CN115150901A - Method, apparatus and storage medium for determining poor quality cells in a communication network - Google Patents
Method, apparatus and storage medium for determining poor quality cells in a communication network Download PDFInfo
- Publication number
- CN115150901A CN115150901A CN202110336724.3A CN202110336724A CN115150901A CN 115150901 A CN115150901 A CN 115150901A CN 202110336724 A CN202110336724 A CN 202110336724A CN 115150901 A CN115150901 A CN 115150901A
- Authority
- CN
- China
- Prior art keywords
- cell
- poor
- quality
- list
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000004891 communication Methods 0.000 title claims abstract description 51
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 230000005540 biological transmission Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 19
- 238000012216 screening Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 12
- 238000005457 optimization Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000003442 weekly effect Effects 0.000 description 6
- 230000003139 buffering effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010044565 Tremor Diseases 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
- H04W36/0005—Control or signalling for completing the hand-off
- H04W36/0011—Control or signalling for completing the hand-off for data sessions of end-to-end connection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/80—Responding to QoS
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
- H04W36/08—Reselecting an access point
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
- H04W36/24—Reselection being triggered by specific parameters
- H04W36/30—Reselection being triggered by specific parameters by measured or perceived connection quality data
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The application discloses a method, a device and a storage medium for determining a poor cell in a communication network, relates to the field of communication, and aims to solve the problem of low accuracy in determining a poor cell in a wireless network in the related art. The method for determining the poor quality cell in the communication network comprises the following steps: obtaining a quality difference user list based on a target model, wherein quality difference users in the quality difference user list are users with satisfaction degree of mobile videos lower than a threshold value in mobile video users; determining a first poor cell list based on the poor user list, wherein poor cells in the first poor cell list are cells with network quality lower than a set condition; determining a target quality cell based on the first quality cell list. The method and the device are used for determining the cell with poor network quality in the communication network.
Description
Technical Field
The present application relates to the field of communications, and in particular, to a method, an apparatus, and a storage medium for determining a poor cell in a communication network.
Background
With the increasing demand for mobile video services, it is most important to ensure the quality of wireless networks in order to meet the demand. Therefore, it is necessary to find a cell with poor user experience when using the mobile video service due to poor quality of the wireless network, and perform network optimization on the cell to meet the user's requirements.
Currently, in the related art, whether a cell is a cell where a user who complains about mobile video dissatisfaction often resides is determined by determining residence time and traffic of the user in the cell, that is, the cell has poor wireless network quality and needs to be optimized.
However, the method determines the cell (cell with poor wireless network quality) where the mobile video is not satisfied and the user often resides by using the residence time or the traffic as a judgment basis, and has the problem of low accuracy.
Disclosure of Invention
The embodiment of the application provides a method, a device and a storage medium for determining a poor cell in a communication network, which can solve the problem of low accuracy in determining a poor cell in a wireless network quality in the related art.
In a first aspect, a method of determining a poor cell in a communication network is provided, the method comprising:
obtaining a quality difference user list based on a target model, wherein quality difference users in the quality difference user list are users with satisfaction degree of mobile videos lower than a threshold value in mobile video users;
determining a first poor cell list based on the poor user list, wherein poor cells in the first poor cell list are cells with network quality lower than a set condition;
determining a target quality difference cell based on the first quality difference cell list.
In a second aspect, an apparatus for determining a poor cell in a communication network is provided, the apparatus comprising:
the obtaining module is used for obtaining a quality difference user list based on a target model, wherein quality difference users in the quality difference user list are users with satisfaction degree of mobile video lower than a threshold value in mobile video users;
a determining module, configured to determine a first poor cell list based on the poor user list, where a poor cell in the first poor cell list is a cell whose network quality is lower than a set condition;
the determining module is further configured to determine a target quality difference cell based on the first quality difference cell list.
In a third aspect, a network device is provided, where the network device includes: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method according to the first aspect as described above.
In a fourth aspect, a computer-readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, carries out the steps of the method according to the first aspect as described above.
In the embodiment of the application, a list of users with mobile video satisfaction lower than a threshold value when the mobile video service is used, namely a list of users unsatisfied with the mobile video, can be obtained through a target model, and then a list of cells with network quality lower than a set condition, namely a list of cells with poor network quality, is determined through the list of users with mobile video unsatisfied; and finally, determining a final target poor cell according to the list of the cells with poor network quality. According to the method for determining the poor cell in the communication network, provided by the embodiment of the application, the user who is not satisfied with the mobile video can be obtained according to the satisfaction degree of the user on the mobile video, and then the cell with poor network quality can be obtained according to the user who is not satisfied with the mobile video, namely, when the cell with poor network quality is determined, the satisfaction degree of the user on the mobile video is considered. Therefore, the method for determining the poor quality cell in the communication network provided by the embodiment of the application has higher accuracy.
Drawings
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 embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of a method for determining a poor cell in a communication network according to an embodiment of the present application.
Fig. 2 is a flowchart of a method for determining a first poor cell list according to an embodiment of the present disclosure.
Fig. 3 is a flowchart of a method for determining a second poor quality cell list according to an embodiment of the present application.
Fig. 4 is a flowchart of a method for determining a target poor cell list according to an embodiment of the present application.
Fig. 5 is a flowchart of another method for determining a target poor cell list according to an embodiment of the present application.
Fig. 6 is a block diagram illustrating an apparatus for determining a poor cell in a communication network according to an embodiment of the present disclosure.
Fig. 7 is a block diagram of a network device according to an embodiment of the present disclosure.
Detailed Description
To make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to solve the problem of low accuracy in determining a cell with poor wireless network quality in the related art, the present application provides a solution, and aims to provide a method for determining a cell with poor quality in a communication network with high accuracy.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
As described in the background art, the quality of the wireless network may directly affect the user experience when using the mobile video service, and also affect the user satisfaction degree on the mobile video, where the mobile video service may be a video in a video application program or a video in a communication application program (for example, a short video in a trembling sound and a video sent by another person in a WeChat), and therefore, the present application mainly determines a cell with poor wireless network quality in the communication network by using a user whose satisfaction degree on the mobile video service is lower than a threshold value when using the mobile video service.
In order to solve the above technical problem, an embodiment of the present application provides a method for determining a poor cell in a communication network, where the poor cell is a cell with poor network quality, and the method obtains, through a target model, a list of users whose satisfaction on a mobile video is lower than a threshold when using a mobile video service, that is, a list of users who are not satisfied with the mobile video, and then determines, through the list of users who are not satisfied with the mobile video, a list of cells whose network quality is lower than a set condition, that is, a list of cells with poor network quality; and finally, determining a final target poor cell according to the list of the cells with poor network quality. The execution subject of the method may be a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, etc.
Fig. 1 is a flowchart of a method for determining a poor cell in a communication network according to an embodiment of the present application. As shown in fig. 1, a method for determining a poor cell in a communication network according to an embodiment of the present application may include:
and step 110, acquiring a quality user list based on the target model, wherein the quality users in the quality user list are users whose satisfaction degree of the mobile video is lower than a threshold value in the mobile video users.
The user with the satisfaction degree of the mobile video lower than the threshold value is the user with dissatisfaction with the mobile video, and the threshold value may be a certain value or a certain condition, for example, the satisfaction degree is lower than 60. The target model can judge the satisfaction degree of the user on the mobile video when the user uses the mobile video service, so that the user who is not satisfied with the mobile video can be judged according to the target model.
As described above, the target model may determine the satisfaction of the user on the mobile video when using the mobile video service, and the satisfaction of the user on the mobile video may reflect the network quality of the cell where the user is located when using the mobile video service. For example, the dissatisfaction of the user with the mobile video may reflect poor network quality of the cell in which the user is using the mobile video service. Therefore, the cell with the network quality lower than the set condition can be determined according to the user with the satisfaction degree of the mobile video lower than the threshold, and the cell with the network quality lower than the preset condition is the cell with poor network quality. The poor network quality of the cell can be expressed in various aspects such as low network speed.
According to the method for determining the poor cell in the communication network, the list of the users with the mobile video satisfaction lower than the threshold value when the mobile video service is used, namely the list of the users unsatisfied with the mobile video, can be obtained through the target model, and then the list of the cells with the network quality lower than the set conditions, namely the list of the cells with the poor network quality, is determined through the list of the users unsatisfied with the mobile video; and finally, determining a final target poor cell according to the list of the cells with poor network quality.
As described above, the satisfaction degree of the user on the mobile video needs to be determined through the target model, and then a list of users who are not satisfied with the mobile video is obtained. Therefore, before the obtaining of the list of users with poor quality, an object model for judging the satisfaction degree of the users to the mobile video can be constructed.
Optionally, before obtaining the list of poor quality users in step 110, the method for determining a poor quality cell in a communication network according to the embodiment of the present application may further include:
acquiring subjective data and objective data of a user, wherein the subjective data is data representing subjective feelings of the user when the user uses a mobile video service, and the objective data comprises at least one of video cache rate, video transmission delay and network round-trip delay;
and constructing a target model based on subjective data of the user and objective data of the user, wherein the target model is used for determining the video satisfaction of the user and outputting the poor user list.
After obtaining subjective data and objective data of a user, the subjective data and the objective data may be used as sample data for constructing a target model. In consideration of the fact that the obtained objective data may not be complete, the missing value interpolation method can be adopted to clean the sample data before the target model is constructed. And then, taking part of sample data as a training set for training the target model, and taking the other part of sample data as a verification set for adjusting the parameters of the target model.
Alternatively, the accuracy requirement of the target model may be 99% and the recall requirement may be 99%.
It is understood that the subjective data is data that can represent the subjective feeling of the user when using the mobile video service, for example, the subjective feeling of the user when watching the video can be very smooth, generally smooth, slightly unsmooth, and heavily unsmooth. The subjective data of the user can reflect the satisfaction degree of the user, for example, when the subjective feeling is very smooth and general smooth, the satisfaction degree of the user is satisfied, and when the subjective feeling is slight unsmooth and severe unsmooth, the satisfaction degree of the user is unsatisfied.
The objective data is data of some objective indexes when the user uses the mobile video service, and the objective data comprises at least one of video cache rate, video transmission delay and network Round Trip Time (RTT). The video buffering rate is a rate of buffering a video when a user watches the video online, the video transmission delay can be a buffering delay of a first 400kb data packet in a video data packet, and the network round-trip delay is an important performance index in a network and indicates that the video data is transmitted from a transmitting end to a receiving end (the receiving end immediately transmits an acknowledgement after receiving the video data), and the total time delay is experienced. The objective data corresponds to the subjective data, and if the video cache rate is low when the user uses the mobile video service, the user feels unsmooth.
Because the subjective feeling of the user is only known by the user, the user cannot obtain the subjective feeling from the network database and cannot obtain the subjective feeling through a machine, the subjective feeling of the user needs to be obtained through testing. The test process may be: testing in a scene covering most data of the whole network by a tester, wherein the scene comprises an airport, a railway station, an office building, a hotel, a low-rise residential area, namely a highway and the like, using a mobile video service in the scene, and recording the subjective feeling at that time so as to obtain the subjective data; and meanwhile, objective data are obtained from a network database, and the objective data correspond to the subjective data obtained through the test.
It can be understood that the data in the network database is analyzed by a Deep Packet Inspection (DPI) technique after intercepting a data Packet from a network transmission medium (e.g., an optical fiber), the objective data can be obtained from the network database, and the network database may further include data of information such as a date, a city, a cell, an equipment manufacturer to which the wireless cell belongs, and an overlay scene to which the wireless cell belongs.
In this way, the tested subjective data and objective data obtained from the network database can be used as sample data for modeling. Because the subjective data are obtained through testing, namely the real feelings of the testing personnel, the reference is provided, and modeling can be related to the objective data. After the target model is constructed, objective data of a user needing to test the video satisfaction of the user can be input into the target model, and the video satisfaction of the user is judged through the target model.
After the satisfaction degree of the user using the mobile video service is judged through the target model, the user who is not satisfied when using the mobile video service can be known, and the user who is not satisfied when using the mobile video service is output, so that the quality difference user list is obtained.
Optionally, the quality difference user list may be a daily-granularity quality difference user list, and the determining a first quality difference cell list according to the quality difference user list in step 120 may include:
counting a daily granularity quality difference user list by taking a week as a unit, screening out users with the occurrence frequency exceeding a first preset frequency in the daily granularity quality difference user list in the week, and determining the screened users as users with normal quality difference;
acquiring a cell in which the user with the normal quality difference is unsatisfied with the mobile video service in one day;
determining the cells aggregated by the users with the normal quality difference in one day according to the distribution condition of the cells in which the users with the normal quality difference in one day are unsatisfied by using the mobile video service, and determining a daily granularity user aggregated cell list according to the aggregated cells of the users with the normal quality difference in one day;
counting a daily granularity constant-quality difference user aggregated cell list by taking a week as a unit, screening out cells of which the occurrence times in the daily granularity constant-quality difference user aggregated cell list exceeds a second preset time and the number of quality difference users in the week exceeds a preset number, and determining a first quality difference cell list according to the screened cells.
It should be noted that the quality difference user list may also be a week-granularity quality difference user list or a month-granularity quality difference user list. The above description of the time units such as day and week is only an exemplary description for easy understanding, and it is not limited in the embodiment of the present application to which the unit is specifically described.
It can be understood that, when the objective model is used to judge the satisfaction degree of the user, objective data of a certain number of users may be input in units of days, that is, objective data of a certain number of users may be input each time a day, then it is judged by the objective model which users among the certain number of users have unsatisfactory satisfaction degree, and finally the objective model may output a list of users whose satisfaction degree is unsatisfactory each day, that is, a list of users with poor daily granularity.
And then counting a weekly day granularity quality difference user list by taking a week as a unit, screening out users with the frequency exceeding a preset number in the weekly day granularity quality difference user list, and determining the screened users as users with the normal quality difference, wherein the users with the normal quality difference represent users who are often unsatisfied with the mobile video. The reason that the mobile video is occasionally dissatisfied by the user may be due to the mobile device of the user, the weather reason and the like, the network optimization of the cell where the user is located is not necessarily required, and the reason that the mobile video is frequently dissatisfied by the user may be due to the fact that the network quality of the cell where the user is located is poor when the user uses the mobile video service, and therefore only users with poor quality are screened out.
After the users with poor constant quality are screened out, the cell where the users with poor constant quality use the mobile video service unsatisfied in one day is obtained, the cell where the users with poor constant quality use the mobile video service unsatisfied in one day can also be obtained from the network database, and the network database comprises objective data, date, time, the cell where the user is located and the like when each user uses the mobile video service. And then, determining the cells aggregated by the users with the constant quality difference in one day according to the cells where the users with the constant quality difference in one day use the mobile video service unsatisfactorily. Specifically, the aggregated cell of users with poor constant quality can be determined by determining the number of users with unsatisfactory mobile video service in each cell, and if the number of users with unsatisfactory mobile video service in a certain cell is greater than 50, the cell is determined as the aggregated cell of users with poor constant quality. And further obtaining the cells aggregated by the users with normal quality difference in one day, namely determining a daily granularity user aggregated cell list with normal quality difference.
And finally, screening out cells with the occurrence frequency exceeding a preset frequency and the quality difference users exceeding the preset number in a weekly daily granularity normal quality difference user aggregation cell list, and determining the screened cells as first quality difference cells so as to determine the first quality difference cell list.
Therefore, the quality difference users can be obtained through the satisfaction degree of the users when the users use the mobile video service, then the users with the normal quality difference are further obtained according to the users with the quality difference, the cells gathered by the users with the normal quality difference are determined according to the cells where the users with the normal quality difference use the mobile video service unsatisfactorily, and finally the first quality difference cell is obtained according to the cells gathered by the users with the normal quality difference. By the method, the condition for judging the first poor-quality cell is reduced step by step, and finally the cell with poor network quality can be accurately determined.
While the first quality-difference cell list is determined by the satisfaction of the user when using the mobile video, the second quality-difference cell can be determined according to the service volume of the cell and the service index of the cell.
In addition to the method for determining a target poor cell by determining the video satisfaction of a user through a target model and obtaining a poor user list, and further obtaining a first poor cell list according to the poor user list and determining the target poor cell from the first poor cell list, the embodiment of the present application further provides another method for determining the target poor cell. That is, while the first poor quality cell list is determined according to the satisfaction of the user when using the mobile video, the second poor quality cell list may be determined according to the traffic volume of the cell and the traffic index of the cell, and then the target poor quality cell may be determined according to the first poor quality cell list and the second poor quality cell list.
Optionally, the method for determining a poor cell in a communication network provided in the embodiment of the present application may further include:
determining a second poor cell list according to the service volume and the service index of each cell in the communication network;
the determining a target quality cell based on the first quality cell list comprises: determining a target poor quality cell based on the first poor quality cell list and the second poor quality cell list.
The traffic volume of the cell may be obtained from traffic data Detail records (xDR, x Detail Record, x represents various types of traffic data) of the cell, the traffic indicator may be a video transmission delay (for example, a buffering delay of a first 400kb or 500kb data packet in a video data packet) of a certain data volume (for example, 400kb or 500kb, and the like), and both the traffic data Detail records and the traffic indicator may be obtained from a network database.
Therefore, whether the cell is worth to perform network optimization can be judged according to the service volume of the cell, and the network quality condition of the cell can be judged according to the service index, namely whether the cell needs to perform network optimization is judged. Due to limited resources, network optimization can be preferentially performed on cells with large traffic and poor network quality.
Optionally, determining the second quality difference cell list according to the traffic volume and the traffic index of each cell in the communication network may specifically include:
acquiring the total traffic and the average video transmission delay of all users in each cell in a communication network in unit time;
for any appointed cell in a communication network, if the total traffic of all users of the appointed cell is greater than a first preset threshold and the average video transmission delay is greater than a second preset threshold, determining the appointed cell as a second poor quality cell;
a second list of poor quality cells is determined based on at least one second poor quality cell determined for each cell in the communication network.
It can be understood that the larger the traffic volume of a cell, the greater the traffic demand of a user, and the more valuable the network optimization for the cell. The average video transmission delay is one of the service indexes of the cell, and represents the average value of the video transmission delay when each user in the cell uses the mobile video service in one day, and can be used for evaluating the network quality of the cell. Thus, the second quality-poor cell may be determined based on the traffic and average video transmission delay for all users of each cell during the day.
Therefore, the poor quality cell can be determined from the dimension beyond the user satisfaction degree, the condition for judging the poor quality cell is enriched, and more poor quality cells can be determined.
According to the embodiment of the application, two quality difference cell lists are determined through two different methods, and finally, a final target quality difference cell is determined according to the two quality difference cell lists. Therefore, the video satisfaction of the user, the cell service volume and the cell service index can be considered respectively, so that the misjudgment situation is reduced, and the accuracy rate of determining the target poor cell is improved.
After obtaining the first quality difference list according to the video satisfaction of the user and obtaining the second quality difference list according to the service volume and the service index of the cell, optionally, the determining the target quality difference cell based on the first quality difference cell list and the second quality difference cell list may include:
acquiring at least one cell existing in the first and second poor quality cell lists at the same time;
and taking the obtained at least one cell as a target quality difference cell.
After obtaining the first and second poor quality cell lists, the first and second poor quality cell lists may be compared, and at least one cell existing in both the first and second poor quality cell lists may be obtained as a target poor quality cell.
And the cells simultaneously existing in the first poor quality cell list and the second poor quality cell list are the cells which are unsatisfactory to the mobile video when the user uses the mobile video service, and the cell in which the user is located has large service volume and network indexes indicating that the network quality is poor. Thus, it can be determined that the target poor cell is a cell that really needs network optimization. When the target poor quality cell is judged, the user satisfaction, the cell service volume and the cell service index are considered respectively, so that the misjudgment condition is reduced, and the accuracy rate of determining the target poor quality cell is improved.
It can be understood that, in the embodiment of the present application, two poor quality cell lists may be determined by two different methods, and finally, a final target poor quality cell list is determined according to the two poor quality cell lists. While some cells may be present in both the first and second poor quality cell lists, there may also be cells present in only one of the two poor quality cell lists.
Thus, optionally, the determining a target poor cell based on the first poor cell list and the second poor cell list may further include:
for a first particular cell that is present in the first list of poor quality cells and not present in the second list of poor quality cells:
judging whether the traffic of all users in one day of the first specific cell exceeds a first preset threshold value;
and if the traffic of all users in the first specific cell in one day exceeds a first preset threshold, taking the first specific cell as a target quality difference cell.
For a second particular cell that appears on the second list of poor quality cells but not on the first list of poor quality cells:
judging whether the number of consecutive days of the second specific cell in the second poor quality cell list exceeds a preset number of days;
and if the number of continuous days of the second specific cell in the second poor quality cell list exceeds a preset number of days, taking the second specific cell as the target poor quality cell.
Optionally, if the total traffic of all users in the first specific cell in one day does not exceed a first preset threshold, the first specific cell is discarded and is not written into the target poor quality cell list.
Optionally, if the number of consecutive days of the second specific cell in the second poor quality cell list does not exceed a preset number of days, discarding the second specific cell and not writing the second specific cell into the target poor quality cell list.
Therefore, the target poor cell can be judged according to the user satisfaction, the cell service volume and the cell service index, and the accuracy and comprehensiveness of determining the target poor cell are improved.
Fig. 2 is a flowchart of a method for determining a first poor cell list according to an embodiment of the present disclosure. As shown in fig. 2, a method for determining a first poor cell list according to an embodiment of the present application may include the following steps:
Therefore, the poor quality user can be obtained through the target model, the normal poor quality user can be further obtained according to the poor quality user, the cell aggregated by the normal poor quality user is determined according to the cell where the normal poor quality user is unsatisfied in using the mobile video service, and finally the first poor quality cell is obtained according to the cell aggregated by the normal poor quality user.
Fig. 3 is a flowchart of a method for determining a second poor quality cell list according to an embodiment of the present application. As shown in fig. 3, a method for determining a second poor cell list according to an embodiment of the present application may include the following steps:
and 310, acquiring the total traffic and the average video transmission delay of all users in each cell in the communication network in unit time.
The method for determining the second poor quality cell list provided by the embodiment of the application determines the second poor quality cell according to the total traffic and the average video transmission delay of all users in each cell. Therefore, the poor quality cell can be determined from the dimension beyond the user satisfaction degree, the condition for judging the poor quality cell is enriched, and more poor quality cells can be determined.
Fig. 4 is a flowchart of a method for determining a target poor cell list according to an embodiment of the present application. As shown in fig. 4, a method for determining a target poor cell list according to an embodiment of the present application may include the following steps:
step 410 compares the first list of poor quality cells and the second list of poor quality cells.
It should be noted that the above-mentioned "within one day", "every week" and "within one week" in the method provided in the embodiment of the present application are only exemplary expressions for easy understanding, and are specifically expressed in what unit, and are not limited in the embodiment of the present application, and the time unit may be other time units than day and week, such as minutes, hours, months, and the like.
Therefore, the target poor quality user can be determined comprehensively based on the satisfaction degree of the user to the mobile video, the service volume of the cell and the service index of the cell, and the satisfaction degree of the user to the mobile video, the service volume of the cell and the service index of the cell can reflect the network quality condition of the cell, so that the method for determining the poor quality cell in the communication network provided by the embodiment of the application has higher accuracy.
Fig. 5 is a flowchart of another method for determining a target poor cell list according to an embodiment of the present application. As shown in fig. 5, a method for determining a poor cell in a communication network according to an embodiment of the present application may further include:
the method comprises the steps of obtaining a daily granularity poor quality user list based on a target model, screening users with the occurrence frequency exceeding a first preset frequency from the daily granularity poor quality user list in a week as users with normal quality, further obtaining a cell list aggregated by the users with normal quality according to the users with normal quality, screening cells with the occurrence frequency exceeding a second preset frequency and the number of the users with poor quality exceeding the preset number in the week from the daily granularity poor quality user aggregated list in the week as first poor quality cells, and finally obtaining the first poor quality cell list.
Determining a second quality difference cell list based on the cell traffic and the service index, determining whether the total traffic of all users of each cell is greater than a first preset threshold value, and meanwhile, whether the average video transmission time delay of all users is greater than a second preset threshold value, if the total traffic of all users of the cell is greater than the first preset threshold value and the average video transmission time delay of all users is greater than the second preset threshold value, determining the cell as a second quality difference user, and finally obtaining the second quality difference cell list.
And finally, determining the target users with poor quality by combining the two methods. For cells that appear on the first list of poor quality cells but not on the second list of poor quality cells: judging whether the traffic of all users in one day of the cell exceeds a first preset threshold value or not; and if the traffic of all users in the first specific cell in one day exceeds a first preset threshold, taking the cell as a target quality difference cell. For cells that appear on the second list of poor quality cells but not on the first list of poor quality cells: judging whether the number of days of the cell continuously appearing in the second poor quality cell list exceeds a preset number of days; and if the number of continuous days of the cell in the second poor quality cell list exceeds the preset number of days, taking the cell as the target poor quality cell.
By the method shown in fig. 5, the target poor quality user can be determined based on the satisfaction of the user on the mobile video, the traffic of the cell, and the traffic index of the cell, and the satisfaction of the user on the mobile video, the traffic of the cell, and the traffic index of the cell can all reflect the network quality condition of the cell.
Fig. 6 is a block diagram illustrating an apparatus for determining a poor cell in a communication network according to an embodiment of the present disclosure. As shown in fig. 6, an apparatus 600 for determining a poor cell in a communication network includes an obtaining module 601 and a determining module 602.
The obtaining module 601 is configured to obtain a quality user list based on a target model, where a quality user in the quality user list is a user whose satisfaction degree on a mobile video is lower than a threshold value among mobile video users.
The determining module 602 is configured to determine a first poor cell list based on the poor user list, where a poor cell in the first poor cell list is a cell whose network quality is lower than a set condition.
The determining module 602 is further configured to determine a target quality difference cell based on the first quality difference cell list.
Optionally, an apparatus for determining a poor cell in a communication network provided in the embodiment of the present application may further include the building module 603.
Optionally, before the obtaining module 601 obtains the list of the users with poor quality, the obtaining module 601 may be further configured to obtain subjective data and objective data of the users, where the subjective data is data representing subjective feelings of the users using the mobile video service, and the objective data includes at least one of a video buffering rate, a video transmission delay, and a network round-trip delay.
The building module 603 may be configured to build a target model based on subjective data of the user and objective data of the user, where the target model is configured to determine video satisfaction of the user and output the poor user list.
Optionally, the determining module 602 may be further configured to determine a second poor cell list according to the service volume and the service index of each cell in the communication network; the determining module 602 is specifically configured to determine a target poor cell based on the first poor cell list and the second poor cell list when the target poor cell is determined by the first poor cell list.
Optionally, when the determining module 602 determines the target poor quality cell based on the first poor quality cell list and the second poor quality cell list, the obtaining module 601 may be further configured to obtain at least one cell existing in both the first poor quality cell list and the second poor quality cell list, and the determining module 602 may be specifically configured to use the obtained at least one cell as the target poor quality cell.
Optionally, the quality difference user list is a daily quality difference user list, and the determining module 602, when determining the first quality difference cell list according to the quality difference user list, may specifically be configured to count the daily quality difference user list in units of weeks, screen out users whose occurrence frequency in the daily quality difference user list exceeds a first preset frequency within a week, and determine the screened users as users with constant quality difference; the obtaining module 601 may be configured to obtain a cell where the constant-quality user is unsatisfied with the mobile video service in one day; the determining module 602 may be further configured to determine, according to a distribution of cells in which users with poor quality use mobile video services are unsatisfied during the day, cells aggregated by users with poor quality during the day, and determine a daily-granularity list of cells aggregated by users with poor quality according to the cells aggregated by users with poor quality during the day; counting a weekly daily granularity constant-quality user aggregated cell list, screening cells with the daily granularity constant-quality user aggregated cell list of a week exceeding a second preset number of times and the quality-poor users exceeding the preset number in the week, and determining a first quality-poor cell list according to the screened cells.
Optionally, when the determining module 602 determines the second poor cell list according to the traffic volume and the traffic index of each cell in the communication network, the obtaining module 601 may be configured to obtain the total traffic volume and the average video transmission delay of all users in each cell in the communication network in unit time; the determining module 602 may be specifically configured to, for any specified cell in the communication network, determine the specified cell as a second poor quality cell if the total traffic of all users of the specified cell is greater than a first preset threshold and the average video transmission delay is greater than a second preset threshold; a second list of poor quality cells is determined based on at least one second poor quality cell determined for each cell in the communication network.
The determining module 602, when determining the target poor quality cell based on the first poor quality cell list and the second poor quality cell list, may specifically be configured to:
for a first particular cell that appears on the first list of poor quality cells but not on the second list of poor quality cells: judging whether the traffic of all users in one day of the first specific cell exceeds a first preset threshold value; if the traffic of all users in the first specific cell in one day exceeds a first preset threshold, taking the first specific cell as a target quality difference cell; for a second particular cell that appears on the second list of poor quality cells but does not appear on the first list of poor quality cells: judging whether the number of consecutive days of the second specific cell in the second poor quality cell list exceeds a preset number of days; and if the number of continuous days of the second specific cell in the second poor quality cell list exceeds a preset number of days, taking the second specific cell as the target poor quality cell.
It should be understood that the method for determining a poor quality cell in a communication network described above can be applied to the apparatus for determining a poor quality cell in a communication network provided in the embodiments of the present application, and therefore, reference may be made to the description of the method above for the apparatus for determining a poor quality cell in a communication network.
Fig. 7 is a block diagram of a network device according to an embodiment of the present application. As shown in fig. 7, the present embodiment provides a network device 700, which includes a memory 701, a processor 702, and a computer program stored on the memory and executable on the processor, and when executed by the processor, the computer program implements any one of the above methods. For example, the computer program may, when executed by the processor, implement the following process: obtaining a quality user list based on a target model, wherein quality users in the quality user list are users with satisfaction degree on a mobile video lower than a threshold value in mobile video users; determining a first poor cell list based on the poor user list, wherein poor cells in the first poor cell list are cells with network quality lower than a set condition; determining a target quality cell based on the first quality cell list. Wherein the network device may be a server.
Embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements any one of the above methods.
From the above description of embodiments, it should be apparent to those skilled in the art that the embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method of determining a poor cell in a communication network, the method comprising:
obtaining a quality difference user list based on a target model, wherein quality difference users in the quality difference user list are users with satisfaction degree of mobile videos lower than a threshold value in mobile video users;
determining a first poor cell list based on the poor user list, wherein poor cells in the first poor cell list are cells with network quality lower than a set condition;
determining a target quality cell based on the first quality cell list.
2. The method of claim 1, wherein prior to said obtaining a list of poor users, the method further comprises:
acquiring subjective data and objective data of a user, wherein the subjective data is data representing subjective feelings of the user when the user uses a mobile video service, and the objective data comprises at least one of video cache rate, video transmission delay and network round-trip delay;
and constructing a target model based on subjective data of the user and objective data of the user, wherein the target model is used for determining the video satisfaction of the user and outputting the poor user list.
3. The method of claim 1, further comprising:
determining a second poor cell list according to the service volume and the service index of each cell in the communication network;
the determining a target quality cell based on the first quality cell list comprises: determining a target quality-poor cell based on the first quality-poor cell list and the second quality-poor cell list.
4. The method of claim 3, wherein determining a target poor cell based on the first poor cell list and the second poor cell list comprises:
acquiring at least one cell existing in the first and second poor quality cell lists at the same time;
and taking the obtained at least one cell as a target quality difference cell.
5. The method of claim 1, wherein the list of poor quality users is a daily-granularity poor quality user list, and wherein determining the first poor quality cell list from the poor quality user list comprises:
counting a daily granularity quality difference user list by taking a week as a unit, screening out users with the occurrence frequency exceeding a first preset frequency in the daily granularity quality difference user list in the week, and determining the screened users as users with normal quality difference;
acquiring a cell where the user with the poor quality is unsatisfied with the mobile video service in one day;
determining the cells aggregated by the users with the normal quality difference in one day according to the distribution condition of the cells in which the users with the normal quality difference in one day are unsatisfied by using the mobile video service, and determining a daily granularity user aggregated cell list according to the aggregated cells of the users with the normal quality difference in one day;
counting a daily granularity constant-quality difference user aggregated cell list by taking a week as a unit, screening out cells of which the occurrence times in the daily granularity constant-quality difference user aggregated cell list exceeds a second preset time and the number of quality difference users in the week exceeds a preset number, and determining a first quality difference cell list according to the screened cells.
6. The method of claim 3, wherein determining the second list of poor cells based on the traffic volume and the traffic indicator of each cell in the communication network comprises:
acquiring the total traffic and the average video transmission time delay of all users in each cell in a communication network in unit time;
for any appointed cell in a communication network, if the total traffic of all users of the appointed cell is greater than a first preset threshold and the average video transmission delay is greater than a second preset threshold, determining the appointed cell as a second poor quality cell;
a second list of poor quality cells is determined based on at least one second poor quality cell determined for each cell in the communication network.
7. The method of claim 3, wherein determining a target poor cell based on the first poor cell list and the second poor cell list further comprises:
for a first particular cell that appears on the first list of poor quality cells but not on the second list of poor quality cells:
judging whether the total traffic of all users in one day of the first specific cell exceeds a first preset threshold value or not;
if the total traffic of all users in one day of the first specific cell exceeds a first preset threshold, taking the first specific cell as a target poor quality cell;
for a second particular cell that is present in the second list of poor quality cells but not in the first list of poor quality cells:
judging whether the number of consecutive days of the second specific cell in the second poor quality cell list exceeds a preset number of days;
and if the continuous days of the second specific cell in the second poor quality cell list exceed the preset days, taking the second specific cell as the target poor quality cell.
8. An apparatus for determining a poor cell in a communication network, the apparatus comprising:
the obtaining module is used for obtaining a quality difference user list based on a target model, wherein quality difference users in the quality difference user list are users with satisfaction degree of mobile video lower than a threshold value in mobile video users;
a determining module, configured to determine a first poor cell list based on the poor user list, where a poor cell in the first poor cell list is a cell with a network quality lower than a set condition;
the determining module is further configured to determine a target quality difference cell based on the first quality difference cell list.
