CN115002557B

CN115002557B - Network speed prediction method, device, equipment and storage medium

Info

Publication number: CN115002557B
Application number: CN202210566262.9A
Authority: CN
Inventors: 张晓彤; 范志巍
Original assignee: Beijing Zitiao Network Technology Co Ltd
Current assignee: Beijing Zitiao Network Technology Co Ltd
Priority date: 2022-05-23
Filing date: 2022-05-23
Publication date: 2024-01-30
Anticipated expiration: 2042-05-23
Also published as: CN115002557A

Abstract

The embodiment of the disclosure provides a network speed prediction method, a device, equipment and a storage medium. The method comprises the following steps: acquiring actual download network speed information and the size of the downloaded video clips corresponding to the first preset number of downloaded video clips; determining the sizes of the video clips to be downloaded corresponding to the second preset number of video clips to be downloaded; and carrying out network speed prediction based on a preset time sequence prediction model, actual downloading network speed information, the size of the downloaded video fragments and the size of the video fragments to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded. By the technical scheme of the embodiment of the disclosure, the downloading network speed of the video clips to be downloaded can be accurately predicted, and further the user watching experience is improved.

Description

Network speed prediction method, device, equipment and storage medium

Technical Field

The embodiment of the disclosure relates to computer technology, in particular to a network speed prediction method, a network speed prediction device, network speed prediction equipment and a storage medium.

Background

With the rapid development of computer technology, a plurality of later videos can be downloaded in advance, so that the smoothness of the next video watched by a user is ensured, and the user watching experience is improved. Typically, each video has multiple code rate steps. Currently, video of a proper code rate gear can be downloaded based on the network speed condition. It can be seen that there is a great need for a way to accurately predict future network speeds in order to download video with more appropriate gear.

Disclosure of Invention

The disclosure provides a network speed prediction method, device, equipment and storage medium, so as to accurately predict the downloading network speed of a video clip to be downloaded, and further improve the viewing experience of a user.

In a first aspect, an embodiment of the present disclosure provides a network speed prediction method, including:

acquiring actual download network speed information and the size of the downloaded video clips corresponding to the first preset number of downloaded video clips;

determining the sizes of the video clips to be downloaded corresponding to the second preset number of video clips to be downloaded;

and carrying out network speed prediction based on a preset time sequence prediction model, the actual downloading network speed information, the downloaded video fragment size and the video fragment size to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded.

In a second aspect, an embodiment of the present disclosure further provides a network speed prediction apparatus, including:

the video slicing information acquisition module is used for acquiring the actual downloaded network speed information and the downloaded video slicing size corresponding to the downloaded video slicing of the first preset number;

the video fragment information to be downloaded determining module is used for determining the size of the video fragment to be downloaded corresponding to the second preset number of video fragments to be downloaded;

The downloading network speed information prediction module is used for predicting the network speed based on a preset time sequence prediction model, the actual downloading network speed information, the downloaded video fragment size and the video fragment size to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded.

In a third aspect, embodiments of the present disclosure further provide an electronic device, including:

one or more processors;

storage means for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the network speed prediction method as described in any of the embodiments of the present disclosure.

In a fourth aspect, the presently disclosed embodiments also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing the network speed prediction method according to any of the presently disclosed embodiments.

According to the technical scheme, the actual downloading network speed information and the downloaded video slicing size corresponding to the first preset number of downloaded video slices are obtained, the size of the video slices to be downloaded corresponding to the second preset number of video slices to be downloaded is determined, network speed prediction is carried out based on a preset time sequence prediction model, the actual downloading network speed information, the downloaded video slicing size and the video slicing size to be downloaded, and the current prediction downloading network speed information corresponding to each video slice to be downloaded is determined, so that more accurate network speed prediction can be achieved, more suitable gear videos can be downloaded, and user watching experience is improved.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

Fig. 1 is a flowchart of a network speed prediction method according to an embodiment of the present disclosure;

FIG. 1 (a) is a schematic diagram of a model structure of a preset time-series prediction model according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of another network speed prediction method according to an embodiment of the present disclosure;

FIG. 2 (a) is a schematic diagram of a model structure of another predetermined timing prediction model according to an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of a network speed prediction device according to an embodiment of the disclosure;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

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 have been shown in the accompanying drawings, it is to 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 are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed 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 respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., 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. Related definitions of other terms will be given in the description below.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

It will be appreciated that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solution should comply with the corresponding legal regulations and the requirements of the relevant regulations.

Fig. 1 is a flow chart of a network speed prediction method provided by an embodiment of the present disclosure, where the embodiment of the present disclosure is applicable to predicting a video slice downloading network speed, the method may be performed by a network speed prediction device, and the device may be implemented in a form of software and/or hardware, optionally, by an electronic device, where the electronic device may be a mobile terminal, a PC end, a server, or the like.

