CN115426526A

CN115426526A - Video playing method, device, storage medium and equipment

Info

Publication number: CN115426526A
Application number: CN202110607945.XA
Authority: CN
Inventors: 唐国明
Original assignee: Tencent Technology Shenzhen Co Ltd; Peng Cheng Laboratory
Current assignee: Tencent Technology Shenzhen Co Ltd; Peng Cheng Laboratory
Priority date: 2021-06-01
Filing date: 2021-06-01
Publication date: 2022-12-02
Anticipated expiration: 2041-06-01
Also published as: CN115426526B

Abstract

The application discloses a video playing method, a video playing device, a storage medium and a video playing device; the application relates to machine learning, data storage and reading of artificial intelligence; the method comprises the steps of obtaining the current residual electric quantity of a mobile terminal where a video playing client is located; estimating anxiety change information of a client object caused by the current residual capacity relative to the reference residual capacity; when the anxiety change information meets the low-power-consumption playing condition, sending a low-power-consumption video clip request to a server; receiving a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request; video playing is carried out according to the target low-power-consumption video clip; the video playing method and device can carry out video playing according to the anxiety change information adaptability of the client object.

Description

Video playing method, device, storage medium and equipment

Technical Field

The present application relates to the field of computers, and in particular, to a video playing method, apparatus, storage medium, and device.

Background

The power of the mobile terminal is lower and lower along with the use of the user, and the reduction of the power may cause anxiety of the user in different degrees, and the user may stop or reduce the use of the mobile terminal or a part of high power consumption applications on the mobile terminal due to the anxiety, for example, if the user generates anxiety due to the attention of the current remaining power of the mobile terminal during the process of watching a video, the user may choose to stop watching the video to slow down the power consumption and relieve the anxiety.

Disclosure of Invention

The embodiment of the application provides a video playing method, a video playing device, a storage medium and video playing equipment, which can carry out video playing adaptively according to anxiety change information of a client object.

The embodiment of the application provides a video playing method, which comprises the following steps:

acquiring the current residual electric quantity of a mobile terminal where a video playing client is located;

estimating anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity;

when the anxiety change information meets the low-power consumption playing condition, sending a low-power consumption video clip request to a server;

receiving a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request;

and playing the video according to the target low-power-consumption video clip.

Specifically, the present application further provides a video playing device, including:

the estimation module is used for estimating anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity;

the sending module is used for sending a low-power-consumption video clip request to a server when the anxiety change information meets the low-power-consumption playing condition;

the receiving module is used for receiving a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request;

and the playing module is used for playing the video according to the target low-power-consumption video clip.

In some embodiments, the predictor module includes an acquisition submodule and a predictor submodule, wherein,

the obtaining submodule is used for obtaining a target anxiety pre-estimation model, wherein the target anxiety pre-estimation model comprises a target mapping relation set, and the target mapping relation set comprises mapping relations between a plurality of preset residual electric quantities and a plurality of preset anxiety information;

and the estimation submodule is used for estimating anxiety change information of the client object caused by the current residual electric quantity relative to the reference residual electric quantity according to the target mapping relation set.

In some embodiments, the predictor module includes a determination unit, a predictor unit, and a calculation unit, wherein,

the determining unit is used for determining a reference residual capacity corresponding to the current residual capacity;

the estimation unit is used for respectively estimating first anxiety information and second anxiety information corresponding to the current residual electric quantity and the reference residual electric quantity according to the target mapping relation set;

a calculating unit, configured to calculate anxiety change information that the current remaining power causes to the client object with respect to the reference remaining power based on the first anxiety information and the second anxiety information.

In some embodiments, the acquisition submodule includes a receiving unit, a determining unit, and a fusing unit, wherein,

the receiving unit is used for receiving the initial anxiety estimation model sent by the server;

the determining unit is used for determining an object anxiety pre-estimation model of the client object;

and the fusion unit is used for fusing the initial anxiety prediction model and the object anxiety prediction model to obtain the target anxiety prediction model.

In some embodiments, the fusion unit is specifically configured to:

obtaining a first fusion weight of the initial anxiety model and obtaining a second fusion weight of the subject anxiety model;

and fusing the initial anxiety prediction model and the object anxiety prediction model based on the first fusion weight and the second fusion weight to obtain the target anxiety prediction model.

In some embodiments, the determination unit comprises an acquisition subunit and a generation subunit, wherein,

the acquisition subunit is used for acquiring a plurality of charging electric quantities of the mobile terminal;

and the generating subunit is used for generating the object anxiety estimation model of the client object according to the plurality of charging electric quantities.

In some embodiments, the object anxiety prediction model comprises a set of object mapping relationships, and the generating subunit is specifically configured to:

setting a plurality of initial anxiety values, wherein each initial anxiety value corresponds to a residual electric quantity;

determining a plurality of target residual capacities matched with the plurality of charging capacities;

updating an initial anxiety value corresponding to each target residual capacity and an initial anxiety value corresponding to a residual capacity smaller than each target residual capacity to obtain a plurality of target anxiety values corresponding to the plurality of residual capacities;

and carrying out standardization processing on the target anxiety values to obtain a plurality of anxiety information corresponding to the residual electric quantities, wherein the corresponding relations between the residual electric quantities and the anxiety information form an object mapping relation set.

In some embodiments, the video playback apparatus further includes:

the file receiving module is used for receiving an index file of a target video sent by the server, wherein the index file comprises address information of a plurality of video clips of the target video;

the sending module is specifically configured to:

when the anxiety change information meets the low-power-consumption playing condition, determining the address information of the target low-power-consumption video clip to be played from the index file;

generating the low-power video clip request for requesting the target low-power video clip;

and sending the low-power-consumption video clip request to the server based on the address information.

