CN109978627A - Modeling method for big data of user internet access behavior of broadband access network - Google Patents
Modeling method for big data of user internet access behavior of broadband access network Download PDFInfo
- Publication number
- CN109978627A CN109978627A CN201910250704.7A CN201910250704A CN109978627A CN 109978627 A CN109978627 A CN 109978627A CN 201910250704 A CN201910250704 A CN 201910250704A CN 109978627 A CN109978627 A CN 109978627A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- access network
- broadband access
- internet behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000006399 behavior Effects 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 10
- 238000011160 research Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 5
- 238000013441 quality evaluation Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 3
- 238000010276 construction Methods 0.000 abstract description 2
- 230000004069 differentiation Effects 0.000 abstract description 2
- 230000004927 fusion Effects 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 12
- 238000012216 screening Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005206 flow analysis Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
-
- 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
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a modeling method facing to big data of internet surfing behaviors of broadband access network users, which provides a semi-supervised learning method of network flow based on a clustering algorithm and a regression algorithm, can dynamically perform regional user subdivision and regional flow prediction according to different input data and provide a regional server building scheme, and respectively provide the scheme for a marketing department, an operation department and a foundation construction department, innovatively promote the fusion among all the telecommunication departments, facilitate enterprises to carry out a sales means aiming at user group differentiation, provide a resource distribution basis for network development in advance, effectively improve the network quality and bring better internet surfing experience for users by optimizing the building of a server.
Description
Technical field
The present invention relates to big data mining analysis, big datas to model field, and especially one kind is towards broadband access network users
The modeling method of internet behavior big data.
Background technique
With the development of internet, number of network users gradually increases.In field of telecommunications, there are hundreds of millions of broadbands to connect
Networking user, the data class that these broadband access network users provide is rich and varied, and the basic document data including user are (as used
Family identity ID, user ascription area, date of birth, occupation), internet behavior data (such as surfing flow, the surf time, browsing content,
Search key), position data (local climate, regional economy total amount, regional broadband access network number of users)；Broadband access network
User is to the requirements at the higher level of network quality and network service, so that network service is continuously improved in network operator and service provider
Quality and increase new business；In addition, carrying out timely and effectively data analysis to broadband access network user data and excavating, find not
With the distribution situation of user group spatially, guidance is provided for building for server of optimization.
User satisfaction is improved, provides their interested business and information for user, this is just needed to the network user
Behavior analyzed, excavate user and surf the Internet feature and online interest etc., to understand user demand in depth, meanwhile, this is also
Network marketing provides an important information channel；Improve network quality, it is necessary to understand in depth network operating condition and
Service condition keeps the monitoring to network flow, constantly adjusts network structure and bandwidth, solves network problem, improves network clothes
Business quality, is effectively treated a large amount of network flow datas；Optimize server to build, it is necessary to understand income, the area of different business
The information such as difference, business demand variation, different user population distribution situation and its ratio, to meet region different user group pair
The demand of bandwidth, business etc. obtains different user group location to the distribution proportion characteristic of server, to reduce clothes
Business device infrastructure cost.
In order to maximally utilise customer resources, currently, there are many for telecommunications broadband access network user behavior point
The method of analysis and prediction.Prediction for the telecommunications broadband access network user traffic data of continuous type, it has been proposed that Duo Zhongjian
Educational inspector's learning method.Some of research achievements regard network flow as linear model, and autoregressive moving average is respectively adopted
(ARMA) model, difference autoregressive moving average (ARIMA) model and difference autoregression summation sliding average (FARIMA) mould
The linear models such as type are predicted.But with the increase of network complexity, network flow characteristic has exceeded in traditional sense
The Poisson distribution or Markov thought distributed, therefore carry out predicting that there are theoretic deficiencies using linear model, very
It is difficult to guarantee the accuracy of prediction.And the prediction of nonlinear model mainly includes artificial neural network, support vector machines, grey mould
Type etc., although the precision of prediction of nonlinear model has a degree of raising compared with linear model, precision of prediction is still not
It is ideal.Neural network haves the shortcomings that easily to sink into local optimum, network structure be difficult to it is determining；Although support vector machines needs sample
This number is small, but its key parameter is difficult to determine；And it is violent situation that gray model, which is only suitable for data variation not,；Therefore, have
Necessity exploitation and a kind of new modeling method is designed, Lai Youhua server is built, and is improved network quality and user satisfaction.
Summary of the invention
For overcome the deficiencies in the prior art, the present invention provides one kind towards broadband access network users internet behavior big data
Modeling method.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of modeling method towards broadband access network users internet behavior big data, method includes the following steps:
S1, the internet behavior data for obtaining broadband access network users, and carry out data and carry out quality evaluation, filter out high quality
Data.
S2, the data of the high quality screened are pre-processed, it is high-quality to what is screened using unsupervised algorithm
The data of amount carry out user area division and label and utilize unsupervised in conjunction with the basic document data and position data of user
Relevance algorithm in habit finds the incidence relation between user's internet behavior and each data fields.
S3, the prediction for being carried out " when m- flow " to the user group of tape label using the regression model in supervised learning, are obtained
The flow tendency situation of each user group, and calculated by statistics, obtain total flow tendency situation.
The distribution situation and quantity of S4, user group by the way that each tape label is calculated, to obtain different use
Demand characteristics of the family group location to server.
Further, in the step S1, according to essential information (such as flow of broadband access network users internet behavior data
Size and data type etc.), it draws a diagram, and data are analyzed by chart, rejects unnecessary data, obtain high-quality
The data of amount.
In the step S2, the data of high quality are divided into two data packets of DataBill and FactorBill, wherein
DataBill is using the internet behavior (such as surf time, browsing content and search key) in user's Internet data as spy
Sign vector, using unsupervised algorithm, is existed respectively with the surfing flow (uplink traffic and downlink traffic) of user's internet behavior data
Time and spatially it is trained research and formed two groups of training sets；FactorBill by user basic document data
It is formed with position data.
The beneficial effects of the present invention are: the present invention dynamically carries out zone user to user's Internet data using clustering algorithm
Subdivision and label, and zone flow prediction is carried out to the user group of subdivision, and by counting statistics, given region server is taken
Scheme is built, sales department, operation department and infrastructure department are respectively supplied to, is innovatively promoted between telecommunications each department
Fusion effectively improves network quality, brings better online experience to user by building for optimization server.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is modeling step diagram of the invention；
Fig. 2 is Holistic modeling block diagram of the invention；
Fig. 3 is the structure chart in Fig. 2 at A；
Fig. 4 is the structure chart in Fig. 2 at B；
Fig. 5 is the structure chart in Fig. 2 at C；
Fig. 6 is the ratio chart of the different types of data of data quality accessment of the invention；
Fig. 7 is the ratio chart for analyzing each type data in data of data quality accessment of the invention；
Fig. 8 is the histogram of the time overlay length of all types of data of data quality accessment of the invention；
Fig. 9 is the time distribution map of the total amount of data of data quality accessment of the invention；
Figure 10 is the structure chart of the DataBill and FactorBill of data prediction of the invention.
Specific embodiment
Referring to figs. 1 to Figure 10, a kind of modeling method towards broadband access network users internet behavior big data, this method packet
Include following steps:
S1, the internet behavior data for obtaining broadband access network users, and carry out data and carry out quality evaluation, filter out high quality
Data.
S2, the data of the high quality screened are pre-processed, it is high-quality to what is screened using unsupervised algorithm
The data of amount carry out user area division and label and utilize unsupervised in conjunction with the basic document data and position data of user
Relevance algorithm in habit finds the incidence relation between user's internet behavior and each data fields.
S3, the prediction for being carried out " when m- flow " to the user group of tape label using the regression model in supervised learning, are obtained
The flow tendency situation of each user group, and calculated by statistics, obtain total flow tendency situation.
