CN106339892A - Real-time monitoring and accurate evaluation method and system based on large data - Google Patents
Real-time monitoring and accurate evaluation method and system based on large data Download PDFInfo
- Publication number
- CN106339892A CN106339892A CN201510406545.7A CN201510406545A CN106339892A CN 106339892 A CN106339892 A CN 106339892A CN 201510406545 A CN201510406545 A CN 201510406545A CN 106339892 A CN106339892 A CN 106339892A
- Authority
- CN
- China
- Prior art keywords
- data
- real
- advertisement
- accurate evaluation
- time monitoring
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a real-time monitoring and accurate evaluation method and system based on large data. The method comprises the steps that the request data of advertisement delivery is acquired; the request data of advertisement delivery is processed; the processed request data are used as intermediate data and stored in a Nosql database; the intermediate data are transferred into a Mysql database from the Nosql database, so that the data are presented on the front page; a decision tree is constructed based on advertisement delivery; and the delivery of each advertisement is monitored to dynamically update the decision tree. According to the invention, target user data can be efficiently optimized, and the real-time monitoring and effect of advertisement delivery are accurately evaluated.
Description
Technical field
The present invention relates to internet, applications technology, more particularly, to a kind of real-time monitoring based on big data and standard
Really appraisal procedure and system.
Background technology
In recent years, the concept of domestic network marketing was very fiery, but existing network marketing efficiency is low, do not have essence
Determine the effective customers in position, lead to substantial amounts of advertising display to give incoherent netizen, therefore, pass through
Effectively brand proposition, product information are delivered to target audience by technological means like clockwork, realize mutually
The precise positioning marketing of networked system, lifting advertisement putting return rate are particularly significant.
Content of the invention
The invention provides a kind of real-time monitoring based on big data and accurate evaluation method, enable to advertisement
The real-time monitoring thrown in and the accurate evaluation of effect, in order to realize this technical scheme, this method includes as follows
Step:
Obtain the request data of advertisement putting;
The request data of advertisement putting is processed;
Using the request data after processing as intermediate data, and it is stored in nosql data base;
By intermediate data from nosql data base's unloading in mysql data base, for carrying out in front end page
Present;
Decision tree is constructed according to the input of advertisement, and monitors the input of advertisement each time with described in dynamic renewal
Decision tree.
In the above-mentioned real-time monitoring based on big data and accurate evaluation method, the data meeting in advertisement putting
Instantaneous transmission, to message queue, obtains the number of request of described advertisement putting from message queue by storm
According to.
In the above-mentioned real-time monitoring based on big data and accurate evaluation method, described nosql data base is
ssdb.
Number of request in the above-mentioned real-time monitoring based on big data and accurate evaluation method, to advertisement putting
Include according to the step being processed:
Every important indicator is differentiated carrying out multi objective monitoring according to the request data after processing, and according to place
Request data after reason carries out various dimensions alternate analyses and monitoring to most important indicators simultaneously.
In the above-mentioned real-time monitoring based on big data and accurate evaluation method, according to the genus of Internet user
Property and advertisement attributes, to build decision tree;
The element of described decision tree includes age, sex, income, interest, adline and clicks on general
Rate.
Simultaneously present invention also offers a kind of real-time monitoring based on big data and accurate evaluation system, comprising:
Acquisition module, for obtaining the request data of advertisement putting;
Processing module, is connected with acquisition module, for processing to the request data of advertisement putting;
Nosql data base, the request data after process is as intermediate data storage in this nosql data base;
Data conversion storage module and mysql data base, described data conversion storage module be used for by described intermediate data from
Nosql data base's unloading in mysql data base, for being presented in front end page;
Decision tree update module, constructs decision tree according to the input of advertisement, and monitors the throwing of advertisement each time
Put and update described decision tree with dynamic.
In the above-mentioned real-time monitoring based on big data and accurate evaluation system, acquisition module obtains advertisement and throws
The step of the request data put is:
In advertisement putting, data meeting instantaneous transmission, to message queue, is obtained from message queue by storm
The request data of described advertisement putting.
In the above-mentioned real-time monitoring based on big data and accurate evaluation system, described nosql data base is
ssdb.