In some embodiments, the video playback apparatus further includes:

the recording module is used for recording the charging electric quantity at the current moment when the charging operation aiming at the mobile terminal is detected;

the trigger module is used for sending the collected multiple charging electric quantities to the server, triggering the server to sample the received multiple charging electric quantities of the multiple mobile terminals to obtain multiple target charging electric quantities, and updating the target anxiety estimation model according to the multiple target charging electric quantities to obtain an updated target anxiety estimation model.

Correspondingly, the embodiment of the present application further provides a storage medium, where the storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute any one of the video playing methods provided in the embodiment of the present application.

Correspondingly, the embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements any one of the video playing methods provided in the embodiment of the present application when executing the computer program.

The method comprises the steps of obtaining the current residual electric quantity of a mobile terminal where a video playing client is located; estimating anxiety change information of a client object caused by the current residual capacity relative to the reference residual capacity; when the anxiety change information meets the low-power-consumption playing condition, sending a low-power-consumption video clip request to a server; receiving a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request; and playing the video according to the target low-power-consumption video clip.

This application can be according to the current residual capacity of video broadcast client place mobile terminal, predict this current residual capacity to the reference residual capacity interval that this current residual capacity corresponds, the anxious transform information of the client object that causes, client object's anxious change information can be perceived to this application, and the video broadcast that carries on of correspondence, when anxious change information satisfies low-power consumption broadcast condition, use low-power consumption video clip to broadcast, reduce the power consumption of video broadcast, slow down the power down speed of moving destination, and then alleviate client object's anxious mood.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a scene schematic diagram of a video playback system of the present application;

FIG. 2 is a schematic flow chart of a video playing method according to the present application;

fig. 3 is another schematic flow chart of the video playing method of the present application;

fig. 4 is a schematic diagram illustrating a streaming video transmission flow of the video playing method of the present application;

FIG. 5 is a schematic diagram of a mobile terminal and a server according to the video playing method of the present application;

fig. 6 is a schematic view of implementing video playing in different playing modes of the video playing method of the present application;

fig. 7 is an interaction diagram of video playing in an online mode of the video playing method of the present application;

fig. 8 is a schematic diagram illustrating LBA model distribution and update of the video playing method of the present application;

fig. 9 is a schematic structural diagram of a video playback device of the present application;

fig. 10 is a schematic structural diagram of a computer device of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the embodiments described in the present application are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

Machine Learning (ML) is a multi-domain cross subject, and relates to multi-domain subjects such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and formal education learning.

The video playing method is related to the technology in the field of artificial intelligence machine learning, for example, a target anxiety estimation model can be constructed and trained through machine learning, and the like.

The video playing method can be integrated in a video playing device, the video playing device can be integrated in a video playing system, the video playing system can comprise one or more computer devices, the computer devices can comprise terminals or servers and the like, wherein the servers can be independent physical servers, server clusters or distributed systems formed by a plurality of physical servers, and cloud servers providing cloud computing services. The terminal may be, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart television, a payment device, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

Referring to fig. 1, the video playing method may be integrated in a video playing system, where the video playing system may include a mobile terminal and a server, and the mobile terminal may obtain the current remaining power of the mobile terminal where the video playing client is located; estimating anxiety change information of a client object caused by the current residual capacity relative to the reference residual capacity; when the anxiety change information meets the low-power consumption playing condition, sending a low-power consumption video clip request to a server; receiving a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request; and playing the video according to the target low-power-consumption video clip. The server can request to determine the low-power-consumption video clip by the low-power-consumption video clip and return the low-power-consumption video clip to the mobile terminal.

It should be noted that the scene schematic diagram of the video playing system shown in fig. 1 is merely an example, and the video playing system and the scene described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not form a limitation to the technical solution provided in the embodiment of the present application, and it is known by a person of ordinary skill in the art that the technical solution provided in the embodiment of the present application is also applicable to similar technical problems with the evolution of a video playing device and the occurrence of a new service scene.

The following are detailed descriptions. In this embodiment, a video playing method will be described in detail, and the video playing method may be integrated on a mobile terminal, as shown in fig. 2, where fig. 2 is a schematic flow diagram of the video playing method provided in this embodiment of the present application. The video playing method can comprise the following steps:

101. and acquiring the current residual electric quantity of the mobile terminal where the video playing client is located.

The video playing client may include a program for providing a video playing service for a user, the mobile terminal may include a computer device used in a moving process, and the current remaining power may include a remaining power displayed by the mobile terminal at a current time.

For example, when the video playing client 1 installed on the mobile terminal 1 is playing a movie, the mobile terminal 1 may determine the current remaining power L through the power query interface.

102. And estimating anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity.

The reference remaining power may include remaining power as reference information, and the anxiety change information may include change information of anxiety of the client object caused by the current remaining power to the reference remaining power. The anxiety change information may characterize a degree of change in anxiety mood of the client object.

Specifically, the anxiety change information may be estimated in various manners, for example, the operations of the user for the video playing client or the mobile terminal and the times of different operations, such as adjusting the playing brightness, adjusting the playing speed, clearing the background application, and the like, may be collected, and the anxiety change information of the client object may be estimated according to the times of the operations, and the like.

For example, the reference remaining capacity M may be determined according to the current remaining capacity L, and anxiety change information X of the object 1 of the mobile terminal caused by the current remaining capacity L to the reference remaining capacity M may be estimated.

In some embodiments, the step of estimating anxiety change information that the current remaining power induces the client object with respect to the reference remaining power may include:

acquiring a target anxiety estimation model, wherein the target anxiety estimation model comprises a target mapping relation set, and the target mapping relation set comprises mapping relations between a plurality of preset residual electric quantities and a plurality of preset anxiety information;

and estimating anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity according to the target mapping relation set.

The target anxiety estimation model may include a model for estimating anxiety-related information of the client object, and the target anxiety estimation model may include a target mapping relationship set, where the target mapping relationship set may include a plurality of groups of preset remaining power and preset anxiety information having mapping relationships.

The target anxiety prediction model can also be realized based on machine learning related technology of artificial intelligence, for example, a neural network model can be constructed, the neural network model is trained through a large amount of sample data, and the trained neural network model is the target anxiety prediction model.

For example, a target anxiety prediction model 1 is obtained, the target anxiety prediction model 1 includes a target mapping relation set 1, the target mapping relation set 1 includes mapping relations between a plurality of preset residual electric quantities and a plurality of preset anxiety information, and anxiety change information X of the object 1 caused by the current residual electric quantity L relative to the reference residual electric quantity M is predicted according to the target mapping relation set 1.

In some embodiments, the step of estimating anxiety change information that the current remaining power induces the client object relative to the reference remaining power according to the target mapping relationship set may include:

determining a reference residual capacity corresponding to the current residual capacity;

respectively estimating first anxiety information and second anxiety information corresponding to the current residual electric quantity and the reference residual electric quantity according to the target mapping relation set;

based on the first anxiety information and the second anxiety information, anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity is calculated.

The reference remaining capacity may be obtained from a current remaining capacity, and different current remaining capacities correspond to different reference remaining capacities, and specifically, a remaining capacity that is lower than the set number of units of the current remaining capacity may be determined as the reference remaining capacity, for example, if the set number is 2, and the current remaining capacity is 20, the reference remaining capacity is 18.

In the target mapping relation set, first anxiety information corresponding to a preset remaining power identical to the current remaining power can be determined, second anxiety information corresponding to a preset remaining power identical to the reference remaining power is determined, an anxiety difference value between the first anxiety information and the second anxiety information is calculated, a power difference value between the current remaining power and the reference remaining power is calculated, and the anxiety change information is obtained by dividing the anxiety difference value and the power difference value.

For example, anxiety information 1 and anxiety information 2 corresponding to the current remaining power L and the reference remaining power M are respectively estimated according to the target mapping relationship set 1, and (anxiety information 1-anxiety information 2)/(current remaining power L-reference remaining power M) is calculated to obtain anxiety change information X of the object 1.

In some embodiments, the step of obtaining a target anxiety prediction model may comprise:

receiving an initial anxiety estimation model sent by a server; determining an object anxiety prediction model of the client object; and fusing the initial anxiety prediction model and the object anxiety prediction model to obtain a target anxiety prediction model.

In order to estimate anxiety change information of a client object more accurately and play video more accurately, a target anxiety estimation model can be obtained by combining an initial anxiety estimation model and an object anxiety estimation model, wherein the initial anxiety estimation model can be obtained based on electric quantity of a large number of different objects and anxiety related data, the object anxiety estimation model can be obtained based on electric quantity of the client object and anxiety related data, and the target anxiety estimation model which is more accurate and more suitable for the client object can be obtained by combining the initial anxiety estimation model and the object anxiety estimation model.

The initial anxiety prediction model can comprise an anxiety prediction model sent by a server, the object anxiety prediction model can comprise an anxiety prediction model obtained by using relevant data of a client object, the initial anxiety prediction model and the object anxiety prediction model in the application can be updated, and the target anxiety prediction model used in the video playing process can also be updated in real time, so that a more accurate prediction result can be obtained.

The method for fusing the initial anxiety prediction model and the object anxiety prediction model may include various methods, for example, parameters of corresponding positions in the initial anxiety prediction model and the object anxiety prediction model may be fused, for example, the initial anxiety prediction model and the object anxiety prediction model may be connected to serve as different parts of the object anxiety prediction model, and the like.

For example, receiving an initial anxiety prediction model C sent by the server; determining a subject anxiety prediction model H of subject 2; and fusing the initial anxiety prediction model C and the object anxiety prediction model H to obtain a target anxiety prediction model 1.

In some embodiments, the step of fusing the initial anxiety prediction model and the object anxiety prediction model to obtain the target anxiety prediction model may include:

obtaining a first fusion weight of the initial anxiety model and obtaining a second fusion weight of the object anxiety model; and fusing the initial anxiety estimation model and the object anxiety estimation model based on the first fusion weight and the second fusion weight to obtain a target anxiety estimation model.

The first fusion weight and the second fusion weight respectively represent the importance degree of the initial anxiety prediction model and the object anxiety prediction model to the target anxiety prediction model, the first fusion weight and the second fusion weight can be in a numerical form, and the numerical value of the weight with higher importance degree is larger. The first fusion weight and the second fusion weight may be preset, or may be flexibly determined according to an actual application scenario, which is not limited herein.

For example, a preset first fusion weight of 0.3 and a preset second fusion weight of 0.7 may be obtained, and then 0.3 × initial anxiety prediction model C +0.7 × object anxiety prediction model H may be obtained to obtain target anxiety prediction model 1.

In some embodiments, the step of determining a subject anxiety prediction model for the client subject may comprise:

collecting a plurality of charging electric quantities of the mobile terminal;

and generating an object anxiety estimation model of the client object according to the plurality of charging electric quantities.

The charging capacity can include a residual capacity of the mobile terminal when the mobile terminal is connected with the charging device, and when the charging operation for the mobile terminal is identified, the residual capacity of the mobile terminal at the moment can be recorded. The charging electric quantity can be continuously collected within a period of time, and a plurality of charging electric quantities are obtained.

The process of generating the object anxiety prediction model according to the plurality of charging electric quantities can comprise the steps of constructing an anxiety prediction network model, taking the plurality of charging electric quantities as training sample data, and training the anxiety prediction network model to obtain the trained object anxiety prediction model.

In some embodiments, the object anxiety prediction model includes an object mapping relationship set, and the step of generating the object anxiety prediction model of the client object according to the plurality of charging capacities may include:

updating the initial anxiety values according to the charging electric quantities to obtain target anxiety values corresponding to the residual electric quantities;

and carrying out standardization processing on the target anxiety values to obtain a plurality of anxiety information corresponding to the residual electric quantity, wherein the corresponding relation between the residual electric quantity and the anxiety information forms an object mapping relation set.

The object anxiety prediction model may include an object mapping relationship set, the object mapping relationship set may include a plurality of groups of remaining battery capacity and anxiety information having mapping relationships, and specifically, the process of obtaining the object mapping relationship set may include:

a plurality of initial anxiety values are set and assigned, for example, each initial anxiety value is assigned 0 and corresponds to a remaining battery capacity, for example, 100 initial anxiety values are set, and the 100 initial anxiety values correspond to the remaining battery capacity of the mobile terminal being 100 to 1 respectively.

The initial anxiety value may be updated according to the charging capacity, for example, a remaining capacity equal to the charging capacity is determined, and the initial anxiety value corresponding to the remaining capacity is updated, and the updating of the initial anxiety value may be performed by accumulating the initial anxiety values, such as adding 1 to 0, i.e., updating the initial anxiety value once. The above operation is performed on each charging capacity, that is, the plurality of initial anxiety values are updated, so that a plurality of target anxiety values corresponding to the plurality of remaining capacities are obtained. There may be repeated values in the plurality of charge capacities, and thus, the update for a certain initial anxiety value may be multiple times; the plurality of charge capacities may be the same as a part of all remaining capacities, and thus a certain initial anxiety value may not be updated.

After the initial anxiety values are updated according to all the charging electric quantities, a plurality of target anxiety values corresponding to a plurality of residual electric quantities are obtained, the target anxiety values are subjected to standardization processing, anxiety information corresponding to each target anxiety value is obtained, and the standardization processing can be used for scaling the data in equal proportion, so that all the data are in a smaller numerical value range, and subsequent use is facilitated. For example, if the number of the charged electric quantities may be 50, dividing each target anxiety value by 50 to obtain anxiety information corresponding to each target anxiety value.

In some embodiments, the step of "updating the initial anxiety values according to the charging electric quantities to obtain target anxiety values corresponding to the remaining electric quantities" may include:

updating the initial anxiety value corresponding to each target residual electric quantity and the initial anxiety value corresponding to the residual electric quantity smaller than each target residual electric quantity to obtain a plurality of target anxiety values corresponding to a plurality of residual electric quantities.

The target remaining capacity may include a remaining capacity matching the charging capacity, for example, the target remaining capacity may include a remaining capacity identical to the charging capacity.

At least one remaining capacity smaller than or equal to the target remaining capacity of all remaining capacities may be determined, and the initial anxiety value corresponding to the at least one remaining capacity may be updated, for example, if the charging capacity may be 20, the initial anxiety value corresponding to the remaining capacity of 1 to 20 may be updated. And operating each charging electric quantity according to the process, namely updating the plurality of initial anxiety values according to the plurality of charging electric quantities to obtain a plurality of target anxiety values.

103. And when the anxiety change information meets the low-power consumption playing condition, sending a low-power consumption video clip request to the server.

The low-power-consumption playing condition may include a filtering condition for the anxiety change information, and the form of the low-power-consumption playing condition may change with the form of the anxiety change information, for example, the anxiety change information may be a numerical value, and then the low-power-consumption playing condition may be a threshold; for another example, the anxiety change information may be a text, and the low power consumption playing condition may be a specific text, and correspondingly, the anxiety change information satisfies the low power consumption playing condition, and may be that the anxiety change information is greater than the first threshold and smaller than the second threshold, or may be that the anxiety change information is "text 1", and so on.

For example, when the anxiety change information X satisfies the preset low power consumption play condition, the low power consumption video clip request 1 may be sent to the server 1.

The video playing client side can play online videos and offline videos, the technical means for achieving video playing in different video playing scenes can be different, for example, in the offline video playing scene, a video file used for achieving video playing can be a file downloaded to a mobile terminal in advance, and when anxiety change information meets a low-power-consumption playing condition, the low-power-consumption video file can be directly obtained from a storage space of the mobile device.

In some embodiments, the video playing method may further include the steps of:

receiving an index file of a target video sent by a server, wherein the index file comprises address information of a plurality of video segments of the target video;

at this time, the step "sending the low power consumption video clip request to the server when the anxiety change information satisfies the low power consumption play condition" may include:

when the anxiety change information meets the low-power consumption playing condition, determining the address information of the target low-power consumption video clip to be played from the index file;

generating a low-power video clip request for requesting a target low-power video clip;

and sending a low-power-consumption video clip request to the server based on the address information.

If the video playing scene is an online video playing scene, video playing can be performed through different Streaming media transmission protocols, for example, HTTP Live Streaming (a Streaming media network transmission protocol based on HTTP), HTTP Dynamic Streaming (a Streaming media network transmission protocol based on HTTP), dynamic Adaptive Streaming over HTTP (a Streaming media network transmission protocol based on HTTP Dynamic Adaptive bit rate Streaming), and the like. The names of the index files in different Streaming media transmission protocols are different, such as an MPD file (a kind of index file) in a DASH protocol (i.e., dynamic Adaptive Streaming over HTTP), an f4m index file in an HDS protocol, and so on.

The target video can comprise a video which is played online by a video playing client, the index file can comprise an index file of a low-power-consumption video clip and an index file of a non-low-power-consumption video clip (namely, a video clip used for normally playing the video), if the anxiety change information meets a low-power-consumption playing condition, the mobile terminal can determine address information of the target low-power-consumption video clip to be played to be acquired from the index file of the low-power-consumption video clip, generate a low-power-consumption video clip request for requesting the target low-power-consumption video clip, send the low-power-consumption video clip request to a specific server according to the address information, and acquire the target low-power-consumption video clip.

