Disclosure of Invention
The disclosure provides a method, a device, an electronic device and a storage medium for generating network bandwidth prediction information, so as to at least solve the problem that network bandwidth information of a terminal device cannot be accurately acquired in advance in the related art. The technical scheme of the present disclosure is as follows:
According to a first aspect of an embodiment of the present disclosure, there is provided a network bandwidth prediction information generating method, including:
acquiring historical network bandwidth data of terminal equipment before prediction time;
outputting a network bandwidth prediction interval for the terminal equipment according to the historical network bandwidth data; the confidence level of the network bandwidth prediction interval including the target network bandwidth value is matched with the current service scene type; the target network bandwidth value is a network bandwidth true value corresponding to the terminal equipment at the prediction time; the current service scene type is a service scene type corresponding to the current service provided by the terminal equipment;
and generating network bandwidth prediction information corresponding to the terminal equipment at the prediction time according to the network bandwidth prediction interval.
In one possible implementation manner, the outputting, according to the historical network bandwidth data, a network bandwidth prediction interval for the terminal device includes:
according to the historical network bandwidth data, determining network bandwidth distribution information of the terminal equipment at target time;
acquiring a service scene type corresponding to a current service provided by the terminal equipment, and determining a network bandwidth prediction interval aiming at the terminal equipment in the network bandwidth distribution information according to the service scene type;
And the interval size corresponding to the network bandwidth prediction interval and the bandwidth sensitivity corresponding to the service scene type are in positive correlation.
In one possible implementation manner, in a case that the target time is a historical time period before the predicted time, the determining network bandwidth distribution information of the terminal device at the target time according to the historical network bandwidth data includes:
according to the historical network bandwidth data, determining network bandwidth sampling values corresponding to sampling points of the terminal equipment in the historical time period;
performing quantile counting operation on the network bandwidth sampling values corresponding to the sampling points to obtain bandwidth counting quantile information of the terminal equipment at the target time;
and determining the bandwidth statistics counting bit number information as the network bandwidth distribution information.
In one possible implementation manner, the determining, according to the size of the prediction interval corresponding to the service scene type, the network bandwidth prediction interval for the terminal device in the network bandwidth distribution information includes:
determining a target quantile interval according to an interval limit parameter corresponding to the service scene type; the target quantile interval comprises a first quantile and a second quantile; the first quantile, the second quantile and the interval limit parameter meet a preset relationship; the interval size of the fractional interval and the bandwidth sensitivity corresponding to the service scene type are in positive correlation;
Determining the network bandwidth sampling value at the first quantile as a first network bandwidth value in the network bandwidth distribution information, and determining the network bandwidth sampling value at the first quantile as a second network bandwidth value in the network bandwidth distribution information;
and determining the network bandwidth prediction interval according to the first network bandwidth value and the second network bandwidth value.
In one possible implementation manner, in the case that the target time is the predicted time, the determining, according to the historical network bandwidth data, network bandwidth distribution information of the terminal device at the target time includes:
extracting historical network bandwidth characteristics in the historical network bandwidth data;
inputting the historical network bandwidth characteristics into a pre-trained network bandwidth information output model to obtain model output information; the model output information comprises probability information that the network bandwidth true value corresponding to the predicted time of the terminal equipment is in each preset network bandwidth candidate interval;
and determining the model output information as the network bandwidth distribution information.
In one possible implementation manner, the determining, according to the size of the prediction interval corresponding to the service scene type, the network bandwidth prediction interval for the terminal device in the network bandwidth distribution information includes:
Determining a target confidence interval according to the target confidence level corresponding to the service scene type; the target confidence interval comprises an interval upper boundary and an interval lower boundary; the target confidence level and the bandwidth sensitivity corresponding to the service scene type are in positive correlation;
determining a third network bandwidth value corresponding to the upper boundary of the interval in the model output information, and determining a fourth network bandwidth value corresponding to the lower boundary of the interval in the model output information;
and determining the network bandwidth prediction interval according to the third network bandwidth value and the fourth network bandwidth value.
In one possible implementation manner, the training method adopted by the pre-trained network bandwidth information output model includes:
obtaining model training data; the model training data comprises at least one sample network bandwidth characteristic and a network bandwidth label interval corresponding to each sample network bandwidth characteristic; the sample network bandwidth characteristics are determined by sampling network bandwidth data corresponding to a data transmission task with preset times; the network bandwidth label interval is a bandwidth interval where a network bandwidth sampling value corresponding to a target data transmission task is located; the target data transmission task is the latest data transmission task in the data transmission tasks with preset times;
And training the network bandwidth information output model to be trained by adopting the model training data until the trained network bandwidth information output model meets the preset training ending condition, so as to obtain the pre-trained network bandwidth information output model.
In one possible implementation manner, the generating, according to the network bandwidth prediction interval, network bandwidth prediction information corresponding to the predicted time by the terminal device includes:
acquiring a network bandwidth lower limit value of the network bandwidth prediction interval;
and determining the network bandwidth lower limit value as a network bandwidth predicted value corresponding to the predicted time of the terminal equipment, and obtaining the network bandwidth predicted information.
According to a second aspect of the embodiments of the present disclosure, there is provided a network bandwidth prediction information generating apparatus, including:
an acquisition unit configured to perform acquisition of historical network bandwidth data of the terminal device before the predicted time;
an output unit configured to perform outputting a network bandwidth prediction interval for the terminal device according to the historical network bandwidth data; the confidence level of the network bandwidth prediction interval including the target network bandwidth value is matched with the current service scene type; the target network bandwidth value is a network bandwidth true value corresponding to the terminal equipment at the prediction time; the current service scene type is a service scene type corresponding to the current service provided by the terminal equipment;
And the generating unit is configured to generate network bandwidth prediction information corresponding to the terminal equipment at the prediction time according to the network bandwidth prediction interval.
In one possible implementation manner, the output unit is configured to determine network bandwidth distribution information of the terminal device at a target time according to the historical network bandwidth data; acquiring a service scene type corresponding to a current service provided by the terminal equipment, and determining a network bandwidth prediction interval aiming at the terminal equipment in the network bandwidth distribution information according to the service scene type; and the interval size corresponding to the network bandwidth prediction interval and the bandwidth sensitivity corresponding to the service scene type are in positive correlation.