As shown in fig. 1, the network speed prediction method specifically includes the following steps:

s110, acquiring actual download network speed information and the size of the downloaded video clips corresponding to the first preset number of downloaded video clips.

The first preset number may be the number of downloaded video clips obtained through prediction in each time preset according to a service requirement, where the first preset number is a value greater than 1, and may be a value 3 or more, and the embodiment is not limited. Each video is downloaded in slices. Each video may include multiple video slices.

Specifically, the client obtains a first preset number of downloaded video clips in reverse order according to time from the video clips downloaded in the history, and obtains actual downloaded network speed information and the size of the downloaded video clips corresponding to each downloaded video clip in the first preset number, so that the network speed can be predicted more accurately. It should be noted that, the obtaining of the first preset number of downloaded video clips may be each video clip of the same video, or may be each video clip of different videos, which is specifically selected according to an actual downloading situation. For example, if the first preset number is 10, if only 5 video clips exist in one recently downloaded historical downloaded video, continuing to acquire the latest downloaded 5 video clips in the previous downloaded video of the historical downloaded video; if there are 10 or more than 10 video clips in one history downloaded video which is downloaded recently, 10 downloaded video clips which are downloaded recently in the history downloaded video which are downloaded recently are obtained.

Illustratively, S110 may include: if the number of the downloaded video clips after the client is started at the time is smaller than the first preset number, determining the difference value number between the first preset number and the number of the downloaded video clips after the client is started at the time; the method comprises the steps of obtaining actual download network speed information and the size of downloaded video fragments corresponding to the number of recently downloaded difference values after last startup, and the actual download network speed information and the size of downloaded video fragments corresponding to each downloaded video fragment after last startup.

Specifically, the number of the downloaded video clips after the client is started is determined, and compared with the first preset number, and if the number of the downloaded video clips after the client is started is smaller than the first preset number, the difference value number between the number of the downloaded video clips after the client is started and the first preset number is determined. Based on the difference number, obtaining the downloaded video clips with the difference number from the last started downloaded video clips, obtaining the actual downloaded network speed information and the downloaded video clip size corresponding to the downloaded video clips, and simultaneously obtaining the actual downloaded network speed information and the downloaded video clip size corresponding to each downloaded video clip after the current start, so that in a period of time after the current start of the client, the accuracy of network speed prediction in the period of time can be ensured by using the downloaded data after the last start to perform network speed prediction due to the fact that the downloading number is smaller. If the number of the downloaded video clips after the client is started up is greater than or equal to the first preset number, acquiring the downloaded video clips of the first preset number which are downloaded recently after the client is started up, and acquiring the actual downloading network speed information and the size of the downloaded video clips corresponding to the downloaded video clips.

For example, if the number of downloaded video clips after the client is started up is 5, the actual download network speed information and the downloaded video clip size corresponding to the last downloaded 5 downloaded video clips at the last time of starting up, and the actual download network speed information and the downloaded video clip size corresponding to the 5 downloaded video clips after the client is started up are obtained. If the number of the downloaded video clips after the client is started is 10 or more, acquiring actual download network speed information and the size of the downloaded video clips corresponding to the 10 downloaded video clips recently downloaded at the current moment after the client is started.

Optionally, obtaining actual download network speed information and a downloaded video clip size corresponding to the downloaded video clip with the number of difference values of the last download after the last startup may include: detecting a network connection mode (such as a Wi-Fi mode or a mobile data mode) after the client is started last time and acquiring actual download network speed information and the size of the downloaded video fragments corresponding to the number of the latest download difference values after the client is started last time if the network connection mode after the client is started this time is the same as the network connection mode after the client is started last time; if the network connection mode of the client after the current startup is different from the network connection mode of the client after the last startup, acquiring the actual downloaded network speed information and the downloaded video fragment size corresponding to the latest downloaded difference value number of the client startup period which is the same as the network connection mode of the client after the current startup. For example, if the network connection mode after the client is started is a mobile data mode, detecting the network connection mode after the client is started last time, and if the network connection mode is the mobile data mode, acquiring actual download network speed information and the size of the downloaded video slices corresponding to the number of the recently downloaded difference values after the client is started last time; if the Wi-Fi mode is adopted, the network connection mode after the client is started for the previous time is continuously detected until the data mode is adopted, and the actual download network speed information and the size of the downloaded video fragments corresponding to the corresponding difference number of the downloaded video fragments are obtained. By acquiring the historical download data corresponding to the same network connection mode, the accuracy of network prediction can be further ensured.

S120, determining the sizes of the video clips to be downloaded corresponding to the second preset number of video clips to be downloaded.

The second preset number may be preset according to the actual service requirement, and the second preset number may be a number greater than or equal to 1, that is, the number of video clips to be downloaded may be one or more. The video clips to be downloaded may refer to video clips that need to be downloaded. The second preset number of video clips to be downloaded may include video clips to be downloaded in the same video, or may include video clips to be downloaded in different videos.

It is noted that the server stores video slicing versions of at least two different code rate gears of each video slice, the same video slice under different code rate gears has different sizes, the higher the code rate gear of the same video slice is, the larger the video slice is, the lower the code rate gear of the same video slice is, and the smaller the video slice is.

Specifically, the client may determine the number of video clips to be downloaded according to the second preset number, and determine the size of each video clip to be downloaded in the corresponding code rate gear of each video clip to be downloaded. The network speed is predicted based on the size of the video clips to be downloaded, so that the accuracy of the network speed prediction can be improved.

Illustratively, S120 may include: determining the size of each video fragment to be downloaded under the preset downloading code rate gear based on the preset downloading code rate gear; or determining the size of the video fragment to be downloaded under the target downloading code rate gear based on the target downloading code rate gear corresponding to the video fragment to be downloaded.

The preset download code rate gear may be a preset default code rate gear. The target download code rate gear may refer to a code rate gear determined from the predicted download network rate information. It should be noted that the target downloading code rate gear may be determined based on the last predicted downloading network speed information corresponding to the last predicted video clip to be downloaded.

Specifically, for each video clip to be downloaded, determining the size of the video clip to be downloaded under the preset downloading code rate gear according to the preset downloading code rate gear; or determining a target downloading code rate gear corresponding to the video fragment to be downloaded according to the current predicted downloading network speed corresponding to the video fragment to be downloaded, which is determined by the last network speed prediction, and determining the size of the video fragment to be downloaded under the target downloading code rate gear corresponding to the video fragment to be downloaded. It should be noted that, the two ways of obtaining the size of the video segment to be downloaded can be selected according to actual situations, the size of the video segment to be downloaded is determined based on the way of the target downloading code rate gear, and the current predicted downloading network speed information corresponding to each video segment to be downloaded can be predicted more accurately.

S130, carrying out network speed prediction based on a preset time sequence prediction model, actual downloading network speed information, the size of the downloaded video fragments and the size of the video fragments to be downloaded, and determining current predicted downloading network speed information corresponding to each video fragment to be downloaded.

The preset time sequence prediction model can be a time sequence prediction model of any network architecture for predicting the network speed. For example, the preset time sequence prediction model may be a recurrent neural network model RNN (Recurrent Neural Network), a Long Short-Term Memory artificial neural network model LSTM (Long Short-Term Memory), or the like. The current predicted download network speed information may refer to network speed information when the next predicted video clip to be downloaded is downloaded.

Specifically, the client inputs the actual download network speed information corresponding to each downloaded video clip, the size of each downloaded video clip and the size of each video clip to be downloaded into a pre-trained preset time sequence prediction model, predicts the download network speed, and determines the current predicted download network speed information corresponding to each video clip to be downloaded according to the output result of the preset time sequence prediction model. Based on the actual downloaded network speed information corresponding to the downloaded video clips as the initial state of the downloaded network speed prediction, the current predicted downloaded network speed information corresponding to each video clip to be downloaded can be predicted more accurately, and the experience effect of the user is further improved. If the second preset number is at least two, the network speed information of the video distribution to be downloaded can be predicted at one time by utilizing the preset time sequence prediction model, so that the strategy depending on network speed measurement can be further improved, the optimization is carried out on the whole, and the user experience is improved.

It should be noted that, a prediction trigger condition exists in the client, and the client performs one time of network speed prediction whenever the prediction trigger condition is satisfied, where the prediction trigger condition may perform one time of network speed prediction for each time of downloading a certain number of video clips to be downloaded, or may perform one time of network speed prediction at certain intervals. And the client performs repeated cyclic prediction on the current predicted downloading network speed information corresponding to each video fragment to be downloaded based on the prediction triggering condition.

In this embodiment, the preset time sequence prediction model may be obtained by training in advance based on sample data. The sample data may include: the method comprises the steps of actually downloading network speed information corresponding to a first preset number of downloaded sample fragments, the size of the downloaded video fragments, the size of the video fragments to be downloaded corresponding to a second preset number of the sample fragments to be downloaded, and actually downloading network speed information (serving as labels) corresponding to the second preset number of the sample fragments to be downloaded. More new sample data can be generated along with the application of the preset time sequence prediction model, and the iterative update training can be continuously carried out on the preset time sequence prediction model based on the new sample data so as to further improve the accuracy of the net speed prediction of the preset time sequence prediction model.

Illustratively, after step S130, it may further include: determining a target code rate gear from at least two code rate gears corresponding to each video fragment to be downloaded based on current predicted downloading network speed information corresponding to the video fragment to be downloaded; downloading the video clips to be downloaded corresponding to the target code rate gear.

Specifically, for each video segment to be downloaded, the target code rate gear can be determined from at least two code rate gears corresponding to the video segment to be downloaded based on a preset corresponding relationship between the network speed information and the downloading code rate gear. When a video clip to be downloaded is needed to be downloaded currently, the video clip version to be downloaded corresponding to the target code rate gear can be downloaded from the server according to the target code rate gear. The corresponding video fragment version to be downloaded is downloaded based on the target code rate gear, so that the more proper code rate gear can be downloaded, the downloading speed is improved, the situation that a user watches video and is blocked is avoided, and the comprehensive experience of the user is further improved.

On the basis of the above technical solutions, the preset time sequence prediction model may include: and the first predictive sub-models are sequentially connected with the second predictive sub-models in a first preset number and the second predictive sub-models in a third preset number, wherein the third preset number is determined based on the second preset number. Wherein the third preset number may be 1 less than the second preset number. For example, if the second preset number is 1, that is, only one piece of network speed information corresponding to the video clip to be downloaded is predicted at a time, the preset time sequence prediction model only includes the first preset number of first prediction sub-models. Each first preset sub-model is connected with each second preset sub-model in sequence, and the output of the last first preset sub-model is connected with the input of the first second preset sub-model. The network architecture of each first predictor model in the embodiments of the present disclosure is the same, and the network architecture of each second predictor model is the same.

Accordingly, S130 may include: inputting the current actual downloading network speed information corresponding to the downloaded current video slice and the video slice size corresponding to the next slice of the current slice into a corresponding current first predictor model, and obtaining the current predicting downloading network speed information corresponding to the first video slice to be downloaded based on the output of the last first predictor model;

Inputting current predicted downloading network speed information corresponding to the first video fragment to be downloaded and the size of the video fragment to be downloaded corresponding to the second video fragment to be downloaded into a first and second prediction sub-model, and determining the current predicted downloading network speed information corresponding to the second video fragment to be downloaded;

and inputting the current predicted downloading network speed information corresponding to the second video fragment to be downloaded and the size of the video fragment to be downloaded corresponding to the next video fragment to be downloaded into the next second prediction sub-model, and determining the current predicted downloading network speed information corresponding to the next video fragment to be downloaded.

Specifically, fig. 1 (a) shows a schematic diagram of a model structure of a preset time sequence prediction model. As shown in fig. 1 (a), n may refer to a first preset number, and k may refer to a second preset number. The preset time sequence prediction model comprises n first preset sub-models and k-1 second preset sub-models. As shown in fig. 1 (a), the actual download network Speed information speed_1 corresponding to the first downloaded video clip and the video clip size fsize_2 corresponding to the second downloaded video clip are input into the first predictor model, and the actual download network Speed information speed_2 corresponding to the second downloaded video clip and the video clip size fsize_3 corresponding to the third downloaded video clip are input into the second first predictor model until the actual download network Speed information speed_n corresponding to the nth downloaded video clip and the video clip size fsize_n+1 corresponding to the first video clip to be downloaded are input into the last first predictor model, and the output result of the last first predictor model is determined as the current predicted download network Speed information speed_n+1 corresponding to the first video clip to be downloaded.

If at least two video clips to be downloaded are predicted each time, namely k is greater than or equal to 2, continuously inputting current predicted downloading network speed information corresponding to the second video clip to be downloaded and the size of the video clip to be downloaded corresponding to the next video clip to be downloaded into the next second prediction sub-model, predicting current predicted downloading network speed information corresponding to the next video clip to be downloaded, and then analogizing until the current predicted downloading network information corresponding to the last video clip in the third preset number is predicted. For example, as shown in fig. 1 (a), the current predicted download network Speed information speed_n+1 corresponding to the first video clip to be downloaded and the video clip size fsize_n+2 corresponding to the second video clip to be downloaded are input into the first second prediction sub-model, and the output result of the first second prediction sub-model is the current predicted download network Speed information speed_n+2 corresponding to the second video clip to be downloaded. Inputting the current predicted downloading network Speed information speed_n+2 corresponding to the second video segment to be downloaded and the video segment size fsize_n+3 corresponding to the third video segment to be downloaded into a second predictor model, determining the output result of the second predictor model as the current predicted downloading network Speed information speed_n+3 corresponding to the third video segment to be downloaded, and analogizing the same until the current predicted downloading network Speed information speed_n+k corresponding to the kth video segment to be downloaded is predicted.

By the prediction mode based on the preset time sequence prediction model shown in fig. 1 (a), the network speed prediction can be more accurately performed, and the prediction effect is further improved.

Fig. 2 is a flow chart of another network speed prediction method provided by an embodiment of the present disclosure, where based on the above embodiment of the present disclosure, a process of network speed prediction is described in detail under a condition that actual round trip delay information corresponding to each downloaded video segment is obtained. Wherein the same or corresponding terms as those of the above-described embodiments are not explained in detail herein.

As shown in fig. 2, the network speed prediction method specifically includes the following steps:

s210, acquiring actual download network speed information corresponding to a first preset number of downloaded video clips, the size of the downloaded video clips and actual round trip delay information corresponding to the downloaded video clips.