In some embodiments, the video playing method may further include the steps of:

when the charging operation aiming at the mobile terminal is detected, recording the charging electric quantity at the current moment;

the collected charging electric quantities are sent to a server, the server is triggered to sample the received charging electric quantities of the mobile terminals to obtain target charging electric quantities, and the target anxiety estimation model is updated according to the target charging electric quantities to obtain an updated target anxiety estimation model.

In the application, the anxiety estimation model stored on the server can be updated, specifically, the video playing client can record the charging electric quantity of the mobile terminal where the client is located and regularly send the recorded charging electric quantities to the server, and the server can receive the charging electric quantities from a large number of different mobile terminals and update the model according to the charging electric quantities.

Specifically, the server can sample a plurality of received charging electric quantities from a plurality of mobile terminals, the sampling method can be flexibly selected, such as random sampling and hierarchical sampling, a plurality of target charging electric quantities can be obtained by sampling, the number of the target charging electric quantities is smaller than that of the charging electric quantities, on one hand, data processing pressure of the server can be reduced by sampling, on the other hand, more representative data can be obtained, and on the other hand, the influence of individual pole data on result accuracy can be avoided.

The method for updating the anxiety estimation model through the target charging capacity can include various modes, such as retraining the anxiety estimation model as training data, generating a new anxiety estimation model, fusing the new anxiety estimation model and the original anxiety estimation model, wherein the fusion process is the process of updating the anxiety estimation model, and the like.

104. And receiving the target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request.

The target low-power-consumption video clip may include a video clip with lower power consumption during playing, and the low-power-consumption video clip may be obtained by processing common video data, for example, adjusting color data of a video image frame, so as to reduce power consumption of a screen of the mobile terminal for displaying the video clip, because on some types of screens, pixel points displaying specific colors consume less power, for example, the power consumption for displaying green pixel points on an OLED screen is about half of that of blue pixel points.

For example, the receiving server requests the target low-power video clip 1 fed back based on the low-power video clip 1.

105. And playing the video according to the target low-power-consumption video clip.

For example, according to the target low-power video segment 1, a low-power movie is played.

According to the method and the device, the current residual capacity of the mobile terminal where the video playing client is located can be estimated, the current residual capacity is estimated to be within the reference residual capacity interval corresponding to the current residual capacity, the anxiety transformation information of the client object is triggered, the anxiety change information of the client object can be perceived, video playing is correspondingly carried out, when the anxiety change information meets the low-power-consumption playing condition, a low-power-consumption video clip is used for playing, the power consumption of video playing is reduced, the power-down speed of a mobile terminal is slowed down, and the anxiety mood of the client object is further relieved.

The method described in the above embodiment is further described in detail by way of example.

The present application will take a video playing system integrated in a computer device as an example to introduce a video playing method, where the computer device may include a mobile terminal and a server, as shown in fig. 3, and fig. 3 is a schematic flow diagram of a video playing method provided in an embodiment of the present application. The video playing method can comprise the following steps:

201. and the mobile terminal receives the anxiety estimation model sent by the server.

202. The mobile terminal updates the prediction model of the anxiety through the collected multiple charging electric quantities to obtain the prediction model of the target anxiety.

203. The mobile terminal acquires the current residual electric quantity of the mobile terminal where the video playing client is located.

204. The mobile terminal predicts anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity through a target anxiety prediction model.

205. And when the anxiety change information meets the low-power-consumption playing condition, the mobile terminal sends a low-power-consumption video clip request to the server.

206. And the mobile terminal receives a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request.

207. And the mobile terminal plays the video according to the target low-power-consumption video clip.

In this application, a video playing client on a mobile terminal may perform online video playing or Live video playing, and the online video playing or Live video playing may be performed based on a certain mobile Streaming media transmission protocol, for example, a mobile Streaming media transmission protocol based on HTTP, such as HTTP Live Streaming (HLS, which belongs to a mobile Streaming media transmission protocol based on HTTP), HTTP Dynamic Streaming (HDS, which belongs to a mobile Streaming media transmission protocol based on HTTP), dynamic Adaptive Streaming over HTTP (DASH, which belongs to a mobile Streaming media transmission protocol based on HTTP), and the like.

The basic principle of the HTTP-based mobile streaming media transmission protocol is to slice a video to obtain a large number of video segments, where the video length of each video segment is in seconds, and an index file of the video segments is generated at the same time, where the index file includes identification information of the video segment and an address of the video segment on a server, and when a mobile terminal requests a video play request from the server, the server returns the index file, and the mobile terminal obtains a video segment used for video play according to the address of the index file.

For example, referring to fig. 4, a streaming media video transmission process based on HTTP is shown by taking a DASH protocol as an example, where an index file of the DASH protocol is an MPD file, a video player on the mobile terminal sends a play request to a video server corresponding to the video player, the video server feeds back the MDP file, the video player on the mobile terminal can send a video segment request of a required video segment to the video server according to an address of the video segment in the MPD file, and the video server can return the video segment according to the video segment request.

The video segments transmitted based on the mobile streaming media transmission protocol may include low-power-consumption video segments after low-power-consumption video transcoding, the video server may perform low-power-consumption transcoding processing on the original video segments, store the processed low-power-consumption video segments in the server in segments, and generate an index file of the low-power-consumption video segments, and the low-power-consumption transcoding processing mode includes, but is not limited to: editing the color content (such as RGB values, etc.) of the video segment, adjusting the brightness/contrast of the video segment, etc.

In the process of playing the video, the mobile terminal and the server participate in the video playing process, see fig. 5, the mobile terminal may include a video player for playing the video, a Low-power video scheduler for determining whether to send a Low-power video clip request to the server, and a battery state interface for querying a remaining power (such as a charging power and a current remaining power) of the mobile terminal, the video server may include a video clip and an index file of a target video, a public LBA model (Low-battery Anxiety model) containing Anxiety information of a predictive user caused by the remaining power, and a public LBA model management module for updating the public LBA model, and perform Low-power transcoding on an original video clip to obtain a Low-power video transcoder of the Low-power video clip. The low battery anxiety model belongs to one of anxiety prediction models in the application.

