CN113676926B - User network sensing portrait method and device - Google Patents
User network sensing portrait method and device Download PDFInfo
- Publication number
- CN113676926B CN113676926B CN202010413096.XA CN202010413096A CN113676926B CN 113676926 B CN113676926 B CN 113676926B CN 202010413096 A CN202010413096 A CN 202010413096A CN 113676926 B CN113676926 B CN 113676926B
- Authority
- CN
- China
- Prior art keywords
- data
- perception
- user
- network
- target user
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000008447 perception Effects 0.000 claims abstract description 270
- 230000004927 fusion Effects 0.000 claims abstract description 104
- 230000006399 behavior Effects 0.000 claims description 42
- 238000012549 training Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 36
- 238000010586 diagram Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 241001269524 Dura Species 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 210000001503 joint Anatomy 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the invention provides a user network perceived image method and a device, wherein the method comprises the following steps: collecting internet surfing behavior data, XDR data, MR data and complaint data of a target user, and analyzing performance data representing network perception of the target user from the internet surfing behavior data; correlating the performance data, XDR data, MR data and complaint data, obtaining perception fusion information of the target user, and obtaining the service type of the perception fusion information according to the perception fusion information; selecting data corresponding to the service type from the perception fusion information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score. The embodiment of the invention realizes accurate user perception portrait.
Description
Technical Field
The invention belongs to the technical field of mobile communication wireless networks, and particularly relates to a user network perceived image method and device.
Background
The prior art mainly relies on user investigation, user complaints and network index monitoring methods to simulate and evaluate user network perception and position the problem of poor network quality.
The user investigation method is characterized in that the evaluation is commonly evaluated by scores or simple descriptions due to strong subjectivity of users, the dimensionality is fuzzy, the specificity is single and poor, accurate user perception evaluation is difficult to obtain from the evaluation, and the root cause of the network quality difference problem is difficult to position.
The user complaint method has hysteresis, and the user perception and the positioning of the network quality difference problem can be known after the user complaint, so that the user experience is seriously influenced. Furthermore, the description of problem phenomena and locations by users is often ambiguous, resulting in difficulties in locating the cause of the quality differences accurately, as well as the network elements or cells involved.
The network index monitoring method is characterized in that the network index is a statistical average value of network element levels, and the minimum network index statistical granularity is in the order of minutes, and the abnormal user perception granularity is in the order of seconds, so that the network index monitoring method is difficult to accurately map the perception condition of a single user, and the situation that the index is excellent but the user perception is poor is commonly existed at present. In addition, the Internet application is flexible and various, and the lack of effective mapping between user experience and a telecommunication protocol is also an important reason for the difficulty in matching measurement indexes with user perception.
Disclosure of Invention
In order to solve the problem that the conventional user network perceived image method is inaccurate to the user network perceived image and has hysteresis or at least partially solve the problem, the embodiment of the invention provides a user network perceived image method and device.
According to a first aspect of an embodiment of the present invention, there is provided a user network perceived image method, including:
collecting internet surfing behavior data, XDR data, MR data and complaint data of a target user, and analyzing performance data representing network perception of the target user from the internet surfing behavior data;
correlating the performance data, XDR data, MR data and complaint data, obtaining perception fusion information of the target user, and obtaining the service type of the perception fusion information according to the perception fusion information;
selecting data corresponding to the service type from the perception fusion information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score;
the service type and the data corresponding to the service type are stored in a pre-associated mode;
the network perception scores and the user network perception descriptions are stored in a pre-associated mode;
and the user perception portrait model is trained and obtained according to the perception fusion information of the user sample and the network perception score of the user sample.
Specifically, the step of collecting internet surfing behavior data of the target user includes:
collecting log data of the target user in an SDK embedded point mode;
capturing network data of the target user through a web crawler or a public API;
and taking the collected log data and the grabbed network data as the internet surfing behavior data of the target user.
Specifically, the step of associating the performance data, the XDR data, the MR data, and the complaint data to obtain the perception fusion information of the target user includes:
according to the time stamp, IMEI, IMSI, MME UE S1AP ID, cell ID and eNB ID fields in the XDR data, MR data and complaint data, correlating the XDR data, MR data and complaint data to obtain the correlation fusion data of the target user;
and associating the performance data with the associated fusion data according to the timestamp, the App Type, the App Sub-Type and the IMEI field which are all present in the performance data and the associated fusion data, and obtaining the perception fusion information of the target user.
Specifically, the step of inputting the selected data into the user perception portrait model and outputting the network perception score of the target user further comprises the following steps:
acquiring the service type of the perception fusion information of each user sample according to the perception fusion information of each user sample;
dividing the perception fusion information of all the user samples into a plurality of data subsets according to the service types of the perception fusion information of all the user samples;
for any data subset, selecting data corresponding to the service type from the data subset according to the service type to which the data subset belongs;
training the user perception portrait model according to the data selected from the data subset to obtain a user perception portrait model corresponding to the service type to which the data subset belongs;
accordingly, the step of inputting the selected data into a user perceived portrayal model and outputting a network perceived score of the target user comprises:
acquiring a user perception portrait model corresponding to the service type according to the service type of the perception fusion information of the target user;
and inputting the data selected from the perception fusion information of the target user into the user perception portrait model corresponding to the service type, and outputting the network perception score of the target user.
Specifically, the step of training the user perceived portrait model according to the data selected from the data subset, and obtaining the user perceived portrait model corresponding to the service type to which the data subset belongs includes:
training a plurality of user perceived portrayal models based on data selected from the subset of data;
and counting the accuracy of each trained user perception portrait model, and selecting the user perception portrait model with the highest accuracy as the user perception portrait model corresponding to the service type to which the data subset belongs.
Specifically, the step of obtaining the user network perception description corresponding to the network perception score further includes:
if the network perception difference problem of the target user is known according to the user network perception description corresponding to the network perception score, acquiring the duration time of the network perception difference problem according to the timestamp in the perception fusion information of the target user;
and acquiring the position information of the target user in the duration time and occupied network element information or cell information from the perception fusion information of the target user.
Specifically, the step of acquiring the location information of the target user within the duration and the occupied network element information or cell information from the perceptive fusion information of the target user further includes:
judging the severity of the network perception difference problem according to the importance of the service type of the perception fusion information of the target user, the user star level and the duration of the network perception difference problem;
judging the importance level of the network element or the cell occupied by the target user according to the number of users, the flow and the scene label of the network element occupied by the target user or the number of users, the flow and the scene label of the cell;
weighting the severity of the network perception difference problem and the importance level of the network element or the cell occupied by the target user to obtain the processing priority of the network perception difference problem;
and if the processing priority reaches a preset threshold, checking network elements or cells occupied by the target user, and determining the reason for causing the problem of poor network perception.
According to a second aspect of an embodiment of the present invention, there is provided a user network aware portrayal device comprising:
the system comprises an acquisition module, a network sensing module and a network sensing module, wherein the acquisition module is used for acquiring internet surfing behavior data, XDR data, MR data and complaint data of a target user and analyzing performance data representing network perception of the target user from the internet surfing behavior data;
the association module is used for associating the performance data, the XDR data, the MR data and the complaint data, acquiring the perception fusion information of the target user, and acquiring the service type of the perception fusion information according to the perception fusion information;
the portrait module is used for selecting data corresponding to the service type from the perception fusion information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score;
the service type and the data corresponding to the service type are stored in a pre-associated mode;
the network perception scores and the user network perception descriptions are stored in a pre-associated mode;
and the user perception portrait model is trained and obtained according to the perception fusion information of the user sample and the network perception score of the user sample.
According to a third aspect of embodiments of the present invention, there is also provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor invoking the program instructions to be able to perform the user network aware representation method provided by any of the various possible implementations of the first aspect.
According to a fourth aspect of embodiments of the present invention, there is also provided a non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the user network aware representation method provided by any one of the various possible implementations of the first aspect.
The embodiment of the invention provides a user network perception portrait method and a device thereof, which are characterized in that user network perception performance data which are analyzed from user internet surfing behavior data are associated with XDR data, MR data and complaint data by collecting the user internet surfing behavior data, XDR data, MR data and complaint data, and corresponding data are selected from the associated data according to the service type of user network perception to carry out network perception scoring, thereby realizing accurate user network perception portrait.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a user network perceived portrait method provided by an embodiment of the present invention;
FIG. 2 is a schematic flow chart of the user network perceived portrait method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a data acquisition flow in a user network perceived portrait method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a data processing flow in a user network aware image capturing method according to an embodiment of the present invention;
FIG. 5 is a flow chart of user perceived portraits based on fusion data in a user network perceived portraits method provided by an embodiment of the present invention;
FIG. 6 is a schematic diagram of a positioning process of a user network perceived difference problem in a user network perceived image method according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a user network aware portrait device according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
In one embodiment of the present invention, a method for user network sensing portrait is provided, and fig. 1 is a schematic flow chart of a method for user network sensing portrait provided in an embodiment of the present invention, where the method includes: s101, collecting internet surfing behavior data, XDR data, MR data and complaint data of a target user, and analyzing performance data representing network perception of the target user from the internet surfing behavior data;
as shown in fig. 2, the implementation principle of this embodiment mainly includes: and automatically collecting user internet surfing behavior data, performing association matching with XDR data, complaint data, an MR fingerprint library and the like, and establishing a second-level granularity user perception fusion data information library. Through big data analysis modeling, user perception image is carried out, and automatic accurate positioning of the perception quality difference problem and preventive maintenance of user perception are further realized.
With the development of communication technology, electronic devices occupy a great deal of time for users, and when users receive a great deal of information provided by a network, massive trace data are left, and the trace can effectively reflect the true perception of the users. In order to accurately evaluate user network perception, accurate positioning of user network perception image and perception quality difference problems is realized, effective data acquisition is important, and accuracy and integrity of subsequent analysis are directly affected. This embodiment requires acquisition of internet surfing behavior data of a target user, user XDR (External Data Representation ) data, complaint data, and MR (Measurement Report ) data. The target user is a user who needs to perform network perception portrait.
A schematic flow chart of data acquisition is shown in fig. 3. The user surfing behavior data comprise various behavior data generated by a user through APP (Application) and web pages and the like by using network functions, and the granularity can reach the second level. More specifically, the user internet surfing behavior data acquisition path mainly comprises log data acquisition and network data acquisition. The log data acquisition can be realized by adopting modes including SDK embedded points and the like; network data collection primarily captures the required network data through a web crawler or public API (Application Programming Interface, application program interface). The collected user internet surfing behavior data mainly comprises: user name, browsed web page view, unique visitor identifier unique identifier, received data traffic received, transmitted data traffic transmit, packet identifier PID, log, average duration of use, total duration of use, network type and operator, message transmission failure, number of accesses to functions and interfaces, number of people, duration and error rate, number of Message transmission and reception, number of phone initiation and reception, number of voice mail Play/Delete, login duration, number of login failures, number of Message transmission failures and phone initiation reception failures, phone call quality, IMEI (International Mobile Equipment Identity, international mobile equipment identification), equipment model number, longitude longitudes, latitude latitudes, website url, submitted information post, etc.
The user XDR Data is realized through platform docking, and the collected XDR Data mainly comprises S1-MME and S1-U/S11 original code streams, namely, local Provisions of the user, local City of the user, roaming Type, interface, xDR ID, IMEI, program start Time Procedure Start Time, program closing Time Procedure End Time, program Status, cell ID, MME UE S1AP ID, IMSI (International Mobile Subscriber Identity ), longitude, latitude, app Type, app Sub-Type, app Content, app Status, operation Type Operation-Type, login Success Lon-Success, login Request Time Login-Request-Time, login Response Time Login-Response-Time, upLink Data UL Data, down Data ((Uniform Resource Identifier), uniform resource identifier), HTTP Response Time HTTP (HyperText Transfer Protocol ) Response Time, HOST name HOST, HTTP Content Type http_content_type, service component indicator Service Comp Flag, service behavior indicator Service Behavior Flag, service Time, video download Time video down Time, initial buffer duration, uplink duration up dura, downlink duration down dura, UL out-of-order IP packets UL Disorder IP Packet, DL out-of-order IP packets DL Disorder IP Packet, UL retransmission IP packets UL Retrans IP Packet, DL retransmission IP packets DL Retrans IP Packet, TCP Response Time TCP (Transmission Control Protocol ) Response Time, TCP acknowledgement Time TCP ACK Time, request Time Req Time, UL AVG RTT, dwavg RTT, and the like.
MR data is implemented by platform interfacing, including user-level and cell-level MR. The user-level MR acquisition data mainly includes a timestamp Time, an MME UE S1AP ID, a positioning longitude Location-Location, a positioning latitude Location-Location, an eNB ID, a Cell ID, an MR type, an AoA (Angle-of-Arrival) Angle ranging, a Serving RSRP (Reference Signal Received Power ), a CQI (Channel Quality Indication, channel quality indication), neighbor Cell information, and the like. The Cell-level MR acquired data mainly comprises fields such as eNB ID, cell ID, timestamp Time, eNB Received Interfere, UL Packet Loss, DL Packet Loss, air interface user plane uplink service byte number, air interface user plane downlink service byte number, uplink and downlink service channel PRB occupancy rate, simultaneous online user number and the like.
The user complaint data acquisition is realized through platform butt joint, and the acquired data mainly comprises fields such as complaint type, complaint time, IMEI, equipment type and the like. The data processing unit mainly performs operations such as analysis, format conversion, normalization processing and the like on the mass data acquired in the steps. And storing the data which are acquired in the steps and can be used for analyzing the network perception of the target user into a data storage unit.
The existing platform conditions of the data sources needing to be collected can be met, the data collection related work is not needed to be additionally carried out after the platform is in butt joint, the existing platform automatically pushes the required collected data, and a large amount of manpower and equipment cost are saved.
The performance data representing the network perception of the target user is resolved from the collected user surfing behavior data, and mainly comprises response time data, frame rate and fluency data, such as SM (application drawing polling frequency), FPS (Frames Per Second, frame rate of filling images per second) and SF (skip Frames, application frame skip times and amplitude), log data and the like.
S102, correlating the performance data, the XDR data, the MR data and the complaint data, acquiring the perception fusion information of the target user, and acquiring the service type of the perception fusion information according to the perception fusion information;
as shown in fig. 4, before the subsequent analysis, the collected massive user sample data needs to be cleaned and fused and correlated, so as to construct a user perception fusion database. And training the user perception portrait model by using the user perception fusion database, so as to establish an accurate user perception portrait model. And correlating the acquired data of the target user to acquire perception fusion information of the target user, so as to portray the network perception of the target user based on the trained perception portrayal model according to the perception fusion information.
The data is cleaned to eliminate the influence of outliers, missing values, etc. on subsequent analysis. Alternatively, the outliers may be processed using direct deletion, average correction, or the like, and the missing values may be interpolated using regression interpolation, lagrangian interpolation, multiple interpolation, or the like.
S103, selecting data corresponding to the service type from the perception fusion information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score;
the user-perceived portrayal model may be a support vector machine, a neural network, a random forest, etc., and the present embodiment is not limited to the type of user-perceived portrayal model.
The service type and the data corresponding to the service type are stored in a pre-associated mode; the network perception scores and the user network perception descriptions are stored in a pre-associated mode; and the user perception portrait model is trained and obtained according to the perception fusion information of the user sample and the network perception score of the user sample.
Common phenomena affecting user network perception mainly include stuck and crashed. According to the embodiment, the second-level business fluency, such as SM data, can be resolved through the user internet surfing behavior data, the user complaint data is further combined, the perception satisfaction degree scoring is conducted on the basis of the user internet surfing behavior data, and the perception satisfaction degree scoring data of the user sample are stored in the user perception fusion information base. The different user behaviors have obvious difference in requirements on network quality due to different service characteristics. Thus, the present embodiment establishes a user perceived satisfaction score criterion based on different user behaviors, as shown in table 1.
Table 1 network awareness scoring criteria for users
According to the embodiment, the user internet surfing behavior data, the XDR data, the MR data and the complaint data are collected, the performance data representing the user network perception is analyzed from the user internet surfing behavior data and is associated with the XDR data, the MR data and the complaint data, and corresponding data are selected from the associated data according to the service type of the user network perception to carry out network perception scoring, so that accurate user network perception portrait is realized.
On the basis of the above embodiment, in this embodiment, the step of associating the performance data, the XDR data, the MR data, and the complaint data to obtain the perception fusion information of the target user includes: according to the time stamp, IMEI, IMSI, MME UE S1AP ID, cell ID and eNB ID fields in the XDR data, MR data and complaint data, correlating the XDR data, MR data and complaint data to obtain the correlation fusion data of the target user;
and correlating the data of the target user and the user sample to finally obtain correlation fusion data comprising a time stamp, GPS (Global Positioning System ) level longitude and latitude information, occupied cell information, network performance indexes, user information and user behavior information. The user information comprises IMEI, IMSI, equipment model number, IP and the like, and the user behavior information comprises url, log, PID and the like.
And associating the performance data with the associated fusion data according to the timestamp, the App Type, the App Sub-Type and the IMEI field which are all present in the performance data and the associated fusion data, and obtaining the perception fusion information of the target user.
And finally, the acquired perception fusion information of the target user and the user sample is user-level network perception fusion information with granularity reaching the second level.
Based on the above embodiment, the step of inputting the selected data into the user perception portrait model and outputting the network perception score of the target user in this embodiment further includes: acquiring the service type of the perception fusion information of each user sample according to the perception fusion information of each user sample; dividing the perception fusion information of all the user samples into a plurality of data subsets according to the service types of the perception fusion information of all the user samples; for any data subset, selecting data corresponding to the service type from the data subset according to the service type to which the data subset belongs; training the user perception portrait model according to the data selected from the data subset to obtain a user perception portrait model corresponding to the service type to which the data subset belongs;
the embodiment establishes a perception association fusion information base of sub-business and user level. As shown in FIG. 5, the user-aware portrayal model training for sub-services is based on a user-aware converged database. The service Type of the awareness fusion information can be distinguished through an App Type, an App Sub-Type and a PID field. Specifically, the user perception score is used as a prediction variable, namely the output of the user perception portrait model, and different types of business data are divided into a plurality of data subsets. Wherein, for each of said subsets, network performance metrics, device type, user XDR data appropriate for the traffic type may be selected as training data for training of the user perceived portrayal model.
Accordingly, the step of inputting the selected data into a user perceived portrayal model and outputting a network perceived score of the target user comprises: acquiring a user perception portrait model corresponding to the service type according to the service type of the perception fusion information of the target user; and inputting the data selected from the perception fusion information of the target user into the user perception portrait model corresponding to the service type, and outputting the network perception score of the target user.
When the network perception scoring is carried out according to the perception fusion information of the target user, a corresponding user perception portrait model is selected according to the type of the perception fusion information for analysis.
According to the embodiment, the secondary perception correlation fusion information base of sub-service and user level is established, so that compared with the traditional scheme, the accuracy of the network element-dependent measurement index is higher, and the user experience is better met; the perception association fusion information base contains massive user behavior data, the samples are rich, and the problem of insufficient characterization mechanism of network element level indexes can be avoided; and an accurate user perceived portrait model is constructed through big data and machine learning, so that the accuracy of user network perceived portrait is improved.
On the basis of the above embodiment, in this embodiment, training the user perceived portrait model according to the data selected from the data subset, and obtaining the user perceived portrait model corresponding to the service type to which the data subset belongs includes: training a plurality of user perceived portrayal models based on data selected from the subset of data; and counting the accuracy of each trained user perception portrait model, and selecting the user perception portrait model with the highest accuracy as the user perception portrait model corresponding to the service type to which the data subset belongs.
Specifically, multiple user perceived portrayal models, such as support vector machines, neural networks, random forests, and the like, are trained simultaneously using each subset of data. And counting the accuracy of each model, and selecting a user perception portrait model with optimal comprehensive performance from the model as a model for user network perception portrait.
On the basis of the foregoing embodiments, the step of obtaining the user network perception description corresponding to the network perception score in this embodiment further includes: if the network perception difference problem of the target user is known according to the user network perception description corresponding to the network perception score, acquiring the duration time of the network perception difference problem according to the timestamp in the perception fusion information of the target user; and acquiring the position information, such as longitude and latitude information, of the target user in the duration time and occupied network element information or cell information, from the perception fusion information of the target user.
Specifically, after the user perception portrait model is obtained, user-level accurate perception evaluation with second granularity can be realized. For a perceived poor user, it is necessary to further locate the quality difference problem that causes the perceived difference for subsequent processing, implementing the steps shown in fig. 6. And outputting the acquired position information and occupied network element information or cell information as perception difference problem positioning analysis data.
On the basis of the above embodiment, as shown in fig. 6, the step of obtaining the location information of the target user within the duration and the occupied network element information or cell information from the perceptive fusion information of the target user in this embodiment further includes: judging the severity of the network perception difference problem according to the importance of the service type of the perception fusion information of the target user, the user star level and the duration of the network perception difference problem;
judging the importance level of the network element or the cell occupied by the target user according to the number of users, the flow and the scene label of the network element occupied by the target user or the number of users, the flow and the scene label of the cell;
weighting the severity of the network perception difference problem and the importance level of the network element or the cell occupied by the target user to obtain the processing priority of the network perception difference problem;
and if the processing priority reaches a preset threshold, checking the network element or the cell occupied by the target user by means of checking key indexes, industrial parameters and the like, and determining the reason causing the problem of poor network perception. Meanwhile, geographic presentation of the poor quality cell is realized based on GPS-level accurate position information.
Through the trained user perception portrait model, user perception evaluation portraits of second-level business can be accurately realized, GPS-level accurate position information in a fusion information base is further combined, and the whole network perception condition can be dynamically reflected and presented in a GIS (Geographic Information System ). In addition, the user perception difference reasons and related network elements or cells can be further positioned in time to form maintenance processing information and push related units and departments, and user care information or processing progress information and the like can be timely sent through various network media.
Because the user perception fusion database can provide GPS-level position information, the position positioning can be realized more accurately, and compared with the traditional scheme, the precision is higher by only relying on user complaints and industrial parameters.
In another embodiment of the present invention, a user network aware portrayal device is provided for implementing the method of the previous embodiments. Thus, the descriptions and definitions in the foregoing embodiments of the user network aware portrayal method may be used for understanding the various execution modules in embodiments of the present invention. FIG. 7 is a schematic diagram of the overall structure of a user network-aware portrayal device according to an embodiment of the present invention, where the device includes an acquisition module 701, an association module 702, and a portrayal module 703; wherein,
the acquisition module 701 is configured to acquire internet surfing behavior data, XDR data, MR data, and complaint data of a target user, and analyze performance data representing network perception of the target user from the internet surfing behavior data;
the association module 702 is configured to associate the performance data, the XDR data, the MR data, and the complaint data, obtain the perception fusion information of the target user, and obtain the service type of the perception fusion information according to the perception fusion information;
the portrait module 703 is configured to select data corresponding to the service type from the awareness converged information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score;
the service type and the data corresponding to the service type are stored in a pre-associated mode; the network perception scores and the user network perception descriptions are stored in a pre-associated mode; and the user perception portrait model is trained and obtained according to the perception fusion information of the user sample and the network perception score of the user sample.
According to the embodiment, the user internet surfing behavior data, the XDR data, the MR data and the complaint data are collected, the performance data representing the user network perception is analyzed from the user internet surfing behavior data and is associated with the XDR data, the MR data and the complaint data, and corresponding data are selected from the associated data according to the service type of the user network perception to carry out network perception scoring, so that accurate user network perception portrait is realized.
Fig. 8 illustrates a physical structure diagram of an electronic device, as shown in fig. 8, which may include: a processor 801, a communication interface (Communications Interface) 802, a memory 803, and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804. The processor 801 may call logic instructions in the memory 803 to perform the following method: collecting internet surfing behavior data, XDR data, MR data and complaint data of a target user, and analyzing performance data representing network perception of the target user from the internet surfing behavior data; correlating the performance data, XDR data, MR data and complaint data, obtaining perception fusion information of the target user, and obtaining the service type of the perception fusion information according to the perception fusion information; selecting data corresponding to the service type from the perception fusion information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score.
Further, the logic instructions in the memory 803 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present embodiment provides a non-transitory computer readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including: collecting internet surfing behavior data, XDR data, MR data and complaint data of a target user, and analyzing performance data representing network perception of the target user from the internet surfing behavior data; correlating the performance data, XDR data, MR data and complaint data, obtaining perception fusion information of the target user, and obtaining the service type of the perception fusion information according to the perception fusion information; selecting data corresponding to the service type from the perception fusion information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable storage medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for user network perception of an image, comprising:
collecting internet surfing behavior data, XDR data, MR data and complaint data of a target user, and analyzing performance data representing network perception of the target user from the internet surfing behavior data;
correlating the performance data, XDR data, MR data and complaint data, obtaining perception fusion information of the target user, and obtaining the service type of the perception fusion information according to the perception fusion information;
selecting data corresponding to the service type from the perception fusion information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score;
the service type and the data corresponding to the service type are stored in a pre-associated mode;
the network perception scores and the user network perception descriptions are stored in a pre-associated mode;
the user perception portrait model carries out training acquisition according to the perception fusion information of the user sample and the network perception score of the user sample;
the step of obtaining the user network perception description corresponding to the network perception score further comprises the following steps:
if the network perception difference problem of the target user is known according to the user network perception description corresponding to the network perception score, acquiring the duration time of the network perception difference problem according to the timestamp in the perception fusion information of the target user;
acquiring the position information of the target user within the duration time and occupied network element information or cell information from the perception fusion information of the target user;
the step of obtaining the location information of the target user in the duration and the occupied network element information or cell information from the perception fusion information of the target user further comprises:
judging the severity of the network perception difference problem according to the importance of the service type of the perception fusion information of the target user, the user star level and the duration of the network perception difference problem;
judging the importance level of the network element or the cell occupied by the target user according to the number of users, the flow and the scene label of the network element occupied by the target user or the number of users, the flow and the scene label of the cell;
weighting the severity of the network perception difference problem and the importance level of the network element or the cell occupied by the target user to obtain the processing priority of the network perception difference problem;
and if the processing priority reaches a preset threshold, checking network elements or cells occupied by the target user, and determining the reason for causing the problem of poor network perception.
2. The user network perceived image method of claim 1 wherein the step of collecting internet surfing behavior data of the target user comprises:
collecting log data of the target user in an SDK embedded point mode;
capturing network data of the target user through a web crawler or a public API;
and taking the collected log data and the grabbed network data as the internet surfing behavior data of the target user.
3. The user network perceived image method of claim 1, wherein the step of correlating the performance data, XDR data, MR data, and complaint data to obtain the perceived fusion information of the target user comprises:
according to the time stamp, IMEI, IMSI, MME UE S1AP ID, cellID and eNBID fields in the XDR data, MR data and complaint data, associating the XDR data, MR data and complaint data to obtain association fusion data of the target user;
and associating the performance data with the associated fusion data according to the timestamp, the App Type, the App Sub-Type and the IMEI field which are all present in the performance data and the associated fusion data, and obtaining the perception fusion information of the target user.
4. The method of claim 1, wherein the step of inputting selected data into a user perceived portrayal model and outputting a network perceived score of the target user is preceded by the step of:
acquiring the service type of the perception fusion information of each user sample according to the perception fusion information of each user sample;
dividing the perception fusion information of all the user samples into a plurality of data subsets according to the service types of the perception fusion information of all the user samples;
for any data subset, selecting data corresponding to the service type from the data subset according to the service type to which the data subset belongs;
training the user perception portrait model according to the data selected from the data subset to obtain a user perception portrait model corresponding to the service type to which the data subset belongs;
accordingly, the step of inputting the selected data into a user perceived portrayal model and outputting a network perceived score of the target user comprises:
acquiring a user perception portrait model corresponding to the service type according to the service type of the perception fusion information of the target user;
and inputting the data selected from the perception fusion information of the target user into the user perception portrait model corresponding to the service type, and outputting the network perception score of the target user.
5. The method of claim 4, wherein training the user-perceived portrayal model based on data selected from the subset of data, and obtaining the user-perceived portrayal model corresponding to the service type to which the subset of data belongs comprises:
training a plurality of user perceived portrayal models based on data selected from the subset of data;
and counting the accuracy of each trained user perception portrait model, and selecting the user perception portrait model with the highest accuracy as the user perception portrait model corresponding to the service type to which the data subset belongs.
6. A consumer network aware portrayal device for performing the consumer network aware portrayal method of any one of claims 1-5, comprising:
the system comprises an acquisition module, a network sensing module and a network sensing module, wherein the acquisition module is used for acquiring internet surfing behavior data, XDR data, MR data and complaint data of a target user and analyzing performance data representing network perception of the target user from the internet surfing behavior data;
the association module is used for associating the performance data, the XDR data, the MR data and the complaint data, acquiring the perception fusion information of the target user, and acquiring the service type of the perception fusion information according to the perception fusion information;
the portrait module is used for selecting data corresponding to the service type from the perception fusion information according to the service type; inputting the selected data into a user perception portrait model, outputting the network perception score of the target user, and obtaining the user network perception description corresponding to the network perception score;
the service type and the data corresponding to the service type are stored in a pre-associated mode;
the network perception scores and the user network perception descriptions are stored in a pre-associated mode;
and the user perception portrait model is trained and obtained according to the perception fusion information of the user sample and the network perception score of the user sample.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the user network aware representation method according to any of claims 1 to 5 when the program is executed by the processor.
8. A non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the user network aware representation method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010413096.XA CN113676926B (en) | 2020-05-15 | 2020-05-15 | User network sensing portrait method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010413096.XA CN113676926B (en) | 2020-05-15 | 2020-05-15 | User network sensing portrait method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113676926A CN113676926A (en) | 2021-11-19 |
| CN113676926B true CN113676926B (en) | 2024-03-19 |
Family
ID=78537745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010413096.XA Active CN113676926B (en) | 2020-05-15 | 2020-05-15 | User network sensing portrait method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113676926B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114866433B (en) * | 2022-04-21 | 2024-03-22 | 中国移动通信集团陕西有限公司 | User service perception evaluation method, device, equipment and computer storage medium |
| CN115134260A (en) * | 2022-07-12 | 2022-09-30 | 北京东土拓明科技有限公司 | User perception improving method and device, computing equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013029214A1 (en) * | 2011-08-26 | 2013-03-07 | Huawei Technologies Co., Ltd. | Video quality monitor and method for determining a network video quality measure in a communication network |
| CN104244307A (en) * | 2014-09-18 | 2014-12-24 | 大唐移动通信设备有限公司 | Anomalous event reporting and processing method and device, base station and management server |
| CN105357699A (en) * | 2015-12-15 | 2016-02-24 | 珠海市经纬天地通讯技术有限公司 | Wireless network quality monitoring system and method |
| CN105791034A (en) * | 2016-05-15 | 2016-07-20 | 北京联合大学 | Browse type service perception analysis method |
| CN106332138A (en) * | 2016-08-31 | 2017-01-11 | 四川亨通网智科技有限公司 | Method for obtaining MRO user information based on S1-MME signalling association |
| CN106572495A (en) * | 2016-09-29 | 2017-04-19 | 中国普天信息产业北京通信规划设计院 | Network quality monitoring method based on signalling and MR data and coverage assessment method based on signalling and MR data |
| CN107371183A (en) * | 2016-05-11 | 2017-11-21 | 大唐移动通信设备有限公司 | A kind of output intent and device of network quality report |
| CN108683527A (en) * | 2018-04-25 | 2018-10-19 | 武汉虹信技术服务有限责任公司 | A kind of user's perceived depth detection method based on MR and XDR |
| CN109391513A (en) * | 2018-10-11 | 2019-02-26 | 西安海润通信技术有限公司 | A kind of network aware intelligent early-warning and method for improving based on big data |
| CN109862580A (en) * | 2017-11-30 | 2019-06-07 | 华为技术有限公司 | A kind of network optimized approach and device |
| CN109982366A (en) * | 2017-12-28 | 2019-07-05 | 中国移动通信集团河北有限公司 | Target value area analysis method, device, equipment and medium based on big data |
| CN109996278A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团四川有限公司 | Road network method for evaluating quality, device, equipment and medium |
| CN110535684A (en) * | 2019-07-24 | 2019-12-03 | 武汉绿色网络信息服务有限责任公司 | A kind of method and apparatus that web-browsing service perception assessment is realized based on DPI |
| WO2020062789A1 (en) * | 2018-09-27 | 2020-04-02 | 中兴通讯股份有限公司 | Video service quality assessment method, apparatus and device, and readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103138963B (en) * | 2011-11-25 | 2016-08-03 | 华为技术有限公司 | A kind of network problem localization method based on user's perception and device |
| US8838134B2 (en) * | 2012-07-20 | 2014-09-16 | Telefonia, S.A. | Method and computer programs for the construction of communting matrices using call detail records and a use for providing user's mobility information |
| US10177964B2 (en) * | 2017-04-19 | 2019-01-08 | Netscout Systems, Inc | System and method for accurate reporting of fault for failed internet protocol-based calls |
-
2020
- 2020-05-15 CN CN202010413096.XA patent/CN113676926B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013029214A1 (en) * | 2011-08-26 | 2013-03-07 | Huawei Technologies Co., Ltd. | Video quality monitor and method for determining a network video quality measure in a communication network |
| CN104244307A (en) * | 2014-09-18 | 2014-12-24 | 大唐移动通信设备有限公司 | Anomalous event reporting and processing method and device, base station and management server |
| CN105357699A (en) * | 2015-12-15 | 2016-02-24 | 珠海市经纬天地通讯技术有限公司 | Wireless network quality monitoring system and method |
| CN107371183A (en) * | 2016-05-11 | 2017-11-21 | 大唐移动通信设备有限公司 | A kind of output intent and device of network quality report |
| CN105791034A (en) * | 2016-05-15 | 2016-07-20 | 北京联合大学 | Browse type service perception analysis method |
| CN106332138A (en) * | 2016-08-31 | 2017-01-11 | 四川亨通网智科技有限公司 | Method for obtaining MRO user information based on S1-MME signalling association |
| CN106572495A (en) * | 2016-09-29 | 2017-04-19 | 中国普天信息产业北京通信规划设计院 | Network quality monitoring method based on signalling and MR data and coverage assessment method based on signalling and MR data |
| CN109862580A (en) * | 2017-11-30 | 2019-06-07 | 华为技术有限公司 | A kind of network optimized approach and device |
| CN109982366A (en) * | 2017-12-28 | 2019-07-05 | 中国移动通信集团河北有限公司 | Target value area analysis method, device, equipment and medium based on big data |
| CN109996278A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团四川有限公司 | Road network method for evaluating quality, device, equipment and medium |
| CN108683527A (en) * | 2018-04-25 | 2018-10-19 | 武汉虹信技术服务有限责任公司 | A kind of user's perceived depth detection method based on MR and XDR |
| WO2020062789A1 (en) * | 2018-09-27 | 2020-04-02 | 中兴通讯股份有限公司 | Video service quality assessment method, apparatus and device, and readable storage medium |
| CN109391513A (en) * | 2018-10-11 | 2019-02-26 | 西安海润通信技术有限公司 | A kind of network aware intelligent early-warning and method for improving based on big data |
| CN110535684A (en) * | 2019-07-24 | 2019-12-03 | 武汉绿色网络信息服务有限责任公司 | A kind of method and apparatus that web-browsing service perception assessment is realized based on DPI |
Non-Patent Citations (8)
| Title |
|---|
| TD-LTE信令数据准确性核查方法;李宝磊;沈亮;戴鹏程;任晓华;;电信工程技术与标准化(02);全文 * |
| XDR与MR数据关联与应用;刘韬;吴涛;王斌;;电信科学(04);全文 * |
| 一种基于多维度排序的TD-LTE优化方法;段卫国;;电信工程技术与标准化(05);全文 * |
| 基于MR的LTE网络结构优化分析;黄友亮;;电信技术(09);全文 * |
| 基于互联网+的"众筹式"网络优化模式研究;杨锐雄;韦劭高;李冉;;邮电设计技术(02);全文 * |
| 基于信令关联与用户识别的LTE高铁感知优化;郭宝;刘毅;张阳;;现代电信科技(05);全文 * |
| 基于大数据分析的4G无线网精准投资研究;李华文;;通信与信息技术(05);全文 * |
| 基于机器学习的细分业务用户感知评估方法;马敏;李威;陈洁;;电信工程技术与标准化(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113676926A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11018958B2 (en) | Communication network quality of experience extrapolation and diagnosis | |
| US10454989B2 (en) | Application quality of experience evaluator for enhancing subjective quality of experience | |
| US9398475B2 (en) | Method, device, and system for monitoring quality of internet access service of mobile terminal | |
| US10349297B2 (en) | Quality of user experience analysis | |
| US10313905B2 (en) | Contextual quality of user experience analysis using equipment dynamics | |
| CN105357699B (en) | Quality of wireless network monitors system and method | |
| US20160065419A1 (en) | Method and apparatus for generating insight into the customer experience of web based applications | |
| CN106911517B (en) | Method and system for positioning end-to-end problem of mobile internet | |
| US10952091B2 (en) | Quality of user experience analysis | |
| EP3013001B1 (en) | Service quality index calculation method and calculation apparatus, and communications system | |
| CN110535684A (en) | A kind of method and apparatus that web-browsing service perception assessment is realized based on DPI | |
| CN111327539B (en) | Service scheduling method, device and equipment | |
| CN103257989A (en) | Webpage download time analysis | |
| CN113676926B (en) | User network sensing portrait method and device | |
| CN105306246B (en) | A kind of method, apparatus and server of the complaint of automatic-answering back device network class | |
| CN108476423A (en) | Use the dynamic user experience quality contextual analysis of equipment | |
| US12052144B2 (en) | Prediction of a performance indicator | |
| CN103096356A (en) | Wireless network performance analysis method | |
| WO2015003551A1 (en) | Network testing method and data collection method thereof, and network testing apparatus and system | |
| WO2015100560A1 (en) | Method for predicting quality of experience of mobile video service, and base station | |
| WO2019239004A1 (en) | Method for determining a performance indicator of a wireless telecommunications network | |
| CN106535240A (en) | Mobile APP centralized performance analysis method based on cloud platform | |
| EP3414870B1 (en) | Calculating service performance indicators | |
| CN108268370B (en) | Website quality analysis method, device and system based on Referer and template library matching | |
| CN114285760A (en) | Webpage access quality evaluation method and device |
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 |