CN107426040A - A kind of Forecasting Methodology of network behavior - Google Patents
A kind of Forecasting Methodology of network behavior Download PDFInfo
- Publication number
- CN107426040A CN107426040A CN201710854916.7A CN201710854916A CN107426040A CN 107426040 A CN107426040 A CN 107426040A CN 201710854916 A CN201710854916 A CN 201710854916A CN 107426040 A CN107426040 A CN 107426040A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- kick
- network behavior
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of Forecasting Methodology of network behavior, belongs to user's behaviors analysis technical field, including:The network behavior data of extraction are pre-processed, obtain the objective network behavioral data using the behavior frequency in the unit interval as fluctuation data;Objective network behavioral data is standardized, and the data after standardization are carried out with folding and obtains folding matrix, is detected to folding the kick in matrix;According to the periodic law, stochastic volatility and kick characteristic shown in objective network behavioral data, the time-varying random differential equation models of network behavior are established, and to the time-varying parameter in model and determine parameter and estimate;Parameter is estimated with preceding some all data training patterns using the continuous iteration of dynamic prediction mode, then predicts next all tracks, is predicted with the network behavior to user.The network behavior stochastic model that the present invention establishes can predict the Future Trajectory of network behavior well, and can reflect the multifrequency nature that network behavior has.
Description
Technical field
The invention belongs to user's behaviors analysis technical field, more particularly, to a kind of Forecasting Methodology of network behavior.
Background technology
With the development and popularization of Internet technology, increasing people carries out handling for Traditional affair by internet,
Particularly " internet+" continues deeply and promoted, and accelerates merging for internet and social life so that the behavior mould of the mankind
Formula generates huge change.However, the depth that internet is participated in people increases, thing followed network security situation is but
It is more severe.The universal law of network behavior is furtherd investigate, the kinetic mechanism of network behavior behind is grasped, can be Network Abnormal
Behavioral value provides theoretical foundation, and then produces important function to Support network security.
The existing modeling to network behavior, it is the time interval aspect from network behavior.Numerous studies show, network
The time interval of behavior has the heterogeneous character for deviateing Poisson, and the time interval sequence for showing as behavior obeys power-law distribution.
For this characteristic of network behavior, the queuing model of task based access control priority is suggested, and this class model regards behavior as one
Individual task, it is intended to be described by the priority of task in the form of being lined up to behavior, reappear the heterogeneity of behavior.But very
Multi net voting behavior such as web page browsing, online game etc. belong to interest drive type, and the queuing model of task based access control priority is obvious
Can not effectively it portray.
As the memory characteristic in network behavior is constantly verified, different from the memory effect mould of task queue's model classification
Type is suggested one after another, and the memory characteristic of this class model subordinate act sets out, it is believed that people can according to the height of historical behavior frequency come
Change the probability that current behavior occurs.In addition, the similar model based on interest is also suggested therewith, this class model thinks interest
Change can influence the generation of behavior.The interest of model hypothesis people constantly changes with the time, and the frequency of behavior is dependent on interest
Change, while also adversely affect interest.But even most interested thing also can be by people circadian rhythm and the external world
The influence of the factors such as environment.Only consider that the model of interest can not effectively portray the network behavior for showing cyclic swing.It is a kind of
Periodicity cascade process model is suggested, and the model considers that Email behavior is influenceed so as to show week by day alternates with night
Phase wave characteristic, portray behavior with the Poisson process of cascade, it is intended to explain the origin of behavior heterogeneous character.But also have many
Positive research show, after the influence from circadian rhythm is weeded out from network behavior data, behavior it is heterogeneous still
In the presence of.This is also with regard to explanation, it is intended to which it is defective that the heterogeneity of behavior, which is only attributed to people's own physiological rhythm and pace of moving things,.
Importantly, whether the time interval of network behavior, which obeys power-law distribution, has many disputes.More and more
Positive research finds that logarithm normal distribution, Weibull distributions, Gamma distributions, or even segmentation distribution can preferably describe network
Behavior.Therefore, the angle beyond time interval is needed badly to carry out the potential kinetic mechanism of network behavior and modeling method
Research.
The content of the invention
For the disadvantages described above or Improvement requirement of prior art, the invention provides a kind of Forecasting Methodology of network behavior,
Thus solve existing for the analysis mode of the network behavior of the existing time interval aspect from network behavior to network behavior
Inaccurate technical problem is described.
To achieve the above object, the invention provides a kind of Forecasting Methodology of network behavior, including:
(1) the network behavior data of collection are pre-processed, obtained using the frequency of behavior in the unit interval as fluctuation number
According to objective network behavioral data;
(2) objective network behavioral data is standardized by the average and standard deviation of objective network behavioral data, and it is right
Data after standardization obtain M*N folding matrix by Zhou Jinhang folding, are detected to folding the kick in matrix, its
In, M represents the quantity of the unit interval in one week, and N represents the total all numbers of data of collection;
(3) according to the periodic law, stochastic volatility and kick characteristic shown in objective network behavioral data, build
The time-varying random differential equation models of vertical network behavior, and to the time-varying parameter in model and determine parameter and estimated to obtain target
Model;
(4) next all network behavior tracks of user are predicted by object module.
Preferably, step (2) specifically includes:
(2.1) byTo jth weekly data Yij, i ∈ [1, M], j ∈ [1, N] standardized, wherein μjTable
Show the average of jth weekly data sequence, σjRepresent the standard deviation of j weekly data sequences;
(2.2) if annual acquire N weekly data sequences altogether, length N*M, then every weekly data of collection is advised
Data sequence X after being standardized after generalizedt, t ∈ [1, M × N], then by all folded datas, it is configured to M*N folding square
Battle array Xij, i ∈ [1, M], j ∈ [1, N], to l, l ∈ LiIfIt is considered as then kick, wherein, Li={ lj=
Xij, j ∈ [1, N] } represent to each moment i in week, i ∈ [1, M], the time series in the presence of a length for N,It is the time
Sequence LiAverage,It is time series LiStandard deviation, ξ is preset value.
Preferably, step (3) specifically includes:
(3.1) according to the periodic law, stochastic volatility and kick characteristic shown in objective network behavioral data,
Establish the time-varying random differential equation models of network behavior:
Wherein, k and d is constant, for adjusting the power of two
Weight, a(t)With c(t)It is time-varying parameter, a(t)Be t return average, c(t)It is diffusion amplitude, N(t)It is that parameter is β(t)Time-varying
Compound poisson process, J(t)It is the kick amplitude of t, obedience average is μt, standard deviation σtNormal distribution, WtRepresent one
Wiener-Hopf equation;
(3.2) byTo time-varying parameter a(t)Estimated, byTime-varying is joined
Number c(t)Estimated, wherein, Xtj(t ∈ [1, M], j ∈ [1, N]) represents M*N folding matrix;
(3.3) according to the kick position detected in kick detection-phase and amplitude, byTo time-varying parameter
β(t)Estimated, byTo time-varying parameter μ(t)And σ(t)Estimated, its
In, ncount(t)Detect all numbers of kick for t, N is total all numbers, μ(t)With σ(t)What respectively t detected is all prominent
The average and variance of jump, XJump(tj)It is the kick point being detected in t in N number of week;
(3.4) combined and estimated by Markov Chain Monte Carlo (Markov Chain Monte Carlo, MCMC) method
Time-varying parameter estimate determining parameter k, d.
Preferably, step (4) specifically includes:
(4.1) the dynamic prediction process of model:Using the continuous iteration of dynamic prediction method with the data training pattern of first N weeks
Estimate parameter, then predict the track of the N+1 weeks;
(4.2) index of model prediction performance is weighed:Compute repeatedly model P times, average is asked for the P bars track predicted
Average track is obtained, and final prediction locus is used as using average track.
In general, by the contemplated above technical scheme of the present invention compared with prior art, it can obtain down and show
Beneficial effect:
(1) present invention considers influence of many factors to network behavior, establishes network row from the track aspect of network behavior
For stochastic model.The network behavior model can be suitably used for all types of network behaviors;
(2) network behavior model proposed by the present invention can predict the Future Trajectory of network behavior well, and can reflect
The multifrequency nature that network behavior has.