9. A network device, characterized in that the network device comprises: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110336724.3A CN115150901B (en) | 2021-03-29 | 2021-03-29 | Method, device and storage medium for determining quality difference cell in communication network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110336724.3A CN115150901B (en) | 2021-03-29 | 2021-03-29 | Method, device and storage medium for determining quality difference cell in communication network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115150901A true CN115150901A (en) | 2022-10-04 |
| CN115150901B CN115150901B (en) | 2024-04-09 |
Family
ID=83403796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110336724.3A Active CN115150901B (en) | 2021-03-29 | 2021-03-29 | Method, device and storage medium for determining quality difference cell in communication network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115150901B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024125207A1 (en) * | 2022-12-16 | 2024-06-20 | 华为技术有限公司 | Network quality analysis method and system, and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108124271A (en) * | 2016-11-29 | 2018-06-05 | 中国联合网络通信集团有限公司 | A kind of network quality appraisal procedure perceived based on user and device |
| US20180227822A1 (en) * | 2017-02-09 | 2018-08-09 | Acer Incorporated | Cell re-selection method used by user equipment and user equipment using the same |
| CN109803295A (en) * | 2019-03-05 | 2019-05-24 | 中国联合网络通信集团有限公司 | A kind of evaluation method and device of communication cell rectification priority |
| CN109996277A (en) * | 2017-12-29 | 2019-07-09 | 中国移动通信集团北京有限公司 | A kind of method and device judging matter difference cell |
| CN111953563A (en) * | 2020-07-31 | 2020-11-17 | 中国移动通信集团江苏有限公司 | User identification method, device, equipment and computer storage medium |
-
2021
- 2021-03-29 CN CN202110336724.3A patent/CN115150901B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108124271A (en) * | 2016-11-29 | 2018-06-05 | 中国联合网络通信集团有限公司 | A kind of network quality appraisal procedure perceived based on user and device |
| US20180227822A1 (en) * | 2017-02-09 | 2018-08-09 | Acer Incorporated | Cell re-selection method used by user equipment and user equipment using the same |
| CN109996277A (en) * | 2017-12-29 | 2019-07-09 | 中国移动通信集团北京有限公司 | A kind of method and device judging matter difference cell |
| CN109803295A (en) * | 2019-03-05 | 2019-05-24 | 中国联合网络通信集团有限公司 | A kind of evaluation method and device of communication cell rectification priority |
| CN111953563A (en) * | 2020-07-31 | 2020-11-17 | 中国移动通信集团江苏有限公司 | User identification method, device, equipment and computer storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024125207A1 (en) * | 2022-12-16 | 2024-06-20 | 华为技术有限公司 | Network quality analysis method and system, and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115150901B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3313043B1 (en) | System and method for determining quality of a media stream | |
| CN103686237B (en) | Recommend the method and system of video resource | |
| CN105930363B (en) | HTML5 webpage-based user behavior analysis method and device | |
| CN104410516B (en) | A kind of customer service perceptibility appraisal procedure and device | |
| CN111371672B (en) | Message pushing method and device | |
| US9231982B2 (en) | Data transfer for network interaction fraudulence detection | |
| WO2020062789A1 (en) | Video service quality assessment method, apparatus and device, and readable storage medium | |
| CN103152599A (en) | Mobile video service user experience quality evaluation method based on ordinal regression | |
| US11570228B2 (en) | System and method for managing video streaming quality of experience | |
| US20150213108A1 (en) | Multidimensional data process method and device thereof | |
| CN101616315A (en) | A kind of method for evaluating video quality, device and system | |
| CN111277451B (en) | Service evaluation method, device, terminal equipment and medium | |
| CN115150901A (en) | Method, apparatus and storage medium for determining poor quality cells in a communication network | |
| Hoßfeld et al. | White Paper on Crowdsourced Network and QoE Measurements--Definitions, Use Cases and Challenges | |
| EP3420698B1 (en) | Predicting multimedia session mos | |
| CN102572501A (en) | Video quality evaluation method and device capable of taking network performance and video self-owned characteristics into account | |
| CN116723313A (en) | Method, system and medium for evaluating quality of experience of QUIC video based on machine learning | |
| CN113840131B (en) | Video call quality evaluation method and device, electronic equipment and readable storage medium | |
| CN108521435B (en) | Method and system for user network behavior portrayal | |
| CN117596621A (en) | Internet surfing satisfaction prediction method and device, electronic equipment and computer storage medium | |
| CN114827951A (en) | Vehicle network quality analysis method and system based on vehicle terminal and storage medium | |
| JP4668851B2 (en) | Quality class determination apparatus, quality class determination method, and program | |
| CN114430381A (en) | Dynamic distribution method and device for service provider | |
| CN114158073A (en) | Network slice deployment method, device, equipment and storage medium | |
| Moreira et al. | Social Distancing and the Internet: What Can Network Performance Measurements Tell Us? |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |