Mobile network video user quality difference processing method, system, device and medium

Abstract

The present disclosure provides a mobile network video user quality difference processing method, system, electronic equipment and storage medium to solve the problem of poor flexibility and accuracy of quality difference user identification. The method comprises: obtaining original user detailed list data of a video user; performing data preprocessing on the detailed list data; obtaining experience index data of each video user through the preprocessed detailed list data to perform threshold analysis of the video user experience index and establish a video user experience index score table; analyzing the video user service duration data through the preprocessed original user detailed list data to establish a video user service duration score table; calculating an acceleration guarantee recommendation value according to the video user experience index score table and the video user service duration score table, and obtaining a video user acceleration guarantee recommendation value table; and selecting a video user according to the acceleration guarantee recommendation value table for network acceleration. The present disclosure can improve the accuracy and evaluation adaptability of quality difference user identification.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of network communication, in particular to a mobile network video user quality difference processing method, a mobile network video user quality difference processing system, an electronic device and a computer readable storage medium. BACKGROUND

[0002] With the rapid development of mobile Internet and streaming media services, users' quality requirements for video services on mobile networks are increasingly improving. How to effectively evaluate and optimize the quality of experience of video users has become an important issue in the field of mobile communication. The quality of experience of mobile network video services is usually quantified by a series of key quality indicators (KQI, Key Quality Indicators), such as download rate, latency, and stall frequency.

[0003] Traditional methods mostly use static thresholds to judge the quality of experience of users, but due to the complexity and instability of mobile network environment, the static threshold method cannot adapt to changes in different network conditions, resulting in poor flexibility and accuracy of identifying poor quality users. Secondly, existing technologies often lack specialized analysis of key quality indicators for video users, making it difficult to accurately reflect the specific experience of video watching. In addition, most existing methods do not consider the video service behavior data of users, making it difficult for experience evaluation to fully reflect users' preferences and needs for video services. Finally, existing technologies usually only identify poor quality users, lack effective optimization and resource allocation means, and cannot provide necessary network acceleration and protection measures for users with poor experience in a timely manner. SUMMARY

[0004] In order to at least solve the problem in the prior art that static threshold setting is used to identify users with poor experience, which cannot adapt to changes in different network conditions, resulting in poor flexibility and accuracy of identifying poor quality users. The present disclosure provides a mobile network video user quality difference processing method, a mobile network video user quality difference processing system, an electronic device and a computer readable storage medium, which can more comprehensively analyze and locate users with poor experience, enhance the accuracy and rationality of scoring, and avoid the one-sidedness of simply relying on network indicators. The system can flexibly cope with changes in different network conditions, avoid evaluation errors under static thresholds, and improve the accuracy and evaluation adaptability of identifying poor quality users.

[0005] In a first aspect, the present disclosure provides a mobile network video user quality difference processing method, the method comprising:

[0006] obtaining original user detailed data of a cellular mobile network accelerated video user;

[0007] performing data preprocessing on the original user detailed data;

[0008] The original user bill data after preprocessing is used to obtain experience index data of each video user, so as to perform threshold analysis on the video user experience index and establish a video user experience index score table; and

[0009] The original user bill data after preprocessing is used to analyze video user service duration data and establish a video user service duration score table.

[0010] The video user experience index score table and the video user service duration score table are used to calculate an acceleration guarantee recommendation value and obtain a video user acceleration guarantee recommendation value table.

[0011] The video user acceleration guarantee recommendation value table is used to select a video user for network acceleration.

[0012] Further, the original user bill data includes:

[0013] User-related fields, protocol size classes, APPIDs, effective download rates, XKB (X Keyboard Extension) startup delays, traffic, and time.

[0014] Further, the data preprocessing of the original user bill data includes:

[0015] Extracting video user bills: based on user-related fields, protocol size classes, and APPIDs, matching video user list data in a cellular mobile network;

[0016] Data cleaning: detecting video user list data and removing abnormal values in the data, and supplementing default values in the data by using a mean filling method;

[0017] Granularity selection and video user service duration data acquisition: selecting a preset time length as a time granularity, and based on the video user list data after data cleaning, calculating the viewing service duration of each video user to obtain video user service duration data as a behavior index for evaluating video user experience.

[0018] Further,

[0019] The experience index includes effective download rates and XKB startup delays.

[0020] The original user bill data after preprocessing is used to obtain experience index data of each video user, so as to perform threshold analysis on the video user experience index and establish a video user experience index score table, including:

[0021] The effective download rate and the XKB start-up delay distribution of the video user are analyzed through the preprocessed original user detailed data, and the thresholds of the effective download rate and the XKB start-up delay are determined, and the effective download rate and the XKB start-up delay are divided into multiple score intervals respectively;

[0022] The low-rate recommended value interval and the high-latency recommended value interval are determined, and the score values corresponding to each interval of the effective download rate and each interval of the XKB start-up delay are determined respectively;

[0023] Based on the score intervals and the score value ranges of the effective download rate and the XKB start-up delay, a video user experience index score table is formulated.

[0024] Further, the video user service duration data is analyzed through the preprocessed original user detailed data, and a video user service duration score table is established, including:

[0025] According to actual business experience, the service duration of the video user is divided into multiple score intervals through the preprocessed original user detailed data, so as to reflect the activity and continuity of the video user watching the video, and the corresponding score values of each score interval are set;

[0026] Based on the score intervals and the score values of the service duration, a video user service duration score table is formulated.

[0027] Further, the acceleration guarantee recommended value is calculated according to the video user experience index score table and the video user service duration score table, and a video user acceleration guarantee recommended value table is obtained, including:

[0028] S1: the weights of the effective download rate and the XKB start-up delay are a and b respectively, the weights of the video user experience index and the video user service duration are c and d respectively, and a+b=1 and c+d=1;

[0029] S2: according to the obtained video user experience index score table, the experience value KQI is calculated, and the specific formula is as follows:

[0030] KQI=LR×a+HL×b;

[0031] Wherein, LR represents the score value corresponding to the interval of the effective download rate of the video user, and HL represents the score value corresponding to the interval of the XKB start-up delay of the video user;

[0032] S3: according to the obtained video user service duration score table, the service duration score value is obtained, and the acceleration guarantee recommended value RV is calculated in combination with the experience value KQI, and the specific formula is as follows:

[0033] RV=KQI×c+T×d;

[0034] Wherein, T is the score value corresponding to the interval in which the video user service duration is located;

[0035] S4: obtaining a video user acceleration guarantee recommendation value table according to the acceleration guarantee recommendation value RV.

[0036] Further, the selecting video users for network acceleration according to the acceleration guarantee recommendation value table comprises:

[0037] According to the acceleration guarantee recommendation value table, the acceleration guarantee recommendation value threshold is obtained, the acceleration guarantee recommendation times of the video users are counted according to the acceleration guarantee recommendation value threshold, and the video users are selected for acceleration according to the acceleration guarantee recommendation times of the video users.

[0038] Further, the counting the acceleration guarantee recommendation times of the video users according to the acceleration guarantee recommendation value threshold and selecting the video users for acceleration according to the acceleration guarantee recommendation times of the video users comprises:

[0039] Taking a preset time length as a granularity, the times of the video users within a certain time period that the acceleration guarantee recommendation value is greater than or equal to the acceleration guarantee recommendation value threshold are counted, and the acceleration guarantee recommendation times are obtained;

[0040] The acceleration guarantee recommendation times of the video users within a certain time period are sorted from high to low, and the users whose acceleration guarantee recommendation times are in a certain proportion of the total number of the video users are selected for acceleration, so as to ensure that the users with poor experience are preferentially provided with code rate guarantee.

[0041] In a second aspect, the disclosure provides a mobile network video user quality difference processing system, the system comprises:

[0042] An acquisition module is configured to acquire original user detailed data of a cellular mobile network acceleration video user;

[0043] A preprocessing module is configured to perform data preprocessing on the original user detailed data;

[0044] An experience index scoring module is configured to acquire experience index data of each video user through the preprocessed original user detailed data, to perform threshold analysis on the video user experience index, and to establish a video user experience index scoring table; and

[0045] A service duration scoring module is configured to analyze video user service duration data through the preprocessed original user detailed data, and to establish a video user service duration scoring table;

[0046] A recommendation value determination module is configured to calculate an acceleration guarantee recommendation value according to the video user experience index scoring table and the video user service duration scoring table, and to obtain an acceleration guarantee recommendation value table of the video users;

[0047] The acceleration module is configured to select the video user for network acceleration according to the acceleration guarantee recommendation value table.

[0048] In a third aspect, the present disclosure provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program stored in the memory, the processor executes the mobile network video user quality difference processing method according to any one of the first aspect.

[0049] In a fourth aspect, the present disclosure provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and when the processor executes the computer program, the mobile network video user quality difference processing method according to any one of the first aspect is implemented.

[0050] Advantages:

[0051] The mobile network video user quality difference processing method, the mobile network video user quality difference processing system, the electronic device and the storage medium provided by the present disclosure can adjust the KQI threshold according to the actual network environment and the user distribution, and ensure the accuracy and flexibility of the quality difference user identification. At the same time, the key KQI indicators of the video user and the behavior data such as service duration are combined to more objectively and comprehensively reflect the video service experience of the video user. The users for priority acceleration are selected through the acceleration guarantee recommendation value, the effective allocation of resources is realized, the users with poor experience can obtain timely service guarantee under the dynamic change of network conditions, and the overall user experience and network resource utilization rate are improved. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 A flowchart of a mobile network video user quality difference processing method provided by the first embodiment of the present disclosure is shown in the figure;

[0053] Figure 2 A flowchart of a mobile network video user quality difference processing method provided by the second embodiment of the present disclosure is shown in the figure;

[0054] Figure 3 An architecture diagram of a mobile network video user quality difference processing system provided by the third embodiment of the present disclosure is shown in the figure;

[0055] Figure 4 An architecture diagram of an electronic device provided by the fourth embodiment of the present disclosure is shown in the figure. DETAILED DESCRIPTION

[0056] In order for those skilled in the art to better understand the technical solutions of the present disclosure, the present disclosure will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments and drawings described herein are only used to explain the present disclosure, and not to limit the present disclosure.

[0057] It should be noted that the terms "first", "second", etc. in the description and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence; and, without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other at will.

[0058] The terms used in the embodiments of the present disclosure are merely for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0059] In the following description, the suffixes such as "module", "part" or "unit" used to represent elements are merely for the convenience of description of the present disclosure, and have no specific meaning. Therefore, "module", "part" or "unit" can be used mixedly.

[0060] The technical solutions of the present disclosure and how the technical solutions of the present disclosure solve the technical problems existing in the prior art will be described in detail below with specific embodiments. It can be understood that in the embodiments of the present application, the execution subject can execute part or all of the steps in the embodiments of the present application, and these steps or operations are only examples, and the embodiments of the present application can also execute other operations or variations of various operations. In addition, each step can be executed in a different order as presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application are executed. In addition, the following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments.

[0061] Figure 1 A flowchart of a mobile network video user quality difference processing method provided by the embodiment of the present disclosure is shown in FIG. 1, which comprises the following steps. Figure 1 As shown in FIG. 1, the method comprises the following steps.

[0062] Step S101: Obtain the original user detail data of the cellular mobile network accelerated video user;

[0063] Step S102: Data preprocessing is performed on the original user detail data;

[0064] Step S103: Obtain the experience index data of each video user through the preprocessed original user detail data, perform threshold analysis on the video user experience index, and establish a video user experience index scoring table; and,

[0065] Step S104: Analyze the video user service duration data through the preprocessed original user detail data, and establish a video user service duration scoring table;

[0066] Step S105: Calculate the acceleration guarantee recommendation value according to the video user experience index score table and the video user service time length score table, and obtain the video user acceleration guarantee recommendation value table;

[0067] Step S106: Select a video user according to the acceleration guarantee recommendation value table for network acceleration.

[0068] The purpose of the embodiments of the present disclosure is to effectively identify video service experience poor users in the cellular mobile network acceleration user group, quantify the acceleration demand degree, intelligently recommend the corresponding acceleration strategy, and improve the video user (referred to as user) experience. Due to the limitation of network resources, in order to achieve the best network acceleration effect, it is necessary to analyze the quality of mobile network video users, so as to fairly and accurately screen out the video users who need to be accelerated and improved in priority, and perform network acceleration processing, and as much as possible to improve the utilization rate of network resources.

[0069] In the present disclosure, the cellular mobile network acceleration refers to the behavior of watching video through the cellular mobile network (non-Wi-Fi condition such as using 4G, 5G, etc. Cellular mobile network), and the video user is a user who needs to be accelerated through the cellular mobile network. The cellular mobile network acceleration is to improve the video watching experience of the user through the performance of the cellular mobile network.

[0070] In order to achieve the purpose of the embodiments of the present disclosure, the embodiments first acquire the original user detailed data of the video user through data acquisition, that is, the data of all video watching, downloading and other behaviors related to the user. For the original user detailed data, preprocessing is needed to remove abnormal data, improve data quality, unify data format, etc.

[0071] Through the preprocessed original user detailed data, the experience index data of each video user is obtained. The user experience index can reflect the video loading time, cache time, smoothness and response speed in the video playing process. Through threshold exploration of the influence of the actual network condition corresponding to the user distribution and experience index data on video watching, the interval of the low rate recommendation value and the interval of the high time delay recommendation value are determined, and the video user experience index score table is obtained. Thus, through dynamic threshold exploration, the threshold value of the experience index KQI is adjusted according to the change of user distribution and network condition. Compared with the traditional fixed threshold method, the dynamic threshold can adaptively cope with different network fluctuations and user demands.

[0072] The user viewing video service duration data can also be obtained through the user detailed data, the video user service duration data is analyzed, and a video user service duration scoring table is established; by introducing the service duration as the behavior data, the actual video service demand of the video user is more comprehensively and accurately evaluated; and the importance degree of the user's demand for mobile network acceleration is reflected.

[0073] Then, the acceleration guarantee recommendation value is calculated according to the video user experience index scoring table and the video user service duration scoring table, the acceleration guarantee recommendation value table of the video user is obtained, and the video user is selected according to the acceleration guarantee recommendation value table for network acceleration. The acceleration guarantee recommendation value table not only considers the demand for service experience improvement, but also considers the preference degree of the video user for the video service, so as to more comprehensively and accurately evaluate the actual video service demand of the video user, and thus to screen out the video user who needs to be accelerated and improved in priority.

[0074] The embodiment of the present disclosure adjusts the KQI threshold according to the actual network environment and the user distribution, ensures the accuracy and flexibility of the identification of the quality difference user, and combines the key KQI index of the video user and the service duration and other behavior data to more objectively and comprehensively reflect the video service experience of the video user. The user who needs to be accelerated in priority is screened out through the acceleration guarantee recommendation value, the effective allocation of resources is realized, the user with poor experience is ensured to obtain timely service guarantee under the dynamically changing network condition, and the overall user experience and network resource utilization rate are improved.

[0075] Further, the original user detailed data includes:

[0076] User related fields, protocol size class, APPID, effective download rate, XKB startup delay, traffic and time.

[0077] Through log collection, API interface (Application Programming Interface, API), or related database query and the like, all video viewing related data of the user can be obtained, and subsequent data statistical analysis of the user is facilitated.

[0078] Further, the data preprocessing of the original user detailed data includes:

[0079] Extracting the video user detailed data: according to the user related fields, the protocol size class and the APPID, the video user list data in the cellular mobile network is matched out;

[0080] Data cleaning: detecting the video user list data and eliminating the abnormal values in the data, and supplementing the default values in the data by using the mean filling method;

[0081] Granularity selection and video user service duration data acquisition: a preset time length is selected as the time granularity, the video user list data after data cleaning is counted to obtain the video user service duration data and the behavior index for evaluating the video user experience.

[0082] The video user list data after data cleaning is counted. A preset time length is selected as the time granularity. The preset time length can be selected according to the actual situation, such as one hour, two hours or three hours, etc. For the convenience of statistics, two hours are preferred as the time granularity, which can effectively balance the demand for real-time monitoring and data stability, timely reflect the dynamic changes of user experience, and make the network quality guarantee more targeted and practical. Taking two hours as the time granularity, the video user service duration data of each cellular mobile network video user is counted as the behavior index for evaluating the video user experience.

[0083] Further,

[0084] The experience index includes effective download rate and XKB start-up delay;

[0085] The experience index includes effective download rate and XKB start-up delay;

[0086] The effective download rate and XKB start-up delay of the video user are analyzed by the preprocessed original user list data to determine the thresholds of the effective download rate and XKB start-up delay, and the effective download rate and XKB start-up delay are divided into multiple scoring intervals respectively;

[0087] The effective download rate and XKB start-up delay of the video user are analyzed by the preprocessed original user list data to determine the thresholds of the effective download rate and XKB start-up delay, and the effective download rate and XKB start-up delay are divided into multiple scoring intervals respectively;

[0088] Based on the scoring interval and scoring value range of the effective download rate and XKB start-up delay, a video user experience index scoring table is formulated.

[0089] Setting the two key KQI indexes of effective download rate and XKB start-up delay can directly reflect the video user's viewing experience; the effective download rate is used to measure the smoothness of the video playback process, and the start-up delay reflects the response speed of the video start after the user clicks to play. Of course, other experience indexes can also be added, such as buffer time, video loading time, stall rate, play smoothness, packet loss rate, etc., which can be set according to the actual situation.

[0090] Through the video user list data, the effective download rate and the XKB starting delay are obtained, the threshold exploration of the video user experience index is performed, and a video user experience index scoring table is established. The specific steps are as follows:

[0091] According to the distribution of the user experience index, reasonable thresholds of the effective download rate and the XKB starting delay are determined, the effective download rate is divided into multiple scoring intervals, and the XKB starting delay is also divided into multiple scoring intervals, such as 4-10. The effective download rate scoring interval is preferably set to 7, and the XKB starting delay is set to 5. According to the actual situation, it is analyzed which interval may cause poor user experience, and the low-rate recommended value interval and the high-delay recommended value interval are determined respectively to ensure the dynamic adaptability of the threshold. The value of each interval is set, and the low-rate recommended value interval and the high-delay recommended value interval are set to a higher value. Therefore, according to the user step situation and the actual experience of each corresponding value, the interval division and assignment are performed. An exemplary value setting is that the effective download rate corresponds to a scoring value range of [0, 10], the lower the effective download rate, the higher the scoring value, and vice versa. The XKB starting delay corresponds to a scoring value range of [0, 10], the higher the XKB starting delay, the higher the scoring value, and vice versa. The scoring value is an integer.

[0092] Based on the exploration results of the threshold values, a video user experience index scoring table is formulated. The scoring table is used to convert the effective download rate and the starting delay into specific scores to quantify the experience of the video user. An exemplary video user experience index scoring table is shown in Table 1.

[0093] Table 1: Video user experience index scoring table

[0094]

[0095] Through dynamic threshold exploration, the reasonable threshold values of each KQI index are determined according to the user distribution, so that the system can dynamically adjust the evaluation standard according to the network environment and user distribution. Compared with the traditional fixed threshold scheme, the dynamic threshold is more flexible and can cope with different problems of line network, region, time and user demand, and adapt to the fluctuation of mobile network conditions and user experience.

[0096] Further, the video user service duration data is analyzed through the preprocessed original user detailed list data, and a video user service duration scoring table is established, including:

[0097] According to the actual business experience, the service duration of the video user is divided into multiple scoring intervals through the preprocessed original user detailed list data to reflect the activity and continuity of the video user watching video, and the corresponding scoring values of each scoring interval are set;

[0098] Based on the score interval and score value of the service duration, a video user service duration score table is formulated.

[0099] In order to obtain the service demand condition of the user for watching the video, according to the actual service experience, the service duration is divided into multiple score intervals, such as 3, and is scored to reflect the activity and continuity of the video user for watching the video. For example, for the two-hour granularity, that is, the 120-minute service duration, the service duration in the range of (60, 120] is scored as 10; the service duration in the range of (20, 60] is scored as 8; the service duration in the range of (6, 20] is scored as 4; and the service duration in the range of [0, 6] is not included in the analysis range.

[0100] Based on the exploration result of the threshold value, a video user service duration score table is formulated, as shown in Table 2, to quantify the behavior of the video user.

[0101] Table 2: Video user service duration score table

[0102]

[0103] Further, the acceleration guarantee recommendation value is calculated according to the video user experience index score table and the video user service duration score table, and a video user acceleration guarantee recommendation value table is obtained, which includes:

[0104] S1: The weights of the preset effective download rate and the XKB startup delay are a and b respectively, the weights of the video user experience index and the video user service duration are c and d respectively, and a+b=1 and c+d=1;

[0105] S2: According to the obtained video user experience index score table, the experience value KQI is calculated, and the specific formula is as follows:

[0106] KQI=LR×a+HL×b;

[0107] Wherein, LR represents the score value corresponding to the interval in which the video user effective download rate is located, and HL represents the score value corresponding to the interval in which the video user XKB startup delay is located;

[0108] S3: According to the obtained video user service duration score table, the service duration score value is obtained, and the acceleration guarantee recommendation value RV is calculated in combination with the experience value KQI, and the specific formula is as follows:

[0109] RV=KQI×c+T×d;

[0110] Wherein, T is the score value corresponding to the interval in which the video user service duration is located;

[0111] S4: The video user acceleration guarantee recommendation value table is obtained according to the acceleration guarantee recommendation value RV.

[0112] The weight values can be set by practical experience, such as setting the weight a of the effective download rate to 0.5-0.8; setting the weight b of the XKB start-up delay to 0.2-0.5, preferably a is set to 0.6 and b is set to 0.4; similarly, the weight c of the user experience index can be set to 0.6-0.9, preferably 0.7, and the weight d of the video user service time length can be set to 0.1-0.4, preferably 0.3.

[0113] According to the formula, a table containing the recommended value of each video user acceleration guarantee can be calculated. Among them, for the experience value, the experience value is between (9, 10] for excellent, (8, 9] for good, (6, 8] for medium, and [0, 6] for poor; for the service time length score value, (8, 10] is long, (4, 8] is medium, and (2, 4] is short.

[0114] The experience index and service time length are given weights in the process of scoring the video user. The weighted scoring mechanism can balance the influence of each index and avoid the deviation of a single index affecting the overall score, thereby ensuring the fairness and accuracy of the identification result, so that the score can comprehensively and objectively reflect the viewing experience of the video user.

[0115] Further, the selecting a video user according to the acceleration guarantee recommended value table includes:

[0116] According to the acceleration guarantee recommended value table, the video user slicing statistics verification is performed to obtain an acceleration guarantee recommended value threshold, the acceleration guarantee recommended times of the video user are counted according to the acceleration guarantee recommended value threshold, and the video user is selected to implement acceleration according to the acceleration guarantee recommended times of the video user.

[0117] According to the obtained acceleration guarantee recommended value table, the video users with different scores are sliced and counted to obtain an acceleration guarantee recommended value threshold. Due to limited network resources, the number of users in each score interval of the acceleration guarantee recommended value is counted to determine the users that can be accelerated and to determine the guarantee recommended value threshold. Taking the above preferred values as an example, it is verified by practice that when the acceleration guarantee recommended value threshold is set to 3, the overall acceleration guarantee effect is optimal. By counting the number of times of exceeding the guarantee recommended value threshold within a certain period of time, it is indicated that the user has a greater demand for network acceleration within this period of time, thereby screening out the users that need to be accelerated and improved in priority, ensuring that the acceleration resources are allocated to the users with the worst experience, so as to improve the network resource utilization rate, and adjusting the acceleration strategy regularly according to the network conditions.

[0118] Further, the counting the acceleration guarantee recommended times of the video user according to the acceleration guarantee recommended value threshold and selecting the video user to implement acceleration according to the acceleration guarantee recommended times of the video user includes:

[0119] The number of times that the acceleration guarantee recommendation value of the video user is greater than or equal to the acceleration guarantee recommendation value threshold within a certain time is counted as a granularity of a preset time length, to obtain an acceleration guarantee recommendation number.

[0120] The acceleration guarantee recommendation number of the video user within a certain time is sorted from high to low, and users whose acceleration guarantee recommendation number is in the top certain proportion of the total number of video users are selected to implement acceleration, to ensure that rate guarantee is provided to users with poor experience in priority.

[0121] The number of times that the acceleration guarantee recommendation value of the video user is greater than or equal to the acceleration guarantee recommendation value threshold within a certain time is counted as a granularity of a preset time length, to obtain an acceleration guarantee recommendation number.

[0122] According to the acceleration guarantee recommendation value, the video user most in need of priority acceleration improvement is screened out, which can ensure that acceleration resources are allocated to users with the worst experience, further improve the utilization rate of network resources, and make limited network and service resources more effectively improve user experience. At the same time, regular acceleration recommendation value calculation and statistics can adapt to the dynamic changes of network and user behavior, to ensure the timeliness and accuracy of the acceleration strategy.

[0123] The embodiments of the present disclosure can comprehensively analyze and locate users with poor experience by comprehensively considering the behavior data of the users, enhance the accuracy and rationality of the score, and avoid the one-sidedness of simply relying on network indicators. At the same time, the dynamic threshold mechanism can make the system flexibly cope with changes in different network conditions, avoid evaluation errors under a static threshold, and improve the accuracy and evaluation adaptability of poor user identification. By calculating the acceleration guarantee recommendation value, the user in need of priority acceleration improvement is screened out, to ensure that acceleration resources are allocated to users with the worst experience, and the acceleration strategy is adjusted according to network conditions on a regular basis, to improve the network resource utilization rate.

[0124] The second embodiment also provides a mobile network video user poor quality processing method, as shown in Figure 2 The method comprises the following steps:

[0125] 1) Data acquisition:

[0126] Obtain the original user detail data of the cellular mobile network acceleration user (i.e. video user), including user related fields, protocol size class, APPID, effective download rate, XKB startup delay, traffic and time.

[0127] 2) Data preprocessing of the original user detail data of the cellular mobile network acceleration user:

[0128] The data preprocessing of the original user detail data of the cellular mobile network acceleration user includes matching the inherited video user list data, data cleaning and statistical granularity selection, obtaining video user service duration data, as follows:

[0129] a. Extract video user details: According to the user related fields, protocol size class and APPID, match the video user list data in the cellular mobile network.

[0130] b. Data cleaning: Detect the video user list data and eliminate outliers in the data to ensure the rationality of the data distribution. For default values, use the mean filling method to supplement to ensure the integrity of the data.

[0131] c. Granularity selection and video user service duration data acquisition: Perform statistical analysis on the video user list data after data cleaning. Select two hours as the time granularity to effectively balance the needs of real-time monitoring and data stability, timely reflect the dynamic changes of user experience, and make the network quality guarantee more targeted and practical. With two hours as the time granularity, the viewing service duration of each cellular mobile network video user is counted as a behavioral indicator for evaluating video user experience, and the video user service duration data is obtained.

[0132] 3) Threshold exploration of effective download rate and XKB startup delay to determine the interval of low rate recommended value and the interval of high latency recommended value, and obtain the video user experience index score table. Analyze the video user service duration data to establish the video user service duration score table. The specific steps of obtaining the video user experience index score table and the video user service duration score table are as follows:

[0133] 3.1) Obtain the effective download rate and XKB startup delay through the video user list data of step 2), and perform threshold exploration of the video user experience index to establish the video user experience index score table, as follows:

[0134] 3.1.1) According to the user distribution, determine reasonable thresholds of effective download rate and XKB startup delay, divide the effective download rate into 7 score intervals and divide the XKB startup delay into 5 score intervals, respectively calculate the low-rate recommended value interval and the high-delay recommended value interval, and ensure the dynamic adaptability of the threshold. The effective download rate corresponds to the score value range [0, 10], the lower the effective download rate, the higher the score value, and vice versa. The XKB startup delay corresponds to the score value range [0, 10], the higher the XKB startup delay, the higher the score value, and vice versa. The score value is an integer.

[0135] 3.1.2) Based on the exploration results of the threshold value, develop a video user experience index score table, as shown in Table 1. The score table is used to convert the effective download rate and startup delay into specific scores to quantify the video user experience.

[0136] Table 1: Video user experience index score example

[0137]

[0138] 3.2) Through the video user service duration data of step 2), explore the threshold of the video user behavior index, and establish a video user service duration score table, the specific steps are as follows:

[0139] 3.2.1) According to the actual business experience, divide the service duration into 3 score intervals to reflect the activity and continuity of video users watching videos. For two-hour granularity, i.e. 120-minute service duration, analyze the service duration in the range (60, 120], the score value is 10; the service duration in the range (20, 60], the score value is 8; the service duration in the range (6, 20], the score value is 4; the service duration in the range [0, 6] is not included in the analysis range.

[0140] 3.2.2) Based on the exploration results of the threshold value, develop a video user service duration score table to quantify the behavior of video users.

[0141] Table 2: Video user service duration score example

[0142]

[0143] 4) Calculate the experience value and acceleration guarantee recommended value according to the video user experience index score table and the video user service duration score table obtained in step 3), and obtain the cellular mobile network acceleration user acceleration guarantee recommended value table. The specific steps are as follows:

[0144] 4.1) According to the actual business experience, the weights of the preset effective download rate and the XKB start-up delay are 0.6 and 0.4 respectively, and the weights of the video user experience index and the video user service duration are 0.7 and 0.3 respectively.

[0145] 4.2) According to the video user experience index score table, the experience value KQI is calculated, and the specific formula is as follows:

[0146] S2: According to the obtained video user experience index score table, the experience value KQI is calculated, and the specific formula is as follows:

[0147] KQI = LR x 0.6 + HL x 0.4;

[0148] Wherein, LR represents the score value corresponding to the interval in which the video user effective download rate is located, and HL represents the score value corresponding to the interval in which the video user XKB start-up delay is located;

[0149] 4.3) According to the video user service duration score table, the service duration score value is obtained, and the experience value KQI is combined to calculate the acceleration guarantee recommendation value RV, and the specific formula is as follows:

[0150] RV = KQI x 0.7 + T x 0.3;

[0151] Wherein, T is the score value corresponding to the interval in which the video user service duration is located;

[0152] 4.4) Obtain the acceleration guarantee recommendation value table of the cellular mobile network acceleration user. Among them, for the experience value, the experience value is between (9, 10] for excellent, (8, 9] for good, (6, 8] for medium, and [0, 6] for poor; for the service duration score value, (8, 10] is long, (4, 8] is medium, and (2, 4] is short. The acceleration guarantee recommendation table is shown in Table 3.

[0153] Table 3: Acceleration guarantee recommendation value table of cellular mobile network acceleration user

[0154] Experience value Business duration score value Acceleration guarantee recommendation value Poor Long 10 Poor Medium 9 Poor Short 8 Medium Long 7 Medium Medium 6 Medium Short 5 Good Long 4 Good Medium 3 Good Short 2 Excellent Long 1 Excellent Medium 0 Excellent Short 0

[0155] 5) According to the acceleration guarantee recommendation value obtained in step 4) and the acceleration guarantee recommendation value table of the cellular mobile network acceleration user, the video user slice statistics verification is performed to obtain the acceleration guarantee recommendation value threshold, the acceleration guarantee recommendation times are counted, the high frequency users are selected for acceleration, and thus the mobile network video user quality difference analysis and guarantee are completed. The specific steps are as follows:

[0156] a2: According to the acceleration guarantee recommendation value obtained in step S4 and the acceleration guarantee recommendation value table of the cellular mobile network, the video users with different scores are sliced and counted to obtain the acceleration guarantee recommendation value threshold. According to actual verification, when the acceleration guarantee recommendation value threshold is set to 3, the overall acceleration guarantee effect is optimal.

[0157] b2: Count the number of times that the video user's acceleration guarantee recommendation value is greater than or equal to 3 per week in two-hour increments.

[0158] c3: Sort the acceleration guarantee recommendation times of the cellular mobile network acceleration guarantee users in each week from high to low, and select the users whose acceleration guarantee recommendation times are in the top 50% of the total number of cellular mobile network acceleration guarantee users to implement acceleration, to ensure that rate guarantee is preferentially provided to users with poor experience.

[0159] The embodiments of the present disclosure are directed to video users among cellular mobile network acceleration users, and combine two key KQI indicators, effective download rate and XKB startup delay, which directly reflect the viewing experience of video users. Effective download rate is used to measure the smoothness of video playback process, and startup delay reflects the response speed of video startup after the user clicks to play. On the basis of traditional QoE (Quality of Experience) evaluation, video user service duration, a behavior data, is further introduced, which directly reflects the preference degree of video users for video services and further reflects the importance degree of mobile network acceleration demand.

[0160] The embodiments of the present disclosure determine reasonable threshold values of various KQI indicators by dynamic threshold exploration combined with user distribution, so that the system can dynamically adjust the evaluation standard according to the network environment and user distribution. Compared with the traditional fixed threshold scheme, the dynamic threshold is more flexible and can cope with different problems of line network, region, time and user demand, and adapt to the fluctuation of mobile network conditions and user experience.

[0161] The embodiments of the present disclosure assign weights to experience indicators and service duration in the process of scoring video users. The weighted scoring mechanism can balance the influence of various indicators, avoid the deviation of a single indicator affecting the overall score, and thus ensure the fairness and accuracy of the identification result, so that the score can comprehensively and objectively reflect the viewing experience of video users.

[0162] The embodiments of the present disclosure filter out video users who most need priority acceleration improvement according to the acceleration guarantee recommendation value, which can ensure that acceleration resources are allocated to users with the worst experience, further improve the utilization rate of network resources, and make limited network and service resources more effectively improve user experience. At the same time, regular acceleration recommendation value calculation and statistics can adapt to the dynamic changes of network and user behavior, and ensure the timeliness and accuracy of the acceleration strategy.

[0163] The third embodiment of the present disclosure further provides a mobile network video user quality difference processing system, as shown in Figure 3 The system comprises:

[0164] an acquisition module 11 configured to acquire original user detail data of a cellular mobile network accelerated video user;

[0165] a preprocessing module 12 configured to perform data preprocessing on the original user detail data;

[0166] an experience index scoring module 13 configured to acquire experience index data of each video user through the preprocessed original user detail data, perform threshold analysis on the video user experience index, and establish a video user experience index scoring table; and

[0167] a service duration scoring module 14 configured to analyze video user service duration data through the preprocessed original user detail data, and establish a video user service duration scoring table;

[0168] a recommended value determination module 15 configured to calculate an acceleration guarantee recommended value according to the video user experience index scoring table and the video user service duration scoring table, and obtain an acceleration guarantee recommended value table of the video user;

[0169] an acceleration module 16 configured to select a video user according to the acceleration guarantee recommended value table for network acceleration.

[0170] Further, the original user detail data includes:

[0171] a user-related field, a protocol size class, an APPID, an effective download rate, an XKB startup delay, traffic, and time.

[0172] Further, the preprocessing module 12 is specifically configured to:

[0173] extract video user details: according to the user-related field, the protocol size class, and the APPID, match out video user list data in the cellular mobile network;

[0174] data cleaning: detect the video user list data and eliminate abnormal values in the data, and supplement default values in the data by using a mean filling method;

[0175] granularity selection and video user service duration data acquisition: select a preset time length as a time granularity, and statistically acquire a viewing service duration of each video user from the video user list data after data cleaning, to obtain video user service duration data as a behavior index for evaluating the video user experience.

[0176] Further,

[0177] The experience index includes an effective download rate and an XKB startup delay.

[0178] The experience index scoring module 13 is specifically configured to:

[0179] The effective download rate and the XKB startup time delay distribution of the video user are analyzed through the preprocessed original user bill data, the thresholds of the effective download rate and the XKB startup time delay are determined, and the effective download rate and the XKB startup time delay are divided into multiple score intervals respectively;

[0180] The low-rate recommended value interval and the high-time-delay recommended value interval are determined, and the score values corresponding to each interval of the effective download rate and each interval of the XKB startup time delay are determined respectively;

[0181] Based on the score interval and the score value range of the effective download rate and the XKB startup time delay, a video user experience index score table is formulated.

[0182] Further, the service duration scoring module 14 is specifically configured as:

[0183] According to the actual service experience, the service duration of the video user is divided into multiple score intervals through the preprocessed original user bill data, so as to reflect the activity and continuity of the video user watching the video, and the corresponding score values of each score interval are set;

[0184] Based on the score interval and the score value of the service duration, a video user service duration score table is formulated.

[0185] Further, the recommended value determination module 15 is specifically configured to obtain a video user acceleration guarantee recommended value table through the following steps:

[0186] S1: The weights of the effective download rate and the XKB startup time delay are a and b respectively, the weights of the video user experience index and the video user service duration are c and d respectively, and a+b=1 and c+d=1;

[0187] S2: According to the obtained video user experience index score table, the experience value KQI is calculated, and the specific formula is as follows:

[0188] KQI=LR×a+HL×b;

[0189] Wherein, LR represents the score value corresponding to the interval of the effective download rate of the video user, and HL represents the score value corresponding to the interval of the XKB startup time delay of the video user;

[0190] S3: According to the obtained video user service duration score table, the service duration score value is obtained, and the acceleration guarantee recommended value RV is calculated in combination with the experience value KQI, and the specific formula is as follows:

[0191] RV=KQI×c+T×d;

[0192] Wherein, T is the score value corresponding to the interval of the service duration of the video user;

[0193] S4: obtaining a video user acceleration guarantee recommendation value table according to the acceleration guarantee recommendation value RV.

[0194] Further, the acceleration module 16 is specifically configured as:

[0195] According to the video user slice statistical verification of the acceleration guarantee recommendation value table, the acceleration guarantee recommendation value threshold is obtained, the acceleration guarantee recommendation times of the video user are counted according to the acceleration guarantee recommendation value threshold, and the video user is selected to implement acceleration according to the acceleration guarantee recommendation times of the video user.

[0196] Further, the acceleration module 16 is specifically configured as:

[0197] With a preset time length as a granularity, the number of times that the acceleration guarantee recommendation value of the video user is greater than or equal to the acceleration guarantee recommendation value threshold within a certain time is counted, and the acceleration guarantee recommendation times are obtained.

[0198] The acceleration guarantee recommendation times of the video user within a certain time are sorted from high to low, and the users whose acceleration guarantee recommendation times are in a certain proportion of the total number of video users are selected to implement acceleration, so as to ensure that the users with poor experience are preferentially provided with rate guarantee.

[0199] The mobile network video user quality difference processing system of the embodiment of the present disclosure is used to implement the mobile network video user quality difference processing method in the method embodiment one and the method embodiment two, so the description is relatively simple, and the specific description can be referred to in the method embodiment.

[0200] In addition, as Figure 4 shown, the fourth embodiment of the present disclosure further provides an electronic device, including a memory 100 and a processor 200, the memory 100 stores a computer program, when the processor 200 runs the computer program stored in the memory 100, the processor 200 executes the above various possible methods.

[0201] Among them, the memory 100 is connected with the processor 200, the memory 100 can adopt flash memory or read-only memory or other storage, and the processor 200 can adopt central processing unit or single-chip microcomputer.

[0202] In addition, the embodiment of the present disclosure further provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to execute the above various possible methods.

[0203] The computer readable storage medium includes a volatile or non-volatile, removable or non-removable medium implemented in any method or technology for storage of information such as computer readable instructions, data structures, computer program modules or other data. The computer readable storage medium includes, but is not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile discs (DVD, Digital Video Disc) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer.

[0204] It can be understood that the above embodiments are only exemplary embodiments adopted for illustrating the principles of the present disclosure, and the present disclosure is not limited thereto. Various modifications and improvements can be made by those of ordinary skill in the art without departing from the spirit and essence of the present disclosure, and these modifications and improvements are also considered to be within the protection scope of the present disclosure.

Claims

1. A mobile network video user quality difference processing method, characterized in that, The method comprises: obtaining original user detail data of a cellular mobile network accelerated video user; data preprocessing of the original user detail data; obtaining experience index data of each video user through the preprocessed original user detail data, performing threshold analysis on the video user experience index, and establishing a video user experience index score table; and analyzing video user service duration data through the preprocessed original user detail data, and establishing a video user service duration score table; calculating an acceleration guarantee recommendation value according to the video user experience index score table and the video user service duration score table, and obtaining a video user acceleration guarantee recommendation value table; selecting a video user according to the acceleration guarantee recommendation value table for network acceleration.

2. The method of claim 1, wherein, The original user detail data comprises: user-related fields, protocol size classes, application IDs APPIDs, effective download rates, XKB startup delays, traffic, and time.

3. The method of claim 2, wherein, The data preprocessing of the original user detail data comprises: extracting video user details: matching video user list data in the cellular mobile network according to user-related fields, protocol size classes, and APPIDs; data cleaning: detecting video user list data and removing abnormal values in the data, and supplementing default values in the data by using mean filling; granularity selection and video user service duration data acquisition: selecting a preset time length as a time granularity, and obtaining video user service duration data by counting the viewing service duration of each video user based on the data cleaned video user list data, and using the video user service duration data as a behavior index for evaluating video user experience.

4. The method of claim 1, wherein the experience index comprises effective download rates and XKB startup delays; obtaining experience index data of each video user through the preprocessed original user detail data, performing threshold analysis on the video user experience index, and establishing a video user experience index score table, comprises: analyzing the distribution of video user effective download rates and XKB startup delays through the preprocessed original user detail data, determining the thresholds of effective download rates and XKB startup delays, and dividing the effective download rates and XKB startup delays into multiple score intervals, respectively; determining low-rate recommendation value intervals and high-latency recommendation value intervals, and determining the score values corresponding to each interval of the effective download rates and each interval of the XKB startup delays, respectively; based on the score intervals and score value ranges of the effective download rates and XKB startup delays, formulating a video user experience index score table.

5. The method of claim 4, wherein, analyzing video user service duration data through the preprocessed original user detail data, and establishing a video user service duration score table, comprises: dividing the service duration of a video user into multiple score intervals according to actual business experience through the preprocessed original user detail data, to reflect the activity and continuity of the video user watching videos, and setting corresponding score values for each score interval; based on the score intervals and score values of the service duration, formulating a video user service duration score table.

6. The method of claim 5, wherein, The accelerating guarantee recommendation value is calculated according to the video user experience index score table and the video user service time length score table, and a video user accelerating guarantee recommendation value table is obtained, comprising: S1: preset weights of the effective download rate and the XKB starting time delay are a and b respectively, weights of the video user experience index and the video user service time length are c and d respectively, and a+b=1 and c+d=1; S2: according to the obtained video user experience index score table, the experience value KQI is calculated, and the specific formula is as follows: KQI=LR×a+HL×b; Wherein, LR represents the score value corresponding to the interval of the video user effective download rate, and HL represents the score value corresponding to the interval of the video user XKB starting time delay; S3: according to the obtained video user service time length score table, the service time length score value is obtained, the accelerating guarantee recommendation value RV is calculated in combination with the experience value KQI, and the specific formula is as follows: RV=KQI×c+T×d; Wherein, T is the score value corresponding to the interval of the video user service time length; S4: the video user accelerating guarantee recommendation value table is obtained according to the accelerating guarantee recommendation value RV.

7. The method of claim 1, wherein, The video user is selected for network acceleration according to the accelerating guarantee recommendation value table, comprising: According to the video user slice statistics verification according to the accelerating guarantee recommendation value table, the accelerating guarantee recommendation value threshold is obtained, the accelerating guarantee recommendation times of the video user are counted according to the accelerating guarantee recommendation value threshold, and the video user is selected for acceleration according to the accelerating guarantee recommendation times of the video user.

8. The method of claim 7, wherein, The accelerating guarantee recommendation times of the video user are counted according to the accelerating guarantee recommendation value threshold, and the video user is selected for acceleration according to the accelerating guarantee recommendation times of the video user, comprising: With a preset time length as a granularity, the number of times that the accelerating guarantee recommendation value of the video user is greater than or equal to the accelerating guarantee recommendation value threshold within a certain time is counted, and the accelerating guarantee recommendation times are obtained; The accelerating guarantee recommendation times of the video user within a certain time are sorted from high to low, and the users whose accelerating guarantee recommendation times are in a certain proportion of the total number of video users are selected for acceleration, so as to ensure that the users with poor experience are preferentially provided with rate guarantee.

9. A mobile network video user quality difference processing system, characterized by, The system comprises: An acquisition module is arranged to acquire original user detailed data of a cellular mobile network accelerating video user; A preprocessing module is arranged to perform data preprocessing on the original user detailed data; An experience index scoring module is arranged to acquire experience index data of each video user through the preprocessed original user detailed data, to perform threshold analysis on the video user experience index, and to establish a video user experience index score table; and A service time length scoring module is arranged to analyze video user service time length data through the preprocessed original user detailed data, and to establish a video user service time length score table; A recommendation value determination module is arranged to calculate an accelerating guarantee recommendation value according to the video user experience index score table and the video user service time length score table, and to obtain a video user accelerating guarantee recommendation value table; An acceleration module is arranged to select a video user for network acceleration according to the accelerating guarantee recommendation value table.

10. An electronic device, comprising: The mobile network video user quality difference processing method according to any one of claims 1-8 is executed by a processor when the processor runs a computer program stored in a memory.

11. A computer readable storage medium, characterized in that, The computer program stored on the computer readable storage medium is executed by a processor to implement the mobile network video user quality difference processing method according to any one of claims 1-8.

Images