CN112511324A

CN112511324A - Big data-based user satisfaction evaluation method and device

Info

Publication number: CN112511324A
Application number: CN201910872704.0A
Authority: CN
Inventors: 张哲�
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Hebei Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Hebei Co Ltd
Priority date: 2019-09-16
Filing date: 2019-09-16
Publication date: 2021-03-16
Anticipated expiration: 2039-09-16
Also published as: CN112511324B

Abstract

The invention discloses a user satisfaction evaluation method and device based on big data, wherein the method comprises the following steps: acquiring service data samples of each preset interface of a core network through a signaling platform, and analyzing and processing the service data samples to obtain service index data samples; acquiring a user satisfaction data sample corresponding to the service data sample; based on a preset algorithm, constructing a satisfaction evaluation model according to the service index data samples and the corresponding user satisfaction data samples; and inputting the service index data to be evaluated into the satisfaction evaluation model to obtain a satisfaction evaluation result. According to the method, objective business index data and user subjective satisfaction data are extracted for mining analysis, a satisfaction evaluation model is constructed, the satisfaction of user network services can be evaluated more quickly and conveniently by applying the model, so that the 'impersonable' user in a network can be identified quickly, and the degree of dependence on user subjective perception in satisfaction evaluation can be reduced.

Description

Big data-based user satisfaction evaluation method and device

Technical Field

The invention relates to the technical field of data processing, in particular to a user satisfaction evaluation method and device based on big data.

Background

At present, the index systems for monitoring network performance and guaranteeing user experience are KPI and KQI. The KPI and KQI index system can ensure that a single network performance index or a single service index has better performance, but the KPI and KQI indexes are not equal to the user experience, the user experience is a comprehensive performance, and the quality of a certain KPI index or KQI index can not be determined. That is to say, at present, operators lack the ability to evaluate the quality of user experience in advance, rely heavily on user feedback, and mostly rely on a research mode to evaluate the user network satisfaction.

The existing user satisfaction evaluation scheme is as follows: and on the one hand, selecting a satisfaction survey object. And randomly selecting a part of users as a sample as much as possible, and requesting the clients to feed back the network satisfaction information in the form of telephone calls or questionnaire surveys. And on the other hand, the satisfaction information is summarized, and the integral user satisfaction score is estimated. And performing summary statistics according to the feedback information, and representing the satisfaction degree scores of all users by using a statistical result. On the other hand, satisfaction evaluation work is periodically performed.

However, the current main means satisfaction investigation mode of the operator for evaluating the satisfaction degree of the customer network has the following defects: first, the samples for satisfactory investigation are very limited. The number of users in the whole network is very large, various network scenes are also very complex, samples researched by the satisfaction degree are randomly selected and can represent a mean level of the satisfaction degree of the users in the whole network to a certain extent, but the mean value is often used for averaging users with poor experience, and the users may complain finally. The satisfaction investigation cannot effectively cover the part of the 'blind' users at all, and the complaints can be solved, but the work of improving the satisfaction of the complaints is very difficult. Second, satisfaction research requires user coordination. Although most users can understand and cooperate with the satisfaction investigation work, some users still think that such investigation takes their time, and may accumulate dissatisfaction. Thirdly, the satisfaction investigation requires a large amount of manpower and material resources. The currently effective means of satisfaction investigation is means of direct calling, questionnaire and the like, the method for realizing the satisfaction investigation is to invest a large amount of manpower and material resources for investigation, and the method for improving the accuracy is to increase the investment and increase the number of samples. Fourth, satisfaction investigations are unpredictable as to user experience degradation. The 'impersonal' user in the network cannot be effectively identified, and the investigation result can only give an evaluation, so that the network perception of the 'impersonal' user cannot be improved in a targeted manner. Therefore, the prior art lacks a mechanism for efficiently evaluating the satisfaction degree of the user.

Disclosure of Invention

In view of the above, the present invention has been made to provide a big data based user satisfaction evaluation method and apparatus that overcomes or at least partially solves the above-mentioned problems.

According to an aspect of the present invention, there is provided a big data-based user satisfaction evaluation method, including:

acquiring service data samples of each preset interface of a core network through a signaling platform, and analyzing and processing the service data samples to obtain service index data samples; acquiring a user satisfaction data sample corresponding to the service data sample; based on a preset algorithm, constructing a satisfaction evaluation model according to the service index data samples and the corresponding user satisfaction data samples; and inputting the service index data to be evaluated into the satisfaction evaluation model to obtain a satisfaction evaluation result.

Optionally, the service satisfaction data samples of various services and the comprehensive satisfaction data samples of the whole service;

the satisfaction evaluation model comprises: the service satisfaction evaluation model aiming at various services and the comprehensive satisfaction evaluation model aiming at the whole service.

Optionally, after the satisfaction evaluation model is constructed according to the service index data samples and the corresponding user satisfaction data samples, the method further includes:

packaging and generating an application program according to the satisfaction evaluation model, and deploying and installing the application program in a signaling platform;

inputting the service index data to be evaluated into the satisfaction evaluation model, and obtaining the satisfaction evaluation result further comprises:

and acquiring service index data to be evaluated, and processing the service index data to be evaluated through an application program deployed in the signaling platform to obtain a satisfaction evaluation result.

Optionally, the method further comprises: and displaying the satisfaction evaluation result.

Optionally, after acquiring a service data sample of each preset interface of the core network through the signaling platform, the method further includes:

carrying out information backfill processing according to the service data sample; wherein, the information backfill processing comprises: and backfilling the international mobile subscriber identity.

Optionally, the preset interface includes: an S1-U interface, an S1-MME interface, an S11 interface and an S6a interface; the service index data sample or the service index data to be evaluated comprises the following data: user perception class, counter indicator data using action class and event class, KPI indicator data and KQI indicator data.

Optionally, the preset algorithm is specifically a principal component analysis algorithm.

According to another aspect of the present invention, there is provided a big-data-based user satisfaction evaluating apparatus, including:

the data acquisition module is used for acquiring service data samples of each preset interface of the core network through the signaling platform; acquiring a user satisfaction data sample corresponding to the service data sample;

the data processing module is used for analyzing and processing the service data sample to obtain a service index data sample;

the data mining module is used for constructing a satisfaction evaluation model according to the service index data samples and the corresponding user satisfaction data samples based on a preset algorithm;

and the evaluation module is used for inputting the service index data to be evaluated into the satisfaction evaluation model to obtain a satisfaction evaluation result.

Optionally, the user satisfaction data samples comprise: service satisfaction data samples of various services and comprehensive satisfaction data samples of the whole service;

Optionally, the apparatus further comprises:

the deployment module is used for generating an application program according to the satisfaction evaluation model in a packaging mode and deploying and installing the application program in the signaling platform;

the evaluation module is further configured to:

Optionally, the apparatus further comprises: and the display module is used for displaying the satisfaction evaluation result.

Optionally, the apparatus further comprises: the backfill processing module is used for carrying out information backfill processing according to the business data sample; wherein, the information backfill processing comprises: and backfilling the international mobile subscriber identity.

According to yet another aspect of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the big data-based user satisfaction evaluation method.

According to still another aspect of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to the big data based user satisfaction evaluating method as described above.

According to the big data-based user satisfaction evaluation method and device, the service data samples of all preset interfaces of the core network are collected through the signaling platform, and the service data samples are analyzed and processed to obtain service index data samples; acquiring a user satisfaction data sample corresponding to the service data sample; based on a preset algorithm, constructing a satisfaction evaluation model according to the service index data samples and the corresponding user satisfaction data samples; and inputting the service index data to be evaluated into the satisfaction evaluation model to obtain a satisfaction evaluation result. The method comprises the steps of extracting objective business index data through a signaling platform, carrying out objective modeling, determining key index data and weight, establishing a mapping relation between the objective business index data and user subjective feelings by combining the distribution of subjective satisfaction data of sample users, and constructing a satisfaction evaluation model, so that the user satisfaction data is counted through the satisfaction evaluation model. The satisfaction degree of the user network service can be evaluated more quickly and conveniently by analyzing the model constructed by the big data, the 'blind' user in the network can be identified quickly, the degree of dependence on the subjective perception of the user in the satisfaction degree evaluation is reduced, the satisfaction degree index granularity is finer, and the problem point identification is quicker.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a flow chart diagram illustrating a big data based user satisfaction assessment method according to an embodiment of the present invention;

FIG. 2 is a flow chart diagram illustrating a big data based user satisfaction assessment method according to another embodiment of the present invention;

FIG. 3 is a schematic diagram illustrating a satisfaction questionnaire in accordance with an embodiment of the present invention;

FIG. 4 is a flow diagram illustrating the calculation of a principal component analysis algorithm in one embodiment of the present invention;

FIG. 5 is a diagram illustrating a user satisfaction computational model in one embodiment of the present invention;

FIG. 6 is a schematic structural diagram of a big-data-based user satisfaction evaluating apparatus according to yet another embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a big-data-based user satisfaction evaluating apparatus according to another embodiment of the present invention;

fig. 8 is a schematic structural diagram of a computing device provided in an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

Fig. 1 is a flowchart illustrating a big data-based user satisfaction evaluating method according to an embodiment of the present invention, where as shown in fig. 1, the method includes:

step S101, acquiring service data samples of each preset interface of the core network through a signaling platform, and analyzing and processing the service data samples to obtain service index data samples.

The method comprises the steps of acquiring service data samples of each interface in a core network through a signaling platform, and calculating and processing the acquired original service data samples to obtain service index data samples, namely original service books corresponding to sample users, such as KPI (Key performance indicator) data and KQI (KQI quality indicator) data.

Step S102, obtaining a user satisfaction degree data sample corresponding to the service data sample.

Meanwhile, user satisfaction data samples corresponding to the service data samples, that is, satisfaction data of the sample users, are also acquired. The user satisfaction data may specifically refer to: and the service satisfaction grading data and the service satisfaction grade data of the sample user to various services, and the comprehensive satisfaction grading data and the comprehensive satisfaction grade data to the service of the operator. In specific implementation, the satisfaction data of the sample user can be acquired in a questionnaire survey mode.

And S103, constructing a satisfaction evaluation model according to the service index data samples and the corresponding user satisfaction data samples based on a preset algorithm.

The business index data sample is objective index data of a sample user, and the user satisfaction data sample is subjective satisfaction data of the sample user, and can be called satisfaction investigation data. In the method of the embodiment, based on a big data processing mode, objective index data and subjective satisfaction data of sample users are mined and analyzed to obtain a calculation formula and weight of the index data for evaluating user satisfaction, and a mathematical model for evaluating user satisfaction is constructed.

And step S104, inputting the service index data to be evaluated into a satisfaction evaluation model to obtain a satisfaction evaluation result.

The satisfaction evaluation result is the user satisfaction score for the service evaluated by the operator. In this step, the basic service data of the user to be evaluated can be obtained, the service index data to be evaluated is obtained by calculation according to the above-mentioned manner of calculating the service index data, the service index data to be evaluated is input into the satisfaction evaluation model, and the satisfaction evaluation result is output.

According to the user satisfaction evaluation method based on big data provided by the embodiment, objective business index data are extracted through a signaling platform to carry out objective modeling, key index data and weight are determined, a mapping relation between the objective business index data and user subjective feelings is established by combining distribution of subjective satisfaction data of sample users, a satisfaction evaluation model is established, and then the user satisfaction data are counted through the satisfaction evaluation model. The model constructed by the big data is analyzed, so that the 'blind' user in the network can be quickly identified, the dependence degree on the subjective perception of the user is reduced, the satisfaction index granularity is finer, and the problem point identification is quicker. By the method, the overall evaluation range can be improved from a small number of sample users to a full number of users, the development of the satisfaction degree improving work can be more directional, and the range covering the users can be wider.

Fig. 2 is a flowchart illustrating a big data-based user satisfaction evaluating method according to another embodiment of the present invention, and as shown in fig. 2, the method includes:

step S201, acquiring a service data sample of each preset interface of the core network through a signaling platform, and analyzing and processing the service data sample to obtain a service index data sample.

The method comprises the steps of acquiring service data samples of each interface in a core network through a signaling platform, such as an S1-U interface, an S1-MME interface, an S11 interface and an S6a interface, and performing a series of calculation processing on the acquired original service data samples to obtain service index data samples.

Specifically, by calculating a service data sample, index data with a lower level is obtained: counter index data of a user perception class, a use action class and an event class, and L1 level index data; then, for the counter index data and/or the L1 level index data, the common index data therein is further calculated as the L2 and L3 level index data with higher level, and for some of the less common index data therein, it can be directly used as a sample without further calculation. Through the above steps, KPI index data and KQI index data can be obtained, that is, the index data samples for data mining analysis and modeling in this embodiment include: counter metric data and/or L1 level metric data and/or L2 level metric data and/or L3 level metric data.

Furthermore, since service data of some interfaces does not carry a user identifier, which user it originates from cannot be identified, it is necessary to perform information backfill processing on this type of service data. Specifically, information backfill processing is carried out according to a service data sample; wherein, the information backfill processing comprises: and backfilling the international mobile subscriber identity, namely backfilling the IMSI, for example, backfilling the IMSI in relation to the service data of the S1-U interface.

Step S202, obtaining a user satisfaction data sample corresponding to the service data sample.

Meanwhile, a user satisfaction data sample corresponding to the business data sample is obtained, and the user satisfaction data sample can be obtained in a questionnaire survey mode during specific implementation. The user satisfaction data specifically includes: the service satisfaction data samples of various services and the comprehensive satisfaction data samples of the whole services, wherein the comprehensive satisfaction data of the whole services is the satisfaction data of the user to the whole service of the operator. The satisfaction data in turn comprises satisfaction score data and satisfaction level data, i.e. the user satisfaction data samples comprise: and the grade of the satisfaction degree of the sample user to various services and the corresponding service satisfaction degree grade, the grade of the comprehensive satisfaction degree to the service of the operator and the corresponding comprehensive satisfaction degree grade data.

The system comprises a Web service, a satisfaction degree score and a satisfaction degree grade, wherein a binning rule between the satisfaction degree score and the satisfaction degree grade can be set according to actual needs, the satisfaction degree grade is also called an experience grade, the binning rule between the satisfaction degree score and the experience grade of the Web service is shown in the first table, and the binning rule between the comprehensive satisfaction degree score and the experience grade of the service is shown in the second table.

Watch 1

Satisfaction score for Web services	Experience, etcStage
		Q Web>80	Has good experience
60<Q Web≤80	General experience
		Q Web≤60	Poor experience

Watch two

CEI value of user integral service	Grade of experience
		QoE score>80	Has good experience
60<QoE score≤80	General experience
		QoE score≤60	Poor experience

Fig. 3 shows a schematic diagram of a satisfaction survey questionnaire in an embodiment of the present invention, where a user satisfaction data sample is obtained by way of questionnaire survey, and the survey questionnaire includes evaluation items that ask users to respectively inquire about experiences of various services, and also includes evaluation items that ask users to inquire about experiences of an operator for an overall service.

And S203, constructing a satisfaction evaluation model according to the service index data samples and the corresponding user satisfaction data samples based on a preset algorithm.

And mining and analyzing the service index data samples and the corresponding user satisfaction degree data samples based on a preset algorithm to obtain each key index data, weight value and calculation g rule for evaluating the user satisfaction degree, so as to construct a model for evaluating the user satisfaction degree. In the method, modeling is carried out based on a service index data sample, key indexes and weights are determined, and a mapping relation between objective service indexes and subjective service perception is established according to subjective service perception distribution fed back by user satisfaction data, so that a mathematical model for evaluating user satisfaction is constructed.

In this embodiment, a principal component analysis method is used for data mining analysis, and fig. 4 shows a flow diagram of a calculation process of a principal component analysis algorithm in an embodiment of the present invention. In the principal component analysis method, an orthogonal transformation is used to convert a vector X with relevant components into (X1, X2, …, xp) T, and the vector X with irrelevant components points to point to p orthogonal directions with the most spread sample points, and then the multidimensional variable system is subjected to dimensionality reduction processing, so that the multidimensional variable system can be converted into a low-dimensional variable system with higher precision. The variable weight is determined by applying the principal component, and the other application direction of the principal component is extended: comprehensive evaluation function of the main component.

The weight of each evaluation factor is determined by using the first principal component obtained by the principal component analysis method. Determining the variable weight by using the principal component, namely using the comprehensive evaluation function of the principal component; the first principal component can explain the maximum variance of all factors (having the maximum characteristic root), the second principal component and the third principal component are decreased, the common consistency of the symbol directions of the factors on the first principal component is realized, and generally, people can use the first principal component to express the attributes such as high or low performance, high or low activity and the like; the second main component embodies the characteristics of balance and special aspects; each variable is subjected to data standardization conversion so as to eliminate the influence of the dimension and the variation size and the numerical value of the index variable; all the weights are added to 1 by the normalization process.

Fig. 5 is a schematic diagram illustrating a user satisfaction calculation model according to an embodiment of the present invention, where W1, W2, W3, W4, and W5 are weight values of various service scores in the model for calculating the comprehensive user satisfaction, W1 is a weight value of Voice Score, W2 is a weight value of SMS Score, W3 is a weight value of Web Score, W4 is a weight value of streamline Score, and W5 is a weight value of IM Score. W6 and W7 are weight values of HTTP Score calculated by KQI index data and weight values of HTTP Score calculated by KPI index data, respectively, in a model for calculating a user satisfaction Score of a Web service. W8 and W9 are similar to W6 and W7, and are not described in detail herein. Wi _1 is a weighted value of each KQI index data in the model of Voice Score calculated by the KQI index data, and Wi _2, Wi _3, Wi _4 and Wi _5 are similar and are not repeated herein.

In practical application, heuristic factor analysis is applied to calculate customer satisfaction, and the weight, dependency relationship and importance of each measurement factor are determined by a mathematical method, so that a formula sample as shown in the following table can be obtained:

wherein, Web _ Score is 8, which represents a boundary in the binning rule, when Web _ Score is <8, which represents that the user satisfaction is poor experience, and when Web _ Score >8, which represents that the user satisfaction is good experience, this is merely an example, and the present invention is not limited to this. The calculation formula shown in table three is a specific formula for calculating Web _ Score by weighted summation according to each index data and its weight.

Watch 1

In this embodiment, the mathematical model expression for evaluating the user satisfaction obtained through big data mining analysis includes:

the formula (1) is to perform weighted summation on the basic KPI indexes of various services, the weights are automatically mined and calculated through big data, and the calculated result is the score of the corresponding service.

KQI_Score=∑Wi×KPIi (1)

And the formula (2) is a formula for weighting and summing the respective KQI scores of the Web services to evaluate the satisfaction score of the Web services, and the weight coefficient is automatically mined and calculated through big data. Similarly, the satisfaction scoring formulas for other broad classes of services, such as video, instant messaging, etc., are similar and not listed here.

Web_Score＝∑Wi×KQI_Score_i (2)

And the formula (3) is a formula for continuously carrying out weighting summation on various service scores to evaluate the comprehensive satisfaction, and the weights are obtained by iterative calculation of a big data mining analysis module.

Score(User)＝Web_Score*W1+Stream_Score*W2+IM_Score*W3+……(3)

And step S204, packaging and generating the application program according to the satisfaction evaluation model, and deploying and installing the application program in the signaling platform.

Specifically, parameters such as a calculation formula and weight of a mathematical model obtained by data mining are packaged to generate an application program, and the application program is installed in a signaling platform.

Step S204, obtaining the service index data to be evaluated, processing the service index data to be evaluated through an application program deployed in a signaling platform to obtain a satisfaction evaluation result, and displaying the satisfaction evaluation result.

In the step, basic service data of a user to be evaluated can be obtained, the service index data to be evaluated is obtained through calculation according to the mode of calculating the service index data, the service index data to be evaluated is input into the satisfaction degree evaluation model, the satisfaction degree evaluation result is output, and meanwhile, the satisfaction degree evaluation result is displayed for background personnel to monitor the user satisfaction degree. Accordingly, the satisfaction evaluation result may include a service satisfaction evaluation result (including a satisfaction score and a satisfaction level) for each type of service, and a comprehensive satisfaction evaluation result (including a satisfaction score and a satisfaction level) for the operator service.

Therefore, according to the user satisfaction evaluation method based on the big data, the model constructed by the big data is analyzed, the users do not need to be investigated one by one, the dependence on the subjective perception of the users is reduced, the 'blind' users in the network can be automatically and quickly identified, the dependence on the subjective perception of the users is reduced, the satisfaction index granularity is finer, and the problem point identification is quicker. By the method, the overall evaluation range can be improved from a small number of sample users to a full number of users, the development of the satisfaction degree improving work can be more directional, and the range covering the users can be wider. In application, satisfaction survey can be achieved through a platform means, a large amount of manpower and material resources are saved, blind users in a network can be identified, intervention is carried out in advance, complaint amount is reduced, areas with low satisfaction scores are optimized in advance, and user perception is improved.

A specific embodiment of the present invention is described below, first, a sample user is investigated, and the purpose of the investigation is to check the experience score distribution of the user for each service and the whole service, that is, to collect a user satisfaction data sample, where the user satisfaction data sample includes the original score and the binning rule, for example, the questionnaire shown in fig. 3 is used to collect the user satisfaction data sample. Secondly, collecting real KQI/KPI index data, using SPSS/R (statistical product and service solution software) to perform factor analysis and subjective and objective correlation analysis on the index data, and obtaining the weight of each index data. And finally, applying the weight of each index data, the original score and the box dividing rule to the modeling of all users to obtain a calculation model for calculating the service satisfaction of all network users, so that the service satisfaction of all network users can be calculated.

Fig. 6 is a schematic structural diagram of a big-data-based user satisfaction evaluating apparatus according to another embodiment of the present invention, as shown in fig. 6, the apparatus includes:

the data acquisition module 61 is used for acquiring service data samples of each preset interface of the core network through the signaling platform; acquiring a user satisfaction data sample corresponding to the service data sample;

the data processing module 62 is configured to analyze and process the service data sample to obtain a service index data sample;

the data mining module 63 is configured to construct a satisfaction evaluation model according to the service index data samples and the corresponding user satisfaction data samples based on a preset algorithm;

and the evaluation module 64 is used for inputting the service index data to be evaluated into the satisfaction evaluation model to obtain a satisfaction evaluation result.

Optionally, the apparatus further comprises:

the evaluation module is further configured to:

According to the method, objective business index data and user subjective satisfaction data are extracted for mining analysis, a satisfaction evaluation model is constructed, the satisfaction of user network services can be evaluated more quickly and conveniently by applying the model, so that users 'impersonation' in a network can be identified quickly, and the degree of dependence on user subjective perception is reduced.

Fig. 7 is a schematic structural diagram of a big-data-based user satisfaction evaluating apparatus according to another embodiment of the present invention, as shown in fig. 7, the apparatus including: a data preprocessing module 71, a memory computing module (IMC)72, a data storage and real-time computing module 73, a big data mining analysis module 74, and a data presentation module 75.

The data preprocessing module 71, the memory computing module (IMC)72, and the data storage and real-time computing module 73 may be implemented based on a signaling platform, and the big data mining analysis module 74 and the data presentation module 75 may be deployed separately. Of course, the invention is not limited thereto.

The data pre-processing module 71 in turn comprises two sub-modules: the data preprocessing module 71 may further include a data distribution module, and the data distribution module is configured to distribute the service data.

An internal memory computing module (IMC)72, configured to receive the document output by the preprocessing module, and compute and output service index data, for example, to perform scheduling on part of counter index data and/or L1 level index data to compute and output L2 level index data, where the service index data output by the IMC includes: counter metric data and/or L1 level metric data and/or L2 level metric data.

And a data storage and real-time calculation module 73, including Hadoop, Spark SQL, and IQ library. The device is configured to perform an operation on a part of the service index data output by the memory calculation module 72 to obtain a higher-level service index number, such as L3-level index data, which includes KPI index data and KQI index data. A portion of the memory is also developed in the data storage and real-time computation module 73 to be used as a sandbox, which functions in cooperation with the big data mining analysis module 74 to perform modeling and tuning work.

And the big data mining analysis module 74 is used for mining and analyzing the data output by the data storage and real-time calculation module 73, packaging the modeling result to generate an APP, and automatically deploying the APP into the data storage and real-time calculation module 74 through a signaling platform. In the big data mining module 74, the data mining analysis process is as follows: the core algorithm adopts a principal component analysis algorithm, and index data such as KPI index data, KQI index data and the like and user research data are mined and analyzed to obtain each index data for evaluating user satisfaction, weight thereof, a calculation formula and the like.

And the data presentation module 75 is configured to present an index result of the APP operation, that is, evaluate the obtained user satisfaction result, so as to facilitate monitoring of the user satisfaction by background personnel.

The flow of data in this embodiment is described below by taking an XDR document as an example.

Firstly, an XDR document enters a data preprocessing module 71 through probe acquisition, and aggregation and IMSI information backfill are completed in the data preprocessing module 71.

And secondly, the data preprocessing module outputs L1 level index data to the IMC module, part of the L1 level data is directly calculated into L2 level indexes and sent into hadoop through data layout calculation, and the IMC module calculates the XDR document backfilled with the IMSI into counter index data.

And thirdly, receiving counter index data from the IMC module and L2 level index data output by data arrangement by Hadoop, and sending the index data to Sandbox for calculation.

And fourthly, the Sandbox is butted with an API (application program interface) from a big data analysis module, and the Sandbox calculates index data in hadoop by using the API of the big data module.

And fifthly, the big data mining analysis module 74 performs data mining through data of the Sandbox, models the APP according to the data mining result, and automatically deploys the APP to the spark SQL.

And sixthly, sending the index data in the Hadoop to spark SQl, periodically calculating through the APP modeled by the big data, and sending the calculation result and the index data in the Hadoop to an IQ library for storage.

Seventhly, the analysis result of the IQ library presents a final result through the data presenting module 75, and the presented result includes the service data of the index to be evaluated and the corresponding satisfaction evaluation result.

It should be noted that the scheme of the present invention may be divided into two execution phases, where the first phase is a model building phase and the second phase is a model application phase. In the model construction stage, business data of each interface of a core network corresponding to a sample user are obtained, the business data samples are calculated to obtain business index data samples, big data mining analysis is carried out by combining with a user satisfaction investigation result, and a model for evaluating the user satisfaction is constructed; in the model application stage, service data of each interface of the core network corresponding to the user to be evaluated is obtained, the service index data to be evaluated is obtained through calculation according to the mode of calculating the service index data, and then the service index data to be evaluated is input into the user satisfaction evaluation model, so that a user satisfaction evaluation result corresponding to the user to be evaluated is obtained.

Wherein the model building phase comprises: and (4) carrying out big data mining analysis by combining the SEQ original index and the user investigation result (such as KQI data and supervisor investigation result) to obtain the calculation rule and index weight of the index data, and constructing a satisfaction calculation model. And in the model application stage, obtaining the SEQ original index, calculating to obtain an objective KQI index, inputting the objective KQI index into a satisfaction calculation model, and outputting a plurality of the scores of the satisfaction of the residential business and the scores of the satisfaction of the whole network.

Embodiments of the present invention provide a non-volatile computer storage medium, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction may execute the big data-based user satisfaction evaluation method in any of the above method embodiments.

The executable instructions may be specifically configured to cause the processor to:

In an alternative approach, the user satisfaction data samples include: service satisfaction data samples of various services and comprehensive satisfaction data samples of the whole service;

In an alternative, the executable instructions cause the processor to:

after a satisfaction evaluation model is built according to the service index data samples and the corresponding user satisfaction data samples, an application program is generated by packaging according to the satisfaction evaluation model, and the application program is deployed and installed in a signaling platform;

the executable instructions cause the processor to:

In an alternative, the executable instructions cause the processor to:

and displaying the satisfaction evaluation result.

In an alternative, the executable instructions cause the processor to:

after business data samples of all preset interfaces of a core network are collected through a signaling platform, information backfill processing is carried out according to the business data samples; wherein, the information backfill processing comprises: and backfilling the international mobile subscriber identity.

In an optional manner, the preset interface includes: an S1-U interface, an S1-MME interface, an S11 interface and an S6a interface; the service index data sample or the service index data to be evaluated comprises the following data: user perception class, counter indicator data using action class and event class, KPI indicator data and KQI indicator data.

In an alternative mode, the preset algorithm is embodied as a principal component analysis algorithm.

Fig. 8 is a schematic structural diagram of an embodiment of a computing device according to the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the XXXX device.

As shown in fig. 8, the computing device may include: a processor (processor)802, a Communications Interface 804, a memory 806, and a communication bus 808.

Wherein: the processor 802, communication interface 804, and memory 806 communicate with one another via a communication bus 808. A communication interface 804 for communicating with network elements of other devices, such as clients or other servers. The processor 802, configured to execute the program 810, may specifically perform relevant steps in the above-described big-data-based user satisfaction assessment method embodiments for a computing device.

In particular, the program 810 may include program code comprising computer operating instructions.

The processor 802 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.

The memory 806 stores a program 810. The memory 806 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 810 may be specifically configured to cause the processor 802 to perform the following operations:

In an optional mode, service satisfaction data samples of various services and comprehensive satisfaction data samples of the whole service are obtained;

In an alternative, the program 810 causes the processor 802 to:

the program 810 causes the processor to perform the following operations:

In an alternative, the program 810 causes the processor 802 to:

and displaying the satisfaction evaluation result.

In an alternative, the program 810 causes the processor 802 to: after business data samples of all preset interfaces of a core network are collected through a signaling platform, information backfill processing is carried out according to the business data samples; wherein, the information backfill processing comprises: and backfilling the international mobile subscriber identity.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.

Claims

1. A big data-based user satisfaction evaluation method comprises the following steps:

acquiring service data samples of each preset interface of a core network through a signaling platform, and analyzing and processing the service data samples to obtain service index data samples;

acquiring a user satisfaction data sample corresponding to the service data sample;

based on a preset algorithm, constructing a satisfaction evaluation model according to the service index data samples and the corresponding user satisfaction data samples;

and inputting the service index data to be evaluated into the satisfaction evaluation model to obtain a satisfaction evaluation result.

2. The method of claim 1, wherein the user satisfaction data samples comprise: service satisfaction data samples of various services and comprehensive satisfaction data samples of the whole service;

3. The method according to claim 1 or 2, wherein after the building of the satisfaction assessment model from the service index data samples and their corresponding user satisfaction data samples, the method further comprises:

packaging and generating an application program according to the satisfaction evaluation model, and deploying and installing the application program in the signaling platform;

inputting the service index data to be evaluated into the satisfaction evaluation model, and obtaining a satisfaction evaluation result further comprises:

and acquiring service index data to be evaluated, and processing the service index data to be evaluated through an application program deployed in a signaling platform to obtain a satisfaction evaluation result.

4. The method of claim 1, wherein the method further comprises: and displaying the satisfaction evaluation result.

5. The method of claim 1, wherein after the collecting, by the signaling platform, the service data samples of the preset interfaces of the core network, the method further comprises:

carrying out information backfill processing according to the service data sample; wherein the information backfilling process comprises: and backfilling the international mobile subscriber identity.

6. The method of claim 1, wherein the preset interface comprises: an S1-U interface, an S1-MME interface, an S11 interface and an S6a interface; the service index data sample or the service index data to be evaluated comprises: user perception class, counter indicator data using action class and event class, KPI indicator data and KQI indicator data.

7. The method according to claim 1, wherein the predetermined algorithm is in particular a principal component analysis algorithm.

8. A big-data-based user satisfaction evaluation apparatus, comprising:

9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the big data based user satisfaction evaluation method according to any one of claims 1-7.

10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the big data based user satisfaction evaluation method of any of claims 1-7.