WO2022188618A1

WO2022188618A1 - Resource preloading method, apparatus and device, and storage medium

Info

Publication number: WO2022188618A1
Application number: PCT/CN2022/077202
Authority: WO
Inventors: 杨典; 严冰
Original assignee: 北京字跳网络技术有限公司
Priority date: 2021-03-12
Filing date: 2022-02-22
Publication date: 2022-09-15
Also published as: CN115086705A

Abstract

The present disclosure provides a resource preloading method, apparatus and device, and a storage medium. The resource preloading method comprises: determining, on the basis of a prediction model, a predicted playing amount of each unplayed resource in the current information stream; and for each unplayed resource, preloading the unplayed resource on the basis of the predicted playing amount.

Description

Resource preloading method, apparatus, device and storage medium

This application claims the priority of a Chinese patent application with application number 202110269706.8 filed with the China Patent Office on March 12, 2021, the entire contents of which are incorporated herein by reference.

technical field

The present disclosure relates to the technical field of streaming media processing, for example, to a resource preloading 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 feed stream video playback scenario, the current video is played and several videos to be watched in the future are loaded in advance. When the user slides to the next video, they can quickly see the first frame of the video, which reduces the duration of the first frame of video playback, and also The freezing rate during playback is reduced, which can greatly improve the user's viewing experience.

SUMMARY OF THE INVENTION

The present disclosure provides a resource preloading method, apparatus, device, and storage medium, so as to provide users with a dynamic preloading scheme, save unnecessary traffic waste, and improve user experience.

In a first aspect, an embodiment of the present disclosure provides a resource preloading method, including:

Determine the expected playback volume of each unplayed resource in the current information stream based on the prediction model;

For each unplayed resource, the unplayed resource is preloaded based on the expected play amount.

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

The expected playback volume determination module is set to determine the expected playback volume of each unplayed resource in the current information stream based on the prediction model;

The preloading module is configured to, for each unplayed resource, preload the unplayed resource based on the expected playing amount.

In a third aspect, an embodiment of the present disclosure further provides a resource preloading 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 preloading 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 computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the embodiments of the present disclosure is implemented The resource preloading method.

Description of drawings

FIG. 1 is an example diagram of an application scenario provided by an embodiment of the present disclosure;

FIG. 2 is a flowchart of a resource preloading method provided by an embodiment of the present disclosure;

3 is a flowchart of a resource preloading method provided by an embodiment of the present disclosure;

4 is a structural diagram of a prediction model provided by an embodiment of the present disclosure;

5 is a flowchart of a video preloading provided by an embodiment of the present disclosure;

FIG. 6 is a structural diagram of a resource preloading apparatus provided by an embodiment of the present disclosure;

FIG. 7 is a structural diagram of a resource preloading device provided by an embodiment of the present disclosure.

Detailed ways

Embodiments of the present disclosure will be described below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. 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.

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.

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 or interdependence of functions performed by these devices, modules or units relation.

Modifications of "a" and "a plurality" mentioned in the present disclosure are illustrative and not restrictive, and should be read as "one or more" unless the context dictates otherwise.

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.

The words appearing in this disclosure are explained.

The information flow in the embodiment of the present disclosure, also referred to as a feed flow, is a continuously updated information flow, which can push information in a Really Simple Syndication (RSS) to a user.

The “feed” in this embodiment of the present disclosure may be a content aggregator formed by combining multiple news sources actively subscribed by the user to help the user continuously obtain the latest feed content. The feed is used in RSS to receive the information source. interface.

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 some factors, so as to determine the sequence of the feed stream content display.

In the playback scenario of short video feed streams, the commonly used preloading method is: the client preloads all videos indiscriminately, that is, all videos are preloaded with the same amount of playback. But different users have different needs for preloading. Therefore, in the playback scenario of complex short video feed streams, indiscriminate video preloading can easily lead to wasted traffic and degraded user experience.

In the feed stream playback scenario, the current resource is played and several resources to be watched in the future are loaded in advance. When the user slides to the next resource, he can quickly see the first frame of the resource, which reduces the duration of the first frame of resource playback and reduces the It can greatly improve the user's viewing experience by reducing the freezing rate during playback. In the playback scenario of feed stream, the commonly used preloading method is: the client preloads all videos indiscriminately, that is, all videos are preloaded with the same amount of playback. However, different users have different requirements for preloading. For example, some users will selectively skip part of the video. Excessive preloading of this part of the video results in wasted traffic cost and download time, and takes up preloading. The time of other videos; sometimes the preloaded cache is not large enough, and when the user's network fluctuates, it is easy to cause video freezes; the user's behavior of watching videos may also change with network conditions, recommendation effects, and the user's current state. Therefore, in the playback scenario of complex short video feed streams, indiscriminate video preloading can easily lead to wasted traffic and degraded user experience.

In order to solve the above problems, the embodiments of the present disclosure provide a resource preloading method, apparatus, device, and storage medium, which dynamically provide users with a personalized preloading scheme by intelligently predicting the playback amount of unplayed resources, saving time and money. Necessary traffic is wasted to improve user experience.

FIG. 1 is an example diagram of an application scenario provided by an embodiment of the present disclosure. As shown in FIG. 1, the client 101 is configured to execute the resource preloading method described in any embodiment of the present disclosure, and the client 101 can send resource preloading information to the server 102 through the network, and preload the resources provided by the server 102 in advance , and play the preloaded assets through the output device.

Wherein, the above-mentioned output device may be an output device built into the client 101, such as a touch screen, etc.; it may also be an external output device connected to the client 101 through a communication line, such as a projector, a digital TV ( television, TV), etc.

In this embodiment, the client 101 is described by taking a computer device as an example, and the computer device may be a computer device including a processor, a memory, an input device, and an output device.

The resource preloading method provided by the embodiments of the present disclosure may also be applied to other smart devices having the same functions as computer devices. The embodiments of the present disclosure describe, but not limit, the application scenarios and application devices of the above resource preloading.

Optionally, the client in this embodiment of the present disclosure may include, but is not limited to, such as a mobile phone, a notebook computer, a digital broadcast receiver, a personal digital assistant (Personal Digital Assistant, PDA), a tablet computer (Portable Android Device, PAD), Portable Multimedia Player (PMP), mobile terminals such as in-vehicle terminals (such as in-vehicle navigation terminals), etc., and stationary terminals such as digital TVs, desktop computers, and the like.

Optionally, a typical scenario to which the embodiments of the present disclosure are applied is a feed media stream, that is, when a user watches the current resource, he can switch to the next resource by sliding down, or switch to the upper resource by sliding up. a resource.

Optionally, this embodiment is applied to another typical scenario where a mobile phone window displays multiple resources, and the user can browse different resources by scrolling up and down, and click to view different resources.

The following describes the resource preloading method, apparatus, device, and storage medium provided by the embodiments of the present disclosure with reference to the embodiments.

FIG. 2 is a flowchart of a method for resource preloading provided by an embodiment of the present disclosure. This embodiment is applicable to the case of dynamically preloading video resources in a feed stream. The method may be executed by a resource preloading device. The apparatus can be implemented by means of software and/or hardware. The resource preloading method is applied to the client.

In this embodiment, a feed stream resource playback application may be installed in the client, and the feed stream resource playback application may be used to play the resource. Exemplarily, a resource preloading device may be added to the feed stream resource playback application, which is used to execute any of the resource preloading methods provided in the embodiments of the present disclosure.

As shown in FIG. 2 , the resource preloading method provided by this embodiment includes steps S11 and S12.

S11. Determine, based on the prediction model, the expected playback amount of each unplayed resource in the current information stream.

Among them, the information flow can be a list of resources that can be continuously slid down and loaded continuously, also known as feed flow, and each feed entry is an independent resource. Wherein, the resource may be audio, video, picture, text, actionable card, any combination of any of the above two or more, and the like.

The current feed stream refers to the feed stream that the server has delivered 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 expected play volume may be the predicted play volume of resources that the user may want to watch. The expected playing amount may be the expected playing number of bytes, for example, the expected playing amount is 2 megabytes (Megabytes, M). The expected playback volume may also be the expected playback duration, for example, the expected playback volume is 10 seconds. The expected playback volume may also be expressed in other metrics, which are not limited in this application.

The expected playback volume of each unplayed resource can be understood as each unplayed resource has its corresponding expected playback volume, and the expected playback volume corresponding to each unplayed resource may be the same or different. In this embodiment, no limitation is imposed.

In one embodiment, a prediction model is obtained through pre-training, and features such as playback-related historical information, user type, video type, etc. are input into the prediction model, and the prediction model outputs the expected playback volume of each unplayed resource in the current feed stream .

In one embodiment, a prediction model is obtained through pre-training, and features such as playback-related historical information, user types, and video types are input into the prediction model, and the prediction model outputs the expected playback ratio of each unplayed resource in the current feed stream. ; Determine the expected playback amount based on the expected playback ratio. For each unplayed resource, the product of the expected play ratio and the unplayed resource amount may be determined as the expected play amount of the unplayed resource.

Since in the above two embodiments, the output results of the prediction models are different, it is only the model parameters set in the model training process that are different. The output results when using the prediction model are consistent with the output results of its training.

In an embodiment of the present disclosure, a method for training a prediction model is provided, which includes the following steps: training a neural network model using features such as a user's previous viewing behavior and operation, user type, and video type to obtain a prediction model.

S12. For each unplayed resource, preload the unplayed resource based on the expected play amount.

In this embodiment, the preloading of the unplayed resources based on the expected playback volume includes: determining preloading configuration information based on the expected playback volume, and preloading the unplayed resources based on the preloading configuration information.

In one embodiment, when it is predicted that the playback duration of the user's subsequent resources is very short, the size of the preloaded resources can be selectively reduced, for example, the size of 300 (Kilobyte, KB) is sufficient, thus achieving the purpose of saving traffic. Or when it is predicted that the user does not play the resource for a long time, the size of the preloaded resource can be selectively increased, for example, 2 megabytes (Megabytes, MB), so as to achieve the purpose of reducing the freeze during the playback process.

The preloading order of each unplayed resource can be determined according to the order of unplayed resources in the feed stream. The priority corresponding to each unplayed resource may also be calculated, and the preloading order of the unplayed resources may be determined based on the priority. In this embodiment, only the preloading sequence of the unplayed resources is described, but not limited.

An embodiment of the present disclosure provides a resource preloading method, which includes: determining an estimated play amount of each unplayed resource in a current information stream based on a prediction model; and for each unplayed resource, preloading the unplayed resource based on the predicted play amount. In the technical solutions of the embodiments of the present disclosure, by intelligently predicting the playback volume of unplayed resources, a personalized preloading solution is dynamically provided to users, which saves unnecessary traffic waste and improves user experience.

On the basis of the above-mentioned embodiment, the embodiment of the present disclosure describes a resource preloading method. FIG. 3 is a flowchart of a resource preloading method provided by the embodiment of the present disclosure. As shown in FIG. The resource preloading method mainly includes the following steps.

S21. Detect whether the loading of the current playback resource is completed.

In this embodiment, the currently playing resource may be understood as the resource currently being played on the current display screen of the client. Loading complete means that all the content of the currently playing resource has been cached to the client.

In one embodiment, the detection of whether the loading of the current playback resource is completed may be to detect whether an identifier of the completion of the loading of the current playback resource is received, and the identifier may be generated by the client itself or sent by the server.

In one embodiment, the detection of whether the loading of the current playback resource is completed may also be to detect whether the loaded byte length of the current playback resource is equal to the total byte length of the current playback resource.

In one embodiment, the detection of whether the loading of the current playback resource is completed may also be to detect whether the loaded duration of the current playback resource is equal to the total duration of the current playback resource.

In this embodiment, only the method for whether the resource is loaded is described, but not limited, and other methods may be selected according to the actual situation to determine whether the resource is loaded.

S22. After detecting that the current playback resource is loaded, determine the expected playback amount of each unplayed resource in the current information stream based on the prediction model.

In one embodiment, if an indication that the loading of the current playback resource is completed is received, it is determined that the loading of the current resource is completed.

In one embodiment, it is determined that the loading of the current resource is completed by detecting that the loaded byte length of the current playback resource is equal to the total byte length of the current playback resource.

In one embodiment, it is determined that the loading of the current resource is completed when it is detected that the loaded duration of the current playback resource is equal to the total duration of the current playback resource.

Before it is detected that the current resource is loaded, it is detected that the user switches to a new resource, that is, the current playback resource is updated, and the switched resource is used as the current playback resource, and an operation of detecting whether the current playback resource is loaded is performed.

In this embodiment, the resource preloading operation is performed only after the current playback resource is downloaded. In this way, the stuck phenomenon of the current playback resource can be avoided, and the user experience can be improved.

S23. For each unplayed resource, while preloading the unplayed resource based on the expected playback amount, detect whether the current user switches to a new resource.

In this embodiment, the new resource refers to other resources other than the current playback resource. Detecting whether the current user switches to a new resource may be detecting whether the user inputs a switching instruction, or detecting whether the player has changed the playback resource information.

The switching instruction may be a user's click instruction on the client terminal, a sliding instruction, an upward sliding instruction, a left sliding instruction, or a right sliding instruction, and the like. The playback resource information includes one or more of the following: publisher information of the playback resource, name of the playback resource, Internet Protocol (IP) address of the playback resource, data packets of the playback resource, and the like.

S24. After the current user switches to the new resource, use the new resource as the current playback resource, and return to executing S21.

When the current user switches to the new resource, it may be detected that the user inputs a switching instruction, or it may be detected that the player has changed the playback resource information.

After the current user switches to the new resource, the new resource is used as the current playback resource, and the operation of detecting whether the current playback resource is loaded is completed.

In this embodiment, downloading the user's current playback resource has the highest priority, and whenever the user switches to a new resource for playback, the preloading operation is performed first after the current playback resource is downloaded. In this way, the stuck phenomenon of the current playback resource can be avoided, and the user experience can be improved.

On the basis of the foregoing embodiments, the embodiments of the present disclosure provide two methods for determining the expected playback amount of each unplayed resource in the current information stream.

In one embodiment, determining the expected playback volume of each unplayed resource in the current information stream based on the prediction model includes: determining the current user type based on the prediction model; Relationships determine the expected amount of playback for each unplayed asset in the current stream.

In this embodiment, the user type may be understood as a type corresponding to a user who plays a specified type of resource for a preset duration.

There is a one-to-one correspondence between the pre-stored user types and the playback volume, but different user types may correspond to the same playback volume.

In this embodiment, after the user type is determined, the corresponding relationship between the user type and the playback volume is searched based on the current user type, and the playback volume corresponding to the current user type is determined as the expected playback volume.

In one embodiment, determining the expected playback volume of each unplayed resource in the current information stream based on the prediction model includes: determining the current user type based on the prediction model; The relationship determines the expected playback ratio of each unplayed resource in the current information stream; for each unplayed resource, the expected playback amount is determined based on the expected playback ratio.

In this embodiment, after the user type is determined, the corresponding relationship between the user type and the playback ratio is searched based on the current user type, and the playback ratio corresponding to the current user type is determined. The playback ratio can be understood as the ratio between the played duration of a type of resource and the total duration of the resource.

In this embodiment, after the playback ratio is obtained, the product of the total duration of the unplayed resources and the playback ratio is used as the expected playback duration of the unplayed resource; or, after the playback ratio is obtained, the total duration of the unplayed resources The product of the number of bytes and the playback ratio is used as the expected number of playback bytes of the unplayed resource.

Determining the current user type based on the prediction model includes: acquiring playback-related historical information and resource information, wherein the resource information includes the playback duration of each played resource, each type of unplayed resource, and the duration of each unplayed resource; The play-related historical information and resource information are input into the prediction model to obtain the current user type.

The resource information includes the playback duration of each broadcasted resource, the type of each unplayed resource, and the duration of each unplayed resource; the playback-related historical information refers to the relevant information obtained when the client plays the historical resource, for example: history The number of likes of resources, comments of historical resources, etc. The play-related historical information may also include user-provided preference information.

The current user type is obtained by inputting the playback-related historical information and resource information into the prediction model, which avoids redundant user type determination steps, can conveniently and quickly determine the current user type, and improves the running speed of the device.

inputting the playback-related historical information and resource information into the prediction model to obtain the current user type, including: inputting the playback-related historical information and resource information into the prediction model to obtain multiple user type probabilities, The user type probability is the probability that the current user belongs to one type of user; the user type corresponding to the largest user type probability among the multiple user type probabilities is determined as the current user type.

In this embodiment, the prediction model outputs multiple user type probabilities, compares the multiple user type probabilities, or sorts them to obtain the maximum user type probability, and determines the user type corresponding to the maximum user type probability as the current user type.

In this embodiment, the current user type is determined according to multiple user type probabilities output by the prediction model, which can improve the accuracy of user type determination.

FIG. 4 is a schematic structural diagram of a prediction model provided by an embodiment of the present disclosure. As shown in FIG. 4 , the prediction model mainly includes an input layer, n intermediate layers and an output layer, and the characteristic parameters received by the input layer mainly include: , the playback duration of each broadcasted resource, the type of each unplayed resource, and the duration of each unplayed resource, etc. After learning and prediction by n intermediate layers, the output layer outputs the probability that the user belongs to the nth category of video. n is any value between 1, 2...k, where k is the total number of all user types.

The probability values output by the prediction model are compared, and the user type corresponding to the maximum probability is determined as the current user type.

In this embodiment, the technical solution of inputting multi-dimensional features into a pre-trained neural network model to obtain the estimated playback duration of the unplayed resources in the current feed stream under the current user's behavior mode can improve the accuracy of determining the estimated playback duration.

In an applicable example, the unplayed resource is an unplayed video resource as an example for description. FIG. 5 is a flowchart of a video preloading provided by an embodiment of the present disclosure. As shown in FIG. 5 , when a user starts to watch a video, the video currently being played by the user is preferentially downloaded. When entering the next video, the next video will be regarded as the currently playing video, and the user's currently playing video will be downloaded first. If the user does not enter the next video after the download of the currently-playing video is completed, the playback-related historical information and video information are fed into the trained prediction model to predict the expected playback volume. Select the preloading configuration according to the prediction result of the prediction model, and start the video preloading. During the video preloading process, if the user switches to the next video, the next video will be regarded as the currently playing video, and the user's currently playing video will be downloaded first. Or, until the video preload ends.

In the above process, downloading the currently playing video of the user has the highest priority, and whenever the user switches to a new video for playback, the preloading operation is performed after the currently playing video is downloaded first.

Compared with indiscriminate preloading, the video preloading method provided by the embodiments of the present disclosure is more personalized. For example, the preloading in the related art loads the subsequent video with a size of 1MB indiscriminately. With the video preloading method provided by the embodiment of the present disclosure, when it is predicted that the user will play a video with a very short duration, it is only necessary to load the subsequent video with a size of 300KB. The size is enough to save traffic, or when the user predicts that the subsequent video playback will be long, you can selectively increase the preload size, such as 2MB, to reduce the freeze during playback.

FIG. 6 is a structural diagram of a resource preloading apparatus provided by an embodiment of the present disclosure. This embodiment is applicable to the case of dynamically preloading video resources in a feed stream, and the resource preloading apparatus can be preloaded through software and/or hardware. way to achieve. The resource preloading method is applied to the client.

As shown in FIG. 6 , the resource preloading apparatus provided in this embodiment mainly includes an expected playback amount determination module 61 and a preloading module 62 .

The expected playback volume determination module 61 is configured to determine the expected playback volume of each unplayed resource in the current information stream based on the prediction model;

The preloading module 62 is configured to, for each unplayed resource, preload the unplayed resource based on the expected playing amount.

An apparatus for resource preloading provided by an embodiment of the present disclosure is configured to perform the following operations: determine the expected playback volume of each unplayed resource in a current information stream based on a prediction model; for each unplayed resource, perform the following operations on the Preload the broadcast resources. In the technical solutions of the embodiments of the present disclosure, by intelligently predicting the playback volume of unplayed resources, a personalized preloading solution is dynamically provided to users, which saves unnecessary traffic waste and improves user experience.

In one embodiment, the estimated playback amount determination module 61 is configured to detect whether the current playback resource is loaded; after detecting that the current playback resource is loaded, it executes a prediction model to determine each unplayed resource in the current information stream. Estimated playback steps.

In one embodiment, the apparatus includes a switch detection module, configured to detect whether the current user switches to a new resource while preloading the unplayed resource based on the expected playback amount;

The expected playback amount determination module 61 is configured to use the new resource as the current playback resource after the current user switches to the new resource, and perform the step of detecting whether the current playback resource is loaded.

In one embodiment, the expected playback amount determination module 61 includes:

A user type determination unit, set to determine the current user type based on the prediction model;

The expected playback amount determination unit is configured to determine the expected playback amount of each unplayed resource in the current information stream based on the current user type and the pre-stored correspondence between the user type and the playback amount.

The expected playback ratio unit is set to determine the expected playback ratio of each unplayed resource in the current information stream based on the corresponding relationship between the current user type and the pre-stored user type and playback ratio;

The expected playback amount determination unit is configured to determine the expected playback amount based on the expected playback ratio for each unplayed resource.

In one embodiment, the user type determination unit is configured to obtain play-related historical information and resource information; input the play-related historical information and resource information into the prediction model to obtain the current user type, wherein the The resource information includes the playing duration of each played resource, the type of each unplayed resource, and the duration of each unplayed resource.

In one embodiment, inputting the play-related historical information and resource information into the prediction model to obtain the current user type, including:

Inputting the playback-related historical information and resource information into the prediction model to obtain multiple user type probabilities, where the user type probabilities are the probabilities that the current user belongs to one type of user;

The user type corresponding to the largest user type probability among the multiple user type probabilities is determined as the current user type.

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

Referring next to FIG. 7 , it shows a schematic structural diagram of a resource preloading device (eg, a terminal device or a server in FIG. 7 ) 700 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, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs, PADs, PMPs, in-vehicle terminals (eg, in-vehicle navigation terminals), etc., as well as mobile terminals such as digital TV, desktop Stationary terminals for computers, etc. The electronic device shown in FIG. 7 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. 7 , the electronic device 700 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 701, which may be based on a program stored in a read-only memory (Read-only Memory, ROM) 702 or from a storage device 708 programs loaded into Random Access Memory (RAM) 703 to perform various appropriate actions and processes. In the RAM 703, various programs and data necessary for the operation of the electronic device 700 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An Input/Output (I/O) interface 705 is also connected to the bus 704 .

The following devices may be connected to the I/O interface 705: Input devices 706 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a Liquid Crystal Display (LCD), speakers output device 707 , vibrator, etc.; storage device 708 including, for example, magnetic tape, hard disk, etc.; and communication device 709 . Communication means 709 may allow electronic device 700 to communicate wirelessly or by wire with other devices to exchange data. Although FIG. 7 shows an electronic device 700 having various means, it is not required to implement or have all of the illustrated means. More or fewer devices may alternatively be implemented or provided.

According to embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. 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 709, or from the storage device 708, or from the ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

The computer-readable medium described above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium 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. Computer readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), Flash memory, optical fiber, portable Compact Disc Read-Only Memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. 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 . The program code embodied on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: electric wire, optical fiber cable, radio frequency (RF), etc., or any suitable combination of the above. The storage medium may be a non-transitory storage medium.

In some embodiments, the client and server can use any currently known or future developed network protocols such as HyperText Transfer Protocol (HTTP) to communicate, and can communicate with digital data in any form or medium. Data communications (eg, communications networks) are interconnected. Examples of communication networks include Local Area Networks (LANs), Wide Area Networks (WANs), 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 developed networks.

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:

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. Where a remote computer is involved, the remote computer may be connected to the user computer through any kind of network, including a LAN or WAN, or may be connected to an external computer (eg, using an Internet service provider to connect through the Internet).

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. In some alternative implementations, the functions noted in the blocks 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. 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 special purpose hardware-based systems that perform the specified functions or operations, or special purpose hardware implemented in combination with 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 in one case.

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 (Application Specific Standard Products) Standard Parts, ASSP), system on chip (System on Chip, SOC), complex programmable logic device (Complex Programmable Logic Device, CPLD) and so on.

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. Machine-readable storage media include one or more wire-based electrical connections, portable computer disks, hard disks, RAM, ROM, EPROM, flash memory, optical fibers, portable CD-ROMs, optical storage devices, magnetic storage devices, or the above any suitable combination of content.

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

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

Check whether the current playback resource is loaded;

After it is detected that the loading of the current playback resource is completed, the step of determining the expected playback amount of each unplayed resource in the current information stream based on the prediction model is performed.

According to one or more embodiments of the present disclosure, a resource preloading method, apparatus, device, and medium are provided. While preloading the unplayed resource based on the expected playback amount, the method further includes:

Detect whether the current user switches to a new resource;

After the current user switches to the new resource, the new resource is used as the current playback resource, and the step of detecting whether the loading of the current playback resource is completed is performed.

Determine the current user type based on the predictive model;

Based on the current user type and the pre-stored correspondence between the user type and the playing volume, the expected playing volume of each unplayed resource in the current information stream is determined.

Determine the current user type based on the predictive model;

Determine the expected playback ratio of each unplayed resource in the current information stream based on the corresponding relationship between the current user type and the pre-stored user type and playback ratio;

For each unplayed resource, the predicted play amount is determined based on the predicted play ratio.

According to one or more embodiments of the present disclosure, a resource preloading method, apparatus, device, and medium are provided, and the current user type is determined based on a prediction model, including:

Acquiring playback-related historical information and resource information, wherein the resource information includes the playback duration of each broadcasted resource, the type of each unplayed resource, and the duration of each unplayed resource;

The play-related historical information and resource information are input into the prediction model to obtain the current user type.

According to one or more embodiments of the present disclosure, a resource preloading method, apparatus, device, and medium are provided, and the playback-related historical information and resource information are input into the prediction model to obtain the current user type, including:

Inputting the playback-related historical information and resource information into the prediction model to obtain multiple user type probabilities, where the user type probabilities are the probabilities that the current user belongs to a type of user;

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, while the above discussion contains several implementation details, these should not be construed as limitations on the scope of the present disclosure. Some 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.

Although the subject matter has been described in language specific to structural features and/or logical acts of method, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

A resource preloading method, including:

Determine the expected playback volume of each unplayed resource in the current information stream based on the prediction model;

For each unplayed resource, the unplayed resource is preloaded based on the expected play amount.
The method according to claim 1, wherein the determining the estimated playback volume of each unplayed resource in the current information stream based on the prediction model comprises:

Check whether the current playback resource is loaded;

After it is detected that the loading of the current playing resource is completed, the predicted playing amount of each unplayed resource in the current information stream is determined based on the prediction model.
The method according to claim 2, wherein, while the preloading the unplayed resource based on the expected playback amount, the method further comprises:

Detect whether the current user switches to a new resource;

After the current user switches to the new resource, the new resource is used as the current playback resource, and it is detected whether the loading of the current playback resource is completed.
The method according to claim 1, wherein the determining the estimated playback volume of each unplayed resource in the current information stream based on the prediction model comprises:

determining the current user type based on the predictive model;

The expected playback volume of each unplayed resource in the current information stream is determined based on the correspondence between the current user type and the pre-stored user type and playback volume.
The method according to claim 1, wherein the determining the estimated playback volume of each unplayed resource in the current information stream based on the prediction model comprises:

determining the current user type based on the predictive model;

Determine the expected playback ratio of each unplayed resource in the current information stream based on the correspondence between the current user type and the pre-stored user type and playback ratio;

For each unplayed resource, the predicted play amount is determined based on the predicted play ratio.
The method according to claim 4 or 5, wherein the determining the current user type based on the prediction model comprises:

Acquiring playback-related historical information and resource information, wherein the resource information includes the playback duration of each broadcasted resource, the type of each unplayed resource, and the duration of each unplayed resource;

The play-related historical information and resource information are input into the prediction model to obtain the current user type.
The method according to claim 6, wherein the inputting the play-related historical information and resource information into the prediction model to obtain the current user type comprises:

Inputting the playback-related historical information and resource information into the prediction model to obtain multiple user type probabilities, wherein the user type probabilities are the probabilities that the current user belongs to one type of user;

A user type corresponding to the largest user type probability among the multiple user type probabilities is determined as the current user type.
A resource preloading device, comprising:

The expected playback volume determination module is set to determine the expected playback volume of each unplayed resource in the current information stream based on the prediction model;

The preloading module is configured to, for each unplayed resource, preload the unplayed resource based on the expected playing amount.
A resource preloading device including:

at least one processor;

a memory, arranged to store at least one program;

When the at least one program is executed by the at least one processor, the at least one processor implements the resource preloading method according to any one of claims 1-7.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the resource preloading method according to any one of claims 1-7.