Service analysis method and apparatus for network device, electronic device, and storage medium

Abstract

Exemplary embodiments of the present application provide a service analysis method and apparatus for a network device, an electronic device, and a storage medium. The method comprises: acquiring an application data sequence and a network data sequence from a service data sequence of a network device; on the basis of the application data sequence and a pretrained discriminative model, determining one or more first application events of an application on a user terminal and corresponding first time information; on the basis of the network data sequence and a pre-established first event determination rule, determining a first network event occurring in the user terminal and corresponding second time information; associating the one or more first application events with the first network event on the basis of the first time information and the second time information; and generating a service analysis result of the network device on the basis of the result of the association.

Description

Service analysis method and device of network equipment, electronic equipment and storage medium

[0001] Cross-reference to Related Applications

[0002] The present application claims priority to the Chinese patent application No. 202411389589.9, filed on September 30, 2024, and entitled "Service analysis method and device of network equipment, electronic equipment and storage medium", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0003] The present application relates to the technical field of data communication, and in particular to a service analysis method and device of network equipment, an electronic equipment and a storage medium. BACKGROUND

[0004] With the development of data communication technology, users have higher and higher requirements for network quality, especially when using real-time applications such as online games and video conferences.

[0005] Taking a real-time strategy (RTS) game in online games as an example, it has extremely high real-time and stability requirements for network communication, and any delay or lag will directly affect the experience of players. SUMMARY

[0006] The present application provides a service analysis method and device of network equipment, an electronic equipment and a storage medium.

[0007] In a first aspect, the present application provides a service analysis method of network equipment, comprising: obtaining an application data sequence and a network data sequence of a service data sequence from the network equipment; determining one or more first application events of an application on a user terminal and corresponding first time information according to the application data sequence and a pre-trained discrimination model; determining a first network event occurring on the user terminal and corresponding second time information based on the network data sequence and a pre-established first event judgment rule; associating the one or more first application events and the first network event according to the first time information and the second time information; and generating a service analysis result of the network equipment based on a result of the association.

[0008] In this way, one or more first application events in the application and first time information of the first application events are determined, and a first network event occurring in the user terminal and second time information of the first network event are determined, and the one or more first application events and the first network event are associated by means of the first time information and the second time information, so as to know which first network event occurs in the user terminal in the process of using the application, and which first application event in the application is affected by the first network event, and the service analysis of the network device is more accurate.

[0009] In an embodiment, before the application data sequence and the network data sequence of the service data sequence from the network device are acquired, the method further comprises:

[0010] The application data sequence and the network data sequence are extracted from the service data sequence.

[0011] In an embodiment, the service data sequence comprises first data, the first data comprises parameter values of a plurality of parameters, the parameter values of the plurality of parameters comprise a parameter value of a parameter corresponding to an application parameter identifier in the first data, and the extracting the application data sequence and the network data sequence from the service data sequence comprises:

[0012] extracting the parameter value of the parameter corresponding to the application parameter identifier from the first data according to the application parameter identifier of the first data; and

[0013] obtaining the application data sequence based on the parameter value of the parameter corresponding to the application parameter identifier of the first data.

[0014] In this way, the required data is acquired from the service data sequence based on the configured application parameter identifier as the application data sequence, and the accuracy of data processing can be improved.

[0015] In an embodiment, the parameter values of the plurality of parameters further comprise a parameter value of a parameter corresponding to a network parameter identifier in the first data, and the extracting the application data sequence and the network data sequence from the service data sequence further comprises:

[0016] extracting the parameter value of the parameter corresponding to the network parameter identifier from the first data according to the network parameter identifier of the first data; and

[0017] obtaining the network data sequence based on the parameter value of the parameter corresponding to the network parameter identifier of the first data.

[0018] In this way, the required data is acquired from the service data sequence based on the configured network parameter identifier as the network data sequence, and the accuracy of data processing can be improved.

[0019] In an embodiment, the determining, according to the application data sequence and the pre-trained discriminant model, the one or more first application events of the application on the user terminal and the corresponding first time information comprises:

[0020] inputting the application data sequence into the pre-trained discriminant model to obtain one or more second application events corresponding to the application data sequence; and

[0021] determining the one or more first application events and the corresponding first time information based on the one or more second application events and one or more collection time periods corresponding to the one or more second application events.

[0022] In some embodiments, the determining, according to the application data sequence and the pre-trained discriminant model, one or more first application events in the application and the corresponding first time information comprises:

[0023] inputting each data in the application data sequence into the discriminant model to obtain a second application event corresponding to each data;

[0024] in response to the second application events corresponding to multiple pieces of data being the same, determining a collection time period of the multiple pieces of data corresponding to the second application event as first time information corresponding to one first application event.

[0025] In this way, the second application event corresponding to each piece of data in the application data sequence is determined by means of the discriminant model, and the collection time of the data corresponding to the same second application event is merged as the first time information of one first application event. Since the second application event is discerned in detail to a single piece of data, the determined first application event and first time information are more accurate.

[0026] In some embodiments, the network data sequence comprises a first data sequence and a second data sequence, the first data sequence is used to represent the service performance of the network device to the user terminal, the second data sequence is used to represent a first network event occurring on the user terminal, and

[0027] The determining, based on the network data sequence and the pre-established first event judgment rule, the first network event occurring on the user terminal and the corresponding second time information comprises:

[0028] finding target data meeting a candidate condition from the first data sequence;

[0029] obtaining a target time period based on the target data, wherein the target time period comprises a collection time period for collecting the target data.

[0030] obtaining a second data sub-sequence from the second data sequence based on the target time period, wherein a collection time period of the second data sub-sequence matches the target time period; and

[0031] determining the first network event and the corresponding second time information based on the first event judgment rule and the second data sub-sequence, wherein the corresponding second time information indicates the collection time period of the target data.

[0032] In this way, the target data meeting the candidate condition is first found, and then the second data sub-sequence corresponding to the first network event is found from the second data sequence according to the collection time period of the target data, and then the specific first network event and the corresponding second time information are determined according to the second data sub-sequence, so that the determination speed is relatively fast, and the accuracy is relatively high.

[0033] In an embodiment, the obtaining of the target time period based on the target data comprises:

[0034] determining a collection time period of the target data based on the target data; and

[0035] performing bidirectional extension processing on the collection time period of the target data to obtain the target time period.

[0036] In an embodiment, the determining of the first network event and the corresponding second time information based on the first event judgment rule and the second data sub-sequence comprises:

[0037] if a parameter value of a parameter of the second data sub-sequence meets the first event judgment rule, determining the first network event as a first event corresponding to the parameter value of the parameter of the second data sub-sequence in the first event judgment rule; and

[0038] determining the second time information based on a collection time period corresponding to the second data sub-sequence.

[0039] In an embodiment, the first data sequence comprises first data, the first data comprises a parameter value of one or more parameters, and the finding of the target data meeting the candidate condition from the first data sequence comprises:

[0040] if the parameter value of the parameter of the first data falls within an abnormal value range of the parameter, determining the first data as the target data.

[0041] In this way, the data with an abnormal parameter value in the first data sequence is taken as the target data, so that the target data with an abnormality can be quickly screened out.

[0042] In an embodiment, the network data sequence further comprises a third data sequence, the third data sequence is used to represent a second network event occurred in the user terminal, the second network event has a lower degree of association with the first application event than the first network event, and before the service analysis result of the network device is generated based on the result of the association, the method further comprises:

[0043] determining the second network event based on the second event judgment rule and the third data sequence.

[0044] In an embodiment, the determining the second network event based on the second event judgment rule and the third data sequence comprises:

[0045] if the parameter value of the parameter of the third data sequence satisfies the second event judgment rule, determining the second event corresponding to the parameter value of the parameter of the second data sequence in the second event judgment rule as the second network event; and

[0046] the generating the service analysis result of the network device based on the result of the association comprises:

[0047] generating the service analysis result of the network device based on the result of the association and the second network event.

[0048] In this way, in the process of using the application by the user terminal, not only the first network event with a higher degree of association with the application event can be found out, but also the second network event with a lower degree of association with the application event can be found out and added to the service analysis result, so as to improve the richness of the service analysis result.

[0049] In an embodiment, the service data sequence comprises first data, the first data comprises a network parameter identifier, the network parameter identifier comprises a first parameter identifier, a second parameter identifier and a third parameter identifier, and the application data sequence and the network data sequence of the service data sequence obtained from the network device comprises:

[0050] extracting a parameter value of a parameter corresponding to the first parameter identifier from the first data to obtain the first data sequence;

[0051] extracting a parameter value of a parameter corresponding to the second parameter identifier from the first data to obtain the second data sequence; and

[0052] extracting a parameter value of a parameter corresponding to the third parameter identifier from the first data to obtain the third data sequence.

[0053] In this way, three data sequences are extracted from the service data sequence according to the configuration once, and the speed is relatively fast.

[0054] In an embodiment, the generating the service analysis result of the network device based on the result of the association comprises:

[0055] If the first network event is a transient network event, the generating the service analysis result of the network device based on the result of the association; and

[0056] If the first network event is a full-process network event, the generating the service analysis result of the network device based on the result of the association and the full-process network event.

[0057] In this way, the first time information and the second time information are associated for the first network event of the transient network event, and the first network event is directly associated to the service analysis result for the first network event of the full-process network event, so that an accurate and refined service analysis result is generated.

[0058] In some embodiments, before the generating the service analysis result of the network device based on the result of the association if the first network event is a transient network event, the method further comprises:

[0059] determining a proportion of a total duration of the first event in a total duration of the use of the application by the user terminal; and

[0060] In response to the proportion being lower than a preset proportion corresponding to the first event, determining that the first event is the transient network event.

[0061] In this way, the first network event whose proportion of the total duration in the total duration of the use of the application by the user terminal is lower than the preset proportion is screened out, and the first network event and the first application event are associated, so as to improve the association accuracy of the first network event and the first application event.

[0062] In some embodiments, before the generating the service analysis result of the network device based on the result of the association and the full-process network event if the first network event is a full-process network event, the method comprises:

[0063] In response to the proportion being not lower than the preset proportion, determining that the first network event is the full-process network event.

[0064] In this way, the first network event whose proportion of the total duration in the total duration of the use of the application by the user terminal is not lower than the preset proportion is screened out, and the first network event is directly added to the service analysis result without being associated with the first application event, so as to improve the completeness of the service analysis.

[0065] In some embodiments, when the proportion is lower than the preset proportion, the first network event is a transient network event; and when the proportion is not lower than the preset proportion, the first network event is a full-process network event.

[0066] In this way, the first network event is divided into a transient network event and a full-process network event, which is beneficial to more accurately understand the first network event.

[0067] In an embodiment, the service data sequence is collected by the network device when the application is running on the user terminal.

[0068] In an embodiment, the first network event includes one of the following: weak signal, air interface occupied by large traffic, WAN port occupied by large traffic, weak signal occupied, 5G same frequency interference, 5G adjacent frequency interference, large traffic of the user terminal, large Internet delay, or power saving of the user terminal.

[0069] In a second aspect, an embodiment of the present application provides a service analysis apparatus of a network device, including:

[0070] An acquisition module is configured to acquire an application data sequence and a network data sequence from a service data sequence of the network device;

[0071] A first determination module is configured to determine one or more first application events of an application on a user terminal and corresponding first time information according to the application data sequence and a pre-trained discrimination model;

[0072] A second determination module is configured to determine a first network event occurring on the user terminal and corresponding second time information based on the network data sequence and a pre-established first event judgment rule; and

[0073] An association module is configured to associate the one or more first application events and the first network event according to the first time information and the second time information; and

[0074] A generation module is configured to generate a service analysis result of the network device based on a result of the association.

[0075] In a third aspect, an embodiment of the present application provides an electronic device, including at least one processor, and a memory in communication connection with the at least one processor, wherein:

[0076] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute any of the above service analysis methods of a network device.

[0077] In a fourth aspect, an embodiment of the present application provides a storage medium, when a computer program in the storage medium is executed by a processor of an electronic device, the electronic device can execute the service analysis method of any of the network devices.

[0078] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising a computer program, when the computer program is executed by a processor, the service analysis method of any of the network devices is implemented. BRIEF DESCRIPTION OF DRAWINGS

[0079] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0080] FIG. 1 is an application scenario provided by an embodiment of the present application;

[0081] FIG. 2 is a flowchart of the service analysis method of the network device provided by an embodiment of the present application;

[0082] FIG. 3 is a flowchart of the service analysis method of the network device provided by an embodiment of the present application;

[0083] FIG. 4 is a structural schematic diagram of the service analysis device of the network device provided by an embodiment of the present application;

[0084] FIG. 5 is a hardware structural schematic diagram of the electronic device for implementing the service analysis method of the network device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0085] In order to make the objects, technical solutions and advantages of the present application clearer, the following will further describe the present application in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0086] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all the embodiments consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0087] And, in the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B; "and / or" in the text is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist together, and B exists alone, in addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0088] It can be understood that, in this article, unless otherwise defined, a data sequence refers to a set of data with a time sequence relationship.

[0089] With the development of data communication technology, users have higher and higher requirements for network quality, especially when using applications such as online games, video conferences, and the like.

[0090] Taking a real-time strategy (RTS) game in an online game as an example, it has extremely high real-time and stability requirements for network communication, and any delay or lag will directly affect the experience of the player. However, in real applications, the network environment of users is complex and variable, and network fluctuations cannot be avoided, so there will be a situation that the user experience is poor. In order to improve the user experience, some Quality of Experience (QOE) and network diagnosis analysis schemes for games appear in the related technology, but these schemes are relatively rough and cannot know the specific impact point of the network problem on the user experience.

[0091] Referring to FIG. 1, FIG. 1 is an application scenario provided by an embodiment of the present application, including a user terminal 100, a network device 200, a first server 300 and a second server 400.

[0092] The user terminal 100 can be a smart phone, a tablet computer, a portable personal computer or any smart device, and various applications can be installed on the user terminal 100, such as online games, video applications, live applications, conference applications, education applications, Internet of Things applications, etc., and the user can play games, watch videos, attend conferences, and online learning through these applications.

[0093] The network device 200, such as a router, a switch, etc., is used to forward data between the user terminal 100 and the first server 300, such as game data, video data, audio data, etc. In FIG. 1, two network devices 200 are taken as an example, in actual applications, there can be only one network device 200, or there can be more network devices 200, and the number of network devices 200 can be different according to different specific application scenarios, which will not be described one by one here.

[0094] The first server 300 can provide various application services for the user terminal 100, and for different application programs on the user terminal 100, the first server 300 can be considered as a background server providing corresponding application services, such as a game server, a video server, a live broadcast server, a conference server, a server of an educational application, a server of an Internet of Things application, and the like. In addition, the first server 300 can be a server, a server cluster composed of a plurality of servers, or a cloud computing center.

[0095] The second server 400 can obtain the service data sequence of the network device 200, and execute the method in the embodiments of the present application based on the service data sequence obtained from each network device 200.

[0096] It should be noted that the application architecture diagram in the embodiments of the present application is used to more clearly illustrate the technical solutions in the embodiments of the present application, and does not constitute a limitation on the technical solutions provided by the embodiments of the present application, and is also not limited to short videos. For other application architectures and business applications, the technical solutions provided by the embodiments of the present application are also applicable to similar problems.

[0097] After introducing the application scenarios of the embodiments of the present application, the determination of the service situation of the network device proposed by the present application will be described in specific embodiments.

[0098] FIG. 2 is a flowchart of a network device service analysis method provided by the embodiments of the present application. The method can be applied to the second server 400 in FIG. 1, and the method includes the following steps.

[0099] In step 201, the application data sequence required for analyzing application events and the network data sequence required for analyzing network events are extracted from the service data sequence of the network device. The service data sequence is collected by the network device during the use of the application by the user terminal.

[0100] The service data sequence is used to represent the service situation of the network device during the use of the application by the user terminal, and the application data sequence and the network data sequence extracted from the service data sequence are both part of the service data sequence.

[0101] In actual application, the application parameter identifier and the network parameter identifier can be configured first, then the parameter value of the parameter corresponding to the application parameter identifier is extracted from each data in the service data sequence according to the configured application parameter identifier, to obtain the application data sequence, and the parameter value of the parameter corresponding to the network parameter identifier is extracted from each data in the service data sequence according to the configured network parameter identifier, to obtain the network data sequence.

[0102] The application events in different applications will be described by way of example.

[0103] For example, in an online game, the application events can include resurrection, team battle, death, etc.; in a live broadcast application, the application events can include audience interaction, connection, voting, etc.; in a video conference application such as an education application, a meeting application, etc., the application events can include interactive discussion, screen sharing, speaker switching, etc.; in an Internet of Things application, the application events can include device state update, device exception, device upgrade, etc.

[0104] It should be noted that for the same application, no matter how the application events are divided, as long as the time information of different application events do not overlap.

[0105] In step 202, one or more first application events in the application and corresponding first time information are determined according to the application data sequence and the pre-trained discrimination model.

[0106] In implementation, each data in the application data sequence can be input into the discrimination model to obtain a second application event corresponding to each data, then each second application event is determined as a first application event, and the collection time period of one or more data corresponding to the second application event is determined as the first time information corresponding to the first application event, wherein the second application event is also an application event in the application.

[0107] In an embodiment, the application data sequence can be collected at a certain collection time interval, so each data in the application data sequence corresponds to a collection time period, and the duration of different first application events is long or short, and the duration of some first application events can be less than the collection time interval, such as resurrection, death, audience interaction, voting, speaker switching, device state update, etc., and the duration of some first application events is greater than the collection time interval, such as team battle, connection, interactive discussion, screen sharing, device exception, device upgrade. Then, when a first application event with a duration less than the collection time interval occurs, only one data corresponds to the first application event, and when a first application event with a duration greater than the collection time interval occurs, multiple continuous data (i.e., an application data sub-sequence) correspond to the first application event.

[0108] In addition, a first application event can occur more than once in the process of using the application by the user terminal, so there can be multiple data with discontinuous collection time corresponding to a first application event, and there can be multiple application data sub-sequences corresponding to a first application event.

[0109] The following illustrates various cases of the first application event.

[0110] Case 1: A first application event with a duration less than the collection time interval occurs once.

[0111] In this case, only one piece of data corresponds to one second application event, and thus, after the second application event is determined as one first application event, the collection time period of the piece of data can be determined as the first time information of the first application event.

[0112] Case 2: The first application event with a duration not greater than the collection time interval occurs more than once.

[0113] In this case, at least two pieces of data correspond to one same second application event, and the at least two pieces of data are discontinuous in time, and thus, after the second application event is determined as one first application event, the collection time period of each piece of data can be determined as the first time information of the first application event.

[0114] Case 3: The first application event with a duration greater than the collection time interval occurs once.

[0115] In this case, one application data subsequence corresponds to one second application event, and thus, after the second application event is determined as one first application event, the collection time period corresponding to the application data subsequence can be determined as the first time information of the first application event.

[0116] Case 4: The first application event with a duration greater than the collection time interval occurs more than once.

[0117] In this case, at least two application data subsequences correspond to multiple second application events, and thus, after the multiple second application events are determined as one first application event, the collection time period corresponding to each application data subsequence can be determined as the first time information of the first application event.

[0118] In step 203, based on the network data sequence and the pre-established first event judgment rule, when the service of the network device to the user terminal meets the candidate condition, the first network event of the user terminal and the corresponding second time information are determined.

[0119] In some embodiments, the network data sequence can include a first data sequence and a second data sequence, the first data sequence is used to represent the service condition of the network device to the user terminal, and the second data sequence is used to represent the first network event of the user terminal.

[0120] In specific implementation, the first network event of the user terminal and the corresponding second time information can be determined according to the following steps.

[0121] Firstly, find the target data in the first data sequence that meets the candidate condition.

[0122] The first data sequence includes parameter values of at least one parameter, and for each data in the first data sequence, if a parameter value of one parameter in the data falls within an abnormal value range of the parameter, the data can be determined as target data, and the abnormal value range is pre-set.

[0123] In the second step, the acquisition time period of each target data is extended bidirectionally to obtain a target time period.

[0124] For example, the acquisition time period of each target data and the time of t seconds before and after the acquisition time period are taken as a target time period.

[0125] In the third step, a second data sub-sequence is intercepted from the second data sequence, and the acquisition time of the second data sub-sequence matches the target time period.

[0126] For example, the acquisition time period contains the target time period, and the difference between the acquisition time period and the target time period is less than a preset time length, which can be a very short time length, such as less than 2 or 3 acquisition time intervals.

[0127] In the fourth step, when the first event judgment rule matches the second data sub-sequence successfully, the first network event corresponding to the first event judgment rule is determined as the first network event occurring on the user terminal, and the acquisition time period of the target data is determined as the second time information corresponding to the first network event.

[0128] In step 204, one or more first application events and first network events are associated according to the first time information and the second time information.

[0129] In some embodiments, after determining that the service of the network device to the user terminal meets the candidate condition, the first network event occurring on the user terminal and the corresponding second time information, the proportion of the total duration of the occurrence of the first network event in the total duration of the user terminal using the application can be determined, and when the proportion is lower than the preset proportion corresponding to the first network event, the first network event can be determined as a transient network event, and one or more first application events and first network events are associated according to the first time information and the second time information to improve the association effect. If the proportion is not lower than the preset proportion of the first network event, the first network event can be determined as a full network event, and the first network event is added to the service analysis result to enrich the service analysis result.

[0130] In step 205, a service analysis result of the network device is generated based on the association result.

[0131] For example, the association result is directly taken as the service analysis result of the network device to the user terminal.

[0132] In the embodiment, in the process that the user terminal uses the application, one or more first application events in the application and first time information of each first application event are determined, a first network event occurring to the user terminal and second time information of the first network event are determined, and the one or more first application events and the first network event are associated by means of the first time information and the second time information, so as to know which first network event occurs to the user terminal in the process that the user terminal uses the application, and which first application event in the application is affected by the first network event, and the service analysis of the network device is more accurate. In this way, the problem that the analysis is rough in the related art when analyzing the service of the network device to the application is solved.

[0133] In some embodiments, the network data sequence can further include a third data sequence, the third data sequence being used to represent a second network event occurring to the user terminal, such as 2.4G roaming 5G, 5G roaming 2.4G, all 2.4G, disconnection, etc., and the association degree between the second network event and the application event is lower than the association degree between the first network event and the application event. At this time, the third data sequence can be matched with a second event judgment rule established in advance, and when the second event judgment rule is matched with the third data sequence successfully, the second network event corresponding to the second event judgment rule can be added to the service analysis result, so as to further enrich the service analysis result.

[0134] The way of extracting the first data sequence, the second data sequence and the third data sequence will be introduced below.

[0135] In specific implementation, the parameter value of the parameter corresponding to the first parameter identifier can be extracted from each data in the service data sequence to obtain the first data sequence, the parameter value of the parameter corresponding to the second parameter identifier can be extracted from each data in the service data sequence to obtain the second data sequence, and the parameter value of the parameter corresponding to the third parameter identifier can be extracted from each data in the service data sequence to obtain the third data sequence, so that the three data sequences are extracted at one time.

[0136] In the embodiment of the application, it can be known from the service analysis result that each first network event is prone to occur in which first application event in the application in the process that the user terminal uses the application, and each first application event in the application is prone to occur which first network event, and the service analysis of the network device is more accurate. In addition, the second network event can be included in the service analysis result, and the service analysis is more comprehensive.

[0137] The scheme of the embodiment of the application will be introduced below by taking the network device as a router and the application as an online game as an example.

[0138] The scheme of the embodiment of the application mainly includes the following steps.

[0139] In a first step, a router serving the user terminal collects data during the use of the online game by the user terminal, obtains a service data sequence, and sends the service data sequence to a cloud server.

[0140] For example, the router collects data every 5 seconds, and obtains one piece of data. A plurality of pieces of data collected in a certain period of time form a service data sequence. One piece of service data can include one or more of the following data: channel utilization of the router, noise floor size, connection frequency band, uplink traffic size (i.e., message size sent by the user terminal to the game server) of each terminal (including the user terminal) connected to the router, downlink traffic size (i.e., message size sent by the game server to the user terminal), uplink packet quantity (i.e., message quantity sent by the user terminal to the game server), downlink packet quantity (i.e., message quantity sent by the game server to the user terminal), whether power saving, received signal strength indication (RSSI), packet loss rate, total delay (sum of delay between the terminal and the router and delay between the router and the game server), whether disconnection, and the like.

[0141] In a second step, the cloud server extracts an application data sequence required for analyzing an application event and a network data sequence required for analyzing a first network event from the service data sequence of the router. The network data sequence includes a first data sequence, a second data sequence, and a third data sequence. In this embodiment, the network data sequence includes the third data sequence.

[0142] Each piece of data in the application data sequence can include uplink traffic size, downlink traffic size, uplink packet quantity, downlink packet quantity, and whether power saving. Each piece of data in the first data sequence can include packet loss rate and total delay. Each piece of data in the second data sequence can include noise floor size and channel utilization of the router, and rssi, downlink traffic size, packet loss rate, and delay of each terminal connected to the router. Each piece of data in the third data sequence can include connection frequency band of the router and whether disconnection.

[0143] In a third step, the cloud server determines one or more first application events in the online game and first time information of each first application event according to the application data sequence and a pre-trained discriminant model.

[0144] First, the training process of the discriminant model is introduced.

[0145] The application data sequence sample is obtained, the label information of each data sample in the application data sequence sample is an application event in an online game, such as a team battle, death, resurrection, dragon fighting, and tower pushing, each data sample in the application data sequence sample is taken as input, and the label information of each service data sample is taken as expected output, the machine learning model is trained until a training end condition is met, the training is stopped, and a trained discrimination model is obtained.

[0146] Next, a process of determining each first application event and first time information of each first application event by using the discrimination model is introduced.

[0147] Each data in the application data sequence is sequentially input into the trained discrimination model, and a second application event corresponding to each data is obtained, and it is assumed that the second application event includes death, resurrection, a team battle, and dragon fighting.

[0148] Generally, death corresponds to only one data, and therefore, the death can be taken as a first application event 1, and a collection time period of the data is determined as first time information of the first application event 1; the resurrection also corresponds to only one data, and therefore, the resurrection can be taken as a first application event 2, and a collection time period of the data is determined as first time information of the first application event 2; it is assumed that the team battle corresponds to two application data subsequences, and therefore, the team battle can be taken as a first application event 3, and collection time periods of the two application data subsequences are determined as first time information of the first application event 3; it is assumed that the dragon fighting corresponds to one application data subsequence, and therefore, the dragon fighting can be taken as a first application event 4, and a collection time period of the application data subsequence is determined as first time information of the first application event 4.

[0149] In a third step, when the service of the router to the user terminal meets the candidate condition based on the network data sequence and the pre-established first event judgment rule, a first network event of the user terminal and corresponding second time information are determined.

[0150] First, how to determine a service anomaly point of the router to the user terminal is introduced.

[0151] In a specific implementation, target data meeting the candidate condition in the first data sequence can be found, for example, for each data (a packet loss rate and a total delay) in the first data sequence, if the packet loss rate is greater than a first threshold value or the total delay is greater than a second threshold value, it is determined that the data is target data meeting the candidate condition, and a collection time period of each target data is a service anomaly point.

[0152] Then, how to determine a first network event in a service anomaly is introduced.

[0153] Here, the collection time period of each target data can be bidirectionally extended to obtain a target time period. For example, 15s of time before and after the collection time period of the target data can be taken as the target time period, and then a second data sub-sequence with a collection time matching the target time period is intercepted from the second data sequence. Then, the second data sub-sequence is matched with the first event judgment rules in Table 1. If the second data sub-sequence matches any first event judgment rule successfully, the first network event corresponding to the first event judgment rule can be determined as the first network event occurring to the user terminal, and the collection time period of the target data can be determined as the first time information of the first network event.

[0154] Table 1

[0155] The background downlink traffic of the user terminal refers to the downlink traffic generated by the application running on the user terminal except online games. Generally, the downlink traffic generated by online games is relatively small. The ping external network delay during game playing refers to the delay between the router and the game server measured by pinging the game server during the game process.

[0156] Next, how to determine whether a first network event is a transient network event or a whole-process network event is introduced.

[0157] Through the above processing, one or more first network events occurring to the user terminal when the router is abnormally serving the user terminal can be known. Then, for each first network event, the proportion of the total duration of the occurrence of the first network event in the total duration of the user playing the game can be determined. If the proportion is not less than the preset proportion of the first network event, the first network event can be determined as a whole-process network event, otherwise, the first network event can be determined as a transient network event. The preset proportions corresponding to the first network events can be referred to Table 2.

[0158] Table 2

[0159] Finally, how to determine whether a second network event occurs to the user during the game playing process is introduced.

[0160] Referring to Table 3, Table 3 is a correspondence between a second network event and a second event judgment rule. In specific implementation, the third data sequence can be matched with the second event judgment rule. If the third data sequence matches any second event judgment rule successfully, the second network event corresponding to the second event judgment rule can be added to the service analysis result.

[0161] Table 3

[0162] Fourthly, the service analysis result of the router to the user terminal is generated according to the results of the second step and the third step.

[0163] Specifically, according to the first time information of the plurality of first application events and the second time information of the instantaneous network event, the plurality of first application events and the instantaneous network event are associated, and then the whole-process network event and the second network event are added to the association to obtain a refined service analysis result of the router to the user terminal.

[0164] In specific implementation, for any one of the instantaneous network event, the whole-process network event and the second network event, if the network event has a performance optimization space, a corresponding relationship between the network event and the optimization strategy can be established in advance, and then in the process of the router serving the user, if any one of the network events occurs, the corresponding optimization strategy can be queried according to the corresponding relationship between the network event and the optimization strategy, and the router can be optimized based on the queried optimization strategy, so as to improve the service quality of the router.

[0165] In the embodiments of the present application, the specific association time between the application events and the network performance problems in the game can be finely identified and diagnosed, which can provide strong support for subsequent products to formulate optimization strategies for specific events and effectively improve the user game experience.

[0166] Based on the same technical concept, the embodiments of the present application also provide a service analysis device of a network device, and the service analysis device of the network device solves the problem in a similar principle to the service analysis method of the network device, so the implementation of the service analysis device of the network device can be referred to the implementation of the service analysis method of the network device, and the repeated parts will not be described here.

[0167] FIG. 3 is a flowchart of the service analysis method of the network device provided by the embodiments of the present application, including the following steps.

[0168] Step 401, obtaining an application data sequence and a network data sequence from a service data sequence of the network device;

[0169] Step 402, determining one or more first application events of an application on a user terminal and corresponding first time information according to the application data sequence and a pre-trained discrimination model;

[0170] Step 403, determining a first network event occurring to the user terminal and corresponding second time information based on the network data sequence and a pre-established first event judgment rule;

[0171] Step 404, associating the one or more first application events and the first network event according to the first time information and the second time information; and

[0172] At step 405, a service analysis result of the network device is generated based on a result of the association.

[0173] The steps of the embodiment have been described in the foregoing embodiments, and the sub-steps of each step or additional steps between the steps are similar to those of the foregoing embodiments, which will not be described herein again.

[0174] FIG. 4 is a structural schematic diagram of a service analysis apparatus of a network device according to an embodiment of the present application, which comprises:

[0175] The acquisition module 301 is configured to acquire an application data sequence and a network data sequence from a service data sequence of the network device.

[0176] The first determination module 302 is configured to determine one or more first application events of the application on the user terminal and corresponding first time information according to the application data sequence and a pre-trained discrimination model.

[0177] The second determination module 303 is configured to determine a first network event occurring on the user terminal and corresponding second time information based on the network data sequence and a pre-established first event judgment rule.

[0178] The association module 304 is configured to associate the one or more first application events and the first network event according to the first time information and the second time information.

[0179] The generation module 305 is configured to generate a service analysis result of the network device based on a result of the association.

[0180] In some embodiments, each piece of data of the service data sequence comprises parameter values of one or more parameters; and the acquisition module 301 is specifically configured to:

[0181] The application data sequence required for analyzing the application event and the network data sequence required for analyzing the network event are extracted from the service data sequence of the network device, comprising:

[0182] According to the configured application parameter identifier, the parameter values of the parameters corresponding to the application parameter identifier are extracted from each piece of data of the service data sequence to obtain the application data sequence.

[0183] According to the configured network parameter identifier, the parameter values of the parameters corresponding to the network parameter identifier are extracted from each piece of data of the service data sequence to obtain the network data sequence.

[0184] In some embodiments, the first determination module 302 is specifically configured to:

[0185] input each data in the application data sequence into the discrimination model to obtain a second application event corresponding to each data;

[0186] determine each second application event as a first application event, and determine a collection time period of one or more data corresponding to the second application event as first time information corresponding to the first application event.

[0187] In some embodiments, the network data sequence includes a first data sequence and a second data sequence, the first data sequence is used to represent service conditions of the network device to the user terminal, and the second data sequence is used to represent a first network event occurring to the user terminal. The second determination module 303 is specifically used for:

[0188] finding target data meeting the candidate condition from the first data sequence;

[0189] performing bidirectional extension processing on a collection time period of each target data to obtain a target time period;

[0190] cutting a second data sub-sequence from the second data sequence, a collection time of the second data sub-sequence matches the target time period;

[0191] when a first event judgment rule matches the second data sub-sequence successfully, determining a first network event corresponding to the first event judgment rule as the first network event occurring to the user terminal, and determining a collection time period of the target data as second time information corresponding to the first network event.

[0192] In some embodiments, the first data sequence includes parameter values of one or more parameters, and the second determination module 303 is specifically used for:

[0193] for each data in the first data sequence, if a parameter value of a parameter in the data falls within an abnormal value range of the parameter, the data is determined as the target data.

[0194] In some embodiments, the network data sequence further includes a third data sequence, the third data sequence is used to represent a second network event occurring to the user terminal, and an association degree between the second network event and an application event is lower than an association degree between the first network event and the application event. The second determination module 303 is further used for:

[0195] matching the third data sequence with a second event judgment rule established in advance;

[0196] When a second event determination rule matches the third data sequence successfully, a second network event corresponding to the second event determination rule is added to the service analysis result.

[0197] In some embodiments, the network parameter identifier includes a first parameter identifier, a second parameter identifier, and a third parameter identifier, and the obtaining module 301 is specifically configured to:

[0198] extract a parameter value of a parameter corresponding to the first parameter identifier from each piece of data in the service data sequence to obtain the first data sequence;

[0199] extract a parameter value of a parameter corresponding to the second parameter identifier from each piece of data in the service data sequence to obtain the second data sequence;

[0200] extract a parameter value of a parameter corresponding to the third parameter identifier from each piece of data in the service data sequence to obtain the third data sequence.

[0201] In some embodiments, the second determining module 303 is further configured to:

[0202] when it is determined that the service of the network device to the user terminal meets the candidate condition, determine a proportion of a total duration of occurrence of a first network event of the user terminal to a total duration of use of the application by the user terminal after the first network event and corresponding second time information occur;

[0203] when the proportion is lower than a preset proportion corresponding to the first network event, associate the one or more first application events and the first network event according to the first time information and the second time information.

[0204] In some embodiments, the generating module 305 is further configured to add the first network event to the service analysis result when the proportion is not lower than the preset proportion.

[0205] In some embodiments, when the proportion is lower than the preset proportion, the first network event is a transient network event; and when the proportion is not lower than the preset proportion, the first network event is a full-process network event.

[0206] The division of the modules in the embodiments of the present application is illustrative, and is merely a logical function division. In actual implementation, another division manner can be used. In addition, each functional module in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The coupling between each module can be realized through some interfaces. These interfaces are usually electrical communication interfaces, but can also be mechanical interfaces or other forms of interfaces. Therefore, the modules described as separate components can or can not be physically separated, and can be located in one place or distributed to different locations of the same or different devices. The integrated modules can be realized in the form of hardware or in the form of software functional modules.

[0207] After introducing the service analysis method and device of the network equipment of the example embodiment of the present application, next, the electronic equipment according to another example embodiment of the present application is introduced.

[0208] Next, the electronic equipment 130 realized according to this embodiment of the present application is described with reference to FIG. 5. The electronic equipment 130 shown in FIG. 5 is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0209] As shown in FIG. 5, the electronic equipment 130 is in the form of a general electronic equipment. The components of the electronic equipment 130 can include but are not limited to the above-mentioned at least one processor 131, the above-mentioned at least one memory 132, and a bus 133 connecting different system components including the memory 132 and the processor 131.

[0210] The bus 133 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor or local bus using any of a variety of bus structures.

[0211] The memory 132 can include a readable medium in the form of volatile memory, such as a random access memory (RAM) 1321 and / or a cache memory 1322, and can further include a read-only memory (ROM) 1323.

[0212] The memory 132 can further include a program / utility 1325 having a set of program modules 1324, including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or a combination can include implementation of a network environment.

[0213] The electronic device 130 can also communicate with one or more external devices 134 such as a keyboard or pointing device, through an input / output (I / O) interface 135. And the electronic device 130 can communicate with one or more devices that enable user interaction with the electronic device 130, and / or one or more devices that enable communication of the electronic device 130 with one or more other electronic devices. This communication can be via the I / O interface 135. The electronic device 130 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the public networks, such as the Internet, through a network adapter 136. As depicted, the network adapter 136 is in communication with the other components of the electronic device 130 through the bus 133. It should be appreciated that other hardware and / or software modules can be used in conjunction with the electronic device 130, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0214] In an example embodiment, a storage medium is also provided, when a computer program in the storage medium is executed by a processor of an electronic device, the electronic device can perform the service analysis method of the network device described above. Optionally, the storage medium can be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0215] In an example embodiment, the electronic device of the present application can at least include at least one processor, and a memory connected to the at least one processor in communication, wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the steps of any service analysis method of the network device provided by the embodiments of the present application.

[0216] In an example embodiment, a computer program product is also provided, when the computer program product is executed by an electronic device, the electronic device can implement any example method provided by the present application.

[0217] Moreover, a computer program product can employ any combination of one or more computer readable media or storage media. A computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0218] The program product for service analysis of network equipment in the embodiments of the present application can employ a CD-ROM and include program codes, and can run on a computing device. However, the program product of the present application is not limited thereto, and in the present document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus or device.

[0219] A readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, in which a readable program code is borne. Such a propagated data signal can take on many forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. A readable signal medium can also be any readable medium that can send, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device.

[0220] The program code contained on a readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, radio frequency (RF), and the like, or any suitable combination thereof.

[0221] Program code implementing the application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider. The application is related to the use of computer system 100 for online analytics, online content, and online advertising.

[0222] It should be noted that, although several units or sub-units of the apparatus are mentioned in the above detailed description, such division into units or sub-units is merely exemplary and not mandatory. Indeed, according to an embodiment of the application, features and functions of two or more units described above can be embodied in a single unit. Conversely, features and functions of one unit described above can be split into multiple units.

[0223] Moreover, while operations of the methods of the present application are described in a particular order in the figures, this is merely for ease of description and is in no way meant to limit the claimed application to a particular order of operations or to performing all of the described operations. Additionally or alternatively, certain steps can be omitted, combined, performed in a different order, and / or split into multiple steps.

[0224] Those skilled in the art will appreciate that embodiments of the present application can be devised for a method, a system, or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0225] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0226] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks.

[0227] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0228] Although preferred embodiments of the application have been described herein, it will be apparent to those skilled in the art that various modifications can be made within the scope of the application. Accordingly, it is intended that all content of the above description and all variations and modifications be included within the scope of the application. The above description is intended to be illustrative and not restrictive. Many other potential applications of the application will be apparent to those skilled in the art.

[0229] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A service analysis method of a network device, comprising: obtaining an application data sequence and a network data sequence from a service data sequence of the network device; determining one or more first application events of an application on a user terminal and corresponding first time information according to the application data sequence and a pre-trained discriminant model; determining a first network event occurred on the user terminal and corresponding second time information based on the network data sequence and a pre-established first event judgment rule; associating the one or more first application events and the first network event according to the first time information and the second time information; and generating a service analysis result of the network device based on a result of the association. Before the obtaining the application data sequence and the network data sequence from the service data sequence of the network device, the method further comprises:

2. The method of claim 1, wherein, extracting the application data sequence and the network data sequence from the service data sequence. The service data sequence comprises first data, the first data comprises parameter values of a plurality of parameters, the parameter values of the plurality of parameters comprise a parameter value of a parameter corresponding to an application parameter identifier in the first data, and the extracting the application data sequence and the network data sequence from the service data sequence comprises:

3. The method of claim 2, wherein, extracting the parameter value of the parameter corresponding to the application parameter identifier from the first data according to the application parameter identifier of the first data; and obtaining the application data sequence based on the parameter value of the parameter corresponding to the application parameter identifier of the first data. The parameter values of the plurality of parameters further comprise a parameter value of a parameter corresponding to a network parameter identifier in the first data, and the extracting the application data sequence and the network data sequence from the service data sequence further comprises:

4. The method of claim 2 or 3, wherein, extracting the parameter value of the parameter corresponding to the network parameter identifier from the first data according to the network parameter identifier of the first data; and obtaining the network data sequence based on the parameter value of the parameter corresponding to the network parameter identifier of the first data. The determining the one or more first application events of the application on the user terminal and the corresponding first time information according to the application data sequence and the pre-trained discriminant model comprises:

5. The method of any one of claims 1 to 4, wherein, inputting the application data sequence into the pre-trained discriminant model to obtain one or more second application events corresponding to the application data sequence; and determining the one or more first application events and the corresponding first time information based on the one or more second application events and one or more collection time periods corresponding to the one or more second application events. The network data sequence comprises a first data sequence and a second data sequence, the first data sequence is used to represent a service performance of the network device to the user terminal, the second data sequence is used to represent a first network event occurred on the user terminal, and 6. The method of any one of claims 1 to 5, wherein, ​ The determining, based on the network data sequence and the pre-established first event judgment rule, of the first network event occurring to the user terminal and the corresponding second time information comprises: finding target data meeting a candidate condition from the first data sequence; obtaining a target time period based on the target data, wherein the target time period comprises a collection time period for collecting the target data; cutting a second data sub-sequence from the second data sequence based on the target time period, wherein a collection time period of the second data sub-sequence matches the target time period; and determining the first network event and the corresponding second time information based on the first event judgment rule and the second data sub-sequence, wherein the corresponding second time information indicates the collection time period of the target data.

7. The method of claim 6, wherein, The obtaining, based on the target data, of the target time period comprises: determining a collection time period of the target data based on the target data; and performing bidirectional extension processing on the collection time period of the target data to obtain the target time period.

8. The method of claim 6 or 7, wherein, The determining, based on the first event judgment rule and the second data sub-sequence, of the first network event and the corresponding second time information comprises: if a parameter value of a parameter of the second data sub-sequence meets the first event judgment rule, determining, as the first network event, a first event corresponding to the parameter value of the parameter of the second data sub-sequence in the first event judgment rule; and determining the second time information based on a collection time period corresponding to the second data sub-sequence.

9. The method of any one of claims 6 to 8, wherein, The first data sequence comprises first data, the first data comprises parameter values of one or more parameters, and the finding, from the first data sequence, of target data meeting the candidate condition comprises: if the parameter values of the parameters of the first data fall within an abnormal value range of the parameters, determining the first data as the target data.

10. The method of any one of claims 6 to 9, wherein, The network data sequence further comprises a third data sequence, the third data sequence is used to represent a second network event occurring to the user terminal, an association degree of the second network event to the first application event is lower than an association degree of the first network event to the first application event, and before the generating, based on the association result, of the service analysis result of the network device, the method further comprises: determining the second network event based on the second event judgment rule and the third data sequence.

11. The method of claim 10, wherein, The determining, based on the second event judgment rule and the third data sequence, of the second network event comprises: if a parameter value of a parameter of the third data sequence meets the second event judgment rule, determining, as the second network event, a second event corresponding to the parameter value of the parameter of the second data sequence in the second event judgment rule; and The generating, based on the association result, of the service analysis result of the network device comprises: generating the service analysis result of the network device based on the association result and the second network event.

12. The method of claim 10 or 11, wherein, The service data sequence includes first data, the first data includes a network parameter identifier, the network parameter identifier includes a first parameter identifier, a second parameter identifier, and a third parameter identifier, and the application data sequence and the network data sequence of the service data sequence from the network device are obtained, including: extracting a parameter value of a parameter corresponding to the first parameter identifier from the first data to obtain the first data sequence; extracting a parameter value of a parameter corresponding to the second parameter identifier from the first data to obtain the second data sequence; and extracting a parameter value of a parameter corresponding to the third parameter identifier from the first data to obtain the third data sequence.

13. The method of any one of claims 10 to 12, wherein, The service analysis result of the network device is generated based on the result of the association, including: if the first network event is a transient network event, the service analysis result of the network device is generated based on the result of the association; and if the first network event is a full-range network event, the service analysis result of the network device is generated based on the result of the association and the full-range network event.

14. The method of claim 13, wherein, If the first network event is a transient network event, the service analysis result of the network device is generated based on the result of the association, and before the first network event is a full-range network event, the method further includes: determining the proportion of the total duration of the first event in the total duration of the user terminal using the application; and in response to the proportion being lower than the preset proportion corresponding to the first event, determining that the first event is the transient network event.

15. The method of claim 14, wherein, If the first network event is a full-range network event, the service analysis result of the network device is generated based on the result of the association and the full-range network event, and before the first network event is a full-range network event, the method includes: in response to the proportion being not lower than the preset proportion, determining that the first network event is the full-range network event.

16. The method of claims 1 to 15, wherein, The service data sequence is collected by the network device when the application is running on the user terminal.

17. The method of claims 1-16, wherein, The first network event includes one of the following: weak signal, large flow occupying air interface, large flow occupying WAN interface, weak signal occupation, 5G same frequency interference, 5G adjacent frequency interference, user terminal large flow, large Internet delay, or user terminal power saving.

18. A service analysis device of a network device, comprising: an acquisition module configured to acquire an application data sequence and a network data sequence of a service data sequence from the network device; a first determination module configured to determine one or more first application events of the application on a user terminal and corresponding first time information according to the application data sequence and a pre-trained discrimination model; a second determination module configured to determine a first network event occurring on the user terminal and corresponding second time information based on the network data sequence and a pre-established first event judgment rule; and an association module configured to associate the one or more first application events and the first network event according to the first time information and the second time information; and a generation module configured to generate a service analysis result of the network device based on a result of the association.

19. An electronic device comprising: at least one processor, and a memory connected with the at least one processor in communication, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 17.

20. A computer readable storage medium, wherein, When the computer program in the storage medium is executed by the processor of the electronic device, the electronic device can perform the method according to any one of claims 1 to 17.

Images