In the above-mentioned real-time monitoring based on big data and accurate evaluation system, described processing module is to advertisement
The step that the request data thrown in is processed includes:
Every important indicator is differentiated carrying out multi objective monitoring according to the request data after processing, and according to place
Request data after reason carries out various dimensions alternate analyses and monitoring to most important indicators simultaneously.
In the above-mentioned real-time monitoring based on big data and accurate evaluation system, described decision tree update module
Attribute according to Internet user and advertisement attributes, to build decision tree;
The element of described decision tree includes age, sex, income, interest, adline and clicks on general
Rate.
The present invention with reference to advertising items the industry, customer type, the practical situation such as put on market, to user
/ media data carries out going deep into comprehensive analysis and assessment monitoring, is divided by various algorithm optimization means such as Bayes
Class, logistic regression, decision tree, principal component analysiss, factorial analyses, cluster, association rule mining etc. are real
Existing recruitment evaluation analysis and prediction, thus effectively optimizing target user data, realize the reality to advertisement putting
When monitoring and effect accurate evaluation.
Brief description
By reading detailed description, the present invention and its spy non-limiting example being made with reference to the following drawings
Levy, profile and advantage will become more apparent upon.Identical labelling instruction identical part in whole accompanying drawings.
Deliberately it is not drawn to scale accompanying drawing, it is preferred that emphasis is the purport of the present invention is shown.
A kind of real-time monitoring based on big data and accurate evaluation method flow diagram that Fig. 1 provides for the present invention;
Fig. 2 is the schematic diagram of decision tree in one embodiment;
A kind of real-time monitoring based on big data and accurate evaluation system schematic that Fig. 3 provides for the present invention.
Specific embodiment
In the following description, give a large amount of concrete details to provide, the present invention more thoroughly to be managed
Solution.It is, however, obvious to a person skilled in the art that the present invention can one or
These details multiple and be carried out.In other examples, in order to avoid obscuring with the present invention,
Some technical characteristics well known in the art are not described.
In order to thoroughly understand the present invention, detailed step and detailed knot will be proposed in following description
Structure, so that explaination technical scheme.Presently preferred embodiments of the present invention is described in detail as follows, but
In addition to these describe in detail, the present invention can also have other embodiment.
Embodiment one
The invention provides a kind of real-time monitoring based on big data and accurate evaluation method, shown in reference Fig. 1,
Comprise the steps:
Step s1: obtain the request data of advertisement putting in real time.
Specifically, in advertisement putting, data understands instantaneous transmission to message queue, by storm from message team
The request data of advertisement putting is obtained in row.
Step s2: the request data of advertisement putting is processed, to meet the real-time multi objective of business datum
Monitoring and the monitoring of real-time various dimensions.
The present invention to each advertisement putting data it is ensured that carrying out a wheel process, to meet the reality of business datum
When multi objective monitoring and real-time various dimensions monitoring.Multi objective monitoring in real time: differentiate important indicator, such as advertisement
Number of request, participate in bid number, successfully bid number, hits etc..For these macro-indicators, all can be
Second level is disposed.Various dimensions monitoring in real time: various dimensions intersection point is carried out simultaneously for most important indicators
Analysis and monitoring.Meet the comprehensive analysis for user interest, advertising plan, adline etc..
Step s3: using the request data after processing as intermediate data, and be stored in nosql data base.
Process billions of data because advertisement putting is daily it is desirable to high is concurrent.Intermediate data storage is filled
Divide and make use of nosql technology, and ssdb is used as intermediate storage layer, ssdb is one and quickly uses
To store the nosql data base that increases income of 1,000,000,000 levels list data, fabulous meets the need to high concurrent
Ask.
Step s4: by intermediate data from nosql data base's unloading in mysql data base, for front end page
Present, realize the visualization of monitoring.
Step s5: the input of monitoring advertisement each time, dynamically update decision tree.It is each that the present invention passes through monitoring
Secondary advertisement putting, dynamically updates decision tree.So that more preferable support to throw in;Genus according to Internet user
Property and advertisement attributes, construct a decision tree.
In an optional embodiment, the element of decision tree include the age, sex, income, interest,
Adline and click probability, can refer to shown in Fig. 2, and in this example, decision tree is directed to clicking rate,
Ad revenue, advertising cost additionally can be designed.This decision tree can be used for improving the wide of real time bid system
Accuse selection strategy.
Advertisement delivery effect accurate evaluation is completed with the offline two parts of hadoop calculating platform jointly by real-time,
And assess and include real-time assessment and offline evaluation.Real-time partial can monitor in real time advertisement exposure at this stage
Amount, click volume, advertisement exposure amount can be analyzed from the time with spatially, expose user group, click
User group etc., provides constructive suggestion with this;In offline evaluation, the present invention can be by hadoop
Calculating platform-ycloud (a kind of cloud computing platform), cluster understands processed offline mass data daily, to every
Individual advertisement putting plan is estimated, and generates multi-dimensional report, provides more fine-grained analysis, be beneficial to
The omnibearing input effect assessing this advertising plan.Form is from user interest, user's sex, age
The light exposure of the Global statistical analysis such as layer, terminal, area this time advertisement putting, clicking rate, income cost
Etc. index, for corporate boss's reference.
The present invention with reference to advertising items the industry, customer type, the practical situation such as put on market, to user
/ media data carries out going deep into comprehensive analysis and assessment monitoring, is divided by various algorithm optimization means such as Bayes
Class, logistic regression, decision tree, principal component analysiss, factorial analyses, cluster, association rule mining etc. are real
Existing recruitment evaluation analysis and prediction, thus effectively optimizing target user data, realize the reality to advertisement putting
When monitoring and effect accurate evaluation.
Embodiment two
In the present embodiment, the invention provides a kind of real-time monitoring based on big data and accurate evaluation system
System, with reference to shown in Fig. 3, comprising: acquisition module 1, processing module 2, nosql data base 3, data turn
Storing module 4, mysql data base 5 and decision tree update module 6.Specifically, the function of its each several part is such as
Under:
Acquisition module 1 is used for obtaining the request data of advertisement putting.Acquisition module obtains the request of advertisement putting
The step of data is: in advertisement putting data can instantaneous transmission to message queue, by storm from disappearing
The request data of advertisement putting is obtained in breath queue.
Processing module 2, is connected with acquisition module, for processing to the request data of advertisement putting, with
Meet real-time multi objective monitoring and the monitoring of real-time various dimensions of business datum.The system that the present invention provides can be right
Each advertisement putting data, it is ensured that carrying out a wheel process, is supervised with the real-time multi objective meeting business datum
Control and the monitoring of real-time various dimensions.Multi objective monitoring in real time: differentiate important indicator, such as ad-request number, ginseng
With number, successfully bid number, the hits etc. of bidding.For these macro-indicators, all can process in second level
Finish.Various dimensions monitoring in real time: various dimensions alternate analyses and monitoring are carried out simultaneously for most important indicators.
Meet the comprehensive analysis for user interest, advertising plan, adline etc..
Nosql data base 3, for storing intermediate data, wherein, the request data after process is as mediant
According to be stored in this nosql data base.
Data conversion storage module 4 and mysql data base 5, data conversion storage module 4 be used for by intermediate data from
Nosql data base 3 unloading, in mysql data base 5, so that front end page presents, realizes the visual of monitoring
Change;
Decision tree update module 6, the input of monitoring advertisement each time, and dynamically update decision tree.
In the present invention one optional embodiment, nosql data base 3 is ssdb.Because advertisement putting is daily
Process billions of data it is desirable to high is concurrent.Intermediate data storage takes full advantage of nosql technology,
And it is used ssdb as intermediate storage layer, fabulous meets the demand to high concurrent.
In the present invention one optional embodiment, decision tree update module is according to the attribute of Internet user and wide
Accuse attribute, to build decision tree.Further, the element of decision tree includes age, sex, receipts
Enter, interest, adline and click on probability, can refer to shown in Fig. 2.
The real-time stream calculation Computational frame storm that the system that the present invention provides employs current industry forefront comes
Receive and process each advertisement putting request and realize real-time monitoring purpose, can be to each advertisement putting plan
Be estimated, generate multi-dimensional report, more fine-grained analysis is provided, be beneficial to omnibearing assessment this
The input effect of secondary advertising plan.Form is from user interest, user's sex, age level, terminal, area
Deng indexs such as the light exposure of Global statistical analysis this time advertisement putting, clicking rate, income costs, for enterprise
Main reference, and then provide foundation for significantly more efficient input advertisement.
