Short video traffic monitoring method, device and server

Abstract

The application provides a short video traffic monitoring method and device and a server, and relates to the field of communication. The method comprises the following steps: a server associates one-time online browsing of the same user to one browsing record according to information in a service code stream. The server processes the browsing record according to a preset service model to obtain an experience index of each browsing record. The server determines whether a wireless cell is a wireless side abnormal cell according to the experience index in each wireless cell. When the wireless cell is the wireless side abnormal cell, the server splices the browsing record and a corresponding quality report to obtain a composite document. The server determines abnormal information of the wireless side abnormal cell according to the composite document in the wireless side abnormal cell. The server locates an abnormal cause of the wireless side abnormal cell according to the abnormal information. The method provided in the application improves the accuracy of abnormal positioning of the wireless cell and improves the accuracy of optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, and in particular to a short video traffic monitoring method, device and server. BACKGROUND

[0002] With the continuous development of short video services, the daily active user number of some short video platforms has exceeded 600 million. In the face of a huge user group, network quality has encountered great challenges.

[0003] Currently, technical personnel can obtain alarm signals, key quality indicators (KPIs), measurement indicators (Measurement Reports, MRs) and the like of base stations and / or cells in suspected problem areas after determining the base stations and / or cells. Technical personnel can accurately locate the base stations and / or cells in the problem areas according to the information.

[0004] However, the network quality optimization achieved using this method has the problem of poor targeting. Further, it can easily lead to low positioning efficiency and blind optimization promotion. SUMMARY

[0005] The present application provides a short video traffic monitoring method, device and server to solve the problem of poor targeting of network quality optimization in the prior art.

[0006] In a first aspect, the present application provides a short video traffic monitoring method, comprising:

[0007] Obtaining a service code stream, and obtaining experience indicators of each browsing record of each user in each wireless cell according to information carried in the service code stream and a preset service model;

[0008] Determining whether each wireless cell is a wireless side abnormal cell according to the experience indicators of each browsing record in each wireless cell;

[0009] When the wireless cell is a wireless side abnormal cell, splicing each browsing record of the wireless side abnormal cell and a corresponding quality report of the browsing record to obtain a composite invoice of each browsing record in the wireless side abnormal cell;

[0010] Locating abnormal information of the wireless side abnormal cell according to a plurality of composite invoices in the wireless side abnormal cell.

[0011] Optionally, the determining whether each wireless cell is a wireless side abnormal cell according to the experience indicators of each browsing record in each wireless cell specifically comprises:

[0012] determining whether the browsing record is an abnormal browsing record of network transmission quality abnormity according to the experience index of each browsing record of the wireless cell;

[0013] determining whether the wireless cell is a wireless side abnormal cell according to the abnormal browsing record of each wireless cell.

[0014] Optionally, the determining whether the wireless cell is a wireless side abnormal cell according to the abnormal browsing record of each wireless cell specifically comprises:

[0015] counting a first number of the abnormal browsing records in each wireless cell;

[0016] determining a downlink round-trip delay corresponding to each experience index according to the experience index of each abnormal browsing record;

[0017] counting a second number of the abnormal browsing records in each wireless cell whose downlink round-trip delay is greater than or equal to a preset super-long delay;

[0018] determining a first ratio according to a ratio of the second number and the first number;

[0019] counting a third number of the abnormal browsing records in each wireless cell which occurs packet loss;

[0020] determining a second ratio according to a ratio of the third number and the first number;

[0021] determining that the wireless cell is a wireless side abnormal cell when the first ratio is greater than or equal to a first threshold value and the second ratio is greater than or equal to a second threshold value.

[0022] Optionally, the obtaining the experience index of each browsing record of each user in each wireless cell according to the information carried in the service code stream and a preset service model specifically comprises:

[0023] identifying a non-encrypted code stream in the service code stream;

[0024] associating a one-time online browsing process of the same user to a browsing record according to associated information in the non-encrypted code stream;

[0025] quantifying each browsing record into an experience index according to a preset service model.

[0026] Optionally, the locating the abnormal information of the wireless side abnormal cell according to the multiple composite invoices in the wireless side abnormal cell specifically comprises:

[0027] According to the composite single bill in the wireless side abnormal cell, a plurality of service parameters corresponding to each of the composite single bills are obtained;

[0028] According to each of the service parameters and a parameter threshold value corresponding to each of the service parameters, an abnormal proportion of each of the service parameters in the wireless side abnormal cell is determined;

[0029] According to the abnormal proportion of each of the service parameters and a proportion threshold value of the service parameter, it is determined whether the service parameter is an abnormal parameter;

[0030] According to the abnormal parameter, the abnormal information of the wireless side abnormal cell is determined.

[0031] Optionally, the method further comprises:

[0032] According to the abnormal information, an optimization scheme is generated;

[0033] The abnormal information and the optimization scheme are sent;

[0034] The optimization scheme at least includes an optimized radio frequency parameter, an optimized wireless parameter, cell expansion, and re-planning of a base station.

[0035] In a second aspect, the present application provides a short video traffic monitoring device, comprising:

[0036] An acquisition module is configured to acquire a service code stream, and obtain an experience index of each browsing record of each user in each wireless cell according to information carried in the service code stream and a preset service model;

[0037] A processing module is configured to determine whether each wireless cell is a wireless side abnormal cell according to the experience index of each browsing record in each wireless cell; when the wireless cell is a wireless side abnormal cell, splice each browsing record of the wireless side abnormal cell and a corresponding quality report of the browsing record to obtain a composite single bill of each browsing record in the wireless side abnormal cell; and locate abnormal information of the wireless side abnormal cell according to a plurality of composite single bills in the wireless side abnormal cell.

[0038] Optionally, the processing module is specifically configured to:

[0039] According to the experience index of each browsing record of the wireless cell, it is determined whether the browsing record is an abnormal browsing record of network transmission quality;

[0040] According to each of the abnormal browsing records of each wireless cell, it is determined whether the wireless cell is a wireless side abnormal cell.

[0041] Optionally, the processing module is specifically configured to:

[0042] counting a first number of the abnormal browsing records in each of the wireless cells;

[0043] determining a downlink round trip time corresponding to each of the experience indexes according to the experience index of each of the abnormal browsing records;

[0044] counting a second number of the abnormal browsing records in each of the wireless cells, where the downlink round trip time is greater than or equal to a preset long time delay;

[0045] determining a first ratio according to a ratio of the second number and the first number;

[0046] counting a third number of the abnormal browsing records in each of the wireless cells, where a packet loss occurs;

[0047] determining a second ratio according to a ratio of the third number and the first number;

[0048] determining that the wireless cell is a wireless side abnormal cell when the first ratio is greater than or equal to a first threshold value and the second ratio is greater than or equal to a second threshold value.

[0049] Optionally, the obtaining module is specifically configured to:

[0050] identify a non-encrypted stream in the service code stream;

[0051] associate a one-time online browsing process of a same user into one browsing record according to associated information in the non-encrypted stream;

[0052] quantify each of the browsing records into an experience index according to a preset service model.

[0053] Optionally, the processing module is specifically configured to:

[0054] obtain a plurality of service parameters corresponding to each of the composite invoices in the wireless side abnormal cell according to the composite invoices;

[0055] determine an abnormal proportion of each of the service parameters in the wireless side abnormal cell according to each of the service parameters and a parameter threshold value corresponding to each of the service parameters;

[0056] determine whether the service parameter is an abnormal parameter according to the abnormal proportion of each of the service parameters and a proportion threshold value of the service parameter;

[0057] determine abnormal information of the wireless side abnormal cell according to the abnormal parameter.

[0058] Optionally, the processing module is further configured to:

[0059] generate an optimization scheme according to the abnormal information;

[0060] send the abnormal information and the optimization scheme;

[0061] The optimization scheme at least includes optimizing radio frequency parameters, optimizing wireless parameters, expanding a cell, and re-planning a base station.

[0062] In a third aspect, the present application provides a server, comprising a memory and a processor.

[0063] The memory is configured to store a computer program, and the processor is configured to execute the short video traffic monitoring method in the first aspect and any possible design of the first aspect according to the computer program stored in the memory.

[0064] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program. When at least one processor of a server executes the computer program, the server executes the short video traffic monitoring method in the first aspect and any possible design of the first aspect.

[0065] In a fifth aspect, the present application provides a computer program product, which comprises a computer program. When at least one processor of a server executes the computer program, the server executes the short video traffic monitoring method in the first aspect and any possible design of the first aspect.

[0066] The short video traffic monitoring method, device and server provided by the present application can obtain a service code stream, and further obtain information carried in the service code stream; according to the information in the service code stream, the information is integrated, and one-time online browsing of the same user is associated into one browsing record; according to a preset service model, the information in the browsing record is processed to obtain an experience index of each browsing record; the experience indexes in each wireless cell are summarized to determine whether the wireless cell is a wireless side abnormal cell; when the wireless cell is a wireless side abnormal cell, each browsing record of the wireless side abnormal cell and a corresponding quality report of the browsing record are spliced to obtain a composite invoice of each browsing record in the wireless side abnormal cell; data in a plurality of composite invoices in the wireless side abnormal cell are summarized to analyze abnormal information of the wireless side abnormal cell; according to the abnormal information, a means of locating an abnormal reason of the wireless side abnormal cell is determined to accurately locate the abnormal cell, so that targeted optimization is realized, the network optimization can improve the user's experience of the key sensitive service, and the effect of accurate optimization of the short video perception is realized. BRIEF DESCRIPTION OF DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0068] Figure 1 A short video traffic monitoring scene schematic diagram provided for an embodiment of the application;

[0069] Figure 2 A flowchart of a short video traffic monitoring method provided for an embodiment of the application;

[0070] Figure 3 A service code stream identification schematic diagram provided for an embodiment of the application;

[0071] Figure 4 A browsing record association schematic diagram provided for an embodiment of the application;

[0072] Figure 5 A model index schematic diagram provided for an embodiment of the application;

[0073] Figure 6 An index dotting schematic diagram provided for an embodiment of the application;

[0074] Figure 7 An index splicing schematic diagram provided for an embodiment of the application;

[0075] Figure 8 An index splicing schematic diagram provided for an embodiment of the application;

[0076] Figure 9 A lag index schematic diagram provided for an embodiment of the application;

[0077] Figure 10 A structure schematic diagram of a short video traffic monitoring device provided for an embodiment of the application;

[0078] Figure 11 A hardware structure schematic diagram of a server provided for an embodiment of the application. DETAILED DESCRIPTION

[0079] In order to make the purpose, technical solutions and advantages of the application clearer, the technical solutions in the application will be described clearly and completely below in combination with the drawings in the application. Obviously, the described embodiments are some embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor also belong to the protection scope of the application.

[0080] The terms "first", "second", "third", "fourth", and the like in the description and in the claims of the present application and above accompanying drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the so-termed terms herein is only to distinguish the different similar embodiments and the use of such terms is not to imply a sequence or order unless clearly indicated by the specification. The terms "comprises", "comprising", "includes", "including", and the like are to be construed open-ended, meaning that they are used to both "include" and also "not to exclude". As such, these terms encompass the possibility that the subject matter of the sentence includes other steps, elements, or items not expressly listed or inherent to the subject matter of the sentence. In addition, where the disclosure above refers to lists of items that can be performed it will be understood that the order of those items are not important and the list can comprise additional or fewer items than those expressly listed.

[0081] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting."

[0082] Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0083] The terms "or" and "and / or" as used herein are to be interpreted as inclusive, i.e., as meaning "one or the other or both". Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". An exception to this definition will occur only when a combination of elements, functions, steps or acts are in some way inherently mutually exclusive.

[0084] With the continuous development of short video business, the daily active user number of some short video platforms has exceeded 600 million. Among them, as an app focusing on music creative short videos, TikTok is also an interesting community for young people to make friends. Facing the huge user group, the short video business has encountered huge network experience challenges. Short video playing lag, long video loading time, more than 5 seconds of lag, etc. are all network quality problems that affect user experience. As of February 2022, the monthly live broadcast of short videos has reached 51,000 times. The live broadcast business has very high requirements for the quality of wireless networks in the "push-pull flow" process. Once the network quality problem occurs, it is easy to cause the user to lag when live streaming.

[0085] With the continuous expansion of short video services, the number of complaints about video stuttering, long video loading time and other issues during use is increasing. Therefore, technical personnel can obtain the user's perception of stuttering through user complaints, and then determine the suspected problem area of the base station and / or cell. Technical personnel can obtain alarm signals, key quality indicators (KPIs), measurement indicators (MeasurementReport, MR) and other information of these base stations and / or cells through on-site retesting. Technical personnel can determine whether the base station and / or cell in the problem area has network quality deterioration according to this information. Alternatively, technical personnel can determine the service perception KQI indicator according to this information, and then determine whether the suspected cell has a short video perception difference. However, this method lacks scene and does not have a complete short video perception monitoring and wireless side user-level data associated with a clear positioning method, which cannot classify and attribute feedback data in more fine-grained. Therefore, the network quality optimization implemented using this method has the problem of poor targeting. Further, it is easy to cause low positioning efficiency and blind optimization improvement. Moreover, the wireless KPI indicator of the cell has too large a granularity and cannot specifically represent the user's real perception, resulting in poor data effectiveness.

[0086] Based on the above pain points, the method provided by the embodiments of the present application proposes a short video traffic monitoring method on the basis of the existing big data platform deployment. The method can improve the user experience of using short videos through real-time monitoring of the traffic of short video services. The present application can accurately locate the user position by establishing a service perception model, and realize efficient and accurate optimization by combining Per Service Per User (PSPU) big data and wireless KPI / MR of each user. Avoiding the short video service perception improvement work from falling into the mass testing and KPI index analysis, the network optimization can target to improve the user's key sensitive service experience. In the implementation process of the present application, the server can combine the core network user-level big data, wireless KPI index, MR index, frequency modulation (FM) and other information, and on the basis of identifying the short video service, analyze the short video service stream to establish a perception index model. The server can also splice the perception index and the wireless side index of the user at the same period through big data association to establish a short video service perception monitoring system, trigger the effect of automatic delimiting and positioning of problems, and realize the monitoring and optimization of real-time short video perception difference problems. After the preset service model of the video service is established, the server can use TCP pipeline indicators to delimit problems. The TCP indicators can include uplink and downlink loopback delay, packet loss rate, etc. The server can also exclude the browsing records of SP, core network elements and other non-interface problems. The server can also transfer these browsing records to the wireless side for splicing. The server can also backfill the user number of the wireless MR, associate with the latitude and longitude information contained in the Over The Top TV (OTT) application layer data of the core network on the open Internet, and combine the planning prediction based on the electronic map to generate a fingerprint library. The server can improve the accuracy of user positioning by backfilling the latitude and longitude of all MRs. The server can also generate a composite bill after splicing the short video service experience bill and the high-precision MR obtained by the above method to realize accurate optimization of short video perception.

[0087] In the following, the exemplary application scenarios of the embodiments of the present application are introduced.

[0088] Figure 1A short video traffic monitoring scenario provided by an embodiment of the present application is shown. The method of the present application can specifically include short video service experience modeling; sensing difference delimitation and screening; core network and backfilling International Mobile Subscriber Identity (IMSI) and latitude and longitude wireless MR splicing; association of base station cell KPI / MR indicators, and convergence analysis problem cell 4 parts. The server can complete the standardization of each part, and realize this step in a digital way. Through this way, the server can replace most of the work previously carried out by manual means with programs, significantly reducing the workload of sensing problem analysis, positioning and optimization, and improving the real-time and automation effect of user experience identification and optimization. As shown in Figure 1 The specific implementation process of the above four steps. The server can obtain service xDR according to service code stream integration. The service xDR can be specifically the browsing records of each user of each wireless cell. Each browsing record includes multiple browsing of one online. The server can use 4G / 5G probes to extract features from the service xDR. Then, according to the extracted features, the server can realize service identification and modeling, and obtain OTT user location information. The server can also obtain a preset service model. The preset service model can include a large number of service parameters. The server can process the service information and modeling data obtained by the probe according to the preset service model, and realize experience rough delimitation. The experience rough delimitation can be specifically that the server extracts user experience information from the service information and modeling data according to the preset service model after obtaining the service information and modeling data. The server can realize rough delimitation of user experience according to the user experience information and the preset threshold. The rough delimitation is specifically used to indicate whether the user experience is abnormal.

[0089] If there is an abnormality, the server can further determine whether the abnormality is an interface below problem. If it is not an interface below problem, the server can continue to analyze the core network OTT side. If it is an interface below problem, the server needs to splice the core network and xDR data after obtaining the data to obtain a composite invoice. The data of the core network is the quality report obtained by the server after obtaining MR positioning enhancement information, and performing user-level service-level wireless quality judgment on the MR positioning enhancement information. The MR positioning enhancement information can include OTT user location information obtained by the server after extracting features from the service xDR using probes. The MR positioning enhancement information can also include wireless data obtained by the server after analyzing CHR, MR, RM, alarm and other data of the unlimited network. If the server cannot perform user-level service-level wireless quality judgment on the MR positioning enhancement information, the server does not process the data.

[0090] After acquiring composite documents, the server can aggregate these documents. The server can then perform unified analysis on a cell-by-cell basis, combining the aggregated composite documents with data such as MR, KPI, and FM to determine if any problems exist within the cell. If a problem is found, the server can determine that the wireless network needs optimization. Otherwise, the server can determine whether the anomaly is on the terminal side or the user side. When the server needs to optimize the wireless network, it can do so through performance optimization, capacity expansion, and base station replanning. After optimization, the server can also evaluate the cell's short video service to determine the effectiveness of the optimization.

[0091] In this application, a server is used as the executing entity to perform the short video traffic monitoring method according to the following embodiments. Specifically, the executing entity can be a server hardware device, a software application implementing the following embodiments on the server, a computer-readable storage medium installed with the software application implementing the following embodiments, or code implementing the software application.

[0092] The technical solutions of this application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0093] Figure 2 A flowchart illustrating a short video traffic monitoring method according to an embodiment of this application is shown. Figure 1 Based on the illustrated embodiments, as Figure 2 As shown, with the server as the execution entity, the method in this embodiment may include the following steps:

[0094] S101. Obtain the service stream and, based on the information carried in the service stream and the preset service model, obtain the experience metrics for each browsing record of each user in each wireless cell.

[0095] In this embodiment, the server can obtain a service code stream. The service code stream is an HTTP-based code stream. Alternatively, the service code stream can be a code stream of a short video service. Alternatively, the service code stream can be a code stream of a TikTok short video service. After obtaining the service code stream, the server can obtain information carried in the service code stream. Alternatively, the information can include referrer information in a HTTP header of the service code stream. The referrer information is information used by a browser to tell a web server the source of information when the browser makes a request to the web server. The server can use the referrer information to indicate which page the request is connected from. Alternatively, the information can also include location information. The location information is information in the HTTP header that has the function of jumping and redirecting. Alternatively, the information can also include host information. The host information includes domain name, IP address, port number, and other information of an http server that a client specifies to access. That is, the host information can be a domain name. Alternatively, the host information can be an IP address. Alternatively, the domain name or IP address of the host information can be followed by a port number. For example, the host information can be Host: www.sina.com:8080. The server can integrate the HTTP packets according to the information of each HTTP packet in the service code stream. The server can associate a web browsing of a same user to a browsing record. The server can also store a preset service model. The preset service model can include a plurality of parameter indicators. The server can process the information in the browsing record according to the preset service model to obtain an experience indicator of each browsing record. The experience indicator includes a plurality of parameter indicators for indicating the quality of the user's web browsing.

[0096] In an example, the specific process of the server obtaining the experience indicator includes the following steps:

[0097] Step 1, identify the non-encrypted code stream in the service code stream.

[0098] In this step, after obtaining the service code stream, the server can obtain the information carried in the packet header of the HTTP packet through the probe. The server can also use the probe to identify the waveform characteristics of the code stream. For example, as shown in Figure 3 , the server can obtain the HTTP packet from the IP Header of the service code stream. The server can obtain the HTTP Header from the HTTP packet. The server can obtain the GET information and host information of the request from the HTTP Header. For example, as shown in Figure 3 , the GET information can include “ / index.htm HTTP / 1.1”. For another example, as shown in Figure 3As shown, the host information can include an IP address "www.douyini.com". After obtaining the information, the server can identify the non-encrypted stream in the service code stream obtained by the server in various ways. For example, as shown in Figure 3 The identification way can include one or more of the following ways: identification based on port, identification based on dynamic signature, identification based on DNS association, identification based on algorithm, identification based on static signature, identification based on association, identification based on behavior characteristics, identification based on user group relationship, etc. The non-encrypted stream can be a non-encrypted OTT service code stream in the service code stream.

[0099] Step 2: According to the association information in the non-encrypted stream, associate the online browsing process of the same user in one time into one browsing record.

[0100] In this step, the server can obtain the association information of each HTTP package from the non-encrypted stream. The association information can include referer, uri, location, host, code stream interval time, etc. The server can determine the association relationship between multiple HTTP packages according to the association information. The server can associate the online browsing process of the same user in one time into one browsing record. For example, the association process can be as shown in Figure 4 As shown, the server can obtain the referer of video 1, video 2, and video 3 as page 1 from the non-encrypted stream of the three videos. The server can associate the three videos as three events of page 1 into one browsing record. The one browsing record can be an xDR. The xDR is an external data representation method. The xDR can be implemented in the presentation layer of the OSI model. The xDR allows to package data in a structure independent of the medium, so that the data can be transmitted in heterogeneous computer systems. The conversion from local representation to xDR is called encoding. The conversion from xDR to local representation is called decoding. The xDR can use software to complete the conversion. Therefore, the xDR can be flexibly used in different operating systems. Moreover, the xDR is independent of the transport layer. In this step, the xDR can be understood as a browsing record or a record list generated by online browsing. One xDR usually corresponds to one online behavior. However, one online browsing can correspond to multiple TCP / UDP streams. Therefore, multiple packages in the code stream need to be associated into one browsing record through multiple key information. The browsing record can include experience information such as time delay and speed of the user in the browsing.

[0101] Step 3: Quantify each browsing record into an experience index according to a preset service model.

[0102] In this step, the server stores a preset service model. The preset service model can include multiple experience indicators. These experience indicators can be obtained by technical personnel according to the service characteristics. The server can quantify the parameters in the browsing record according to the preset service model to obtain multiple experience indicators. For example, the preset service model can be as shown in Figure 5 The business model can set multiple indicators for the business layer and the interconnection layer respectively. The indicators of the business layer are basic quality indicators. In the Web Browsing process, the indicators can include page response delay, page download rate, page response success rate, etc. In the Video Streaming process, the indicators can include xKB startup delay, video effective download rate, etc. In the File Access process, the indicators can include file sharing / multimedia response delay, file sharing / multimedia upload / download rate, etc. In the short video process, the indicators can include short video startup delay, pipe effective download rate, etc. In the game process, the indicators can include game battle delay, etc. The indicators of the interconnection layer are mainly divided into pipe indicators and end-to-end delimiting parameters. The pipe indicators are the indicators of the DNS / TCP layer. The pipe indicators can include DNS success rate, DNS delay, TCP establishment success rate, TCP packet loss rate, TCP retransmission rate, TCP out-of-order rate, round-trip time (RTT) (three-way handshake), RTT (number transmission), user group effective rate (bandwidth). The end-to-end delimiting parameters are TCP layer delimiting parameters. The parameters are used to support KPI delimiting. The parameters can include server packet sending delay, server sending window, terminal receiving window, terminal dynamic receiving window, terminal request response delay, interface down packet loss rate, interface down number transmission RTT, interface down out-of-order rate, interface up packet loss rate, interface up number transmission RTT, interface up out-of-order rate.

[0103] S102, according to the experience indicators of each browsing record in each wireless cell, determine whether the wireless cell is a wireless side abnormal cell.

[0104] In this embodiment, the server can extract multiple parameter indicators in each browsing record according to the preset service model as shown in Figure 5 After extracting the multiple parameter indicators in each browsing record, the server can use the parameter indicators as the experience indicators of the browsing record. The server can summarize the experience indicators in each wireless cell to determine whether the wireless cell is a wireless side abnormal cell.

[0105] In an example, the determination process can include the following steps:

[0106] Step 1, according to the experience indicators of each browsing record in the wireless cell, determine whether the browsing record is an abnormal browsing record with network transmission quality anomaly.

[0107] In this step, the server first needs to determine whether each browsing record is an abnormal browsing record of network transmission quality according to the experience index. The judgment of the network transmission quality is the definition of the service layer KQI quality degradation problem. The server can assist in defining the problem caused by the network transmission quality through specific TCP parameters. The server can mainly perform dotting through a probe. Furthermore, the server can determine the time delay information of the information in the transmission process through the dotting information. The server can determine whether the browsing record has network transmission quality abnormality according to the time delay information. The probe is a tool deployed in the core network to realize the detection and analysis of bidirectional code stream data through the S1-U (LTE) port or the N3 (SA) port. Through the probe, the server can represent the time delay performance of the link pipe by calculating the RTT of the TCP packet, and indirectly obtain the user's perception of good and bad.

[0108] The dotting process can be as shown in Figure 6 Figure 6 ​This diagram illustrates the timing points obtained by the probe during multiple handshakes between a UE (User Equipment) and the SP (Service Provider) server. During the first handshake, after the signal is output by the UE, a synchronization sequence number (SYN) is generated as it passes through the Serving GPRS Support Node (SGSN) / Evolved Node B (eNodeB). The probe generates the first timing point signal when it detects this first handshake. This first handshake signal can reach the SP Server through the network elements of the GSM / GPRS / EDGE network's core network (CN), such as the Gateway GPRS Support Node (GGSN) / Serving Gateway (SGW). During the second handshake, the SP Server can send back a SYN and an acknowledgment character (ACK) to the UE. Simultaneously, the signal of this second handshake can be detected by the probe, generating the second timing point signal. The time difference between the first and second timing point signals can be denoted as RTT_est_cn. During the third handshake, the UE sends a signal containing an ACK to the SP Server. The signal of the third handshake can be detected by the probe, generating a third marker signal. The time difference between the third and second marker signals can be denoted as RTT_est_radio. The time difference between the third and first marker signals can be denoted as RTT_set. After completing the three-way handshake, the UE can send a Get request to the SP Server. The signal of this Get request can be detected by the probe, generating a fourth marker signal. The time difference between the fourth and third marker signals can be denoted as the terminal response delay. The SP Server can send a feedback signal containing an ACK to the UE. This feedback signal can be detected by the probe, generating a fifth marker signal. The time difference between the fifth and fourth marker signals can be denoted as RTT_data1_cn. Subsequently, the SP Server can send data to the UE. This data can be divided into multiple packets. For example, such as... Figure 6As shown, the data is divided into 6 packets. These 6 packets can be denoted as data sn=1, data sn=2, data sn=3, data sn=4, data sn=5, and data sn=6, respectively. When the SP Server sequentially sends these 6 data packets to the UE, the probe can detect the signal of the data packets and mark them. Figure 6As shown, the probe can detect a signal containing data sn=1 and generate a sixth marker signal. The time difference between the sixth and fifth marker signals can be recorded as the server response delay. After receiving a signal from the SP Server, the UE can send an ACK sn=1 signal back to the SP Server. When this signal can be detected by the probe, the probe can generate a seventh marker signal. The time difference between the seventh and sixth marker signals can be recorded as RTT_data1_radio. When a signal containing data sn=3 is detected by the probe, the probe can generate an eighth marker signal. The time difference between the eighth and seventh marker signals can be recorded as the hunger delay. This hunger delay indicates the duration during which all bytes received by the probe have been acknowledged and the probe waits for the next byte. After receiving a signal containing data sn=3 from the SP Server, the UE can send an ACK sn=3 signal back to the SP Server. When the probe detects a signal containing ACK sn=3, it can generate a ninth marker signal. The time difference between the ninth and eighth radio dot signals can be denoted as RTT_data3_radio. If the signal with data sn=4 is not detected by the probe, the probe can perform packet loss counts++. If the probe detects the signal with data sn=6 and generates ten radio dot signals, then detects the signal with data sn=5 and generates eleven radio dot signals, the signal with data sn=5 can be considered an out-of-sequence signal. When the UE fails to parse data sn=3, the UE can send a signal containing DupACK sn=3 to the SP Server to request the SP Server to retransmit the data packet with data sn=3. When the SP Server receives the DupACK sn=3 signal, it can retransmit the data packet with data sn=3 multiple times to ensure that the UE can receive the data packet with data sn=3. When multiple signals containing retransmission data sn=3 are detected by the probe, the probe can generate the twelfth, thirteenth, and so on. The time difference between the twelfth and thirteenth marker signals can be denoted as the Continuous Retransmission Delay. Figure 6 The dot data can be shown in Table 1 below.

[0109] Table 1

[0110]

[0111] Step 2, determine whether the wireless cell is a wireless side abnormal cell according to the abnormal browsing records of each wireless cell.

[0112] In this step, after the server filters the abnormal browsing records from all the browsing records, the server can aggregate the abnormal browsing records of each wireless cell. When the server analyzes using the TCP pipe index, it mainly refers to the network average value, and the analysis is very complex, without a unified standard. Therefore, in actual analysis, there may be different reference values for different business types and network types. In order to improve the analysis efficiency, the server usually analyzes by comparing the changes before and after, horizontal comparison and other methods. In the three-way handshake process of UE and SP Server, the time delay, interface below RTT, and packet loss are usually related to the wireless side network / user / terminal. Among them, the interface refers to the S1-U (LTE) interface or N3 (SA) interface where the probe is located. The interface below RTT refers to the wireless end transmission delay. The second handshake delay, interface above RTT, and packet loss are usually related to the core network and OTT. Among them, the interface above RTT refers to the server transmission delay. The server rarely uses other indicators for judgment. Alternatively, when the short video is a TikTok short video, the server usually takes data with downlink RTT ultra-long delay ratio higher than 30% or downlink packet loss rate higher than 1% as the judgment standard of abnormality when analyzing user experience. Among them, the downlink RTT ultra-long delay usually refers to the downlink RTT delay greater than 200ms.

[0113] The specific process in which the server determines whether the wireless cell is a wireless side abnormal cell according to the aggregated abnormal browsing records of each wireless cell can include the following steps:

[0114] Step 21, the server can count the first number of abnormal browsing records in each wireless cell.

[0115] Step 22, the server can determine the downlink round-trip delay corresponding to each experience index according to the experience index of each abnormal browsing record.

[0116] Step 23, the server can count the second number of abnormal browsing records in each wireless cell with downlink round-trip delay greater than or equal to a preset ultra-long delay. For example, the preset ultra-long delay can be 200ms.

[0117] Step 24, the server can determine a first ratio according to the ratio of the second number and the first number.

[0118] Step 25, the server can count a third number of abnormal browsing records with packet loss in each wireless cell.

[0119] Step 26, the server can determine a second ratio according to the ratio of the third number and the first number.

[0120] Step 27, when the first ratio is greater than or equal to a first threshold value, and the second ratio is greater than or equal to a second threshold value, the server can determine that the wireless cell is a wireless-side abnormal cell. For example, the first threshold value can be 30%, and the second threshold value can be 1%.

[0121] Step 3, when the wireless cell is not a wireless-side abnormal cell, the server can continue to analyze and locate the cause through the core network and the OTT side.

[0122] S103, when the wireless cell is a wireless-side abnormal cell, splice each browsing record of the wireless-side abnormal cell and the corresponding quality report of the browsing record to obtain a composite invoice of each browsing record in the wireless-side abnormal cell.

[0123] In this embodiment, after the server determines the abnormality of the wireless cell through service identification modeling and experience demarcation, it can be determined whether the abnormality is caused by a wireless-side problem. If the abnormality is caused by a wireless-side problem, the server can determine that the wireless cell is a wireless-side abnormal cell. When the server determines that a wireless cell is a wireless-side abnormal cell, the server needs to associate the indicators and alarms of the wireless device side to comprehensively judge the cause of the poor perception and realize cause positioning.

[0124] Since the original MR does not usually contain user identification and location information, the server usually needs to associate the signaling plane xDR of the core network to backfill the IMSI information. Then, the server can generate a composite invoice by combining the OTT application information in the core network user plane code stream with the MR and the work parameters. The OTT application information contains latitude and longitude. The server can use these composite invoices to generate a feature library. The feature library can also be a fingerprint library. That is, each composite invoice is a feature. The server can backfill the latitude and longitude for the full MR to obtain MR with user identification and latitude and longitude information. The splicing process of data backfilling can be as shown in Figure 7 In this process, the user plane xDR and the MR are associated through user identification (IMSI), time (StartTime<TimeStamp<EndTime), and wireless cell (SAI_CGI_ECGI=Server Cell), so that a complete composite invoice containing service perception indicators and wireless measurement indicators is spliced. The splicing process can be as shown in Figure 8The server can splice the TimeStamp, RSRP / SINR / TXP / TA, Longtiude, Latitude parameters in the MR with the parameters of StartTime, EndTime, IMSI, service type, SAI_CGI_ECGI, KQI (xKB / speed), TCP KPI (DL_RTT / DL_LONG_RTT_RATE) in the user plane xDR to obtain the spliced xDR. The spliced xDR is the composite bill.

[0125] In S104, the abnormal information of the wireless-side abnormal cell is located according to the multiple composite bills in the wireless-side abnormal cell.

[0126] In this embodiment, the server can obtain multiple composite bills in the wireless-side abnormal cell. The server can summarize the data in the composite bills to analyze the abnormal information of the wireless-side abnormal cell. The server can locate the abnormal cause of the wireless-side abnormal cell according to the abnormal information.

[0127] In an example, the specific steps of the server to locate the abnormal information can include:

[0128] In S101, multiple service parameters corresponding to each composite bill are obtained according to the composite bills in the wireless-side abnormal cell.

[0129] In this step, the server can extract the parameters of each composite bill from the data of the composite bill. The server can also calculate the service parameters according to the parameters of all the composite bills in a wireless-side abnormal cell. For example, the service parameters can include RRC user number, downlink PRB utilization rate, uplink packet loss number, cell coverage far point user uplink packet loss number, Reference Signal Receiving Power (RSRP), Physical Uplink Shared Channel (PUSCH), uplink Modulation and Coding Scheme (MCS), downlink MCS, phone-to-base station distance (TA), interference, number of non-neighbor cells, base station alarm, VoLTE uplink initial block error rate (iBLER), and the like.

[0130] In S102, the abnormal proportion of each service parameter in the wireless-side abnormal cell is determined according to each service parameter and the parameter threshold value corresponding to each service parameter.

[0131] In this step, the server stores a parameter threshold corresponding to each service parameter. The server can compare each service parameter with the parameter threshold to determine the service parameter with an anomaly. The server can calculate the anomaly proportion of each service parameter according to the number of abnormal service parameters and the total amount of service parameters. The total amount of service parameters is the number of documents that meet the criteria in the wireless side abnormal cell. For example, the parameter threshold corresponding to the service parameter RSRP can be -110. When RSRP is greater than or equal to -110, it indicates that the composite document has weak downlink coverage. The parameter threshold corresponding to the service parameter PUSCH can be -130. When PUSCH is less than -130, it indicates that the composite document has weak uplink coverage. The parameter threshold corresponding to the service parameters uplink MCS and downlink MCS can be 3. When uplink MCS or downlink MCS is less than 3, it indicates that the composite document has poor uplink quality or poor downlink quality. When the service parameter TA is greater than the parameter threshold 1KM, it indicates that it exceeds the urban coverage. When the service parameter TA is greater than the parameter threshold 2KM, it indicates that it exceeds the suburban coverage.

[0132] Step 3, according to the anomaly proportion of each service parameter and the proportion threshold of the service parameter, determine whether the service parameter is an abnormal parameter.

[0133] In this step, the server stores a proportion threshold corresponding to each service parameter. The server can compare each service parameter with the proportion threshold to determine whether the service parameter is an abnormal parameter. For example, the proportion threshold of the service parameter RRC user number can be 100. When the RRC user number is greater than 100, the RRC user number is an abnormal parameter. The proportion threshold of the service parameter downlink PRB utilization rate can be 50%. When the downlink PRB utilization rate is greater than 50%, the downlink PRB utilization rate is an abnormal parameter. The proportion threshold of the service parameter interference can be -100dBm. When the interference is greater than -100dBm, the interference is an abnormal parameter. The proportion threshold of the service parameter number of times without neighboring cells can be 1000 times / week. When the number of times without neighboring cells is greater than 1000 times / week, the number of times without neighboring cells is an abnormal parameter. The proportion threshold of the service parameter VoLTE uplink iBLER can be 20%. When the VoLTE uplink iBLER is greater than 20%, the VoLTE uplink iBLER is an abnormal parameter.

[0134] Alternatively, the server can compare the abnormal proportion of each service parameter with the proportion threshold to determine whether the service parameter is an abnormal parameter. For example, the proportion threshold corresponding to the ratio of the uplink packet loss quantity of the cell coverage far point user to the uplink packet loss quantity of the service parameter can be 50%. When the ratio of the uplink packet loss quantity of the cell coverage far point user to the uplink packet loss quantity is greater than 50%, the uplink packet loss quantity is an abnormal parameter. The proportion threshold of the service parameter RSRP can be 80%. When the number of RSRP greater than or equal to -110 accounts for less than 80% in all service parameters, the RSRP is an abnormal parameter. The proportion threshold of the service parameter PUSCH can be 40%. When the number of PUSCH less than -130 accounts for greater than 40% in all service parameters, the PUSCH is an abnormal parameter. The proportion threshold of the service parameter uplink MCS can be 30%. When the number of uplink MCS less than 3 accounts for greater than 30% in all service parameters, the uplink MCS is an abnormal parameter. The proportion threshold of the service parameter downlink MCS can be 30%. When the number of downlink MCS less than 3 accounts for greater than 30% in all service parameters, the downlink MCS is an abnormal parameter. The proportion threshold of the service parameter TA can be 30%. When the number of TA greater than 1 KM accounts for greater than 30% in all service parameters, the TA is an abnormal parameter. And / or, when the number of TA greater than 2 KM accounts for greater than 30% in all service parameters, the TA is an abnormal parameter.

[0135] Step 4, determining the abnormal information of the wireless side abnormal cell according to the abnormal parameter.

[0136] In this step, different abnormal parameters can correspond to different abnormal information. The abnormal information can include an abnormal reason. The server can determine the abnormal reason according to different abnormal parameters. For example, the service parameter RRC user number and the service parameter downlink PRB utilization rate can correspond to a capacity problem. The service parameter uplink packet loss quantity and the service parameter RSRP can correspond to a downlink weak coverage problem. The service parameter PUSCH can correspond to an uplink weak coverage problem. The service parameter uplink MCS can correspond to an uplink quality problem. The service parameter downlink MCS can correspond to a downlink quality problem. The service parameter TA can correspond to an over coverage problem. The service parameter interference can correspond to an uplink interference problem. The service parameter number of times without neighboring cells can correspond to a neighboring cell problem. The service parameter base station alarm and the service parameter VoLTE uplink iBLER can correspond to an uplink error code problem. The service parameter RSRP can correspond to MR good coverage rate (MDT).

[0137] The above steps can be specifically as shown in Table 2.

[0138] Table 2

[0139]

[0140]

[0141] In an example, the server can further generate an optimization scheme according to the abnormal information after determining the abnormal information. The optimization scheme includes but is not limited to optimizing radio frequency parameters, optimizing wireless parameters, expanding a cell, re-planning a base station, etc. The server can send the abnormal information and the optimization scheme to a technician. The technician can perform site investigation, audit, etc. according to the abnormal information and the optimization scheme, thereby realizing optimization.

[0142] The short video traffic monitoring method provided in the application, the server can obtain a service code stream, and then obtain the information carried in the service code stream. The server can integrate the information according to the information in the service code stream, and associate the online browsing of the same user at a time into a browsing record. The server can process the information in the browsing record according to a preset service model to obtain an experience index of each browsing record. The server can summarize the experience index in each wireless cell to determine whether the wireless cell is a wireless side abnormal cell. When the wireless cell is a wireless side abnormal cell, the server can splice each browsing record of the wireless side abnormal cell and the corresponding quality report of the browsing record to obtain a composite invoice of each browsing record in the wireless side abnormal cell. The server can summarize the data in the multiple composite invoices in the wireless side abnormal cell to analyze the abnormal information of the wireless side abnormal cell. The server can locate the abnormal reason of the wireless side abnormal cell according to the abnormal information. In the application, the short video service code stream is monitored in real time to accurately locate the possible abnormalities of the wireless cell, thereby realizing targeted optimization, improving the user's experience of sensitive services, and realizing accurate optimization of short video perception.

[0143] On the basis of the above embodiments, the technician obtains the short video stall ratio of a certain cell before using the technical solution shown in the application and the short video stall ratio of the cell after using the technical solution shown in the application. The experimental results can be as shown in Figure 9 As shown in Figure 9 From March 7 to May 15, the technician counted the short video stall ratio in a period of 7 days. It is known that the technical solution shown in the application is applied in the cell on March 7. As can be seen from Figure 9 It can be seen that the short video stall ratio of the cell gradually decreases from 18.02% to 3.91% over time, which improves the service perception of the short video in the cell, and the improvement effect is obvious.

[0144] Figure 10 Fig. 1 shows a structural schematic diagram of a short video traffic monitoring device according to an embodiment of the application.Figure 10 As shown, the short video traffic monitoring device 10 of the embodiment is used to implement the operation corresponding to the server in any of the method embodiments, and the short video traffic monitoring device 10 of the embodiment comprises:

[0145] The acquisition module 11 is configured to acquire a service code stream, and obtain an experience index of each browsing record of each user in each wireless cell according to information carried in the service code stream and a preset service model.

[0146] The processing module 12 is configured to determine whether the wireless cell is a wireless side abnormal cell according to the experience index of each browsing record in each wireless cell. When the wireless cell is the wireless side abnormal cell, splice each browsing record of the wireless side abnormal cell and the corresponding quality report of the browsing record to obtain a composite invoice of each browsing record in the wireless side abnormal cell. According to a plurality of composite invoices in the wireless side abnormal cell, locate the abnormal information of the wireless side abnormal cell.

[0147] Optionally, the processing module 12 is specifically configured to:

[0148] determine whether the browsing record is an abnormal browsing record of network transmission quality abnormality according to the experience index of each browsing record of the wireless cell.

[0149] determine whether the wireless cell is the wireless side abnormal cell according to the abnormal browsing record of each wireless cell.

[0150] Optionally, the processing module 12 is specifically configured to:

[0151] count a first number of the abnormal browsing records in each wireless cell.

[0152] determine a downlink round-trip delay corresponding to each experience index according to the experience index of each abnormal browsing record.

[0153] count a second number of the abnormal browsing records in each wireless cell, wherein the downlink round-trip delay of each abnormal browsing record is greater than or equal to a preset super-long delay.

[0154] determine a first ratio value according to a ratio of the second number and the first number.

[0155] count a third number of the abnormal browsing records in each wireless cell, wherein a packet loss occurs in each abnormal browsing record.

[0156] determine a second ratio value according to a ratio of the third number and the first number.

[0157] determine that the wireless cell is the wireless side abnormal cell when the first ratio value is greater than or equal to a first threshold value and the second ratio value is greater than or equal to a second threshold value.

[0158] Optionally, the acquisition module 11 is specifically configured to:

[0159] Identify the non-encrypted code stream in the service code stream.

[0160] According to the association information in the non-encrypted code stream, the online browsing process of the same user is associated into a browsing record.

[0161] According to the preset service model, each browsing record is quantified as an experience index.

[0162] Optionally, the processing module 12 is specifically configured to:

[0163] According to the composite single bill in the wireless side abnormal cell, a plurality of service parameters corresponding to each composite single bill are obtained.

[0164] According to each service parameter and the parameter threshold value corresponding to each service parameter, the abnormal proportion of each service parameter in the wireless side abnormal cell is determined.

[0165] According to the abnormal proportion of each service parameter and the proportion threshold value of the service parameter, it is determined whether the service parameter is an abnormal parameter.

[0166] According to the abnormal parameter, the abnormal information of the wireless side abnormal cell is determined.

[0167] Optionally, the processing module 12 is further configured to:

[0168] According to the abnormal information, an optimization scheme is generated.

[0169] The abnormal information and the optimization scheme are sent.

[0170] The optimization scheme includes but is not limited to optimizing radio frequency parameters, optimizing wireless parameters, cell expansion, and re-planning base station.

[0171] The short video traffic monitoring device 10 provided by the embodiment of the application can execute the above-mentioned method embodiment, and the specific implementation principle and technical effect can be referred to the above-mentioned method embodiment, which will not be described here in detail.

[0172] Figure 11 A hardware structure schematic diagram of a server provided by an embodiment of the application is shown. As shown in the figure, the server 20 is used to realize the operation corresponding to the server in any of the above-mentioned method embodiments, and the server 20 of the embodiment can include a memory 21, a processor 22 and a communication interface 24. Figure 11

[0173] ​The memory 21 is configured to store a computer program. The memory 21 can include a random access memory (RAM), and can further include a non-volatile memory (NVM), for example, at least one disk memory, and can be a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0174] The processor 22 is configured to execute the computer program stored in the memory, so as to implement the short video traffic monitoring method in the above embodiments. Details can be referred to the related description in the method embodiments. The processor 22 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0175] Optionally, the memory 21 can be independent or integrated with the processor 22.

[0176] When the memory 21 is independent of the processor 22, the server 20 can further include a bus 23. The bus 23 is configured to connect the memory 21 and the processor 22. The bus 23 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0177] The communication interface 24 can be connected with the processor 21 through the bus 23. The communication interface 24 is configured to obtain the code stream of the short video service.

[0178] The server provided in the embodiment can be used to execute the short video traffic monitoring method, and the implementation manner and technical effects are similar, which will not be described here.

[0179] The application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method provided by the various embodiments.

[0180] The computer readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates transfer of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general purpose or special purpose computer. For example, the computer readable storage medium can be coupled to the processor, such that the processor can read information from, and write information to, the computer readable storage medium. Of course, the computer readable storage medium can be a component of the processor. Accordingly, the processor and the computer readable storage medium can be considered to be a specialized computer for executing the computer program. The specialized computer can be a user device. Alternatively, the specialized computer can be a discrete component of the user device.

[0181] In particular, the computer readable storage medium can be realized by any type of volatile or non-volatile storage devices, or a combination thereof, such as static random access memory (SRAM), electrically-erasable programmable read-only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage devices, flash memory, magnetic disks, or optical disks. The storage medium can be any available medium that can be accessed by a general purpose or special purpose computer.

[0182] The application also provides a computer program product, which includes a computer program stored in a computer readable storage medium. At least one processor of a device can read the computer program from the computer readable storage medium, and the at least one processor executes the computer program to enable the device to implement the method provided by the various embodiments.

[0183] The embodiments of the present application further provide a chip, which comprises a memory and a processor. The memory is used to store a computer program. The processor is used to call and run the computer program from the memory, so that the device installed with the chip executes the method in the various possible embodiments.

[0184] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, apparatuses or modules, which can be electrical, mechanical or other forms.

[0185] Among them, each module can be physically separated, for example, installed in different positions of one device, or installed on different devices, or distributed to multiple network elements, or distributed to multiple processors. Each module can also be integrated together, for example, installed in the same device, or integrated in a set of codes. Each module can exist in the form of hardware, or can exist in the form of software, or can be realized in the form of software plus hardware. The present application can select part or all of the modules to achieve the purpose of the embodiments of the present application according to actual needs.

[0186] When each module is realized in the form of an integrated module of a software function module, it can be stored in a computer readable storage medium. The above software function module stored in a storage medium includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of the steps of the method of each embodiment of the present application.

[0187] It should be understood that although each step in the flowchart in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise stated in this article, the execution of these steps has no strict sequence limitation, and they can be executed in other orders. Moreover, at least part of the steps in the figure can include a plurality of sub-steps or a plurality of stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or sub-steps or stages of other steps.

[0188] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0189] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features. The modification or replacement does not make the essence of the corresponding technical solution deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring short video traffic, characterized in that, The method includes: The service stream is obtained, and based on the information carried in the service stream and the preset service model, the experience index of each user's browsing record in each wireless cell is obtained. Based on the experience metrics of each browsing record in each wireless cell, determine whether the wireless cell is an abnormal wireless cell. When the wireless cell is a wireless-side abnormal cell, each browsing record and the corresponding wireless quality report of the wireless-side abnormal cell are spliced ​​together. The splicing is based on the user identifier IMSI, time and wireless cell identifier to obtain a composite document for each browsing record in the wireless-side abnormal cell. The composite document includes service perception indicators and wireless measurement indicators. Based on multiple composite documents in the abnormal wireless cell, the abnormal information of the abnormal wireless cell is located.

2. The method according to claim 1, characterized in that, The step of determining whether a wireless cell is an abnormal wireless cell based on the experience metrics of each browsing record in each wireless cell specifically includes: Based on the experience metrics of each browsing record in the wireless cell, determine whether the browsing record is an abnormal browsing record with abnormal network transmission quality; Based on the abnormal browsing records of each wireless cell, determine whether the wireless cell is an abnormal cell on the wireless side.

3. The method according to claim 2, characterized in that, The step of determining whether a wireless cell is an abnormal wireless cell based on the abnormal browsing records of each wireless cell specifically includes: Count the first number of abnormal browsing records in each of the aforementioned wireless cells; Based on the experience metrics of each of the aforementioned abnormal browsing records, determine the downlink round-trip latency corresponding to each of the aforementioned experience metrics; The second number of abnormal browsing records in each of the wireless cells whose downlink round-trip latency is greater than or equal to a preset excessive latency is counted. The first ratio is determined based on the ratio of the second quantity to the first quantity; The third number of abnormal browsing records in each of the aforementioned wireless cells where packet loss occurred is counted; The second ratio is determined based on the ratio of the third quantity to the first quantity; When the first ratio is greater than or equal to the first threshold and the second ratio is greater than or equal to the second threshold, the wireless cell is determined to be an abnormal wireless cell.

4. The method according to any one of claims 1-3, characterized in that, The process of obtaining experience metrics for each browsing record of each user in each wireless cell based on the information carried in the service stream and a preset service model specifically includes: Identify the unencrypted stream in the service bitstream; Based on the association information in the unencrypted stream, a single online browsing process of the same user is associated with a single browsing record; Based on the preset business model, each browsing record is quantified into an experience metric.

5. The method according to any one of claims 1-3, characterized in that, The step of locating the abnormal information of the abnormal cell on the radio side based on multiple composite documents in the abnormal cell on the radio side specifically includes: Based on the composite document in the abnormal cell on the wireless side, multiple service parameters corresponding to each composite document are obtained; Based on each of the service parameters and the corresponding parameter threshold, the abnormal proportion of each service parameter in the abnormal cell on the wireless side is determined. Based on the abnormality ratio of each business parameter and the ratio threshold of the business parameter, it is determined whether the business parameter is an abnormal parameter; Based on the abnormal parameters, the abnormal information of the abnormal cell on the wireless side is determined.

6. The method according to any one of claims 1-3, characterized in that, The method further includes: Based on the aforementioned anomaly information, an optimization plan is generated; Send the exception information and the optimization plan; The optimization scheme includes at least optimizing radio frequency parameters, optimizing wireless parameters, expanding cell capacity, and replanning base stations.

7. A short video traffic monitoring device, characterized in that, The device includes: The acquisition module is used to acquire the service bitstream and, based on the information carried in the service bitstream and the preset service model, obtain the experience index of each user's browsing record in each wireless cell. The processing module is used to determine whether a wireless cell is an abnormal wireless cell based on the experience indicators of each browsing record in each wireless cell; when the wireless cell is an abnormal wireless cell, it concatenates each browsing record of the abnormal wireless cell with the corresponding wireless quality report, wherein the concatenation is based on the user identifier IMSI, time, and wireless cell identifier to obtain a composite document for each browsing record in the abnormal wireless cell, the composite document containing service perception indicators and wireless measurement indicators; and locates the abnormal information of the abnormal wireless cell based on multiple composite documents in the abnormal wireless cell.

8. A server, characterized in that, The server includes: a memory and a processor; The memory is used to store computer programs; the processor is used to implement the short video traffic monitoring method as described in any one of claims 1 to 6 according to the computer programs stored in the memory.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, is used to implement the short video traffic monitoring method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the short video traffic monitoring method according to any one of claims 1 to 6.

Images