. Determine, based on the duration prediction model, the expected playback duration of the unplayed resources in the current feed stream.

In one embodiment, in response to detecting that the current resource starts playing, the expected playing duration of the unplayed resource in the current feed stream is determined based on the duration prediction model.

Wherein, the detection of the start of playback of the current resource may be the detection of the first frame of the current resource to start playback, and the detection of the start of playback of the current resource may also be or detected that the user executes an operation instruction corresponding to the start of the broadcast, such as detecting that the user clicks the start button. The user performs a slide-up or slide-down operation. It is also detected that the current resource starts to play and a resource switching instruction can also be detected. In this embodiment, only the manner in which the current resource is detected to start playing is described, but not limited.

In this embodiment, after it is detected that the current resource starts to play, the expected playback duration of the unplayed resources in the current feed stream is predicted, and the time point is specified for predicting the playback duration of the unplayed resources, so as to avoid frequent prediction, resulting in Waste of resources, can effectively save memory resources.

In one embodiment, determining the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model includes: acquiring historical user behavior and unplayed resource parameters, where the unplayed resource parameters include unplayed resource types, unplayed resource types, and unplayed resource parameters. The number, duration of unplayed resources, and total duration of unplayed resources; input the user's historical behavior and parameters of unplayed resources into the duration prediction model to obtain the expected playback duration of unplayed resources in the current feed stream.

Among them, the user's historical behavior refers to the relevant operation behavior of the user's previous viewing of historical resources, such as: liking, commenting, following, adding to favorites, downloading, and sharing. Resource type is a parameter that characterizes the resource category, such as action, funny, eating and broadcasting, beauty and so on.

For example, on the basis of the above embodiment, user-defined information can also be obtained while obtaining the user's historical behavior and parameters of unplayed resources. The user's historical behavior, user-defined information and unplayed resource parameters are input into the duration prediction model to obtain the expected playing duration of the unplayed resources in the current feed stream.

The above-mentioned user-defined information refers to the personal information disclosed by the user on the user terminal, for example, it may be a user's nickname, a user type, and the like.

For example, when using the duration prediction model to predict the expected playback duration of the unplayed resources in the current feed stream, the input of the duration prediction model is to use the user's historical behavior, user-defined information, the type of unplayed resources, the number of unplayed resources, each The duration of unplayed resources and the total duration of unplayed resources. Get the estimated playback time of the unplayed resources in the current feed stream under the behavior mode of the current user.

It should be noted that, for the training method and structure of the duration prediction model, reference may be made to the description in the foregoing embodiment, which is not limited in this embodiment.

In this embodiment, the multi-dimensional feature input pre-trained neural network model is used to obtain the technical solution of the estimated playback duration of the unplayed resources in the current feed stream under the behavior mode of the current user, which can improve the accuracy of the estimated playback duration.

S22. Determine, based on the duration prediction model, a comparison result between the expected playback duration of the unplayed resources in the current feed stream and the preset duration.

S23. Determine whether the expected playback duration is greater than the preset duration, and perform S24 based on the judgment result that the expected playback duration is greater than the preset duration, and perform S27 based on the judgment result that the expected playback duration is less than or equal to the preset duration.

S24. In response to determining that the expected playback duration is greater than a preset duration, forbid the delivery of supplementary resources.

In this embodiment, if the expected playback duration is greater than the preset duration, it indicates that the unplayed resources in the current feed stream are sufficient, and there is no need to request the server for resource delivery. At this time, the delivery of video resources is suspended, and the user terminal collects relatively more real-time user behavior operations to achieve a better recommendation effect.

S25. Detect the play state of the next resource.

In this embodiment, the next resource refers to the resource to be played after the current resource in the current feed stream is played. Detecting the playback state of the next resource can be understood as detecting whether the next resource starts playing in real time.

S26. In response to detecting that the playing state of the next resource is to start playing, return to executing S21.

If it is detected that the playback status of the next resource is starting to play, it indicates that the user starts to watch the next resource. At this time, the step of determining the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model is re-executed, and the prediction supplement is determined. The timing of resource delivery avoids frequent predictions and waste of resources, which can effectively save memory resources.

S27. In response to determining that the expected playback duration is less than or equal to the preset duration, trigger the delivery of the supplementary resource.

In one embodiment, triggering the start of delivery of the supplementary resource includes: sending a resource delivery request to the server, where the resource delivery request is used to request the server to deliver the resource.

In this embodiment, if the expected playback duration is less than or equal to the preset duration, it indicates that the remaining playback duration is insufficient, and new resources need to be added to the current feed stream. At this time, the client sends a resource delivery request to the server. The server delivers pre-prepared resources.

For example, when the client sends a resource delivery request to the server, the client can also send user behavior information to the server. The server selects multiple candidate videos from the massive videos according to the user behavior information, and scores and sorts the candidate videos. , select the personalized top N videos and send them to the current user's feed stream.

For example, after receiving the supplementary resources issued by the server, preloading the supplementary resources is performed, which reduces the phenomenon of subsequent playback jams and the like, and improves the overall playback experience.

In the technical solution of the embodiment of the present disclosure, the result of comparing the estimated playback duration of the unplayed resources in the feed stream with the preset duration is used to determine the delivery timing of the supplementary resources, thereby realizing the effect of dynamically delivering the video resources of the feed stream. When the remaining playback time is insufficient, video resources are added to the feed stream in a timely manner. By adding video resources to the feed stream in advance, the supplemented videos can also be pre-loaded and other strategies, reducing subsequent video playback freezes and other phenomena. The playback experience is improved. When the remaining playback time is sufficient, the video resources will be temporarily released, and relatively more real-time user behaviors and operations will be collected to achieve a better recommendation effect.

On the basis of the above-mentioned embodiment, another implementation is provided, in which a comparison result between the expected playback duration of the unplayed resources in the current feed stream and the preset duration is determined based on the duration prediction model.

In this embodiment, the comparison result between the estimated playback duration of the unplayed resources in the current feed stream and the preset duration is directly output by the duration prediction model.

It should be noted that, in the above embodiment, the output of the duration prediction model is the expected playback duration of the unplayed resources in the current feed stream, that is, a time value. The comparison between the expected playback duration and the preset duration is performed by the resource delivery device. In this embodiment, the estimated playback duration of the unplayed resources in the current feed stream is an intermediate variable in the duration prediction model, and the duration prediction model can directly compare the estimated playback duration of the unplayed resources in the current feed stream with the preset duration. , the output of the duration prediction model is a binary variable, that is, the output content is: "Yes" or "No". For example, in response to determining that the expected playback duration is less than or equal to a preset duration, the duration prediction model outputs "Yes", and in response to determining that the expected playback duration is greater than the preset duration, the duration prediction model outputs "No". For example, when the duration prediction model outputs "Yes", it triggers the delivery of supplementary resources, and when the duration prediction model outputs "No", the delivery of supplementary resources is prohibited.

In the embodiment of the present disclosure, the comparison result is directly output by the duration prediction model, which can reduce the computing time of the resource delivery device and improve the speed of determining the resource delivery timing.

In an application example, the unplayed resource is a video resource as an example for description. FIG. 4 is a schematic diagram of the interaction between the server and the user provided by the embodiment of the present disclosure. As shown in FIG. 4 , after the client detects that the video is started, Send the corresponding features to the trained duration prediction model for prediction, and determine whether the playback duration of the unplayed video in the feed stream is greater than the preset duration x seconds. If the playback duration of the unplayed video is longer than the preset duration x seconds, the logic for sending more videos will not be triggered, and the judgment will be made when the next video is played. If the playback duration of the unplayed video is less than or equal to the preset duration x seconds, the logic for delivering more videos is triggered, that is, the client sends a video delivery request to the server to request the server to deliver the video. At the same time, the client sends the user's historical behavior to the server, and the server selects multiple candidate videos from the massive videos according to the user's historical behavior, scores and sorts the candidate videos, and selects the personalized top N videos and sends them to the current user's in the feed stream.

Through the prediction and judgment process in this embodiment, the effect of dynamically delivering short video resources of the feed stream is achieved. When the remaining playing time is insufficient, video resources are added to the feed stream in a timely manner, and video resources are added to the feed stream in advance by adding video resources to the feed stream. , the supplemented video can be pre-loaded and other strategies, which reduce the phenomenon of subsequent video playback stuttering and other phenomena, and improve the overall playback experience; when the remaining playback time is sufficient, the delivery of video resources is postponed, and relatively more real-time user behaviors and operations are collected. achieve a better recommendation effect.

FIG. 5 is a schematic diagram of an apparatus for delivering resources provided by an embodiment of the present disclosure. This embodiment is applicable to the case of dynamically delivering video resources in a feed stream, and the apparatus may be implemented by means of software and/or hardware. . The resource issuing device is configured in computer equipment. The computer device is installed with an application program that executes the feed stream playback, for example, the resource delivery method is performed by the client side that installs the feed stream playback application program.

As shown in FIG. 5 , the resource delivery apparatus provided in this embodiment mainly includes a playback duration prediction module 51 and a delivery timing determination module 52 .

Wherein, the playback duration prediction module 51 is set to determine the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model;

The delivery timing determination module 52 is configured to determine the delivery timing of the supplementary resource based on the comparison result between the estimated playback duration and the preset duration.

An embodiment of the present disclosure provides a resource delivery device, which is mainly configured to perform the following operations: determine the expected playback duration of unplayed resources in the current feed stream based on a duration prediction model; based on the comparison result between the expected playback duration and the preset duration, Determine the timing for issuing supplementary resources. In the technical solution of the embodiment of the present disclosure, the result of comparing the estimated playback duration of the unplayed resources in the feed stream with the preset duration is used to determine the delivery timing of the supplementary resources, thereby realizing the effect of dynamically delivering the video resources of the feed stream.

In one embodiment, the method further includes: determining, based on the duration prediction model, a comparison result between the expected playback duration of the unplayed resources in the current feed stream and a preset duration, and performing a comparison based on the comparison result between the expected playback duration and the preset duration to determine the supplementary Operation of resource delivery timing.

In one embodiment, the playback duration prediction module 51 is configured to, in response to detecting that the current resource starts playing, determine the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model.

In one embodiment, the playback duration prediction module 51 is configured to obtain user historical behavior and unplayed resource parameters, where the unplayed resource parameters include unplayed resource type, number of unplayed resources, unplayed resource duration and unplayed resources total duration;

Input the user's historical behavior and unplayed resource parameters into the duration prediction model to obtain the expected playing duration of the unplayed resources in the current feed stream.

In one embodiment, the delivery timing determination module 52 is configured to trigger the supplementary resource to start delivering in response to determining that the expected playback duration is less than or equal to a preset duration; in response to determining that the expected playback duration is greater than the preset duration, Supplementary resource distribution is prohibited.

In one embodiment, in response to determining that the expected playback duration is greater than the preset duration, after prohibiting the delivery of the supplementary resource, the method further includes: detecting the playback state of the next resource; in response to detecting that the playback state of the next resource is to start playing , to perform the operation of determining the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model.

The resource distribution apparatus provided in this embodiment can execute the resource distribution method provided by any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the resource distribution method.

Referring next to FIG. 6 , it shows a schematic structural diagram of an electronic device (eg, a terminal device or a server in FIG. 6 ) 600 suitable for implementing an embodiment of the present disclosure. Terminal devices in the embodiments of the present disclosure may include, but are not limited to, such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (eg, mobile terminals such as in-vehicle navigation terminals), etc., and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in FIG. 6 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 6 , an electronic device 600 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 601 that may be loaded into random access according to a program stored in a read only memory (ROM) 602 or from a storage device 606 A program in a memory (RAM) 603 executes various appropriate actions and processes. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604 .

Typically, the following devices can be connected to the I/O interface 605: input devices 608 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 606 of a computer, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. Communication means 609 may allow electronic device 600 to communicate wirelessly or by wire with other devices to exchange data. Although FIG. 6 shows an electronic device 600 having various means, it should be understood that not all of the illustrated means are required to be implemented or available. More or fewer devices may alternatively be implemented or provided.

For example, the processes described above with reference to the flowcharts may be implemented as computer software programs according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication device 609, or from the storage device 608, or from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

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

In some embodiments, the client and the server can use any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) to communicate, and can communicate with digital data in any form or medium. Data communications (eg, communication networks) are interconnected. Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.

The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device:

Determine the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model;

Computer program code for performing operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and This includes conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through Internet connection).

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.

The units involved in the embodiments of the present disclosure may be implemented in a software manner, and may also be implemented in a hardware manner. Among them, the name of the unit does not constitute a limitation of the unit itself under certain circumstances.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical Devices (CPLDs) and more.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, a method, apparatus, device, and medium for delivering resources are provided, including:

According to one or more embodiments of the present disclosure, a method, apparatus, device, and medium for delivering resources are provided, further comprising:

Based on the duration prediction model, determine the comparison result between the expected playback duration and the preset duration of the unplayed resources in the current feed stream, and perform the operation of determining the delivery timing of the supplementary resource based on the comparison result between the expected playback duration and the preset duration.

According to one or more embodiments of the present disclosure, a resource delivery method, apparatus, device, and medium are provided, and the estimated playback duration of the unplayed resources in the current feed stream is determined based on a duration prediction model, including:

In response to detecting that the current resource starts to play, the expected playing duration of the unplayed resource in the current feed stream is determined based on the duration prediction model.

Obtaining the user's historical behavior and parameters of unplayed resources, where the parameters of unplayed resources include the type of unplayed resources, the number of unplayed resources, the duration of unplayed resources, and the total duration of unplayed resources;

According to one or more embodiments of the present disclosure, a method, apparatus, device, and medium for delivering resources are provided. Based on the comparison result between the estimated playback duration and the preset duration, determining the timing for delivering supplementary resources includes:

In response to determining that the expected playback duration is less than or equal to the preset duration, triggering the start of delivery of supplementary resources;

In response to determining that the expected playback duration is greater than the preset duration, the delivery of supplementary resources is prohibited.

According to one or more embodiments of the present disclosure, a method, device, device and medium for delivering resources are provided, and in response to determining that the expected playback duration is greater than the preset duration, after forbidding the issuance of supplementary resources, it also includes:

Detect the playback status of the next resource;

In response to detecting that the playing state of the next resource is to start playing, an operation of determining the expected playing duration of the unplayed resource in the current feed stream based on the duration prediction model is performed.

According to one or more embodiments of the present disclosure, a method, apparatus, device and medium for delivering resources are provided to trigger a video resource delivery operation, including:

Trigger the delivery of supplementary resources, including:

A resource delivery request is sent to the server, where the resource delivery request is used to request the server to deliver resources.

The foregoing descriptions are merely exemplary embodiments of the present disclosure and illustrative of the technical principles employed. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, and should also cover, without departing from the above-mentioned disclosed concept, the technical solutions formed by the above-mentioned technical features or Other technical solutions formed by any combination of its equivalent features. For example, a technical solution is formed by replacing the above features with the technical features disclosed in the present disclosure (but not limited to) with similar functions.

Additionally, although operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although the above discussion contains several implementation-specific details, these should not be construed as limitations on the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Claims

A method for delivering resources, comprising:

Determine the expected playback duration of the unplayed resources in the current information feed stream based on the duration prediction model;

Based on the comparison result between the predicted playback duration and the preset duration, the timing for delivering the supplementary resource is determined.
The method of claim 1, further comprising:

Based on the duration prediction model, a comparison result between the expected playback duration of the unplayed resources in the current feed stream and the preset duration is determined.
The method according to claim 1, wherein the determining the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model comprises:

In response to detecting that the current resource starts to play, the expected playing duration of the unplayed resource in the current feed stream is determined based on the duration prediction model.
The method according to claim 1 or 2, wherein the determining the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model comprises:

Obtaining the user's historical behavior and parameters of unplayed resources, where the parameters of unplayed resources include the type of unplayed resources, the number of unplayed resources, the duration of unplayed resources, and the total duration of unplayed resources;

The user's historical behavior and the unplayed resource parameters are input into the duration prediction model to obtain the expected playing duration of the unplayed resources in the current feed stream.
The method according to claim 1 or 2, wherein the determining the timing for delivering the supplementary resource based on the comparison result between the expected playback duration and the preset duration includes:

In response to determining that the expected playback duration is less than or equal to the preset duration, triggering the start of delivery of supplementary resources;

In response to determining that the expected playback duration is greater than the preset duration, distributing the supplementary resource is prohibited.
The method according to claim 5, wherein in response to determining that the expected playback duration is greater than a preset duration, after prohibiting the delivery of the supplementary resource, the method further comprises:

Detect the playback status of the next resource;

In response to detecting that the playing state of the next resource is to start playing, the operation of determining the expected playing duration of the unplayed resource in the current feed stream based on the duration prediction model is performed.
The method according to claim 5, wherein the triggering the start of issuing the supplementary resource comprises:

A resource delivery request is sent to the server, where the resource delivery request is used to request the server to deliver resources.
A resource distribution device, comprising:

The playback duration prediction module is set to determine the expected playback duration of the unplayed resources in the current feed stream based on the duration prediction model;

The delivery timing determination module is configured to determine the delivery timing of the supplementary resource based on the comparison result between the estimated playback duration and the preset duration.
A resource delivery device, including:

one or more processors;

memory, arranged to store one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors implement the resource delivery method according to any one of claims 1-7.
A computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, implements the resource delivery method according to any one of claims 1-7.