Brief description of the drawings
Fig. 1 is a kind of schematic flow sheet of the Forecasting Methodology of network behavior disclosed in the embodiment of the present invention;
Fig. 2 is the method that the microblog data in a kind of data to network behavior disclosed in the embodiment of the present invention is pre-processed
Schematic flow sheet;
Fig. 3 be it is a kind of to microblogging group behavior data normalization and kick detects schematic diagram disclosed in the embodiment of the present invention,
Wherein, (a) represents granularity initial data in 2014;(b) represent that data after trend are gone in standardization;(c) represent to detect before going trend
The kick signal arrived;(d) represent to go after trend the kick detected;
Fig. 4 is a kind of time-varying parameter being calculated according to 50 weeks microblog datas before 2015 disclosed in the embodiment of the present invention
a(t)、c(t);
Fig. 5 be one kind disclosed in the embodiment of the present invention by taking the annual data of microblogging 2015 as an example, to the prediction locus of the 21st week with
Real trace comparison diagram, MAPE 15.14%, RMSE 979.78;
Fig. 6 is a kind of prediction result figure by taking the annual data of microblogging 2015 as an example disclosed in the embodiment of the present invention, wherein, (a)
Represent the psd of True Data;(b) psd of prediction data is represented;(c) pdf of True Data is represented;(d) prediction data is represented
pdf。
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as in addition, technical characteristic involved in each embodiment of invention described below
Conflict can is not formed each other to be mutually combined.
The present invention provides a kind of Forecasting Methodology of network behavior from the fluctuation track aspect of network behavior.According to existing reality
Card research, network behavior generally have the characteristics such as heterogeneous, cyclic swing and Memorability.The present invention occurs with the unit interval
Behavior frequency sequence portray network behavior (be referred to as action trail), and according to above-mentioned behavioral trait, by action trail
Change the cyclic swing for being summarized as being influenceed by circadian rhythm, the random fluctuation being affected by the external environment and the shadow by accident
Loud kick, finally establishes the random differential equation models of behavior accordingly, and according to the random differential equation models of foundation to
Next all network behavior tracks at family are predicted.
It is as shown in Figure 1 a kind of schematic flow sheet of the Forecasting Methodology of network behavior disclosed in the embodiment of the present invention, in Fig. 1
In shown method, comprise the following steps:
(1) the network behavior data of extraction are pre-processed, obtained using the frequency of behavior in the unit interval as fluctuation number
According to objective network behavioral data;
In an optional embodiment, as shown in Fig. 2 illustrating process of data preprocessing, comprise the following steps:
Remove the invalid information in primitive network behavioral data, such as system message, the record of timing error, and network
Content of the act is empty record;
Extract the timestamp information that network behavior content ID, ID and network behavior occur;
Sorted according to network behavior content ID, remove the record that network behavior content ID is repeated;
The timestamp information that network behavior occurs is converted into Beijing time;
Temporally information is resequenced to network behavior data, counts the quantity of network behavior in time per unit, finally
Form the objective network behavioral data using the behavior frequency in the unit interval as fluctuation data.
(2) objective network behavioral data is standardized by the average and standard deviation of objective network behavioral data, and it is right
Data after standardization obtain M*N folding matrix by Zhou Jinhang folding, are detected to folding the kick in matrix, its
In, M represents the unit interval quantity in one week, and N represents the total all numbers of data of collection;
Wherein, the detection for the trend meeting strong influence kick that data have, carrying out standardization to data can go well
Except the long-term trend in data.
In an optional embodiment, step (2) specifically includes:
(2.1) byTo jth weekly data Yij, i ∈ [1, M], j ∈ [1, N] standardized, wherein μjTable
Show the average of jth weekly data sequence, σjRepresent the standard deviation of j weekly data sequences;
(2.2) if annual acquire N weekly data sequences altogether, length N*M, then every weekly data of collection is advised
Data sequence X after being standardized after generalizedt, t ∈ [1, M × N], then by all folded datas, it is configured to M*N folding square
Battle array Xij, i ∈ [1, M], j ∈ [1, N], to l, l ∈ LiIfIt is considered as then kick, wherein, Li={ lj=
Xij, j ∈ [1, N] } represent to each moment i in week, i ∈ [1, M], in the presence of time series (the shared M bars that a length is N
Time series),It is time series LiAverage,It is time series LiStandard deviation, ξ is preset value, it is preferable that ξ is taken as
3。
As shown in figure 3, be disclosed in the embodiment of the present invention it is a kind of to micro blog network behavioral data standardization and kick detect
Schematic diagram, wherein, the unit interval is hour, and now M values are 168, and (a) represents granularity initial data in 2014;(b) rule are represented
Generalized goes data after trend;(c) kick for representing to go before trend to detect is illustrated;(d) represent to go after trend the kick detected.
As seen from Figure 3, after data go trend, there are preferable kick Detection results.
(3) according to the periodic law, stochastic volatility and kick characteristic shown in objective network behavioral data, build
The time-varying random differential equation models of vertical network behavior, and to the time-varying parameter in model and determine parameter and estimated to obtain target
Model;
In an optional embodiment, step (3) specifically includes:
(3.1) according to the periodic law, stochastic volatility and kick characteristic shown in objective network behavioral data,
Establish the time-varying random differential equation models of network behavior:
Wherein, k and d is constant, for adjusting the power of two
Weight, a(t)With c(t)It is time-varying parameter, a(t)Be t return average, c(t)It is diffusion amplitude, N(t)It is that parameter is β(t)Time-varying
Compound poisson process, J(t)It is the kick amplitude of t, obedience average is μt, standard deviation σtNormal distribution, WtRepresent one
Wiener-Hopf equation;
Wherein, this model portrays network behavior in terms of three:
a:Drift term k (a(t)-Xt) dt is time-varying equation of linear regression, portray the daily fluctuation rule of network behavior.Due to
The periodic law of human behavior elapses continuous change over time, therefore, will return average a herein(t)It is arranged to time-varying parameter;
b:Diffusion termPortray network behavior is influenceed by external factor in mood, weather etc., caused small
Amplitude random fluctuation;The rule behavioral implications at fluctuation moment in by historical track per the moment, therefore, random fluctuation amplitude
c(t)Time-varying parameter is arranged to, determines the amplitude that parameter d is used for population equilibrium random fluctuation;
C. kick item J(t)dN(t)Portray network behavior is influenceed by accident or much-talked-about topic, and caused violent ripple
It is dynamic, due to the Poisson characteristics that accident typically exhibits, portrayed herein with compound poisson process.
(3.2) byTo time-varying parameter a(t)Estimated, byTime-varying is joined
Number c(t)Estimated, wherein, Xtj(t ∈ [1, M], j ∈ [1, N]) represents M*N folding matrix;
Be as shown in Figure 4 disclosed in the embodiment of the present invention it is a kind of according to 50 weeks microblog datas before 2015 be calculated when
Variable element a(t)、c(t)。
(3.3) according to the kick position detected in kick detection-phase and amplitude, byTo time-varying parameter
β(t)Estimated, byTo time-varying parameter μ(t)And σ(t)Estimated, its
In, ncount(t)Detect all numbers of kick for t, N is total all numbers, μ(t)With σ(t)What respectively t detected is all prominent
The average and variance of jump, XJump(tj)It is the kick point being detected in t in N number of week;
(3.4) time-varying parameter that estimation is combined by Markov Chain Monte Carlo MCMC methodology is estimated to determining parameter k, d
Meter.
(4) next all network behavior tracks of user are predicted by object module.
In an optional embodiment, step (4) specifically includes:
(4.1) the dynamic prediction process of model:It is continuous using dynamic prediction method to investigate the estimated performance of model comprehensively
Iteration estimated parameter with the data training pattern of first N weeks, then predicted the track of the N+1 weeks;Preferably, N is no less than 10.
(4.2) index of model prediction performance is weighed:Compute repeatedly model P times, average is asked for the P bars track predicted
Average track is obtained, and final prediction locus is used as using average track.Preferably, P values are not less than 1000 times.
Using the relative error index of prediction locus and actual path (Mean Absolute Percentage Error,
MAPE) and absolute error index (Root Mean Squared Error, RMSE) carries out qualitative portray to estimated performance.Index
It is calculated as follows:
Model prediction performance is portrayed from data probability distributions aspect and frequency domain aspect using PDF and PSD curves.Such as
Be shown in Fig. 5 one kind disclosed in the embodiment of the present invention by taking the annual data of microblogging 2015 as an example, to the prediction locus of the 21st week with it is true
Track comparison diagram, wherein, the unit interval is hour, and now M values are 168, MAPE 15.14%, RMSE 979.78;Such as figure
It is a kind of prediction result figure by taking the annual data of microblogging 2015 as an example disclosed in the embodiment of the present invention shown in 6, wherein, (a) represents true
The psd of real data;(b) psd of prediction data is represented;(c) pdf of True Data is represented;(d) pdf of prediction data is represented.From
It can be seen from the figure that, it can be very good to predict the Future Trajectory of network behavior using the inventive method.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, all any modification, equivalent and improvement made within the spirit and principles of the invention etc., all should be included
Within protection scope of the present invention.
Claims (4)
- A kind of 1. Forecasting Methodology of network behavior, it is characterised in that including:(1) the network behavior data of collection are pre-processed, obtained using the frequency of behavior in the unit interval as fluctuation data Objective network behavioral data;(2) objective network behavioral data is standardized by the average and standard deviation of objective network behavioral data, and to specification Data after change obtain M*N folding matrix by Zhou Jinhang folding, are detected to folding the kick in matrix, wherein, M Represent the quantity of the unit interval in one week, N represents the data of collection always all numbers;(3) according to the periodic law, stochastic volatility and kick characteristic shown in objective network behavioral data, net is established The time-varying random differential equation models of network behavior, and to the time-varying parameter in model and determine parameter and estimated to obtain target mould Type;(4) next all network behavior tracks of user are predicted by object module.
- 2. according to the method for claim 1, it is characterised in that step (2) specifically includes:(2.1) byTo jth weekly data Yij, i ∈ [1, M], j ∈ [1, N] standardized, wherein μjRepresent jth The average of weekly data sequence, σjRepresent the standard deviation of j weekly data sequences;(2.2) if annual acquire N weekly data sequences altogether, length N*M, then every weekly data of collection is standardized Data sequence X after being standardized afterwardst, t ∈ [1, M × N], then by all folded datas, it is configured to M*N folding matrix Xij, i ∈ [1, M], j ∈ [1, N], to l, l ∈ LiIfIt is considered as then kick, wherein, Li={ lj=Xij,j ∈ [1, N] } represent to each moment i in week, i ∈ [1, M], the time series in the presence of a length for N,It is time series LiAverage,It is time series LiStandard deviation, ξ is preset value.
- 3. according to the method for claim 2, it is characterised in that step (3) specifically includes:(3.1) according to the periodic law, stochastic volatility and kick characteristic shown in objective network behavioral data, establish The time-varying random differential equation models of network behavior:Wherein, k and d is constant, for adjusting the weight of two, a(t)With c(t)It is time-varying parameter, a(t)Be t return average, c(t)It is diffusion amplitude, N(t)It is that parameter is β(t)Time-varying answer Close Poisson process, J(t)It is the kick amplitude of t, obedience average is μt, standard deviation σtNormal distribution, WtRepresent a dimension Receive process;(3.2) byTo time-varying parameter a(t)Estimated, byTo time-varying parameter c(t) Estimated, wherein, Xtj(t ∈ [1, M], j ∈ [1, N]) represents M*N folding matrix;(3.3) according to the kick position detected in kick detection-phase and amplitude, byTo time-varying parameter β(t)Enter Row estimation, byTo time-varying parameter μ(t)And σ(t)Estimated, wherein, ncount(t)Detect all numbers of kick for t, N is total all numbers, μ(t)With σ(t)All kicks that respectively t detects Average and variance, XJump(tj)It is the kick point being detected in t in N number of week;(3.4) time-varying parameter that estimation is combined by Markov Chain Monte Carlo MCMC methodology is estimated determining parameter k, d.
- 4. according to the method for claim 3, it is characterised in that step (4) specifically includes:(4.1) the dynamic prediction process of model:Estimated using the continuous iteration of dynamic prediction method with the data training pattern of first N weeks Parameter, then predict the track of the N+1 weeks;(4.2) index of model prediction performance is weighed:Compute repeatedly model P times, the P bars track predicted is asked for being worth to Average track, and final prediction locus is used as using average track.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710854916.7A CN107426040B (en) | 2017-09-20 | 2017-09-20 | A kind of prediction technique of network behavior |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710854916.7A CN107426040B (en) | 2017-09-20 | 2017-09-20 | A kind of prediction technique of network behavior |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107426040A true CN107426040A (en) | 2017-12-01 |
CN107426040B CN107426040B (en) | 2019-08-30 |
Family
ID=60433680
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710854916.7A Expired - Fee Related CN107426040B (en) | 2017-09-20 | 2017-09-20 | A kind of prediction technique of network behavior |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107426040B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108228887A (en) * | 2018-01-31 | 2018-06-29 | 百度在线网络技术(北京)有限公司 | For generating the method and apparatus of information |
CN109597833A (en) * | 2018-10-15 | 2019-04-09 | 平安科技(深圳)有限公司 | Event prediction method, apparatus, computer equipment and storage medium based on big data |
CN110149343A (en) * | 2019-05-31 | 2019-08-20 | 国家计算机网络与信息安全管理中心 | A kind of abnormal communications and liaison behavioral value method and system based on stream |
CN116975300A (en) * | 2023-09-22 | 2023-10-31 | 中国铁塔股份有限公司吉林省分公司 | Information mining method and system based on big data set |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102075352A (en) * | 2010-12-17 | 2011-05-25 | 北京邮电大学 | Method and device for predicting network user behavior |
US20160361441A1 (en) * | 2015-04-16 | 2016-12-15 | Alder Biopharmaceuticals, Inc. | Use of anti-pacap antibodies and antigen binding fragments thereof for treatment, prevention, or inhibition of photophobia |
-
2017
- 2017-09-20 CN CN201710854916.7A patent/CN107426040B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102075352A (en) * | 2010-12-17 | 2011-05-25 | 北京邮电大学 | Method and device for predicting network user behavior |
US20160361441A1 (en) * | 2015-04-16 | 2016-12-15 | Alder Biopharmaceuticals, Inc. | Use of anti-pacap antibodies and antigen binding fragments thereof for treatment, prevention, or inhibition of photophobia |
US20160376363A1 (en) * | 2015-04-16 | 2016-12-29 | Alder Biopharmaceuticals, Inc. | Use of anti-pacap antibodies and antigen binding fragments thereof for treatment, prevention, or inhibition of photophobia |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108228887A (en) * | 2018-01-31 | 2018-06-29 | 百度在线网络技术(北京)有限公司 | For generating the method and apparatus of information |
CN108228887B (en) * | 2018-01-31 | 2019-12-03 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating information |
CN109597833A (en) * | 2018-10-15 | 2019-04-09 | 平安科技(深圳)有限公司 | Event prediction method, apparatus, computer equipment and storage medium based on big data |
CN110149343A (en) * | 2019-05-31 | 2019-08-20 | 国家计算机网络与信息安全管理中心 | A kind of abnormal communications and liaison behavioral value method and system based on stream |
CN110149343B (en) * | 2019-05-31 | 2021-07-16 | 国家计算机网络与信息安全管理中心 | Abnormal communication behavior detection method and system based on flow |
CN116975300A (en) * | 2023-09-22 | 2023-10-31 | 中国铁塔股份有限公司吉林省分公司 | Information mining method and system based on big data set |
CN116975300B (en) * | 2023-09-22 | 2024-01-26 | 中国铁塔股份有限公司吉林省分公司 | Information mining method and system based on big data set |
Also Published As
Publication number | Publication date |
---|---|
CN107426040B (en) | 2019-08-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liang et al. | Spatial-temporal aware inductive graph neural network for C-ITS data recovery | |
Mohan et al. | An approach to forecast impact of Covid‐19 using supervised machine learning model | |
CN107426040A (en) | A kind of Forecasting Methodology of network behavior | |
CN106682770B (en) | Dynamic microblog forwarding behavior prediction system and method based on friend circle | |
Toole et al. | Tracking employment shocks using mobile phone data | |
Subbian et al. | Detecting large reshare cascades in social networks | |
Janczura et al. | Efficient estimation of Markov regime-switching models: An application to electricity spot prices | |
WO2019153604A1 (en) | Device and method for creating human/machine identification model, and computer readable storage medium | |
Qu et al. | An intrusion detection model based on deep belief network | |
CN108234462A (en) | A kind of method that intelligent intercept based on cloud protection threatens IP | |
CN111460294A (en) | Message pushing method and device, computer equipment and storage medium | |
CN109523021A (en) | A kind of dynamic network Structure Prediction Methods based on long memory network in short-term | |
CN107870957A (en) | A kind of popular microblogging Forecasting Methodology based on information gain and BP neural network | |
CN109767225B (en) | Network payment fraud detection method based on self-learning sliding time window | |
Liu et al. | Sparse-gev: Sparse latent space model for multivariate extreme value time serie modeling | |
CN110837888A (en) | Traffic missing data completion method based on bidirectional cyclic neural network | |
CN110378124A (en) | A kind of network security threats analysis method and system based on LDA machine learning | |
CN115221396A (en) | Information recommendation method and device based on artificial intelligence and electronic equipment | |
CN111967011B (en) | Interpretable internal threat assessment method | |
Qiao et al. | Feature selection strategy for machine learning methods in building energy consumption prediction | |
CN111768031A (en) | Method for predicting crowd gathering tendency based on ARMA algorithm | |
CN106777162A (en) | A kind of high accuracy microblogging forwards Forecasting Methodology | |
CN103593385A (en) | Novel multi-model intelligent internet police detection method for use in big data environments | |
Xie et al. | Modelling cascades over time in microblogs | |
Liu et al. | Predicting construction accidents on sites: An improved atomic search optimization algorithm approach |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190830 Termination date: 20200920 |
|
CF01 | Termination of patent right due to non-payment of annual fee |