CN109034871A - Big data precision marketing model building method - Google Patents
Big data precision marketing model building method Download PDFInfo
- Publication number
- CN109034871A CN109034871A CN201810694269.2A CN201810694269A CN109034871A CN 109034871 A CN109034871 A CN 109034871A CN 201810694269 A CN201810694269 A CN 201810694269A CN 109034871 A CN109034871 A CN 109034871A
- Authority
- CN
- China
- Prior art keywords
- data
- precision marketing
- big data
- building method
- model building
- 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; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Abstract
The invention discloses a kind of big data precision marketing model building methods, rely on major telecom operators and collect user's Internet data of coming, are based on big data model, screen to data.By the above-mentioned means, big data precision marketing model building method provided by the invention, the building of the telecommunication user internet behavior portrait towards precision marketing, can label according to user's internet behavior for user, and carry out precision marketing, it is supplied to businessman's use.
Description
Technical field
The present invention relates to big data analysis and the field of data mining, in particular to are precisely sought based on telecom operators' big data
Sell the construction method of model.
Background technique
It is existing by the novel circulation way frequency of various APP as the popularity rate that internet and mobile Internet are applied is promoted,
E-commerce development reaches its maturity, and the propagation and sale of brand master can realize that marketing is brand again in mobile Internet simultaneously
Main propagation provides content and public praise, and the status that digital marketing is propagated in the main marketing communication of brand is persistently promoted.
Traditional marketing communication mode, including television advertising is launched, newspaper advertisement is launched etc., but such precision for obtaining visitor
It is too low.
Summary of the invention
The invention mainly solves the technical problem of providing a kind of big data precision marketing model building methods, towards accurate
The building of the telecommunication user internet behavior portrait of marketing, can label according to user's internet behavior for user, and carry out accurate
Marketing is supplied to businessman's use.
In order to solve the above technical problems, one technical scheme adopted by the invention is that: it provides a kind of big data and precisely seeks
Model building method is sold, comprising the following specific steps
Step 1, data prediction is carried out to the internet behavior data of user, obtaining format, clearly user and use 4g online are visited
The result data asked;
Step 2, the url of every profession and trade related web site is collected, and is made as industry library;
Step 3, read step 1 generate result data, and by each result data url and industry library in url into
Row matching, if identical, for this internet records, label, has obtained user related information;
Step 4, calling model handles obtained user related information, obtains the satisfactory cell-phone number of various industries
Clue;
Step 5, cell-phone number clue obtained above is supplied to the client of every profession and trade, carries out precision marketing use;
Step 6, client is analyzed using the summarized results data that cell-phone number clue carries out precision marketing, and by result data
Import model in and Optimized model.
In a preferred embodiment of the present invention, the internet behavior data in the step 1 be related in have: hand
Machine number, imei, access time, access url, UserAgent and Cookie.
In a preferred embodiment of the present invention, data are carried out using Hadoop MapReduce in the step 1
Pretreatment, comprising: deletion error data, completion missing data and format data.
In a preferred embodiment of the present invention, the industry library in the step 2 is made of 3 column, including number, domain name
With industry name.
In a preferred embodiment of the present invention, the knot generated in the step 3 using MapReduce read step 1
Fruit data.
In a preferred embodiment of the present invention, the user related information in the step 3 include user mobile phone number,
Url and affiliated industry.
The beneficial effects of the present invention are: big data precision marketing model building method of the invention, towards precision marketing
The building of telecommunication user internet behavior portrait, can label according to user's internet behavior for user, and carry out precision marketing,
It is supplied to businessman's use.
Specific embodiment
The technical scheme in the embodiments of the invention will be clearly and completely described below, it is clear that described implementation
Example is only a part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's all other embodiment obtained without making creative work belongs to the model that the present invention protects
It encloses.
The embodiment of the present invention includes:
A kind of big data precision marketing model building method, comprising the following specific steps
Step 1, data prediction is carried out to the internet behavior data of user, obtaining format, clearly user and use 4g online are visited
The result data asked;
Step 2, the url of every profession and trade related web site is collected, and is made as industry library;
Step 3, read step 1 generate result data, and by each result data url and industry library in url into
Row matching, if identical, for this internet records, label, has obtained user related information;
Step 4, calling model handles obtained user related information, obtains the satisfactory cell-phone number of various industries
Clue;
Step 5, cell-phone number clue obtained above is supplied to the client of every profession and trade, carries out precision marketing use;
Step 6, client is analyzed using the summarized results data that cell-phone number clue carries out precision marketing, and by result data
Import model in and Optimized model.
Among the above, the user related information in the step 3 includes user mobile phone number, url and affiliated industry etc..
Detailed implementation is as follows:
Step 1, telecom operators possess a large number of users internet behavior data, and these data are typically stored at hadoop HDFS
Distributed storage in, using Hadoop MapReduce, data are pre-processed, comprising: deletion error data, completion lack
Lose data, format data etc., the structural data of final output format cleaning, Internet data can be related in have: hand
Machine number, imei, access time, url, UserAgent, Cookie of access etc..
Step 2, analysis needs the client of clue, and the demand of affiliated industry and client often access to search the industry
Url or app, arranges url and app, and the domain name addresses taken is put into address base.Wherein, address base is mainly by 3 column structures
At number, domain name, industry name.
Step 3, it is read out using the result data that MapReduce generates step 1, the number in the province according to needed for client
According to, load data, and handle every data line.By in this internet log url and step 2 in url in the library url carry out pair
Than recording the label of upper the industry for this if this url occurs in current library.