The distribution situation and quantity of S4, user group by the way that each tape label is calculated, to obtain different use
Demand characteristics of the family group location to server.
Further, in the step S1, according to essential information (such as flow of broadband access network users internet behavior data
Size and data type etc.), it draws a diagram, and data are analyzed by chart, rejects unnecessary data, obtain high-quality
The data of amount.
Further, in the step S2, the data of high quality are divided into two data of DataBill and FactorBill
Packet, wherein DataBill is with internet behavior (such as surf time, browsing content and the search key in user's Internet data
Deng) feature vector is used as to utilize unsupervised calculation with the surfing flow (uplink traffic and downlink traffic) of user's internet behavior data
Method is trained research and two groups of training sets of formation to it over time and space respectively；FactorBill by user base
This data and position data are formed, and referring in particular to Figure 10, table 1, table 2 and table 3, in the present embodiment, DataBill is existed
The training set that spatially training research obtains is denoted as B1 (for the cell array of 1*7), the training that training research in time obtains
Integrate and be denoted as B2 (as the cell array of 1*22), the basic document data (being denoted as UserFactor attribute) of user include user identity
The position data (being denoted as NaturalFactor attribute) of ID, user ascription area, date of birth, occupation and income, user includes star
Phase, weather, temperature, air quality, area, regional economy total amount and regional number of users, by the basic document of B1 and B2 and user
Data and the analysis of being associated property of position data, and for Nominal Attribute as week, weather and area, using differential technique come
Value, in the present embodiment, the identical distance of value is 1, and the different value of value is 0.
The Spatial Dimension training set B1 and time dimension training set B2 of 1 data prediction of table
The UserFactor attribute of 2 data prediction of table
| Attribute-name | User identity ID | User ascription area | Date of birth | Occupation | Income |
| Attribute type | Nominally | Nominally | Numerical value | Nominally | Numerical value |
The NaturalFactor attribute of 3 data prediction of table
| Attribute-name | Week | Weather | Temperature | Air quality | Area | Regional economy total amount | Regional number of users |
| Attribute type | Nominally | Nominally | Numerical value | Numerical value | Nominally | Numerical value | Numerical value |
Embodiment
In the present embodiment, the statistical information of Sichuan province broadband access network user behavior big data is chosen, shares 446.8MB
Size, 1606995 records, is divided into 6 kinds of different types, and time span is from April 10,23 days to 2017 January in 2015；It is right
Different types of data essential information can be shown in Table 4, can will become apparent from the ratio that different types of data account for sum by Fig. 6
Example.
The essential information of six seed type data of 4 data quality accessment of table
Next screening rejecting is carried out to data, referring to table 5 it is found that number of users, online duration, browsing content, search are closed
Keyword, entrance (upload) byte number, outlet (downloading) byte number, entrance (upload) rate, outlet (downloading) rate, total rate,
The data such as access number are as can analyze data, and by date, user ascription area, date of birth, occupation, value (sampling) time zone
Between, remote server IP, bandwidth types are as classification data；And the ratio shared by data of analyzing in different types of data is
It is different, it may be seen that this species diversity in table 6, for us, can the let us data that are used to analyze be only me
Real concern, and the quantity that data can be analyzed can measure a kind of data type be it is more important, have in other words more
The high quality of data.We are shown by this cake chart of Fig. 7 all analyzes ratio shared by every kind of data type in data
Example more has the value of analysis come more which type of data with this, and combines Fig. 6, it can be found that all the period of time traffic statistics,
100M customer analysis, online user's analysis, point bandwidth online user analysis, peak flow measurement type possess it is a considerable number of can
Data are analyzed, and the data volume for accumulating number of users is less, even, it is believed that the data of accumulation this type of number of users are in data
Measuring does not have break-up value on this dimension, therefore, we can reject accumulation number of users data.
The structure list of the different types of data of 5 data quality accessment of table
The analysis classes data proportion of the different types of data of 6 data quality accessment of table
In the present embodiment, data are (on April 10,23 days to 2017 January in 2015) distributed more widely in time, since data exist
It is on time and discontinuous, and not all time point has complete data (data have missing values), nor institute's having time
Point has data, therefore, chooses the data in certain period of time, and abandon the data on other periods and be conducive to us and mention
The high quality of data, referring to table 7, Fig. 8 and Fig. 9, it can be seen that the time overlay length of Various types of data type, and pass through observation hair
It is existing, there is no any data in time of the April 1 30 days to 2016 July in 2015 up to 247 days, while in April, 2016
Data volume is also and few after 1 day, that is to say, that the data rich degree after on July 30th, 2015 was insufficient, at 2015 7
Before months 30 days, there are all types of data in data set, and all the period of time traffic statistics quantity after on April 1st, 2016
On significantly reduce, and it is abnormal for having several values obviously.Due to after on July 30th, 2015 continuity of data it is bad and
The quality of data is very poor, we can improve the overall quality of data by abandoning subsequent data.
The time overlay length of all types of data of 7 data quality accessment of table
| Record count | Type weight (min) | Time overlay length (min) | |
| 100M customer analysis | 73160 | 5 | 365800 |
| Online user's analysis | 353007 | 5 | 1765035 |
| Divide bandwidth online user analysis | 762022 | 5 | 3810110 |
| Peak flow statistics | 30710 | 5 | 153550 |
| All the period of time flow analysis | 994230 | 5 | 4971150 |
| Accumulate number of users | 9552 | 35 | 334320 |
It is final to determine with the 22 regional 100M users in Sichuan Province on January 23rd, 2015 by the analysis and screening to above-mentioned data
It is research sample to 20:00 to the 22:30 evening peak period on July 30th, 2015.
In the present embodiment, the data after screening being divided into two groups, are denoted as X | Y (X or Y) and X+Y (X and Y), wherein X is indicated
Surf time, browsing content and search key in user's internet behavior data, Y indicate upper in user's internet behavior data
Net flow carries out clustering algorithm to X+Y and is marked, is added to this two group data set respectively, obtains X | Y label and X+Y label,
By X+Y label and user basic document data and being associated property of position data analyze, depth excavate user's internet behavior and
Incidence relation between the different data such as customer service behavior, daily life facilitates enterprise real to divide to user group
Sales aid of the hand-manipulating of needle to user group differentiation；By X | the data of Y label are used for regression algorithm (supervised learning), predict all kinds of use
The flow at family, specifically, if after carrying out zone user subdivision and label, obtaining 3 user group U1 to some regional (being denoted as P1)
~U3, i.e. U (P1)={ { U1 }, { U2 }, { U3 } }, wherein U1={ u11, u12, u13, u14, u15 }, U2=u21, u22,
U23, u24, u25 }, U3={ u31, u32, u33, u34, u35, u36 }.For 7 days one week, for every class user group, according to
The training sample of their Monday to Saturdays carries out machine learning, and the flow tendency on their Sundays is predicted using regression algorithm, for
Same user group, since their internet behavior feature is similar, their surfing flow tendencies are similar, this greatly reduces pre-
The complexity of survey.For certain height area P11~P15, the predicted flow rate of relative users is counted and is added, this height can be obtained
The total flow tendency in area.As shown in figure 4, P11~P15 flow tendency is compared and analyzed, can shift to an earlier date for network Development
The foundation of resource allocation is provided；The predicted flow rate of P11~P15 is for statistical analysis, the prediction of the available area P1 flow
Or tendency, in this way by always to a point method total again, the precision of prediction of flow can be effectively improved；The X+Y that last basis obtains
The data of label calculate user group proportion in each height area, obtain the maximum user group of proportion, larger to meet
The demand of ratio user group builds server, available region server distribution situation and quantity, in Fig. 5, P1
User's ratio in area calculates as follows:
In the present embodiment, the concept of " dictionary " is proposed, and in Fig. 5, by P11, P12, P14 generate " dictionary ", and P13, P15 can be by
" looking up the dictionary " obtains.Wherein, " dictionary " should have integrality (comprising all types of user group in P1) and independence (each user for including
Group is mutually indepedent).By calculating it is found that the ratio of one's respective area shared by user group U1 is maximum in P11, therefore, to meet this user
Demand of the group U1 to bandwidth and business etc., obtains demand of the U1 to location P11 server, and then obtain P11 to service
The distribution of device and the demand of quantity.Similarly, obtain user group U3 and U2 to the clothes of location P12 and P14 respectively by P12 and P14
The demand for device distribution and the quantity of being engaged in, this just produces " dictionary " comprising P1 all types user group.Further, P1 is serviced
The overlapping region of device distribution optimizes, this just obtains the distribution situation and quantity of the area P1 server, for basic construction department
Server building plan is provided.
Above embodiment cannot limit the protection scope of the invention, and the personnel of professional skill field are not departing from
In the case where the invention general idea, the impartial modification and variation done still fall within the range that the invention is covered
Within.
Claims (3)
1. a kind of modeling method towards broadband access network users internet behavior big data, which is characterized in that this method include with
Lower step:
S1, the internet behavior data for obtaining broadband access network users, and carry out data and carry out quality evaluation, filter out high quality
Data；
S2, the data of the high quality screened are pre-processed, using unsupervised algorithm to the high quality screened
Data carry out user area division and label, in conjunction with the basic document data and position data of user, using in unsupervised learning
Relevance algorithm, find the incidence relation between user's internet behavior and each data fields；
S3, the prediction for being carried out " when m- flow " to the user group of tape label using the regression model in supervised learning, are obtained each
The flow tendency situation of user group, and calculated by statistics, obtain total flow tendency situation；
The distribution situation and quantity of S4, user group by the way that each tape label is calculated, to obtain different user group
Demand characteristics of the location to server.
2. the modeling method according to claim 1 towards broadband access network users internet behavior big data, feature exist
In the step S1, according to essential information (such as uninterrupted and data type of broadband access network users internet behavior data
Deng), it draws a diagram, and data are analyzed by chart, rejects unnecessary data, obtain the data of high quality.
3. the modeling method according to claim 1 towards broadband access network users internet behavior big data, feature exist
In the step S2, the data of high quality are divided into two data packets of DataBill and FactorBill, wherein DataBill
Be using the internet behavior (such as surf time, browsing content and search key) in user's Internet data as feature vector,
With the surfing flow (uplink traffic and downlink traffic) of user's internet behavior data, using unsupervised algorithm, respectively in the time and
The two groups of training sets for being spatially trained research to it and being formed；FactorBill is by the basic document data of user and position
Data are formed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910250704.7A CN109978627B (en) | 2019-03-29 | 2019-03-29 | Modeling method for big data of broadband access network user surfing behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910250704.7A CN109978627B (en) | 2019-03-29 | 2019-03-29 | Modeling method for big data of broadband access network user surfing behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109978627A true CN109978627A (en) | 2019-07-05 |
| CN109978627B CN109978627B (en) | 2023-08-08 |
Family
ID=67081796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910250704.7A Active CN109978627B (en) | 2019-03-29 | 2019-03-29 | Modeling method for big data of broadband access network user surfing behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109978627B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111030893A (en) * | 2019-12-31 | 2020-04-17 | 上海途鸽数据科技有限公司 | Method and device for analyzing user behaviors in cloud communication application scene |
| CN111245650A (en) * | 2020-01-07 | 2020-06-05 | 广东九联科技股份有限公司 | Network bandwidth optimization management method based on machine learning |
| CN111815361A (en) * | 2020-07-10 | 2020-10-23 | 北京思特奇信息技术股份有限公司 | Region boundary calculation method and device, electronic equipment and storage medium |
| CN112910984A (en) * | 2021-01-26 | 2021-06-04 | 国网福建省电力有限公司泉州供电公司 | Electric power internet of things flow prediction method based on FGn and Poisson process |
