CN108090787A - A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction - Google Patents
A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction Download PDFInfo
- Publication number
- CN108090787A CN108090787A CN201711368254.9A CN201711368254A CN108090787A CN 108090787 A CN108090787 A CN 108090787A CN 201711368254 A CN201711368254 A CN 201711368254A CN 108090787 A CN108090787 A CN 108090787A
- Authority
- CN
- China
- Prior art keywords
- user
- apriori algorithm
- excavated
- ticket
- prediction
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
Abstract
A kind of method that the present invention discloses call bill data depth excavation based on Apriori algorithm and user's behavior prediction, includes the following steps：Step 1 corresponds to behavioural characteristic according to relevant information in ticket and user, looks for out the incidence relation frequency of the peculiar ticket information of some of which and some subsequent behavioural characteristics of user；Step 2, the frequency intensity occurred according to above-mentioned incidence relation, are ranked up above-mentioned relation.The continuous item compared with High relevancy that has in the top is found out, and then the behavior of different user is excavated according to this rule, is counted；Step 3, the prediction that user's corelation behaviour etc. is provided based on Apriori algorithm.
Description
Technical field
The invention belongs to big data analysis and machine learning method, more particularly to one kind based on if Apriori algorithm
Forms data depth is excavated and the method for user's behavior prediction.
Background technology
Include the dialing numbers of current talking in telecom operators' ticket big data, dial the time, dial duration, access
The information such as base station, often some mobile phone usage behaviors subsequent with user or operation are associated for these information, by these letters
The depth of breath is excavated, and can be realized the relevant prediction of some terminal users, and then be obtained on user behavior feature and demand
The useful information reflected indirectly, these information are instructing the decision-making of the service operation of operator and auxiliary activities provider
Etc. have highly important reference value, it may have huge economic value and social benefit.
Apriori algorithm is widely used in moving communicating field.Mobile value-added service is increasingly becoming Mobile Communications Market
On most vibrant, the most potential, business that attracts most attention.With the recovery of industry, more and more value-added services are shown by force
The growth momentum of strength, the characteristics of showing using diversification, brand marketing, management centralization, cooperation depth.For this
Trend, widely applied Apriori algorithm is applied by many companies in correlation rule data mining.
Apriori algorithm is a kind of frequent item set algorithm of Mining Association Rules, and core concept is given birth to by Candidate Set
Carry out Mining Frequent Itemsets Based into downward closing two stages of detection with plot.Its basic thought is：All frequency collection are found out first,
The frequency that these item collections occur is at least as predefined minimum support.Then collected by frequency and generate Strong association rule, this
A little rules must are fulfilled for minimum support and Minimum support4.Then desired rule is generated using the frequency collection found, generated only
The strictly all rules of item comprising set, the right part of each of which rule only have one, here using the definition of middle rule.
Once these rules are generated, then only those are just left more than the rule for the Minimum support4 that user gives.In order to
All frequency collection are generated, have used recursive method.
If there is a correlation rule, its support and confidence level be both greater than the minimum support that pre-defines with
Confidence level, just it is referred to as Strong association rule for we.Strong association rule can be used for understanding the hiding relation between item.So it closes
The main purpose of connection analysis is exactly in order to find Strong association rule, and Apriori algorithm is then mainly used to help to find strong association
Rule.
Based on above-mentioned principle, set forth herein a kind of call bill data depth excavation based on Apriori algorithm and user behaviors
The method and system of prediction, by the user bill big data information of magnanimity, to the forward and backward use that different information occur in ticket
There is the excavation of the frequent item set of behavior, statistics in family, provides the useful letter reflected indirectly on user behavior feature and demand
Breath, and then Accurate Prediction is made to the corelation behaviour of user.
The content of the invention
Ticket big data information for magnanimity and the frequent item set wherein contained propose a kind of to be based on Apriori algorithm
Call bill data depth excavate and the method for user's behavior prediction, by the user bill big data information of magnanimity, to ticket
The behavioural characteristic frequency for the forward and backward generation that the related implicit information of middle related information items and user information different from ticket occur
The excavation of numerous item collection, statistics provide the Accurate Prediction of user's corelation behaviour etc. based on Apriori algorithm.
A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction, including walking as follows
Suddenly：
Step 1 corresponds to behavioural characteristic according to relevant information in ticket and user, looks for out the peculiar ticket information of some of which
(such as after big flow consumption, user more often dials and supplements with money with the incidence relation frequency of some subsequent behavioural characteristics of user
Phone is supplemented with money；With after the call of some or some particular numbers, user is always and some other particular person or specific number
Code is taken on the telephone；The user for logging in some websites also necessarily logs in other some specific websites in the recent period；It has carried out under some resources
The user of load also can download other resource simultaneously；Some people one appear in certain time point, certain position will be to certain class crowd
Or number call phone etc.)；
Step 2, the frequency intensity occurred according to above-mentioned incidence relation, are ranked up above-mentioned relation.It will be in the top
It is found out with the continuous item compared with High relevancy, and then the behavior of different user is excavated according to this rule, is counted, Jin Erti
Preceding accurate prediction；
Step 3, the prediction that user's corelation behaviour etc. is provided based on Apriori algorithm, first to different in ticket big data
User is handled, is classified, and is carried out just classification based on attribute informations such as gender, age, region, consumption habits, is avoided because of data
Forecasting inaccuracy caused by the inconsistency that diversity generates is true, to eliminate the shadow of the excessively multipair analysis result accuracy of data type
It rings.
Compared with prior art, the present invention has following apparent advantage and advantageous effect：
(1) excavate set forth herein a kind of call bill data depth based on Apriori algorithm and the method for user's behavior prediction,
By in the user bill big data information of magnanimity, to the related implicit information and ticket of related information items in ticket and user
The excavation for the behavioural characteristic frequent item set that user occurs, statistics, user is provided based on Apriori algorithm after middle item of information, ticket
The prediction of corelation behaviour etc..
(2) it is first right before phone bill using Apriori algorithm according to being excavated because the diversity of teledata
Above-mentioned data are classified, selected, eliminate distracter, and then avoid predicting caused by teledata diversity not accurate enough
The problem of.
Description of the drawings
Fig. 1 is that a kind of call bill data depth based on Apriori algorithm proposed by the invention is excavated and user behavior is pre-
The method flow diagram of survey；
Specific embodiment
The present invention will be further described with reference to the accompanying drawings and detailed description.
The flow chart of method involved in the present invention is as shown in Figure 1, comprise the following steps：
Ticket big data information for magnanimity and the frequent item set wherein contained propose a kind of to be based on Apriori algorithm
Call bill data depth excavate and the method for user's behavior prediction, by the user bill big data information of magnanimity, to ticket
In, after ticket user occur the frequent item set of behavior excavation, statistics, provide the prediction of user's corelation behaviour etc..
A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction, passes through magnanimity
In user bill big data information, to the excavation of the frequent item set of behavior, statistics occurs in user in ticket, after ticket, use is provided
The prediction of family corelation behaviour etc..
A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction, including walking as follows
Suddenly：
1st, behavioural characteristic is corresponded to according to relevant information in ticket and user, some of which is looked for out based on Apriori algorithm
Peculiar ticket information and some subsequent behavioural characteristics of user incidence relation frequency (such as after big flow consumption, Yong Hugeng
It often dials and supplements phone with money and supplemented with money；With after some or the call of some particular numbers, user is always and some other is special
Determine people or particular number is taken on the telephone；The user for logging in some websites also necessarily logs in other some specific websites in the recent period；It carries out
The user of some resource downloadings also can download other resource simultaneously；Some people are once appearing in certain time point, certain position
It can be to certain class crowd or number call phone etc.)；
2nd, based on this frequent 1 Item Sets C of generation candidate1={ { after big flow consumption }, { user, which dials, supplements phone progress with money
Supplement with money, { dial some particular person or particular number taken on the telephone }, { logging in some specific websites }, { downloading some resources },
{ appearing in certain time point, certain position }, { to certain class crowd or number call phone } }.
3rd, transaction database is scanned, is defined as D, its each of which item record T, is C1Subset, then association rule
All it is then shaped like A->The expression formula of B, A, B are C1Subset, and the intersection of A and B is sky, and support is defined as probability P
(AUB).Calculate the frequent 1 Item Sets C of candidate1In each support of the Item Sets in D, and then can be obtained according to minimum support
Go out frequent 1 Item Sets L1。
4th, similarly, according to L1Generate the frequent 2 Item Sets C of candidate2。
5th, transaction database D is scanned, calculates the frequent 2 Item Sets C of candidate2In each support of the Item Sets in D, can be with
Draw frequent 2 Item Sets L2。
According to the frequency intensity that above-mentioned incidence relation occurs, above-mentioned relation is ranked up.By it is in the top have compared with
The continuous item of High relevancy is found out, and then the behavior of different user is excavated according to this rule, is counted, and then essence in advance
Really prediction；
6th, similarly, according to L2Generate the frequent 3 Item Sets C of candidate3。
7th, transaction database D is scanned, calculates the frequent 3 Item Sets C of candidate3In each support of the Item Sets in D, can be with
Draw frequent 3 Item Sets L3。
8th, repeat the above steps, until that cannot find " k item collections ".
If L=L1UL2UL3U…ULk-1, further respectively calculate correlation rule confidence level, it can be deduced that frequently association rule
Then, so find different item between incidence relation.
9th, it is to further improve accuracy of the Apriori algorithm to ticket analysis result, improves user's behavior prediction precision,
The present invention first handles different user in ticket big data, is classified, based on categories such as gender, age, region, consumption habits
Property information carry out just classification, avoid because data diversity generate inconsistency caused by forecasting inaccuracy it is true, to eliminate data
The influence of the excessively multipair analysis result accuracy of type.
Claims (1)
1. a kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction, which is characterized in that bag
Include following steps：
Step 1 corresponds to behavioural characteristic according to relevant information in ticket and user, looks for out the peculiar ticket information of some of which with using
The incidence relation frequency of some subsequent behavioural characteristics of family；
Step 2, the frequency intensity occurred according to above-mentioned incidence relation, are ranked up above-mentioned relation.In the top is had
Continuous item compared with High relevancy is found out, and then the behavior of different user is excavated according to this rule, is counted；
Step 3, the prediction that user's corelation behaviour etc. is provided based on Apriori algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711368254.9A CN108090787A (en) | 2017-12-18 | 2017-12-18 | A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711368254.9A CN108090787A (en) | 2017-12-18 | 2017-12-18 | A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108090787A true CN108090787A (en) | 2018-05-29 |
Family
ID=62176017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711368254.9A Pending CN108090787A (en) | 2017-12-18 | 2017-12-18 | A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108090787A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635006A (en) * | 2018-12-17 | 2019-04-16 | 山大地纬软件股份有限公司 | Social security business association rule digging and recommendation apparatus and method based on Apriori |
| CN109784721A (en) * | 2019-01-15 | 2019-05-21 | 东莞市友才网络科技有限公司 | A kind of plateform system of employment data analysis and data mining analysis |
| CN112215646A (en) * | 2020-10-12 | 2021-01-12 | 四川长虹电器股份有限公司 | Brand promotion method based on improved Aprion algorithm |
| CN113935787A (en) * | 2021-12-15 | 2022-01-14 | 山东柏源技术有限公司 | Financial information management system based on association rule mining algorithm |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590232A (en) * | 2014-11-11 | 2016-05-18 | 中国移动通信集团广东有限公司 | Client relation generation method and apparatus, and electronic device |
-
2017
- 2017-12-18 CN CN201711368254.9A patent/CN108090787A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590232A (en) * | 2014-11-11 | 2016-05-18 | 中国移动通信集团广东有限公司 | Client relation generation method and apparatus, and electronic device |
Non-Patent Citations (2)
| Title |
|---|
| S. GANESHMOORTHY: ""An Improved Intellectual Analysis Precedence and Storage for Business Intelligence from Web Uses Access Data"", 《COMPUTATIONAL ADVANCEMENT IN COMMUNICATION CIRCUITS AND SYSTEMS》 * |
| 林湘粤等: ""基于海量数据的用户点击模式识别"", 《电信网技术》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635006A (en) * | 2018-12-17 | 2019-04-16 | 山大地纬软件股份有限公司 | Social security business association rule digging and recommendation apparatus and method based on Apriori |
| CN109784721A (en) * | 2019-01-15 | 2019-05-21 | 东莞市友才网络科技有限公司 | A kind of plateform system of employment data analysis and data mining analysis |
| CN109784721B (en) * | 2019-01-15 | 2021-01-26 | 广东度才子集团有限公司 | Employment data analysis and data mining analysis platform system |
| CN112215646A (en) * | 2020-10-12 | 2021-01-12 | 四川长虹电器股份有限公司 | Brand promotion method based on improved Aprion algorithm |
| CN113935787A (en) * | 2021-12-15 | 2022-01-14 | 山东柏源技术有限公司 | Financial information management system based on association rule mining algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615116B (en) | Telecommunication fraud event detection method and system | |
| CN108090787A (en) | A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction | |
| CN104076944B (en) | A kind of method and apparatus of chatting facial expression input | |
| CN106778876A (en) | User classification method and system based on mobile subscriber track similitude | |
| CN102722709B (en) | Method and device for identifying garbage pictures | |
| CN102110170B (en) | System with information distribution and search functions and information distribution method | |
| CN109902216A (en) | A kind of data collection and analysis method based on social networks | |
| CN102083010B (en) | Method and equipment for screening user information | |
| CN104572688A (en) | Information push method and device | |
| CN105869035A (en) | Mobile user credit evaluation method and apparatus | |
| CN106022708A (en) | Method for predicting employee resignation | |
| CN104463603A (en) | Credit assessment method and system | |
| EP2652909B1 (en) | Method and system for carrying out predictive analysis relating to nodes of a communication network | |
| CN103957516A (en) | Junk short message filtering method and engine | |
| CN109711746A (en) | A kind of credit estimation method and system based on complex network | |
| Guo et al. | GroupMe: Supporting group formation with mobile sensing and social graph mining | |
| CN109118155A (en) | A kind of method and device generating operation model | |
| CN107644106A (en) | The internuncial method of automatic mining business, terminal device and storage medium | |
| CN109389501A (en) | A kind of calculating equipment, computing system | |
| CN110502702A (en) | User's behavior prediction method and device | |
| Manley et al. | New forms of data for understanding urban activity in developing countries | |
| CN108776857A (en) | NPS short messages method of investigation and study, system, computer equipment and storage medium | |
| Maji et al. | Data warehouse based analysis on CDR to retain and acquire customers by targeted marketing | |
| CN113850630A (en) | Satisfaction degree prediction method and device, storage medium and electronic equipment | |
| CN106293354B (en) | Shortcut menu self-adaptive display control method, server and portable terminal |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180529 |