In a possible implementation manner, in the case that the target time is a historical time period before the predicted time, the output unit is configured to determine, according to the historical network bandwidth data, a network bandwidth sampling value corresponding to each sampling point of the terminal device in the historical time period; performing quantile counting operation on the network bandwidth sampling values corresponding to the sampling points to obtain bandwidth counting quantile information of the terminal equipment at the target time; and determining the bandwidth statistics counting bit number information as the network bandwidth distribution information.
In one possible implementation, the output unit is configured to determine a target quantile interval according to an interval limit parameter corresponding to the service scene type; the target quantile interval comprises a first quantile and a second quantile; the first quantile, the second quantile and the interval limit parameter meet a preset relationship; the interval size of the fractional interval and the bandwidth sensitivity corresponding to the service scene type are in positive correlation; determining the network bandwidth sampling value at the first quantile as a first network bandwidth value in the network bandwidth distribution information, and determining the network bandwidth sampling value at the first quantile as a second network bandwidth value in the network bandwidth distribution information; and determining the network bandwidth prediction interval according to the first network bandwidth value and the second network bandwidth value.
In one possible implementation, in the case that the target time is at the predicted time, the output unit is configured to perform extracting a historical network bandwidth feature in the historical network bandwidth data; inputting the historical network bandwidth characteristics into a pre-trained network bandwidth information output model to obtain model output information; the model output information comprises probability information that the network bandwidth true value corresponding to the predicted time of the terminal equipment is in each preset network bandwidth candidate interval; and determining the model output information as the network bandwidth distribution information.
In one possible implementation manner, the output unit is configured to determine a target confidence interval according to a target confidence level corresponding to the service scene type; the target confidence interval comprises an interval upper boundary and an interval lower boundary; the target confidence level and the bandwidth sensitivity corresponding to the service scene type are in positive correlation; determining a third network bandwidth value corresponding to the upper boundary of the interval in the model output information, and determining a fourth network bandwidth value corresponding to the lower boundary of the interval in the model output information; and determining the network bandwidth prediction interval according to the third network bandwidth value and the fourth network bandwidth value.
In one possible implementation, the apparatus is further configured to perform acquiring model training data; the model training data comprises at least one sample network bandwidth characteristic and a network bandwidth label interval corresponding to each sample network bandwidth characteristic; the sample network bandwidth characteristics are determined by sampling network bandwidth data corresponding to a data transmission task with preset times; the network bandwidth label interval is a bandwidth interval where a network bandwidth sampling value corresponding to a target data transmission task is located; the target data transmission task is the latest data transmission task in the data transmission tasks with preset times; and training the network bandwidth information output model to be trained by adopting the model training data until the trained network bandwidth information output model meets the preset training ending condition, so as to obtain the pre-trained network bandwidth information output model.
In one possible implementation manner, the generating unit is specifically configured to perform obtaining a network bandwidth lower limit value of the network bandwidth prediction interval; and determining the network bandwidth lower limit value as a network bandwidth predicted value corresponding to the predicted time of the terminal equipment, and obtaining the network bandwidth predicted information.
According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising a memory storing a computer program and a processor implementing the network bandwidth prediction information generation method according to the first aspect or any one of the possible implementations of the first aspect when the processor executes the computer program.
According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the network bandwidth prediction information generation method according to the first aspect or any one of the possible implementations of the first aspect.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program stored in a readable storage medium, from which at least one processor of a device reads and executes the computer program, such that the device, when executed, implements the network bandwidth prediction information generation method according to the first aspect or any one of the possible implementations of the first aspect.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects: the method comprises the steps of obtaining historical network bandwidth data of terminal equipment before prediction time, outputting a network bandwidth prediction interval aiming at the terminal equipment according to the historical network bandwidth data, matching a confidence level of the network bandwidth truth value corresponding to the prediction time of the terminal equipment in the output network bandwidth prediction interval with a service scene type corresponding to the current provided service of the terminal equipment, and generating network bandwidth prediction information corresponding to the prediction time of the terminal equipment according to the network bandwidth prediction interval; therefore, the network bandwidth prediction interval of the terminal equipment at the prediction time can be determined based on the historical network bandwidth data, so that the bandwidth prediction result can show the fluctuation condition of the bandwidth, the interval size of the network bandwidth prediction interval can be flexibly changed according to different service scene types, the sensitive requirement of matching different service scene types on the bandwidth fluctuation is further realized, overestimation of the network bandwidth condition of the terminal equipment in the future is avoided, the future network bandwidth information of the terminal equipment is accurately acquired in advance, and the condition that the service effect is poor when the terminal equipment provides service is avoided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure.
It should be further noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by the user or sufficiently authorized by each party.
The method for generating the network bandwidth prediction information provided by the present disclosure can be applied to an application environment as shown in fig. 1. Wherein the terminal device 102 communicates with the electronic device 104 via a network. The data storage system may store data that the electronic device 104 needs to process. The data storage system may be integrated on the electronic device 104 or may be located on a cloud or other network server. Wherein the electronic device 104 obtains historical network bandwidth data of the terminal device 102 before the predicted time; the electronic equipment 104 outputs a network bandwidth prediction interval for the terminal equipment according to the historical network bandwidth data; the network bandwidth prediction interval comprises a confidence level of a target network bandwidth value and is matched with the current service scene type; the target network bandwidth value is a network bandwidth true value corresponding to the predicted time of the terminal equipment; the current service scene type is the service scene type corresponding to the current service provided by the terminal equipment; the electronic device 104 generates network bandwidth prediction information corresponding to the terminal device 102 at the prediction time according to the network bandwidth prediction interval. In practical applications, the terminal device 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, etc. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The electronic device 104 may be implemented as a stand-alone server or as a cluster of servers. It should be noted that, the method for generating network bandwidth prediction information provided by the present disclosure may also be directly applied to the terminal device 102 itself.
Fig. 2 is a flowchart illustrating a method of generating network bandwidth prediction information, for use in an electronic device, according to an exemplary embodiment, comprising the following steps.
In step 202, historical network bandwidth data of the terminal device prior to the predicted time is obtained.
The predicted time may refer to a time corresponding to a network bandwidth prediction target.
Wherein the network bandwidth may include at least one of a download bandwidth and an upload bandwidth.
The historical network bandwidth data may refer to network bandwidth data of the terminal device in a historical period of time before the predicted time. In practical application, the historical network bandwidth data may include network bandwidths corresponding to a plurality of sampling points of the terminal device in a historical time period; of course, the historical network bandwidth data may also include data transmission information obtained after the terminal device executes the data transmission tasks corresponding to the plurality of sampling points in the historical time period. Taking a file downloading task as an example of a data transmission task, the data transmission information corresponding to the file downloading task can be the file size, the transmission time consumption, the round trip delay and the packet loss rate corresponding to each file downloading task.
In specific implementation, the electronic device acquires historical network bandwidth data of the terminal device before the prediction time; specifically, the electronic device may control the terminal device to perform bandwidth sampling operation in a historical time period before the predicted time, that is, may control the terminal device to execute corresponding data transmission tasks (e.g., file downloading tasks) at a plurality of sampling points in the historical time period, so as to obtain information such as file size, transmission time consumption, round trip delay, packet loss rate, actual network bandwidth value, and the like corresponding to each data transmission task, so as to obtain the historical network bandwidth data.
In step 204, a network bandwidth prediction interval for the terminal device is output based on the historical network bandwidth data.
The network bandwidth prediction interval comprises a confidence level of a target network bandwidth value and is matched with the current service scene type. In other words, the confidence level of the network bandwidth truth value corresponding to the prediction time of the terminal device in the network bandwidth prediction interval is matched with the current service scene type.
The target network bandwidth value is a network bandwidth true value corresponding to the predicted time of the terminal equipment.
The current service scene type is a service scene type corresponding to the current service provided by the terminal equipment.
The currently provided service may refer to a service corresponding to a current function of the terminal device. For example, the currently provided services may include streaming services such as video play services, live services, and the like. Wherein the currently provided service may include a plurality of service scenario types.
For example, taking the current service as the video playing service as an example, the service scene types of the video playing service include a long video playing scene, a short video playing scene, and the like. The sensitivity requirements of different traffic scenario types for corresponding network bandwidths are different. For example, long video playing scenes, such as a scene in which a user is focused on watching an online movie, can cache most resources in advance, and is very insensitive to bandwidth fluctuation in a short time; and the short video playing scene, such as the scene that the user continuously slides the short video, needs to load new video resources frequently and rapidly, and the bandwidth fluctuation in the short video can cause the downloading speed to be lower than expected, so as to influence the service effect of the video playing service.
Based on this, the interval size of the network bandwidth prediction interval corresponding to the short video play scene may be larger than the interval size of the network bandwidth prediction interval corresponding to the long video play scene; that is, the electronic device needs to output network bandwidth prediction intervals of different interval sizes for different service scene types; in the short video playing scene, the confidence level of the network bandwidth truth value corresponding to the prediction time of the terminal equipment in the network bandwidth prediction interval can be higher than the confidence level of the network bandwidth truth value corresponding to the prediction time of the terminal equipment in the network bandwidth prediction interval in the long video playing scene.
In a specific implementation, the electronic device outputs a network bandwidth prediction interval for the terminal device according to the historical network bandwidth data. Specifically, the electronic device may determine network bandwidth distribution information of the terminal device at the target time according to the historical network bandwidth data; and acquiring a service scene type corresponding to the current service provided by the terminal equipment, and determining a network bandwidth prediction interval aiming at the terminal equipment in the network bandwidth distribution information according to the confidence level matched with the service scene type.
For example, the electronic device may use a method of fitting data by using a model, that is, the electronic device may determine a probability distribution of a network bandwidth corresponding to the predicted time by using a machine learning model, and determine a predicted interval of the network bandwidth by using a confidence interval of a confidence level matched with the service scene type.
For another example, the electronic device may perform data statistics, that is, the electronic device may calculate a distribution situation of a network bandwidth corresponding to each data sampling point of the terminal device in a certain historical time period, and determine a network bandwidth prediction interval by adopting a quantile interval corresponding to a confidence level matched with the service scene type. In the following, a process of outputting a network bandwidth prediction interval for a terminal device according to historical network bandwidth data will be described in detail, and not described in detail.
In step 206, according to the network bandwidth prediction interval, network bandwidth prediction information corresponding to the predicted time by the terminal device is generated.
In a specific implementation, after the electronic device obtains a network bandwidth prediction interval of the terminal device, the electronic device generates network bandwidth prediction information corresponding to the prediction time of the terminal device according to the network bandwidth prediction interval. Specifically, the electronic device may use a certain network bandwidth value in the network bandwidth prediction interval as a network bandwidth prediction value of the terminal device, so as to generate network bandwidth prediction information corresponding to the terminal device at the prediction time.
In the method for generating the network bandwidth prediction information, the historical network bandwidth data of the terminal equipment before the prediction time is obtained, the network bandwidth prediction interval for the terminal equipment is output according to the historical network bandwidth data, the confidence level of the network bandwidth truth value corresponding to the prediction time of the terminal equipment in the output network bandwidth prediction interval is matched with the service scene type corresponding to the current service provided by the terminal equipment, and then the network bandwidth prediction information corresponding to the prediction time of the terminal equipment is generated according to the network bandwidth prediction interval; therefore, the network bandwidth prediction interval of the terminal equipment at the prediction time can be determined based on the historical network bandwidth data, so that the bandwidth prediction result can show the fluctuation condition of the bandwidth, the interval size of the network bandwidth prediction interval can be flexibly changed according to different service scene types, the sensitive requirement of matching different service scene types on the bandwidth fluctuation is further realized, overestimation of the network bandwidth condition of the terminal equipment in the future is avoided, the future network bandwidth information of the terminal equipment is accurately acquired in advance, and the condition that the service effect is poor when the terminal equipment provides service is avoided.
In an exemplary embodiment, outputting a network bandwidth prediction interval for a terminal device based on historical network bandwidth data, comprising: according to the historical network bandwidth data, determining network bandwidth distribution information of the terminal equipment at the target time; and acquiring a service scene type corresponding to the current service provided by the terminal equipment, and determining a network bandwidth prediction interval aiming at the terminal equipment in the network bandwidth distribution information according to the service scene type.
The interval size corresponding to the network bandwidth prediction interval and the bandwidth sensitivity degree corresponding to the service scene type are in positive correlation. In other words, the more sensitive the service scene type is to the bandwidth volatility, the larger the corresponding interval size of the network bandwidth prediction interval.
For example, for a service scene type of a video such as a movie watched by a user for a long time, which is less sensitive to bandwidth volatility, the interval size corresponding to the network bandwidth prediction interval may be the first interval size; for the service scene type of the short video which is rapidly slid by the user and is sensitive to the bandwidth fluctuation, the interval size corresponding to the network bandwidth prediction interval can be the second interval size. Wherein the first interval size is smaller than the second interval size.
The network bandwidth distribution information may be information reflecting a distribution condition of a network bandwidth value when the terminal device is at the target time.
In practical applications, the network bandwidth distribution information may include network bandwidth distribution history information and network bandwidth distribution prediction information. It should be noted that the type of the network bandwidth distribution information depends on the type of the target time.
Specifically, in the case that the target time is a historical time period before the predicted time, the network bandwidth distribution information is network bandwidth distribution historical information, namely, network bandwidth distribution conditions of the terminal equipment in the historical time period are represented; and under the condition that the target time is the predicted time, the network bandwidth distribution information is network bandwidth distribution prediction information, namely, the probability distribution condition of each network bandwidth interval where the network bandwidth of the characterization terminal equipment is located under the predicted time.
In a specific implementation, in a process of outputting a network bandwidth prediction interval for the terminal device according to historical network bandwidth data, the electronic device can determine network bandwidth distribution information of the terminal device at a target time according to historical network bandwidth data obtained by sampling the network bandwidth of the terminal device in a historical time period. Specifically, in the case that the target time is a historical time period before the predicted time, the electronic device may determine a network bandwidth distribution situation of the terminal device in the historical time period, so as to obtain network bandwidth distribution information; under the condition that the target time is the predicted time, the electronic equipment can determine probability distribution conditions of each network bandwidth interval where the network bandwidth of the terminal equipment is located under the predicted time so as to obtain network bandwidth distribution information.
The electronic device can acquire the service scene type corresponding to the current service provided by the terminal device, and determine a network bandwidth prediction interval for the terminal device in the network bandwidth distribution information according to the service scene type. It should be noted that, the process of determining the network bandwidth prediction interval for the terminal device in the network bandwidth distribution information according to the service scene type by the electronic device will be further described below, and not be described too much.
According to the technical scheme of the embodiment, network bandwidth distribution information of the terminal equipment at the target time is determined according to historical network bandwidth data, the service scene type corresponding to the current service provided by the terminal equipment is obtained, and then the network bandwidth prediction interval for the terminal equipment is determined in the network bandwidth distribution information according to the service scene type, so that the network bandwidth prediction interval of the terminal equipment at the prediction time is determined based on the historical network bandwidth data, the interval size of the network bandwidth prediction interval can be flexibly changed according to different service scene types to match the sensitive requirements of the different service scene types on bandwidth fluctuation, and therefore the situation that the terminal equipment cannot accurately control the data transmission strategy for the terminal equipment due to overestimation of the future network bandwidth situation can be effectively avoided.
In an exemplary embodiment, in a case where the target time is a historical time period before the predicted time, determining network bandwidth distribution information of the terminal device at the target time according to the historical network bandwidth data includes: according to the historical network bandwidth data, determining network bandwidth sampling values corresponding to sampling points of the terminal equipment in a historical time period; performing quantile counting operation on the network bandwidth sampling values corresponding to the sampling points to obtain bandwidth counting quantile information of the terminal equipment at the target time; and determining the bandwidth statistics counting bit number information as network bandwidth distribution information.
In practical applications, in the case that the target time is a historical time period before the predicted time, the network bandwidth distribution information may refer to distribution information of network bandwidth of the terminal device in the historical time period.
In a specific implementation, under the condition that the target time is a historical time period before the predicted time, the electronic device can determine a network bandwidth sampling value corresponding to each sampling point of the terminal device in the historical time period according to the historical network bandwidth data; then, the electronic device may use a preset data statistics module (data statistics software) to perform quantile statistics operation on the network bandwidth sampling values corresponding to the sampling points, so as to obtain quantile information of the network bandwidth sampling values corresponding to the sampling points, so as to obtain bandwidth statistics quantile information of the terminal device at the target time. For ease of understanding by those skilled in the art, referring to FIG. 3, FIG. 3 provides an exemplary diagram of the results of a bandwidth statistics score number; the abscissa may refer to the bandwidth of the sampling point, and the ordinate is the number of occurrences of the sampling point corresponding to the bandwidth. The electronic device determines the bandwidth statistics number of bits information of the terminal device at the target time as the network bandwidth distribution information.
According to the technical scheme of the embodiment, under the condition that the target time is a historical time period before the predicted time, network bandwidth sampling values corresponding to sampling points of the terminal equipment in the historical time period are determined according to historical network bandwidth data; and performing quantile counting operation on the network bandwidth sampling values corresponding to the sampling points to obtain the bandwidth counting quantile information of the terminal equipment at the target time, thereby effectively determining the network bandwidth distribution information of the terminal equipment at the target time in a data counting mode.
In an exemplary embodiment, determining a network bandwidth prediction interval for a terminal device in the network bandwidth distribution information according to a service scene type includes: determining a target quantile interval according to an interval limit parameter corresponding to the service scene type; the target quantile interval comprises a first quantile and a second quantile; the first quantile, the second quantile and the interval limit parameter meet a preset relationship; in the network bandwidth distribution information, determining a network bandwidth sampling value at a first quantile as a first network bandwidth value, and in the network bandwidth distribution information, determining a network bandwidth sampling value at the first quantile as a second network bandwidth value; and determining a network bandwidth prediction interval according to the first network bandwidth value and the second network bandwidth value.
The interval size of the fractional interval and the bandwidth sensitivity corresponding to the service scene type are in positive correlation. In other words, the more sensitive the traffic scene type is to bandwidth volatility, the larger the interval size of the corresponding fractional interval. For example, for a service scene type in which a user views a video such as a movie for a long time, which is less sensitive to bandwidth volatility, the interval size of the corresponding fractional interval may be set to a first interval value; for the service scene type of the short video which is rapidly slid by the user and is sensitive to the bandwidth fluctuation, the interval size of the corresponding quantile interval can be set to be a second interval value. Wherein the first interval value is smaller than the second interval value.
For the understanding of those skilled in the art, please refer to fig. 3 again, wherein 310 is a [40,60] quantile interval corresponding to a long video playing scene, i.e. 40% quantile to 60% quantile; 320 is the [30,70] quantile interval corresponding to the short video playing scene, namely 30% quantile to 70% quantile. It can be seen that the interval size of the [40,60] quantile interval is smaller than the interval size of the [30,60] quantile interval.
In the specific implementation, in the process that the electronic equipment determines a network bandwidth prediction interval for the terminal equipment in the network bandwidth distribution information according to the service scene type, the electronic equipment can determine a target quantile interval according to an interval limit parameter corresponding to the service scene type; the target quantile interval comprises a first quantile and a second quantile; the first quantile, the second quantile and the interval boundary parameter satisfy a preset relationship. In practical applications, the target quantile interval may be expressed as an [ a, b ] quantile interval; wherein a=x, b=x+y, y=100-2*x; x = interval boundary parameter. The first quantile may be expressed as an a% quantile; the second quantile may be expressed as a b% quantile.
For example, for a long video playing scene, the electronic device obtains a section limit parameter corresponding to the long video playing scene as 40; the electronic equipment can determine that a target quantile interval corresponding to the long video playing scene is expressed as [40,60] quantile interval; for a short video playing scene, the electronic equipment acquires a section limit parameter corresponding to the short video playing scene as 30; the electronic device may determine that the target quantile interval corresponding to the short video play scene is represented as [30,70] quantile interval.
Then, the electronic device may determine, in the network bandwidth distribution information, the network bandwidth sampling value at the first quantile as a first network bandwidth value, and determine, in the network bandwidth distribution information, the network bandwidth sampling value at the first quantile as a second network bandwidth value; and finally, the electronic equipment determines a network bandwidth prediction interval according to the first network bandwidth value and the second network bandwidth value. Then, in the above example, the target quantile interval of the short video playing scene is the [30,70] quantile interval, and the electronic device can determine, according to the network bandwidth distribution information, that the network bandwidth sampling value at 30% of the quantiles is the first network bandwidth value, and determine, according to the network bandwidth distribution information, that the network bandwidth sampling value at 70% of the quantiles is the second network bandwidth value; and the electronic equipment determines a network bandwidth prediction interval according to the first network bandwidth value and the second network bandwidth value. In practical applications, the network bandwidth prediction interval may be denoted as [ first network bandwidth value, second network bandwidth value ].
According to the technical scheme of the embodiment, a target quantile interval is determined according to interval limit parameters corresponding to the service scene type; the target quantile interval comprises a first quantile and a second quantile; in the network bandwidth distribution information, determining a network bandwidth sampling value in a first quantile as a first network bandwidth value, and in the network bandwidth distribution information, determining a network bandwidth sampling value in the first quantile as a second network bandwidth value; and determining a network bandwidth prediction interval according to the first network bandwidth value and the second network bandwidth value, so that the confidence level of the network bandwidth truth value which corresponds to the prediction time and is possibly in the network bandwidth prediction interval can be matched with the service scene type which corresponds to the current provided service of the terminal equipment.
Fig. 4 is a flowchart illustrating another network bandwidth prediction information generation method according to an exemplary embodiment, as shown in fig. 4, including the following steps.
In step 402, historical network bandwidth data of the terminal device before the predicted time is obtained.
In step 404, according to the historical network bandwidth data, network bandwidth sampling values corresponding to sampling points in a historical time period before the predicted time of the terminal device are determined.
In step 406, a quantile counting operation is performed on the network bandwidth sampling values corresponding to the sampling points, so as to obtain bandwidth counting quantile information of the terminal device at the target time.
In step 408, the bandwidth statistics quantile information is determined to be network bandwidth distribution information.
In step 410, a target quantile interval is determined according to an interval limit parameter corresponding to the service scene type; the target quantile interval comprises a first quantile and a second quantile; the first quantile, the second quantile and the interval limit parameter meet a preset relationship; the interval size of the fractional interval and the bandwidth sensitivity corresponding to the service scene type are in positive correlation.
In step 412, the network bandwidth sample value at the first quantile is determined to be a first network bandwidth value in the network bandwidth distribution information, and the network bandwidth sample value at the first quantile is determined to be a second network bandwidth value in the network bandwidth distribution information.
In step 414, a network bandwidth prediction interval is determined from the first network bandwidth value and the second network bandwidth value.
In step 416, according to the network bandwidth prediction interval, network bandwidth prediction information corresponding to the predicted time by the terminal device is generated.
It should be noted that, the specific limitation of the above steps may be referred to the specific limitation of a method for generating network bandwidth prediction information, which is not described herein.
In an exemplary embodiment, in a case that the target time is at the predicted time, determining network bandwidth distribution information of the terminal device at the target time according to the historical network bandwidth data includes: extracting historical network bandwidth characteristics from historical network bandwidth data; inputting the historical network bandwidth characteristics into a pre-trained network bandwidth information output model to obtain model output information; the model output information comprises probability information that the network bandwidth true value corresponding to the prediction time of the terminal equipment is in each preset network bandwidth candidate interval; and determining the model output information as network bandwidth distribution information.
In practical application, when the target time is the predicted time, the network bandwidth distribution information may refer to probability information that the network bandwidth true value corresponding to the predicted time of the terminal device is in each preset network bandwidth candidate interval.
The historical network bandwidth characteristic may refer to a network bandwidth characteristic of the terminal device during a historical time period. In practical application, the historical network bandwidth characteristic can characterize the characteristics of file size, transmission time consumption, round trip delay, packet loss rate and the like corresponding to the preset number of file transmission tasks executed by the terminal equipment in the historical time period.
In a specific implementation, under the condition that the target time is the predicted time, the electronic device can determine probability information that a network bandwidth true value corresponding to the predicted time of the terminal device is in each preset network bandwidth candidate interval according to historical network bandwidth data so as to obtain network bandwidth distribution information; specifically, the electronic device may extract historical network bandwidth characteristics from the historical network bandwidth data; then, the electronic equipment can input the historical network bandwidth characteristics into a pre-trained network bandwidth information output model to obtain model output information; the model output information comprises probability information that the network bandwidth true value corresponding to the prediction time of the terminal equipment is in each preset network bandwidth candidate interval.
More specifically, the network bandwidth can be divided into K network bandwidth candidate intervals, the historical network bandwidth characteristics are processed through a pre-trained network bandwidth information output model, and probability values of the network bandwidth truth values corresponding to the prediction time of the terminal equipment in the K network bandwidth candidate intervals are output as the probability information; wherein the sum of probability values corresponding to the K network bandwidth candidate intervals is 100%. The electronic device determines the model output information as network bandwidth distribution information.
According to the technical scheme, the historical network bandwidth characteristics in the historical network bandwidth data are extracted, and the historical network bandwidth characteristics are input into a pre-trained network bandwidth information output model to obtain model output information; the model output information comprises probability information that the network bandwidth true value corresponding to the predicted time of the terminal equipment is in each preset network bandwidth candidate interval, so that the probability information that the network bandwidth true value corresponding to the predicted time of the terminal equipment is in each preset network bandwidth candidate interval is determined by utilizing the historical network bandwidth characteristics in the historical network bandwidth data under the condition that the target time is the predicted time, and the network bandwidth distribution information used for determining the network bandwidth predicted interval is obtained rapidly and effectively.
In an exemplary embodiment, determining a network bandwidth prediction interval for a terminal device in the network bandwidth distribution information according to a service scene type includes: determining a target confidence interval according to a target confidence level corresponding to the service scene type; the target confidence interval comprises an interval upper boundary and an interval lower boundary; determining a third network bandwidth value corresponding to the upper boundary of the interval in the model output information, and determining a fourth network bandwidth value corresponding to the lower boundary of the interval in the model output information; and determining a network bandwidth prediction interval according to the third network bandwidth value and the fourth network bandwidth value.
The target confidence level and the bandwidth sensitivity corresponding to the service scene type are in positive correlation. In other words, the more sensitive the traffic scene type is to bandwidth volatility, the higher the corresponding target confidence level. For example, for a business scenario type where a user views a video such as a movie for a long period of time, which is less sensitive to bandwidth volatility, the target confidence level may be set to 70%; for the traffic scene type where the user is fast sliding short video, which is more sensitive to bandwidth volatility, the target confidence level may be set to 90%. For ease of understanding by those skilled in the art, a schematic diagram of a bandwidth forecast confidence interval is provided by way of example in fig. 5. The 90% confidence interval is a target confidence interval corresponding to a short video playing scene, and the 70% confidence interval is a target confidence interval corresponding to a long video playing scene.
In the specific implementation, in the process that the electronic equipment determines a network bandwidth prediction interval for the terminal equipment in the network bandwidth distribution information according to the service scene type, the electronic equipment can determine a target confidence interval according to a target confidence level corresponding to the service scene type; the electronic equipment can determine a third network bandwidth value corresponding to the upper boundary of the target confidence interval in the model output information, and determine a fourth network bandwidth value corresponding to the lower boundary of the target confidence interval in the model output information; the electronic device may determine a network bandwidth prediction interval from the third network bandwidth value and the fourth network bandwidth value.
For example, for a business scenario type of a user quick-slide short video, the electronic device may determine that the target confidence level for the business scenario type is 90%; the electronic equipment determines that the target confidence interval is a 90% confidence interval based on the target confidence level; the electronic equipment further obtains a third network bandwidth value corresponding to the upper boundary of the 90% confidence interval in the model output information, and a fourth network bandwidth value corresponding to the lower boundary of the 90% confidence interval in the model output information; and the electronic equipment determines a network bandwidth prediction interval according to the third network bandwidth value and the fourth network bandwidth value. In practical applications, the network bandwidth prediction interval may be represented as [ third network bandwidth value, fourth network bandwidth value ]. Specifically, the electronic device may symmetrically integrate the removal probabilities from two ends of the K network bandwidth intervals in the model output information to 5% of the bandwidth interval, and the rest is the network bandwidth prediction interval corresponding to the 90% confidence interval.
According to the technical scheme of the embodiment, the target confidence interval is determined according to the target confidence level corresponding to the service scene type; the target confidence interval comprises an interval upper boundary and an interval lower boundary; determining a third network bandwidth value corresponding to the interval upper bound of the target confidence interval in the model output information, and determining a fourth network bandwidth value corresponding to the interval lower bound of the target confidence interval in the model output information; and determining a network bandwidth prediction interval according to the third network bandwidth value and the fourth network bandwidth value, so that the confidence level of the network bandwidth truth value which corresponds to the prediction time and is possibly in the network bandwidth prediction interval at the end of the terminal equipment can be matched with the service scene type which corresponds to the current provided service of the terminal equipment.
In an exemplary embodiment, the training method adopted by the pre-trained network bandwidth information output model comprises the following steps: obtaining model training data; the model training data comprises at least one sample network bandwidth characteristic and a network bandwidth label interval corresponding to each sample network bandwidth characteristic; training the network bandwidth information output model to be trained by adopting model training data until the trained network bandwidth information output model meets the preset training ending condition, so as to obtain the pre-trained network bandwidth information output model.
The sample network bandwidth characteristics are determined by sampling network bandwidth data corresponding to a preset number of data transmission tasks.
For example, in the case where the network bandwidth of the terminal device is predicted to be the download bandwidth, the data transmission task may refer to a file downloading task, and the terminal device is controlled to execute a preset number of file downloading tasks (for example, 10 file downloading tasks), so as to determine file downloading information such as a file size, time consumption for downloading, round trip delay counted by using a bottom layer transmission algorithm, and packet loss rate corresponding to each file downloading task. And carrying out feature engineering on the file downloading information to obtain a feature vector which can be one-dimensional, namely a sample downloading bandwidth feature, so as to obtain the feature in the corresponding piece of training data.
The network bandwidth label interval is a bandwidth interval where a network bandwidth sampling value corresponding to a target data transmission task is located, and the target data transmission task is the latest data transmission task in the data transmission tasks with the preset times.
For example, by splitting the download bandwidth into K download bandwidth intervals, each download bandwidth sample falls into one of the download bandwidth intervals, denoted as K. In practical application, a download bandwidth interval in which a latest file download task in a preset number of file download tasks falls may be determined as a download bandwidth label interval corresponding to the sample download bandwidth feature, so as to obtain a label (label) in the corresponding piece of training data.
TABLE 1
For ease of understanding by those skilled in the art, table 1 provides exemplary schematic representations of a data record form of model training data; the training data record comprises M characteristics and labels, wherein the M characteristics comprise sample downloading bandwidth characteristics; the label includes a network bandwidth label interval k corresponding to the sample network bandwidth characteristic.
In a specific implementation, in the process that the electronic equipment trains the pre-trained network bandwidth information output model, the electronic equipment can acquire the model training data; specifically, the electronic device may control the terminal device to execute a preset number of data transmission tasks, and collect data transmission information generated in the process that the terminal device executes the preset number of data transmission tasks, so as to obtain at least one sample network bandwidth feature and a network bandwidth label interval corresponding to each sample network bandwidth feature. Of course, the electronic device may also receive pre-constructed model training data to obtain the model training data.
The electronic equipment can train the network bandwidth information output model to be trained by adopting model training data until the trained network bandwidth information output model meets the preset training ending condition, so as to obtain the pre-trained network bandwidth information output model. Specifically, the electronic device may input any one of the sample network bandwidth characteristics into the above-mentioned network bandwidth information output model to be trained, so as to obtain a model output result of the network bandwidth information output model to be trained; the model output result comprises probability information that a network bandwidth true value corresponding to a label time of the terminal equipment is in each preset network bandwidth candidate interval, wherein the label time corresponds to a network bandwidth label interval corresponding to any sample network bandwidth characteristic; the electronic device can determine a model loss value of the network bandwidth information output model to be trained according to the model output result and the network bandwidth label interval and through a preset loss function.
The electronic equipment can adjust the parameters of the network bandwidth information output model to be trained according to the model loss value of the network bandwidth information output model to be trained, so as to obtain a trained network bandwidth information output model; by adopting the mode, iterative training is carried out on the network bandwidth information output model until the model loss value of the trained network bandwidth information output model meets the preset condition, so as to determine that the trained network bandwidth information output model meets the preset training ending condition, and the pre-trained network bandwidth information output model is obtained.
According to the technical scheme, model training data are obtained; the model training data comprises at least one sample network bandwidth characteristic and a network bandwidth label interval corresponding to each sample network bandwidth characteristic; training the network bandwidth information output model to be trained by using model training data to obtain a pre-trained network bandwidth information output model, so that the pre-trained network bandwidth information output model can learn the mapping relation between the sample network bandwidth characteristics and the corresponding network bandwidth label interval, the subsequent pre-trained network bandwidth information output model is convenient to use, probability information that the network bandwidth true value corresponding to the equipment terminal at the prediction time is in each preset network bandwidth candidate interval is determined, and the network bandwidth distribution information corresponding to the output equipment terminal at the prediction time is realized.
In an exemplary embodiment, generating network bandwidth prediction information corresponding to a predicted time by a terminal device according to a network bandwidth prediction interval includes: acquiring a network bandwidth lower limit value of a network bandwidth prediction interval; and determining the lower limit value of the network bandwidth as a network bandwidth predicted value corresponding to the predicted time of the terminal equipment, and obtaining network bandwidth predicted information.
In a specific implementation, in a process of generating network bandwidth prediction information corresponding to a prediction time by an electronic device according to a network bandwidth prediction interval, the electronic device can determine a minimum value in the network bandwidth prediction interval as a network bandwidth lower limit value of the network bandwidth prediction interval; and the electronic equipment determines the network bandwidth lower limit value as a network bandwidth predicted value corresponding to the predicted time of the terminal equipment, so that the electronic equipment obtains the network bandwidth predicted information of the terminal equipment under the predicted time.
According to the technical scheme, the network bandwidth lower limit value of the network bandwidth prediction interval is obtained, and the network bandwidth lower limit value is determined as the network bandwidth prediction value corresponding to the terminal equipment at the prediction time, so that the condition that the terminal equipment is in the future network bandwidth can be represented by adopting the network bandwidth minimum value in the network bandwidth prediction interval as far as possible, the condition that the terminal equipment cannot accurately control the data transmission strategy aiming at the terminal equipment due to overestimation of the network bandwidth condition in the future is avoided, and the condition that the playing service effect of the terminal equipment is poor is avoided.
Fig. 6 is a flowchart of another network bandwidth prediction information generation method according to another exemplary embodiment, as shown in fig. 6, including the following steps.
In step 602, historical network bandwidth data of the terminal device prior to the predicted time is obtained.
In step 604, historical network bandwidth characteristics in the historical network bandwidth data are extracted.
In step 606, the historical network bandwidth characteristics are input into a pre-trained network bandwidth information output model to obtain model output information; the model output information comprises probability information that the network bandwidth true value corresponding to the prediction time of the terminal equipment is in each preset network bandwidth candidate interval.
In step 608, a target confidence interval is determined according to the target confidence level corresponding to the service scene type; the target confidence interval comprises an interval upper boundary and an interval lower boundary; the target confidence level and the bandwidth sensitivity corresponding to the service scene type are in positive correlation.
In step 610, a third network bandwidth value corresponding to the upper bound of the interval in the model output information is determined, and a fourth network bandwidth value corresponding to the lower bound of the interval in the model output information is determined.
In step 612, a network bandwidth prediction interval is determined from the third network bandwidth value and the fourth network bandwidth value.
In step 614, according to the network bandwidth prediction interval, network bandwidth prediction information corresponding to the predicted time by the terminal device is generated.
It should be noted that, the specific limitation of the above steps may be referred to the specific limitation of a method for generating network bandwidth prediction information, which is not described herein.
It should be understood that, although the steps in the flowcharts of fig. 2, 4, and 6 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps of fig. 2, 4, and 6 may include a plurality of steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
It should be understood that the same/similar parts of the embodiments of the method described above in this specification may be referred to each other, and each embodiment focuses on differences from other embodiments, and references to descriptions of other method embodiments are only needed.
Fig. 7 is a block diagram illustrating a network bandwidth prediction information generating apparatus according to an exemplary embodiment. Referring to fig. 7, the apparatus includes:
an acquisition unit 710 configured to perform acquisition of historical network bandwidth data of the terminal device before the predicted time;
an output unit 720 configured to perform outputting a network bandwidth prediction interval for the terminal device according to the historical network bandwidth data; the confidence level of the network bandwidth prediction interval including the target network bandwidth value is matched with the current service scene type; the target network bandwidth value is a network bandwidth true value corresponding to the terminal equipment at the prediction time; the current service scene type is a service scene type corresponding to the current service provided by the terminal equipment;
and a generating unit 730 configured to generate network bandwidth prediction information corresponding to the prediction time by the terminal device according to the network bandwidth prediction interval.
In an exemplary embodiment, the output unit 720 is configured to determine network bandwidth distribution information of the terminal device at a target time according to the historical network bandwidth data; acquiring a service scene type corresponding to a current service provided by the terminal equipment, and determining a network bandwidth prediction interval aiming at the terminal equipment in the network bandwidth distribution information according to the service scene type; and the interval size corresponding to the network bandwidth prediction interval and the bandwidth sensitivity corresponding to the service scene type are in positive correlation.
In an exemplary embodiment, in the case that the target time is a historical time period before the predicted time, the output unit 720 is configured to determine, according to the historical network bandwidth data, a network bandwidth sampling value corresponding to each sampling point of the terminal device in the historical time period; performing quantile counting operation on the network bandwidth sampling values corresponding to the sampling points to obtain bandwidth counting quantile information of the terminal equipment at the target time; and determining the bandwidth statistics counting bit number information as the network bandwidth distribution information.
In an exemplary embodiment, the output unit 720 is configured to determine a target quantile interval according to an interval limit parameter corresponding to the traffic scene type; the target quantile interval comprises a first quantile and a second quantile; the first quantile, the second quantile and the interval limit parameter meet a preset relationship; the interval size of the fractional interval and the bandwidth sensitivity corresponding to the service scene type are in positive correlation; determining the network bandwidth sampling value at the first quantile as a first network bandwidth value in the network bandwidth distribution information, and determining the network bandwidth sampling value at the first quantile as a second network bandwidth value in the network bandwidth distribution information; and determining the network bandwidth prediction interval according to the first network bandwidth value and the second network bandwidth value.
In an exemplary embodiment, in the case that the target time is at the predicted time, the output unit 720 is configured to perform extraction of a historical network bandwidth feature in the historical network bandwidth data; inputting the historical network bandwidth characteristics into a pre-trained network bandwidth information output model to obtain model output information; the model output information comprises probability information that the network bandwidth true value corresponding to the predicted time of the terminal equipment is in each preset network bandwidth candidate interval; and determining the model output information as the network bandwidth distribution information.
In an exemplary embodiment, the output unit 720 is configured to determine a target confidence interval according to a target confidence level corresponding to the service scene type; the target confidence interval comprises an interval upper boundary and an interval lower boundary; the target confidence level and the bandwidth sensitivity corresponding to the service scene type are in positive correlation; determining a third network bandwidth value corresponding to the upper boundary of the interval in the model output information, and determining a fourth network bandwidth value corresponding to the lower boundary of the interval in the model output information; and determining the network bandwidth prediction interval according to the third network bandwidth value and the fourth network bandwidth value.
In an exemplary embodiment, the apparatus is further configured to perform acquiring model training data; the model training data comprises at least one sample network bandwidth characteristic and a network bandwidth label interval corresponding to each sample network bandwidth characteristic; the sample network bandwidth characteristics are determined by sampling network bandwidth data corresponding to a data transmission task with preset times; the network bandwidth label interval is a bandwidth interval where a network bandwidth sampling value corresponding to a target data transmission task is located; the target data transmission task is the latest data transmission task in the data transmission tasks with preset times; and training the network bandwidth information output model to be trained by adopting the model training data until the trained network bandwidth information output model meets the preset training ending condition, so as to obtain the pre-trained network bandwidth information output model.
In an exemplary embodiment, the generating unit 730 is specifically configured to obtain a lower limit value of the network bandwidth prediction interval; and determining the network bandwidth lower limit value as a network bandwidth predicted value corresponding to the predicted time of the terminal equipment, and obtaining the network bandwidth predicted information.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Fig. 8 is a block diagram of an electronic device 800 for performing the above-described network bandwidth prediction information generation method, according to an example embodiment. For example, the electronic device 800 may be a server. Referring to fig. 8, electronic device 800 includes a processing component 820 that further includes one or more processors and memory resources represented by memory 822 for storing instructions, such as application programs, executable by processing component 820. The application programs stored in memory 822 may include one or more modules each corresponding to a set of instructions. Further, the processing component 820 is configured to execute instructions to perform the methods described above.
The electronic device 800 may further include: the power component 824 is configured to perform power management of the electronic device 800, the wired or wireless network interface 826 is configured to connect the electronic device 800 to a network, and the input output (I/O) interface 828. The electronic device 800 may operate based on an operating system stored in memory 822, such as Windows Server, mac OS X, unix, linux, freeBSD, or the like.
In an exemplary embodiment, a computer-readable storage medium is also provided, such as memory 822, including instructions executable by a processor of electronic device 800 to perform the above-described method. The storage medium may be a computer readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
In an exemplary embodiment, a computer program product is also provided, comprising instructions therein, executable by a processor of the electronic device 800 to perform the above-described method.
It should be noted that the descriptions of the foregoing apparatus, the electronic device, the computer readable storage medium, the computer program product, and the like according to the method embodiments may further include other implementations, and the specific implementation may refer to the descriptions of the related method embodiments and are not described herein in detail.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.