The actual round trip delay information may refer to the time required by the server to transmit video slice data to the client. The actual Round Trip delay information may be an actual value corresponding to a Round Trip delay RTT (Round Trip Time).

Specifically, the client sequentially obtains a first preset number of downloaded video clips according to a reverse time sequence from the video clips downloaded in the history, and obtains actual downloading network speed information corresponding to each downloaded video clip in the first preset number, wherein the size of the downloaded video clip and the actual round trip time delay information, so that the network speed can be predicted more accurately based on the actual round trip time delay information.

S220, determining the sizes of the video clips to be downloaded corresponding to the second preset number of video clips to be downloaded.

S230, carrying out network speed prediction based on a preset time sequence prediction model, actual downloading network speed information, actual round trip delay information, downloaded video fragment size and video fragment size to be downloaded, and determining current predicted downloading network speed information corresponding to each video fragment to be downloaded.

The current predicted round trip delay information may refer to network speed delay information when the next predicted video segment to be downloaded is downloaded. The preset time sequence prediction model in the embodiment of the disclosure can predict the round trip delay information of the video clips to be downloaded while predicting the downloading network speed information of the video clips to be downloaded, so that when at least two video clips to be downloaded exist, the downloading network speed information of the next video clip to be downloaded can be predicted based on the predicted round trip delay information corresponding to the last video clip to be downloaded, thereby ensuring that the input information of each prediction submodule in the preset time sequence prediction model is consistent, and further more accurately predicting the current predicted downloading network speed information corresponding to a plurality of video clips to be downloaded at one time.

Specifically, the client inputs the actual download network speed information, the size of each downloaded video fragment, the actual round trip delay information and the size of each video fragment to be downloaded corresponding to each downloaded video fragment into a pre-trained preset time sequence prediction model, predicts the download network speed, and determines the current predicted download network speed information corresponding to each video fragment to be downloaded according to the output result of the preset time sequence prediction model. Based on the actual download network speed information and the actual round trip delay information corresponding to the downloaded video clips as the initial state of the download network speed prediction, the current prediction download network speed information corresponding to each video clip to be downloaded can be predicted more accurately, and the experience effect of a user is further improved. If the second preset number is at least two, the current predicted downloading network speed information and the current predicted round-trip delay information corresponding to each video segment to be downloaded can be predicted by utilizing a preset time sequence prediction model, so that the current predicted downloading network speed information corresponding to a plurality of video segments to be downloaded in the next network speed prediction stage can be predicted according to the current predicted downloading network speed information and the current predicted round-trip delay information corresponding to the video segments to be downloaded, and the strategy depending on network speed measurement can be further improved, so that the optimization is performed on the whole, and the user experience is improved.

In this embodiment, the preset time sequence prediction model may be obtained by training in advance based on sample data. The sample data may include: the method comprises the steps of actually downloading network speed information and actually round trip delay information corresponding to a first preset number of downloaded sample fragments, downloaded video fragment sizes, video fragment sizes to be downloaded corresponding to a second preset number of sample fragments to be downloaded and actually downloading network speed information (serving as labels) corresponding to the second preset number of sample fragments to be downloaded. The preset time sequence prediction model is trained by utilizing sample data with round trip delay information, so that the trained preset time sequence prediction model can more accurately predict the network speed.

According to the technical scheme, the current predicted downloading network speed information corresponding to each video clip to be downloaded is determined by carrying out network speed prediction based on the preset time sequence prediction model, the actual downloading network speed information, the actual round trip time delay information, the size of each video clip to be downloaded and the size of each video clip to be downloaded, so that the actual round trip time delay information corresponding to the video clip to be downloaded is also input into the preset time sequence prediction model, the accuracy of predicting the downloading network speed information can be further improved, more suitable gear video is downloaded, and the watching experience of a user is improved.

On the basis of the above technical solutions, the preset time sequence prediction model may include: and the first predictive sub-models are sequentially connected with the second predictive sub-models in a first preset number and the second predictive sub-models in a third preset number, wherein the third preset number is determined based on the second preset number.

Accordingly, S230 may include: inputting the current actual downloading network speed information and the current actual round trip delay information corresponding to the downloaded current video fragments and the video fragment size corresponding to the next fragment of the current fragments into corresponding current first prediction sub-models, and obtaining the current prediction downloading network speed information and the current prediction round trip delay information corresponding to the first video fragment to be downloaded based on the output of the last first prediction sub-model;

inputting current predicted downloading network speed information and current predicted round-trip delay information corresponding to the first video fragment to be downloaded and the size of the video fragment to be downloaded corresponding to the second video fragment to be downloaded into a first and second prediction sub-model, and determining the current predicted downloading network speed information and the current predicted round-trip delay information corresponding to the second video fragment to be downloaded;

and inputting the current predicted downloading network speed information and the current predicted round-trip delay information corresponding to the second video fragment to be downloaded and the size of the video fragment to be downloaded corresponding to the next video fragment to be downloaded into the next second prediction sub-model, and determining the current predicted downloading network speed information and the current predicted round-trip delay information corresponding to the next video fragment to be downloaded.

Specifically, fig. 2 (a) shows a schematic diagram of a model structure of a preset time sequence prediction model. As shown in fig. 2 (a), in the preset timing prediction model, n may refer to a first preset number, and k may refer to a second preset number. The preset time sequence prediction model comprises n first preset sub-models and k-1 second preset sub-models. As shown in fig. 2 (a), the actual download network Speed information speed_1 corresponding to the first downloaded video slice, the actual round trip delay information rtt_1 corresponding to the first downloaded video slice, and the video slice size fsize_2 corresponding to the second downloaded video slice are input into a first prediction sub-model; inputting the actual download network Speed information speed_2 corresponding to the second downloaded video slice, the actual round trip delay information rtt_2 corresponding to the second downloaded video slice and the video slice size fsize_3 corresponding to the second downloaded video slice into a second first predictor model; and analogically, inputting the actual download network Speed information speed_n corresponding to the nth downloaded video slice, the actual round trip delay information rtt_n corresponding to the nth downloaded video slice and the video slice size fsize_n+1 corresponding to the first video slice to be downloaded into the last first prediction sub-model. The output result of the last first prediction sub-model may be the current predicted download network Speed information speed_n+1 and the current predicted round trip delay information rtt_n+1 corresponding to the first video segment to be downloaded.

If at least two video clips to be downloaded are predicted each time, namely k is greater than or equal to 2, continuously inputting current predicted downloading network speed information and current predicted round-trip delay information corresponding to the second video clip to be downloaded and the size of the video clip to be downloaded corresponding to the next video clip to be downloaded into the next second prediction sub-model, predicting current predicted downloading network speed information and current predicted round-trip delay information corresponding to the next video clip to be downloaded, and so on until the current predicted downloading network information corresponding to the last video clip in the third preset number is predicted. For example, as shown in fig. 2 (a), the current predicted download network Speed information speed_n+1 and the current predicted round trip delay information rtt_n+1 corresponding to the first video segment to be downloaded, and the video segment size fsize_n+2 corresponding to the second video segment to be downloaded are input into the first second prediction sub-model, and the output result of the first second prediction sub-model is the current predicted download network Speed information speed_n+2 and the current predicted round trip delay information rtt_n+2 corresponding to the second video segment to be downloaded. And simultaneously inputting current predicted downloading network Speed information speed_n+2 and current predicted round trip delay information rtt_n+2 corresponding to the second video segment to be downloaded and video segment size fsize_n+3 corresponding to the third video segment to be downloaded into a second predictor model, wherein the output result of the second predictor model is current predicted downloading network Speed information speed_n+3 and current predicted round trip delay information rtt_n+3 corresponding to the third video segment to be downloaded, and the like until the current predicted downloading network Speed information speed_n+k corresponding to the kth video segment to be downloaded is predicted.

By the prediction mode based on the preset time sequence prediction model shown in fig. 2 (a), accuracy of network speed prediction can be further improved, and further prediction effect is improved.

Fig. 3 is a schematic structural diagram of a network speed prediction apparatus according to an embodiment of the present disclosure, as shown in fig. 3, where the apparatus specifically includes: the device comprises a video slicing information acquisition module 310, a video slicing information to be downloaded determining module 320 and a downloading network speed information predicting module 330.

The video slicing information obtaining module 310 is configured to obtain actual download network speed information and a downloaded video slicing size corresponding to a first preset number of downloaded video slices; the to-be-downloaded video clip information determining module 320 is configured to determine a size of a video clip to be downloaded corresponding to a second preset number of video clips to be downloaded; the download network speed information prediction module 330 is configured to perform network speed prediction based on a preset time sequence prediction model, the actual download network speed information, the size of the downloaded video segment, and the size of the video segment to be downloaded, and determine current predicted download network speed information corresponding to each video segment to be downloaded.

Based on the above technical solution, the video slicing information obtaining module 310 may be specifically configured to:

if the number of the downloaded video clips after the client is started at the time is smaller than the first preset number, determining the difference value number between the first preset number and the number of the downloaded video clips after the client is started at the time;

the method comprises the steps of obtaining actual download network speed information and the size of downloaded video fragments corresponding to the number of recently downloaded difference values after last startup, and the actual download network speed information and the size of downloaded video fragments corresponding to each downloaded video fragment after last startup.

Based on the above technical solution, the video clip information determining module 320 to be downloaded may be specifically configured to:

determining the size of each video fragment to be downloaded under the preset downloading code rate gear based on the preset downloading code rate gear; or,

and determining the size of the video fragment to be downloaded under the target downloading code rate gear based on the target downloading code rate gear corresponding to the video fragment to be downloaded, wherein the target downloading code rate gear is determined based on the last predicted downloading network speed information corresponding to the video fragment to be downloaded obtained by last prediction.

On the basis of the above technical solutions, the preset time sequence prediction model may include: the method comprises the steps of sequentially connecting a first preset number of first predictor models and a third preset number of second predictor models, wherein the third preset number is determined based on the second preset number; the download network speed information prediction module 330 may be configured to:

inputting the current actual downloading network speed information corresponding to the downloaded current video slice and the video slice size corresponding to the next slice of the current slice into a corresponding current first predictor model, and obtaining the current predicting downloading network speed information corresponding to the first video slice to be downloaded based on the output of the last first predictor model;

Based on the above technical solutions, the video slicing information obtaining module 310 may be further configured to: acquiring actual round trip delay information corresponding to each downloaded video fragment; the download network speed information prediction module 330 may include:

the downloading network speed information prediction unit is used for predicting the network speed based on a preset time sequence prediction model, actual downloading network speed information, actual round trip delay information, the size of the downloaded video fragments and the size of the video fragments to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded.

On the basis of the above technical solutions, the preset time sequence prediction model includes: and the first predictive sub-models are sequentially connected with the second predictive sub-models in a first preset number and the second predictive sub-models in a third preset number, wherein the third preset number is determined based on the second preset number.

The download network speed information prediction unit may be specifically configured to: inputting the current actual downloading network speed information and the current actual round trip delay information corresponding to the downloaded current video fragments and the video fragment size corresponding to the next fragment of the current fragments into corresponding current first prediction sub-models, and obtaining the current prediction downloading network speed information and the current prediction round trip delay information corresponding to the first video fragment to be downloaded based on the output of the last first prediction sub-model; inputting current predicted downloading network speed information and current predicted round-trip delay information corresponding to the first video fragment to be downloaded and the size of the video fragment to be downloaded corresponding to the second video fragment to be downloaded into a first and second prediction sub-model, and determining the current predicted downloading network speed information and the current predicted round-trip delay information corresponding to the second video fragment to be downloaded; and inputting the current predicted downloading network speed information and the current predicted round-trip delay information corresponding to the second video fragment to be downloaded and the size of the video fragment to be downloaded corresponding to the next video fragment to be downloaded into the next second prediction sub-model, and determining the current predicted downloading network speed information and the current predicted round-trip delay information corresponding to the next video fragment to be downloaded.

Based on the above technical solutions, the network speed prediction device further includes: the target code rate gear determining module is used for determining a target code rate gear from at least two code rate gears corresponding to each video fragment to be downloaded based on current predicted downloading network speed information corresponding to the video fragment to be downloaded; downloading the video clips to be downloaded corresponding to the target code rate gear.

The network speed prediction device provided by the embodiment of the disclosure can execute the network speed prediction method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

It should be noted that each unit and module included in the above apparatus are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for convenience of distinguishing from each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. Referring now to fig. 4, a schematic diagram of an electronic device (e.g., a terminal device or server in fig. 4) 400 suitable for use in implementing embodiments of the present disclosure is shown. The 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 (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 4 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.

As shown in fig. 4, the electronic device 400 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 401, which may perform various suitable actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage means 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data necessary for the operation of the electronic device 400 are also stored. The processing device 401, the ROM402, and the RAM403 are connected to each other by a bus 404. An edit/output (I/O) interface 405 is also connected to bus 404.

In general, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, magnetic tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 shows an electronic device 400 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communications device 409, or from storage 408, or from ROM 402. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 401.

The electronic device provided by the embodiment of the present disclosure and the network speed prediction method provided by the foregoing embodiment belong to the same inventive concept, and technical details not described in detail in the present embodiment may be referred to the foregoing embodiment, and the present embodiment has the same beneficial effects as the foregoing embodiment.

The present disclosure provides a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the network speed prediction method provided by the above embodiments.

It should be noted that the computer readable medium described 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 electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

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

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to:

the computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring actual download network speed information and the size of the downloaded video clips corresponding to the first preset number of downloaded video clips; determining the sizes of the video clips to be downloaded corresponding to the second preset number of video clips to be downloaded; and carrying out network speed prediction based on a preset time sequence prediction model, the actual downloading network speed information, the downloaded video fragment size and the video fragment size to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded.

Alternatively, the computer-readable medium carries one or more programs which, when executed by a computer processor, cause the processor to implement a network speed prediction method as described in any one of the above.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming 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 (for example, through the Internet using an Internet service provider).

The flowcharts 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, which comprises one or more executable instructions for implementing the specified logical function(s). 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 will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The name of the unit does not in any way constitute a limitation of the unit itself, for example the first acquisition unit may also be described as "unit acquiring at least two internet protocol addresses".

The functions described above herein 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: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, there is provided a network speed prediction method, including:

According to one or more embodiments of the present disclosure, there is provided a network speed prediction method [ example two ] further comprising:

optionally, the obtaining the actual download network speed information and the downloaded video clip size corresponding to the first preset number of downloaded video clips includes:

and acquiring the actual download network speed information and the downloaded video fragment size corresponding to the downloaded video fragments with the difference value number which are downloaded recently after the last time, and the actual download network speed information and the downloaded video fragment size corresponding to each downloaded video fragment after the last time.

According to one or more embodiments of the present disclosure, there is provided a network speed prediction method [ example three ], further comprising:

optionally, the determining the size of the video clip to be downloaded corresponding to the second preset number of video clips to be downloaded includes:

According to one or more embodiments of the present disclosure, there is provided a network speed prediction method [ example four ], further comprising:

optionally, the preset time sequence prediction model includes: the first preset number of first predictor models and the third preset number of second predictor models are sequentially connected, wherein the third preset number is determined based on the second preset number;

The step of predicting the network speed based on a preset time sequence prediction model, the actual downloading network speed information, the downloaded video fragment size and the video fragment size to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded comprises the following steps:

According to one or more embodiments of the present disclosure, there is provided a network speed prediction method [ example five ], further comprising:

optionally, acquiring actual round trip delay information corresponding to each downloaded video segment;

and carrying out network speed prediction based on a preset time sequence prediction model, the actual downloading network speed information, the actual round trip delay information, the downloaded video fragment size and the video fragment size to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded.

According to one or more embodiments of the present disclosure, there is provided a network speed prediction method [ example six ] further comprising:

The step of predicting the network speed based on a preset time sequence prediction model, the actual downloading network speed information, the actual round trip delay information, the downloaded video fragment size and the video fragment size to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded comprises the following steps:

inputting the current actual downloading network speed information and the current actual round trip delay information corresponding to the downloaded current video fragments and the video fragment size corresponding to the next fragment of the current fragments into corresponding current first prediction sub-models, and obtaining the current prediction downloading network speed information and the current prediction round trip delay information corresponding to the first video fragment to be downloaded based on the output of the last first prediction sub-model;

According to one or more embodiments of the present disclosure, there is provided a network speed prediction method [ example seventh ], further comprising:

optionally, after determining the current predicted download network speed information corresponding to each video clip to be downloaded, the method further includes:

determining a target code rate gear from at least two code rate gears corresponding to each video fragment to be downloaded based on current predicted downloading network speed information corresponding to the video fragment to be downloaded;

and downloading the video clips to be downloaded corresponding to the target code rate gear.

According to one or more embodiments of the present disclosure, there is provided a network speed prediction apparatus, including:

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting 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.

Although the subject matter has been described in language specific to structural features and/or methodological acts, 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 example forms of implementing the claims.

Claims

1. A network speed prediction method, comprising:

based on a preset time sequence prediction model, the actual downloading network speed information, the downloaded video fragment size and the video fragment size to be downloaded, carrying out network speed prediction, and determining current predicted downloading network speed information corresponding to each video fragment to be downloaded; the preset time sequence prediction model comprises the following steps: the first preset number of first predictor models and the third preset number of second predictor models are sequentially connected, wherein the third preset number is determined based on the second preset number;

and carrying out network speed prediction based on the first predictor model, the second predictor model, the actual downloading network speed information, the downloaded video fragment size and the video fragment size to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded.

2. The network speed prediction method according to claim 1, wherein the obtaining the actual downloaded network speed information and the downloaded video clip size corresponding to the first preset number of downloaded video clips includes:

3. The network speed prediction method according to claim 1, wherein the determining the size of the video clip to be downloaded corresponding to the second preset number of video clips to be downloaded includes:

4. The network speed prediction method according to claim 1, wherein the determining the current predicted download network speed information corresponding to each video clip to be downloaded based on the preset time sequence prediction model, the actual download network speed information, the downloaded video clip size and the video clip size to be downloaded includes:

5. The network speed prediction method according to claim 1, the method further comprising:

acquiring actual round trip delay information corresponding to each downloaded video fragment;

6. The network speed prediction method according to claim 5, wherein the preset time sequence prediction model comprises: the first preset number of first predictor models and the third preset number of second predictor models are sequentially connected, wherein the third preset number is determined based on the second preset number;

7. The network speed prediction method according to claim 1, further comprising, after determining current predicted download network speed information corresponding to each video clip to be downloaded:

8. A network speed prediction apparatus, comprising:

The downloading network speed information prediction module is used for predicting the network speed based on a preset time sequence prediction model, the actual downloading network speed information, the downloaded video fragment size and the video fragment size to be downloaded, and determining the current predicted downloading network speed information corresponding to each video fragment to be downloaded; the preset time sequence prediction model comprises the following steps: the method comprises the steps of sequentially connecting a first preset number of first predictor models and a third preset number of second predictor models, wherein the third preset number is determined based on the second preset number;

the download network speed information prediction module is used for:

9. An electronic device, the electronic device comprising:

one or more processors;

storage means for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the network speed prediction method of any of claims 1-7.

10. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the network speed prediction method of any one of claims 1-7.