CN119815066B - Data processing methods and apparatus, non-volatile storage media - Google Patents

Abstract

This application discloses a data processing method and apparatus, and a non-volatile storage medium. The method includes: acquiring live streaming time-series data corresponding to a live video stream; classifying live streaming time-node data from multiple live streaming time-node data into those exhibiting preset conditions and those not exhibiting preset conditions, and determining a live streaming bandwidth requirement index based on the classification results; determining a network quality characteristic quantification factor to characterize network performance; determining a live streaming value characteristic quantification factor to characterize the value of the live stream; and determining a comprehensive quantitative evaluation index for the live streaming acceleration requirement corresponding to the live video stream based on the live streaming bandwidth requirement index, the network quality characteristic quantification factor, and the live streaming value characteristic quantification factor. This application solves the technical problem of being unable to accurately provide live streaming acceleration services to target users due to the inability to accurately determine the acceleration needs of different users for live streaming.

Description

Data processing method and device and nonvolatile storage medium

Technical Field

The application relates to the technical field of big data analysis, in particular to a data processing method and device and a nonvolatile storage medium.

Background

The live broadcast industry is raised and developed, and goes through the industry sprouting stage from platform technology progress and flow cost reduction, and live broadcast is taken as a more direct information sharing mode to be integrated into the daily life of vast residents in a popular way, and the live broadcast presents a multiplex form rapid development stage, especially is integrated with the electronic commerce industry, so that the live broadcast becomes a direct and effective medium for touching users in various industries. Meanwhile, with the rapid development of the live broadcast industry and the popularization in different industries, the network rate of the live broadcast account becomes an important factor affecting the live broadcast effect, so that the network rate requirement of a live broadcast user is judged, and the network rate is optimized according to the actual live broadcast account requirement in time.

Social development and technical progress, the live broadcast demand can be judged by a big data mining technology, but the prior art still has a plurality of defects in combination with the actual situation.

Specifically, the conventional user demand recognition method cannot accurately capture the real demand of the user, particularly in the live broadcast field, the demand of the user changes at any time, the target user with high demands on the aspects of network, smoothness, plug flow stability and the like cannot be accurately recognized, and further the live broadcast acceleration service cannot be accurately provided for the target user.

In view of the above problems, no effective solution has been proposed at present.

Disclosure of Invention

The application provides a data processing method and device and a nonvolatile storage medium, which at least solve the technical problem that the acceleration service of live broadcasting cannot be accurately provided for a target user because the acceleration requirements of different users on live broadcasting cannot be accurately determined.

According to one aspect of the application, a data processing method is provided, which comprises the steps of obtaining live time sequence data corresponding to video live, wherein the live time sequence data comprise a plurality of live time node data, classifying live time node data with preset conditions and live time node data without preset conditions in the live time node data, and determining a live bandwidth demand index according to classification results, wherein the preset conditions comprise that live quality index of video live does not meet preset requirements due to floating of the network bandwidth index, determining a network quality characteristic quantization factor used for representing network performance according to the number of times of network problems in the video live, determining a live value characteristic quantization factor used for representing live value according to the number of watching people of video live, and live value characteristic quantization factor, and determining a comprehensive live acceleration demand quantization evaluation index corresponding to video live according to the live bandwidth demand index, the network quality characteristic quantization factor and the live value characteristic quantization factor.

The method comprises the steps of selecting live time node data with preset conditions and live time node data without preset conditions from a plurality of live time node data, classifying the live time node data with the preset conditions and the live time node data without the preset conditions, determining a live bandwidth demand index according to classification results, calculating a mathematical expected value of the target time sequence, normalizing the mathematical expected value to obtain a network quality level index in a video process, using the first preset time as an independent variable, giving a first numerical value to the live time node data with the preset conditions in the time window, giving a second numerical value to the live time node data without the preset conditions in the time window to obtain a first time sequence corresponding to the time window, obtaining live time node data in the second preset time, combining the first time sequences corresponding to the time windows in the second preset time, obtaining a target time sequence, calculating the mathematical expected value of the target time sequence, normalizing the mathematical expected value to obtain a network quality level index in the video process, mapping the first trend equation to obtain a first target, obtaining a first target by using a least square linear equation, mapping the first trend equation to the first trend index, and obtaining a network quality change trend index.

Optionally, determining a network quality characteristic quantization factor for representing network performance according to the number of times of network problems occurring in a live video broadcast process, wherein the network quality characteristic quantization factor comprises the steps of obtaining the number of times of network problems occurring in the live video broadcast process in a first preset statistical period, determining the first number of times of network problems occurring in each first time step, adding a weight coefficient to the first number of times corresponding to the i-th first time step according to the sequence from the starting time to the ending time of the first preset statistical period to obtain a plurality of second times, wherein the weight coefficient is the reciprocal of the fibonacci number, the fibonacci number F [ i ] = F [ i-1] +f [ i-2] corresponding to the i-th first time step, wherein F [0] = 1, F [1] = 1, i is a positive integer greater than 1, and calculating the second number of times in a summation manner to obtain the network quality characteristic quantization factor.

The method comprises the steps of obtaining the number of live video watching persons in a second preset statistical period, determining expected live video watching persons in a unit second time step according to the ratio of the number of the watching persons to the number of the second time step, generating a second time sequence of the number of the live video watching persons corresponding to each second time step and live video income information in each second time step, performing linear regression fitting on the second time sequence by using a least square regression method to obtain a second target equation, mapping a second slope in the second target equation into a second digital interval by triangular transformation to obtain a income change trend index, and performing multiplication calculation on the expected live video watching persons in the unit second time step and the income change trend index to obtain the live video value characteristic quantization factor.

The method comprises the steps of obtaining identification information of a target object for video live broadcast, determining whether the target object belongs to a multi-channel network mechanism according to the identification information, and multiplying the target object corresponding to the video live broadcast with a preset weight coefficient to obtain the target live broadcast acceleration demand comprehensive quantitative evaluation index under the condition that the target object belongs to the multi-channel network mechanism.

Optionally, determining a comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast according to the live broadcast bandwidth demand index, the network quality characteristic quantization factor and the live broadcast value characteristic quantization factor comprises respectively carrying out normalization processing on the live broadcast bandwidth demand index, the network quality characteristic quantization factor and the live broadcast value characteristic quantization factor, and carrying out multiplication calculation on normalization processing results to obtain the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast.

Optionally, after the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast is determined, the method further comprises dynamically adjusting network resource allocation of the live broadcast service according to the comprehensive quantitative evaluation index of the live broadcast acceleration demand.

According to the still further aspect of the application, a data processing device is provided, which comprises an acquisition module, a first determination module and a fourth determination module, wherein the acquisition module is used for acquiring live time sequence data corresponding to video live, the live time sequence data comprises a plurality of live time node data, the first determination module is used for classifying live time node data with preset conditions and live time node data without preset conditions in the plurality of live time node data, and determining a live bandwidth demand index according to classification results, the preset conditions comprise live quality indexes of video live caused by floating of the network bandwidth indexes do not meet preset requirements, the second determination module is used for determining network quality characteristic quantification factors used for representing network performance according to the number of times of network problems in the video live process, the third determination module is used for determining live value characteristic quantification factors used for representing live value according to the number of watching live video live and live income information, and the fourth determination module is used for determining a live value characteristic quantification index corresponding to the video live broadcast acceleration comprehensive quantification assessment index according to the bandwidth demand index, the network quality characteristic quantification factors and the live value characteristic quantification factors.

According to still another aspect of the present application, there is also provided a nonvolatile storage medium including a stored program, wherein the program, when run, controls a device in which the storage medium is located to execute the above data processing method.

According to still another aspect of the present application, there is also provided an electronic device including a memory and a processor for executing a program stored in the memory, wherein the program executes the above data processing method when running.

According to yet another aspect of the present application, there is also provided a computer program, wherein the computer program implements the above data processing method when being executed by a processor.

According to yet another aspect of the present application, there is also provided a computer program product comprising a non-volatile computer readable storage medium, wherein the non-volatile computer readable storage medium stores a computer program which, when executed by a processor, implements the above data processing method.

The method comprises the steps of acquiring live time sequence data corresponding to video live, wherein the live time sequence data comprise a plurality of live time node data, classifying live time node data with preset conditions and live time node data without preset conditions in the live time node data, and determining a live bandwidth demand index according to classification results, wherein the preset conditions comprise that live quality indexes of video live do not meet preset requirements due to floating of network bandwidth indexes, network quality characteristic quantization factors used for representing network performance are determined according to the number of times of network problems in the video live process, live value characteristic quantization factors used for representing live value are determined according to the number of watching persons of the video live and live gain information, and the method of determining a comprehensive quantization evaluation index of live acceleration demands corresponding to the video live is achieved according to the live bandwidth demand index, the network quality characteristic quantization factors and the live value characteristic quantization factors, so that the purpose of accurately determining acceleration demands of different users on the network live is achieved, and further the technical problem that direct broadcasting service cannot be provided for target users due to the fact that the acceleration demands of different users on the network cannot be accurately determined is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

FIG. 1 is a flow chart of a data processing method according to an embodiment of the present application;

FIG. 2 is a flow chart of another data processing method according to an embodiment of the application;

FIG. 3 is a block diagram of a data processing apparatus according to an embodiment of the present application;

fig. 4 is a block diagram of a hardware structure of a computer terminal of a data processing method according to an embodiment of the present application.

Detailed Description

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above 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 application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In order to better understand the embodiments of the present application, technical terms related to the embodiments of the present application are explained as follows:

Forgetting curve the forgetting curve is found by the Ebinhaos study of German psychologists and describes the rule of forgetting new things by human brain. Forgetting starts immediately after learning and the progress of forgetting is not uniform, with initial forgetting being fast and later gradually slow.

Near-cause effects-near-cause effects are a concept in psychology, meaning that we are more susceptible to recently experienced events or information when making decisions or decisions, and ignore longer-term historical or global situations.

The MCN is any entity or organization which cooperates with a content creator or directly produces various unique contents, and executes business and operation functions on a Network platform for issuing the contents, the MCN is not affiliated to a platform owner or directly affiliated to a Channel, and the MCN provides various services such as content planning, propaganda popularization, vermicelli management, subscription agency and the like for Network red and self-media.

In the related art, firstly, the user demand recognition method cannot accurately capture the real demand of the user, particularly in the live broadcast field, the demand of the user changes at any time, and the target user with high demands on the aspects of network, smoothness, plug flow stability and the like cannot be accurately recognized. Second, the user portrayal construction method relies on limited data sources, resulting in a user portrayal that is not sufficiently comprehensive and accurate. Again, the related operation strategies are rough, and accurate operation popularization can not be performed for different user groups, so that the operation effect is not ideal. In order to solve the above problems, related solutions are provided in the embodiments of the present application, and are described in detail below.

According to an embodiment of the present application, there is provided a method embodiment of a data processing method, it being noted that the steps shown in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that herein.

FIG. 1 is a flow chart of a data processing method according to an embodiment of the present application, as shown in FIG. 1, the method includes the steps of:

step S101, acquiring live time sequence data corresponding to video live, wherein the live time sequence data comprises a plurality of live time node data.

In step S101, a series of live time node data may be formed by monitoring live video streams in real time, and collecting and recording key performance indicators in the live process, including but not limited to live bandwidth, delay, packet loss rate, number of viewers, audience interaction frequency, live revenue, etc. These data are stored in a time series form to facilitate subsequent analysis.

Step S102, classifying live time node data with preset conditions and live time node data without preset conditions in the plurality of live time node data, and determining live bandwidth requirement indexes according to classification results, wherein the preset conditions comprise that live quality indexes of video live broadcast do not meet preset requirements due to floating of network bandwidth indexes.

The network bandwidth index includes, but is not limited to, the following dimensions of uploading bandwidth, downloading bandwidth, packet loss rate, delay and jitter. The network bandwidth index in step S102 may be any one of the above dimensions, or may be a weighted combination of multiple dimensions. Live quality metrics include, but are not limited to, video resolution, video frame rate, interaction delay. The live broadcast quality index in step S102 may be any one of the above dimensions, or may be a weighted combination of multiple dimensions.

For example, for a preset minimum video resolution, in high definition live broadcast, the preset minimum resolution may be set to 720p. Live quality is considered not up to standard when network bandwidth is reduced to a level insufficient to maintain this resolution. For a preset maximum delay time, the live delay should be kept within 2 seconds to ensure that the viewer experiences real-time. Once the delay exceeds the preset value, the live quality may be considered to be affected. Buffering of no more than 1 time per 5 minutes, no more than 5 seconds each time, for example, is acceptable for a preset video buffering frequency and duration. Buffering events beyond this frequency and duration are considered live quality degradation. For preset audio synchronization errors, synchronization errors of less than 100 milliseconds are acceptable, beyond which value the live experience may be affected. For the preset packet loss rate, the packet loss rate not exceeding 1% is the basic requirement of the live broadcast service. An increase in the packet loss rate means a decrease in transmission efficiency and a decrease in video quality.

Step S103, determining a network quality characteristic quantization factor for representing network performance according to the number of times of network problems in the live video process.

Wherein the delay time, typically in milliseconds (ms), represents the average time of data from transmission to reception. The preset requirement may be less than 100ms, otherwise considered a network problem. Packet loss rate, which is the proportion of packets that fail to arrive successfully during network transmission, is typically expressed in percent. For example, a packet loss rate exceeding 1% may be considered a network problem. Maximum bandwidth and average bandwidth, respectively, represent the maximum and average data transfer rates that the network can provide in Mbps (megabits per second). A network problem may be considered when the actual bandwidth of the network is below a required minimum bandwidth threshold. Jitter-time fluctuations in network delay, also typically in milliseconds. For example, jitter exceeding 20ms may be regarded as a problem. The encryption error rate is the proportion of data packets which are not correctly encrypted or decrypted in the data transmission process, the preset encryption success rate is 100%, and any situation lower than the preset encryption success rate can be regarded as a network problem. Connection failure rate, which is the ratio of attempting to establish a network connection but failing, the preset connection success rate is 100%, and the connection failure rate exceeding a certain threshold (e.g., 0.5%) can indicate that the network is unstable.

And step S104, determining a live value characteristic quantization factor for representing the live value according to the number of viewers of the live video and the live broadcast income information.

Step S105, determining a comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast according to the live broadcast bandwidth demand index, the network quality characteristic quantitative factor and the live broadcast value characteristic quantitative factor.

According to the method, live time sequence data corresponding to video live are obtained, the live time sequence data comprise a plurality of live time node data, the live time node data with preset conditions and the live time node data without the preset conditions are classified in the live time node data, and a live bandwidth demand index is determined according to classification results, wherein the preset conditions comprise that live quality indexes of the video live do not meet preset requirements due to floating of network bandwidth indexes, network quality characteristic quantization factors used for representing network performance are determined according to the number of times of network problems in the video live process, live value characteristic quantization factors used for representing live value are determined according to the number of watching persons of the video live and live income information, and the purpose of accurately determining the direct broadcast acceleration demand comprehensive quantization evaluation index corresponding to the video live broadcast according to the live bandwidth demand index, the network quality characteristic quantization factors and the live value characteristic quantization factors is achieved, so that the aim of accurately determining the acceleration demands of different users on the network live is achieved, and the technical effect of accurately providing live acceleration services for target users is achieved.

The steps shown in fig. 1 are exemplarily illustrated and explained below.

According to some optional embodiments of the application, classifying live time node data with preset conditions and live time node data without preset conditions in a plurality of live time node data, and determining a live bandwidth demand index according to classification results, can be achieved by taking a first preset duration as a time window, counting live time node data in the time window, assigning a first numerical value to the live time node data with preset conditions in the time window, assigning a second numerical value to the live time node data without preset conditions in the time window, obtaining a first time sequence corresponding to the time window, obtaining live time node data in the second preset duration, wherein the second preset duration comprises a plurality of time windows, merging the first time sequences corresponding to the time windows in the second preset duration, obtaining a target time sequence, calculating a mathematical expected value of the target time sequence, normalizing the mathematical expected value, obtaining a network quality level index in a video process, taking the first preset duration as an independent variable, assigning a second numerical value to the live time node data without preset conditions in the time window, obtaining a first time sequence corresponding to the live time node data in the time window, obtaining a first trend equation by using a linear transformation trend equation, obtaining a first trend equation, obtaining a network quality change trend index, and a network quality change trend equation, and obtaining a first trend network quality change trend equation.

For example, D indicates whether there is a need for live acceleration, and 24 hours is taken as a time window, and live time node data in the time window is counted.

In the time window, if the live broadcast abnormality occurs in the live broadcast time node data due to the bandwidth, the current bandwidth is indicated to be incapable of meeting the live broadcast requirement, and at the moment, D is assigned to be 1, otherwise, D is assigned to be 0. Adding the time variable t on this basis constructs a time series { D _t } that fits into a "0-1" distribution, since the bandwidth requirement is usually abnormal, so { D _t } is mostly recorded as 0. Counting a plurality of 24-hour time sequences { D _t }, obtaining a target time sequence { D _d }, quantifying the size of the bandwidth requirement of the live broadcast by calculating an expected E value of the target time sequence { D _d }, wherein the E value and the bandwidth requirement are in positive correlation, and if the E value is 0, indicating that the broadband has no influence on the live broadcast, the expected E is calculated according to the following formula:

In the statistical time, the value range of the expected E of the anomaly calculated according to the formula (1) is [0, + ] and the data with the E value larger than 100 is uniformly assigned as 100 in consideration of the disastrous effect on the live broadcast if the live broadcast anomaly occurs more than a certain number of times in one day, and the value range of the expected E of the anomaly is scaled to the [0, 100) interval, and meanwhile, in order to facilitate the subsequent integrated calculation, the value range of the E is scaled to the [0, 1) interval through logarithmic transformation and is recorded as EG.

The calculation formula is as follows:

EG=log₁₀₀E (2)

For the target time sequence { D _d }, taking time D as an independent variable, taking the abnormal times D _d as a dependent variable, taking n ₁ as a sequence length, fitting a linear equation by using a least square method, recording the slope as b, and judging the { D _d } trend of the time sequence by analyzing the slope b of the linear equation. If the slope b is positive, it indicates that the time series is in an ascending trend. If the slope b is negative, it indicates that the time series is in a decreasing trend. When the slope b is close to zero, it is indicated that the time sequence may not have obvious variation trend, and the variation amplitude can be judged according to the absolute value of b. The specific calculation formula of the slope b is as follows:

Because the slope b value is in the range (- ≡, in +++). In order to eliminate the dimensional influence between different indicators when fused, the data are made to be comparable, for subsequent analysis, the value range of b is mapped to the (-1, 1) interval by triangular transformation and is recorded as LB, and the calculation formula is as follows:

Because neither the network quality level EG nor the network quality change trend LB can obviously influence the network quality perception of the anchor, the requirement of the anchor on the live broadcast acceleration is triggered, the requirement EGL of the live broadcast on the bandwidth is obtained by calculating in a weighted average mode, and the formula is as follows:

According to other alternative embodiments of the application, the network quality characteristic quantization factor used for representing the network performance is determined according to the number of times of network problems occurring in the live video process, and the network quality characteristic quantization factor can be obtained by obtaining the number of times of network problems occurring in the live video process in a first preset statistical period, wherein the first preset statistical period comprises a plurality of first time steps, determining the first number of times of network problems occurring in each first time step, adding a weight coefficient to the first number of times corresponding to the ith first time step according to the sequence from the starting time to the ending time of the first preset statistical period, obtaining a plurality of second times, wherein the weight coefficient is the reciprocal of the fibonacci number, and the fibonacci number F [ i ] =f [ i-1] +f [ i-2] corresponding to the ith first time step, wherein F [0] =1, i is a positive integer greater than 1, and summing the plurality of second times, so as to obtain the network quality characteristic quantization factor.

In the above embodiment, first, the preset statistical period and the time step preset statistical period are determined, that is, the first preset statistical period is set, for example, the first 10 minutes of the whole live broadcast process is taken as the statistical period. First time step-dividing the 10 minutes into a plurality of first time steps of 1 minute each for more careful monitoring of network conditions.

Second, network problems may include conditions of a dip in the upload bandwidth, abnormal packet loss rate, significant increase in delay, and the like. In each first time step (e.g. each of the last 10 minutes) it is detected whether the network problem defined above has occurred during the live video. If so, recording the first time step of the network problem, otherwise, recording the first time step of the network problem. The number of times of occurrence of the network problem in each first time step, namely the first time, is further counted.

Again, the number of times the network problem occurs (i.e., the first time) within each time step is assigned a weight coefficient that is the inverse of F [ i ], i.e., 1/F [ i ]. And weighting the occurrence times of the network problems in each first time step one by one from the 1 st minute to the 10 th minute of live broadcasting according to a positive sequence manner from the starting time to the ending time of the first preset statistical period.

Let the first preset statistical period be the first 10 minutes after the start of the live video, each first time step being 1 minute. The first 10 values of the fibonacci sequence are defined as F [0] =1, F [1] =1, F [2] =2, F [3] =3, F [4] =5, F [5] =8, F [6] =13, F [7] =21, F [8] =34, F [9] =55 using the first 10 values of the fibonacci sequence as the denominator of the weight coefficient.

The number of network problems occurring in the live video process (first time number) is recorded in each first time step. The number of network problems occurring in the statistical period is assumed to be 1 min (F1=1) where 2 network problems occur, 2 min (F2=2) where 1 network problem occurs, 3 min (F3=3) where 3 network problems occur, 4 min (F4=5) where 2 network problems occur, 5 min (F5=8) where 4 network problems occur, 6 min (F6=13) where 1 network problem occurs, 7 min (F7=21) where 2 network problems occur, 8 min (F8=34) where 3 network problems occur, and 9 min (F9=55) where 1 network problem occurs.

Then for minute 1 (F [1] =1): second number=2/1=2, for minute 2 (F [2] =2): second number=1/2=0.5, for minute 3 (F [3] =3): second number=3/3=1, for minute 4 (F [4] =5): second number=2/5=0.4, for minute 5 (F [5] =8): second number=4/8=0.5, for minute 6 (F [6] =13): second number=1/13+.0.077, for minute 7 (F [7] =21) =second number=2/21+.0.095, for minute 8 (F [8] =34): second number=3/34+.088, for minute 9 (F [9] =55): second number=1/55+.0.018.

And finally, summing and calculating a plurality of second times to obtain the network quality characteristic quantization factor.

It should be noted that, unlike the live attribute related problem, the live host can intuitively feel that the related problem has a negative effect on the ongoing live broadcast, the network factor mainly displays the related problem that the back-end network cannot provide the network resources required by live broadcast in the live broadcast process from the network back-end data, such as network congestion, too high packet loss rate, network delay, network jitter and other network quality problems, the network quality problem does not necessarily affect the current live broadcast effect after occurrence, but is in the condition of resource mismatch for a long time, and finally, the satisfaction degree of the live broadcast host is necessarily reduced, so the network related problem is one of the main reasons for producing adverse effects on live broadcast, that is, the root cause of affecting the live broadcast image except the difference between the live broadcast host and the equipped hardware equipment. Therefore, the live broadcast demand can be predicted more accurately by quantifying the network quality characteristics. Because the quality problems such as network delay and the like occasionally appear and are not obvious to the live broadcast owner, the live broadcast owner is only influenced by the relative frequency of the related problems, and therefore the frequency of the problems can be generated through the network quality, namely the network quality factors are quantized by the occurrence times of the network problems. Meanwhile, the live-broadcast host is considered as an individual live-broadcast host, the relevant decision is mainly based on the decision of the live-broadcast host, and according to the Egntohaos forgetting curve theory and the psychological 'near-cause effect' theory, the live-broadcast host is characterized in that the memory of the live-broadcast host follows the forgetting curve, namely, the longer the time is from the current time, the weaker the relevant memory is, and the action is more easily influenced by the latest event or information when the decision is made. Therefore, the influence factors of forgetting curve time span and 'near-cause effect' on the live broadcast main decision need to be added to be corrected when the frequency is calculated.

Since different network problems will affect the live broadcast, in the counting process, whatever problem appears is included in the statistics, the counting period includes N ₂ steps, the number of network problems appearing in a fixed time step is N _i, where N is the number of appearing problems, i is a specific time step in the counting period, in order to take the "forgetting curve" and "near effect" into account, according to the distance between the network problems appearing and the counting time from the near to the far, the reciprocal of the fibonacci number F (i) (F [ i ] = F [ i-1] +f [ i-2] (i > = 2, F [0] = 1, F [1] = 1)) is added as a weighting coefficient, and the reciprocal is counted as a weighting coefficientAdding coefficients to construct a network quality characteristic quantization factor, then carrying out weighted sum calculation, and recording the network quality characteristic quantization factor as an NF calculation formula as follows:

In some alternative embodiments of the application, the determination of the live value characteristic quantization factor for representing the live value according to the number of live viewers and live income information can be achieved by obtaining the number of live viewers in a second preset statistical period, wherein the second preset statistical period comprises a plurality of second time steps, determining the expected value of live viewers in a second time step according to the ratio of the number of viewers to the number of the second time steps, generating a second time sequence of the number of viewers corresponding to each second time step and live income information in each second time step, performing linear regression fitting on the second time sequence by using a least square regression method to obtain a second target equation, mapping the second slope in the second target equation into a second digital interval by triangular transformation to obtain a change trend index, and performing multiplication calculation on the expected value of live viewers in the second time step and the change trend index to obtain the live value characteristic quantization factor.

It can be appreciated that the live value LSR (LIVE STREAMING revenue), that is, the actual benefit value brought by the live account for the live host, for example, the live data such as account vermicelli quantity, praise quantity, play quantity and the like, which are positively related to platform commission and live sales conditions, can indirectly reflect the value of the live account, and embody the value of the account produced by the live host, so that the related value can directly influence the willingness of the live host to input cost. For example, the gain value of the live account number which is steadily generated is very large or the gain value is always increasing, and the future gain value is expected to be very considerable, so that the live host is insensitive to the network resource cost investment for improving the broadcasting quality of the live account number and improving the satisfaction degree of the audience, and otherwise, the willingness of the live host to improve the account number performance is not high. Therefore, the live broadcast main cost investment sensitivity can be quantified by constructing a live broadcast profit characteristic quantification factor.

According to the analysis, two points are needed to be considered in quantitative analysis of live broadcast income, namely the stable income value of a live broadcast main live broadcast account, which is a main influencing factor of cost input of the live broadcast main, and the growth of the live broadcast account, namely the change trend of the value condition of the live broadcast account, are quantized, and the cost input wish of the live broadcast main can be judged. And the stable income value of the live broadcast main live broadcast account can be quantified, the number of the last live broadcast watching persons of the live broadcast account can be evaluated, meanwhile, the situation that the number of the single live broadcast watching persons is easily influenced by abnormal events is considered, the fluctuation is relatively large, and the influence on the stable value of the live broadcast account cannot be evaluated. Therefore, in order to eliminate the influence of abnormal values on the evaluation result, the expected live-broadcast account gain stability is quantitatively evaluated by calculating the expected number of viewers of the live-broadcast account for about six months and monthly, the value-recording expected IE is recorded, the statistical period comprises M months, the statistical month is M, the number of viewers of the corresponding statistical month is I _m, and the expected number of viewers of the live-broadcast account for about six months and monthly has the following calculation formula:

The growth of the live broadcast main live account, namely the index change trend of the number of viewers and the like, is also an important influence factor of the live broadcast main cost input willingness, but the related change trend can be used as a factor of account value predictability rather than an explicit factor, and the account value cannot be estimated independently in general, but the index change trend of the number of viewers can be used as a weighted item to correct the live broadcast account value quantitative estimation, so that the accuracy of the live broadcast value characteristic quantitative factor estimation is improved, and the value trend of the live broadcast account is calculated quantitatively.

In order to quantify the change trend ICT (Income CHANGE TREND) of the value of the live account over time, a change time sequence of the number of people watching live account month is constructed, wherein x is the statistical month, y is the statistical month current month live income, the total month number is contained in n ₃ statistical period, a least square regression method dataset is used for carrying out linear regression fitting, the slope of a fitting equation is calculated as the ICT, then whether the change of the live income over time is an increasing or decreasing trend is judged according to the positive and negative of the ICT, meanwhile, the change range of the number of people watching live account can be judged according to the absolute value of the ICT, and the calculation formula is as follows:

because the range of values for slope Ib is (- ≡, in +++). The value of the live account cannot be directly corrected as a coefficient, so by triangular transformation, mapping the value range of b to (-1, 1), taking the value obtained by normalization calculation as a live account value change influence factor coefficient, and adopting a coefficient calculation formula as follows:

Considering that if the value of the live account number is zero under the condition of a stable time sequence, the value of Ib1 is zero, the quantitative evaluation value of the value stability of the live account number is 0. Therefore, by adding 1 to Ib, mapping the value range to the (0, 2) range, and multiplying the value range as a weighting coefficient by the profit expectation IE to obtain the final live value characteristic quantization factor, wherein the calculation formula is as follows:

LSR=(1+Ib)IE (10)

The method for determining the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast comprises the steps of obtaining identification information of a target object for the live broadcast, determining whether the target object belongs to a multi-channel network mechanism according to the identification information, and multiplying the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast with a preset weight coefficient under the condition that the target object belongs to the multi-channel network mechanism to obtain the comprehensive quantitative evaluation index of the target live broadcast acceleration demand.

In addition, according to the live broadcast bandwidth demand index, the network quality characteristic quantization factor and the live broadcast value characteristic quantization factor, the live broadcast acceleration demand comprehensive quantization evaluation index corresponding to the live broadcast video is determined.

It should be noted that, through analyzing the scene of the live broadcast industry, two live broadcast ecologies mainly exist, one is an independent live broadcast owner without adding an MCN mechanism, and as all related activities of the live broadcast process are solely responsible, the reason for influencing the acceleration demand of the live broadcast is mainly that the live broadcast is unsmooth in blocking during the live broadcast period, the interaction with the live broadcast audience is influenced, the watching experience and satisfaction of the live broadcast audience are influenced, and finally the income acquired in the live broadcast main live broadcast process is influenced. From the technical point of view, the reason why the live broadcast is not smooth and the blocking occurs is mainly that the short-time uplink and downlink data flow is overlarge, and the original transacted network basic resources cannot meet the requirements, so that the network is congested.

In order to obtain factors affecting the direct broadcast acceleration demand of a direct broadcast owner more comprehensively, disassemble and refine specific scenes, and converge factor characteristics from three aspects of direct broadcast attributes, network quality and direct broadcast income conditions, wherein the direct broadcast attributes are composed of direct broadcast software DPI data and platform side user data, and comprise characteristics of direct broadcast platform vermicelli quantity, direct broadcast frequency, audience interaction times, audience quantity and the like, the characteristics mainly show direct broadcast bandwidth demand degree, for example, the audience quantity in the direct broadcast process is overlarge, and is mismatched with network bandwidth, network jam is possibly caused, bandwidth needs to be increased for solving, buffer time, buffer times, picture definition and the like in the network quality characteristics show the network quality problems in the direct broadcast, network quality improvement needs to be carried out timely, otherwise, the direct broadcast watching comfort level and smoothness are influenced, and further the audience satisfaction is influenced, and the current account number of direct broadcast account number is relevant characteristics, such as the direct broadcast account number of the direct broadcast account number can reflect the value.

The other live ecology is a group live broadcast acceleration demand attached to a live broadcast base, a network red hatching base and a specific live broadcast industry, and under the live broadcast ecology condition, the whole live broadcast group industry attribute, the region and the staged live broadcast acceleration demand are comprehensively considered besides the acceleration demand of a single live broadcast owner.

And calculating the demand degree of the direct broadcast acceleration service under the individual direct broadcast main live broadcast scene and the direct broadcast group scene according to the quantization indexes calculated according to the different direct broadcast acceleration demand scenes in the previous steps.

1. And (5) an acceleration demand quantitative evaluation analysis model under the individual live broadcast main live broadcast scene.

The individual live main live scene constructs three influencing factors of a bandwidth demand degree quantization index EGL, a network quality characteristic quantization factor NF and a live income characteristic quantization factor LSR of live. Because the three influence factors have different dimensions, comparison and combination cannot be performed, and in order to eliminate the dimension influence, the value ranges of the three influence factors are mapped to (-1, 1) space respectively through a Z-score normalization method, so that normalized influence factor indication EGL _nor,NF_nor,LSR_nor is obtained. And summing the three influencing factors, calculating the mean value to obtain a comprehensive quantitative evaluation index single_LSA of the direct broadcast acceleration requirement under the individual direct broadcast main direct broadcast scene, wherein the calculation formula is as follows:

2. the acceleration demand quantitative evaluation analysis model is attached to a live broadcast base, a network red hatching base and a live broadcast main scene of a specific live broadcast industry.

Compared with individual independent live broadcast owners, the network acceleration business handling method depends on the decision of a live broadcast base manager, and not only considers the acceleration requirements of a single live broadcast owner, but also comprehensively considers the acceleration requirements of the whole live broadcast group industry attribute, the belonging area and the staged plan on the live broadcast. By analyzing these factors, the main influencing factors are found to be the industry attribute of the live broadcast group, and are divided into two cases, wherein one is public welfare organization, the income value is not generally used as a guide, the price factor is relatively insensitive, and when the live broadcast accelerating service is purchased, whether the live broadcast propaganda effect required to be obtained can be achieved is considered. In addition, the commercial enterprise live broadcasting industry mainly takes the value of the live broadcasting integrally generated benefits as a guide, considers the live broadcasting integrally generated benefits, and if the live broadcasting integrally does not reach the income expectation, the possibility of purchasing the live broadcasting acceleration service is not high, otherwise, the possibility of purchasing is increased. According to the situation, the live broadcast acceleration service of the public welfare institution has higher purchase probability, and the commercial enterprise is smaller, so that the service needs to be corrected by adding a weight coefficient, the weight coefficient is recorded as beta, if the service is the public welfare institution, the coefficient is assigned as 1, and the commercial enterprise client is assigned as 0.8.

For the direct broadcast acceleration requirement group_LSA of the direct broadcast main Group attached to the Group, the industry coefficient beta is added for weighting and quantifying, and the calculation formula is as follows:

Group_LSA=β*Single_LSA (12)

According to the single_LSA and the group_LSA values, the processing of the direct broadcast acceleration requirement in the direct broadcast main direct broadcast scene can be correspondingly judged, and the larger the value is, the higher the requirement is, and the lower the requirement is otherwise. In the actual operation process, the operation recommendation can be carried out on the clients according to the single_LSA value and the group_LSA value in batches and multiple gradients, so that the operation success rate is improved, and the operation cost is reduced.

As other optional embodiments of the application, after determining the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast, the method can further execute the step of dynamically adjusting the network resource allocation of the live broadcast service according to the comprehensive quantitative evaluation index of the live broadcast acceleration demand.

Assume that the current live platform monitors LSAD-CQI for two live accounts a and B as 8.5 and 4.2, respectively. Account a has a high live bandwidth demand, frequent network problems, and high viewers and revenues, while these features of account B are relatively weak. Based on the above, the live broadcast platform decides to provide more network resources for the account a, including improving uplink bandwidth, optimizing CDN node distribution, and increasing server cache, so as to ensure live broadcast smoothness and user satisfaction of the account a. Meanwhile, the platform keeps the network resource allocation to account B unchanged, but continuously monitors its LSAD-CQI for subsequent adjustment.

Through the steps, the method has the advantages that 1. Abundant and high-quality data sources are obtained, and the back-end network data of an operator, the network quality data of a live broadcast platform and the user behavior data of the live broadcast platform are comprehensively considered. In particular, the back-end network data of the operators comprise quasi-real-time data of network quality change and the like. Compared with the traditional method of simply using live broadcast platform data or network back-end data, the method has better data support in the aspect of live broadcast acceleration demand evaluation, and the analyzed live broadcast acceleration demand is more accurate. 2. And in the evaluation process of the live broadcast acceleration demand scenes, the quantitative evaluation of the live broadcast acceleration demand multi-scene is creatively performed from two scenes of single live broadcast and live broadcast main with organization management, so that the live broadcast acceleration differentiation evaluation analysis of different live broadcast main groups is realized, and a theoretical basis is provided for the formulation of differentiated operation policies.

FIG. 2 is a flow chart of another data processing method according to an embodiment of the present application, as shown in FIG. 2, the method comprising the steps of:

Step S201, demand analysis. First, the acceleration requirements of live broadcast in different scenes are identified. Key factors include 1. Live attributes including live type (e.g., games, education, entertainment, etc.), live duration, live hours (peak or off-peak hours), etc. 2. Network quality, namely, network problems such as packet loss rate, delay, bandwidth fluctuation and the like in the live broadcast process. 3. Live income conditions, namely income related to a live owner, the number of viewers, user interactions (such as comments and praise) and the like, and reflect the commercial value and the user participation of live.

And S202, constructing individual live factor characteristic quantization factors. Based on the result of the demand analysis, an individual live factor characteristic quantization factor is constructed, and the factor comprehensively considers specific attributes of live broadcast, such as live broadcast type, time period and the like, and provides a preliminary quantization index for each live broadcast scene so as to facilitate subsequent analysis.

And S203, constructing a network quality characteristic quantization factor. The network quality feature quantization factor is constructed based on the frequency of network problems in the live broadcast process. The method specifically comprises the steps of monitoring network problems, namely detecting network quality in the live broadcast process in real time, and recording the number of problems in a specific time window (such as every minute).

And S204, constructing a live broadcast profit characteristic quantization factor.

The live broadcast profit characteristic quantification factor relates to analysis of commercial value and user participation of live broadcast, and specifically comprises the following steps of 1, evaluating the current value of a live broadcast account number by considering factors such as a vermicelli foundation, the number of viewers, the conversion rate and the like of a live broadcast owner. 2. And tracking the profit trend and the user growth trend of the live account, and evaluating the long-term growth potential of the account. 3. And quantifying the value and growth of the live account number, and establishing a characteristic quantification factor reflecting the live income condition for evaluating the potential business return of the live accelerating service.

And step 205, constructing a quantitative evaluation analysis model of the live broadcast acceleration requirements under multiple scenes.

And in the model construction stage, the three quantization factors (individual live factor characteristics, network quality characteristics and live income characteristics) are weighted and summed, and the average value is calculated, so that the comprehensive quantization evaluation index of the live acceleration requirement is finally obtained.

And acquiring the identification information of the target object in video live broadcasting from a background database of the live broadcasting platform. This may include the unique ID of the live account, the ID of the affiliated institution, etc., to facilitate subsequent attribution determination and demand assessment. And inquiring the registration information or contract terms of the target object according to the identification information to determine whether the live account belongs to an MCN organization. MCN institutions often have special collaboration with live platforms, and a flagged live account may enjoy a particular resource priority or preference policy. For determining a target object belonging to the MCN mechanism, the target object is adjusted according to the direct broadcast acceleration demand comprehensive quantitative evaluation index (LSAD-CQI) and a preset weight coefficient to obtain the target direct broadcast acceleration demand comprehensive quantitative evaluation index.

The three live broadcast scenes are assumed to be scene A, namely one educational live broadcast, the live broadcast attribute is good, the network quality is general, and the income situation is excellent. And a scene B, wherein a game is live, the live attribute is excellent, the network quality is poor, and the income situation is good. And a scene C, namely entertainment live broadcast, the live broadcast attribute is general, the network quality is good, and the income situation is general.

By analyzing and quantifying the three feature factors in each scene, the values of scene a (aif=80), (NQF =50), (lrf=90) are obtained. Scene B (aif=90), (NQF =30), (lrf=70). Scene C (aif=50), (NQF =80), (lrf=50).

According to the model output calculation formula, the following comprehensive quantitative evaluation index is calculated, wherein LSAD-CQI _A＝73.33;LSAD-CQI_B＝63.33;LSAD-CQI_C =60.

Based on multi-scene analysis, three key factors including live broadcast attribute, network quality and live broadcast income condition can be comprehensively considered by constructing LSAD-CQI model, and an accurate quantitative evaluation index is provided for live broadcast acceleration service. The platform can dynamically adjust network resource allocation according to the level of LSAD-CQI values, and preferentially meets the live broadcast scene with higher LSAD-CQI, so that the overall live broadcast experience and the resource utilization efficiency are optimized. The method not only improves the pertinence of the live broadcast acceleration service, but also promotes the healthy development of the live broadcast industry, and meets the requirements of users on high-quality live broadcast experience.

According to the method, through fully analyzing the live actual scenes, corresponding live acceleration scene demand quantitative evaluation models are respectively constructed from the individual live main live angle and the organized management live main live angle, and the differential evaluation quantification of the live acceleration demands under different scenes is realized. The method has the advantages that through the live broadcast acceleration demand quantitative evaluation model, the mode that qualitative analysis is carried out on the live broadcast acceleration demands of a live broadcast main body mainly by means of subjective experience and simple statistical analysis is changed, the obtained result is more evidence and scientific, the accuracy of the live broadcast acceleration service evaluation result is effectively improved, in addition, after the live broadcast main body is scored through the quantitative model, the live broadcast acceleration demand quantitative evaluation model is more convenient and effective in the aspect of result landing use, the demand degree score is obtained through quantitative scoring evaluation on the live broadcast acceleration demands of each live broadcast main body, wherein the evaluation score value is larger, the description demand degree is higher, otherwise, the demand degree is smaller, and the display of the live broadcast acceleration demand degree of the live broadcast main body in a more visual mode is realized. Operators can formulate multi-gradient operation strategies aiming at different influence degrees through the size of the direct broadcast main direct broadcast acceleration demand score, build differentiated operation capacity and realize accurate release of operation resources.

Fig. 3 is a block diagram of a data processing apparatus according to an embodiment of the present application, as shown in fig. 3, including:

The acquiring module 31 is configured to acquire live time sequence data corresponding to live video, where the live time sequence data includes a plurality of live time node data.

The first determining module 32 is configured to classify, among the plurality of live time node data, live time node data in which a preset condition occurs and live time node data in which the preset condition does not occur, and determine a live bandwidth requirement index according to a classification result, where the preset condition includes that a live quality index of the live video broadcast does not meet a preset requirement due to a floating of the network bandwidth index.

A second determining module 33 is configured to determine a network quality feature quantization factor for characterizing network performance according to the number of network problems occurring in the live video process.

A third determining module 34 is configured to determine a live value feature quantization factor for characterizing a live value according to the number of viewers of the live video and live revenue information.

And the fourth determining module 35 is configured to determine a comprehensive quantitative evaluation index of the live broadcast acceleration requirement corresponding to the live broadcast according to the live broadcast bandwidth requirement index, the network quality characteristic quantization factor and the live broadcast value characteristic quantization factor.

Optionally, the first determining module 32 is further configured to perform the steps of taking a first preset duration as a time window, counting live time node data in the time window, assigning a first value to live time node data with a preset condition in the time window, assigning a second value to live time node data without the preset condition in the time window, obtaining a first time sequence corresponding to the time window, obtaining live time node data in a second preset duration, wherein the second preset duration comprises a plurality of time windows, merging the first time sequences corresponding to the time windows in the second preset duration to obtain a target time sequence, calculating a mathematical expected value of the target time sequence, normalizing the mathematical expected value to obtain a network quality level index in a video live process, taking the first preset duration as an independent variable, taking the number of the first value as a dependent variable, obtaining a first target by using a least square linear equation, mapping a first slope in the first target to the first digital interval to obtain a network quality change trend index, and summing the network quality level and the network quality change trend index, and obtaining a live bandwidth requirement change index by triangular transformation.

Optionally, the second determining module 33 is further configured to obtain the number of times of occurrence of the network problem in the live video broadcast process in a first preset statistical period, where the first preset statistical period includes a plurality of first time steps, determine the first number of times of occurrence of the network problem in each first time step, add a weight coefficient to the first number of times corresponding to the i-th first time step according to the sequence from the start time to the end time of the first preset statistical period, and obtain a plurality of second numbers of times, where the weight coefficient is the reciprocal of the fibonacci number, the fibonacci number F [ i ] =f [ i-1] +f [ i-2] corresponding to the i-th first time step, where F [0] =1, F [1] =1, i is a positive integer greater than 1, and calculate the sum of the plurality of second numbers to obtain the network quality feature quantization factor.

Optionally, the third determining module 34 is further configured to obtain a number of live video watching persons in a second preset statistical period, where the second preset statistical period includes a plurality of second time steps, determine a desired live video watching person number of a unit second time step according to a ratio of the number of the live video watching persons to the number of the second time steps, generate a second time sequence related to the number of the live video watching persons corresponding to each second time step and live video income information in each second time step, perform linear regression fitting on the second time sequence by using a least squares regression method to obtain a second objective equation, map a second slope in the second objective equation to the second digital interval by triangular transformation to obtain a income change trend index, and multiply calculate the desired live video watching person number of the unit second time step and the income change trend index to obtain the live video value feature quantization factor.

Optionally, the fourth determining module 35 is further configured to obtain identification information of a target object for live video broadcast, determine whether the target object belongs to a multi-channel network mechanism according to the identification information, and multiply a comprehensive quantitative evaluation index of a live video broadcast acceleration requirement corresponding to the live video broadcast with a preset weight coefficient to obtain a comprehensive quantitative evaluation index of the target live video broadcast acceleration requirement if the target object belongs to the multi-channel network mechanism.

Optionally, the fourth determining module 35 is further configured to perform a normalization process on the live broadcast bandwidth requirement index, the network quality feature quantization factor, and the live broadcast value feature quantization factor, and multiply calculate the normalization result to obtain a comprehensive quantization evaluation index of the live broadcast acceleration requirement corresponding to the live broadcast.

Optionally, the data processing device is further configured to perform the step of dynamically adjusting network resource allocation of the live broadcast service according to the live broadcast acceleration demand comprehensive quantitative evaluation index after determining the live broadcast acceleration demand comprehensive quantitative evaluation index corresponding to the live broadcast.

It should be noted that each module in fig. 3 may be a program module (for example, a set of program instructions for implementing a specific function), or may be a hardware module, and for the latter, it may be expressed in a form, but is not limited to, that each module is expressed in a form of one processor, or the functions of each module are implemented by one processor.

It should be noted that, the preferred implementation manner of the embodiment shown in fig. 3 may refer to the related description of the embodiment shown in fig. 1, which is not repeated herein.

Fig. 4 shows a block diagram of a hardware structure of a computer terminal for implementing a data processing method. As shown in fig. 4, the computer terminal 40 may include one or more processors 402 (shown in the figures as 402a, 402b, 402 n), which processor 402 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, a memory 404 for storing data, and a transmission module 406 for communication functions. Among other things, a display, an input/output interface (I/O interface), a Universal Serial BUS (USB) port (which may be included as one of the ports of the BUS BUS), a network interface, a power supply, and/or a camera. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 4 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the computer terminal 40 may also include more or fewer components than shown in FIG. 4, or have a different configuration than shown in FIG. 4.

It should be noted that the one or more processors 402 and/or other data processing circuits described above may be referred to herein generally as "data processing circuits. The data processing circuit may be embodied in whole or in part in software, hardware, firmware, or any other combination. Furthermore, the data processing circuitry may be a single stand-alone processing module or incorporated, in whole or in part, into any of the other elements in the computer terminal 40. As referred to in embodiments of the application, the data processing circuit acts as a processor control (e.g., selection of the path of the variable resistor termination connected to the interface).

The memory 404 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the data processing methods in the embodiments of the present application, and the processor 402 executes the software programs and modules stored in the memory 404 to perform various functional applications and data processing, that is, implement the data processing methods described above. Memory 404 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 404 may further include memory located remotely from processor 402, which may be connected to computer terminal 40 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission module 406 is used to receive or transmit data via a network. The specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 40. In one example, the transmission module 406 includes a network adapter (Network Interface Controller, NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission module 406 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.

The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 40.

It should be noted here that, in some alternative embodiments, the computer terminal shown in fig. 4 described above may include hardware elements (including circuits), software elements (including computer code stored on a computer readable medium), or a combination of both hardware elements and software elements. It should be noted that fig. 4 is only one example of a specific example, and is intended to illustrate the types of components that may be present in the computer terminal described above.

It should be noted that, the computer terminal shown in fig. 4 is configured to execute the data processing method shown in fig. 1, so that the explanation of the method for executing the command is also applicable to the electronic device, and will not be repeated herein.

The embodiment of the application also provides a nonvolatile storage medium, which comprises a stored program, wherein the program controls the equipment where the storage medium is located to execute the data processing method when running.

The non-volatile storage medium executes a program of acquiring live time sequence data corresponding to video live, wherein the live time sequence data comprises a plurality of live time node data, classifying live time node data with preset conditions and live time node data without preset conditions in the live time node data, and determining a live bandwidth demand index according to classification results, wherein the preset conditions comprise that live quality index of the video live does not meet preset requirements due to floating of the network bandwidth index, determining a network quality characteristic quantization factor used for representing network performance according to the number of times of network problems in the video live process, determining a live value characteristic quantization factor used for representing live value according to the number of watching people of the video live and live income information, and determining a comprehensive quantization evaluation index of the live acceleration demand corresponding to the video live according to the live bandwidth demand index, the network quality characteristic quantization factor and the live value characteristic quantization factor.

The embodiment of the application also provides electronic equipment, which comprises a memory and a processor, wherein the processor is used for running a program stored in the memory, and the data processing method is executed when the program runs.

The processor is used for operating a program for executing the following functions of acquiring live time sequence data corresponding to video live, wherein the live time sequence data comprises a plurality of live time node data, classifying live time node data with preset conditions and live time node data without preset conditions in the live time node data, and determining a live bandwidth demand index according to classification results, wherein the preset conditions comprise that live quality index of the video live does not meet preset requirements due to floating of the network bandwidth index, a network quality characteristic quantization factor for representing network performance is determined according to the number of times of network problems in the video live process, a live value characteristic quantization factor for representing live value is determined according to the number of watching persons of the video live and live income information, and a comprehensive quantization evaluation index of the live acceleration demand corresponding to the video live is determined according to the live bandwidth demand index, the network quality characteristic quantization factor and the live value characteristic quantization factor.

The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.

In the above embodiment of the present application, the collected information is information and data authorized by the user or sufficiently authorized by each party, and the processes of collection, storage, use, processing, transmission, provision, disclosure, application, etc. of the related data all comply with the related laws and regulations and standards, necessary protection measures are taken without violating the public welfare, and corresponding operation entries are provided for the user to select authorization or rejection.

In the several embodiments provided in the present application, it should be understood that the disclosed technology may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, for example, may be a logic function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the related art or all or part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a U disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, etc. which can store the program code.

The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application, which are intended to be comprehended within the scope of the present application.

Claims (8)

1. A data processing method, characterized in that it includes: Obtain the live streaming time series data corresponding to the live video broadcast, wherein the live streaming time series data includes multiple live streaming time node data; The live streaming time node data is classified into those that have a preset condition and those that do not, and the live streaming time node data is classified into those that do not have the preset condition. Based on the classification results, the live streaming bandwidth requirement index is determined. The preset condition includes: the live streaming quality index of the video live stream does not meet the preset requirements due to fluctuations in the network bandwidth index. Based on the number of network problems that occurred during the live video broadcast, a quantification factor for network quality characteristics used to characterize network performance was determined. Based on the number of viewers and revenue information of the live video stream, a quantitative factor for the live stream value characteristic is determined to characterize the value of the live stream. Based on the live streaming bandwidth requirement index, the network quality characteristic quantification factor, and the live streaming value characteristic quantification factor, a comprehensive quantitative evaluation index for the live streaming acceleration requirement corresponding to the video live streaming is determined. After determining the comprehensive quantitative evaluation index of the live streaming acceleration demand corresponding to the live video streaming, the method further includes: dynamically adjusting the network resource allocation of the live streaming service according to the comprehensive quantitative evaluation index of the live streaming acceleration demand. The system categorizes live streaming time node data from multiple live streaming time node data sets into those exhibiting a preset condition and those not exhibiting the preset condition. Based on the categorization results, it determines the live streaming bandwidth requirement index, including: using a first preset duration as a time window, statistically analyzing the live streaming time node data within the time window; assigning a first value to the live streaming time node data exhibiting the preset condition within the time window, and assigning a second value to the live streaming time node data not exhibiting the preset condition within the time window, thereby obtaining a first time series corresponding to the time window; and acquiring the live streaming time node data within a second preset duration, wherein the second preset duration includes multiple time windows. The first time series corresponding to multiple time windows within the second preset duration are merged to obtain a target time series; the expected value of the target time series is calculated and normalized to obtain a network quality level index during the live video broadcast; a linear equation is fitted using the least squares method with the first preset duration as the independent variable and the number of the first values as the dependent variable to obtain a first objective equation; the first slope in the first objective equation is mapped to a first numerical interval through trigonometric transformation to obtain a network quality change trend index; the network quality level index and the network quality change trend index are weighted and summed to obtain the live broadcast bandwidth demand index. 2. The method according to claim 1, characterized in that, determining a network quality feature quantification factor for characterizing network performance based on the number of network problems occurring during the live video broadcast includes: The number of network problems that occurred during a live video broadcast within a first preset statistical period is obtained, wherein the first preset statistical period includes multiple first time steps; Determine the first occurrence of a network problem within each first time step; According to the order from the start time to the end time of the first preset statistical period, a weight coefficient is added to the first number corresponding to the i-th first time step to obtain multiple second numbers. The weight coefficient is the reciprocal of the Fibonacci number. The Fibonacci number corresponding to the i-th first time step is F[i]=F[i-1]+F[i-2], where F[0]=1, F[1]=1, and i is a positive integer greater than 1. The network quality feature quantification factor is obtained by summing multiple second-order calculations. 3. The method according to claim 1, characterized in that, based on the number of viewers and revenue information of the live video stream, determining a quantitative factor for the live stream value characteristic used to characterize the live stream value includes: Obtain the number of viewers of the live video broadcast within a second preset statistical period, wherein the second preset statistical period includes multiple second time steps; The expected number of live viewers per unit of the second time step is determined based on the ratio of the number of viewers to the number of the second time step. Generate a second time series of information on the number of viewers for each second time step and the live streaming revenue within each second time step; The second time series was fitted with a linear regression using the least squares regression method to obtain the second objective equation. By using trigonometric transformation, the second slope in the second objective equation is mapped to the second numerical interval to obtain the income change trend indicator; The expected number of live viewers and the revenue trend index for the second time step of the unit are multiplied to obtain the quantitative factor of the live value feature. 4. The method according to claim 1, characterized in that determining the comprehensive quantitative evaluation index of live streaming acceleration demand corresponding to the live video broadcast includes: Obtain the identification information of the target object conducting the video live stream; Based on the identification information, determine whether the target object belongs to a multi-channel network organization; When the target object belongs to a multi-channel network organization, the comprehensive quantitative evaluation index of the live streaming acceleration demand corresponding to the live video is multiplied by a preset weight coefficient to obtain the comprehensive quantitative evaluation index of the target live streaming acceleration demand. 5. The method according to claim 1, characterized in that, based on the live streaming bandwidth demand index, the network quality characteristic quantification factor, and the live streaming value characteristic quantification factor, a comprehensive quantitative evaluation index for the live streaming acceleration demand corresponding to the video live streaming is determined, including: The live streaming bandwidth requirement index, the network quality characteristic quantification factor, and the live streaming value characteristic quantification factor are normalized respectively, and the normalization results are multiplied to obtain the comprehensive quantitative evaluation index of the live streaming acceleration requirement corresponding to the live video. 6. A data processing apparatus, characterized in that it comprises: The acquisition module is used to acquire the live streaming time series data corresponding to the live video, wherein the live streaming time series data includes multiple live streaming time node data; The first determining module is used to classify live streaming time node data that exhibits a preset condition and live streaming time node data that does not exhibit the preset condition from multiple live streaming time node data, and determine the live streaming bandwidth requirement index based on the classification result. The preset condition includes: the live streaming quality index of the video live stream does not meet the preset requirements due to fluctuations in the network bandwidth index. The second determining module is used to determine a network quality feature quantification factor for characterizing network performance based on the number of network problems that occur during the live video broadcast. The third determining module is used to determine the live streaming value feature quantification factor to characterize the value of the live streaming based on the number of viewers and the revenue information of the live streaming. The fourth determining module is used to determine the comprehensive quantitative evaluation index of the live streaming acceleration demand corresponding to the video live streaming based on the live streaming bandwidth demand index, the network quality characteristic quantification factor, and the live streaming value characteristic quantification factor. The data processing device is further configured to, after determining the comprehensive quantitative evaluation index of the live streaming acceleration demand corresponding to the live video, perform the following steps: dynamically adjust the network resource allocation of the live streaming service according to the comprehensive quantitative evaluation index of the live streaming acceleration demand. The first determining module is further configured to perform the following steps: using a first preset duration as a time window, statistically analyze the live streaming time node data within the time window; assign a first value to the live streaming time node data where the preset situation occurs within the time window, and assign a second value to the live streaming time node data where the preset situation does not occur within the time window, thereby obtaining a first time series corresponding to the time window; acquire the live streaming time node data within a second preset duration, wherein the second preset duration includes multiple time windows, merge the first time series corresponding to the multiple time windows within the second preset duration, and obtain a target time series; calculate the expected value of the target time series, and normalize the expected value to obtain a network quality level index during the live video streaming process; using the first preset duration as the independent variable and the number of the first value as the dependent variable, fit a linear equation using the least squares method to obtain a first objective equation; map the first slope in the first objective equation to a first numerical interval through trigonometric transformation to obtain a network quality change trend index; and perform a weighted summation of the network quality level index and the network quality change trend index to obtain the live streaming bandwidth demand index. 7. A non-volatile storage medium, characterized in that the non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device where the non-volatile storage medium is located to execute the data processing method according to any one of claims 1 to 5. 8. A computer program product comprising a computer program, characterized in that, when the computer program is executed by a processor, it implements the data processing method according to any one of claims 1 to 5.