Data processing method and device and nonvolatile storage medium

Abstract

The invention discloses a data processing method and device and a nonvolatile storage medium. The method comprises the following steps: acquiring live broadcast time sequence data corresponding to video live broadcast; classifying the live broadcast time node data in which the preset condition occurs and the live broadcast time node data in which the preset condition does not occur in the multiple pieces of live broadcast time node data, and determining a live broadcast bandwidth demand index according to a classification result; determining a network quality characteristic quantification factor used for representing network performance; determining a live broadcast value feature quantification factor used for representing the live broadcast value; and according to the live broadcast bandwidth demand index, the network quality feature quantification factor and the live broadcast value feature quantification factor, determining a live broadcast acceleration demand comprehensive quantification evaluation index corresponding to the video live broadcast. According to the method and the device, the technical problem that the live broadcast acceleration service cannot be accurately provided for the target user due to the fact that the acceleration requirements of different users on the network live broadcast cannot be accurately determined is solved.

Description

Technical Field

[0001] The present application relates to the technical field of big data analysis, and specifically, to a data processing method and device, and a non-volatile storage medium. Background Art

[0002] The rise and development of the live broadcast industry has gone through the budding stage of the industry, which began with the advancement of platform technology and the reduction of traffic costs, the wild development stage of live broadcast as a more direct way of information sharing, and the popularization and integration into the daily lives of the majority of residents. Live broadcast has shown a rapid development stage in multiple forms, especially the integration with the e-commerce industry, making it a direct and effective medium for all walks of life to reach users. At the same time, with the rapid development of the live broadcast industry and its promotion in different industries, the network speed of the live broadcast account has become an increasingly important factor affecting the live broadcast effect. Therefore, it is particularly important to judge the network speed requirements of live broadcast users and optimize the network speed in time according to the actual needs of the live broadcast account.

[0003] With social development and technological progress, we can use big data mining technology to judge the demand for live broadcasting, but combined with the actual situation, the existing technology still has many shortcomings.

[0004] Specifically, traditional user demand identification methods cannot accurately capture the real needs of users, especially in the live broadcast field, where user needs change at any time. It is impossible to accurately identify target users with high demands on network, fluency, streaming stability, etc., and thus it is impossible to accurately provide live broadcast acceleration services to target users.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The present application provides a data processing method and device, and a non-volatile storage medium to at least solve the technical problem of being unable to accurately provide live broadcast acceleration services to target users due to the inability to accurately determine the acceleration requirements of different users for live broadcasting.

[0007] According to one aspect of the present application, a data processing method is provided, including: obtaining live broadcast time series data corresponding to a live video broadcast, wherein the live broadcast time series data includes a plurality of live broadcast time node data; classifying the live broadcast time node data in which a preset situation occurs and the live broadcast time node data in which the preset situation does not occur among the plurality of live broadcast time node data, and determining a live broadcast bandwidth demand index according to the classification result, wherein the preset situation includes: the live broadcast quality index of the live video broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index; determining a network quality feature quantitative factor for characterizing network performance according to the number of network problems occurring during the live video broadcast; determining a live broadcast value feature quantitative factor for characterizing the live broadcast value according to the number of viewers of the live video broadcast and the live broadcast revenue information; determining a comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast according to the live broadcast bandwidth demand index, the network quality feature quantitative factor and the live broadcast value feature quantitative factor.

[0008] Optionally, the live broadcast time node data with preset situations and the live broadcast time node data without preset situations are classified among the multiple live broadcast time node data, and the live broadcast bandwidth demand index is determined according to the classification result, including: taking a first preset time length as a time window, and counting the live broadcast time node data within the time window; assigning a first value to the live broadcast time node data with preset situations within the time window, and assigning a second value to the live broadcast time node data without preset situations within the time window, to obtain a first time series corresponding to the time window; obtaining the live broadcast time node data within a second preset time length, wherein the second preset time length includes multiple time windows, The first time series corresponding to multiple time windows within the second preset time length are merged to obtain a target time series; the mathematical expectation value of the target time series is calculated, and the mathematical expectation value is normalized to obtain a network quality level indicator during the live video broadcast; the first preset time length is used as the independent variable, and the number of the first numerical values ​​is used as the dependent variable, and the least squares method is used to fit the linear equation to obtain a first target equation; through trigonometric transformation, the first slope in the first target equation is mapped to the first digital interval to obtain a network quality change trend indicator; weighted summation of the network quality level indicator and the network quality change trend indicator is performed to obtain a live broadcast bandwidth demand indicator.

[0009] Optionally, based on the number of times network problems occur during live video broadcasting, a network quality feature quantization factor used to characterize network performance is determined, including: obtaining the number of times network problems occur during live video broadcasting within a first preset statistical period, wherein the first preset statistical period includes multiple first time steps; determining the first number of times network problems occur in each first time step; adding a weight coefficient to the first number corresponding to the i-th first time step in order from the start time to the end time of the first preset statistical period to obtain multiple second numbers, wherein the weight coefficient is the reciprocal of the Fibonacci number, and the Fibonacci number corresponding to the i-th first time step is F[i]=F[i-1]+F[i-2], wherein F[0]=1, F[1]=1, and i is a positive integer greater than 1; and summing the multiple second numbers to obtain the network quality feature quantization factor.

[0010] Optionally, based on the number of viewers of the live video broadcast and the live broadcast revenue information, a live broadcast value characteristic quantitative factor used to characterize the value of the live broadcast is determined, including: obtaining 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; determining the expected number of live broadcast viewers per unit second time step based on the ratio of the number of viewers to the number of second time steps; generating a second time series of the number of viewers corresponding to each second time step and the live broadcast revenue information within each second time step; using the least squares regression method to perform linear regression fitting on the second time series to obtain a second target equation; mapping the second slope in the second target equation to a second digital interval through trigonometric transformation to obtain a revenue change trend indicator; multiplying the expected number of live broadcast viewers per unit second time step and the revenue change trend indicator to obtain the live broadcast value characteristic quantitative factor.

[0011] Optionally, determining a comprehensive quantitative evaluation index of live broadcast acceleration demand corresponding to live video broadcast includes: obtaining identification information of a target object for live video broadcast; determining whether the target object belongs to a multi-channel network organization based on the identification information; and when the target object belongs to the multi-channel network organization, multiplying the comprehensive quantitative evaluation index of live broadcast acceleration demand corresponding to the live video broadcast by a preset weight coefficient to obtain a comprehensive quantitative evaluation index of the target live broadcast acceleration demand.

[0012] Optionally, based on the live broadcast bandwidth demand index, the network quality characteristic quantification factor and the live broadcast value characteristic quantification factor, a comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast is determined, including: normalizing the live broadcast bandwidth demand index, the network quality characteristic quantification factor and the live broadcast value characteristic quantification factor respectively, and multiplying the normalized results to obtain the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast.

[0013] Optionally, after determining the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast, the method also includes: dynamically adjusting the network resource allocation of the live broadcast service according to the comprehensive quantitative evaluation index of the live broadcast acceleration demand.

[0014] According to another aspect of the present application, a data processing device is also provided, including: an acquisition module, used to acquire live broadcast time series data corresponding to live video broadcast, wherein the live broadcast time series data includes multiple live broadcast time node data; a first determination module, used to classify the live broadcast time node data that have preset situations and the live broadcast time node data that have not preset situations among the multiple live broadcast time node data, and determine the live broadcast bandwidth demand index according to the classification result, wherein the preset situation includes: the live broadcast quality index of the live broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index; a second determination module, used to determine the network quality feature quantitative factor used to characterize the network performance according to the number of network problems occurring during the live video broadcast; a third determination module, used to determine the live broadcast value feature quantitative factor used to characterize the live broadcast value according to the number of viewers of the live video broadcast and the live broadcast revenue information; a fourth determination module, used to determine the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast according to the live broadcast bandwidth demand index, the network quality feature quantitative factor and the live broadcast value feature quantitative factor.

[0015] According to another aspect of the present application, a non-volatile storage medium is provided, the storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the above data processing method.

[0016] According to another aspect of the present application, an electronic device is provided, including: a memory and a processor, the processor being used to run a program stored in the memory, wherein the above data processing method is executed when the program is run.

[0017] According to yet another aspect of the present application, a computer program is provided, wherein the above data processing method is implemented when the computer program is executed by a processor.

[0018] According to another aspect of the present application, a computer program product is provided, which includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above data processing method is implemented.

[0019] In the present application, a method is adopted to obtain live time series data corresponding to live video broadcast, wherein the live time series data includes multiple live time node data; the live time node data with preset situations and the live time node data without preset situations are classified in the multiple live time node data, and the live bandwidth demand index is determined according to the classification result, wherein the preset situation includes: the live quality index of the live video broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index; according to the number of network problems occurring during the live video broadcast, the network quality characteristic quantitative factor used to characterize the network performance is determined; according to the number of viewers of the live video broadcast and the live broadcast revenue information, the live broadcast value characteristic quantitative factor used to characterize the live broadcast value is determined; according to the live bandwidth demand index, the network quality characteristic quantitative factor and the live broadcast value characteristic quantitative factor, the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast is determined, so as to achieve the purpose of accurately determining the acceleration needs of different users for live network broadcast, thereby realizing the technical effect of accurately providing live broadcast acceleration services to target users, thereby solving the technical problem of being unable to accurately provide live broadcast acceleration services to target users due to the inability to accurately determine the acceleration needs of different users for live network broadcast. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 is a flow chart of a data processing method according to an embodiment of the present application;

[0022] Figure 2 is a flow chart of another data processing method according to an embodiment of the present application;

[0023] Figure 3 is a structural diagram of a data processing device according to an embodiment of the present application;

[0024] Figure 4 It is a hardware structure block diagram of a computer terminal according to a data processing method of an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0028] Forgetting curve: The forgetting curve was discovered by German psychologist Ebbinghaus and describes the pattern of human brain forgetting new things. Forgetting begins immediately after learning, and the process of forgetting is not uniform. The forgetting speed is very fast at first, and then gradually slows down.

[0029] Recency effect: The recency effect is a concept in psychology, which means that when we make judgments or decisions, we are more likely to be influenced by events or information we have recently experienced, and ignore the longer-term history or overall situation.

[0030] Multi-Channel Network (MCN): Any entity or organization that collaborates with content creators or directly produces a variety of unique content, and performs business and operational functions on the online platform where the content is published. MCN is not affiliated with the platform owner or directly affiliated with the channel itself. MCN provides various services such as content planning and production, publicity and promotion, fan management, and contract agency for Internet celebrities and self-media.

[0031] In the related technologies, firstly, the user demand identification method cannot accurately capture the real needs of users, especially in the field of live broadcasting, where user needs change at any time, and it is impossible to accurately identify target users with high demands on network, fluency, and streaming stability. Secondly, the user portrait construction method relies on limited data sources, resulting in the user portrait being not comprehensive and accurate. Thirdly, the relevant operation strategy is relatively extensive and cannot carry out accurate operation and promotion for different user groups, resulting in unsatisfactory operation results. In order to solve the above problems, relevant solutions are provided in the embodiments of the present application, which are described in detail below.

[0032] According to an embodiment of the present application, a method embodiment of a data processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] Figure 1 is a flow chart of a data processing method according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0034] Step S101, obtaining live time series data corresponding to the live video broadcast, wherein the live time series data includes a plurality of live time node data.

[0035] In step S101, by real-time monitoring of the live video stream, key performance indicators during the live broadcast process can be collected and recorded, including but not limited to live broadcast bandwidth, delay, packet loss rate, number of viewers, audience interaction frequency, live broadcast revenue, etc., to form a series of live broadcast time node data. These data are stored in the form of time series for subsequent analysis.

[0036] Step S102, classifying the live broadcast time node data that meet the preset conditions and the live broadcast time node data that do not meet the preset conditions among the multiple live broadcast time node data, and determining the live broadcast bandwidth demand index based on the classification result, wherein the preset conditions include: the live broadcast quality index of the video live broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index.

[0037] The network bandwidth index includes, but is not limited to, the following dimensions: upload bandwidth, download bandwidth, packet loss rate, delay, and jitter. The network bandwidth index in step S102 can be any one of the above dimensions, or a weighted combination of multiple dimensions. The live broadcast quality index includes, but is not limited to, video resolution, video frame rate, and interactive delay. The live broadcast quality index in step S102 can be any one of the above dimensions, or a weighted combination of multiple dimensions.

[0038] For example, for the preset minimum video resolution, in HD live broadcast, the preset minimum resolution may be set to 720p. When the network bandwidth is reduced to a level that is insufficient to maintain this resolution, the live broadcast quality is considered to be substandard. For the preset maximum delay time, the live broadcast delay should be kept within 2 seconds to ensure that the audience feels real-time. Once the delay exceeds the preset value, it can be considered that the live broadcast quality is affected. For the preset video buffering frequency and duration: For example, buffering no more than once every 5 minutes and no more than 5 seconds each time is acceptable. Buffering events that exceed this frequency and duration are considered to have degraded live broadcast quality. For the preset audio synchronization error, a synchronization error of less than 100 milliseconds is acceptable, and exceeding this value may affect the live broadcast experience. For the preset packet loss rate: a packet loss rate of no more than 1% is a basic requirement for live broadcast services. An increase in packet loss rate means reduced transmission efficiency and reduced video quality.

[0039] Step S103, determining a network quality feature quantization factor for characterizing network performance according to the number of times network problems occur during the live video broadcast.

[0040] Among them, delay time: usually in milliseconds (ms), indicating the average time from data transmission to reception. The preset requirement can be less than 100ms, otherwise it is considered a network problem. Packet loss rate: indicates the proportion of data packets that failed to arrive successfully during network transmission, usually expressed as a percentage. For example, a packet loss rate of more than 1% can be considered a network problem. Maximum bandwidth and average bandwidth: respectively indicate the maximum and average data transmission rates that the network can provide, in Mbps (megabits per second). When the actual bandwidth of the network is lower than the required minimum bandwidth threshold, it can be considered a network problem. Jitter: The time fluctuation of network delay, usually also in milliseconds. For example, jitter exceeding 20ms can be considered a problem. Encryption error rate: The proportion of data packets that are not correctly encrypted or decrypted during data transmission. The preset encryption success rate is 100%. Any situation below this value can be considered a network problem. Connection failure rate: The proportion of attempts to establish a network connection but failed. The preset connection success rate is 100%. A connection failure rate exceeding a certain threshold (such as 0.5%) can indicate network instability.

[0041] Step S104, determining a live broadcast value characteristic quantitative factor for characterizing the value of the live broadcast according to the number of viewers of the live video broadcast and the live broadcast revenue information.

[0042] Step S105, determining the 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.

[0043] According to the above steps, the live broadcast time series data corresponding to the live broadcast of the video is obtained, wherein the live broadcast time series data includes multiple live broadcast time node data; the live broadcast time node data with preset conditions and the live broadcast time node data without preset conditions are classified among the multiple live broadcast time node data, and the live broadcast bandwidth demand index is determined according to the classification result, wherein the preset conditions include: the live broadcast quality index of the live broadcast of the video does not meet the preset requirements due to the fluctuation of the network bandwidth index; according to the number of network problems occurring during the live broadcast of the video, the network quality characteristic quantitative factor used to characterize the network performance is determined; according to the number of viewers of the live broadcast of the video and the live broadcast revenue information, the live broadcast value characteristic quantitative factor used to characterize the live broadcast value is determined; according to the live broadcast bandwidth demand index, the network quality characteristic quantitative factor and the live broadcast value characteristic quantitative factor, the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast of the video is determined, thereby achieving the purpose of accurately determining the acceleration needs of different users for network live broadcast, thereby realizing the technical effect of accurately providing live broadcast acceleration services to target users.

[0044] The following Figure 1 The steps shown are exemplary and explanatory.

[0045] According to some optional embodiments of the present application, live broadcast time node data with preset situations and live broadcast time node data without preset situations are classified among multiple live broadcast time node data, and the live broadcast bandwidth demand index is determined according to the classification result. This can be achieved by the following method: taking a first preset duration as a time window, and counting the live broadcast time node data within the time window; assigning a first numerical value to the live broadcast time node data with preset situations within the time window, and assigning a second numerical value to the live broadcast time node data without preset situations within the time window, to obtain a first time series corresponding to the time window; obtaining the live broadcast time node data within a second preset duration, wherein the second preset duration The method includes multiple time windows, and the first time series corresponding to the multiple time windows within the second preset time length are merged to obtain the target time series; the mathematical expectation value of the target time series is calculated, and the mathematical expectation value is normalized to obtain the network quality level indicator during the video live broadcast; the first preset time length is used as the independent variable, the number of the first numerical value is used as the dependent variable, and the least squares method is used to fit the linear equation to obtain the first target equation; through trigonometric transformation, the first slope in the first target equation is mapped to the first digital interval to obtain the network quality change trend indicator; the network quality level indicator and the network quality change trend indicator are weighted and summed to obtain the live broadcast bandwidth demand indicator.

[0046] For example, D represents whether there is a demand for live broadcast acceleration, and 24 hours is used as a time window to count the live broadcast time node data within the time window.

[0047] In the time window, if the live broadcast time node data shows that the live broadcast is abnormal due to bandwidth reasons, it means that the current bandwidth cannot meet the live broadcast demand. At this time, D is assigned to 1, otherwise D is assigned to 0. Based on this, adding the time variable t, the time series {D t}, because bandwidth demand is usually an abnormal phenomenon, so {D t Most records are 0. Statistics of multiple 24-hour time series {D t}, and get the target time series {D d}, by calculating the target time series {D d The expected E value of} can quantify the bandwidth demand of live broadcast, and the E value is positively correlated with the bandwidth demand. If the E value is 0, it means that broadband has no effect on live broadcast. The calculation formula of expected E is as follows:

[0048]

[0049] The range of the expected abnormality E calculated according to formula (1) within the statistical time is [0, +∞). Considering that if the live broadcast anomaly occurs more than a certain number of times in a day, it will have a catastrophic impact on the live broadcast, the data with E values ​​greater than 100 are uniformly assigned a value of 100, and the range of the expected abnormality E is scaled to the interval [0, 100). At the same time, in order to facilitate subsequent integrated calculations, the value range of E is scaled to the interval [0, 1) through logarithmic transformation, denoted as EG.

[0050] The calculation formula is as follows:

[0051] EG=log 100 E (2)

[0052] For the target time series {D d}, with time d as the independent variable, the number of abnormalities D d is the dependent variable, n1 is the sequence length, and the least squares method is used to fit the linear equation. The slope is b. By analyzing the slope b of the linear equation, the {D d} trend. If the slope b is positive, it means that the time series is on an upward trend. If the slope b is negative, it means that the time series is on a downward trend. When the slope b is close to zero, it means that the time series may not have an obvious trend of change. At the same time, the magnitude of the change can be determined based on the absolute value of b. The specific calculation formula for the slope b is as follows:

[0053]

[0054] Because the slope b value range is (-∞, +∞), in order to eliminate the dimensional impact between different indicators when they are integrated and make the data comparable for subsequent analysis, the value range of b is mapped to the interval (-1, 1) through trigonometric transformation and recorded as LB. The calculation formula is as follows:

[0055]

[0056] Because both the network quality level EG and the network quality change trend LB will significantly affect the anchor's perception of network quality and trigger the anchor's demand for live broadcast acceleration, the bandwidth demand EGL for live broadcast is calculated in the form of weighted average. The formula is as follows:

[0057]

[0058] According to some other optional embodiments of the present application, determining a network quality feature quantization factor for characterizing network performance based on the number of network problems that occur during live video broadcasting can be achieved by the following method: obtaining the number of network problems that occur during live video broadcasting within a first preset statistical period, wherein the first preset statistical period includes multiple first time steps; determining the first number of network problems that occur within each first time step; adding a weight coefficient to the first number corresponding to the i-th first time step in order from the start time to the end time of the first preset statistical period to obtain multiple second numbers, wherein the weight coefficient is the reciprocal of the Fibonacci number, and the Fibonacci number corresponding to the i-th first time step is F[i]=F[i-1]+F[i-2], wherein F[0]=1, F[1]=1, and i is a positive integer greater than 1; and summing the multiple second numbers to obtain the network quality feature quantization factor.

[0059] In the above embodiment, first, the preset statistical period and time step are determined. Preset statistical period: set the first preset statistical period, for example, the first 10 minutes of the entire live broadcast process is used as the statistical period. First time step: divide these 10 minutes into multiple first time steps, each time step is 1 minute, so as to monitor the network status more carefully.

[0060] Secondly, network problems may include sudden drops in upload bandwidth, abnormal packet loss rates, and significant increases in latency. In each first time step (e.g., every minute in the last 10 minutes), detect whether the above-defined network problems occur during the live video broadcast. If they occur, it is recorded as the first time step in which the network problem occurs; otherwise, it is recorded as the first time step in which the network problem does not occur. Further count the number of times the network problem occurs in each first time step, i.e., the number of first times.

[0061] Again, a weight coefficient is assigned to the number of times the network problem occurs in each time step (i.e., the first number), and the weight coefficient is the reciprocal of F[i], i.e., 1 / F[i]. In the positive order from the start time to the end time of the first preset statistical period, starting from the 1st minute of the live broadcast to the 10th minute, the number of times the network problem occurs in each first time step is weighted one by one.

[0062] Assume that the first preset statistical period is the first 10 minutes after the start of the live video broadcast, and each first time step is 1 minute. The first 10 values ​​of the Fibonacci sequence are used as the denominator of the weight coefficient, and the first 10 values ​​of the Fibonacci sequence are defined as follows: 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.

[0063] In each first time step, the number of times a network problem occurs during the live video broadcast (the number of first times) is recorded. Assume that the number of network problems that occur during the statistical period is as follows: 1st minute (F[1]=1): 2 network problems occur; 2nd minute (F[2]=2): 1 network problem occurs; 3rd minute (F[3]=3): 3 network problems occur; 4th minute (F[4]=5): 2 network problems occur; 5th minute (F[5]=8): 4 network problems occur; 6th minute (F[6]=13): 1 network problem occurs; 7th minute (F[7]=21): 2 network problems occur; 8th minute (F[8]=34): 3 network problems occur; 9th minute (F[9]=55): 1 network problem occurs.

[0064] Then for the first minute (F[1]=1): the second number = 2 / 1=2; for the second minute (F[2]=2): the second number = 1 / 2=0.5; for the third minute (F[3]=3): the second number = 3 / 3=1; for the fourth minute (F[4]=5): the second number = 2 / 5=0.4; for the fifth minute (F[5]=8): the second number = 4 / 8=0.5; for the sixth minute (F[6]=13): the second number = 1 / 13≈0.077; for the seventh minute (F[7]=21): the second number = 2 / 21≈0.095; for the eighth minute (F[8]=34): the second number = 3 / 34≈0.088; for the ninth minute (F[9]=55): the second number = 1 / 55≈0.018.

[0065] Finally, the network quality characteristic quantitative factor can be obtained by summing up multiple secondary numbers.

[0066] It should be noted that, unlike the occurrence of problems related to live broadcast attributes, the live broadcaster can intuitively feel the negative impact of the related problems on the ongoing live broadcast. The network factor mainly shows from the network backend data that the backend network cannot provide the network resources required for live broadcast during the live broadcast, and the related problems caused by the resources, such as network congestion, high packet loss rate, network delay, network jitter and other network quality problems. The occurrence of network quality problems may not necessarily affect the current live broadcast effect, but a long period of resource mismatch will inevitably lead to a decrease in the live broadcaster's satisfaction with the live broadcast. Therefore, network-related problems are one of the main reasons for the adverse effects of live broadcasts, that is, the fundamental reason that affects the perception of the live broadcast picture in addition to the differences between the individual live broadcasters and their hardware equipment. Therefore, by quantifying the network quality characteristics, a more accurate prediction of live broadcast demand can be made. Because occasional quality problems such as network delays are not obvious to the live broadcaster, only when the related problems occur relatively frequently will they affect the live broadcast of the live broadcaster. Therefore, the network quality factor can be quantified by the frequency of network quality problems, that is, the number of times network problems occur. At the same time, as an individual live streamer, the relevant decision is mainly based on his own judgment. According to Ebbinghaus's forgetting curve theory and the "recency effect" theory in psychology, the individual memory of the live streamer follows the forgetting curve, that is, the longer the time from the present, the weaker the relevant memory, and the behavior has a "recency effect", that is, when making decisions, it is more susceptible to the influence of recent events or information. Therefore, when calculating the frequency, it is necessary to add the factors that affect the decision of the live streamer, such as the time span of the forgetting curve and the "recency effect".

[0067] Because different network problems will affect the live broadcast, in the counting process, no matter what kind of problem occurs, it will be included in the statistics, and the number of steps included in the statistical period is n2, and the number of network problems that occur in a fixed time step is N. i , where N is the number of times the problem occurs, and i is a specific time step within the statistical period. In order to take the "forgetting curve" and "recency effect" into consideration, 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 the weighting coefficient according to the statistical time from the occurrence of network problems to the distant ones, which is recorded as That is, add coefficients to construct the network quality feature quantization factor, and then perform weighted sum i. The network quality feature quantization factor is NF. The calculation formula is as follows:

[0068]

[0069] In some optional embodiments of the present application, determining a live broadcast value characteristic quantitative factor for characterizing the value of the live broadcast based on the number of viewers of the live video broadcast and the live broadcast revenue information can be achieved by the following method: obtaining 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; determining an expected value of the number of live broadcast viewers per unit second time step based on a ratio of the number of viewers to the number of second time steps; generating a second time series regarding the number of viewers corresponding to each second time step and the live broadcast revenue information within each second time step; performing linear regression fitting on the second time series using the least squares regression method to obtain a second target equation; mapping the second slope in the second target equation to a second digital interval through trigonometric transformation to obtain a revenue change trend indicator; multiplying the expected value of the live broadcast viewers per unit second time step and the revenue change trend indicator to obtain a live broadcast value characteristic quantitative factor.

[0070] It is understandable that the live streaming value LSR (Live streaming revenue), that is, the actual benefit value brought by the live streaming account to the live streamer, such as the number of account fans, number of likes, and number of views, which are positively correlated with the platform commission and live streaming sales, can indirectly reflect the value of the live streaming account and reflect the value produced by the account for the live streamer. Therefore, the size of the relevant value will directly affect the live streamer's willingness to invest costs. For example, if the live streaming account has already generated a very large stable revenue value or the revenue value has been growing positively, and the future revenue value is expected to be very considerable, then the live streamer is not sensitive to the network resource cost investment to improve the broadcast quality of the live streaming account and increase the audience satisfaction; on the contrary, the live streamer is not very willing to improve the account performance. Therefore, the sensitivity of the live streamer's cost investment can be quantified by constructing a quantitative factor of the live streaming revenue characteristics.

[0071] According to the above analysis, two points need to be considered for the quantitative analysis of live broadcast revenue. One is the stable revenue value of the live broadcaster's live broadcast account, which is the main influencing factor for the live broadcaster's cost investment; the other point is the growth of the live broadcast account, that is, the quantification of the changing trend of the live broadcast account value, which can also determine the live broadcaster's willingness to invest costs. For the quantification of the stable revenue value of the live broadcaster's live broadcast account, the number of viewers of the live broadcast account in the most recent live broadcast can be used for evaluation. At the same time, considering that the number of viewers of a single live broadcast is easily affected by abnormal events and fluctuates greatly, it is impossible to evaluate the impact on the stable value of the live broadcast account. Therefore, in order to eliminate the impact of outliers on the evaluation results, the stability of the live broadcast account's revenue is quantitatively evaluated by calculating the expected number of viewers per month for the past six months. The expected value is IE, the statistical period includes M months, the statistical month is m, and the number of viewers in the corresponding statistical month is I. m, then the expected calculation formula for the number of monthly live viewers of the live account in the past six months is:

[0072]

[0073] The growth of the live broadcast host's live broadcast account, that is, the changing trend of indicators such as the number of viewers, is also an important influencing factor of the live broadcast host's willingness to invest costs. However, the relevant changing trend can be regarded as a factor of the anticipation of the account value rather than an explicit factor. Under normal circumstances, the account value cannot be evaluated alone. However, the changing trend of the number of viewers indicator as a characteristic of the anticipation factor can be used as a weighted item to correct the quantitative evaluation of the live broadcast account value, improve the accuracy of the evaluation of the quantitative factors of the live broadcast value characteristics, and then quantify the value trend of the live broadcast account.

[0074] In order to facilitate the quantification of the income change trend (ICT) of the value of the live broadcast account over time, a time series {(x, y)} of the number of monthly viewers of the live broadcast account is constructed, where x is the statistical month, y is the live broadcast income of the statistical month, and n3 is the total number of months included in the statistical period. The least squares regression method is used to perform linear regression fitting on the data set, and the slope of the fitting equation is calculated as ICT. Then, based on the "positive or negative" of ICT, it is judged whether the live broadcast income changes over time with an increasing or decreasing trend. At the same time, the magnitude of the change in the number of live broadcast viewers can be judged based on the absolute value of ICT. The calculation formula is as follows:

[0075]

[0076] Because the slope Ib value range is (-∞, +∞), it cannot be directly used as a coefficient to correct the value of the live broadcast account. Therefore, through trigonometric transformation, the value range of b is mapped to (-1, 1), and the normalized value is used as the coefficient of the factor affecting the change of the live broadcast account value. The coefficient calculation formula is as follows:

[0077]

[0078] Considering that if the value of the live broadcast account is a stable time series, the value of Ib1 is zero, which will lead to a quantitative evaluation value of the stability of the live broadcast account value of 0. Therefore, by adding 1 to Ib and mapping its value range to the range of (0, 2), it is multiplied with the expected return IE as a weighted coefficient to obtain the final live broadcast value feature quantitative factor. The calculation formula is as follows:

[0079] LSR=(1+Ib)IE (10)

[0080] As some optional embodiments of the present application, determining the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast can be achieved by the following method: obtaining the identification information of the target object for the live video broadcast; determining whether the target object belongs to a multi-channel network organization based on the identification information; when the target object belongs to the multi-channel network organization, multiplying the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast by a preset weight coefficient to obtain the comprehensive quantitative evaluation index of the target live broadcast acceleration demand.

[0081] In addition, based on the live broadcast bandwidth demand index, the network quality characteristic quantitative factor and the live broadcast value characteristic quantitative factor, the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast can be determined. This can be achieved by the following method: normalizing the live broadcast bandwidth demand index, the network quality characteristic quantitative factor and the live broadcast value characteristic quantitative factor respectively, and multiplying the normalized results to obtain the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast.

[0082] It should be noted that through the analysis of the live broadcast industry scenario, it is found that there are mainly two types of live broadcast ecosystems. One is independent live broadcasters who have not joined MCN organizations. Since they are responsible for all activities related to the live broadcast process, the main reason affecting their demand for live broadcast acceleration is that they encounter lags and unsmoothness during their live broadcasts, which affects the interaction with the audience watching the live broadcast, and then affects the viewing experience and satisfaction of the audience, and ultimately affects the income obtained by the live broadcaster during the live broadcast. From a technical perspective, the main reason for the unsmooth live broadcast is that the short-term uplink and downlink data traffic is too large, and the original network infrastructure resources cannot meet the demand, causing network congestion.

[0083] In order to more comprehensively obtain the factors that affect the live broadcast host's demand for live broadcast acceleration, the specific scenarios are disassembled and refined, and the factor characteristics are converged from three aspects: live broadcast attributes, network quality, and live broadcast revenue. The live broadcast attributes are composed of the DPI data of the live broadcast software and the user data on the platform side, including the number of fans of the live broadcast platform, the frequency of live broadcast, the number of audience interactions, the number of viewers, and other characteristics. This part of the characteristics mainly shows the degree of demand for live broadcast bandwidth. For example, if the number of viewers is too large during the live broadcast, it will not match the network bandwidth, which may cause network jams and congestion, and the bandwidth needs to be increased to solve it; the buffering time, buffering times, picture clarity, etc. in the network quality characteristics show the actual network quality problems in the live broadcast, and the network quality needs to be improved in time, otherwise it will affect the comfort and smoothness of the live broadcast, and then affect the audience satisfaction; the number of fans, likes, and playbacks of the anchor's live broadcast account reflect the characteristics related to the popularity of the live broadcast account, which can reflect the value of the live broadcast account.

[0084] Another live broadcast ecology is dependent on the live broadcast base, Internet celebrity incubation base, and the collective live broadcast acceleration needs of specific live broadcast industries. In this live broadcast ecology, in addition to considering the acceleration needs of individual live broadcasters, we must also comprehensively consider the industry attributes of the entire live broadcast group, the region to which they belong, and the phased live broadcast acceleration needs.

[0085] Based on the quantitative indicators calculated for different live broadcast acceleration demand scenarios in the previous steps, the demand level for live broadcast acceleration services in individual live broadcast scenarios and live broadcast group scenarios is calculated.

[0086] 1. Quantitative evaluation and analysis model for acceleration demand in the live broadcast scenario of individual live broadcasters.

[0087] The individual live broadcast host live broadcast scene constructed three influencing factors: the quantitative index of bandwidth demand for live broadcast EGL, the quantitative factor of network quality characteristics NF, and the quantitative factor of live broadcast revenue characteristics LSR. Because the three influencing factors have different dimensions, they cannot be compared and merged. In order to eliminate the dimension effect, the Z-score normalization method is used to map the value ranges of the three influencing factors to the (-1, 1) space, and the normalized influencing factor indicator EGL is obtained. nor , NF nor , LSR nor The sum of the three influencing factors is calculated to obtain the comprehensive quantitative evaluation index Single_LSA of the live broadcast acceleration demand in the live broadcast scenario of an individual live broadcaster. The calculation formula is as follows:

[0088]

[0089] 2. Develop a quantitative evaluation and analysis model for accelerating demand in live broadcasting scenarios that are dependent on live broadcasting bases, internet celebrity incubation bases, and live broadcasting main scenarios in specific live broadcasting industries.

[0090] Compared with individual independent live broadcasters, live broadcasters who are attached to live broadcast bases, Internet celebrity incubation bases, and live broadcasters in specific live broadcast industries, the handling of network acceleration services generally depends on the decision of the live broadcast base manager, who not only considers the needs of individual live broadcasters for acceleration, but also comprehensively considers the industry attributes of the entire live broadcast group, the region to which they belong, and the needs of live broadcast acceleration in phased plans. By analyzing these factors, it is found that the main influencing factor is the industry attributes of the live broadcast group, which can be divided into two situations. One is a public welfare organization, which is generally not oriented by income value and is relatively insensitive to price factors. When purchasing live broadcast acceleration services, it is more considered whether the desired live broadcast publicity effect can be achieved. The other is the commercial live broadcast industry, which is mainly oriented by the income value generated by the live broadcast as a whole. It will consider the income of the live broadcast as a whole. If the overall income does not meet the expected income, the possibility of purchasing live broadcast acceleration services is not great, otherwise the possibility of purchasing is increased. According to this situation, public welfare organizations are more likely to purchase live broadcast acceleration services, while commercial enterprises are smaller, so it is necessary to correct it by adding a weight coefficient, which is denoted as β. If it is a public welfare organization, the coefficient is assigned to 1, and the commercial enterprise customer is assigned to 0.8.

[0091] For the live broadcast acceleration demand Group_LSA of the live broadcast hosts attached to the group, it is also necessary to add the industry coefficient β for weighted quantification. The calculation formula is as follows:

[0092] Group_LSA=β*Single_LSA (12)

[0093] According to the value of single_LSA and Group_LSA, the demand for live broadcast acceleration in the live broadcast scenario can be judged accordingly. The larger the value, the higher the demand, and vice versa. In the actual operation process, according to the value of single_LSA and Group_LSA, operation recommendations can be made to customers in batches and multiple levels to improve the operation success rate and reduce operation costs.

[0094] As other optional embodiments of the present application, after determining the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast, the following steps can also be performed: dynamically adjust the network resource allocation of the live broadcast service according to the comprehensive quantitative evaluation index of the live broadcast acceleration demand.

[0095] Assume that the current live broadcast platform monitors the LSAD-CQI of two live broadcast accounts A and B as 8.5 and 4.2 respectively. Account A has high live broadcast bandwidth requirements, frequent network problems, and high number of viewers and revenue, while these characteristics of account B are relatively weak. Based on this, the live broadcast platform decides to provide more network resources for account A, including increasing uplink bandwidth, optimizing CDN node distribution, and increasing server cache to ensure smooth live broadcast and user satisfaction of account A. At the same time, the platform keeps the network resource allocation to account B unchanged, but continues to monitor its LSAD-CQI for subsequent adjustments.

[0096] Through the above steps, it can be seen that this application has the following advantages: 1. Rich and high-quality data sources: It comprehensively considers the operator's back-end network data, the live broadcast platform network quality data, and the live broadcast platform user behavior data. In particular, the operator's back-end network data contains quasi-real-time data on changes in network quality, etc. Compared with the traditional use of live broadcast platform data or network back-end data, it has better data support in the evaluation of live broadcast acceleration needs, making the analyzed live broadcast acceleration needs more accurate. 2. More comprehensive analysis of acceleration demand scenarios: In the process of evaluating live broadcast acceleration demand scenarios, an innovative quantitative evaluation of multiple scenarios of live broadcast acceleration needs was conducted from two scenarios: single live broadcast hosts and live broadcast hosts managed by institutions. This realizes the differentiated evaluation and analysis of live broadcast acceleration for different groups of live broadcast hosts, and provides a theoretical basis for the formulation of differentiated operation policies.

[0097] Figure 2 is a flow chart of another data processing method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0098] Step S201: Demand analysis. First, identify the acceleration needs of live broadcast in different scenarios. Key factors include: 1. Live broadcast attributes: including live broadcast type (such as games, education, entertainment, etc.), live broadcast duration, live broadcast time period (peak or non-peak time period), etc. 2. Network quality: refers to network problems encountered during live broadcast, such as packet loss rate, delay, bandwidth fluctuation, etc. 3. Live broadcast revenue: involves the live broadcast host's revenue, number of viewers, user interaction (such as comments, likes), etc., reflecting the commercial value and user participation of live broadcast.

[0099] Step S202: Construct individual live broadcast factor characteristic quantitative factors. Based on the results of demand analysis, construct individual live broadcast factor characteristic quantitative factors, which comprehensively consider the specific attributes of live broadcast, such as live broadcast type, time period, etc., and provide a preliminary quantitative index for each live broadcast scene for subsequent analysis.

[0100] Step S203: Constructing a network quality feature quantification factor. The network quality feature quantification factor is constructed based on the frequency of network problems during the live broadcast. Specifically, it includes: Network problem monitoring: Real-time detection of network quality during the live broadcast, recording the number of problems within a specific time window (such as every minute).

[0101] Step S204: constructing a quantitative factor of live broadcast revenue characteristics.

[0102] The characteristic quantitative factor of live broadcast revenue involves the analysis of the commercial value and user engagement of live broadcast. The specific steps include: 1. Consider the fan base, number of viewers, conversion rate and other factors of the live broadcaster to evaluate the current value of the live broadcast account. 2. Track the revenue trend and user growth trend of the live broadcast account to evaluate the long-term growth potential of the account. 3. Quantify the value and growth of the live broadcast account and establish a characteristic quantitative factor that reflects the status of live broadcast revenue, which is used to evaluate the potential commercial return of the live broadcast acceleration service.

[0103] Step S205: Construct a quantitative evaluation and analysis model for live broadcast acceleration requirements in multiple scenarios.

[0104] During the model building phase, the above three quantitative factors (individual live broadcast factor characteristics, network quality characteristics, and live broadcast revenue characteristics) are weighted and summed, and the mean is calculated to finally obtain a comprehensive quantitative evaluation index for live broadcast acceleration demand.

[0105] Obtain the identification information of the target object that is currently broadcasting a live video from the background database of the live broadcast platform. This may include the unique ID of the live broadcast account, the ID of the organization to which it belongs, etc., to facilitate subsequent attribution judgment and demand assessment. Based on the identification information, query the registration information or contract terms of the target object to determine whether the live broadcast account belongs to an MCN organization. MCN organizations usually have special cooperation with live broadcast platforms, and their live broadcast accounts may enjoy specific resource priorities or preferential policies. For target objects determined to belong to MCN organizations, we will adjust them according to their comprehensive quantitative evaluation index for live broadcast acceleration needs (LSAD-CQI) and the preset weight coefficient to obtain the comprehensive quantitative evaluation index for target live broadcast acceleration needs.

[0106] Assume that there are three live broadcast scenarios: Scenario A: an educational live broadcast with good live broadcast attributes, average network quality, and excellent revenue. Scenario B: a game live broadcast with excellent live broadcast attributes, poor network quality, and good revenue. Scenario C: an entertainment live broadcast with average live broadcast attributes, good network quality, and average revenue.

[0107] By analyzing and quantifying the three characteristic factors in each scenario, the following values ​​are obtained: Scenario A: (AIF=80), (NQF=50), (LRF=90). Scenario B: (AIF=90), (NQF=30), (LRF=70). Scenario C: (AIF=50), (NQF=80), (LRF=50).

[0108] According to the model output calculation formula, the following comprehensive quantitative evaluation indicators are calculated: LSAD-CQI A =73.33;LSAD-CQI B =63.33;LSAD-CQI C =60.

[0109] Based on multi-scenario analysis, by constructing the LSAD-CQI model, we can comprehensively consider the three key factors of live broadcast attributes, network quality, and live broadcast revenue, providing accurate quantitative evaluation indicators for live broadcast acceleration services. The platform can dynamically adjust network resource allocation according to the LSAD-CQI value, giving priority to live broadcast scenarios with higher LSAD-CQI values, thereby optimizing the overall live broadcast experience and resource utilization efficiency. This method not only improves the pertinence of live broadcast acceleration services, but also promotes the healthy development of the live broadcast industry and meets users' demand for high-quality live broadcast experience.

[0110] Through the above steps, it can be seen that this application has fully analyzed the actual live broadcast scene, and from the perspective of individual live broadcast hosts and organized live broadcast hosts, respectively constructed corresponding live broadcast acceleration scene demand quantitative evaluation models, so as to realize the differentiated evaluation and quantification of live broadcast acceleration demand in different scenarios. Through the quantitative evaluation model of live broadcast acceleration demand, the previous method of qualitatively analyzing the live broadcast host's live broadcast acceleration demand, which mainly relied on subjective experience and simple statistical analysis, has been changed. The results obtained are more based on evidence and more scientific, and the accuracy of the evaluation results of live broadcast acceleration services has been effectively improved. In addition, after scoring the live broadcast host through the quantitative model, it is more convenient and effective in the use of the results. The quantitative evaluation model of live broadcast acceleration demand obtains the demand degree score by quantitatively scoring and evaluating the live broadcast acceleration demand of each live broadcast host. The larger the evaluation score value, the higher the demand degree, and vice versa, the smaller the demand degree, which realizes the display of the live broadcast host's live broadcast acceleration demand degree in a more intuitive way. The operator can formulate multi-gradient operation strategies for different degrees of influence according to the size of the live broadcast host's live broadcast acceleration demand score, build differentiated operation capabilities, and realize the precise delivery of operation resources.

[0111] Figure 3 is a structural diagram of a data processing device according to an embodiment of the present application, such as Figure 3 As shown, the device comprises:

[0112] The acquisition module 31 is used to acquire the live broadcast time series data corresponding to the live video broadcast, wherein the live broadcast time series data includes a plurality of live broadcast time node data.

[0113] The first determination module 32 is used to classify the live broadcast time node data that have preset situations and the live broadcast time node data that have not preset situations among multiple live broadcast time node data, and determine the live broadcast bandwidth demand index according to the classification result, wherein the preset situation includes: the live broadcast quality index of the video live broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index.

[0114] The second determination module 33 is used to determine a network quality feature quantification factor for characterizing network performance according to the number of times network problems occur during the live video broadcast.

[0115] The third determination module 34 is used to determine a live broadcast value characteristic quantitative factor for characterizing the value of the live broadcast according to the number of viewers of the live video broadcast and the live broadcast revenue information.

[0116] The fourth determination module 35 is used to determine the 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.

[0117] Optionally, the first determination module 32 is also used to perform the following steps: taking the first preset duration as the time window, and counting the live broadcast time node data within the time window; assigning a first numerical value to the live broadcast time node data in which a preset situation occurs within the time window, and assigning a second numerical value to the live broadcast time node data in which the preset situation does not occur within the time window, to obtain a first time series corresponding to the time window; obtaining the live broadcast time node data within the second preset duration, wherein the second preset duration includes multiple time windows, and merging the first time series corresponding to the multiple time windows within the second preset duration to obtain a target time series; calculating the mathematical expectation value of the target time series, and normalizing the mathematical expectation value to obtain a network quality level indicator during the live video broadcast; taking the first preset duration as the independent variable and the number of the first numerical values ​​as the dependent variable, using the least squares method to fit the linear equation to obtain a first target equation; mapping the first slope in the first target equation to a first digital interval through trigonometric transformation to obtain a network quality change trend indicator; performing weighted summation on the network quality level indicator and the network quality change trend indicator to obtain a live broadcast bandwidth demand indicator.

[0118] Optionally, the second determination module 33 is also used to perform the following steps: obtain the number of times network problems occur during the live video broadcast within a first preset statistical period, wherein the first preset statistical period includes multiple first time steps; determine the first number of times network problems occur within each first time step; add a weight coefficient to the first number corresponding to the i-th first time step in order from the start time to the end time of the first preset statistical period to obtain multiple second numbers, wherein the weight coefficient is the reciprocal of the Fibonacci number, and the Fibonacci number corresponding to the i-th first time step is F[i]=F[i-1]+F[i-2], wherein F[0]=1, F[1]=1, and i is a positive integer greater than 1; and sum up the multiple second numbers to obtain a network quality feature quantization factor.

[0119] Optionally, the third determination module 34 is further used to perform the following steps: 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; determine the expected value of the number of live broadcast viewers per second time step based on the ratio of the number of viewers to the number of second time steps; generate a second time series of information about the number of viewers corresponding to each second time step and the live broadcast revenue within each second time step; use the least squares regression method to perform linear regression fitting on the second time series to obtain a second target equation; map the second slope in the second target equation to a second digital interval through trigonometric transformation to obtain an income change trend indicator; multiply the expected value of the live broadcast viewers per second time step and the income change trend indicator to obtain a quantitative factor of the live broadcast value feature.

[0120] Optionally, the fourth determination module 35 is also used to perform the following steps: obtaining identification information of a target object for live video broadcast; determining whether the target object belongs to a multi-channel network organization based on the identification information; and when the target object belongs to a multi-channel network organization, multiplying a comprehensive quantitative evaluation index of live broadcast acceleration demand corresponding to the live video broadcast by a preset weight coefficient to obtain a comprehensive quantitative evaluation index of target live broadcast acceleration demand.

[0121] Optionally, the fourth determination module 35 is also used to execute the following steps: normalize the live broadcast bandwidth demand index, the network quality characteristic quantification factor and the live broadcast value characteristic quantification factor respectively, and multiply the normalization results to obtain a comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast.

[0122] Optionally, the data processing device is also used to perform the following steps after determining the comprehensive quantitative evaluation index of live broadcast acceleration demand corresponding to the live video broadcast: dynamically adjust the network resource allocation of the live broadcast service according to the comprehensive quantitative evaluation index of live broadcast acceleration demand.

[0123] It should be noted that the above Figure 3 The modules in the embodiment may be program modules (e.g., a set of program instructions for implementing a specific function) or hardware modules. For the latter, they may be expressed in the following forms, but are not limited thereto: the expression form of the above modules is a processor, or the functions of the above modules are implemented by a processor.

[0124] It should be noted that Figure 3 The preferred implementation of the illustrated embodiment can be found in Figure 1 The relevant description of the illustrated embodiment will not be repeated here.

[0125] Figure 4 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a data processing method. Figure 4 As shown, the computer terminal 40 may include one or more (402a, 402b, ..., 402n are used to illustrate) processors 402 (the 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. In addition, it may also include: 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 can be understood by those skilled in the art that Figure 4 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 4 More or fewer components as shown, or with Figure 4 Different configurations shown.

[0126] It should be noted that the one or more processors 402 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 40. As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0127] The memory 404 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the data processing method in the embodiment of the present application. The processor 402 executes various functional applications and data processing by running the software programs and modules stored in the memory 404, that is, realizing the above-mentioned data processing method. The memory 404 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 404 may further include a memory remotely arranged relative to the processor 402, and these remote memories may be connected to the computer terminal 40 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0128] The transmission module 406 is used to receive or send data via a network. The specific example of the above network 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), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 406 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0129] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 40 .

[0130] It should be noted that, in some optional embodiments, the above Figure 4 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 4 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0131] It should be noted that Figure 4 The computer terminal shown is used to execute Figure 1 The data processing method shown, therefore the relevant explanations in the execution method of the above command are also applicable to the electronic device and will not be repeated here.

[0132] An embodiment of the present application further provides a non-volatile storage medium, which includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the above data processing method.

[0133] A program for a non-volatile storage medium to perform the following functions: obtaining live time series data corresponding to a live video broadcast, wherein the live time series data includes a plurality of live time node data; classifying the live time node data that encounters a preset situation and the live time node data that does not encounter the preset situation among the plurality of live time node data, and determining a live bandwidth demand index based on the classification result, wherein the preset situation includes: the live quality index of the live video broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index; determining a network quality feature quantitative factor for characterizing network performance based on the number of network problems that occur during the live video broadcast; determining a live value feature quantitative factor for characterizing the value of the live broadcast based on the number of viewers of the live video broadcast and the live broadcast revenue information; determining a comprehensive quantitative evaluation index for the live broadcast acceleration demand corresponding to the live video broadcast based on the live bandwidth demand index, the network quality feature quantitative factor and the live broadcast value feature quantitative factor.

[0134] An embodiment of the present application further provides an electronic device, including: a memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the above data processing method is executed when the program is run.

[0135] The processor is used to run a program that performs the following functions: obtaining live broadcast time series data corresponding to live video broadcast, wherein the live broadcast time series data includes multiple live broadcast time node data; classifying the live broadcast time node data that have preset situations and the live broadcast time node data that have not preset situations among the multiple live broadcast time node data, and determining the live broadcast bandwidth demand index based on the classification result, wherein the preset situation includes: the live broadcast quality index of the live broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index; determining the network quality characteristic quantitative factor used to characterize the network performance according to the number of network problems that occur during the live video broadcast; determining the live broadcast value characteristic quantitative factor used to characterize the live broadcast value according to the number of viewers of the live video broadcast and the live broadcast revenue information; determining the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast according to the live broadcast bandwidth demand index, the network quality characteristic quantitative factor and the live broadcast value characteristic quantitative factor.

[0136] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0137] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0138] In the above-mentioned embodiments of the present application, the collected information is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary protection measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0140] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0141] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0142] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0143] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A data processing method, characterized in that: include: Acquire live time series data corresponding to the live video broadcast, wherein the live time series data includes a plurality of live time node data; Classifying the live broadcast time node data with preset conditions and the live broadcast time node data without the preset conditions among the plurality of live broadcast time node data, and determining the live broadcast bandwidth demand index according to the classification result, wherein the preset conditions include: the live broadcast quality index of the video live broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index; Determine a network quality feature quantification factor for characterizing network performance according to the number of network problems that occur during the live video broadcast; Determine a live broadcast value characteristic quantitative factor for characterizing the value of the live broadcast according to the number of viewers of the live broadcast and the live broadcast revenue information; According to the live broadcast bandwidth demand index, the network quality characteristic quantification factor and the live broadcast value characteristic quantification factor, a comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the video live broadcast is determined.

2. The method according to claim 1, characterized in that Classifying the live broadcast time node data where a preset situation occurs and the live broadcast time node data where the preset situation does not occur among the plurality of live broadcast time node data, and determining the live broadcast bandwidth demand index according to the classification result, including: Taking a first preset time length as a time window, counting the live broadcast time node data within the time window; Assigning a first value to the live broadcast time node data in which the preset situation occurs within the time window, and assigning a second value to the live broadcast time node data in which the preset situation does not occur within the time window, to obtain a first time series corresponding to the time window; Acquire the live broadcast time node data within a second preset duration, wherein the second preset duration includes a plurality of the time windows, and merge the first time series corresponding to the plurality of the time windows within the second preset duration to obtain a target time series; Calculating the mathematical expectation value of the target time series, and normalizing the mathematical expectation value to obtain a network quality level indicator during the live video broadcast; Taking the first preset time length as an independent variable and the number of the first values ​​as a dependent variable, a least squares method is used to fit a linear equation to obtain a first target equation; By means of trigonometric transformation, the first slope in the first objective equation is mapped into a first digital interval to obtain a network quality change trend indicator; The network quality level index and the network quality change trend index are weightedly summed to obtain the live broadcast bandwidth demand index.

3. The method according to claim 1, characterized in that According to the number of times the network problem occurs during the live video broadcast, a network quality feature quantitative factor for characterizing network performance is determined, including: Obtain the number of network problems that occur during live video broadcasting within a first preset statistical period, wherein the first preset statistical period includes a plurality of first time steps; determining the number of first occurrences of a network problem within each of the first time steps; In 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, wherein the weight coefficient is the reciprocal of the Fibonacci number, and the Fibonacci number corresponding to the i-th first time step is F[i]=F[i-1]+F[i-2], wherein F[0]=1, F[1]=1, and i is a positive integer greater than 1; The network quality feature quantization factor is obtained by summing up a plurality of the second orders.

4. The method according to claim 1, characterized in that According to the number of viewers of the live video broadcast and the live broadcast revenue information, a live broadcast value characteristic quantitative factor for characterizing the live broadcast value is determined, including: Obtaining the number of viewers of the live video broadcast within a second preset statistical period, wherein the second preset statistical period includes a plurality of second time steps; Determine an expected number of live broadcast viewers per second time step according to a ratio of the number of viewers to the number of the second time step; Generate a second time series of information about the number of viewers corresponding to each of the second time steps and the live broadcast revenue within each of the second time steps; Using the least squares regression method to perform linear regression fitting on the second time series to obtain a second target equation; By means of trigonometric transformation, the second slope in the second objective equation is mapped into a second digital interval to obtain an income change trend indicator; The expected value of the number of live broadcast viewers in the second time step of the unit and the income change trend index are multiplied to obtain the quantitative factor of the live broadcast value feature.

5. The method according to claim 1, characterized in that Determine the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast, including: Obtain identification information of a target object for the live video broadcast; Determining whether the target object belongs to a multi-channel network organization according to the identification information; In the case where the target object belongs to a multi-channel network organization, the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast is multiplied by a preset weight coefficient to obtain the comprehensive quantitative evaluation index of the target live broadcast acceleration demand.

6. The method according to claim 1, characterized in that According to the live broadcast bandwidth demand index, the network quality feature quantification factor and the live broadcast value feature quantification factor, a comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live broadcast of the video is determined, including: The live broadcast bandwidth demand index, the network quality characteristic quantification factor and the live broadcast value characteristic quantification factor are normalized respectively, and the normalization results are multiplied to obtain the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the video live broadcast.

7. The method according to claim 1, characterized in that After determining the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast, the method further includes: dynamically adjusting the network resource allocation of the live broadcast service according to the comprehensive quantitative evaluation index of the live broadcast acceleration demand.

8. A data processing device, characterized in that: include: An acquisition module, used to acquire live time series data corresponding to the live video broadcast, wherein the live time series data includes a plurality of live time node data; The first determination module is used to classify the live broadcast time node data with preset conditions and the live broadcast time node data without the preset conditions in the plurality of live broadcast time node data, and determine the live broadcast bandwidth demand index according to the classification result, wherein the preset conditions include: the live broadcast quality index of the video live broadcast does not meet the preset requirements due to the fluctuation of the network bandwidth index; A second determination module is used to determine a network quality feature quantification factor used to characterize network performance according to the number of network problems that occur during the live video broadcast; A third determination module is used to determine a live broadcast value characteristic quantitative factor used to characterize the live broadcast value according to the number of viewers of the live broadcast and the live broadcast revenue information; The fourth determination module is used to determine the comprehensive quantitative evaluation index of the live broadcast acceleration demand corresponding to the live video broadcast according to the live broadcast bandwidth demand index, the network quality characteristic quantitative factor and the live broadcast value characteristic quantitative factor.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the data processing method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 7 is implemented.

Images