The video playing method of the present application may include an online playing mode and an offline playing mode, and specifically refer to fig. 6, in the online mode, a low-power-consumption video scheduler of a mobile terminal obtains a remaining power (i.e., a current remaining power) of the mobile terminal through a battery state interface, and then a decision scheduling module thereof makes a decision as to whether to perform a low-power-consumption video clip request or not through a certain scheduling algorithm according to the obtained current remaining power and a private LBA model of a user of the mobile terminal, and finally transmits a scheduling result to a video player, and the video player performs a video index file and a video clip request according to the decision result.

Referring to fig. 6, in the offline mode, when the video player of the mobile terminal plays a video for the first time, the video server sends the public LBA model to the video player, and the private LBA model management module of the low-power video scheduler of the mobile terminal obtains and stores the public LBA model, and then the low-power video scheduler may sense the charging behavior of the client through the battery status interface, and locally record the remaining power (i.e., the charging power) of the mobile terminal when the charging behavior of the user occurs, and update the previously obtained public LBA model with the private LBA model management module by using the obtained remaining power for multiple times, so that the public LBA model better conforms to the low-power anxiety characteristic of the user of the mobile terminal.

The video server samples a plurality of residual electric quantities sent by a plurality of mobile terminals, and updates the original public LBA model according to the sampled residual electric quantities, and the updated public LBA model can be distributed to the mobile terminals.

As shown in fig. 7, specifically, a client video player may request a video server to play a video, and the video server may return an index file (such as an MPD file) of the video to the video player; the video player sends a scheduling request to the low-power-consumption video scheduler, and the video scheduling can inquire and return the residual electric quantity of the current equipment through a battery state interface; the low-power-consumption video scheduler can give a scheduling result of whether to request the low-power-consumption video or not according to the current electric quantity information and the private LBA model of the client through a certain scheduling algorithm and returns the scheduling result to the video player; the video player requests a corresponding (low-power consumption or non-low-power consumption) video file segment from the video server according to the scheduling result and the video index file, and the video server returns the corresponding video segment and plays the video segment at the client; and after every set time, repeating the steps until the video playing is finished or the user quits the video player.

Distribution and update of LBA model see fig. 8, which may specifically include:

1) Model distribution: when a client installs a video APP or carries out video on demand/live broadcast for the first time, the video server distributes an initial public LBA model to the client. The initial model can be obtained by investigating data, and can also be simply assumed through a priori knowledge.

2) Local deployment: the LBA model distributed to the client is acquired and stored by a private LBA model management module of the low-power-consumption video scheduler, and is used as one of input information of a decision scheduling module scheduling algorithm.

3) Recording a charging event: for any customer, whether watching video or not, as long as its low power video scheduler (via the battery status interface) senses the customer's charging behavior, the charging event (the remaining charge of the device at the time of charging, referred to as the charging threshold) is recorded locally.

4) Updating the model: with the acquired multi-charge threshold information, the private LBA model management module can make it better conform to the low battery anxiety characteristic of the customer by updating the previous public LBA model.

5) Sampling charging events: the video server randomly samples the charging thresholds of a number of clients.

6) Updating the model: the 'public LBA model management module' of the video server updates the original public LBA model by an update algorithm.

7) Deployment at a server side: the updated public LBA model is used as a new model to be acquired and stored by the public LBA model management module, and is subsequently distributed to newly added clients.

The construction principle of the LBA model may include: the LBA model is essentially a mapping (expressed by the function f (-)) that reflects the degree of anxiety between the amount of remaining power of the client mobile and the level of anxiety that the user motivates to generate low power: the remaining capacity is an independent variable (represented by a random variable e), the value range is [0,100% ], and the corresponding battery capacity is from 0 to a full-charge state; the anxiety degree of the user is a dependent variable (represented by a), the value range is [0,1], and the anxiety degree corresponds to the state from no low battery anxiety to the highest low battery anxiety feeling. Generally, the low battery anxiety degree of the client is increased along with the reduction of the terminal battery, but a specific quantitative relation between the two needs to be established by a certain method.

Specifically, the method for constructing the public LBA model may include:

1) A simple hypothesis: f (-) is approximated using an off-the-shelf monotonically decreasing function, for example, assuming f (-) is a linear function, the public LBA model can be expressed as a =1-e.

2) User survey method: first, charging threshold information of a large number of mobile users is obtained in the form of questionnaires, for example, by the question "do you have a thought or impulse of charging when the amount of electricity left in a mobile phone is enough in the case of convenient charging? (optional answers from 1 to 100%, particle size 1%) ". Assuming that charging threshold information of N users is obtained in a manner similar to the above questionnaire (each threshold is an integer in the interval [1,100], which represents that the user selects charging when the electric quantity is several percent), the corresponding value of f (-) under different discrete electric quantity values can be obtained by using the following LBA model construction algorithm.

The LBA model construction algorithm may include: it is known that: the charging thresholds of N users are initialized first: firstly, 100 initial values are set as 0 variables, the reference numbers are 1,2, \8230, the reference numbers are \8230, and 100 represents the electric quantity from 0 to 100 percent; then, counting: for each charging threshold, if the answer is b (charge capacity), then 1 is added to the variable labeled 1 to b; and (3) accumulation: after N rounds of counting, obtaining 100 variable values between [0, N ]; and (4) final standardization: by dividing each variable by N, 100 real values between 0,1 are obtained, representing the user's anxiety at different electrical quantities (1%, 2%, \ 8230;, 100%) after normalization.

Construction of private LBA model: for each client, its initial private LBA model comes from the video server, i.e., the initial private LBA model is consistent with the public LBA model.

The method for updating the LBA model may be divided into a private LBA model update and a public LBA model update, and specifically, the private LBA model update may include: the original private LBA model can be updated to better conform to the low battery anxiety change characteristics of the client itself, using the charging event (charging threshold) information collected by the client. Assuming that the client has collected M charging events for the client, i.e., M charging thresholds (each threshold is an integer within the interval [1,100], representing that each time the client will charge at a few percent of the charge), the LBA model update is performed using the following method:

firstly, establishing an LBA model by using an algorithm 1 (LBA model establishment algorithm) according to the charging threshold of M users, and marking the model as f1; then, the original private LBA model is marked as f2, and then the new private LBA model is obtained by performing weighted average on the f1 model and the f2 model: f = α · f1+ (1- α) · f2; wherein α is the private LBA model update weight coefficient, the value is (0, 1), and the larger the value is, the larger the influence of the local charging threshold on the LBA model update is, and in actual use, the video service provider can set the update weight coefficient according to the requirement.

Public LBA model updates may include: the video server periodically samples the random charging threshold value in the client, namely randomly selects a certain number of clients, and the clients randomly select the charging threshold value once and report the charging threshold value to the server. The server updates the common LBA model with these several number of charge thresholds collected each cycle. Assuming that K charging thresholds of users are collected in a certain period, the LBA model in the period is updated as follows:

firstly, establishing an LBA model by using an algorithm 1 (LBA model establishing method) according to the charging threshold values of the K users, and marking the model as f1; then, the original public LBA model is marked as f2, and then the f1 and f2 models are weighted and averaged to obtain a new private LBA model: f = β · f1+ (1- β) · f2; wherein β is a public LBA model update weight coefficient, and the value is (0, 1), the larger the value is, the larger the influence of the newly sampled charge threshold on the LBA model update is, and in actual use, a video service provider can set the update weight coefficient according to the requirement.

The decision scheduling algorithm may include: in the process of playing videos by a client, a scheduling decision module of a low-power-consumption video scheduler periodically inquires the residual electric quantity of current mobile equipment, and determines whether to request a low-power-consumption video file by combining a private LBA (logical block addressing) model of the client by using the following algorithm:

(1) Let the private LBA model of the client be f, the slope value of the model at the device power level e can be approximately expressed as:

f’(e)＝[f(e-1％)-f(e)]/1％

f '(e) represents the rate at which the user's sense of low battery anxiety increases when the device has a battery remaining of e.

(2) If the judgment condition f' (e) > gamma is satisfied, performing a low-power-consumption video request, otherwise performing a normal video file request (similar to a DASH protocol); wherein gamma is a preset threshold value for starting the low-power-consumption video request, the range is [0, + ∞ ], the larger the value is set, the higher the threshold value representing the request of the low-power-consumption video is, otherwise, the lower the threshold value is; the value of γ may be set by the service provider in a unified manner, or may be set by the user himself or herself as required.

In order to better implement the video playing method provided in the embodiment of the present application, an embodiment of the present application further provides a device based on the video playing method. The meaning of the noun is the same as that in the video playing method, and specific implementation details can refer to the description in the method embodiment.

Fig. 9 is a schematic structural diagram of a video playing apparatus according to an embodiment of the present application, where the video playing apparatus may include an obtaining module 301, a predicting module 302, a sending module 303, a receiving module 304, and a playing module 305, where,

an obtaining module 301, configured to obtain a current remaining power of a mobile terminal where a video playing client is located;

the estimation module 302 is configured to estimate anxiety change information of the client object caused by the current remaining power relative to the reference remaining power;

a sending module 303, configured to send a low-power-consumption video clip request to the server when the anxiety change information meets the low-power-consumption playing condition;

a receiving module 304, configured to receive a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request;

and a playing module 305, configured to play a video according to the target low-power-consumption video segment.

the obtaining submodule is used for obtaining a target anxiety prediction model, the target anxiety prediction model comprises a target mapping relation set, and the target mapping relation set comprises mapping relations between a plurality of preset residual electric quantities and a plurality of preset anxiety information;

the pre-estimation unit is used for respectively pre-estimating first anxiety information and second anxiety information corresponding to the current residual electric quantity and the reference residual electric quantity according to the target mapping relation set;

and the calculating unit is used for calculating anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity based on the first anxiety information and the second anxiety information.

and the fusion unit is used for fusing the initial anxiety estimation model and the object anxiety estimation model to obtain a target anxiety estimation model.

In some embodiments, the fusion unit is specifically configured to:

acquiring a first fusion weight of the initial anxiety model and a second fusion weight of the object anxiety model;

and fusing the initial anxiety estimation model and the object anxiety estimation model based on the first fusion weight and the second fusion weight to obtain a target anxiety estimation model.

and the generating subunit is used for generating an object anxiety estimation model of the client object according to the plurality of charging electric quantities.

updating the initial anxiety value corresponding to each target residual electric quantity and the initial anxiety value corresponding to the residual electric quantity smaller than each target residual electric quantity to obtain a plurality of target anxiety values corresponding to a plurality of residual electric quantities;

and carrying out standardization processing on the target anxiety values to obtain a plurality of anxiety information corresponding to the residual electric quantities, wherein the corresponding relation between the residual electric quantities and the anxiety information forms an object mapping relation set.

In some embodiments, the video playback apparatus further includes:

the file receiving module is used for receiving an index file of the target video sent by the server, wherein the index file comprises address information of a plurality of video segments of the target video;

at this time, the sending module is specifically configured to:

In some embodiments, the video playback device further comprises:

In the application, the obtaining module 301 may obtain a current remaining power of a mobile terminal where a video playing client is located, the estimating module 302 may estimate anxiety change information of a client object caused by the current remaining power relative to a reference remaining power, the sending module 303 may send a low-power-consumption video clip request to a server when the anxiety change information satisfies a low-power-consumption playing condition, the receiving module 304 may receive a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request, and finally the playing module 305 may play a video according to the target low-power-consumption video clip.

In addition, an embodiment of the present application further provides a computer device, where the computer device may be a terminal or a server, as shown in fig. 10, which shows a schematic structural diagram of the computer device according to the embodiment of the present application, and specifically:

the computer device may include components such as a processor 401 of one or more processing cores, memory 402 of one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 10 is not intended to be limiting of computer devices and may include more or fewer components than those shown, or some of the components may be combined, or a different arrangement of components. Wherein:

the processor 401 is a control center of the computer device, connects various parts of the entire computer device using various interfaces and lines, performs various functions of the computer device and processes data by operating or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory 402, thereby integrally monitoring the computer device. Optionally, processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles operating systems, user pages, application programs, and the like, and the modem processor mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.

The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the computer device, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.

The computer device further comprises a power supply 403 for supplying power to the various components, and preferably, the power supply 403 is logically connected to the processor 401 through a power management system, so that the functions of managing charging, discharging, and power consumption are realized through the power management system. The power supply 403 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

The computer device may also include an input unit 404, the input unit 404 being operable to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

Although not shown, the computer device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 401 in the computer device loads the executable file corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application programs stored in the memory 402, thereby implementing various functions as follows:

acquiring the current residual electric quantity of a mobile terminal where a video playing client is located; estimating anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity; when the anxiety change information meets the low-power-consumption playing condition, sending a low-power-consumption video clip request to a server; receiving a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request; and playing the video according to the target low-power-consumption video clip.

The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.

According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the method provided in the various alternative implementations of the above embodiments.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by a computer program, which may be stored in a computer-readable storage medium and loaded and executed by a processor, or by related hardware controlled by the computer program.

To this end, an embodiment of the present application further provides a storage medium, where a computer program is stored, where the computer program can be loaded by a processor to execute steps in any one of the video playing methods provided in the embodiments of the present application. For example, the computer program may perform the steps of:

acquiring the current residual capacity of a mobile terminal where a video playing client is located; estimating anxiety change information of a client object caused by the current residual capacity relative to the reference residual capacity; when the anxiety change information meets the low-power consumption playing condition, sending a low-power consumption video clip request to a server; receiving a target low-power-consumption video clip returned by the server based on the low-power-consumption video clip request; and playing the video according to the target low-power-consumption video clip.

Wherein the storage medium may include: read Only Memory (ROM), random Access Memory (RAM), magnetic or optical disks, and the like.

Since the computer program stored in the storage medium can execute the steps in any video playing method provided in the embodiments of the present application, beneficial effects that can be achieved by any video playing method provided in the embodiments of the present application can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.

The video playing method, apparatus, storage medium and device provided in the embodiments of the present application are described in detail above, and specific examples are applied herein to explain the principles and embodiments of the present application, and the description of the embodiments is only used to help understand the method and core ideas of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A video playback method, comprising:

and playing the video according to the target low-power-consumption video clip.

2. The method of claim 1, wherein the predicting the current remaining power to cause anxiety change information of a client object relative to a reference remaining power comprises:

and estimating anxiety change information of the client object caused by the current residual electric quantity relative to the reference residual electric quantity according to the target mapping relation set.

3. The method of claim 2, wherein the predicting the anxiety change information of the client object caused by the current remaining power relative to the reference remaining power according to the target mapping relation set comprises:

calculating anxiety change information of the client object caused by the current residual capacity relative to the reference residual capacity based on the first anxiety information and the second anxiety information.

4. The method of claim 2, wherein the obtaining a target anxiety estimate model comprises:

receiving an initial anxiety estimation model sent by the server;

determining an object anxiety pre-estimation model of the client object;

and fusing the initial anxiety prediction model and the object anxiety prediction model to obtain the target anxiety prediction model.

5. The method according to claim 4, wherein said fusing said initial anxiety prediction model and said object anxiety prediction model to obtain said target anxiety prediction model comprises:

obtaining a first fusion weight of the initial anxiety model and obtaining a second fusion weight of the object anxiety model;

6. The method of claim 4, wherein determining the object anxiety prediction model of the client object comprises:

collecting a plurality of charging electric quantities of the mobile terminal;

and generating the object anxiety estimation model of the client object according to the plurality of charging electric quantities.

7. The method of claim 6, wherein the object anxiety prediction model comprises a set of object mapping relationships, and wherein generating the object anxiety prediction model for the client object based on the plurality of charging capacities comprises:

8. The method of claim 7, wherein the updating the initial anxiety values according to the charging capacities to obtain target anxiety values corresponding to the remaining capacities comprises:

updating an initial anxiety value corresponding to each target remaining power amount and an initial anxiety value corresponding to a remaining power amount smaller than each target remaining power amount to obtain the plurality of target anxiety values corresponding to the plurality of remaining power amounts.

9. The method of claim 1, further comprising:

receiving an index file of a target video sent by the server, wherein the index file comprises address information of a plurality of video clips of the target video;

when the anxiety change information meets the low-power consumption playing condition, sending a low-power consumption video clip request to a server, wherein the request comprises:

10. The method of claim 2, further comprising:

sending a plurality of collected charging electric quantities to the server, triggering the server to sample the plurality of received charging electric quantities of the plurality of mobile terminals to obtain a plurality of target charging electric quantities, and updating the target anxiety estimation model according to the plurality of target charging electric quantities to obtain an updated target anxiety estimation model.

11. A video playback apparatus, comprising:

the acquisition module is used for acquiring the current residual electric quantity of the mobile terminal where the video playing client is located;

the sending module is used for sending a low-power-consumption video clip request to a server when the anxiety change information meets a low-power-consumption playing condition;

12. A storage medium, characterized in that it stores a plurality of computer programs adapted to be loaded by a processor for performing the steps of the method according to any one of claims 1 to 10.

13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 10 when executing the computer program.