Above presently preferred embodiments of the present invention is described.It is to be appreciated that the present invention does not limit to
In above-mentioned particular implementation, wherein the equipment describing in detail and structure are not construed as using this area to the greatest extent
In common mode be practiced;Any those of ordinary skill in the art, without departing from the technology of the present invention
In the case of aspects, all can be utilized the methods and techniques content of the disclosure above that technical solution of the present invention is done
Go out many possible variations and modification, or be revised as the Equivalent embodiments of equivalent variations, this has no effect on this
The flesh and blood of invention.Therefore, every content without departing from technical solution of the present invention, according to the present invention's
Technical spirit, to any simple modification made for any of the above embodiments, equivalent variations and modification, all still falls within this
In the range of inventive technique scheme protection.
Claims (10)
1. a kind of real-time monitoring based on big data and accurate evaluation method are it is characterised in that include as follows
Step:
Obtain the request data of advertisement putting;
The request data of advertisement putting is processed;
Using the request data after processing as intermediate data, and it is stored in nosql data base;
By intermediate data from nosql data base's unloading in mysql data base, for carrying out in front end page
Present;
Decision tree is constructed according to the input of advertisement, and monitors the input of advertisement each time with described in dynamic renewal
Decision tree.
2. the real-time monitoring based on big data as claimed in claim 1 and accurate evaluation method, its feature
It is, in advertisement putting, data understands instantaneous transmission to message queue, by storm from message queue
Obtain the request data of described advertisement putting.
3. the real-time monitoring based on big data as claimed in claim 1 and accurate evaluation method, its feature
It is, described nosql data base is ssdb.
4. the real-time monitoring based on big data as claimed in claim 1 and accurate evaluation method, its feature
It is, the step that the request data of advertisement putting is processed includes:
Every important indicator is differentiated carrying out multi objective monitoring according to the request data after processing, and according to place
Request data after reason carries out various dimensions alternate analyses and monitoring to most important indicators simultaneously.
5. the real-time monitoring based on big data as claimed in claim 1 and accurate evaluation method, its feature
It is, the attribute according to Internet user and advertisement attributes, to build decision tree;
The element of described decision tree includes age, sex, income, interest, adline and clicks on general
Rate.
6. a kind of real-time monitoring based on big data and accurate evaluation system are it is characterised in that include:
Acquisition module, for obtaining the request data of advertisement putting;
Processing module, is connected with acquisition module, for processing to the request data of advertisement putting;
Nosql data base, the request data after process is as intermediate data storage in this nosql data base;
Data conversion storage module and mysql data base, described data conversion storage module be used for by described intermediate data from
Nosql data base's unloading in mysql data base, for being presented in front end page;
Decision tree update module, constructs decision tree according to the input of advertisement, and monitors the throwing of advertisement each time
Put and update described decision tree with dynamic.
7. the real-time monitoring based on big data as claimed in claim 6 and accurate evaluation system, its feature
It is, the step that acquisition module obtains the request data of advertisement putting is:
In advertisement putting, data meeting instantaneous transmission, to message queue, is obtained from message queue by storm
The request data of described advertisement putting.
8. the real-time monitoring based on big data as claimed in claim 6 and accurate evaluation system, its feature
It is, described nosql data base is ssdb.
9. the real-time monitoring based on big data as claimed in claim 6 and accurate evaluation system, its feature
It is, the step that described processing module is processed to the request data of advertisement putting includes:
Every important indicator is differentiated carrying out multi objective monitoring according to the request data after processing, and according to place
Request data after reason carries out various dimensions alternate analyses and monitoring to most important indicators simultaneously.
10. the real-time monitoring based on big data as claimed in claim 6 and accurate evaluation system, its feature
Be, described decision tree update module according to the attribute of Internet user and advertisement attributes, to build decision-making
Tree;
The element of described decision tree includes age, sex, income, interest, adline and clicks on general
Rate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510406545.7A CN106339892A (en) | 2015-07-13 | 2015-07-13 | Real-time monitoring and accurate evaluation method and system based on large data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510406545.7A CN106339892A (en) | 2015-07-13 | 2015-07-13 | Real-time monitoring and accurate evaluation method and system based on large data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106339892A true CN106339892A (en) | 2017-01-18 |
Family
ID=57826988
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510406545.7A Pending CN106339892A (en) | 2015-07-13 | 2015-07-13 | Real-time monitoring and accurate evaluation method and system based on large data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106339892A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107273554A (en) * | 2017-08-04 | 2017-10-20 | 郑州轻工业学院 | Elevator intelligent monitoring system and method |
CN108898432A (en) * | 2018-06-25 | 2018-11-27 | 武汉斗鱼网络科技有限公司 | Advertisement putting effect evaluation method and device and electronic equipment |
CN110489612A (en) * | 2019-08-26 | 2019-11-22 | 秒针信息技术有限公司 | A kind of the multi objective monitoring method and device of information |
CN111861573A (en) * | 2020-07-24 | 2020-10-30 | 网易传媒科技(北京)有限公司 | Information delivery processing method and device, storage medium and electronic equipment |
CN113361891A (en) * | 2021-05-31 | 2021-09-07 | 北京达佳互联信息技术有限公司 | Data acquisition method and device |
-
2015
- 2015-07-13 CN CN201510406545.7A patent/CN106339892A/en active Pending
Non-Patent Citations (3)
Title |
---|
成妍虹: "决策树在户外广告投放平台上的应用", 《自动化与仪器仪表》 * |
李春豹: "企业IT闲散资源整合系统设计与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
马豫青等: "NoSQL数据库技术在移动互联网中的应用", 《平顶山学院学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107273554A (en) * | 2017-08-04 | 2017-10-20 | 郑州轻工业学院 | Elevator intelligent monitoring system and method |
CN108898432A (en) * | 2018-06-25 | 2018-11-27 | 武汉斗鱼网络科技有限公司 | Advertisement putting effect evaluation method and device and electronic equipment |
CN108898432B (en) * | 2018-06-25 | 2022-05-13 | 武汉斗鱼网络科技有限公司 | Advertisement putting effect evaluation method and device and electronic equipment |
CN110489612A (en) * | 2019-08-26 | 2019-11-22 | 秒针信息技术有限公司 | A kind of the multi objective monitoring method and device of information |
CN111861573A (en) * | 2020-07-24 | 2020-10-30 | 网易传媒科技(北京)有限公司 | Information delivery processing method and device, storage medium and electronic equipment |
CN113361891A (en) * | 2021-05-31 | 2021-09-07 | 北京达佳互联信息技术有限公司 | Data acquisition method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Miralles-Pechuán et al. | A novel methodology for optimizing display advertising campaigns using genetic algorithms | |
CN108133418A (en) | Real-time credit risk management system | |
CN106339892A (en) | Real-time monitoring and accurate evaluation method and system based on large data | |
CN112734559B (en) | Enterprise credit risk evaluation method and device and electronic equipment | |
US8600858B1 (en) | Determining financial sentiment based on contests | |
Hansen et al. | An econometric test of water market structure in the western United States | |
CN110517150B (en) | Method and device for generating financial market product transaction report | |
US20190347675A1 (en) | System and method for user cohort value prediction | |
CN109213936B (en) | Commodity searching method and device | |
CN106570718A (en) | Information releasing method and releasing system | |
CN103927615A (en) | Associating An Entity With A Category | |
WO2020150611A1 (en) | Systems and methods for entity performance and risk scoring | |
US20130103617A1 (en) | Computer-Implemented Systems And Methods For Forecasting And Estimation Using Grid Regression | |
JP2012088994A (en) | Advertising effect analysis system and method of the same | |
CN112053097A (en) | Loan collection method and device, electronic equipment and storage medium | |
US10181130B2 (en) | Real-time updates to digital marketing forecast models | |
CN115983900A (en) | Method, apparatus, device, medium, and program product for constructing user marketing strategy | |
US20170345096A1 (en) | Method and system for providing a dashboard for determining resource allocation for marketing | |
US11257108B2 (en) | Systems and methods for dynamic product offerings | |
CN115049429A (en) | Gain prediction method and device and computer equipment | |
CN113379464A (en) | Block chain-based site selection method, device, equipment and storage medium | |
CN114841566A (en) | Operation management method, device and computer storage medium | |
Wodecki | The reserve price optimization for publishers on real-time bidding on-line marketplaces with time-series forecasting | |
CN112200389A (en) | Data prediction method, device, equipment and storage medium | |
US20150254682A1 (en) | Harmonized system number analysis |
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 |
Application publication date: 20170118 |
|
RJ01 | Rejection of invention patent application after publication |