CN106447383A - Cross-time multi-dimensional abnormal data monitoring method and system - Google Patents
Cross-time multi-dimensional abnormal data monitoring method and system Download PDFInfo
- Publication number
- CN106447383A CN106447383A CN201610770514.4A CN201610770514A CN106447383A CN 106447383 A CN106447383 A CN 106447383A CN 201610770514 A CN201610770514 A CN 201610770514A CN 106447383 A CN106447383 A CN 106447383A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- click
- web
- cheating
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0245—Surveys
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a cross-time multi-dimensional abnormal data monitoring method and system. The method includes: collecting Web logs and OLA log queries to obtain website information, delivery advertisement information and user information; cleaning obtained heterogeneous data by employing Python in a Spark environment, generating an electronic table corresponding to each dimension, and preparing modeling analysis; establishing a normal advertisement click behavior model by employing a GBDT algorithm; conducting a modeling analysis on an abnormal data sample by employing a support vector machine, and establishing an abnormal advertisement click behavior model; and generating a cheating click monitoring model, and deploying an online anti-cheating model. According to the method and system, the problems of fusion analysis of various heterogeneous data and small sample classification accuracy are solved by employing machine learning and cloud computing technologies through monitoring of cheating Internet advertisement traffic, subsequent Internet advertisement click data can be recorded and analyzed in a whole machine learning chain, the anti-cheating model is improved, and the accuracy of advertisement delivery can be better achieved.
Description
Technical field
The present invention relates to field of computer technology, more particularly, to a kind of method across time, the monitoring of various dimensions abnormal data
And system.
Background technology
The various cheatings that online advertisement easily produces after throwing in, including by program or script malice analog subscriber
The ad click that the improper approach flow that click etc. brings produces, compromises the interests of advertiser and advertising platform, existing skill
In art, supervised learning method is mainly based upon to the modeling method of abnormal ad click behavior, from original log, extracts each
The feature of record, experience manually labels, and regenerates model, not only efficiency is low for this method, and cannot adapt to opening up of business
Exhibition, when access data volume reaches more than TB or even PB rank, all cannot meet industry from ageing and process performance
Business demand.
Therefore, the urgent technical problem solving of those skilled in the art is needed to be exactly at present：How innovatively
A kind of effective measures are proposed, by multidimensional analysis inquiry is carried out to the magnanimity displaying daily record of ad system, click logs on line, system
The anti-cheating model of fixed exception ad click behavior, filters the function that cheating is clicked on, to be monitored to cheating ad click.
Content of the invention
For solving the above problems, the invention discloses a kind of method and system across time, the monitoring of various dimensions abnormal data,
To formulate the anti-cheating model of abnormal ad click behavior, filter the function that cheating is clicked on, to be supervised to cheating ad click
Survey.
One side according to embodiments of the present invention, a kind of method across time, the monitoring of various dimensions abnormal data providing,
Including：
Collect Web daily record and OLAP log query, obtain site information, displaying advertising messages and user profile, by receiving
Collection Web daily record and OLAP log query, obtain website click on record, website, website visiting timestamp, web IP address,
Access subject of Web site, advertisement classification, location advertising, advertisement form, advertisement size and user name, access browser, user interest
Label；
Using Python, the isomeric data of acquisition is carried out under Spark environment, generates the corresponding electronics of each dimension
Form, prepares modeling analysis；
Set up normal ad click behavior model using GBDT algorithm, described normal ad click behavior model is using not
Find the practise fraud user clicking on, advertisement, the model of data on flows foundation, GBDT algorithm will utilize Python under Spark environment
After the isomeric data of acquisition is carried out, as input, GBDT is a kind of integrated learning approach to the data set generating each dimension,
Base learner is CART decision tree, for recurrence and classification prediction, GBDT training T wheel, each error taken turns according to model before
Multiple base learners are finally grouped together using the method for linear weighted function and form a strong learner by the CART tree of training；
Abnormal data sample is modeled analyze using SVMs, sets up abnormal ad click behavior model, institute
State support vector machine method be built upon Statistical Learning Theory VC dimension is theoretical and Structural risk minization basis on, according to having
Limit sample information seeks optimal compromise between the complexity and learning ability of model, to obtaining best Generalization Ability, leads to
Cross calculating classification border support vector the carrying out under sample data is classified, in SVM modeling, make different classes of sample width
Divide, expand frontier distance；
After obtaining normal ad click behavior model and setting up abnormal ad click behavior model, by two Model Fusion,
Generate cheating and click on monitoring model, deployment anti-cheating model online, and in real time click information is analyzed.
Based in another embodiment of said method, described collection Web daily record and OLAP log query, obtain website letter
Breath, displaying advertising messages and user profile include：
Collect Web daily record and OLAP log query, obtain site information, displaying advertising messages and user profile；
The data separation collected is normal site information, displaying advertising messages and user profile, and the website of exception
Information, displaying advertising messages and user profile.
Based in another embodiment of said method, when described Web daily record accesses Web server for the network user, Web
The access log information that server is automatically set up, include ID, the URL of interviewed Web, the IP address of user, the access date and
Time.
Based in another embodiment of said method, described generation each dimension corresponding electrical form content includes：It is
No click, station address, advertisement position size, web site tags, input advertisement classification, user name, browser title, timestamp.
Other side according to embodiments of the present invention, provide a kind of across the time, various dimensions abnormal data monitoring be
System, including：Anti- cheating model portion on Web log pattern, OLAP log query module, local analytics data MBM, line
Administration's module；
By collecting web log pattern and OLAP log query module, obtain normal data and abnormal data；By local
Analyze data MBM are carried out and set up model to obtaining data；Online by cheating model deployment module anti-on line
On multidimensional data is analyzed assess, deployment anti-cheating model online, in real time click information is analyzed.
Based in another embodiment of said system, the described web log pattern storage network user accesses Web server
When, the access log information that Web server is set up automatically, including ID, the URL of interviewed Web, the IP address of user, access
Date and time information.
Based in another embodiment of said system, described local analytics data MBM passes through in Spark ring
Using Python, the isomeric data of acquisition is carried out under border, generates normal data, set up using GBDT algorithm normally wide
Accuse and click on behavior model, SVMs abnormal data to be modeled analyze, and sets up abnormal ad click behavior model.
Based in another embodiment of said system, on described line, anti-cheating model deployment module is by normal ad click
Behavior model and abnormal ad click behavior model merge, and generation is practised fraud and clicked on monitoring model, and deployment anti-cheating model online is real
When click information is analyzed.
Compared with prior art, the present invention includes advantages below：
The present invention passes through monitoring cheating Internet advertising flow, using machine learning and cloud computing technology, solves multiple different
The analysis of structure data fusion and small sample classification accuracy problems, the present invention can also record subsequently in whole machine learning chain
Internet advertising click data, and this is analyzed, improve anti-cheating model, preferably to realize the accurate of advertisement putting
Degree.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used in technology description to do one simply to introduce.
Fig. 1 is a kind of flow chart across time, one embodiment of method of various dimensions abnormal data monitoring of the present invention.
Fig. 2 is a kind of flow chart across time, another embodiment of method of various dimensions abnormal data monitoring of the present invention.
Fig. 3 is a kind of structural representation across time, one embodiment of system of various dimensions abnormal data monitoring of the present invention
Figure.
In figure：Anti- on 1 Web log pattern, 2 OLAP log query modules, 3 local analytics data MBM, 4 lines
Cheating model deployment module.
Specific embodiment
Purpose, technical scheme and advantage for making the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described it is clear that described embodiment only
It is only a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill
The every other embodiment that personnel are obtained under the premise of not making creative work, broadly falls into the scope of protection of the invention.
Fig. 1 is a kind of flow chart across time, one embodiment of method of various dimensions abnormal data monitoring of the present invention, such as
Shown in Fig. 1, a kind of described method across time, the monitoring of various dimensions abnormal data, including：
10, collect Web daily record and OLAP log query, obtain site information, displaying advertising messages and user profile, pass through
Collect Web daily record and OLAP log query, obtain website and click on record, website, website visiting timestamp, website IP ground
Location, access subject of Web site, advertisement classification, location advertising, advertisement form, advertisement size and user name, access browser, Yong Huxing
Interesting label；
20, using Python, the isomeric data of acquisition is carried out under Spark environment, generates the corresponding electricity of each dimension
Sub-table, prepares modeling analysis；
30, set up normal ad click behavior model using GBDT algorithm, described normal ad click behavior model is to make
With not finding the model of the user clicking on, advertisement, data on flows foundation of practising fraud, GBDT algorithm will utilize under Spark environment
After the isomeric data of acquisition is carried out by Python, as input, GBDT is a kind of integrated to the data set generating each dimension
Learning method, base learner is CART decision tree, for the prediction that returns and classify, GBDT training T wheel, each wheel basis model before
Error training CART tree, finally using the method for linear weighted function, multiple base learners are grouped together strong of formation one
Practise device；
40, abnormal data sample is modeled analyze using SVMs, sets up abnormal ad click behavior model,
Described support vector machine method is built upon in the VC dimension theory and Structural risk minization basis of Statistical Learning Theory, according to
Finite sample information seeks optimal compromise between the complexity and learning ability of model, to obtaining best Generalization Ability,
By calculating classification border support vector, the carrying out under sample data is classified, in SVM modeling, make different classes of sample
Wide division, expands frontier distance；
50, after obtaining normal ad click behavior model and setting up abnormal ad click behavior model, two models are melted
Close, generate cheating and click on monitoring model, deployment anti-cheating model online, and in real time click information is analyzed.
Fig. 2 is a kind of flow chart across time, another embodiment of method of various dimensions abnormal data monitoring of the present invention,
As shown in Fig. 2 described collection Web daily record and OLAP log query, obtain site information, displaying advertising messages and user profile bag
Include：
11, collect Web daily record and OLAP log query, obtain site information, displaying advertising messages and user profile；
12, the data separation collected is normal site information, displaying advertising messages and user profile, and the net of exception
Stand information, displaying advertising messages and user profile.
The method across time, the monitoring of various dimensions abnormal data being provided based on the above embodiment of the present invention, described Web daily record
When accessing Web server for the network user, the access log information that Web server is set up automatically, including ID, interviewed Web
URL, the IP address of user, access date and time.
The method across time, the monitoring of various dimensions abnormal data being provided based on the above embodiment of the present invention, described generation is each
Dimension corresponding electrical form content includes：Whether click on, station address, advertisement position size, web site tags, throw in commercial paper
Not, user name, browser title, timestamp.
Fig. 3 is a kind of structural representation across time, one embodiment of system of various dimensions abnormal data monitoring of the present invention
Figure, as shown in figure 3, a kind of system across time, the monitoring of various dimensions abnormal data, including：Web log pattern 1, OLAP daily record are looked into
Ask anti-cheating model deployment module 4 on module 2, local analytics data MBM 3, line；
By collecting web log pattern 1 and OLAP log query module 2, obtain normal data and abnormal data；By this
Ground analyze data and MBM 3 to obtain data be carried out and set up model；By cheating model deployment module 4 anti-on line
On line multidimensional data is analyzed assessing, deployment anti-cheating model online, in real time click information is analyzed.
The system across time, the monitoring of various dimensions abnormal data being provided based on the above embodiment of the present invention, described web daily record
When the module 1 storage network user accesses Web server, the access log information that Web server is automatically set up, including ID,
The URL of interviewed Web, the IP address of user, access date and time information.
The system across time, the monitoring of various dimensions abnormal data being provided based on the above embodiment of the present invention, described local point
Analyse data and MBM 3 is by being carried out the isomeric data of acquisition using Python under Spark environment, generate normal
Data, sets up normal ad click behavior model using GBDT algorithm, and SVMs abnormal data is modeled point
Analysis, sets up abnormal ad click behavior model.
The system across time, the monitoring of various dimensions abnormal data being provided based on the above embodiment of the present invention, anti-on described line
Normal ad click behavior model and abnormal ad click behavior model are merged by cheating model deployment module 4, generate cheating point
Hit monitoring model, deployment anti-cheating model online, in real time click information is analyzed.
Above a kind of method and system across time, the monitoring of various dimensions abnormal data provided by the present invention is carried out in detail
Thin introduce, specific case used herein is set forth to the principle of the present invention and embodiment, the saying of above example
Bright it is only intended to help and understands the method for the present invention and its core concept；Simultaneously for one of ordinary skill in the art, foundation
The thought of the present invention, all will change in specific embodiments and applications, and in sum, this specification content is not
It is interpreted as limitation of the present invention.
Finally it should be noted that：The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention,
Although being described in detail to the present invention with reference to the foregoing embodiments, for a person skilled in the art, it still may be used
To modify to the technical scheme described in foregoing embodiments, or equivalent is carried out to wherein some technical characteristics,
All any modification, equivalent substitution and improvement within the spirit and principles in the present invention, made etc., should be included in the present invention's
Within protection domain.
Claims (8)
1. a kind of method monitored across time, various dimensions abnormal data is it is characterised in that include：
Collect Web daily record and OLAP log query, obtain site information, displaying advertising messages and user profile, by collecting Web
Daily record and OLAP log query, obtain website and click on record, website, website visiting timestamp, web IP address, access net
Station owner inscribes, advertisement classification, location advertising, advertisement form, advertisement size and user name, access browser, user interest label；
Using Python, the isomeric data of acquisition is carried out under Spark environment, generates the corresponding electrical form of each dimension,
Prepare modeling analysis；
Set up normal ad click behavior model using GBDT algorithm, described normal ad click behavior model is to use not finding
The model that the user of cheating click, advertisement, data on flows are set up, GBDT algorithm will will be obtained using Python under Spark environment
After the isomeric data obtaining is carried out, as input, GBDT is a kind of integrated learning approach to the data set generating each dimension, base
Practising device is CART decision tree, for recurrence and classification prediction, GBDT training T wheel, each error training taken turns according to model before
CART tree, finally using linear weighted function method by multiple base learners be grouped together formation one strong learner；
Abnormal data sample is modeled analyze using SVMs, the abnormal ad click behavior model of foundation, described
Hold vector machine method to be built upon in the VC dimension theory and Structural risk minization basis of Statistical Learning Theory, according to limited sample
This information seeks optimal compromise between the complexity and learning ability of model, to obtaining best Generalization Ability, by meter
Calculate classification border support vector the carrying out under sample data is classified, in SVM modeling, different classes of sample width divided,
Expand frontier distance；
After obtaining normal ad click behavior model and setting up abnormal ad click behavior model, two Model Fusion generate
Monitoring model, deployment anti-cheating model online are clicked in cheating, and in real time click information are analyzed.
2. method according to claim 1, it is characterised in that described collection Web daily record and OLAP log query, obtains net
Information, displaying advertising messages and the user profile of standing includes：
Collect Web daily record and OLAP log query, obtain site information, displaying advertising messages and user profile；
By the data separation collected be normal site information, displaying advertising messages and user profile, and exception site information,
Displaying advertising messages and user profile.
3. method according to claim 1 is it is characterised in that described Web daily record accesses Web server for the network user
When, the access log information that Web server is set up automatically, including ID, the URL of interviewed Web, the IP address of user, access
Date and time.
4. method according to claim 1 is it is characterised in that each dimension of described generation corresponding electrical form content bag
Include：Whether click on, station address, advertisement position size, web site tags, throw in advertisement classification, user name, browser title, the time
Stamp.
5. a kind of system monitored across time, various dimensions abnormal data is it is characterised in that include：Web log pattern, OLAP day
Anti- cheating model deployment module on will enquiry module, local analytics data MBM, line；
By collecting web log pattern and OLAP log query module, obtain normal data and abnormal data；By local analytics
Data MBM are carried out and set up model to obtaining data；Right on line by cheating model deployment module anti-on line
Multidimensional data is analyzed assessing, deployment anti-cheating model online, in real time click information is analyzed.
6. system according to claim 5 is it is characterised in that the described web log pattern storage network user accesses Web clothes
During business device, the access log information that Web server is automatically set up, including ID, the URL of interviewed Web, the IP address of user,
Access date and time information.
7. system according to claim 6 is it is characterised in that described local analytics data MBM pass through
Using Python, the isomeric data of acquisition is carried out under Spark environment, generates normal data, set up using GBDT algorithm
Normal ad click behavior model, SVMs abnormal data to be modeled analyze, and sets up abnormal ad click behavior
Model.
8. the system according to claim 6 or 7 will be it is characterised in that anti-cheating model deployment module will be normal on described line
Ad click behavior model and abnormal ad click behavior model merge, and generate cheating and click on monitoring model, deployment is counter online to be made
Disadvantage model, is analyzed to click information in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610770514.4A CN106447383A (en) | 2016-08-30 | 2016-08-30 | Cross-time multi-dimensional abnormal data monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610770514.4A CN106447383A (en) | 2016-08-30 | 2016-08-30 | Cross-time multi-dimensional abnormal data monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106447383A true CN106447383A (en) | 2017-02-22 |
Family
ID=58091765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610770514.4A Pending CN106447383A (en) | 2016-08-30 | 2016-08-30 | Cross-time multi-dimensional abnormal data monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106447383A (en) |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103047A (en) * | 2017-03-31 | 2017-08-29 | 北京奇艺世纪科技有限公司 | A kind of method and device for inquiring about advertisement putting abnormal cause |
| CN107330718A (en) * | 2017-06-09 | 2017-11-07 | 晶赞广告（上海）有限公司 | A kind of anti-cheat method of media and device, storage medium, terminal |
| CN107483443A (en) * | 2017-08-22 | 2017-12-15 | 北京京东尚科信息技术有限公司 | advertisement information processing method, client, storage medium and electronic equipment |
| CN107609172A (en) * | 2017-09-28 | 2018-01-19 | 链家网（北京）科技有限公司 | A kind of cross-system multi-dimensional data search processing method and device |
| WO2018161824A1 (en) * | 2017-03-10 | 2018-09-13 | 博彦科技股份有限公司 | Exceptional data detection method and device |
| CN108959415A (en) * | 2018-06-07 | 2018-12-07 | 北京奇艺世纪科技有限公司 | A kind of exception dimension localization method, device and electronic equipment |
| CN109145030A (en) * | 2018-06-26 | 2019-01-04 | 阿里巴巴集团控股有限公司 | A kind of detection method and device of abnormal data access |
| CN109412900A (en) * | 2018-12-04 | 2019-03-01 | 腾讯科技（深圳）有限公司 | A kind of network state knows the method and device of method for distinguishing, model training |
| CN109408268A (en) * | 2018-10-09 | 2019-03-01 | 浪潮软件股份有限公司 | A kind of new retail barcode scanning data exception detection method based on cloud POS machine |
| CN109409529A (en) * | 2018-09-13 | 2019-03-01 | 北京中科闻歌科技股份有限公司 | A kind of event cognitive analysis method, system and storage medium |
| CN109743300A (en) * | 2018-12-20 | 2019-05-10 | 浙江鹏信信息科技股份有限公司 | A kind of security incident automation method of disposal based on isomery model strategy library |
| CN109858886A (en) * | 2019-02-18 | 2019-06-07 | 国网吉林省电力有限公司电力科学研究院 | A cost control success rate improvement analysis method based on ensemble learning |
| CN110210507A (en) * | 2018-10-29 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Detection method, device and the readable storage medium storing program for executing that machine is clicked |
| CN110266510A (en) * | 2018-03-21 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Network control strategy generation method and device, network control method, storage medium |
| WO2019218751A1 (en) * | 2018-05-16 | 2019-11-21 | 阿里巴巴集团控股有限公司 | Processing method, apparatus and device for risk prediction of insurance service |
| CN110502492A (en) * | 2019-08-14 | 2019-11-26 | 深圳市优课在线教育有限公司 | A kind of real-time anti-cheating detection and method for early warning towards online education |
| CN110781605A (en) * | 2019-11-05 | 2020-02-11 | 恩亿科(北京)数据科技有限公司 | Advertisement putting model testing method and device, computer equipment and storage medium |
| CN110881022A (en) * | 2018-09-06 | 2020-03-13 | 福建雷盾信息安全有限公司 | Large-scale network security situation detection and analysis method |
| CN110992104A (en) * | 2019-12-11 | 2020-04-10 | 杭州古点网络科技有限公司 | Abnormal advertisement flow detection method based on user portrait |
| CN110992096A (en) * | 2019-12-03 | 2020-04-10 | 秒针信息技术有限公司 | Prediction model training method and device and media identification prediction method and device |
| CN111105259A (en) * | 2018-10-29 | 2020-05-05 | 北京奇虎科技有限公司 | A user identification method, device, electronic device and storage medium |
| CN111291720A (en) * | 2020-03-10 | 2020-06-16 | 孔华 | Building advertisement identification system based on cloud computing network |
| CN111708678A (en) * | 2020-08-18 | 2020-09-25 | 北京志翔科技股份有限公司 | An abnormality monitoring method and device |
| CN111738770A (en) * | 2020-06-28 | 2020-10-02 | 北京达佳互联信息技术有限公司 | Advertisement abnormal flow detection method and device |
| CN111861568A (en) * | 2020-07-23 | 2020-10-30 | 上海志窗信息科技有限公司 | Internet advertisement monitoring system and method thereof |
| CN111882367A (en) * | 2020-08-11 | 2020-11-03 | 北京云和互动信息技术有限公司 | Method for monitoring and tracking online advertisements through user internet behavior analysis |
| CN112101678A (en) * | 2020-09-23 | 2020-12-18 | 东莞理工学院 | GBDT-based student personality tendency prediction method |
| CN112118259A (en) * | 2020-09-17 | 2020-12-22 | 四川长虹电器股份有限公司 | Unauthorized vulnerability detection method based on classification model of lifting tree |
| CN112406894A (en) * | 2019-08-21 | 2021-02-26 | 美光科技公司 | Smart recording of wrong vehicle behavior |
| CN112651790A (en) * | 2021-01-19 | 2021-04-13 | 恩亿科(北京)数据科技有限公司 | OCPX self-adaptive learning method and system based on user reach in fast-moving industry |
| CN112950249A (en) * | 2019-12-16 | 2021-06-11 | 旺脉信息科技(上海)有限公司 | Method and system for processing advertisement flow data, electronic equipment and storage medium |
| CN114238064A (en) * | 2021-12-30 | 2022-03-25 | 深圳依时货拉拉科技有限公司 | Cheating detection method and device, storage medium and computer equipment |
| CN114331519A (en) * | 2021-12-23 | 2022-04-12 | 杭州迈库网络科技有限公司 | Advertisement data tracking system and monitoring terminal thereof |
| CN114626876A (en) * | 2022-02-23 | 2022-06-14 | 深圳市创梦天地科技有限公司 | Training method, system and related device for abnormal flow detection model |
| CN114663121A (en) * | 2020-12-23 | 2022-06-24 | 华扬联众数字技术股份有限公司 | Method and device for abnormal advertising traffic detection |
| US12210401B2 (en) | 2019-09-05 | 2025-01-28 | Micron Technology, Inc. | Temperature based optimization of data storage operations |
| CN119624543A (en) * | 2024-11-22 | 2025-03-14 | 南京合宜信息技术有限公司 | A method and system for optimizing precise advertising delivery |
| US12443387B2 (en) | 2019-08-21 | 2025-10-14 | Micron Technology, Inc. | Intelligent audio control in vehicles |
| US12497055B2 (en) | 2019-08-21 | 2025-12-16 | Micron Technology, Inc. | Monitoring controller area network bus for vehicle control |
| US12518570B2 (en) | 2019-12-18 | 2026-01-06 | Lodestar Licensing Group Llc | Predictive maintenance of automotive transmission |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102821002A (en) * | 2011-06-09 | 2012-12-12 | 中国移动通信集团河南有限公司信阳分公司 | Method and system for network flow anomaly detection |
| CN103200262A (en) * | 2013-04-02 | 2013-07-10 | 亿赞普(北京)科技有限公司 | Method, device and system for advertisement scheduling based on mobile network |
| CN103390027A (en) * | 2013-06-25 | 2013-11-13 | 亿赞普(北京)科技有限公司 | Internet advertisement anti-spamming method and system |
| US20140068411A1 (en) * | 2012-08-31 | 2014-03-06 | Scott Ross | Methods and apparatus to monitor usage of internet advertising networks |
-
2016
- 2016-08-30 CN CN201610770514.4A patent/CN106447383A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102821002A (en) * | 2011-06-09 | 2012-12-12 | 中国移动通信集团河南有限公司信阳分公司 | Method and system for network flow anomaly detection |
| US20140068411A1 (en) * | 2012-08-31 | 2014-03-06 | Scott Ross | Methods and apparatus to monitor usage of internet advertising networks |
| CN103200262A (en) * | 2013-04-02 | 2013-07-10 | 亿赞普(北京)科技有限公司 | Method, device and system for advertisement scheduling based on mobile network |
| CN103390027A (en) * | 2013-06-25 | 2013-11-13 | 亿赞普(北京)科技有限公司 | Internet advertisement anti-spamming method and system |
Cited By (54)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018161824A1 (en) * | 2017-03-10 | 2018-09-13 | 博彦科技股份有限公司 | Exceptional data detection method and device |
| CN107103047A (en) * | 2017-03-31 | 2017-08-29 | 北京奇艺世纪科技有限公司 | A kind of method and device for inquiring about advertisement putting abnormal cause |
| CN107330718A (en) * | 2017-06-09 | 2017-11-07 | 晶赞广告（上海）有限公司 | A kind of anti-cheat method of media and device, storage medium, terminal |
| CN107483443A (en) * | 2017-08-22 | 2017-12-15 | 北京京东尚科信息技术有限公司 | advertisement information processing method, client, storage medium and electronic equipment |
| CN107483443B (en) * | 2017-08-22 | 2020-06-05 | 北京京东尚科信息技术有限公司 | Advertisement information processing method, client, storage medium and electronic device |
| CN107609172A (en) * | 2017-09-28 | 2018-01-19 | 链家网（北京）科技有限公司 | A kind of cross-system multi-dimensional data search processing method and device |
| CN107609172B (en) * | 2017-09-28 | 2020-11-24 | 贝壳找房(北京)科技有限公司 | Cross-system multi-dimensional data retrieval processing method and device |
| CN110266510A (en) * | 2018-03-21 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Network control strategy generation method and device, network control method, storage medium |
| WO2019218751A1 (en) * | 2018-05-16 | 2019-11-21 | 阿里巴巴集团控股有限公司 | Processing method, apparatus and device for risk prediction of insurance service |
| CN108959415B (en) * | 2018-06-07 | 2022-03-04 | 北京奇艺世纪科技有限公司 | Abnormal dimension positioning method and device and electronic equipment |
| CN108959415A (en) * | 2018-06-07 | 2018-12-07 | 北京奇艺世纪科技有限公司 | A kind of exception dimension localization method, device and electronic equipment |
| CN109145030A (en) * | 2018-06-26 | 2019-01-04 | 阿里巴巴集团控股有限公司 | A kind of detection method and device of abnormal data access |
| CN110881022A (en) * | 2018-09-06 | 2020-03-13 | 福建雷盾信息安全有限公司 | Large-scale network security situation detection and analysis method |
| CN109409529A (en) * | 2018-09-13 | 2019-03-01 | 北京中科闻歌科技股份有限公司 | A kind of event cognitive analysis method, system and storage medium |
| CN109408268B (en) * | 2018-10-09 | 2021-11-19 | 浪潮软件股份有限公司 | New retail code scanning data anomaly detection method based on cloud POS machine |
| CN109408268A (en) * | 2018-10-09 | 2019-03-01 | 浪潮软件股份有限公司 | A kind of new retail barcode scanning data exception detection method based on cloud POS machine |
| CN111105259B (en) * | 2018-10-29 | 2024-04-02 | 北京奇虎科技有限公司 | A user identification method, device, electronic device and storage medium |
| CN110210507A (en) * | 2018-10-29 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Detection method, device and the readable storage medium storing program for executing that machine is clicked |
| CN111105259A (en) * | 2018-10-29 | 2020-05-05 | 北京奇虎科技有限公司 | A user identification method, device, electronic device and storage medium |
| CN109412900A (en) * | 2018-12-04 | 2019-03-01 | 腾讯科技（深圳）有限公司 | A kind of network state knows the method and device of method for distinguishing, model training |
| CN109743300A (en) * | 2018-12-20 | 2019-05-10 | 浙江鹏信信息科技股份有限公司 | A kind of security incident automation method of disposal based on isomery model strategy library |
| CN109858886B (en) * | 2019-02-18 | 2021-03-19 | 国网吉林省电力有限公司电力科学研究院 | Integrated learning-based cost control success rate promotion analysis method |
| CN109858886A (en) * | 2019-02-18 | 2019-06-07 | 国网吉林省电力有限公司电力科学研究院 | A cost control success rate improvement analysis method based on ensemble learning |
| CN110502492A (en) * | 2019-08-14 | 2019-11-26 | 深圳市优课在线教育有限公司 | A kind of real-time anti-cheating detection and method for early warning towards online education |
| US12443387B2 (en) | 2019-08-21 | 2025-10-14 | Micron Technology, Inc. | Intelligent audio control in vehicles |
| CN112406894A (en) * | 2019-08-21 | 2021-02-26 | 美光科技公司 | Smart recording of wrong vehicle behavior |
| US12497055B2 (en) | 2019-08-21 | 2025-12-16 | Micron Technology, Inc. | Monitoring controller area network bus for vehicle control |
| US12210401B2 (en) | 2019-09-05 | 2025-01-28 | Micron Technology, Inc. | Temperature based optimization of data storage operations |
| CN110781605B (en) * | 2019-11-05 | 2023-08-25 | 恩亿科(北京)数据科技有限公司 | Advertisement putting model testing method and device, computer equipment and storage medium |
| CN110781605A (en) * | 2019-11-05 | 2020-02-11 | 恩亿科(北京)数据科技有限公司 | Advertisement putting model testing method and device, computer equipment and storage medium |
| CN110992096A (en) * | 2019-12-03 | 2020-04-10 | 秒针信息技术有限公司 | Prediction model training method and device and media identification prediction method and device |
| CN110992096B (en) * | 2019-12-03 | 2023-08-29 | 秒针信息技术有限公司 | Prediction model training method and device and media identification prediction method and device |
| CN110992104A (en) * | 2019-12-11 | 2020-04-10 | 杭州古点网络科技有限公司 | Abnormal advertisement flow detection method based on user portrait |
| CN112950249A (en) * | 2019-12-16 | 2021-06-11 | 旺脉信息科技(上海)有限公司 | Method and system for processing advertisement flow data, electronic equipment and storage medium |
| US12518570B2 (en) | 2019-12-18 | 2026-01-06 | Lodestar Licensing Group Llc | Predictive maintenance of automotive transmission |
| CN111291720B (en) * | 2020-03-10 | 2020-12-08 | 嘉兴瑞知环保科技有限公司 | Building advertisement recognition system based on cloud computing network |
| CN111291720A (en) * | 2020-03-10 | 2020-06-16 | 孔华 | Building advertisement identification system based on cloud computing network |
| CN111738770A (en) * | 2020-06-28 | 2020-10-02 | 北京达佳互联信息技术有限公司 | Advertisement abnormal flow detection method and device |
| CN111738770B (en) * | 2020-06-28 | 2023-09-26 | 北京达佳互联信息技术有限公司 | Advertisement abnormal flow detection method and device |
| CN111861568A (en) * | 2020-07-23 | 2020-10-30 | 上海志窗信息科技有限公司 | Internet advertisement monitoring system and method thereof |
| CN111882367A (en) * | 2020-08-11 | 2020-11-03 | 北京云和互动信息技术有限公司 | Method for monitoring and tracking online advertisements through user internet behavior analysis |
| CN111882367B (en) * | 2020-08-11 | 2023-11-21 | 北京云和互动信息技术有限公司 | Method for monitoring and tracking online advertisements through analysis of user surfing behavior |
| CN111708678A (en) * | 2020-08-18 | 2020-09-25 | 北京志翔科技股份有限公司 | An abnormality monitoring method and device |
| CN112118259B (en) * | 2020-09-17 | 2022-04-15 | 四川长虹电器股份有限公司 | Unauthorized vulnerability detection method based on classification model of lifting tree |
| CN112118259A (en) * | 2020-09-17 | 2020-12-22 | 四川长虹电器股份有限公司 | Unauthorized vulnerability detection method based on classification model of lifting tree |
| CN112101678A (en) * | 2020-09-23 | 2020-12-18 | 东莞理工学院 | GBDT-based student personality tendency prediction method |
| CN114663121A (en) * | 2020-12-23 | 2022-06-24 | 华扬联众数字技术股份有限公司 | Method and device for abnormal advertising traffic detection |
| CN112651790A (en) * | 2021-01-19 | 2021-04-13 | 恩亿科(北京)数据科技有限公司 | OCPX self-adaptive learning method and system based on user reach in fast-moving industry |
| CN112651790B (en) * | 2021-01-19 | 2024-04-12 | 恩亿科(北京)数据科技有限公司 | OCPX self-adaptive learning method and system based on user touch in quick-elimination industry |
| CN114331519A (en) * | 2021-12-23 | 2022-04-12 | 杭州迈库网络科技有限公司 | Advertisement data tracking system and monitoring terminal thereof |
| CN114238064A (en) * | 2021-12-30 | 2022-03-25 | 深圳依时货拉拉科技有限公司 | Cheating detection method and device, storage medium and computer equipment |
| CN114626876B (en) * | 2022-02-23 | 2025-09-23 | 深圳市创梦天地科技有限公司 | Training method, system and related devices for abnormal traffic detection model |
| CN114626876A (en) * | 2022-02-23 | 2022-06-14 | 深圳市创梦天地科技有限公司 | Training method, system and related device for abnormal flow detection model |
| CN119624543A (en) * | 2024-11-22 | 2025-03-14 | 南京合宜信息技术有限公司 | A method and system for optimizing precise advertising delivery |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106447383A (en) | Cross-time multi-dimensional abnormal data monitoring method and system | |
| CN103136695B (en) | Media deliver Value Engineering Method and its system | |
| JP5596152B2 (en) | Information matching method and system on electronic commerce website | |
| CN103902674B (en) | The acquisition method and device of the comment data of particular topic | |
| JP5072160B2 (en) | System and method for estimating the spread of digital content on the World Wide Web | |
| CN104834641B (en) | The processing method and related system of network media information | |
| CN109902708A (en) | A kind of recommended models training method and relevant apparatus | |
| KR101180439B1 (en) | System for optimizing landing page and method thereof | |
| CN107908606A (en) | Method and system based on different aforementioned sources automatic report generation | |
| CN104035927A (en) | User behavior-based search method and system | |
| CN105447186A (en) | Big data platform based user behavior analysis system | |
| CN102710770A (en) | Identification method for network access equipment and implementation system for identification method | |
| CN108415913A (en) | Crowd's orientation method based on uncertain neighbours | |
| CN104965863B (en) | An object clustering method and device | |
| CN106528777A (en) | Cross-screen user identification normalizing method and system | |
| CN110309737A (en) | A kind of information processing method applied to cigarette sales counter, apparatus and system | |
| CN105447148A (en) | Cookie identifier association method and apparatus | |
| CN108268519A (en) | A kind of method and apparatus of recommendation network object | |
| CN113989499B (en) | Intelligent alarm method in bank scene based on artificial intelligence | |
| CN110335116A (en) | A data commodity recommendation method based on edge computing | |
| CN109544271A (en) | A kind of trade managing system | |
| CN111611469A (en) | Identification information determination method and device, electronic device and storage medium | |
| CN107766904A (en) | One kind retrospect scale merges printing traceability code method and device | |
| CN109543780A (en) | A kind of electronic business card device and electronic business card marketing method | |
| CN106708851A (en) | Information processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |