CN109921941B

CN109921941B - Network service quality evaluation and optimization method, device, medium and electronic equipment

Info

Publication number: CN109921941B
Application number: CN201910203371.2A
Authority: CN
Inventors: 周瑞卿; 宁斌晖; 张丹
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-03-18
Filing date: 2019-03-18
Publication date: 2021-09-17
Anticipated expiration: 2039-03-18
Also published as: CN109921941A

Abstract

The embodiment of the application provides a method, a device, a medium and an electronic device for evaluating and optimizing network service quality. The network service quality evaluation method comprises the following steps: acquiring network state data detected by terminal equipment, and acquiring service experience data of a specified application program running on the terminal equipment; determining a network blockage index according to the network state data and a weight coefficient for evaluating the network blockage situation, and determining a service blockage index according to the service experience data; updating the weight coefficient according to the matching degree between the network stuck index and the service stuck index so as to enable the matching degree to reach a set value; and re-determining the network blockage index based on the updated weight coefficient, and evaluating the service quality of the specified application program according to the re-determined network blockage index. The technical scheme of the embodiment of the application is beneficial to improving the service experience of the appointed application program.

Description

Network service quality evaluation and optimization method, device, medium and electronic equipment

Technical Field

The present application relates to the field of computer and communication technologies, and in particular, to a method, an apparatus, a medium, and an electronic device for evaluating and optimizing network service quality.

Background

In the related art, a detection and monitoring index system for a telecommunication operator is generally specific to a base station of the whole operator, and the detection and monitoring index generally only represents the network quality of the dimension of the base station, but has the problems of insufficient sensing capability, lack of monitoring dimension and the like for specific services (such as services of real-time games, video playing and the like).

Disclosure of Invention

Embodiments of the present application provide a method, an apparatus, a medium, and an electronic device for evaluating and optimizing network service quality, so that the actual service quality of an application can be effectively measured at least to a certain extent, so as to take corresponding network optimization measures for the application.

Additional features and advantages of embodiments of the present application will be set forth in the detailed description which follows, or may be learned by practice of the application.

According to an aspect of an embodiment of the present application, a method for evaluating network service quality is provided, including: acquiring network state data detected by terminal equipment, and acquiring service experience data of a specified application program running on the terminal equipment; determining a network blockage index according to the network state data and a weight coefficient for evaluating the network blockage situation, and determining a service blockage index according to the service experience data; updating the weight coefficient according to the matching degree between the network stuck index and the service stuck index so as to enable the matching degree to reach a set value; and re-determining the network blockage index based on the updated weight coefficient, and evaluating the service quality of the specified application program according to the re-determined network blockage index.

According to an aspect of an embodiment of the present application, a method for optimizing network service quality is provided, including: detecting network state data of an environment where the terminal equipment is located and service experience data of a specified application program running on the terminal equipment; reporting the network state data and the service experience data to data processing equipment so that the data processing equipment can evaluate the service quality of the specified application program according to the network state data and the service experience data; acquiring service quality data aiming at the specified application program sent by the data processing equipment, and predicting the blocking condition of the specified application program according to the service quality data and the current network state data of the terminal equipment; and performing network optimization processing on the specified application program according to the pause condition.

According to an aspect of an embodiment of the present application, there is provided a network service quality assessment apparatus, including: the terminal equipment comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring network state data detected by the terminal equipment and acquiring service experience data of a specified application program running on the terminal equipment; the determining unit is used for determining a network blockage index according to the network state data and a weight coefficient for evaluating the network blockage situation, and determining a service blockage index according to the service experience data; the first processing unit is used for updating the weight coefficient according to the matching degree between the network blockage indexes and the service blockage indexes so as to enable the matching degree to reach a set value; and the second processing unit is used for re-determining the network blockage index based on the updated weight coefficient and evaluating the service quality of the specified application program according to the re-determined network blockage index.

In some embodiments of the present application, based on the foregoing scheme, the determining unit is configured to: determining the packet loss number, the total number of transmitted data frames and the number of data frames in each network speed measurement index interval of the specified application program within a preset time length according to the network state data; determining a weight coefficient corresponding to each network speed measurement index interval according to the corresponding relation between the weight coefficient and the network speed measurement index interval; and calculating the network blockage indexes based on the packet loss number, the total number of the data frames, the number of the data frames in each network speed measurement index interval and the weight corresponding to each network speed measurement index interval.

In some embodiments of the present application, based on the foregoing solution, the determining unit is configured to calculate the network stuck indicator by the following formula:

wherein qoe represents the network stuck indicator; s_iRepresenting the number of data frames in the ith network speed measurement index interval; q. q.s_iRepresenting the weight corresponding to the ith network speed measurement index interval; c₂Representing the number of lost packets; c₁Representing the total number of data frames.

In some embodiments of the present application, based on the foregoing solution, the first processing unit is configured to: determining the matching degree between the network blockage indexes and the service blockage indexes according to the network blockage indexes and the service blockage indexes; and adjusting the weight coefficient according to the matching degree, re-determining the network stuck index based on the adjusted weight coefficient, and re-adjusting the weight coefficient based on the re-determined network stuck index until the matching degree reaches the set value.

In some embodiments of the present application, based on the foregoing solution, the first processing unit is configured to: dividing to obtain a plurality of stuck index intervals according to the numerical distribution range of the network stuck index and the numerical distribution range of the business stuck index; and determining the matching degree of the network blockage indexes and the business blockage indexes in each blockage index interval according to the distribution condition of the network blockage indexes in each blockage index interval and the distribution condition of the business blockage indexes in each blockage index interval.

In some embodiments of the present application, based on the foregoing solution, the first processing unit is further configured to: and after the matching degree reaches the set value, periodically adjusting the weight coefficient according to the recalculated network blockage index and the service blockage index.

In some embodiments of the present application, based on the foregoing solution, the second processing unit is configured to: and generating service quality information of the network equipment aiming at the specified application program based on the redetermined network blockage indicator and the network state data detected by the terminal equipment so as to evaluate the service quality of the specified application program according to the service quality information.

In some embodiments of the present application, based on the foregoing scheme, the service quality information includes any one or more of the following combinations: the data distribution condition of the network device aiming at the service quality of the specified application program, the capacity density of the network device aiming at the specified application program, the bearing capacity of the network device aiming at the specified application program, the position of the network device, the coverage area of the network device and the classification attribute label of the network device.

In some embodiments of the present application, based on the foregoing solution, the network service quality assessment apparatus further includes: the statistical unit is used for counting the service quality data of the appointed application program at each time node; and the third processing unit is used for determining the congestion period of the network equipment aiming at the specified application program according to the service quality data of the specified application program at each time node, and/or predicting the service quality change condition of the specified application program.

According to an aspect of an embodiment of the present application, there is provided a network service quality optimization apparatus, including: the detection unit is used for detecting the network state data of the environment where the terminal equipment is located and the service experience data of the specified application program running on the terminal equipment; a reporting unit, configured to report the network state data and the service experience data to a data processing device, so that the data processing device evaluates the service quality of the designated application according to the network state data and the service experience data; the prediction processing unit is used for acquiring the service quality data aiming at the specified application program sent by the data processing equipment and predicting the blocking condition of the specified application program according to the service quality data and the current network state data of the terminal equipment; and the optimization processing unit is used for carrying out network optimization processing on the specified application program according to the blockage situation.

In some embodiments of the present application, based on the foregoing solution, the optimization processing unit is configured to: if the specified application program is determined to be in a non-stuck state currently and in a stuck state after a preset time length according to the stuck condition, establishing a special bearer for the specified application program; if the specified application program is determined to be in the stuck state currently and is in the non-stuck state after a preset time length according to the stuck condition, establishing a special bearer for the specified application program; and if the specified application program is determined to be in the stuck state currently and in the stuck state after a preset time length according to the stuck condition, executing network switching operation or establishing a special bearer for the specified application program.

According to an aspect of an embodiment of the present application, there is provided a computer-readable medium, on which a computer program is stored, which, when being executed by a processor, implements a network quality of service assessment method as described in the above embodiment, or implements a network quality of service optimization method as described in the above embodiment.

According to an aspect of an embodiment of the present application, there is provided an electronic device including: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement a network quality of service assessment method as described in the above embodiments, or a network quality of service optimization method as described in the above embodiments.

In the technical solutions provided in some embodiments of the present application, a network stuck index is determined according to network state data and a weight coefficient for evaluating a network stuck condition, a service stuck index is determined according to service experience data, and the weight coefficient is updated according to a matching degree between the network stuck index and the service stuck index, so that the matching degree between the network stuck index and the service stuck index reaches a set value, so that the weight coefficient can be updated according to the matching degree between the network stuck index and the service stuck index, and it is ensured that the network stuck index calculated according to the updated weight coefficient can be matched with an actual service stuck index, and further, the service quality of an application program can be evaluated through the network stuck index. Therefore, the technical scheme of the embodiment of the application realizes the association between the network state data and the service experience data, so that the actual service quality of the specified application program is effectively measured based on the network state data detected by the terminal device, and further, the corresponding network optimization measures are conveniently taken for the specified application program, and the service experience of the specified application program is favorably improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:

FIG. 1 illustrates an exemplary system architecture diagram to which aspects of embodiments of the present application may be applied;

FIG. 2 shows a flow diagram of a network quality of service assessment method according to an embodiment of the present application;

FIG. 3 illustrates a flow diagram for determining a network stuck indicator based on network status data and weight coefficients for evaluating a network stuck condition according to one embodiment of the present application;

FIG. 4 illustrates a flow chart for updating weighting coefficients based on a degree of match between a network stuck indicator and a traffic stuck indicator according to an embodiment of the present application;

FIG. 5 shows a flow diagram of a method of network quality of service optimization according to an embodiment of the present application;

FIG. 6 shows a block diagram of a network traffic system according to one embodiment of the present application;

FIG. 7 illustrates density profiles of network and game kation rates according to one embodiment of the present application;

FIG. 8 illustrates a bin statistical plot of network and game kation rates according to one embodiment of the present application;

FIG. 9 illustrates a graph of network morton rate versus game morton rate according to an embodiment of the present application;

FIG. 10 illustrates a thermodynamic diagram of base station traffic experience metrics according to one embodiment of the present application;

FIG. 11 shows a plot of base station stuck rate according to one embodiment of the present application;

FIG. 12 illustrates a stuck trend graph of a base station according to one embodiment of the present application;

FIG. 13 shows a flow diagram of a method of network optimization according to an embodiment of the present application;

FIG. 14 shows a block diagram of a quality of service assessment apparatus according to an embodiment of the present application;

FIG. 15 shows a block diagram of a quality of service optimization apparatus according to an embodiment of the present application;

FIG. 16 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

Fig. 1 shows an exemplary system architecture diagram to which the technical solution of the embodiments of the present application can be applied.

As shown in fig. 1, the system architecture 100 may include terminal devices (e.g., one or more of a smartphone 101, a tablet 102, and a portable computer 103 shown in fig. 1, or may also be a desktop computer, etc.), a network 104, and a server 105. The network 104 serves as a medium for providing communication links between terminal devices and the server 105. Network 104 may include various connection types, such as wired communication links, wireless communication links, and so forth.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, server 105 may be a server cluster comprised of multiple servers, or the like.

In an embodiment of the present application, the terminal device may detect network state data in a network environment, acquire service experience data of a specific application (such as a game application, a video application, and the like) running on the terminal device, and report the detected network state data and the acquired service experience data to the server 105.

In an embodiment of the present application, after acquiring the network state data and the service experience data reported by the terminal device, the server 105 may determine a network stuck index according to the network state data and a weight coefficient for evaluating a network stuck condition, and determine a service stuck index according to the service experience data. And then updating the weight coefficient according to the matching degree between the network blockage index and the service blockage index so that the matching degree between the network blockage index and the service blockage index reaches a set value, further re-determining the network blockage index based on the updated weight coefficient, and evaluating the service quality of the specified application program according to the re-determined network blockage index. Therefore, the technical scheme of the embodiment of the application can realize the association between the network state data and the service experience data, so that the actual service quality of the specified application program can be effectively measured based on the network state data detected by the terminal device, and further, the corresponding network optimization measures can be conveniently taken for the specified application program, and the service experience of the specified application program can be favorably improved.

The implementation details of the technical solution of the embodiment of the present application are set forth in detail below:

fig. 2 shows a flowchart of a network quality of service assessment method according to an embodiment of the present application, which may be performed by a server, which may be the server shown in fig. 1. Referring to fig. 2, the method for evaluating network service quality at least includes steps S210 to S240, which are described in detail as follows:

in step S210, network status data detected by the terminal device is obtained, and service experience data of a specific application running on the terminal device is obtained.

In an embodiment of the present application, the network state data detected by the terminal device may include SINR (Signal to Interference plus Noise Ratio), RSSI (Received Signal Strength Indication), RSRP (Reference Signal Receiving Power), RSRQ (Reference Signal Receiving Quality), frequency point, Physical Cell Identifier (PCI), Cell Identifier (CI), number of lost packets in a specific application, network speed measurement value, and the like.

In an embodiment of the present application, the service experience data of the specific application running on the terminal device may include FPS (Frames Per Second) of the specific application, network hop condition, network delay condition in the application, and the like.

In one embodiment of the present application, the specified application may be any application installed on the terminal device, such as a game application sensitive to time delay, a video application, an instant messaging application, and the like.

Continuing to refer to fig. 2, in step S220, a network stuck indicator is determined according to the network state data and the weight coefficient for evaluating the network stuck condition, and a service stuck indicator is determined according to the service experience data.

In an embodiment of the present application, as shown in fig. 3, the process of determining the network stuck indicator according to the network status data and the weight coefficient for evaluating the network stuck condition in step S220 may include the following steps S310 to S330, which are described in detail as follows:

in step S310, the packet loss number, the total number of transmitted data frames, and the number of data frames in each network speed measurement indicator interval of the designated application program within the predetermined time period are determined according to the network status data.

In an embodiment of the present application, a plurality of network speed measurement index intervals may be divided in advance, as shown in table 1, for example, 5 network speed measurement index intervals may be divided, where each network speed measurement index interval corresponds to a different network speed measurement delay.

Network speed measurement index interval 1	0-150 milliseconds
		Network speed measurement index interval 2	150-
Network speed measurement index interval 3	200-
		Network speed measurement index interval 4	300- & lt460 & gtmilliseconds
Network speed measurement index interval 5	Greater than 460 milliseconds

TABLE 1

In an embodiment of the application, the terminal device may perform network speed measurement for a plurality of times for a specific application within a predetermined time, for example, perform speed measurement according to a predetermined period (for example, the period is 1 second, 5 seconds, and the like), determine an interval in which a network speed measurement index obtained by performing speed measurement each time is located, and further may count the number of data frames located in each network speed measurement index interval.

In one embodiment of the present application, the designated application may be a real-time hand game application, and the predetermined duration may be a duration of one game, that is, the total number of lost packets, the total number of transmitted data frames, and the number of data frames in each network speed measurement indicator interval are counted in each game.

In step S320, determining a weight coefficient corresponding to each network speed measurement index interval according to a corresponding relationship between the weight coefficient and the network speed measurement index interval.

In an embodiment of the application, at an initial stage, a corresponding relationship between the network speed measurement indicator interval and the weight coefficient may be preset, and then the weight coefficient corresponding to each network speed measurement indicator interval may be determined based on the corresponding relationship. For example, for the interval division shown in table 1, the weight coefficient corresponding to the network speed measurement indicator interval 1 may be 0, the weight coefficient corresponding to the network speed measurement indicator interval 2 may be 0.2, the weight coefficient corresponding to the network speed measurement indicator interval 3 may be 0.7, the weight coefficient corresponding to the network speed measurement indicator interval 4 may be 0.9, and the weight coefficient corresponding to the network speed measurement indicator interval 5 may be 1.0.

In step S330, the network stuck indicator is calculated based on the number of lost packets, the total number of data frames, the number of data frames in each network speed measurement indicator interval, and the weight corresponding to each network speed measurement indicator interval.

In the embodiment of the application, because the packet loss number and the network speed measurement index have an association relationship with the network stuck condition, the network stuck index can be calculated according to the packet loss number, the total number of data frames, the number of data frames in each network speed measurement index interval and the weight corresponding to each network speed measurement index interval.

In one embodiment of the present application, the network stuck indicator may be calculated by the following formula:

wherein qoe represents the network stuck indicator; s_iRepresenting the number of data frames in the ith network speed measurement index interval; q. q.s_iRepresenting the weight corresponding to the ith network speed measurement index interval; c₂Indicating the aforementioned number of lost packets; c₁Representing the aforementioned total number of data frames.

In one embodiment of the present application, the network stuck indicator may represent a stuck condition of the network, for example, if the network stuck indicator qoe is greater than or equal to 3%, it represents network stuck.

In an embodiment of the application, determining the service stuck indicator according to the service experience data may be to quantize and statistically analyze the service experience data, for example, may quantize and normalize service experience data, such as FPS of a specified application, network hopping condition, and network delay condition in the application, to the same evaluation latitude, and then perform weighted summation processing according to a weight of each service experience data to obtain the service stuck indicator.

Continuing to refer to fig. 2, in step S230, the weighting factor is updated according to the matching degree between the network stuck indicator and the traffic stuck indicator, so that the matching degree reaches a set value.

In an embodiment of the present application, as shown in fig. 4, the step S230 of updating the weight coefficient according to the matching degree between the network stuck indicator and the traffic stuck indicator so that the matching degree reaches the set value may include:

step S410, according to the network stuck index and the service stuck index, determining the matching degree between the network stuck index and the service stuck index.

In one embodiment of the present application, the matching degree between the network stuck indicator and the traffic stuck indicator represents the degree of similarity between the network stuck indicator and the traffic stuck indicator at the same time. For example, if the network stuck indicator and the service stuck indicator are numerical values, the matching degree between the two indicators may be a difference value between the two indicators, and a smaller difference value indicates a higher matching degree between the two indicators.

In an embodiment of the present application, a plurality of stuck index intervals may be obtained by dividing according to a numerical distribution range of a network stuck index and a numerical distribution range of a service stuck index, and then a matching degree of the network stuck index and the service stuck index in each stuck index interval may be determined according to a distribution condition of the network stuck index in each stuck index interval and a distribution condition of the service stuck index in each stuck index interval. The technical scheme of the embodiment can evaluate the matching degree between the network stuck index and the service stuck index in a fine-grained manner, further more accurately determine the correlation between the network stuck index and the service stuck index, and simultaneously facilitate the accurate adjustment of the weight coefficient according to the matching degree of the network stuck index and the service stuck index in each stuck index interval.

Step S420, adjusting the weight coefficient according to the matching degree, re-determining the network stuck index based on the adjusted weight coefficient, and re-adjusting the weight coefficient based on the re-determined network stuck index until the matching degree reaches the set value.

In the embodiment shown in fig. 4, the process of adjusting the weight coefficient may be a cyclic process, that is, determining a matching degree between the network stuck indicator and the service stuck indicator according to the calculated network stuck indicator and the service stuck indicator, then adjusting the weight coefficient according to the matching degree, recalculating the network stuck indicator according to the adjusted weight coefficient, recalculating the matching degree between the network stuck indicator and the service stuck indicator according to the recalculated network stuck indicator, and adjusting the weight coefficient … … again until the matching degree between the network stuck indicator and the service stuck indicator reaches a set value. The technical scheme of the embodiment can ensure that the network blockage index can be matched with the service blockage index by repeatedly adjusting the weight coefficient, and further can realize the association between the network state data and the service experience data so as to effectively measure the actual service quality of the specified application program based on the network state data detected by the terminal equipment.

In an embodiment of the present application, after the matching degree between the network stuck indicator and the service stuck indicator reaches a set value, the weight coefficient may be periodically adjusted according to the recalculated network stuck indicator and the service stuck indicator, so as to ensure that the calculated weight coefficient can adapt to the change of the network environment. For example, after the matching degree between the network stuck indicator and the traffic stuck indicator reaches the set value by adjusting the weight coefficient, if the network environment changes (for example, the network device is upgraded, the number of network devices is increased, etc.), the matching degree between the network stuck indicator and the actual traffic stuck indicator is reduced due to the weight coefficient calculated according to the previous network environment, and therefore, the weight coefficient can be periodically (for example, the period can be 1 week, 1 month, 1 quarter, etc.) adjusted according to the recalculated network stuck indicator and the traffic stuck indicator.

Continuing to refer to fig. 2, in step S240, the network stuck indicator is re-determined based on the updated weighting factor, and the service quality of the specified application program is evaluated according to the re-determined network stuck indicator.

In the embodiment of the application, the weight coefficient is updated, so that the network stuck index can be matched with the service stuck index, and further the service stuck index can be indirectly determined through the network stuck index, and therefore the service quality of the specified application program can be evaluated according to the newly determined network stuck index. For example, if the designated application is a real-time game application, the quality of service of the real-time game application in a certain geographic area (e.g., a certain base station coverage area or areas, a certain city area, etc.) may be evaluated.

In an embodiment of the present application, the process of evaluating the service quality of the specific application according to the re-determined network stuck indicator in step S240 may include: and generating the service quality information of the network equipment aiming at the specified application program based on the redetermined network blockage indicator and the network state data detected by the terminal equipment so as to evaluate the service quality of the specified application program according to the service quality information.

In one embodiment of the present application, the quality of service information may include any combination of one or more of the following: data distribution of the network device for the service quality of the specified application, capacity density of the network device for the specified application, carrying capacity of the network device for the specified application, location of the network device, coverage of the network device, and classification attribute label of the network device.

In one embodiment of the present application, the network device may be a base station, and the data distribution of the network device for the service quality of the specified application may be a data distribution graph (such as a thermodynamic diagram) of the base station for the service quality of the specified application; the capacity density of the network device for a given application may be the number of given applications running under each base station; the bearing capacity of the network equipment for the specified application program can be the maximum number of the specified application programs running under each base station on the premise of ensuring that the specified application programs have better service quality; the location of the network device may be deployment location information of the base stations, such as showing deployment locations of the respective base stations in the form of a map; the coverage of the network device may be the network coverage of each base station; the class attribute tag of the network device may be a class tag determined according to the environment in which the base station is located, for example, the tag may be a school, an office area, a business area, a public venue, and the like.

In an embodiment of the present application, the service quality data of the specified application program at each time node may also be counted; and further, according to the service quality data of the specified application program at each time node, determining the congestion period of the network equipment for the specified application program, and/or predicting the service quality change condition of the specified application program.

In one embodiment of the present application, the congestion period of the network device for a given application may be a period during which each base station is stuck for the given application; predicting a change in quality of service for a given application may be predicting a stuck condition of the application for a future period of time. According to the technical scheme of the embodiment, the congestion period of the network equipment for the specified application program is determined, and/or the service quality change condition of the specified application program is predicted, so that the network of the specified application program can be optimized in time according to the congestion period and/or the predicted service quality change condition of the specified application program, and the specified application program is ensured to have better service quality.

Fig. 5 shows a flowchart of a network service quality optimization method according to an embodiment of the present application, which may be executed by a terminal device, and the server may be the terminal device shown in fig. 1 (e.g., the smart phone 101, the tablet computer 102, and the portable computer 103). Referring to fig. 5, the method for optimizing network service quality at least includes steps S510 to S540, which are described in detail as follows:

in step S510, network status data of an environment where the terminal device is located and service experience data of a specific application running on the terminal device are detected.

In an embodiment of the present application, the network state data for detecting the environment where the terminal device is located may include SINR, RSSI, RSRP, RSRQ, frequency point, physical cell identification code, cell unique identifier, number of lost packets in a specified application, network speed measurement value, and the like. The service experience data of the designated application running on the terminal device may include an FPS of the designated application, a network hopping condition, a network delay condition within the application, and the like. The designated application may be any application installed on the terminal device, such as a game application, a video application, an instant messaging application, and the like.

In step S520, the network state data and the service experience data are reported to a data processing device, so that the data processing device evaluates the service quality of the designated application according to the network state data and the service experience data.

In one embodiment of the present application, the data processing apparatus may be an apparatus having a calculation processing function, such as a server. The process of the data processing device evaluating the service quality of the specified application according to the network state data and the service experience data may refer to the technical solutions of the foregoing embodiments.

In step S530, the service quality data for the specified application program sent by the data processing device is obtained, and the stuck condition of the specified application program is predicted according to the service quality data and the current network state data of the terminal device.

In an embodiment of the application, the service quality data for the specified application sent by the data processing device may include a data distribution situation of the network device for the service quality of the specified application, and then the terminal device may determine information of the network device connected to the terminal device according to the current network state data, and predict a stuck situation of the specified application based on the data distribution situation of the network device connected to the terminal device for the service quality of the specified application.

In one embodiment of the present application, the quality of service data sent by the data processing device for the specific application may include a congestion period of the network device for the specific application, and then the terminal device may determine whether the specific application running on the terminal device reaches the congestion period according to the current network state data and the congestion period, and predict the stuck condition of the specific application.

In an embodiment of the application, the data processing device may further train the machine learning model according to the network state data of the environment where the terminal device is located and the service experience data of the specified application program running on the terminal device, and predict a stuck condition of the specified application program based on the machine learning model obtained after training and the network state data detected by the terminal device.

In one embodiment of the present application, the stuck condition of the specified application may include a current stuck condition and a stuck condition for a subsequent period of time of the specified application. For example, if the designated application is a real-time game application, the current game pause condition and the next game pause condition of the real-time game application can be predicted.

Continuing to refer to fig. 5, in step S540, the designated application is subjected to network optimization according to the hiton condition.

In an embodiment of the present application, the process of performing the network optimization processing on the specified application program according to the hiton condition in step S540 may be: if the specified application program is determined to be in a non-stuck state at present and in a stuck state after a preset time length according to the stuck condition, establishing a special bearer for the specified application program so as to ensure the service quality of the specified application program after the preset time length by establishing the special bearer in advance. For example, for a real-time game application, if it is determined that the current game is stuck but the next game is not stuck, a dedicated bearer may be established in advance for performing a network optimization process, so as to ensure that the next game is not stuck.

In an embodiment of the present application, the process of performing the network optimization processing on the specified application program according to the hiton condition in step S540 may be: and if the specified application program is determined to be in the stuck state currently and is in the non-stuck state after the preset time length according to the stuck condition, establishing a special bearing for the specified application program. The dedicated bearer established in this embodiment may be established quickly, so as to optimize the network quality of the specified application as soon as possible and ensure the current service quality of the specified application.

In an embodiment of the present application, the process of performing the network optimization processing on the specified application program according to the hiton condition in step S540 may be: and if the specified application program is determined to be in the stuck state currently and in the stuck state after a preset time length according to the stuck condition, executing network switching operation or establishing a special bearer for the specified application program. In the embodiment, when the specified application program is determined to be in the stuck state at present and is also in the stuck state after the preset time, the network switching operation is executed, so that the specified application program can be switched to other networks with better network quality as soon as possible to ensure the service quality of the specified application program; and when the specified application program is determined to be in the stuck state at present and is also in the stuck state after the preset time, establishing a special bearer for the specified application program, so that the service quality of the specified application program can be ensured.

The technical solution of the embodiment of the present application is described in detail below by taking an example in which a specific application is a game application:

in an embodiment of the present application, as shown in fig. 6, a network service system according to an embodiment of the present application may include: the system comprises a base station detection module 601, a network optimization active intervention module 602, a cloud control module 603, a base station quality big data background module 604 and the like.

In an embodiment of the present application, the base station detection module 601 is mainly responsible for detecting relevant information of a registered cell base station and a neighboring cell base station in a network environment where the mobile terminal is located, detecting information of the mobile terminal and a network speed measurement result of the mobile terminal, and uploading detected relevant data to the base station quality big data background module 604 for analysis. The base station quality big data background module 604 is configured to parse base station feature data related to service experience according to data reported by the base station detection module 601, perform base station portrayal and experience quality measurement, and finally generate multi-dimensional description details of cell base station granularity. The network optimization active intervention module 602 performs comprehensive evaluation by actively detecting and sensing the current field intensity index of the game client under the condition of following 3GPP protocol specifications and combining with the experience Quality data of the game Service at the base station (the data is acquired from the base station Quality big data background module 604 by the cloud control module 603 and is sent to the network optimization active intervention module 602), and further determines whether a QOS (Quality of Service) real-time game specific bearer is established between the terminal and the base station, so as to realize network optimization processing of the game Service.

The following description is made for the implementation details of each module:

the data collected and reported by the base station detection module 601 is shown in table 2, and mainly includes mobile terminal information, base station information, and network speed measurement information. The mobile terminal information may include: an operating system (such as an android, saiban, IOS operating system, etc.), a hardware platform (i.e., a base frequency adopted by the mobile terminal), a model, geographic coordinates, signal strength, etc.

The base station information may include: the base station comprises a base station cell ID, SINR, RSSI, RSRP, RSRQ, a frequency point, a physical cell identification code, a cell unique identifier and the like.

The network speed measurement information may include: detailed data directly connected in a game client starting stage, detailed data forwarded in the game client starting stage, network jump data in a game, speed measurement time delay in the game and the like.

TABLE 2

In an embodiment of the present application, the base station detection module 601 may be a client SDK (Software Development Kit) running on the mobile terminal, and the client SDK may report the detected data to the base station quality big data background module 604 in a form of log when the game is over, and then the base station quality big data background module 604 performs cleaning and data normalization processing on different types of data (time, speed measurement sequence log, type) through different preprocessing techniques, and finally stores the obtained feature data in a database, for example, in a HDFS (Hadoop Distributed File System) cluster.

In an embodiment of the present application, the data reported by the base station probing module 601 may include the following data types: numerical sequence class data, category type data, numerical type data.

In one embodiment of the present application, the numerical sequence class data may include: speed-measuring link ping delay, speed-up link ping delay, ping delay to CDN (Content Delivery Network), and delay to Air Interface (Air Interface). Among other things, the preprocessing for such data may be to split it into statistical index descriptions such as variance, standard deviation, mean, maximum, minimum, sequence length, and so on.

In one embodiment of the present application, the classification data may include: signal strength, channel id, base station id, operating system information (such as operating system name, operating system version, etc.), base station frequency point, physical cell identification code, cell unique identifier, etc. Where such data may be pre-processed in the form of a list for convenient analysis.

In one embodiment of the present application, the numerical data may include: RSRP, RSRQ, RSSI, SINR, packet loss rate, in-game speed measurement delay and the like. Among other things, the preprocessing for such data may be to split it into statistical index descriptions such as variance, standard deviation, mean, maximum, minimum, and so on.

The base station quality big data background module 604 is configured to determine base station communication field strength information and service experience data according to the data reported by the base station detection module 601, and further perform comprehensive analysis based on the base station communication field strength information and the service experience data to determine a base station service experience portrait.

In one embodiment of the present application, the base station communication field strength information may include, for example: RSRP, RSRQ, RSSI, SINR, packet loss rate, network speed measurement delay, base station id and the like. The business experience data may include, for example: the number of games, jump, FPS, game play delay, game play duration, etc.

In an embodiment of the application, in order to correlate the base station field intensity data with the service experience data, the morton rate may be calculated as a service experience measurement standard, for example, a result of network speed measurement in a game may be quantized to obtain a network morton rate, a game morton rate may be quantized to obtain a game morton rate, and then fitting analysis may be performed on the network morton rate and the game morton rate to achieve a purpose of approximately describing the game morton rate by using a common network morton rate.

In an embodiment of the present application, the network speed measurement result in the game may be segmented, where each segment is a speed measurement result interval, and each speed measurement result interval corresponds to a katon weight, and then the network katon rate may be expressed as:

the network stuck rate (sum (the number of frames in each speed measurement result interval, x the stuck weight) + the number of lost packets)/the total number of frames.

In an embodiment of the present application, the traffic hiton rate may be obtained by performing quantization processing on traffic delay in a game, FPS of a game client, network hopping condition, and the like.

In an embodiment of the application, the katon weight corresponding to each speed measurement result interval may be preset in an initial condition, and may be adjusted according to the network katon rate and the game katon rate obtained by calculation, where the specific process is as follows:

in an embodiment of the present application, as shown in fig. 7, the network morton rate and the game morton rate calculated according to the related data of the multiple games reported by the multiple terminals are generated in the same coordinate system, so as to obtain the density distribution maps of the network morton rate and the game morton rate. As can be seen from FIG. 7, the network and game morton rates have a relatively high overlap ratio within a certain morton rate range (e.g., between 0-0.2 as shown in FIG. 7), which is shown to be relatively dense in FIG. 7; in other stuck rate ranges, the network stuck rate and the game stuck rate have a lower degree of overlap, and are shown more sparsely in fig. 7.

In one embodiment of the present application, as shown in fig. 8, the katon rate value can be divided into 5 intervals (the number of intervals is only an example), each interval represents one kind of katon level (i.e. 1-5 grades of katon), and the piecewise overlap ratio analysis is performed according to the intervals. As shown in fig. 8, the ordinate represents the number of samples of the katton rate, which may be in units of hundred million, ten thousand, or the like. In section 1, 801 represents the number of samples for which the network katon rate is greater than the game katon rate; in interval 2, 802 represents the number of samples for which the network katon rate is greater than the game katon rate; in section 3, 803 indicates the number of samples for which the network katon rate is greater than the game katon rate; in interval 4, 804 represents the number of samples for which the game kation rate is greater than the network kation rate; in interval 5, 805 represents the number of samples for which the game jam rate is greater than the network jam rate.

In one embodiment of the present application, based on the distribution of the network morton rate and the game morton rate in each section shown in fig. 8, the morton weight may be adjusted so that the distribution of the network morton rate and the game morton rate in each section is as identical as possible. The katon weight shown in table 3 can be obtained, for example, by fitting the network katon rate and the game katon rate:

speed measurement result interval (taking network delay index as an example)	Katton weight
		Delay 0-150 milliseconds	0
Delay 150-	0.2
		Delay 200-	0.7
Delay 300-	0.9
		Delay time greater than 460 milliseconds	1

TABLE 3

In an embodiment of the present application, after the katon weight is adjusted, the network katon rate can be recalculated by the adjusted katon weight, and the katon weight can be adjusted again by the adjustment scheme of the foregoing embodiment until the calculated network katon rate matches the distribution of the game katon rate in each interval.

In one embodiment of the application, after the network morton rate is matched with the distribution situation of the game morton rate in each interval by adjusting the morton weight, the game morton rate can be approximately described through the network morton rate, and the overlap ratio with the actual experience of the service is higher in most scenes. For example, in the coordinate system shown in fig. 9, the abscissa represents the game jam rate, the ordinate represents the network jam rate, and each point in the coordinate system represents a sample (for example, the network jam rate and the game jam rate of one game are taken as one sample). It can be seen that, by adjusting the mortgage rate, each point formed by the network mortgage rate and the game mortgage rate is located on the straight line 901 or near the straight line 901, and then the game mortgage rate can be approximately described by the network mortgage rate.

In one embodiment of the present application, after the network morton rate can be approximately described by adjusting the morton weight, the game service experience image of the base station can be established based on the value of the network morton rate. For example, the following capability system of the base station may be established according to data (such as field strength of the base station, packet loss rate, network delay information, and the like) reported by a plurality of terminal devices:

firstly, a service experience index system of a base station of a whole network operator;

base station location, capacity density, carrying capacity, coverage, category attribute tags (such as schools, offices, business districts, public venues, etc.);

and thirdly, predicting the congestion period of the base station, the tide time of the jamming condition of the base station and the like.

For example, in an embodiment of the present application, as shown in fig. 10, a hot spot area of the game service may be shown on a map in the form of a thermodynamic diagram, for example, a darker area (e.g., area 1001) indicates that there are a greater number of terminals in the game service in the area; or a morton area of game play may be presented on the map in the form of a thermodynamic diagram, e.g. a darker area (e.g. area 1001) indicates that game play in that area compares the morton.

For another example, in an embodiment of the present application, as shown in fig. 11, the network seizure rates of multiple time periods may be counted, and the seizure rate trend may be drawn according to the network seizure rates of multiple time periods to obtain a trend graph of the base station seizure rate, so as to determine the congestion period of the base station according to the trend graph, or predict the seizure tidal time of the base station.

For another example, in an embodiment of the present application, as shown in fig. 12, a seizure trend of the base station may be plotted according to the network seizure rates of the plurality of periods obtained through statistics, and then a congestion period of the base station may be determined according to the trend graph, or a seizure tidal time of the base station may be predicted.

In an embodiment of the present application, the network optimization active intervention module 602 may calculate, based on rich base station image data (high-precision geographical location information, service experience quality data, tidal time prediction information, congestion period prediction information, and the like), a blocking condition of a game service accurately identified depending on mass data, so as to take a network optimization intervention measure. For example, as shown in fig. 13, the processing procedure of the network optimization proactive intervention module 602 may include the following steps:

step S1301, the client SDK collects real-time network status data and obtains data issued by the cloud control module.

In an embodiment of the present application, as shown in fig. 6, the client SDK in the network optimization active intervention module 602 may obtain the data issued by the cloud control module 603 in step S611, and obtain the real-time network status data in step S612.

In one embodiment of the present application, the network status data may include base station communication field strength information, and the like. The data sent by the cloud control module may include service experience quality data of the base station, tidal time prediction information, congestion period prediction information, and the like.

In an embodiment of the application, the cloud control module may further train the machine learning model through network state data and game service experience data reported by the client SDK to obtain a model for predicting a game application stuck condition, and then data sent by the cloud control module and acquired by the client SDK may further include parameter information of the model, so as to predict the stuck condition of the game application according to the parameter information of the model. Alternatively, the machine learning model may be a logistic regression model.

In step S1302, the client SDK predicts a network hang-up condition according to the real-time network status data and the data issued by the cloud control module.

In an embodiment of the application, for example, the client SDK may determine whether the network reaches the congestion period according to the real-time network state data and the congestion period prediction information sent by the cloud control module, and further predict the network congestion condition.

In an embodiment of the application, the client SDK may also predict a stuck condition of the game application according to the model parameter issued by the cloud control module. And when the cloud control module determines that the parameters of the model change, the changed model parameters can be transmitted to the client side SDK, so that the client side SDK can process the parameters based on the latest model parameters.

Step S1303, a network stuck condition prediction result is obtained.

In one embodiment of the present application, a network stuck condition may include a current stuck condition and a stuck condition for a subsequent period of time. Such as the current game's katton situation and the next game's katton situation.

And step S1304, performing network optimization processing according to the network blockage situation prediction result.

In an embodiment of the present application, as shown in fig. 6, the terminal device in the network optimization active intervention module 602 may invoke the prediction result of the client SDK to perform the network optimization processing through step S613.

In one embodiment of the present application, the network optimization process may include optimization measures such as network handover (e.g., handover from a mobile network to Wi-Fi, handover between base stations, etc.), and QOS dedicated bearer activation, so as to reasonably schedule base station bearer resources. For example, if it is determined that the current game is stuck but the next game is not stuck, a dedicated bearer may be established in advance for performing network optimization processing to ensure that the next game is not stuck; if it is determined that the current game is stuck and the next game is stuck, the network can be switched to other networks with better network quality.

The above embodiment has been described with the game application as an example, and in other embodiments of the present application, the specified application may also be a video application, an instant messaging application, and the like.

According to the technical scheme, the client can adapt to complex and changeable network environments flexibly, the blocking classification result of the service experience quality of the application program in the base station can be predicted accurately, then network optimization measures can be taken timely, the application with high time delay requirements is guaranteed to have excellent network quality, and the use experience of users is effectively improved.

The following describes an embodiment of an apparatus of the present application, which may be used to perform a network service quality evaluation method or a network service quality optimization method in the foregoing embodiments of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method described above in the present application.

Fig. 14 shows a block diagram of a quality of service evaluation apparatus according to an embodiment of the present application.

Referring to fig. 14, a service quality assessment apparatus 1400 according to an embodiment of the present application includes: an acquisition unit 1402, a determination unit 1404, a first processing unit 1406 and a second processing unit 1408.

The obtaining unit 1402 is configured to obtain network state data detected by a terminal device, and obtain service experience data of a specific application running on the terminal device; the determining unit 1404 is configured to determine a network seizure indicator according to the network state data and a weight coefficient for evaluating a network seizure condition, and determine a service seizure indicator according to the service experience data; the first processing unit 1406 is configured to update the weight coefficient according to a matching degree between the network stuck indicator and the traffic stuck indicator, so that the matching degree reaches a set value; the second processing unit 1408 is configured to re-determine the network stuck indicator based on the updated weighting factor and evaluate the quality of service of the specified application according to the re-determined network stuck indicator.

In some embodiments of the present application, the determining unit 1404 is configured to: determining the packet loss number, the total number of transmitted data frames and the number of data frames in each network speed measurement index interval of the specified application program within a preset time length according to the network state data; determining a weight coefficient corresponding to each network speed measurement index interval according to the corresponding relation between the weight coefficient and the network speed measurement index interval; and calculating the network blockage indexes based on the packet loss number, the total number of the data frames, the number of the data frames in each network speed measurement index interval and the weight corresponding to each network speed measurement index interval.

In some embodiments of the present application, the determining unit 1404 is configured to calculate the network stuck indicator by the following formula:

In some embodiments of the present application, the first processing unit 1406 is configured to: determining the matching degree between the network blockage indexes and the service blockage indexes according to the network blockage indexes and the service blockage indexes; and adjusting the weight coefficient according to the matching degree, re-determining the network stuck index based on the adjusted weight coefficient, and re-adjusting the weight coefficient based on the re-determined network stuck index until the matching degree reaches the set value.

In some embodiments of the present application, the first processing unit 1406 is configured to: dividing to obtain a plurality of stuck index intervals according to the numerical distribution range of the network stuck index and the numerical distribution range of the business stuck index; and determining the matching degree of the network blockage indexes and the business blockage indexes in each blockage index interval according to the distribution condition of the network blockage indexes in each blockage index interval and the distribution condition of the business blockage indexes in each blockage index interval.

In some embodiments of the present application, the first processing unit 1406 is configured to: and after the matching degree reaches the set value, periodically adjusting the weight coefficient according to the recalculated network blockage index and the service blockage index.

In some embodiments of the present application, the second processing unit 1408 is configured to: and generating service quality information of the network equipment aiming at the specified application program based on the redetermined network blockage indicator and the network state data detected by the terminal equipment so as to evaluate the service quality of the specified application program according to the service quality information.

In some embodiments of the present application, the quality of service information comprises a combination of any one or more of: the data distribution condition of the network device aiming at the service quality of the specified application program, the capacity density of the network device aiming at the specified application program, the bearing capacity of the network device aiming at the specified application program, the position of the network device, the coverage area of the network device and the classification attribute label of the network device.

In some embodiments of the present application, the network quality of service evaluation apparatus 1400 further includes: the statistical unit is used for counting the service quality data of the appointed application program at each time node; and the third processing unit is used for determining the congestion period of the network equipment aiming at the specified application program according to the service quality data of the specified application program at each time node, and/or predicting the service quality change condition of the specified application program.

Fig. 15 shows a block diagram of a quality of service optimization apparatus according to an embodiment of the present application.

Referring to fig. 15, a quality of service optimization apparatus 1500 according to an embodiment of the present application includes: a detection unit 1502, a reporting unit 1504, a prediction processing unit 1506, and an optimization processing unit 1508.

The detecting unit 1502 is configured to detect network state data of an environment where the terminal device is located and service experience data of a specific application running on the terminal device; the reporting unit 1504 is configured to report the network state data and the service experience data to a data processing device, so that the data processing device evaluates the service quality of the designated application according to the network state data and the service experience data; the prediction processing unit 1506 is configured to obtain quality of service data, which is sent by the data processing device and is for the specified application program, and predict a stuck condition of the specified application program according to the quality of service data and current network state data of the terminal device; the optimization processing unit 1508 is configured to perform network optimization processing on the specified application according to the hiton condition.

In some embodiments of the present application, the optimization processing unit 1508 is configured to: if the specified application program is determined to be in a non-stuck state currently and in a stuck state after a preset time length according to the stuck condition, establishing a special bearer for the specified application program; if the specified application program is determined to be in the stuck state currently and is in the non-stuck state after a preset time length according to the stuck condition, establishing a special bearer for the specified application program; and if the specified application program is determined to be in the stuck state currently and in the stuck state after a preset time length according to the stuck condition, executing network switching operation or establishing a special bearer for the specified application program.

It should be noted that the computer system 1600 of the electronic device shown in fig. 16 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 16, computer system 1600 includes a Central Processing Unit (CPU)1601, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 1602 or a program loaded from a storage portion 1608 into a Random Access Memory (RAM) 1603. In the RAM 1603, various programs and data necessary for system operation are also stored. The CPU 1601, ROM 1602, and RAM 1603 are connected to each other via a bus 1604. An Input/Output (I/O) interface 1605 is also connected to the bus 1604.

The following components are connected to the I/O interface 1605: an input portion 1606 including a keyboard, a mouse, and the like; an output section 1607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage portion 1608 including a hard disk and the like; and a communication section 1609 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 1609 performs communication processing via a network such as the internet. The driver 1610 is also connected to the I/O interface 1605 as needed. A removable medium 1611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1610 as necessary, so that a computer program read out therefrom is mounted in the storage portion 1608 as necessary.

In particular, according to embodiments of the present application, the processes described below with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 1609, and/or installed from the removable media 1611. When the computer program is executed by a Central Processing Unit (CPU)1601, various functions defined in the system of the present application are executed.

It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by an electronic device, cause the electronic device to implement the method described in the above embodiments.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A method for evaluating network service quality is characterized by comprising the following steps:

acquiring network state data detected by terminal equipment, and acquiring service experience data of a specified application program running on the terminal equipment;

determining a network blockage index according to the network state data and a weight coefficient for evaluating the network blockage situation, and determining a service blockage index according to the service experience data;

updating the weight coefficient according to the matching degree between the network stuck index and the service stuck index so as to enable the matching degree to reach a set value;

and re-determining the network blockage index based on the updated weight coefficient, and evaluating the service quality of the specified application program according to the re-determined network blockage index.

2. The method of claim 1, wherein determining a network stuck indicator according to the network status data and a weight coefficient for evaluating a network stuck condition comprises:

determining the packet loss number, the total number of transmitted data frames and the number of data frames in each network speed measurement index interval of the specified application program within a preset time length according to the network state data;

determining a weight coefficient corresponding to each network speed measurement index interval according to the corresponding relation between the weight coefficient and the network speed measurement index interval;

and calculating the network blockage indexes based on the packet loss number, the total number of the data frames, the number of the data frames in each network speed measurement index interval and the weight corresponding to each network speed measurement index interval.

3. The method according to claim 2, wherein the network stuck indicator is calculated based on the number of lost packets, the total number of data frames, the number of data frames in each network speed measurement indicator interval, and the weight corresponding to each network speed measurement indicator interval by using the following formula:

4. The method of claim 1, wherein updating the weighting factor according to a matching degree between the network stuck indicator and the traffic stuck indicator so that the matching degree reaches a set value comprises:

determining the matching degree between the network blockage indexes and the service blockage indexes according to the network blockage indexes and the service blockage indexes;

and adjusting the weight coefficient according to the matching degree, re-determining the network stuck index based on the adjusted weight coefficient, and re-adjusting the weight coefficient based on the re-determined network stuck index until the matching degree reaches the set value.

5. The method of claim 4, wherein determining a matching degree between the network stuck indicator and the traffic stuck indicator according to the network stuck indicator and the traffic stuck indicator comprises:

dividing to obtain a plurality of stuck index intervals according to the numerical distribution range of the network stuck index and the numerical distribution range of the business stuck index;

and determining the matching degree of the network blockage indexes and the business blockage indexes in each blockage index interval according to the distribution condition of the network blockage indexes in each blockage index interval and the distribution condition of the business blockage indexes in each blockage index interval.

6. The method of claim 1, further comprising:

and after the matching degree reaches the set value, periodically adjusting the weight coefficient according to the recalculated network blockage index and the service blockage index.

7. The method of any of claims 1 to 6, wherein the evaluating the service quality of the specified application according to the re-determined network stuck indicator comprises:

and generating service quality information of the network equipment aiming at the specified application program based on the redetermined network blockage indicator and the network state data detected by the terminal equipment so as to evaluate the service quality of the specified application program according to the service quality information.

8. The method of claim 7, wherein the QoS information comprises any one or more of the following:

the data distribution condition of the network device aiming at the service quality of the specified application program, the capacity density of the network device aiming at the specified application program, the bearing capacity of the network device aiming at the specified application program, the position of the network device, the coverage area of the network device and the classification attribute label of the network device.

9. The method of any of claims 1 to 6, further comprising:

counting the service quality data of the appointed application program at each time node;

and determining the congestion period of the network equipment aiming at the specified application program according to the service quality data of the specified application program at each time node, and/or predicting the service quality change condition of the specified application program.

10. A method for optimizing network service quality is characterized by comprising the following steps:

detecting network state data of an environment where the terminal equipment is located and service experience data of a specified application program running on the terminal equipment;

reporting the network state data and the service experience data to data processing equipment so that the data processing equipment can evaluate the service quality of the specified application program according to the network state data and the service experience data;

acquiring service quality data aiming at the specified application program sent by the data processing equipment, and predicting the blocking condition of the specified application program according to the service quality data and the current network state data of the terminal equipment;

and performing network optimization processing on the specified application program according to the pause condition.

11. The method of claim 10, wherein performing network optimization on the specified application according to the stuck condition comprises:

if the specified application program is determined to be in a non-stuck state currently and in a stuck state after a preset time length according to the stuck condition, establishing a special bearer for the specified application program;

if the specified application program is determined to be in the stuck state currently and is in the non-stuck state after a preset time length according to the stuck condition, establishing a special bearer for the specified application program;

and if the specified application program is determined to be in the stuck state currently and in the stuck state after a preset time length according to the stuck condition, executing network switching operation or establishing a special bearer for the specified application program.

12. A network quality of service assessment apparatus, comprising:

the terminal equipment comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring network state data detected by the terminal equipment and acquiring service experience data of a specified application program running on the terminal equipment;

the determining unit is used for determining a network blockage index according to the network state data and a weight coefficient for evaluating the network blockage situation, and determining a service blockage index according to the service experience data;

the first processing unit is used for updating the weight coefficient according to the matching degree between the network blockage indexes and the service blockage indexes so as to enable the matching degree to reach a set value;

and the second processing unit is used for re-determining the network blockage index based on the updated weight coefficient and evaluating the service quality of the specified application program according to the re-determined network blockage index.

13. A network quality of service optimization apparatus, comprising:

the detection unit is used for detecting the network state data of the environment where the terminal equipment is located and the service experience data of the specified application program running on the terminal equipment;

a reporting unit, configured to report the network state data and the service experience data to a data processing device, so that the data processing device evaluates the service quality of the designated application according to the network state data and the service experience data;

the prediction processing unit is used for acquiring the service quality data aiming at the specified application program sent by the data processing equipment and predicting the blocking condition of the specified application program according to the service quality data and the current network state data of the terminal equipment;

and the optimization processing unit is used for carrying out network optimization processing on the specified application program according to the blockage situation.

14. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out a network quality of service assessment method according to any one of claims 1 to 9, or carries out a network quality of service optimization method according to claim 10 or 11.

15. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the network quality of service assessment method of any one of claims 1 to 9, or to implement the network quality of service optimization method of claim 10 or 11.