CN116362359A - User satisfaction prediction method, device, equipment and medium based on AI big data - Google Patents
User satisfaction prediction method, device, equipment and medium based on AI big data Download PDFInfo
- Publication number
- CN116362359A CN116362359A CN202111583147.4A CN202111583147A CN116362359A CN 116362359 A CN116362359 A CN 116362359A CN 202111583147 A CN202111583147 A CN 202111583147A CN 116362359 A CN116362359 A CN 116362359A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- prediction
- training
- user perception
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012549 training Methods 0.000 claims abstract description 93
- 230000008447 perception Effects 0.000 claims abstract description 90
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000012360 testing method Methods 0.000 claims description 29
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 238000000513 principal component analysis Methods 0.000 claims description 7
- 238000004806 packaging method and process Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 239000002131 composite material Substances 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 18
- 238000013473 artificial intelligence Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000013526 transfer learning 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a user satisfaction prediction method, device, equipment and medium based on AI big data, and relates to the technical field of communication. The method comprises the following steps: acquiring original data used by a user network, and extracting user perception characteristic data in the original data; processing and analyzing the user perception characteristic data to obtain a training sample; based on a preset algorithm, constructing a user perception prediction model according to the training sample; and inputting the network usage data of the user to be tested into the user perception prediction model to obtain a user satisfaction degree prediction result. The method, the device, the equipment and the medium for predicting the user satisfaction based on the AI big data are used for constructing a user perception prediction model based on the data such as the network, the service and the complaint of the user and combining an AI big data machine algorithm to automatically predict the user satisfaction.
Description
Technical Field
The disclosure relates to the technical field of communication, and in particular relates to a user satisfaction prediction method, device, equipment and medium based on AI big data.
Background
The global mobile internet service has been rapidly developed, and many regions have been in the 5G network era, and at the same time, the service usage has also changed with the proliferation of users using the high-speed mobile internet. In the 2G era, users mainly use voice telephones; in the 3G/4G era, a large amount of traffic transmitted in the network is video traffic, and as more and more users like to watch video content using the mobile internet, the requirements of the users are higher and higher, so that higher requirements are put on the network quality of operators, the system quality of content providers and the like.
The user perception evaluation method taking the user experience as the center becomes a popular technology of the Internet, and the method taking the actual perception result of the terminal user as the evaluation core can better embody the satisfaction degree of the client. The quality of experience (Quality of Experience, QOE) of a user is a user end-to-end concept, which refers to the subjective experience of the user to the service, and is the overall performance of the system perceived from the user's perspective.
In the increasingly aggressive market competition environment, products and functions provided by large operators gradually tend to be homogeneous, so that the perception of the network by consumers is changed from simple product quality to service quality, and the quality of user service largely determines the degree of loyalty of consumers in purchasing, which brings new requirements and challenges to service management work. For this purpose, a net recommendation value (Net Promoter Score, NPS) assessment system is introduced, embedded into a user-oriented service management strategy, and the acceptance degree and recommendation willingness of network services in the user's mind are reflected by NPS scoring, so that the service management direction is guided.
In the related art, the traditional NPS evaluation system only starts from investigation data to evaluate, analyze and maintain. However, the traditional NPS evaluation system management method has the problems of small coverage user plane, high investigation cost and relatively delayed time, and meanwhile, in view of factors such as questionnaire length, the deeper business problem cannot be located.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The disclosure provides a user satisfaction prediction method, device, equipment and medium based on AI big data, which at least overcomes the problems of small coverage user plane, high investigation cost, incapability of positioning deep business problems and relative time lag of an NPS evaluation system provided in the related technology to a certain extent.
Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.
According to one aspect of the present disclosure, there is provided a user satisfaction prediction method based on AI big data, including:
Acquiring original data used by a user network, and extracting user perception characteristic data in the original data;
processing and analyzing the user perception characteristic data to obtain a training sample;
based on a preset algorithm, constructing a user perception prediction model according to the training sample;
and inputting the network usage data of the user to be tested into the user perception prediction model to obtain a user satisfaction degree prediction result.
In one embodiment of the present disclosure, the user-perceived feature data includes network quality data, traffic usage data, voice call usage data, video traffic usage data, game traffic usage data, web browsing traffic data, tariff service data for the user.
In one embodiment of the present disclosure, the subscriber network uses raw data to obtain from the network asset library data, deep packet inspection DPI data, wireless measurement report MR data, performance measurement PM data, tariff data, complaint data.
In one embodiment of the present disclosure, the processing and analyzing the user perception feature data to obtain a training sample includes:
preprocessing the original data to obtain preprocessed characteristic data;
and carrying out principal component analysis on the preprocessed characteristic data, calculating information gain of each column, screening principal components according to the information gain result, and taking the obtained principal components as data of a training model to form a training sample.
In one embodiment of the present disclosure, the preprocessing of the raw data includes:
filling the missing value by adopting KNNiputer;
processing each attribute variable by using a box method;
performing box-cox transformation on the heavy tail distribution attribute to obey Gaussian distribution;
alternatively, the partial columns are Cartesian-product-generated into composite attributes.
In one embodiment of the disclosure, the constructing a user perception prediction model according to the training sample based on a preset algorithm includes:
the training samples comprise a training set and a testing set, data in the training set are randomly extracted according to a preset proportion to serve as training data, and initial model training is conducted according to the training data; taking the rest data in the training set as test data, inputting the test data into the initial model to calculate f1score, precision, accuracy and model weight of each initial model, and obtaining a user perception prediction model to be verified;
inputting the test set into a user perception prediction model to be verified, and performing satisfaction prediction to obtain a satisfaction prediction value;
voting is carried out according to the obtained user perception prediction model to be verified and the satisfaction degree prediction value, and an optimal prediction value is obtained;
and determining the target weight of the user perception prediction model to be verified according to the optimal prediction value, and further obtaining the user perception prediction model.
In one embodiment of the present disclosure, after the constructing the user perception prediction model according to the training sample based on the preset algorithm, the method further includes:
and packaging and generating an application program according to the user perception prediction model, and deploying and installing the application program in an NPS evaluation system management system.
According to another aspect of the present disclosure, there is provided a user satisfaction prediction control device based on AI big data, including:
the data extraction module is used for acquiring original data used by a user network and extracting user perception characteristic data in the original data;
the data processing module is used for processing and analyzing the user perception characteristic data to obtain a training sample;
the model training module is used for constructing a user perception prediction model according to the training sample based on a preset algorithm;
and the data prediction module is used for inputting the network usage data of the user to be detected into the user perception prediction model to obtain a user satisfaction degree prediction result.
According to another aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the AI-big-data-based user satisfaction prediction method described above via execution of the executable instructions.
According to another aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described AI-big data-based user satisfaction prediction method.
According to the user satisfaction prediction method, device, equipment and medium based on the AI big data, the user satisfaction prediction model is built by combining the AI big data machine algorithm based on the network, service, complaint and other data of the user by applying the big data analysis means, so that the user satisfaction is automatically predicted.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.
FIG. 1 shows a flowchart of a user satisfaction prediction method based on AI big data in an embodiment of the disclosure;
FIG. 2 is a flowchart showing a user satisfaction prediction method based on AI big data in a further embodiment of the present disclosure
FIG. 3 illustrates a portion of a raw data graph of a user's usage network in an embodiment of the present disclosure;
FIG. 4 illustrates a component information gain map in an embodiment of the present disclosure;
FIG. 5 illustrates a partial principal component data diagram in an embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a user satisfaction prediction control device based on AI big data in an embodiment of the disclosure;
fig. 7 shows a block diagram of an electronic device in an embodiment of the disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
According to the scheme, the user perception prediction model of the net recommendation value (Net Promoter Score, NPS) is built by combining the artificial intelligent AI big data algorithm based on the user network perception data by applying the big data analysis means, and the satisfaction degree of the user is automatically predicted, so that network optimization and service promotion are performed for users with low satisfaction degree, the effectiveness of construction, optimization and marketing is greatly improved, the satisfaction degree of the user is improved, and the network service quality is improved. For ease of understanding, several terms referred to in this application are first explained below.
Artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.
The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
Machine Learning (ML) is a multi-domain interdisciplinary, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. It is specially studied how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, and reorganizes existing knowledge structures to continuously improve own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, confidence networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.
With research and advancement of artificial intelligence technology, research and application of artificial intelligence technology is being developed in various fields, such as common smart home, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned, automatic driving, unmanned aerial vehicles, robots, smart medical treatment, smart customer service, etc., and it is believed that with the development of technology, artificial intelligence technology will be applied in more fields and with increasing importance value.
The scheme provided by the embodiment of the application relates to technologies such as big data processing and machine learning of artificial intelligence, is a software program applied to a computer, uses original data to model by using a user network, predicts and evaluates satisfaction of a user, actively predicts possibility of user complaints, is convenient for improving network quality and improving user experience, and is specifically described by the following embodiments:
first, the embodiment of the disclosure provides a user satisfaction prediction method based on AI big data, which can be executed by any system with computing processing capability.
Fig. 1 shows a flowchart of a user satisfaction prediction method based on AI big data in an embodiment of the disclosure, and as shown in fig. 1, the user satisfaction prediction method based on AI big data provided in the embodiment of the disclosure includes the following steps:
S102, obtaining user network use original data, and extracting user perception characteristic data in the original data;
in this embodiment, the customer network uses raw data to detect DPI data, wireless measurement report MR data, performance measurement PM data, tariff data, complaint data from the network asset library data, depth data packets.
Specifically, based on the dimensions of DPI data, MR data, PM data, tariff data, complaint data, and the like, the user-perceived feature attributes can be reflected, and the user-perceived feature data includes about 60 or more attribute variables of user network quality data, traffic usage data, voice call usage data, video service usage data, game service usage data, web browsing service data, tariff service data, and the like, and is converted.
Fig. 3 illustrates a partial original data chart of a user using a network in an embodiment of the present disclosure, where, as shown in fig. 3, basic information of the user using the network original data includes a contact number, a voice quality score, and a surfing quality score, where the voice quality score and the surfing quality score are scores of satisfaction degrees of the user on fairy tale quality or surfing quality of mobile services of an operator, the score is from 1 to 10, and the greater the score, the higher the satisfaction degree. The characteristic data comprises quality difference user analysis data, user service condition data and user complaint condition data, wherein the quality difference user analysis data comprises an uplink rate and a downlink rate of seven days, average flow of seven days, package change condition in two months, consumption change condition, terminal change month, terminal change and the like. The user service condition data comprises page response success rate, page response time length, page display success rate, page display time length, page downloading rate, video playing success rate, video playing waiting time length, video playing cartoon frequency, video service downloading rate, access success rate, access time delay, message sending/receiving success rate, message sending/receiving rate, abnormal line dropping rate and the like. The complaint condition data of the user is whether complaints are received within seven days, 1 indicates that the complaints are over within seven days, and 0 indicates that the complaints are not received within seven days.
S104, processing and analyzing the user perception characteristic data to obtain a training sample;
specifically, in the obtained user perception feature data table, there are problems of partial data missing, abnormal values, partial column presenting heavy tail distribution, and the like, and in order to ensure the validity of data, in this embodiment, before a user perception prediction model is constructed, the user perception feature data needs to be preprocessed to obtain a training sample.
The training samples comprise a training set and a testing set, the training set is used for training and verifying the user perception prediction model by dividing the obtained training samples into the training set and the testing set, so that when the user perception prediction model predicts the user satisfaction of the data in the testing set, the obtained predicted value is more in line with the actual situation, and the accuracy of the user perception prediction model is improved.
S106, constructing a user perception prediction model according to the training sample based on a preset algorithm;
generally, the AI algorithm includes a decision tree, a random forest algorithm, a logistic regression algorithm, a support vector machine SVM, a gaussian naive bayes (Gaussian Naive Bayes) algorithm, a K nearest KNN algorithm, a K-means algorithm, an Adaboost algorithm, a neural network, a markov and other common algorithms, and in the AI algorithm, based on the type of each data in the training sample, the preset algorithm selects the KNN algorithm, the decision tree, the SVM and the gaussian naive bayes algorithm to train the user perception prediction model.
When model training is carried out, the characteristics of the user are selected as X, the network perceived data of the user investigated by the worker is selected as Y, the network perceived data of the user in the user training set is marked, the predicted result is converted, the mark with the predicted value score being greater than 6 is 1, and the mark with the predicted value score being less than or equal to 6 is 1. Inputting the training set into preset algorithms to obtain initial models corresponding to the preset algorithms, and calculating f1score, precision, accuracy and confusion matrix of each initial model to measure the quality of the initial models, wherein the precision represents the proportion of the example divided into the positive examples to the positive examples in general; f1score characterizes the quality of the initial model, and the closer to 1, the better the initial model; each column of the confusion matrix represents a prediction category, and the total number of each column represents the number of data predicted to be the category; each row represents the true home class of data, the total number of data for each row represents the number of data instances for that class, and the values in each column represent the number of classes for which the true data is predicted. Expressed in table 1, the following is used:
TABLE 1 confusion matrix
| Positive example Positive | Counterexample Negative | |
| Correct True | True TP | True negative TN |
| False error | False positive FP | False negative FN |
The calculation formulas of the precision rate, the accuracy rate and the f1score are as follows:
precision rate
Accuracy rate of
And adding the precision, the accuracy and the f1score to obtain the weight value of each initial model, inputting the test set into the trained initial model, obtaining a final prediction result aiming at network perception data through voting, weighting and voting the most likely prediction value for each initial model by the final prediction result, obtaining the final prediction value, converting the final prediction value, and converting the final prediction value into a label perceived by a user in a fractional form.
In order to verify the accuracy of the user satisfaction degree prediction mode obtained by training, when an initial model is trained, 70% of data of a training set is randomly selected as training data, the rest 30% of the data are used as test data, the initial model is trained through the training data, after the initial model is trained, the rest 30% of the test data are input into the model for verification, if the verification result passes, a final user perception prediction model is generated according to the weight value, if the verification result does not pass, the weight value of each initial model is adjusted, and then the final user perception prediction model is output.
In addition, the number of the initial models can be adjusted, for example, four preset algorithms are adopted to train the initial models, each algorithm builds 10 initial models, and then builds 40 initial models in total, so that the accuracy and the precision of the final user perception prediction model can be improved, and the prediction result of the user satisfaction degree is more accurate.
S108, inputting the network usage data of the user to be tested into the user perception prediction model to obtain a user satisfaction degree prediction result.
In this embodiment, after the user perception prediction model is trained, an application program is generated by packaging according to the user perception prediction model, and the application program is deployed and installed in the NPS evaluation system management system, so as to implement automatic prediction of user satisfaction, optimize network and service of users with low satisfaction in time, and promote user experience.
According to the user satisfaction prediction method based on the AI big data, the user satisfaction prediction model is built by combining the AI big data machine algorithm through the big data analysis means based on the network, service, complaint and other data of the user, so that the user satisfaction is automatically predicted.
In one embodiment of the present disclosure, as shown in fig. 2, step S104 processes and analyzes the user perception feature data to obtain a training sample, which specifically includes:
s202, preprocessing original data to obtain preprocessed characteristic data;
s204, performing principal component analysis on the preprocessed characteristic data, calculating information gain of each column, and screening principal components according to information gain results, wherein the obtained principal components are used as data of a training model to form training samples.
Specifically, the preprocessing of the original data includes:
filling the missing value by adopting KNNiputer;
processing each attribute variable by using a box method;
performing box-cox transformation on the heavy tail distribution attribute to obey Gaussian distribution;
alternatively, the partial columns are Cartesian-product-generated into composite attributes.
When the missing value exists in the initial data, the missing value is filled by adopting KNNIMPER, and the specific method is as follows:
marking all lines containing missing values, and calculating data of the nearest top k of the line data, wherein the distance between two points is obtained by the following formula:
and interpolating the missing values using the average value of the nearest neighbor data.
When each attribute variable is processed by using the box method, the specific steps are as follows:
The first quartile of data for each column of data is calculated as Q1 and the third quartile as Q3.
If the upper limit value is q3+1.5× (Q3-Q1) and the lower limit value is Q1-1.5× (Q3-Q1), then the data exceeding the upper limit value or falling below the lower limit value in the one row of data is recorded as an abnormal value, and the abnormal value may be replaced with the upper limit value or the lower limit value.
Performing box-cox transformation on the heavy tail distribution attribute to obey Gaussian distribution, wherein the concrete steps are as follows:
drawing a probability distribution map for each column of data, and judging the distribution condition of the column of data through an image;
continuing box-cox transformation on the columns distributed on the heavy ends, wherein the transformation formula is as follows:
in this embodiment, after the original data is preprocessed, preprocessed feature data is obtained, and principal component analysis is performed on the preprocessed feature data, where the information entropy (Information entropy) is an index most commonly used for measuring the purity of a sample set, and it is assumed that the proportion of the kth sample in the current sample set D is p k (k=1, 2,) the information entropy of each column is calculated as follows:
after the information entropy is calculated, the calculation results are sequenced to obtain a component information gain diagram shown in fig. 4, principal components are screened from the component information gain diagram, and the obtained principal components are used as data of a training model to form training samples, and a part of principal component data diagram shown in fig. 5 is formed.
According to the user satisfaction prediction method based on the AI big data, the obtained user network is preprocessed in the modes of performing missing value filling, box-cos transformation, abnormal value correction and the like by using original data, and the preprocessed characteristic data are used for screening main components to obtain training samples, so that the data coverage is wide, and the accuracy of a prediction result is high.
In one embodiment of the present disclosure, step S106 builds a user perception prediction model from training samples based on a preset algorithm, including:
the training samples comprise a training set and a testing set, data in the training set are randomly extracted according to a preset proportion to serve as training data, and initial model training is conducted according to the training data; taking the rest data in the training set as test data, inputting the test data into the initial model to calculate f1score, precision, accuracy and model weight of each initial model, and obtaining a user perception prediction model to be verified;
inputting the test set into a user perception prediction model to be verified, and performing satisfaction prediction to obtain a satisfaction prediction value;
voting is carried out according to the obtained user perception prediction model to be verified and the satisfaction degree prediction value, and an optimal prediction value is obtained;
And determining the target weight of the user perception prediction model to be verified according to the optimal prediction value, and further obtaining the user perception prediction model.
Generally, the preset ratio can take a value between 70% and 80%, for example, the training data is 70% of the training sample, the test data is 30% of the training sample, that is, the training data and the test data are 7: 3. The size of the preset proportion can be determined according to practical situations, and the application is not particularly limited.
Specifically, the flow of the KNN algorithm is:
setting a parameter K; calculating the distance between the point to be predicted and the known point by using a formula I;
and sequencing the calculated results from small to large, and taking the first K points.
The points to be predicted are classified into one of the most categories.
In the decision tree algorithm, the following flow is adopted:
initializing a threshold epsilon of the information gain; judging whether the samples are the same class of output D i If yes, returning to the single-node tree T, and marking the sample as D i ；
Judging whether the feature is empty, if so, returning to the single-node tree T, wherein the sample marking category is the category with the largest number of output category D examples in the sample;
and calculating the information gain of each characteristic pair output D in the A, selecting the characteristic Ag with the maximum information gain, returning to the single-node tree T if the information gain of Ag is smaller than the threshold epsilon, and marking the sample as the type with the maximum number of instances of the output type D in the sample. Otherwise, the corresponding sample outputs D are separated into different categories Di by different values Agi of the characteristic Ag. Each class produces a child node.
The corresponding characteristic value is Agi, the number T of the added nodes is returned, and the information gain is calculated by adopting a formula III.
For all child nodes, let d=di, a=a- { Ag } recursively call the above steps, get the subtree Ti and return.
The algorithm flow for the SVM is as follows:
for training set t= { (x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n ,y n ) Solving a quadratic programming problem:
solution to
Calculating the parameter w and selecting a positive component
Calculating b, wherein,
constructing decision boundaries: g (x) = (w) * ×x)+b * Equation six =0
From this, the decision function is found: f (x) =sgn (g (x)).
The flow for the gaussian naive bayes algorithm is as follows:
let x= { a1, a2,..an } be the item to be classified, where a is one characteristic attribute of x.
The category set is c= { y1, y2,..;
the values of P (y1|x), P (y2|x), P (yn|x) were calculated separately, where:
x is considered to be of the yk type if P (yk|x) =max { P (y1|x), P (y2|x),..p (yn|x) }.
In this example, after training the initial model by training data, inputting test data into each initial model to obtain a user perception prediction model to be verified, inputting a test set into the user perception prediction model to be verified to perform prediction verification, so as to determine whether a prediction result of the user perception prediction model to be verified is accurate and effective, if the verification result has deviation, adjusting a weight value of the user perception prediction model to be verified, and if the verification result passes, outputting the user perception prediction model.
The table 2 is a data table of f1score, accuracy and precision calculated by the training set and the testing set, and it can be found from the prediction results of the user perception prediction model to be verified trained by the training sample and the user perception prediction model, and the user perception prediction model can accurately predict the user NPS perception by using the values calculated by the training set and the testing set.
FIG. 2 prediction result data table
| Type(s) | f1score | Precision rate | Accuracy rate of |
| Training set | 0.6623 | 0.7806 | 0.7277 |
| Test set | 0.6555 | 0.7800 | 0.7133 |
According to the user satisfaction prediction method based on the AI big data, through the big data analysis means, based on the network, service, complaint and other data of the user, the user perception prediction model is built by combining an AI big data machine algorithm, so that the user satisfaction is predicted automatically.
Based on the same inventive concept, the embodiment of the disclosure also provides a user satisfaction prediction control device based on AI big data, as described in the following embodiment. Since the principle of solving the problem of the embodiment of the device is similar to that of the embodiment of the method, the implementation of the embodiment of the device can be referred to the implementation of the embodiment of the method, and the repetition is omitted.
Fig. 6 shows a schematic diagram of a user satisfaction prediction control device based on AI big data in an embodiment of the disclosure, as shown in fig. 6, the device includes a data extraction module 601, a data processing module 602, a model training module 603, and a data prediction module 604, where:
the data extraction module 601 is configured to obtain original data used by a user network, and extract user perception feature data in the original data;
the data processing module 602 is configured to process and analyze the user perception feature data to obtain a training sample;
the model training module 603 is configured to construct a user perception prediction model according to a training sample based on a preset algorithm;
the data prediction module 604 is configured to input the user network usage data test set to the user perception prediction model to obtain a user satisfaction degree prediction result.
Specifically, the user perception characteristic data includes network quality data, traffic usage data, voice call usage data, video service usage data, game service usage data, web browsing service data, and tariff service data of the user.
Further, the subscriber network uses raw data to detect DPI data, wireless measurement report MR data, performance measurement PM data, tariff data, complaint data from the network asset library data, deep data packets.
In one embodiment of the present disclosure, the data processing module 602 includes a preprocessing module and a principal component analysis module, not shown in the drawings, wherein,
the preprocessing module is used for preprocessing the original data to obtain preprocessed characteristic data;
the principal component analysis module is used for carrying out principal component analysis on the preprocessed characteristic data, calculating information gain of each column, screening principal components according to information gain results, and taking the obtained principal components as data of a training model to form training samples.
Further, the preprocessing module is specifically configured to:
filling the missing value by adopting KNNiputer;
processing each attribute variable by using a box method;
performing box-cox transformation on the heavy tail distribution attribute to obey Gaussian distribution;
alternatively, the partial columns are Cartesian-product-generated into composite attributes.
In one embodiment of the present disclosure, the preset algorithm includes a K nearest neighbor KNN algorithm, a decision tree, a support vector machine SVM, a gaussian naive bayes algorithm.
In one embodiment of the present disclosure, the model training module 603 includes an initial model training sub-module, a satisfaction prediction sub-module, a vote sub-module, and a model determination sub-module, which are not shown in the drawings, wherein,
The initial model training sub-module is used for randomly extracting data in the training set as training data according to a preset proportion and carrying out initial model training according to the training data; taking the rest data in the training set as test data, inputting the test data into the initial model to calculate f1score, precision, accuracy and model weight of each initial model, and obtaining a user perception prediction model to be verified;
the satisfaction prediction sub-module is used for inputting the test set into a user perception prediction model to be verified, and performing satisfaction prediction to obtain a satisfaction prediction value;
the voting submodule is used for voting according to the obtained user perception prediction model to be verified and the satisfaction degree prediction value to obtain an optimal prediction value;
and the model determination submodule is used for determining the target weight of the user perception prediction model to be verified according to the optimal prediction value, so as to obtain the user perception prediction model.
In one embodiment of the present disclosure, the apparatus further comprises a packaging module not shown in the drawings,
and the packaging module is specifically used for packaging and generating an application program according to the user perception prediction model after constructing the user perception prediction model according to the training set based on a preset algorithm, and arranging and installing the application program in an NPS evaluation system management system.
Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
According to the user satisfaction prediction method and device based on the AI big data, the user satisfaction prediction model is built by combining the AI big data machine algorithm through the big data analysis means based on the network, service, complaint and other data of the user, so that the user satisfaction is automatically predicted.
An electronic device 700 according to this embodiment of the invention is described below with reference to fig. 7. The electronic device 700 shown in fig. 7 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 7, the electronic device 700 is embodied in the form of a general purpose computing device. Components of electronic device 700 may include, but are not limited to: the at least one processing unit 710, the at least one memory unit 720, and a bus 730 connecting the different system components, including the memory unit 720 and the processing unit 710.
Wherein the storage unit stores program code that is executable by the processing unit 710 such that the processing unit 710 performs steps according to various exemplary embodiments of the present invention described in the above-mentioned "exemplary methods" section of the present specification. For example, the processing unit 710 may perform real-time monitoring of congestion of the first message transmission channel for data transmission between the control plane device and the forwarding plane device as shown in fig. 3; and when the first message transmission channel is monitored to be in a congestion state, controlling to open a second message transmission channel so as to complete data transmission between the control plane device and the forwarding plane device.
The memory unit 720 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 7201 and/or cache memory 7202, and may further include Read Only Memory (ROM) 7203.
The storage unit 720 may also include a program/utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The electronic device 700 may also communicate with one or more external devices 740 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the system 700, and/or any device (e.g., router, modem, etc.) that enables the electronic device 700 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 750. Also, system 700 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through network adapter 760. As shown, network adapter 760 communicates with other modules of electronic device 700 over bus 730. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 700, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.
A program product for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read-only memory (CD-ROM) and comprise program code and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order or that all illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (10)
1. The user satisfaction prediction method based on the AI big data is characterized by comprising the following steps:
acquiring original data used by a user network, and extracting user perception characteristic data in the original data;
processing and analyzing the user perception characteristic data to obtain a training sample;
based on a preset algorithm, constructing a user perception prediction model according to the training sample;
and inputting the network usage data of the user to be tested into the user perception prediction model to obtain a user satisfaction degree prediction result.
2. The method of claim 1, wherein the user-perceived feature data comprises network quality data, traffic usage data, voice call usage data, video traffic usage data, game traffic usage data, web browsing traffic data, tariff service data for the user.
3. The method of claim 1, wherein the subscriber network uses raw data obtained from network asset library data, deep packet inspection DPI data, wireless measurement report MR data, performance measurement PM data, tariff data, complaint data.
4. The method of claim 1, wherein the processing the user perception feature data to obtain training samples comprises:
preprocessing the original data to obtain preprocessed characteristic data;
and carrying out principal component analysis on the preprocessed characteristic data, calculating information gain of each column, screening principal components according to the information gain result, and taking the obtained principal components as data of a training model to form a training sample.
5. The method of claim 4, wherein the preprocessing of the raw data comprises:
filling the missing value by adopting KNNiputer;
processing each attribute variable by using a box method;
performing box-cox transformation on the heavy tail distribution attribute to obey Gaussian distribution;
alternatively, the partial columns are Cartesian-product-generated into composite attributes.
6. The method according to any one of claims 1-5, wherein the constructing a user perception prediction model from the training samples based on a preset algorithm comprises:
The training samples comprise a training set and a testing set, data in the training set are randomly extracted according to a preset proportion to serve as training data, and initial model training is conducted according to the training data; taking the rest data in the training set as test data, inputting the test data into the initial model to calculate f1score, precision, accuracy and model weight of each initial model, and obtaining a user perception prediction model to be verified;
inputting the test set into a user perception prediction model to be verified, and performing satisfaction prediction to obtain a satisfaction prediction value;
voting is carried out according to the obtained user perception prediction model to be verified and the satisfaction degree prediction value, and an optimal prediction value is obtained;
and determining the target weight of the user perception prediction model to be verified according to the optimal prediction value, and further obtaining the user perception prediction model.
7. The method of claim 6, wherein after the constructing a user perception prediction model from the training samples based on the preset algorithm, the method further comprises:
and packaging and generating an application program according to the user perception prediction model, and deploying and installing the application program in an NPS evaluation system management system.
8. A user satisfaction prediction control device based on AI big data, characterized by comprising:
The data extraction module is used for acquiring original data used by a user network and extracting user perception characteristic data in the original data;
the data processing module is used for processing and analyzing the user perception characteristic data to obtain a training sample;
the model training module is used for constructing a user perception prediction model according to the training sample based on a preset algorithm;
and the data prediction module is used for inputting the network data of the user to be detected into the user perception prediction model to obtain a user satisfaction degree prediction result.
9. An electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the AI big data based user satisfaction prediction method of any of claims 1-7 via execution of the executable instructions.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the AI big data-based user satisfaction prediction method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111583147.4A CN116362359A (en) | 2021-12-22 | 2021-12-22 | User satisfaction prediction method, device, equipment and medium based on AI big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111583147.4A CN116362359A (en) | 2021-12-22 | 2021-12-22 | User satisfaction prediction method, device, equipment and medium based on AI big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116362359A true CN116362359A (en) | 2023-06-30 |
Family
ID=86927427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111583147.4A Pending CN116362359A (en) | 2021-12-22 | 2021-12-22 | User satisfaction prediction method, device, equipment and medium based on AI big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116362359A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596585A (en) * | 2023-07-11 | 2023-08-15 | 亚信科技（中国）有限公司 | User satisfaction obtaining method and device, electronic equipment and storage medium |
| CN117057459A (en) * | 2023-07-28 | 2023-11-14 | 中移互联网有限公司 | Training method and device of user satisfaction prediction model, electronic equipment and medium |
| CN117786544A (en) * | 2024-02-28 | 2024-03-29 | 浪潮通信信息系统有限公司 | User satisfaction obtaining method and device, electronic equipment and storage medium |
-
2021
- 2021-12-22 CN CN202111583147.4A patent/CN116362359A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596585A (en) * | 2023-07-11 | 2023-08-15 | 亚信科技（中国）有限公司 | User satisfaction obtaining method and device, electronic equipment and storage medium |
| CN116596585B (en) * | 2023-07-11 | 2023-11-03 | 亚信科技（中国）有限公司 | User satisfaction obtaining method and device, electronic equipment and storage medium |
| CN117057459A (en) * | 2023-07-28 | 2023-11-14 | 中移互联网有限公司 | Training method and device of user satisfaction prediction model, electronic equipment and medium |
| CN117786544A (en) * | 2024-02-28 | 2024-03-29 | 浪潮通信信息系统有限公司 | User satisfaction obtaining method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11521221B2 (en) | Predictive modeling with entity representations computed from neural network models simultaneously trained on multiple tasks | |
| US11907675B2 (en) | Generating training datasets for training neural networks | |
| CN116362359A (en) | User satisfaction prediction method, device, equipment and medium based on AI big data | |
| US20200118145A1 (en) | Characterizing and Modifying User Experience of Computing Environments Based on Behavior Logs | |
| CN112541122A (en) | Recommendation model training method and device, electronic equipment and storage medium | |
| CN110363427A (en) | Model quality evaluation method and apparatus | |
| WO2021035412A1 (en) | Automatic machine learning (automl) system, method and device | |
| CN111800289B (en) | Communication network fault analysis method and device | |
| US20190156231A1 (en) | User segmentation using predictive model interpretation | |
| CN112819024B (en) | Model processing method, user data processing method and device and computer equipment | |
| CN114417174B (en) | Content recommendation method, device, equipment and computer storage medium | |
| CN114595323B (en) | Portrait construction, recommendation, model training method, apparatus, device and storage medium | |
| CN112269943B (en) | Information recommendation system and method | |
| CN118094420A (en) | Questionnaire assessment method, model training method, device, equipment and storage medium | |
| CN110704614B (en) | Information processing method and device for predicting user group type in application | |
| US20220253690A1 (en) | Machine-learning systems for simulating collaborative behavior by interacting users within a group | |
| KR20240011370A (en) | Non face-to-face learning curriculum creation and recommendation system based on coding learning data | |
| CN115618065A (en) | Data processing method and related equipment | |
| CN111143688B (en) | Evaluation method and system based on mobile news client | |
| US9532165B2 (en) | Method and apparatus for location prediction using short text | |
| CN113407808A (en) | Method and device for judging applicability of graph neural network model and computer equipment | |
| CN113344369A (en) | Method and device for attributing image data, electronic equipment and storage medium | |
| CN111915339A (en) | Data processing method, device and equipment | |
| CN111506510B (en) | Software quality determining method and related device | |
| CN112905896B (en) | Training method of recommended number model, and mixed content recommendation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |