CN113837514A - User satisfaction evaluation method and device, computing device and storage medium - Google Patents
User satisfaction evaluation method and device, computing device and storage medium Download PDFInfo
- Publication number
- CN113837514A CN113837514A CN202010588046.5A CN202010588046A CN113837514A CN 113837514 A CN113837514 A CN 113837514A CN 202010588046 A CN202010588046 A CN 202010588046A CN 113837514 A CN113837514 A CN 113837514A
- Authority
- CN
- China
- Prior art keywords
- index
- user satisfaction
- wireless network
- data
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims description 25
- 230000035945 sensitivity Effects 0.000 claims abstract description 107
- 238000000034 method Methods 0.000 claims abstract description 55
- 238000013210 evaluation model Methods 0.000 claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000010801 machine learning Methods 0.000 claims abstract description 20
- 230000008859 change Effects 0.000 claims description 43
- 230000008447 perception Effects 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 208000018910 keratinopathic ichthyosis Diseases 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000012549 training Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000005065 mining Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000010354 integration Effects 0.000 description 4
- 238000010295 mobile communication Methods 0.000 description 4
- 238000010206 sensitivity analysis Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a method and a device for evaluating user satisfaction, computing equipment and a storage medium, wherein the method comprises the following steps: acquiring index data of at least one wireless network index and user satisfaction data; calculating a sensitivity coefficient of the user satisfaction degree to at least one wireless network index according to the index data of at least one wireless network index and the user satisfaction degree data; constructing a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction on at least one wireless network index; performing tuning processing on the user satisfaction evaluation model by adopting a machine learning algorithm; and evaluating the user satisfaction based on the user satisfaction evaluation model. Through the mode, the more sensitive wireless network indexes and the sensitivity thereof are searched through the objective data of the network side, and compared with a setting mode which is completely limited by manual experience, the method has higher scientificity, objectivity and rationality; and, the satisfaction degree of the user to the service can be accurately evaluated from objective data on the network side.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for evaluating user satisfaction, computing equipment and a storage medium.
Background
With the continuous development of the mobile communication market, the competition of mobile communication services is increasingly intense, the market competition is changed from simple technical competition and price competition into comprehensive competition of service, price and service innovation at present, and the service quality and the user satisfaction degree are crucial to attracting and retaining users. The user satisfaction is a core concept in a CRM (Customer Relationship Management) system, and is a matching degree between a user expectation value and a final obtained value.
The existing user satisfaction evaluation work is developed in the form of a questionnaire, and the main query indexes include but are not limited to: 1. voice call quality, 2 mobile phone internet quality, 3 price package, 4 business propaganda, 5 business handling, 6 reminding service, 7 consulting complaint and other seven major indexes, and user satisfaction is calculated through the index and score mapping relation.
However, the inventor finds that the prior art has at least the following defects in the process of implementing the invention: firstly, the sampling capacity samples are obviously few, the current mobile 4G user stock is about 7.35 hundred million, and 350 ten thousand users are added in the last half and month of 2019, for example, according to the existing evaluation method, the sample proportion accounts for the total number
A large short board exists in the accuracy, cost consumption and the like of the evaluation method; secondly, the evaluation data source is too single, feedback is basically only carried out in a user subjective mode, the sampling result is influenced by the sensitivity of the user to one or more factors, for example, the user is sensitive to the expense, under the condition that the network quality is still enough, the expectation cannot be reached, and the user is most likely to carry out derogation feedback in satisfaction degree investigation, so that the condition of' one loss is caused; thirdly, the weights of all the query indexes and the mapping satisfaction degree scores are preset artificially and empirically and depend on the top-level party to a great extentThe subjective factors of the case designer, such as learning, experience and prejudgement, cannot form an optimal weight system with scientific, objective and linkage properties.
Disclosure of Invention
In view of the above, the present invention has been made to provide an evaluation method, apparatus, computing device, and storage medium for user satisfaction that overcome or at least partially address the above-mentioned problems.
According to an aspect of the present invention, there is provided a user satisfaction evaluation method, including:
acquiring index data of at least one wireless network index and user satisfaction data;
calculating a sensitivity coefficient of the user satisfaction degree to at least one wireless network index according to the index data of at least one wireless network index and the user satisfaction degree data;
constructing a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction on at least one wireless network index;
performing tuning processing on the user satisfaction evaluation model by adopting a machine learning algorithm;
and evaluating the user satisfaction based on the user satisfaction evaluation model.
Optionally, calculating a sensitivity coefficient of the user satisfaction to the at least one wireless network indicator according to the indicator data of the at least one wireless network indicator and the user satisfaction data further comprises:
for any wireless network index, determining the change rate of user satisfaction data when the change rate of the index data of the wireless network index is a preset value under the condition that the index data of other wireless network indexes are not changed;
and calculating the sensitivity coefficient of the user satisfaction to the wireless network index according to the change rate of the index data of the wireless network index and the change rate of the user satisfaction data.
Optionally, after calculating a sensitivity coefficient of the user satisfaction to the at least one wireless network indicator, the method further comprises:
and aiming at any wireless network index, judging whether the absolute value of the sensitivity coefficient of the user satisfaction degree to the wireless network index reaches a preset threshold value, if so, retaining the sensitivity coefficient of the user satisfaction degree to the wireless network index, otherwise, filtering the sensitivity coefficient of the user satisfaction degree to the wireless network index.
Optionally, the wireless network metrics include one or more of: an O domain index, a B domain index and an M domain index;
and the user satisfaction data is obtained by calculation according to the scores of the users on each satisfaction query index and the weight value of each satisfaction query index.
Optionally, the method further comprises:
analyzing the index data of the O-domain index to determine the quality grade information of the network quality;
analyzing the index data of the B-domain index to determine the quality grade information of the timeliness of complaint treatment;
and generating a user perception portrait according to the quality grade information of the network quality and the quality grade information of the complaint processing timeliness.
According to another aspect of the present invention, there is provided an evaluation apparatus of user satisfaction, including:
the data acquisition module is suitable for acquiring index data of at least one wireless network index and user satisfaction data;
the sensitivity evaluation module is suitable for calculating the sensitivity coefficient of the user satisfaction degree to at least one wireless network index according to the index data of at least one wireless network index and the user satisfaction degree data;
the model building module is suitable for building a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction on at least one wireless network index;
the tuning processing module is suitable for tuning the user satisfaction evaluation model by adopting a machine learning algorithm;
and the satisfaction evaluation module is suitable for evaluating the user satisfaction based on the user satisfaction evaluation model.
Optionally, the sensitivity evaluation module is further adapted to:
for any wireless network index, determining the change rate of user satisfaction data when the change rate of the index data of the wireless network index is a preset value under the condition that the index data of other wireless network indexes are not changed;
and calculating the sensitivity coefficient of the user satisfaction to the wireless network index according to the change rate of the index data of the wireless network index and the change rate of the user satisfaction data.
Optionally, the apparatus further comprises:
and the filtering module is suitable for judging whether the absolute value of the sensitivity coefficient of the user satisfaction degree to the wireless network index reaches a preset threshold value or not aiming at any wireless network index, if so, the sensitivity coefficient of the user satisfaction degree to the wireless network index is reserved, and otherwise, the sensitivity coefficient of the user satisfaction degree to the wireless network index is filtered.
Optionally, the wireless network metrics include one or more of: an O domain index, a B domain index and an M domain index;
and the user satisfaction data is obtained by calculation according to the scores of the users on each satisfaction query index and the weight value of each satisfaction query index.
Optionally, the apparatus further comprises:
the user portrait generation module is suitable for analyzing the index data of the O domain index and determining the quality grade information of the network quality; analyzing the index data of the B-domain index to determine the quality grade information of the timeliness of complaint treatment; and generating a user perception portrait according to the quality grade information of the network quality and the quality grade information of the complaint processing timeliness.
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 user satisfaction evaluation method.
According to still another aspect of the present invention, a computer storage medium is provided, in which at least one executable instruction is stored, and the executable instruction causes a processor to perform operations corresponding to the above-mentioned user satisfaction evaluation method.
According to the evaluation method, the evaluation device, the computing equipment and the storage medium of the user satisfaction degree, the method comprises the following steps: acquiring index data of at least one wireless network index and user satisfaction data; calculating a sensitivity coefficient of the user satisfaction degree to at least one wireless network index according to the index data of at least one wireless network index and the user satisfaction degree data; constructing a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction on at least one wireless network index; performing tuning processing on the user satisfaction evaluation model by adopting a machine learning algorithm; and evaluating the user satisfaction based on the user satisfaction evaluation model. Through the mode, on one hand, the more sensitive wireless network indexes and the sensitivity thereof are searched through the objective data of the network side, and compared with a setting mode which is completely limited by manual experience, the method has higher scientificity, objectivity and rationality; on the other hand, the degree of satisfaction of the user with the service can be accurately evaluated from objective data on the network side.
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 illustrating a method for evaluating user satisfaction provided by an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for evaluating user satisfaction provided by another embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a single item data sensitivity analysis in an embodiment of the present invention;
FIG. 4 is a flow chart illustrating a method for evaluating user satisfaction in an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus for evaluating user satisfaction provided by an embodiment of the present invention;
fig. 6 shows a schematic structural diagram of a computing device provided by 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 shows a flowchart of a user satisfaction evaluating method provided by an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step S110, index data of at least one wireless network index and user satisfaction data are obtained.
The wireless network indicator is a network-side objective indicator of the wireless network, such as a KPI indicator of an O domain, a KPI indicator of a B domain, a KPI indicator of an M domain, and the like. The user satisfaction data is the subjective score of the user on the service provided by the mobile communication, and is mainly obtained in a manual questionnaire mode and a telephone inquiry mode, and is obtained by calculating according to the score of the user on each satisfaction inquiry index and the weighted value of each satisfaction inquiry index.
And step S120, calculating a sensitivity coefficient of the user satisfaction degree to the at least one wireless network index according to the index data of the at least one wireless network index and the user satisfaction degree data.
The purpose of this step is: and analyzing the relation between the wireless network index and the user satisfaction, and evaluating the sensitivity of the user satisfaction to the wireless network index data, namely the influence degree of the wireless network index on the user satisfaction. And calculating the sensitivity coefficient of the user satisfaction degree to each wireless network index, wherein the larger the sensitivity coefficient is, the more the influence of the user satisfaction degree on the wireless network index is, and the more the user satisfaction degree is sensitive to the wireless network index.
And step S130, constructing a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction to at least one wireless network index.
After the sensitivity coefficient of the user satisfaction degree to each wireless network index is calculated, the sensitivity coefficients of the wireless network indexes are integrated, and a weighting algorithm model for calculating the user satisfaction degree is constructed. For example, the user satisfaction evaluation model is: the user satisfaction is the index value of index 1 × sensitivity coefficient 1+ index value of index 2 × sensitivity coefficient 2+ … … + index value × sensitivity coefficient n.
And step S140, performing tuning treatment on the user satisfaction evaluation model by adopting a machine learning algorithm.
After the user satisfaction evaluation model is initially constructed, the user satisfaction evaluation model is further optimized, so that the accuracy of the user satisfaction evaluation model is improved. Specifically, more wireless network index data and corresponding user satisfaction data are obtained as training samples by adopting a machine learning algorithm, and the sensitivity coefficient in the user satisfaction evaluation model is continuously updated so as to continuously improve the accuracy of the user satisfaction model.
And S150, evaluating the user satisfaction based on the user satisfaction evaluation model.
In the subsequent process, when the user satisfaction needs to be evaluated, wireless network index data corresponding to the user is obtained, and the user satisfaction evaluation model is adopted for calculation to obtain the user satisfaction.
The user satisfaction in the general sense is the scoring of the user based on subjective perception, and under the same condition, the user satisfaction is often not matched with the service value actually provided by the operator due to the influence of the user subjective perception. In the embodiment of the application, the user satisfaction is evaluated based on objective index data of a network side.
In summary, the method of this embodiment analyzes the mapping relationship between the network index data and the user satisfaction data according to objective wireless network index data and subjective user satisfaction data, calculates the sensitivity of the user satisfaction to the wireless network index, establishes a model for calculating the user satisfaction from the wireless network index data based on the sensitivity of each wireless network index, optimizes the preliminarily established user satisfaction evaluation model based on a machine learning manner, and can evaluate the user satisfaction objectively by using the user satisfaction evaluation model. On one hand, the method of seeking more sensitive wireless network indexes through objective data of a network side has higher scientificity, objectivity and rationality compared with a setting method completely limited by manual experience; on the other hand, the satisfaction degree of the user to the service can be accurately evaluated from objective data of the network side, the perception portrait of the user can be completed, a potential user group with poor satisfaction degree can be comprehensively mined, and then the satisfaction degree promotion strategy can be accurately adapted.
Fig. 2 is a flowchart illustrating a method for evaluating user satisfaction according to another embodiment of the present invention, and as shown in fig. 2, the method includes the following steps:
step S210, index data of at least one wireless network index and user satisfaction data are obtained.
The wireless network index is an objective index of the wireless network, and comprises an O-domain index, a B-domain index, M-domain data and the like. The user satisfaction data is the subjective score of the user on the service provided by the mobile communication, and mainly depends on the manual questionnaire mode and the telephone inquiry mode.
Wherein, the O domain: in the data field of Operation support system, the O field index mainly covers the relevant indexes of the network quality, such as: VOLTE call completing rate, VOLTE call dropping rate, VOLTE single call completing rate and the like in the OMC, webpage browsing and refreshing time length in an end-to-end System (SEQ), video buffering time length, instant messaging end-to-end time delay, game experience blocking rate and the like.
B domain: in the data field of Business support system, the B-field index mainly covers user data and service data, such as: user information, user consumption habits, terminal information, ARPU grouping, service contents, service audience groups and the like.
And M domain: data field of Management support system, B field data mainly covers position information, such as: crowd flow trajectory, map information, etc.
Optionally, after step S210, the following steps are further performed: and screening out at least one target wireless network index from the at least one wireless network index. In the subsequent steps, the selected target wireless network indexes are processed. Specifically, based on expert experience, the selection is performed according to the influence on the target index when the wireless network index changes or according to the probability of adopting the wireless network index in the modeling process.
Step S220, for any wireless network index, determining a change rate of the user satisfaction data when the change rate of the index data of the wireless network index is a preset value under the condition that the index data of other wireless network indexes are not changed.
The purpose of this step is to analyze the influence of the fluctuation degree of the index data of the wireless network index on the user satisfaction. The method adopts a single data source sensitivity analysis mode to respectively evaluate the sensitivity of the user satisfaction degree to each data source, namely the wireless network index.
Specifically, the method ensures that the selected wireless network index data only has one dependent variable, the index data of the rest wireless network indexes are kept unchanged, and the change rate of the user satisfaction when the index data of the wireless network indexes serving as the dependent variables change values according to a certain change amplitude is calculated.
Step S230, calculating a sensitivity coefficient of the user satisfaction for the wireless network index according to the change rate of the index data of the wireless network index and the change rate of the user satisfaction data.
Watch 1
The sensitivity coefficient of the user satisfaction to the wireless network index is the change rate of the user satisfaction data/the change rate of the index data of the wireless network index. Table one shows a single data sensitivity analysis matrix in an embodiment of the present invention.
And analyzing by taking the VOLTE call completing rate as single data, and calculating the sensitivity coefficient of the index data according to a single data sensitivity formula, wherein the single data sensitivity formula calculation formula is as follows:
in this embodiment, a is user satisfaction data, and F is an index value of a wireless network index.
For example, when the change rate of the VOLTE call completing rate is 5% (the data of other wireless network indicators remain unchanged), the change rate of the user satisfaction degree is: (X)P5-XP)/XPAnd then the sensitivity coefficient of the call completing rate of the VOLTE is as follows:
and the sensitivity coefficients of the VOLTE call completing rate under different change rates are analogized according to the mode, and the sensitivity coefficients are calculated by the rest of the O-domain indexes, the B-domain indexes and the M-domain indexes according to the mode, which is not described herein again. Finally, the sensitivity coefficient of each wireless network index can be obtained: sAF1、SAF2、SAF3…SAFn。
Step S240, determining whether an absolute value of a sensitivity coefficient of the user satisfaction to the wireless network index reaches a preset threshold, if so, retaining the sensitivity coefficient of the user satisfaction to the wireless network index, otherwise, filtering out the sensitivity coefficient of the user satisfaction to the wireless network index.
The sensitivity coefficient S of the user satisfaction degree to the wireless network index is calculated through the stepsAFWherein S isAF>0, representing the positive change of the user satisfaction degree and the wireless network index; sAF<0, representing that the user satisfaction and the wireless network index reversely change; i SAFIf the greater the | is, the more sensitive the user satisfaction is to the wireless network index is, the key factors influencing the user satisfaction can be judged according to the sensitivity coefficient.
Specifically, whether the absolute value of the sensitivity coefficient reaches a preset threshold value is judged, if yes, the wireless network index is a key factor influencing the user satisfaction degree, otherwise, the wireless network index is not a key factor influencing the user satisfaction degree, and the wireless network index is filtered out in order to save computing resources.
FIG. 3 is a diagram showing a single term data sensitivity analysis in an embodiment of the present invention, in which the variation amplitude Δ F/F of the data source, the customer satisfaction degree, and the customer satisfaction degree Xp are fitted to straight line functions, the slope of each straight line reflects the sensitivity of the customer satisfaction degree to the data source, and the greater the slope, the higher the sensitivity.
And step S250, constructing a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction to each wireless network index.
The step of constructing the user satisfaction evaluation model refers to constructing a model based on KPI index values of each data source and sensitivity coefficients of each data source, wherein the data sources are wireless network indexes, and the user satisfaction model is as follows:
user satisfaction (KPI index value S of data source 1)AF1+ KPI index value S of data Source 1AF2+ … … + KPI index value S for data Source nAFn
And step S260, performing tuning treatment on the user satisfaction evaluation model by adopting a machine learning algorithm.
The machine learning model has the function that on the basis of the user satisfaction evaluation, parameter model tuning (fine tuning correction and iterative updating) is further carried out through optimization strategy machine learning, and training sample data mainly is acquired index data of wireless network indexes and corresponding user satisfaction data.
Optionally, a GBDT algorithm and an XGboost algorithm in the integrated algorithm are adopted for semi-supervised learning, so that parameters of the user satisfaction evaluation model are optimized.
The GBDT (Gradient Boosting Decision Tree) is an algorithm for classifying or regressing data by using an additive model (i.e., a linear combination of basis functions) and continuously reducing residual errors generated in a training process, and the model accuracy is higher than that of a general machine learning classification algorithm.
The GBDT generates a weak classifier through multiple iterations, each iteration generates a weak classifier, and each classifier is trained on the residual error of the last classifier. The requirements for weak classifiers are generally sufficiently simple and are low variance and high variance. Because the training process is to continuously improve the accuracy of the final classifier by reducing the bias. The weak classifiers are typically selected as classification regression trees. The regression tree depth for each class is not very deep due to the high variance and simplicity requirements described above. The final total classifier is obtained by weighting and summing the weak classifiers obtained by each training round, namely, an addition model. The loss function can be reduced as quickly as possible during each round of training, and the local optimal solution or the global optimal solution can be reached through convergence as quickly as possible.
The XGboost (eXtreme Gradient Boosting) is a supervision model algorithm, and the training task mainly searches for an optimal parameter set by minimizing an objective function. For the classification problem, since the corresponding value of the leaf node of the CART tree is an actual score, not a definite category, it is beneficial to implement an efficient optimization algorithm.
Step S270, evaluating the user satisfaction degree based on the user satisfaction degree evaluating model.
In the subsequent process, when the user satisfaction needs to be evaluated, the index data of each wireless network index corresponding to the user is obtained, the user satisfaction evaluation model is adopted for calculation, and the user satisfaction is obtained and is evaluated based on the objective index data of the network side.
Optionally, the method of this embodiment further includes the following steps: analyzing the index data of the O-domain index to determine the quality grade information of the network quality; analyzing the index data of the B-domain index to determine the quality grade information of the timeliness of complaint treatment; and generating a user portrait according to the quality grade information of the network quality and the quality grade information of the complaint processing timeliness.
The network quality mainly relates to O-domain indicators, such as KPI indicators of coverage rate, call drop rate, etc., and the quality of the network quality can be evaluated according to the O-domain indicators. The timeliness of complaint handling mainly relates to B-domain indicators, such as KPIs like ARPU grouping (related to customer importance), and 10086 platform data. In the embodiment, the O domain index is analyzed to determine the quality condition of the network quality, the B domain index is analyzed to determine the quality condition of the complaint processing timeliness, and finally, the user perception portrait is analyzed according to the quality condition of the network quality and the quality condition of the complaint processing timeliness, so that the purpose of mining the user perception portrait according to objective index data of the network side is achieved, corresponding measures can be taken according to the user perception portrait, and the situation that a user subjectively gives a score with low satisfaction degree and even carries the portrait is avoided. In practical application, the method can predict and mine the potential user group with poor satisfaction degree, and further can develop the satisfaction degree improving work aiming at the user group.
For example, in the case of both network quality and complaint handling timeliness dimensionality, if the user scores low, the user is maliciously derogated; under the condition that the network quality and the complaint handling timeliness dimensionality are poor, the user carries the transfer risk, and belongs to a potential transfer carrying user, for the user, the network basic problem can be solved firstly, and the customer care rate and the tracking problem solving rate are required to be improved; under the condition that the network quality is good but the complaint handling timeliness is poor, if a user belongs to a potential user with low satisfaction degree, customer service is required to timely and actively initiate customer care to release a question; under the conditions of poor network quality and good complaint handling timeliness, users belong to potential users with low satisfaction degree, and need to promote and solve the network basic problem in time so as to avoid continuous deterioration of user satisfaction degree.
Fig. 4 shows a flowchart of the method for evaluating user satisfaction in the embodiment of the present invention, and as shown in fig. 4, the method of the embodiment mainly includes two stages: first, a construction phase, i.e., a coarse tuning phase, of a data source sensitivity model (i.e., a user satisfaction model), in which processes mainly performed include: determining an analysis target index, namely user satisfaction; selecting an uncertainty data source to be analyzed, namely selecting a wireless network index to be analyzed; analyzing the index influence caused by the fluctuation degree of the uncertain data, namely analyzing the change rate of the user satisfaction when the index data of the wireless network index fluctuates; determining a data source sensitivity factor, namely calculating a sensitivity coefficient of user satisfaction to wireless network indexes; selecting a final fitting data source sensitivity factor set, namely filtering the wireless network indexes according to the sensitivity factors, thereby reserving the wireless network indexes finally used for constructing the model; and completing the construction of a data source sensitivity model, namely constructing a user satisfaction evaluation model based on the sensitivity coefficient of the wireless network index.
And secondly, finely adjusting the model constructed in the coarse adjustment stage by using a machine algorithm model, and adjusting and optimizing the model constructed in the first stage by mainly adopting a GBDT algorithm and an XGboost algorithm.
The method of the embodiment has wide application significance, for example, the method can be used for evaluating the user satisfaction degree of objective index data on a network side; the method can also be applied to mining potential derogative user groups, and whether the users are maliciously derogated when the users are undermined is evaluated based on objective index data at the network side; the method can also be applied to a precise dynamic adaptation satisfaction degree promotion strategy. The objective index data of the network side corresponding to the user and the generated user satisfaction data can be used for training and tuning of the user satisfaction model.
In summary, in the method of the embodiment, the amplitude value of the single variable data is adjusted through the data source sensitivity model to study the sensitivity of the single variable data affecting the satisfaction degree, the user perception model is established by combining with the integration algorithm in the machine learning algorithm, the artificial subjective presetting of each characteristic value is replaced, the user satisfaction degree can be accurately and objectively evaluated, the accurate positioning of users with low satisfaction degree is facilitated, the comprehensive prediction and mining of potential user groups with poor satisfaction degree are facilitated, and then the satisfaction degree improvement work can be performed on the user groups.
Fig. 5 is a schematic structural diagram of an embodiment of the user satisfaction evaluating apparatus according to the present invention. As shown in fig. 5, the apparatus includes:
a data obtaining module 51, adapted to obtain index data of at least one wireless network index and user satisfaction data;
the sensitivity evaluation module 52 is adapted to calculate a sensitivity coefficient of the user satisfaction to the at least one wireless network index according to the index data of the at least one wireless network index and the user satisfaction data;
the model building module 53 is suitable for building a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction on at least one wireless network index;
the tuning processing module 54 is adapted to perform tuning processing on the user satisfaction evaluation model by using a machine learning algorithm;
and the satisfaction evaluation module 55 is adapted to evaluate the user satisfaction based on the user satisfaction evaluation model.
In an alternative approach, the sensitivity evaluation module 52 is further adapted to:
for any wireless network index, determining the change rate of user satisfaction data when the change rate of the index data of the wireless network index is a preset value under the condition that the index data of other wireless network indexes are not changed;
and calculating the sensitivity coefficient of the user satisfaction to the wireless network index according to the change rate of the index data of the wireless network index and the change rate of the user satisfaction data.
In an optional manner, the apparatus further comprises:
and the filtering module is suitable for judging whether the absolute value of the sensitivity coefficient of the user satisfaction degree to the wireless network index reaches a preset threshold value or not aiming at any wireless network index, if so, the sensitivity coefficient of the user satisfaction degree to the wireless network index is reserved, and otherwise, the sensitivity coefficient of the user satisfaction degree to the wireless network index is filtered.
In an alternative approach, the wireless network metrics include one or more of: an O domain index, a B domain index and an M domain index;
and the user satisfaction data is obtained by calculation according to the scores of the users on each satisfaction query index and the weight value of each satisfaction query index.
In an optional manner, the apparatus further comprises:
the user portrait generation module is suitable for analyzing the index data of the O domain index and determining the quality grade information of the network quality; analyzing the index data of the B-domain index to determine the quality grade information of the timeliness of complaint treatment; and generating a user perception portrait according to the quality grade information of the network quality and the quality grade information of the complaint processing timeliness.
Therefore, the device adjusts the amplitude value of the single variable data through the data source sensitivity model to study the sensitivity of the single variable data influencing the satisfaction degree, the user perception model is established by combining with the integration algorithm in the machine learning algorithm, the artificial subjective presetting of each characteristic value is replaced, the user satisfaction degree can be accurately and objectively evaluated, the accurate positioning of users with low satisfaction degree is facilitated, the comprehensive prediction and mining of potential user groups with poor satisfaction degree are facilitated, and the satisfaction degree improving work can be carried out on the user groups.
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 method for evaluating user satisfaction in any of the above method embodiments.
The executable instructions may be specifically configured to cause the processor to:
acquiring index data of at least one wireless network index and user satisfaction data;
calculating a sensitivity coefficient of the user satisfaction degree to at least one wireless network index according to the index data of at least one wireless network index and the user satisfaction degree data;
constructing a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction on at least one wireless network index;
performing tuning processing on the user satisfaction evaluation model by adopting a machine learning algorithm;
and evaluating the user satisfaction based on the user satisfaction evaluation model.
In an alternative, the executable instructions cause the processor to:
for any wireless network index, determining the change rate of user satisfaction data when the change rate of the index data of the wireless network index is a preset value under the condition that the index data of other wireless network indexes are not changed;
and calculating the sensitivity coefficient of the user satisfaction to the wireless network index according to the change rate of the index data of the wireless network index and the change rate of the user satisfaction data.
In an alternative, the executable instructions cause the processor to:
and aiming at any wireless network index, judging whether the absolute value of the sensitivity coefficient of the user satisfaction degree to the wireless network index reaches a preset threshold value, if so, retaining the sensitivity coefficient of the user satisfaction degree to the wireless network index, otherwise, filtering the sensitivity coefficient of the user satisfaction degree to the wireless network index.
In an alternative approach, the wireless network metrics include one or more of: an O domain index, a B domain index and an M domain index;
and the user satisfaction data is obtained by calculation according to the scores of the users on each satisfaction query index and the weight value of each satisfaction query index.
In an alternative, the executable instructions cause the processor to: analyzing the index data of the O-domain index to determine the quality grade information of the network quality;
analyzing the index data of the B-domain index to determine the quality grade information of the timeliness of complaint treatment;
and generating a user perception portrait according to the quality grade information of the network quality and the quality grade information of the complaint processing timeliness.
Therefore, according to the method, the amplitude value of the single variable data is adjusted through the data source sensitivity model to study the sensitivity of the single variable data influencing the satisfaction degree, the user perception model is established by combining with the integration algorithm in the machine learning algorithm, the artificial subjective presetting of each characteristic value is replaced, the user satisfaction degree can be accurately and objectively evaluated, the accurate positioning of users with low satisfaction degree is facilitated, the comprehensive prediction and mining of a potential user group with poor satisfaction degree are facilitated, and then the satisfaction degree improving work can be carried out on the user group.
Fig. 6 is a schematic structural diagram of an embodiment of a computing device according to the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the computing device.
As shown in fig. 6, the computing device may include: a processor (processor)602, a communication Interface 604, a memory 606, and a communication bus 608.
Wherein: the processor 602, communication interface 604, and memory 606 communicate with one another via a communication bus 608. A communication interface 604 for communicating with network elements of other devices, such as clients or other servers. The processor 602, configured to execute the program 610, may specifically perform relevant steps in the above-described embodiment of the method for evaluating user satisfaction of a computing device.
In particular, program 610 may include program code comprising computer operating instructions.
The processor 602 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.
And a memory 606 for storing a program 610. Memory 606 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 610 may specifically be configured to cause the processor 602 to perform the following operations:
acquiring index data of at least one wireless network index and user satisfaction data;
calculating a sensitivity coefficient of the user satisfaction degree to at least one wireless network index according to the index data of at least one wireless network index and the user satisfaction degree data;
constructing a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction on at least one wireless network index;
performing tuning processing on the user satisfaction evaluation model by adopting a machine learning algorithm;
and evaluating the user satisfaction based on the user satisfaction evaluation model.
In an alternative, the program 610 causes the processor 602 to:
for any wireless network index, determining the change rate of user satisfaction data when the change rate of the index data of the wireless network index is a preset value under the condition that the index data of other wireless network indexes are not changed;
and calculating the sensitivity coefficient of the user satisfaction to the wireless network index according to the change rate of the index data of the wireless network index and the change rate of the user satisfaction data.
In an alternative, the program 610 causes the processor 602 to:
and aiming at any wireless network index, judging whether the absolute value of the sensitivity coefficient of the user satisfaction degree to the wireless network index reaches a preset threshold value, if so, retaining the sensitivity coefficient of the user satisfaction degree to the wireless network index, otherwise, filtering the sensitivity coefficient of the user satisfaction degree to the wireless network index.
In an alternative, the program 610 causes the processor 602 to: the wireless network metrics include one or more of: an O domain index, a B domain index and an M domain index;
and the user satisfaction data is obtained by calculation according to the scores of the users on each satisfaction query index and the weight value of each satisfaction query index.
In an alternative, the program 610 causes the processor 602 to: analyzing the index data of the O-domain index to determine the quality grade information of the network quality;
analyzing the index data of the B-domain index to determine the quality grade information of the timeliness of complaint treatment;
and generating a user perception portrait according to the quality grade information of the network quality and the quality grade information of the complaint processing timeliness.
Therefore, the computing equipment adjusts the amplitude value of the single variable data through the data source sensitivity model to study the sensitivity of the single variable data influencing the satisfaction degree, the user perception model is established by combining with the integration algorithm in the machine learning algorithm, the artificial subjective presetting of each characteristic value is replaced, the user satisfaction degree can be accurately and objectively evaluated, the accurate positioning of users with low satisfaction degree is facilitated, the comprehensive prediction and mining of a potential user group with poor satisfaction degree are facilitated, and the satisfaction degree improving work can be carried out on the user group.
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 (10)
1. A method of assessing user satisfaction, comprising:
acquiring index data of at least one wireless network index and user satisfaction data;
calculating a sensitivity coefficient of the user satisfaction degree to the at least one wireless network index according to the index data of the at least one wireless network index and the user satisfaction degree data;
constructing a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction to the at least one wireless network index;
performing tuning processing on the user satisfaction evaluation model by adopting a machine learning algorithm;
and evaluating the user satisfaction based on the user satisfaction evaluation model.
2. The method of claim 1, wherein the calculating a sensitivity coefficient of user satisfaction to the at least one wireless network metric based on metric data of the at least one wireless network metric and user satisfaction data further comprises:
for any wireless network index, determining the change rate of user satisfaction data when the change rate of the index data of the wireless network index is a preset value under the condition that the index data of other wireless network indexes are not changed;
and calculating the sensitivity coefficient of the user satisfaction to the wireless network index according to the change rate of the index data of the wireless network index and the change rate of the user satisfaction data.
3. The method of claim 1 or 2, wherein after calculating a sensitivity coefficient of user satisfaction to the at least one wireless network metric, the method further comprises:
and aiming at any wireless network index, judging whether the absolute value of the sensitivity coefficient of the user satisfaction degree to the wireless network index reaches a preset threshold value, if so, retaining the sensitivity coefficient of the user satisfaction degree to the wireless network index, otherwise, filtering the sensitivity coefficient of the user satisfaction degree to the wireless network index.
4. The method of any of claims 1-3, wherein the wireless network metrics include one or more of: an O domain index, a B domain index and an M domain index;
and the user satisfaction data is obtained by calculation according to the scores of the users on each satisfaction query index and the weight value of each satisfaction query index.
5. The method of claim 4, wherein the method further comprises:
analyzing the index data of the O-domain index to determine the quality grade information of the network quality;
analyzing the index data of the B-domain index to determine the quality grade information of the timeliness of complaint treatment;
and generating a user perception portrait according to the quality grade information of the network quality and the quality grade information of the complaint processing timeliness.
6. An evaluation apparatus of user satisfaction, comprising:
the data acquisition module is suitable for acquiring index data of at least one wireless network index and user satisfaction data;
the sensitivity evaluation module is suitable for calculating a sensitivity coefficient of the user satisfaction degree to the at least one wireless network index according to the index data of the at least one wireless network index and the user satisfaction degree data;
the model building module is suitable for building a user satisfaction evaluation model according to the sensitivity coefficient of the user satisfaction to the at least one wireless network index;
the tuning processing module is suitable for tuning the user satisfaction evaluation model by adopting a machine learning algorithm;
and the satisfaction evaluation module is suitable for evaluating the user satisfaction based on the user satisfaction evaluation model.
7. The apparatus of claim 6, wherein the sensitivity evaluation module is further adapted to:
for any wireless network index, determining the change rate of user satisfaction data when the change rate of the index data of the wireless network index is a preset value under the condition that the index data of other wireless network indexes are not changed;
and calculating the sensitivity coefficient of the user satisfaction to the wireless network index according to the change rate of the index data of the wireless network index and the change rate of the user satisfaction data.
8. The apparatus of claim 6 or 7, wherein the apparatus further comprises:
and the filtering module is suitable for judging whether the absolute value of the sensitivity coefficient of the user satisfaction degree to the wireless network index reaches a preset threshold value or not aiming at any wireless network index, if so, the sensitivity coefficient of the user satisfaction degree to the wireless network index is reserved, and otherwise, the sensitivity coefficient of the user satisfaction degree to the wireless network index is filtered.
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 user satisfaction evaluation method according to any one of claims 1-5.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of assessing user satisfaction of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010588046.5A CN113837514A (en) | 2020-06-24 | 2020-06-24 | User satisfaction evaluation method and device, computing device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010588046.5A CN113837514A (en) | 2020-06-24 | 2020-06-24 | User satisfaction evaluation method and device, computing device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113837514A true CN113837514A (en) | 2021-12-24 |
Family
ID=78963468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010588046.5A Pending CN113837514A (en) | 2020-06-24 | 2020-06-24 | User satisfaction evaluation method and device, computing device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837514A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114375003A (en) * | 2021-12-29 | 2022-04-19 | 中国电信股份有限公司 | Method, device and storage medium for improving 5G user satisfaction |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106559582A (en) * | 2015-09-29 | 2017-04-05 | 亿阳信通股份有限公司 | A kind of VoLTE user's subjective perception support method and system |
| CN108280652A (en) * | 2016-12-31 | 2018-07-13 | 中国移动通信集团辽宁有限公司 | The analysis method and device of user satisfaction |
| CN109377252A (en) * | 2018-08-30 | 2019-02-22 | 广州崇业网络科技有限公司 | A kind of customer satisfaction prediction technique based on big data frame |
| CN109803295A (en) * | 2019-03-05 | 2019-05-24 | 中国联合网络通信集团有限公司 | A kind of evaluation method and device of communication cell rectification priority |
| CN111242660A (en) * | 2018-11-29 | 2020-06-05 | 北京京东尚科信息技术有限公司 | User satisfaction investigation method, device, equipment and computer-readable storage medium |
-
2020
- 2020-06-24 CN CN202010588046.5A patent/CN113837514A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106559582A (en) * | 2015-09-29 | 2017-04-05 | 亿阳信通股份有限公司 | A kind of VoLTE user's subjective perception support method and system |
| CN108280652A (en) * | 2016-12-31 | 2018-07-13 | 中国移动通信集团辽宁有限公司 | The analysis method and device of user satisfaction |
| CN109377252A (en) * | 2018-08-30 | 2019-02-22 | 广州崇业网络科技有限公司 | A kind of customer satisfaction prediction technique based on big data frame |
| CN111242660A (en) * | 2018-11-29 | 2020-06-05 | 北京京东尚科信息技术有限公司 | User satisfaction investigation method, device, equipment and computer-readable storage medium |
| CN109803295A (en) * | 2019-03-05 | 2019-05-24 | 中国联合网络通信集团有限公司 | A kind of evaluation method and device of communication cell rectification priority |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114375003A (en) * | 2021-12-29 | 2022-04-19 | 中国电信股份有限公司 | Method, device and storage medium for improving 5G user satisfaction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108320171B (en) | Hot-sold commodity prediction method, system and device | |
| US11763145B2 (en) | Article recommendation method and apparatus, computer device, and storage medium | |
| US9864951B1 (en) | Randomized latent feature learning | |
| CN107862022B (en) | Culture resource recommendation system | |
| CN111881343A (en) | Information pushing method and device, electronic equipment and computer readable storage medium | |
| KR102340463B1 (en) | Sample weight setting method and device, electronic device | |
| US20190220710A1 (en) | Data processing method and data processing device | |
| US11257019B2 (en) | Method and system for search provider selection based on performance scores with respect to each search query | |
| CN110689368B (en) | Method for designing advertisement click rate prediction system in mobile application | |
| CN108665148B (en) | Electronic resource quality evaluation method and device and storage medium | |
| CN111695084A (en) | Model generation method, credit score generation method, device, equipment and storage medium | |
| CN112966189B (en) | Fund product recommendation system | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| CN112104505A (en) | Application recommendation method and device, server and computer-readable storage medium | |
| CN105681089B (en) | Networks congestion control clustering method, device and terminal | |
| CN113837514A (en) | User satisfaction evaluation method and device, computing device and storage medium | |
| CN109523296B (en) | User behavior probability analysis method and device, electronic equipment and storage medium | |
| WO2022134946A1 (en) | Model training method, apparatus, storage medium, and device | |
| CN115269543A (en) | Data sampling method | |
| CN114862092A (en) | Evaluation method and device based on neural network | |
| CN110020728B (en) | Service model reinforcement learning method and device | |
| CN113849745A (en) | Object recommendation method, device, equipment and storage medium | |
| CN111428119A (en) | Query rewriting method and device and electronic equipment | |
| CN113869544A (en) | Reflow user prediction model establishing method and device, electronic equipment and storage medium |
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 |