Step 4, it using the result data in Spark load step 3, counts each cell-phone number in certain time and accesses each row
The number of industry.It is greater than 2 times according to the every profession and trade access thresholds of setting, such as access times, less than 200 times, then it is assumed that normal
Access behavior, this cell-phone number just meet current industry.
Step 5, the data in step 4 are exported, are supplied to precision marketing client, dial use, and mark and whether connect,
The information such as whether have intention.
Step 6, by step 5 generate as a result, feed back in cluster again, generated in data procedures with modification, Ge Gehuan
The parameter in border, such as: access times, access url, access time.
Big data precision marketing model building method of the invention, has the advantages that compared with the prior art
A: the cheap user's internet behavior data of telecom operators are cashed;
B: precision marketing is carried out for trade company, is given a clue;
C: allowing entire data flow, forms closed loop, improves precision.
In conclusion big data precision marketing model building method of the invention, on the telecommunication user towards precision marketing
The building of net behavior portrait, can label, and carry out precision marketing for user according to user's internet behavior, be supplied to businessman
It uses.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright description is applied directly or indirectly in other relevant technology necks
Domain is included within the scope of the present invention.
Claims (6)
1. a kind of big data precision marketing model building method, which is characterized in that comprising the following specific steps
Step 1, data prediction is carried out to the internet behavior data of user, obtaining format, clearly user and use 4g online are visited
The result data asked;
Step 2, the url of every profession and trade related web site is collected, and is made as industry library;
Step 3, read step 1 generate result data, and by each result data url and industry library in url into
Row matching, if identical, for this internet records, label, has obtained user related information;
Step 4, calling model handles obtained user related information, obtains the satisfactory cell-phone number of various industries
Clue;
Step 5, cell-phone number clue obtained above is supplied to the client of every profession and trade, carries out precision marketing use;
Step 6, client is analyzed using the summarized results data that cell-phone number clue carries out precision marketing, and by result data
Import model in and Optimized model.
2. big data precision marketing model building method according to claim 1, which is characterized in that in the step 1
Internet behavior data be related in have: cell-phone number, imei, access time, access url, UserAgent and
Cookie。
3. big data precision marketing model building method according to claim 1, which is characterized in that in the step 1
Data are pre-processed using Hadoop MapReduce, comprising: deletion error data, completion missing data and formatting number
According to.
4. big data precision marketing model building method according to claim 1, which is characterized in that in the step 2
Industry library be made of 3 column, including number, domain name and industry name.
5. big data precision marketing model building method according to claim 1, which is characterized in that in the step 3
The result data generated using MapReduce read step 1.
6. big data precision marketing model building method according to claim 1, which is characterized in that in the step 3
User related information include user mobile phone number, url and affiliated industry.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810694269.2A CN109034871A (en) | 2018-06-29 | 2018-06-29 | Big data precision marketing model building method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810694269.2A CN109034871A (en) | 2018-06-29 | 2018-06-29 | Big data precision marketing model building method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109034871A true CN109034871A (en) | 2018-12-18 |
Family
ID=65521920
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810694269.2A Pending CN109034871A (en) | 2018-06-29 | 2018-06-29 | Big data precision marketing model building method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109034871A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103778555A (en) * | 2014-01-21 | 2014-05-07 | 北京集奥聚合科技有限公司 | User attribute mining method and system based on user tags |
CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
CN107451861A (en) * | 2017-07-27 | 2017-12-08 | 中兴软创科技股份有限公司 | A kind of method of user's online feature recognition under big data |
-
2018
- 2018-06-29 CN CN201810694269.2A patent/CN109034871A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103778555A (en) * | 2014-01-21 | 2014-05-07 | 北京集奥聚合科技有限公司 | User attribute mining method and system based on user tags |
CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
CN107451861A (en) * | 2017-07-27 | 2017-12-08 | 中兴软创科技股份有限公司 | A kind of method of user's online feature recognition under big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5443513B2 (en) | Method and system for handling cookies across domains | |
CN106339469A (en) | Method and device for recommending data | |
CN103945430B (en) | A kind of mobile terminal style recommends method and device | |
CN103207873A (en) | Method and system for displaying exclusive user page | |
CN108647068A (en) | Start the method and system and medium product that page realizes that application is recommended in APP | |
CN104754611A (en) | User perception evaluation method and system | |
CN109726098A (en) | Interface test method, device and computer readable storage medium | |
CN102799636A (en) | Method and system for displaying webpage by mobile terminal | |
CN107786621A (en) | A kind of user information management method, access processing method and device and system | |
KR101035327B1 (en) | Method and System for Providing Auto Evolution Type Webpage Using Log Analysis | |
CN109144652A (en) | A kind of view display methods, device, electronic equipment and storage medium | |
CN104270654A (en) | Internet video playing and monitoring method and device | |
CN104301148A (en) | User behavior recording method based on website access | |
CN109388673A (en) | Can multiple person cooperational creation network creation and reading system | |
CN203206260U (en) | System and method for flow analysis | |
CN109086158A (en) | A kind of Analysis on Abnormal method, apparatus and server | |
CN106445439A (en) | Method for online exhibiting pictures | |
CN105989167B (en) | Collecting method and device based on news client | |
CN103605549A (en) | Interface exit display method and device | |
CN107609041A (en) | List page generation method and device | |
CN106886245A (en) | A kind of accurate countdown realization method and system | |
CN102957747A (en) | Method and system for identifying user source and communicating instant messaging tool | |
CN104572794A (en) | Method and system for showing network information in a user-friendly manner | |
CN104731833A (en) | Web layout method and device | |
CN103970773B (en) | A kind of method for updating pages and device of webpage |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
RJ01 | Rejection of invention patent application after publication |