Live broadcast flow monitoring method and device, equipment and medium

Abstract

The embodiment of the invention provides a live broadcast flow monitoring method and device, equipment and a medium. The method comprises the following steps: acquiring target identification information according to real-time live broadcast flow data; wherein the target identification information comprises item information and time information; obtaining session trend data of the same time period according to the target identification information; aggregating each session trend data to obtain session number group data; calculating the session number group data to obtain a session trend data mean value; performing numerical value configuration on the data traffic state model according to the session trend data mean value; and monitoring the real-time live broadcast flow data of the monitoring node according to the data flow state model to obtain a monitoring result of whether the flow is abnormal or not. According to the embodiment of the invention, the real-time live broadcast flow data can be monitored according to the data flow state model, the abnormal live broadcast flow can be accurately monitored, and the efficiency of monitoring the live broadcast flow is improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a live broadcast traffic monitoring method, device, equipment and medium. Background Art

[0002] With the development of network technology, live streaming has become an important information exchange platform. In live streaming, live streaming traffic data will directly or indirectly affect sales. Therefore, traffic delivery tools (such as Juliang Qianchuan) can be used to deliver traffic to quickly gain attention and increase the popularity of the live streaming room. Generally speaking, there is a positive correlation between the flow of people in the live streaming room and the traffic delivery, that is, the higher the amount of delivery, the higher the traffic. However, if the advertisement is not accurately delivered to the target group or banned words are triggered during the live streaming, live streaming traffic anomalies may occur; for example, the live streaming room sells women's clothing, but the target group selected by the delivery strategy is men.

[0003] Currently, live broadcast operators usually judge whether the live broadcast traffic is normal based on past experience. However, manual experience judgment may have omissions, resulting in failure to monitor abnormal traffic in a timely manner, thereby causing economic losses.

[0004] Therefore, the existing live broadcast traffic monitoring method has the problem of low efficiency in monitoring abnormal live broadcast traffic. Summary of the invention

[0005] The embodiments of the present invention provide a live broadcast traffic monitoring method, device, equipment and medium, aiming to solve the problem of low monitoring efficiency in existing live broadcast traffic monitoring methods.

[0006] In a first aspect, an embodiment of the present invention provides a live broadcast traffic monitoring method, the method comprising:

[0007] Acquire target identification information according to the real-time live broadcast traffic data; wherein the target identification information includes project information and time information;

[0008] Acquire the session trend data in the same time period according to the target identification information;

[0009] Aggregating the trend data of each session to obtain session array data;

[0010] Calculating the data of the game array to obtain the average value of the game trend data;

[0011] The data flow state model is numerically configured according to the mean value of the session trend data;

[0012] The real-time live traffic data of the monitoring node is monitored according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal.

[0013] In a second aspect, an embodiment of the present invention further provides a live broadcast traffic monitoring device, the device comprising:

[0014] A first acquisition unit is used to acquire target identification information according to the real-time live broadcast traffic data; wherein the target identification information includes project information and time information;

[0015] A second acquisition unit, used for acquiring the session trend data in the same time period according to the target identification information;

[0016] An aggregation unit, used for aggregating the trend data of each session to obtain session array data;

[0017] A calculation unit, used for calculating the game array data to obtain the game trend data mean;

[0018] A configuration unit, used for numerically configuring a data flow state model according to a mean value of the session trend data;

[0019] The monitoring unit is used to monitor the real-time live traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal.

[0020] In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0021] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, wherein the computer program includes program instructions, and wherein the program instructions, when executed by a processor, can implement the method described in the first aspect above.

[0022] The embodiments of the present invention provide a method, device, equipment and medium for monitoring live broadcast traffic, the method comprising: obtaining target identification information according to real-time live broadcast traffic data; wherein the target identification information comprises project information and time information; obtaining the session trend data of the same time period according to the target identification information; aggregating the session trend data to obtain session array data; calculating the session array data to obtain the session trend data mean; numerically configuring the data traffic state model according to the session trend data mean; monitoring the real-time live broadcast traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal. The embodiments of the present invention can monitor the real-time live broadcast traffic data according to the data traffic state model, realize accurate monitoring of abnormal live broadcast traffic, and improve the efficiency of monitoring live broadcast traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0024] Figure 1 A flow chart of a live broadcast traffic monitoring method provided by an embodiment of the present invention;

[0025] Figure 2 A schematic block diagram of a live streaming traffic monitoring device provided by an embodiment of the present invention;

[0026] Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0029] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0030] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] See also Figure 1 , Figure 1 A flow chart of a live broadcast traffic monitoring method provided by an embodiment of the present invention. The live broadcast traffic monitoring method is applied to a controller of an intelligent terminal, which may be an electronic device such as a tablet computer, a laptop computer, or a desktop computer.

[0032] Figure 1 The following is a flow chart of a live streaming traffic monitoring method provided by an embodiment of the present invention. Figure 1 As shown, the method includes the following steps S110-S160.

[0033] S110. Obtain target identification information according to real-time live broadcast traffic data; wherein the target identification information includes project information and time information.

[0034] In this embodiment, target identification information is obtained based on real-time live traffic data, so as to obtain historical live traffic data matching the real-time live traffic data from a preset database based on the target identification information, and the historical live traffic data is used as a basis for judging whether the real-time live traffic data of the current live broadcast room is abnormal.

[0035] At present, live broadcast operators usually judge whether the live broadcast traffic is normal based on past experience. However, manual experience judgment may have omissions, resulting in failure to monitor abnormal traffic in time, thereby causing economic losses. The embodiment of the present invention can obtain target identification information based on real-time live broadcast traffic data, obtain historical live broadcast traffic data matching the real-time live broadcast traffic data from a preset database based on the target identification information, monitor the real-time live broadcast traffic data based on the historical live broadcast traffic data, achieve accurate monitoring of abnormal live broadcast traffic, and improve the efficiency of monitoring live broadcast traffic.

[0036] Specifically, the real-time live broadcast traffic data includes session information, real-time delivery data, real-time session trend data and project information; wherein, the session information includes store ID, live broadcast account ID, session ID, session start time, session end time, anchor layout, shift operation, etc.; the real-time delivery data includes session ID, delivery amount, delivery method, delivery target, delivery cycle, delivery population, etc.; the real-time session trend data includes session ID, number of people entering, number of people leaving, number of people joining the group, number of people commenting, average viewing time per person, delivery amount, etc. In the real-time session trend data, trend data such as number of people entering, number of people leaving, number of people joining the group, number of people commenting, average viewing time per person, delivery amount, etc. are recorded by minute; the project information includes project ID, store ID, live broadcast account ID, etc.; the target identification information can be customized by the staff; the target identification information may include project information and time information, and the time information is obtained from the delivery data and the session information.

[0037] Furthermore, before obtaining the target identification information based on the real-time live broadcast traffic data, it is also necessary to determine whether the authorization information of the target store is received; if the authorization information of the target store is received, execute the next step (i.e., obtain the target identification information based on the real-time live broadcast traffic data); if the authorization information of the target store is not received, it is impossible to interact with the data of the store / live broadcast room to obtain the target identification information.

[0038] In one embodiment, step S110 includes: obtaining project information, delivery data and session information according to the real-time live broadcast traffic data; determining the time period to which the marking time belongs according to the marking time of the delivery data; judging whether the current day is a working day according to the session start time in the session information, and obtaining a first judgment result; judging whether the next day is a working day according to the session start time, and obtaining a second judgment result; using the time period, the first judgment result and the second judgment result as the time information.

[0039] In this embodiment, project information, delivery data and session information are obtained according to the real-time live broadcast traffic data; the project information includes project ID, store ID, live broadcast account ID, etc.; the time period to which the marking time belongs is determined according to the marking time of the delivery data, and the marking time is the traffic delivery time, and the time period includes early morning, morning, noon, afternoon, evening and midnight; according to the session start time in the session information, it is judged whether the current day is a working day to obtain a first judgment result; according to the session start time, it is judged whether the next day is a working day to obtain a second judgment result; the time period, the first judgment result and the second judgment result are used as the time information.

[0040] If the project ID in the project information is XM01, the store ID is DP01, and the live broadcast account ID is ZH01, the time period in the time information is early morning, the first judgment result is yes, and the second judgment result is no, then historical live broadcast traffic data with project ID XM01, store ID DP01, live broadcast account ID ZH01, time period being early morning, today being a working day, and the next day not being a working day is obtained from the preset database; wherein the labels of the live broadcast traffic data of any historical session obtained are all normal, so as to realize accurate monitoring of abnormal live broadcast traffic based on the historical live broadcast traffic data; the labels of the live broadcast traffic data are obtained by the operators.

[0041] Specifically, the database is used to store live broadcast traffic data, which includes session information and delivery data of each session, session trend data and project information.

[0042] S120: Acquire session trend data in the same time period according to the target identification information.

[0043] In this embodiment, the session trend data (and historical live broadcast traffic data) of the same time period is obtained according to the target identification information; if the project ID in the project information is XM01, the store ID is DP01, and the live broadcast account ID is ZH01, the time period in the time information is early morning, the first judgment result is yes, and the second judgment result is no, then the session trend data with project ID XM01, store ID DP01, live broadcast account ID ZH01, time period is early morning, today is a working day, and next day is not a working day is obtained from the preset database, and the session trend data includes session ID, live broadcast duration (lt), average number of people entering per minute (wu), average number of people leaving per minute (lu), average number of people joining the group per minute (au), average number of comments per minute (cu), average average viewing time per person per minute (awt), average amount of investment per minute (ad), etc.

[0044] S130, aggregating the session trend data to obtain session array data.

[0045] In this embodiment, the trend data of each session are aggregated to obtain the session array data Array ([

[0046] (lt1, wu1, lu1, au1, cu1, awt1, ad1),

[0047] (lt2, wu2, lu2, au2, cu2, awt2, ad1), ...

[0049] ]); wherein each row of data in the session array data represents the live broadcast traffic data of a historical session; lt is the live broadcast duration, wu is the average number of people entering per minute, lu is the average number of people leaving per minute, au is the average number of people joining the group per minute, cu is the average number of people commenting per minute, awt is the average average viewing time per person per minute, and ad is the average amount of money invested per minute.

[0050] S140, calculating the session array data to obtain the session trend data mean.

[0051] In this embodiment, the scene array data Array([

[0052] (lt1, wu1, lu1, au1, cu1, awt1, ad1),

[0053] (lt2, wu2, lu2, au2, cu2, awt2, ad2), ...

[0055] lt n , n ,lun , au n ,cu n , awt n ,ad n ]) is calculated to obtain the average of the session trend data, which includes avg(lt), avg(wu), avg(lu), avg(au), avg(cu), avg(awt), and avg(ad); avg(lt) is the historical average live broadcast time, avg(wu) is the historical average number of people entering per minute, avg(lu) is the historical average number of people leaving per minute, avg(au) is the historical average number of people joining the group per minute, avg(cu) is the historical average number of comments per minute, avg(awt) is the historical average average viewing time per person per minute, and avg(ad) is the historical average amount of money invested per minute.

[0056] Specifically, avg(lt) = (lt1+lt2+...+lt n ) / n, the calculation method of avg(wu), avg(lu), avg(au), avg(cu), avg(awt), and avg(ad) is the same as that of avg(lt).

[0057] In one embodiment, the session trend data includes multiple parameter items, and step S140 includes: calculating the session array data to obtain the mean of the parameter items corresponding to each of the parameter items; and using the mean of each of the parameter items as the mean of the session trend data.

[0058] In this embodiment, the session trend data includes multiple parameter items such as session ID, live broadcast time (lt), average number of people entering per minute (wu), average number of people leaving per minute (lu), average number of people joining the group per minute (au), average number of people commenting per minute (cu), average average viewing time per person per minute (awt), average amount of money invested per minute (ad), etc.; the session array data Array([

[0059] (lt1, wu1, lu1, au1, cu1, awt1, ad1),

[0060] (lt2, wu2, lu2, au2, cu2, awt2, ad2), ...

[0062] lt n , n ,lu n , au n ,cu n , awt n ,ad n]) is calculated to obtain the mean values ​​of the corresponding parameter items avg(lt), avg(wu), avg(lu), avg(au), avg(cu), avg(awt), and avg(ad); wherein avg(lt) is the historical average live broadcast duration, avg(wu) is the historical average number of people entering per minute, avg(lu) is the historical average number of people leaving per minute, avg(au) is the historical average number of people joining the group per minute, avg(cu) is the historical average number of comments per minute, avg(awt) is the historical average average viewing time per person per minute, and avg(ad) is the historical average amount of money invested per minute.

[0063] Specifically, avg(lt) = (lt1+lt2+...+lt n ) / n, the calculation method of avg(wu), avg(lu), avg(au), avg(cu), avg(awt), and avg(ad) is the same as that of avg(lt).

[0064] S150. Numerical configuration of the data flow state model is performed according to the mean value of the session trend data.

[0065] In this embodiment, the Gaussian Naive Bayes formula in the data traffic state model is numerically configured according to the mean values ​​of the game trend data (avg(lt), avg(wu), avg(lu), avg(au), avg(cu), avg(awt), avg(ad)) to monitor the real-time live traffic data according to the data traffic state model, accurately monitor the abnormal live traffic, and improve the efficiency of monitoring the live traffic.

[0066] The Gaussian Naive Bayes formula in the data traffic state model is:

[0067]

[0068] Among them, μ γ is the mean of the parameter items (avg(lt), avg(wu), avg(lu), avg(au), avg(cu), avg(awt), avg(ad)).

[0069] S160: Monitor the real-time live traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal.

[0070] In this embodiment, the data flow status model is numerically configured according to the mean value of the session trend data, so as to monitor the real-time live broadcast flow data of the monitoring node according to the data flow status model, and obtain a monitoring result of whether the flow is abnormal, thereby realizing accurate monitoring of abnormal live broadcast flow and improving the efficiency of monitoring live broadcast flow; the real-time live broadcast flow data includes session information, real-time delivery data, real-time session trend data and project information. The present invention monitors the real-time session trend data of the real-time live broadcast flow data of the monitoring node according to the data flow status model, and obtains a monitoring result of whether the flow is abnormal.

[0071] In one embodiment, each monitoring node includes at least one trend point, and step S160 includes: obtaining trend point live traffic data of the trend point in the monitoring node; calculating the live traffic data of each trend point according to the data traffic state model to obtain the trend point probability value corresponding to each trend point; calculating each trend point probability value to obtain the trend point mean; judging whether the trend point mean is less than a preset threshold; if so, obtaining a monitoring result of traffic abnormality.

[0072] In this embodiment, every 5 minutes is used as a monitoring node (the specific setting can be made according to the needs), and each monitoring node includes 5 trend points (that is, every 1 minute is used as a trend point); the trend point live traffic data of the trend point in the monitoring node is obtained; the live traffic data of each trend point is calculated according to the data traffic state model to obtain the trend point probability value corresponding to each trend point; the probability value of each trend point is calculated to obtain the trend point mean (the trend point mean is the probability value of the detection node); it is determined whether the trend point mean is less than a preset threshold value, which can be set to 0.5; if it is less than, a monitoring result of abnormal traffic is obtained; if it is greater than, a monitoring result of normal traffic is obtained.

[0073] In the embodiment of the present invention, the real-time live traffic data is monitored every 5 minutes through the data traffic state model, so as to accurately monitor abnormal live traffic and improve the efficiency of monitoring live traffic.

[0074] In one embodiment, the trend point live traffic data includes multiple trend parameter items. After obtaining the trend point live traffic data of the trend point in the monitoring node, it also includes: calculating the trend parameter item variance corresponding to each trend parameter item according to a preset variance calculation formula, the live traffic data of each trend point and the mean of the trend data of the session.

[0075] In this embodiment, the trend point live broadcast traffic data includes multiple trend parameter items such as live broadcast duration (lt), average number of people entering per minute (wu), average number of people leaving per minute (lu), average number of people joining the group per minute (au), average number of people commenting per minute (cu), average average viewing time per minute (awt), and average amount of investment per minute (ad).

[0076] The variance calculation formula is: Among them, S is the trend parameter item variance corresponding to each of the trend parameter items, x is the trend point live traffic data of the trend point in the monitoring node, μ is the parameter item mean corresponding to each of the parameter items, and n is the duration of two adjacent monitoring nodes.

[0077] The trend point live traffic data includes multiple trend parameter items. Taking the trend parameter item wu as an example, if every 5 minutes is used as a monitoring node (n=5), each monitoring node includes 5 trend points, then

[0078] x is wu s1 , s2 , s3 , s4 , s5 ;

[0079] μ is avg(wu);

[0080] S(wu)=((wu s1 -avg(wu)) 2 +(wu s2 -avg(wu)) 2 +(wu s3 -avg(wu)) 2 +(wu s4 -avg(wu)) 2 +(wu s5 -avg(wu)) 2 ) / 5; where avg(wu) is the historical average number of people entering per minute, and S(wu) is the variance corresponding to the trend parameter item (wu).

[0081] In one embodiment, the live traffic data of each trend point is calculated according to the data traffic state model to obtain the trend point probability value corresponding to each trend point, including: calculating the live traffic data of each trend point according to the variance of each trend parameter item and the Gaussian naive Bayes formula in the data traffic state model to obtain the trend point probability value corresponding to each trend point; wherein the trend point probability values ​​include multiple trend parameter item probabilities.

[0082] In this embodiment, the live broadcast traffic data of each trend point is calculated according to the variance of each trend parameter item and the Gaussian naive Bayes formula in the data traffic state model to obtain the trend point probability value corresponding to each trend point; wherein, the live broadcast traffic data of the trend point includes multiple trend parameter items such as live broadcast duration (lt), average number of people entering per minute (wu), average number of people leaving per minute (lu), average number of people joining the group per minute (au), average number of people commenting per minute (cu), average average viewing time per minute (awt), average amount of investment per minute (ad), etc., and the trend point probability value includes multiple trend parameter item probabilities.

[0083] The Gaussian Naive Bayes formula is:

[0084]

[0085] Among them, x i is the trend parameter item, is the variance of the trend parameter term, μ γ is the mean of the parameter items (avg(lt), avg(wu), avg(lu), avg(au), avg(cu), avg(awt), avg(ad)), P(x i |Y) is the trend parameter x i The corresponding trend point probability value.

[0086] Taking the trend parameter item wu as an example (the calculation method of other trend parameters is the same as that of trend parameter item wu), if every 5 minutes is used as a monitoring node, a monitoring node includes 5 trend points, and x in a monitoring node wu The value of s1 , s2 , s3 , s4 , s5 ; According to the trend parameter variance The trend parameter item wu in the monitoring node is calculated using the Gaussian Naive Bayes formula to obtain each trend parameter item (wu s1 , s2 , s3 , s4 , s5 ) corresponding to the trend point probability value (i.e. P(wu s1 ), P(wu s2 ), P(wu s3 ), P(wu s4 ), P(wu s5 ));

[0087] P(wu s1 ) as an example, in, The trend parameter term variance corresponding to the trend parameter term wu, avg(wu) is the historical average number of people entering per minute, P(wu s1 |Y) is the trend parameter wu s1 The corresponding trend point probability value, that is, under the condition that Y(avg(wu)) occurs, event wu s1 Probability of occurrence.

[0088] Further, still taking the trend parameter item wu as an example, the trend point probability value (P(wu s1 ), P(wu s2 ), P(wu s3 ), P(wu s4 ), P(wu s5 )) to calculate and obtain the trend point mean J corresponding to the trend parameter item wu wu (i.e., the probability value of the trend parameter item wu at the monitoring node); where J wu =(P(wu s1 )+P(wu s2 )+P(wu s3 )+P(wu s4 )+P(wu s5 )) / 5; Determine the trend point mean J corresponding to the trend parameter item wu wu Is it less than a preset threshold? If so, a flow abnormality monitoring result is obtained; wherein the preset threshold can be set to 0.5.

[0089] Furthermore, if the mean value of the trend points corresponding to any trend parameter item in the monitoring node is less than a preset threshold, a monitoring result of abnormal flow is obtained.

[0090] In one embodiment, after step S160, the method further includes: if the monitoring result is yes, generating a pop-up reminder corresponding to the monitoring result through a plug-in.

[0091] In this embodiment, the staff can monitor the real-time trend data of the sessions through the background software. If the live broadcast traffic is abnormal, a pop-up window reminder corresponding to the monitoring result is generated through the plug-in; for example, in a monitoring node, J wu If the number of people entering in real time is less than the preset threshold (i.e. the number of people entering in history is less than the number of people entering in the same time period), a pop-up window will prompt "Abnormal number of people entering" and the staff can judge whether to stop the broadcast based on the prompt.

[0092] At present, live broadcast operators usually judge whether the live broadcast traffic is normal based on past experience. The embodiments of the present invention can monitor the real-time live broadcast traffic data according to the data traffic status model, reduce the dependence of the operation position on the operation experience, and improve the efficiency of monitoring the live broadcast traffic.

[0093] In summary, the embodiments of the present invention can monitor real-time live traffic data according to the data traffic state model, achieve accurate monitoring of abnormal live traffic, and improve the efficiency of monitoring live traffic.

[0094] Figure 2 A schematic block diagram of a live streaming traffic monitoring device provided by an embodiment of the present invention. Figure 2 As shown, corresponding to the above live traffic monitoring method, the present invention also provides a live traffic monitoring device. The live traffic monitoring device includes a unit for executing the above live traffic monitoring method. The device is configured in the controller of the smart terminal, and the smart terminal can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, etc. Figure 2 , the live broadcast traffic monitoring device 700 includes:

[0095] The first acquisition unit 701 is used to acquire target identification information according to the real-time live broadcast traffic data; wherein the target identification information includes project information and time information;

[0096] The second acquisition unit 702 is used to acquire the session trend data in the same time period according to the target identification information;

[0097] Aggregation unit 703, used for aggregating the session trend data to obtain session array data;

[0098] A calculation unit 704 is used to calculate the game array data to obtain the game trend data mean;

[0099] A configuration unit 705, configured to perform numerical configuration on the data flow state model according to the average value of the session trend data;

[0100] The monitoring unit 706 is used to monitor the real-time live traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal.

[0101] In some embodiments, when the first acquisition unit 701 executes the step of acquiring target identification information according to real-time live broadcast traffic data, wherein the target identification information includes project information and time information, it is specifically used to:

[0102] According to the real-time live broadcast traffic data, project information, delivery data and session information are obtained; according to the marking time of the delivery data, the time period to which the marking time belongs is determined; according to the session start time in the session information, whether the current day is a working day is determined to obtain a first judgment result; according to the session start time is determined whether the next day is a working day is determined to obtain a second judgment result; the time period, the first judgment result and the second judgment result are used as the time information.

[0103] In some embodiments, the session trend data includes multiple parameter items, and the calculation unit 704, when executing the step of calculating the session array data to obtain the session trend data mean, is specifically used for:

[0104] The field array data is calculated to obtain the mean value of the parameter item corresponding to each of the parameter items; and the mean value of each of the parameter items is used as the mean value of the field trend data.

[0105] In some embodiments, each of the monitoring nodes includes at least one trend point. When the monitoring unit 706 performs the step of monitoring the real-time live traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal, it is specifically used to:

[0106] Obtain the trend point live traffic data of the trend point in the monitoring node; calculate the live traffic data of each trend point according to the data traffic state model to obtain the trend point probability value corresponding to each trend point; calculate each trend point probability value to obtain the trend point mean; determine whether the trend point mean is less than a preset threshold; if less than, obtain a monitoring result of traffic abnormality.

[0107] In some embodiments, the trend point live traffic data includes a plurality of trend parameter items, and the monitoring unit 706, after executing the step of acquiring the trend point live traffic data of the trend point in the monitoring node, is further used to:

[0108] The trend parameter item variance corresponding to each trend parameter item is calculated based on a preset variance calculation formula, the live broadcast traffic data of each trend point and the mean value of the session trend data.

[0109] In some embodiments, when the monitoring unit 706 calculates the live broadcast traffic data of each trend point according to the data traffic state model to obtain the trend point probability value corresponding to each trend point, it is specifically used to:

[0110] The live traffic data of each trend point is calculated according to the variance of each trend parameter item and the Gaussian Naive Bayes formula in the data traffic state model to obtain the trend point probability value corresponding to each trend point; wherein the trend point probability value includes multiple trend parameter item probabilities.

[0111] In some embodiments, after the monitoring unit 706 performs the step of monitoring the real-time live data of each monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal, it is further used to:

[0112] If the monitoring result is yes, a pop-up reminder corresponding to the monitoring result is generated through the plug-in.

[0113] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned live traffic monitoring device and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0114] The live streaming traffic monitoring device can be implemented in the form of a computer program. Figure 3 Runs on the computer device shown.

[0115] See also Figure 3 , Figure 3 800 is a schematic block diagram of an electronic device provided by an embodiment of the present invention. The electronic device 800 may be a controller of a smart terminal, and the smart terminal may be an electronic device such as a tablet computer, a laptop computer, or a desktop computer.

[0116] See also Figure 3 The electronic device 800 includes a processor 802 , a memory and a network interface 805 connected via a system bus 801 , wherein the memory may include a non-volatile storage medium 803 and an internal memory 804 .

[0117] The non-volatile storage medium 803 can store an operating system 8031 ​​and a computer program 8032. The computer program 8032 includes program instructions, and when the program instructions are executed, the processor 802 can execute a live broadcast traffic monitoring method.

[0118] The processor 802 is used to provide computing and control capabilities to support the operation of the entire electronic device 800 .

[0119] The internal memory 804 provides an environment for the operation of the computer program 8032 in the non-volatile storage medium 803. When the computer program 8032 is executed by the processor 802, the processor 802 can execute a live broadcast traffic monitoring method.

[0120] The network interface 805 is used to communicate with other devices over the network. Figure 3 The structure shown in the figure is merely a block diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the electronic device 800 to which the solution of the present invention is applied. The specific electronic device 800 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0121] The processor 802 is used to run the computer program 8032 stored in the memory to implement the following steps:

[0122] Obtain target identification information according to real-time live traffic data; wherein the target identification information includes project information and time information; obtain session trend data of the same time period according to the target identification information; aggregate the session trend data to obtain session array data; calculate the session array data to obtain a mean value of the session trend data; numerically configure a data traffic state model according to the mean value of the session trend data; monitor the real-time live traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal.

[0123] In some embodiments, when the processor 802 implements the step of acquiring target identification information according to real-time live traffic data, wherein the target identification information includes project information and time information, the processor 802 specifically implements the following steps:

[0124] According to the real-time live broadcast traffic data, project information, delivery data and session information are obtained; according to the marking time of the delivery data, the time period to which the marking time belongs is determined; according to the session start time in the session information, whether the current day is a working day is determined to obtain a first judgment result; according to the session start time is determined whether the next day is a working day is determined to obtain a second judgment result; the time period, the first judgment result and the second judgment result are used as the time information.

[0125] In some embodiments, the session trend data includes multiple parameter items. When the processor 802 calculates the session array data to obtain the session trend data mean value, the processor 802 specifically implements the following steps:

[0126] The field array data is calculated to obtain the mean value of the parameter item corresponding to each of the parameter items; and the mean value of each of the parameter items is used as the mean value of the field trend data.

[0127] In some embodiments, each of the monitoring nodes includes at least one trend point. When the processor 802 implements the step of monitoring the real-time live traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal, the processor 802 specifically implements the following steps:

[0128] Obtain the trend point live traffic data of the trend point in the monitoring node; calculate the live traffic data of each trend point according to the data traffic state model to obtain the trend point probability value corresponding to each trend point; calculate each trend point probability value to obtain the trend point mean; determine whether the trend point mean is less than a preset threshold; if less than, obtain a monitoring result of traffic abnormality.

[0129] In some embodiments, the trend point live traffic data includes multiple trend parameter items. After implementing the step of acquiring the trend point live traffic data of the trend point in the monitoring node, the processor 802 further implements the following steps:

[0130] The trend parameter item variance corresponding to each trend parameter item is calculated based on a preset variance calculation formula, the live broadcast traffic data of each trend point and the mean value of the session trend data.

[0131] In some embodiments, when the processor 802 calculates the live traffic data of each trend point according to the data traffic state model to obtain the trend point probability value corresponding to each trend point, the processor 802 specifically implements the following steps:

[0132] The live traffic data of each trend point is calculated according to the variance of each trend parameter item and the Gaussian Naive Bayes formula in the data traffic state model to obtain the trend point probability value corresponding to each trend point; wherein the trend point probability value includes multiple trend parameter item probabilities.

[0133] In some embodiments, after the processor 802 implements the step of monitoring the real-time live broadcast data of each monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal, it further implements the following steps:

[0134] If the monitoring result is yes, a pop-up reminder corresponding to the monitoring result is generated through the plug-in.

[0135] It should be understood that in the embodiment of the present invention, the processor 802 may be a central processing unit (CPU), and the processor 802 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0136] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0137] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the following steps:

[0138] Obtain target identification information according to real-time live traffic data; wherein the target identification information includes project information and time information; obtain session trend data of the same time period according to the target identification information; aggregate the session trend data to obtain session array data; calculate the session array data to obtain a mean value of the session trend data; numerically configure a data traffic state model according to the mean value of the session trend data; monitor the real-time live traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal.

[0139] In one embodiment, the processor executes the program instructions to obtain target identification information according to real-time live traffic data; wherein the target identification information includes project information and time information, and specifically implements the following steps:

[0140] According to the real-time live broadcast traffic data, project information, delivery data and session information are obtained; according to the marking time of the delivery data, the time period to which the marking time belongs is determined; according to the session start time in the session information, whether the current day is a working day is determined to obtain a first judgment result; according to the session start time is determined whether the next day is a working day is determined to obtain a second judgment result; the time period, the first judgment result and the second judgment result are used as the time information.

[0141] In one embodiment, the session trend data includes a plurality of parameter items, and when the processor executes the program instructions to calculate the session array data and obtain the session trend data mean value step, the processor specifically implements the following steps:

[0142] The field array data is calculated to obtain the mean value of the parameter item corresponding to each of the parameter items; and the mean value of each of the parameter items is used as the mean value of the field trend data.

[0143] In one embodiment, each of the monitoring nodes includes at least one trend point. When the processor executes the program instructions to monitor the real-time live traffic data of the monitoring node according to the data traffic state model and obtains a monitoring result of whether the traffic is abnormal, the following steps are specifically implemented:

[0144] Obtain the trend point live traffic data of the trend point in the monitoring node; calculate the live traffic data of each trend point according to the data traffic state model to obtain the trend point probability value corresponding to each trend point; calculate each trend point probability value to obtain the trend point mean; determine whether the trend point mean is less than a preset threshold; if less than, obtain a monitoring result of traffic abnormality.

[0145] In one embodiment, the trend point live traffic data includes a plurality of trend parameter items. After the processor executes the program instructions to implement the step of acquiring the trend point live traffic data of the trend point in the monitoring node, the processor further implements the following steps:

[0146] The trend parameter item variance corresponding to each trend parameter item is calculated based on a preset variance calculation formula, the live broadcast traffic data of each trend point and the mean value of the session trend data.

[0147] In one embodiment, when the processor executes the program instructions to calculate the live traffic data of each trend point according to the data traffic state model to obtain the trend point probability value corresponding to each trend point, the following steps are specifically implemented:

[0148] The live traffic data of each trend point is calculated according to the variance of each trend parameter item and the Gaussian Naive Bayes formula in the data traffic state model to obtain the trend point probability value corresponding to each trend point; wherein the trend point probability value includes multiple trend parameter item probabilities.

[0149] In one embodiment, after the processor executes the program instructions to monitor the real-time live data of each monitoring node according to the data traffic state model and obtains a monitoring result of whether the traffic is abnormal, it further implements the following steps:

[0150] If the monitoring result is yes, a pop-up reminder corresponding to the monitoring result is generated through the plug-in.

[0151] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0152] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0153] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and 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.

[0154] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0155] 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 storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0156] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A live broadcast traffic monitoring method, characterized in that: The method comprises: Acquire target identification information according to the real-time live broadcast traffic data; wherein the target identification information includes project information and time information; Acquire the session trend data in the same time period according to the target identification information; Aggregating the trend data of each session to obtain session array data; Calculating the data of the game array to obtain the average value of the game trend data; The data flow state model is numerically configured according to the mean value of the session trend data; The real-time live traffic data of the monitoring node is monitored according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal.

2. The live broadcast traffic monitoring method according to claim 1, characterized in that: The target identification information is obtained according to the real-time live broadcast traffic data; wherein the target identification information includes project information and time information, including: Acquire project information, delivery data and session information according to the real-time live broadcast traffic data; Determine the time period to which the marking time belongs according to the marking time of the delivery data; Determine whether the current day is a working day according to the session start time in the session information, and obtain a first determination result; Determine whether the next day is a working day according to the start time of the session, and obtain a second determination result; The time period, the first judgment result, and the second judgment result are used as the time information.

3. The live broadcast traffic monitoring method according to claim 1 is characterized in that: The session trend data includes multiple parameter items, and the session array data is calculated to obtain the session trend data mean, including: Calculating the field array data to obtain the mean value of the parameter item corresponding to each of the parameter items; The mean of each parameter item is used as the mean of the session trend data.

4. The live streaming traffic monitoring method according to claim 3 is characterized in that: The monitoring nodes each include at least one trend point, and the real-time live traffic data of the monitoring node is monitored according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal, including: Obtaining trend point live traffic data of the trend point in the monitoring node; Calculate the live broadcast traffic data of each trend point according to the data traffic state model to obtain a trend point probability value corresponding to each trend point; Calculating the probability value of each trend point to obtain a trend point mean; Determine whether the trend point mean is less than a preset threshold; If it is less than, the monitoring result of abnormal flow is obtained.

5. The live broadcast traffic monitoring method according to claim 4 is characterized in that: The trend point live traffic data includes a plurality of trend parameter items. After acquiring the trend point live traffic data of the trend point in the monitoring node, the method further includes: The trend parameter item variance corresponding to each trend parameter item is calculated based on a preset variance calculation formula, the live broadcast traffic data of each trend point and the mean value of the session trend data.

6. The live broadcast traffic monitoring method according to claim 5 is characterized in that: The calculating the live broadcast traffic data of each trend point according to the data traffic state model to obtain the trend point probability value corresponding to each trend point includes: The live traffic data of each trend point is calculated according to the variance of each trend parameter item and the Gaussian Naive Bayes formula in the data traffic state model to obtain the trend point probability value corresponding to each trend point; wherein the trend point probability value includes multiple trend parameter item probabilities.

7. The live broadcast traffic monitoring method according to claim 1, characterized in that: After monitoring the real-time live broadcast data of each monitoring node according to the data traffic state model and obtaining a monitoring result of whether the traffic is abnormal, the method further includes: If the monitoring result is yes, a pop-up reminder corresponding to the monitoring result is generated through the plug-in.

8. A live broadcast traffic monitoring device, characterized in that: The device comprises: A first acquisition unit is used to acquire target identification information according to the real-time live broadcast traffic data; wherein the target identification information includes project information and time information; A second acquisition unit, used for acquiring the session trend data in the same time period according to the target identification information; An aggregation unit, used for aggregating the trend data of each session to obtain session array data; A calculation unit, used for calculating the game array data to obtain the game trend data mean; A configuration unit, used for numerically configuring a data flow state model according to a mean value of the session trend data; The monitoring unit is used to monitor the real-time live traffic data of the monitoring node according to the data traffic state model to obtain a monitoring result of whether the traffic is abnormal.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method according to any one of claims 1 to 7 can be implemented.

Images