| CN116723339A (en) * | 2023-08-11 | 2023-09-08 | 腾讯科技（深圳）有限公司 | Content data distribution method and device, storage medium and electronic equipment |
| CN116886571A (en) * | 2023-09-07 | 2023-10-13 | 武汉博易讯信息科技有限公司 | Analysis method, equipment and computer readable medium for home broadband user |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101990003A (en) * | 2010-10-22 | 2011-03-23 | 西安交通大学 | User action monitoring system and method based on IP address attribute |
| CN102238045A (en) * | 2010-04-27 | 2011-11-09 | 广州迈联计算机科技有限公司 | System and method for predicting user behavior in wireless Internet |
| CN102752123A (en) * | 2011-04-20 | 2012-10-24 | 中国移动通信集团设计院有限公司 | Method and device for forecasting flow and configuring capacity of network equipment interface |
| CN103024762A (en) * | 2012-12-26 | 2013-04-03 | 北京邮电大学 | Service feature based communication service forecasting method |
| CN104331404A (en) * | 2013-07-22 | 2015-02-04 | 中国科学院深圳先进技术研究院 | A user behavior predicting method and device based on net surfing data of a user's cell phone |
| US20160285704A1 (en) * | 2015-03-27 | 2016-09-29 | Iosif Gasparakis | Technologies for dynamic network analysis and provisioning |
| CN107682178A (en) * | 2017-08-30 | 2018-02-09 | 国信优易数据有限公司 | A kind of mobile subscriber's online operation behavior Forecasting Methodology and device |
| CN108462888A (en) * | 2018-03-14 | 2018-08-28 | 江苏有线数据网络有限责任公司 | The intelligent association analysis method and system of user's TV and internet behavior |
| US20180359268A1 (en) * | 2016-02-24 | 2018-12-13 | Ping An Technology (Shenzhen) Co., Ltd. | Method and Device of Identifying Network Access Behavior, Server and Storage Medium |
| CN109495317A (en) * | 2018-12-13 | 2019-03-19 | 中国南方电网有限责任公司 | Data network method for predicting and device |
-
2019
- 2019-03-29 CN CN201910250704.7A patent/CN109978627B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102238045A (en) * | 2010-04-27 | 2011-11-09 | 广州迈联计算机科技有限公司 | System and method for predicting user behavior in wireless Internet |
| CN101990003A (en) * | 2010-10-22 | 2011-03-23 | 西安交通大学 | User action monitoring system and method based on IP address attribute |
| CN102752123A (en) * | 2011-04-20 | 2012-10-24 | 中国移动通信集团设计院有限公司 | Method and device for forecasting flow and configuring capacity of network equipment interface |
| CN103024762A (en) * | 2012-12-26 | 2013-04-03 | 北京邮电大学 | Service feature based communication service forecasting method |
| CN104331404A (en) * | 2013-07-22 | 2015-02-04 | 中国科学院深圳先进技术研究院 | A user behavior predicting method and device based on net surfing data of a user's cell phone |
| US20160285704A1 (en) * | 2015-03-27 | 2016-09-29 | Iosif Gasparakis | Technologies for dynamic network analysis and provisioning |
| US20180359268A1 (en) * | 2016-02-24 | 2018-12-13 | Ping An Technology (Shenzhen) Co., Ltd. | Method and Device of Identifying Network Access Behavior, Server and Storage Medium |
| CN107682178A (en) * | 2017-08-30 | 2018-02-09 | 国信优易数据有限公司 | A kind of mobile subscriber's online operation behavior Forecasting Methodology and device |
| CN108462888A (en) * | 2018-03-14 | 2018-08-28 | 江苏有线数据网络有限责任公司 | The intelligent association analysis method and system of user's TV and internet behavior |
| CN109495317A (en) * | 2018-12-13 | 2019-03-19 | 中国南方电网有限责任公司 | Data network method for predicting and device |
Non-Patent Citations (1)
| Title |
|---|
| 倪明: ""智能接入网用户行为建模及管控研究"", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, no. 12, pages 138 - 299 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111030893A (en) * | 2019-12-31 | 2020-04-17 | 上海途鸽数据科技有限公司 | Method and device for analyzing user behaviors in cloud communication application scene |
| CN111245650A (en) * | 2020-01-07 | 2020-06-05 | 广东九联科技股份有限公司 | Network bandwidth optimization management method based on machine learning |
| CN111815361A (en) * | 2020-07-10 | 2020-10-23 | 北京思特奇信息技术股份有限公司 | Region boundary calculation method and device, electronic equipment and storage medium |
| CN112910984A (en) * | 2021-01-26 | 2021-06-04 | 国网福建省电力有限公司泉州供电公司 | Electric power internet of things flow prediction method based on FGn and Poisson process |
| CN112910984B (en) * | 2021-01-26 | 2023-05-23 | 国网福建省电力有限公司泉州供电公司 | Electric power Internet of things flow prediction method based on FGn and Poisson processes |
| CN116723339A (en) * | 2023-08-11 | 2023-09-08 | 腾讯科技（深圳）有限公司 | Content data distribution method and device, storage medium and electronic equipment |
| CN116723339B (en) * | 2023-08-11 | 2023-11-14 | 腾讯科技（深圳）有限公司 | Content data distribution method and device, storage medium and electronic equipment |
| CN116886571A (en) * | 2023-09-07 | 2023-10-13 | 武汉博易讯信息科技有限公司 | Analysis method, equipment and computer readable medium for home broadband user |
| CN116886571B (en) * | 2023-09-07 | 2023-11-21 | 武汉博易讯信息科技有限公司 | Analysis method, equipment and computer readable medium for home broadband user |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109978627B (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109978627A (en) | Modeling method for big data of user internet access behavior of broadband access network | |
| CN110245981B (en) | Crowd type identification method based on mobile phone signaling data | |
| CN109754597B (en) | Urban road regional congestion regulation and control strategy recommendation system and method | |
| He et al. | Customer preference and station network in the London bike-share system | |
| CN109711865A (en) | A method of prediction is refined based on the mobile radio communication flow that user behavior excavates | |
| CN109962795A (en) | A kind of 4G customer churn method for early warning and system based on multidimensional union variable | |
| CN112541028B (en) | Water environment big data monitoring system and method | |
| CN103024762A (en) | Service feature based communication service forecasting method | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| CN111191966B (en) | Power distribution network voltage disqualification period identification method based on space-time characteristics | |
| CN106332052B (en) | Micro-area public security early warning method based on mobile communication terminal | |
| CN104866922B (en) | A kind of off-grid prediction technique of user and device | |
| CN105208411A (en) | Method and device for realizing digital television target audience statistics | |
| CN104750829A (en) | User position classifying method and system based on signing in features | |
| Xu et al. | Hybrid holiday traffic predictions in cellular networks | |
| Zhao et al. | Celltrademap: Delineating trade areas for urban commercial districts with cellular networks | |
| CN108459997A (en) | High skewness data value probability forecasting method based on deep learning and neural network | |
| Zhou et al. | Discovering spatio-temporal dependencies based on time-lag in intelligent transportation data | |
| CN106209426A (en) | A kind of server load state assessment analysis method and system based on D S evidence theory | |
| CN111127099A (en) | E-commerce user analysis system based on big data and analysis method thereof | |
| CN105761093A (en) | Knowledge-space-based behavior result evaluation method and device | |
| Ramadiani et al. | Evaluation of student academic performance using e-learning with the association rules method and the importance of performance analysis | |
| Ghnemat et al. | Classification of Mobile Customers Behavior and Usage Patterns using Self-Organizing Neural Networks. | |
| Sindhura et al. | Human Resource Management based Economic analysis using Data Mining | |
| Zhao et al. | Urban scale trade area characterization for commercial districts with cellular footprints |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |