Online member management method and system based on big data analysis and computer storage medium
1. An online member management method based on big data analysis is characterized in that: the method comprises the following steps:
s1, acquiring account detailed information: acquiring the detailed information of each online member account in the platform through a detailed information acquisition module, and counting the detailed information of each online member account in the platform;
s2, account member level extraction: extracting the member grade in the detailed information of each online member account in the platform through a member grade extraction module respectively to obtain the member grade in the detailed information of each online member account in the platform;
s3, member expiration and renewal time statistics: extracting the expiration time and the renewal time of each member in the detailed information of each online member account in the platform through a time extraction module to obtain the expiration time and the renewal time of each member in each online member account in the platform;
s4, analyzing the member renewal time interval: calculating each time of member renewal time interval in each online member account in the platform through a time interval analysis module, and counting each time of member renewal time interval in each online member account in the platform;
s5, account recharging amount statistics: counting the recharging amount of each time in each online member account in the platform through a recharging amount counting module, and counting the recharging amount of each time in each online member account in the platform;
s6, analyzing the difference value of the additional recharging amount: extracting standard recharging amount corresponding to each online member grade in a platform stored in a storage database through a recharging amount analysis module, and calculating an accumulated additional recharging amount difference value in each online member account in the platform;
s7, obtaining the account use duration: respectively acquiring the use time of each user in each online member account in the platform through a use time acquisition module, extracting the member registration time of each online member account in the platform, and calculating the use time ratio of the users in each online member account in the platform;
s8, analyzing the user loyalty estimation coefficient: and extracting the loyalty influence proportional coefficient corresponding to each online member grade in the platform stored in the storage database through the analysis server, calculating the comprehensive loyalty estimation coefficient of the users in each online member account in the platform, arranging the comprehensive loyalty estimation coefficients of the users in each online member account in the platform in sequence from large to small, and displaying the comprehensive loyalty estimation coefficients in sequence.
2. The online member management method based on big data analysis as claimed in claim 1, wherein: the step S2 includes counting the member levels of the online member accounts in the platform, and forming a member level set of the online member accounts in the platformHeAX (a)1x,a2x,...,aix,...,anx)，aix represents the member rating of the ith online member account in the platform.
3. The online member management method based on big data analysis as claimed in claim 1, wherein: the step S3 includes counting the member expiration time of each time in each online member account in the platform, and forming a member expiration time set A of each time in each online member account in the platformit(ait1,ait2,...,aitj,...,aitm)，aitjExpressed as the jth member expiration time in the ith online member account in the platform; meanwhile, the member renewal time of each time in each online member account in the platform is counted to form a member renewal time set A of each time in each online member account in the platformit′(ait′1,ait′2,...,ait′j,...,ait′m)，ait′jRepresented as the jth member renewal time in the ith online member account in the platform.
4. The online member management method based on big data analysis as claimed in claim 1, wherein: the calculation formula of each member renewal time interval in each online member account in the platform is delta a'it′j＝ait′j-aitj，Δa′it′jExpressed as the jth member renewal time interval, a, in the ith online member account in the platformit′jExpressed as the jth member renewal time in the ith online member account in the platform, aitjRepresented as the jth member expiration time in the ith online member account in the platform.
5. The online member management method based on big data analysis as claimed in claim 1, wherein: the step S5 includes steps of forming each of the platformsEach recharging amount set A in online member accountir(Air1,Air2,...,Airf,...,Airs)，AirfThe charging amount is expressed as the f-th charging amount in the ith online member account in the platform, and s is more than or equal to m.
6. The online member management method based on big data analysis as claimed in claim 1, wherein: the calculation formula of the difference value of the accumulated additional recharging amount in each online member account in the platform isΔAiR is expressed as the difference value of the accumulated additional recharging amount in the ith online member account in the platform, AirfExpressed as the f-th recharging amount in the ith online member account in the platform,expressed as the standard recharge amount corresponding to the member level of the ith online member account in the platform.
7. The online member management method based on big data analysis as claimed in claim 1, wherein: the calculation formula of the user usage time ratio in each online member account in the platform isAik is the ratio of the user's use time in the ith online member account in the platform, aiTvExpressed as the length of time of using the v-th user in the ith online member account in the platform, TNow thatRepresents the current time, aiTNote thatRepresented as the member registration time for the ith online member account in the platform.
8. The online member management method based on big data analysis as claimed in claim 1, wherein:the calculation formula of the comprehensive loyalty prediction coefficient of the users in each online member account in the platform isξiExpressed as the loyalty prediction coefficient of the user in the ith online member account in the platform,expressed as the loyalty influence scaling factor, Δ A, corresponding to the membership grade of the ith online membership account in the platformiR is expressed as the difference value of the accumulated additional recharging amount in the ith online member account in the platform,expressed as standard recharging amount corresponding to the member level of the ith online member account in the platform, e is expressed as a natural number and is equal to 2.718, eta and alpha are respectively expressed as compensation coefficients of the influence of the account use duration and the member renewal time interval on the loyalty, Aik is expressed as the user usage time ratio of the ith online member account in the platform, delta a'it′jRepresented as the jth member renewal time interval in the ith online member account in the platform.
9. An online member management system based on big data analysis is characterized in that: the detailed information acquisition module is respectively connected with the member grade extraction module and the time extraction module, the member grade extraction module is respectively connected with the recharge amount analysis module and the analysis server, the time extraction module is connected with the time interval analysis module, the recharge amount analysis module is respectively connected with the recharge amount statistic module, the storage database and the analysis server, and the analysis server is respectively connected with the time interval analysis module, the service life acquisition module and the storage database.
10. A computer storage medium, characterized in that: the computer storage medium is burned with a computer program, and when the computer program runs in a memory of a server, the method for managing the online members based on big data analysis according to any one of claims 1 to 8 is implemented.
Background
Currently, many mobile internet platforms have a membership system, which is to maintain a faithful user group and increase user viscosity through various preferences and permissions for members. With the increasing number of member accounts in the platform, managing the online member accounts is one of the important basic functions of the current mobile internet platform.
At present, the existing online member account management of the platform has some defects:
1. the existing platform online member management method only classifies online member account numbers according to consumption conditions, cannot perform comprehensive analysis in multiple aspects by utilizing online member account information, and cannot accurately screen platform loyalty member accounts, so that the viscosity of online member users in a platform is reduced, the online member accounts of the platform cannot be managed, and further the daily management requirements of the online member users of the platform cannot be met;
2. the existing online member management method of the platform mostly adopts manual management, lacks a systematic management analysis mode, and can not accurately analyze the loyalty of online member users of the platform, so that the strengthened management of the online member groups of the platform is neglected, the user loss of the online member groups of the platform is caused, and the online member account management level of the platform is further influenced;
in order to solve the above problems, an online member management method, system and computer storage medium based on big data analysis are designed.
Disclosure of Invention
The invention aims to provide an online member management method, a system and a computer storage medium based on big data analysis.
The purpose of the invention can be realized by the following technical scheme:
in a first aspect, the present invention provides an online member management method based on big data analysis, including the following steps:
s1, acquiring account detailed information: acquiring the detailed information of each online member account in the platform through a detailed information acquisition module, and counting the detailed information of each online member account in the platform;
s2, account member level extraction: extracting the member grade in the detailed information of each online member account in the platform through a member grade extraction module respectively to obtain the member grade in the detailed information of each online member account in the platform;
s3, member expiration and renewal time statistics: extracting the expiration time and the renewal time of each member in the detailed information of each online member account in the platform through a time extraction module to obtain the expiration time and the renewal time of each member in each online member account in the platform;
s4, analyzing the member renewal time interval: calculating each time of member renewal time interval in each online member account in the platform through a time interval analysis module, and counting each time of member renewal time interval in each online member account in the platform;
s5, account recharging amount statistics: counting the recharging amount of each time in each online member account in the platform through a recharging amount counting module, and counting the recharging amount of each time in each online member account in the platform;
s6, analyzing the difference value of the additional recharging amount: extracting standard recharging amount corresponding to each online member grade in a platform stored in a storage database through a recharging amount analysis module, and calculating an accumulated additional recharging amount difference value in each online member account in the platform;
s7, obtaining the account use duration: respectively acquiring the use time of each user in each online member account in the platform through a use time acquisition module, extracting the member registration time of each online member account in the platform, and calculating the use time ratio of the users in each online member account in the platform;
s8, analyzing the user loyalty estimation coefficient: and extracting the loyalty influence proportional coefficient corresponding to each online member grade in the platform stored in the storage database through the analysis server, calculating the comprehensive loyalty estimation coefficient of the users in each online member account in the platform, arranging the comprehensive loyalty estimation coefficients of the users in each online member account in the platform in sequence from large to small, and displaying the comprehensive loyalty estimation coefficients in sequence.
In a possible design of the first aspect, the step S2 includes counting member levels of each online member account in the platform, and forming a member level set AX (a) of each online member account in the platform1x,a2x,...,aix,...,anx)，aix represents the member rating of the ith online member account in the platform.
In a possible design of the first aspect, the step S3 includes counting the expiration times of each member in each online member account in the platform, and forming a set a of expiration times of each member in each online member account in the platformit(ait1,ait2,...,aitj,...,aitm)，aitjExpressed as the jth member expiration time in the ith online member account in the platform; meanwhile, the member renewal time of each time in each online member account in the platform is counted to form a member renewal time set A of each time in each online member account in the platformit′(ait′1,ait′2,...,ait′j,...,ait′m)，ait′jRepresented as the jth member renewal time in the ith online member account in the platform.
In a possible design of the first aspect, the formula of each member renewal time interval calculation in each online member account in the platform is Δ a'it′j＝ait′j-aitj，Δa′it′jExpressed as the ith online member account in the platformThe j-th member renewal time interval in the house, ait′jExpressed as the jth member renewal time in the ith online member account in the platform, aitjRepresented as the jth member expiration time in the ith online member account in the platform.
In a possible design of the first aspect, the step S5 includes forming each recharging amount set a in each online member account in the platformir(Air1,Air2,...,Airf,...,Airs)，AirfThe charging amount is expressed as the f-th charging amount in the ith online member account in the platform, and s is more than or equal to m.
In a possible design of the first aspect, the accumulated additional recharge amount difference value in each online member account in the platform is calculated byΔAiR is expressed as the difference value of the accumulated additional recharging amount in the ith online member account in the platform, AirfIs expressed as the f recharging amount, R 'in the ith online member account in the platform'aixExpressed as the standard recharge amount corresponding to the member level of the ith online member account in the platform.
In a possible design of the first aspect, the calculation formula of the usage duration ratio of the users in the online member accounts in the platform isAik is the ratio of the user's use time in the ith online member account in the platform, aiTvExpressed as the length of time of using the v-th user in the ith online member account in the platform, TNow thatRepresents the current time, aiTNote thatRepresented as the member registration time for the ith online member account in the platform.
In one possible design of the first aspect, the calculation formula of the integrated loyalty prediction coefficient of the users in the online member accounts in the platform isξiExpressed as the loyalty prediction coefficient of the user in the ith online member account in the platform,expressed as the loyalty influence scaling factor, Δ A, corresponding to the membership grade of the ith online membership account in the platformiR is expressed as the difference value of the accumulated additional recharging amount in the ith online member account in the platform,expressed as standard recharging amount corresponding to the member level of the ith online member account in the platform, e is expressed as a natural number and is equal to 2.718, eta and alpha are respectively expressed as compensation coefficients of the influence of the account use duration and the member renewal time interval on the loyalty, Aik is expressed as the user usage time ratio of the ith online member account in the platform, delta a'it′jRepresented as the jth member renewal time interval in the ith online member account in the platform.
In a second aspect, the invention further provides an online member management system based on big data analysis, the detailed information acquisition module is respectively connected with the member level extraction module and the time extraction module, the member level extraction module is respectively connected with the recharge amount analysis module and the analysis server, the time extraction module is connected with the time interval analysis module, the recharge amount analysis module is respectively connected with the recharge amount statistic module, the storage database and the analysis server, and the analysis server is respectively connected with the time interval analysis module, the use duration acquisition module and the storage database.
In a third aspect, the present invention further provides a computer storage medium, where a computer program is burned into the computer storage medium, and when the computer program runs in a memory of a server, the online member management method based on big data analysis according to the present invention is implemented.
Has the advantages that:
(1) the invention provides an online member management method, a system and a computer storage medium based on big data analysis, which lay a foundation for later extracting the detailed information of each online member account by acquiring the detailed information of each online member account in a platform, and respectively extract the member grade, the expiration time and the renewal time of each member in the detailed information of each online member account in the platform, and analyze the renewal time interval of each member in each online member account in the platform, thereby being capable of carrying out comprehensive analysis in multiple aspects by using the information of the online member accounts, effectively embodying the function of accurately screening the platform loyalty member accounts, counting each recharging amount in each online member account in the platform, analyzing the difference value of additional recharging amounts accumulated in each online member account in the platform, and acquiring the usage duration ratio of users in each online member account in the platform, and reliable reference data is provided for the comprehensive loyalty prediction coefficient of the users in each online member account in the later-stage computing platform, so that the loyalty of the online member users in the later-stage computing platform is more accurate and reliable.
(2) According to the invention, by calculating the comprehensive loyalty estimation coefficients of the users in each online member account in the platform and sequentially arranging and displaying the comprehensive loyalty estimation coefficients according to the sequence from large to small, the users of the loyalty member groups in the platform can be visually displayed, the strengthened management of the loyalty member groups in the platform is realized, the viscosity of the users of the loyalty member groups in the platform is increased, the user loss of the loyalty member groups in the platform is avoided, the daily management requirements of the member users on the platform line are further met, and the member account management level on the platform line is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the method steps of the present invention;
fig. 2 is a schematic view of a module connection structure according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a first aspect of the present invention provides an online member management method based on big data analysis, including the following steps:
s1, acquiring account detailed information: the detailed information of each online member account in the platform is acquired through the detailed information acquisition module, the detailed information of each online member account in the platform is counted, and a detailed information set PA (PA) of each online member account in the platform is formed1,pa2,...,pai,...,pan)，paiRepresented as detailed information of the ith online member account in the platform.
Specifically, the invention lays a foundation for extracting the detailed information of each online member account in the later period by acquiring the detailed information of each online member account in the platform.
S2, account member level extraction: and respectively extracting the member grade in the detailed information of each online member account in the platform through a member grade extraction module to obtain the member grade in the detailed information of each online member account in the platform.
In this embodiment, the step S2 includes counting the member levels of the online member accounts in the platform, and forming a member level set AX (a) of the online member accounts in the platform1x,a2x,...,aix,...,anx)，aix represents the member rating of the ith online member account in the platform.
Specifically, the invention provides a reliable reference basis for the comprehensive loyalty estimation coefficient of the users in the online member accounts in the later-stage computing platform by extracting the member grades in the detailed information of the online member accounts in the platform, and improves the accuracy and reliability of the loyalty estimation coefficient of the online member users in the later-stage computing platform.
S3, member expiration and renewal time statistics: and respectively extracting the expiration time and the renewal time of each member in the detailed information of each online member account in the platform through a time extraction module to obtain the expiration time and the renewal time of each member in each online member account in the platform.
In this embodiment, the step S3 includes counting the expiration times of each member in each online member account in the platform, and forming a set a of expiration times of each member in each online member account in the platformit(ait1,ait2,...,aitj,...,aitm)，aitjExpressed as the jth member expiration time in the ith online member account in the platform; meanwhile, the member renewal time of each time in each online member account in the platform is counted to form a member renewal time set A of each time in each online member account in the platformit′(ait′1,ait′2,...,ait′j,...,ait′m)，ait′jRepresented as the jth member renewal time in the ith online member account in the platform.
S4, analyzing the member renewal time interval: and calculating the renewal time interval of each member in each online member account in the platform through a time interval analysis module, and counting the renewal time interval of each member in each online member account in the platform.
In this embodiment, the formula of each member renewal time interval calculation in each online member account in the platform is Δ a'it′j＝ait′j-aitj，Δa′it′jExpressed as the jth member renewal time interval, a, in the ith online member account in the platformit′jExpressed as the jth member renewal time in the ith online member account in the platform, aitjDenoted as the ith line in the platformA jth member expiration time in the member account.
Specifically, the invention analyzes the time interval of each member renewal in each online member account in the platform by respectively extracting each member expiration time and each member renewal time in the detailed information of each online member account in the platform, thereby performing comprehensive analysis in multiple aspects by using the online member account information and effectively embodying the function of accurately screening the platform loyalty member accounts.
S5, account recharging amount statistics: and counting the recharging amount of each time in each online member account in the platform through a recharging amount counting module, and counting the recharging amount of each time in each online member account in the platform.
In this embodiment, the step S5 includes configuring each recharging amount set a in each online member account in the platformir(Air1,Air2,...,Airf,...,Airs)，AirfThe charging amount is expressed as the f-th charging amount in the ith online member account in the platform, and s is more than or equal to m.
S6, analyzing the difference value of the additional recharging amount: and extracting standard recharging amount corresponding to each online member grade in the platform stored in the storage database through a recharging amount analysis module, and calculating an additional recharging amount difference value accumulated in each online member account in the platform.
In this embodiment, the calculation formula of the difference between the accumulated additional recharge amounts in each online member account in the platform isΔAiR is expressed as the difference value of the accumulated additional recharging amount in the ith online member account in the platform, AirfExpressed as the f-th recharging amount in the ith online member account in the platform,expressed as the standard recharge amount corresponding to the member level of the ith online member account in the platform.
Specifically, the online membership account analysis method based on the online membership account statistics platform has the advantages that the difference value of the additional recharging amount accumulated in each online membership account in the analysis platform is obtained through counting each recharging amount in each online membership account in the platform, reliable reference data are provided for the comprehensive loyalty degree estimation coefficient of the user in each online membership account in the later-stage calculation platform, and therefore the loyalty degree of the online membership user in the later-stage analysis platform is more accurate and reliable.
S7, obtaining the account use duration: the using time length obtaining module is used for respectively obtaining the using time length of each user in each online member account in the platform, extracting the member registration time of each online member account in the platform and calculating the using time length ratio of each user in each online member account in the platform.
In this embodiment, the step S7 includes counting the user durations of each time in each online member account in the platform, and forming a user duration set a of each time in each online member account in the platformiT(aiT1,aiT2,...,aiTv,...,aiTu)，aiTvAnd is expressed as the length of the use time of the v-th user in the ith online member account in the platform.
In this embodiment, the calculation formula of the usage duration ratio of the users in each online member account in the platform isAik is the ratio of the user's use time in the ith online member account in the platform, aiTvExpressed as the length of time of using the v-th user in the ith online member account in the platform, TNow thatRepresents the current time, aiTNote thatRepresented as the member registration time for the ith online member account in the platform.
Specifically, the method and the device for online membership calculation of the late-stage analysis platform have the advantages that the using time of each user in each online member account in the platform is obtained, the using time of each user in each online member account in the platform is calculated, and reliable reference data are provided for the comprehensive loyalty degree estimation coefficient of each user in each online member account in the late-stage calculation platform, so that the loyalty degree of each online member user in the later-stage analysis platform is more accurate and reliable.
S8, analyzing the user loyalty estimation coefficient: and extracting the loyalty influence proportional coefficient corresponding to each online member grade in the platform stored in the storage database through the analysis server, calculating the comprehensive loyalty estimation coefficient of the users in each online member account in the platform, arranging the comprehensive loyalty estimation coefficients of the users in each online member account in the platform in sequence from large to small, and displaying the comprehensive loyalty estimation coefficients in sequence.
In this embodiment, the calculation formula of the comprehensive loyalty estimation coefficient of the users in each online member account in the platform isξiExpressed as the loyalty prediction coefficient of the user in the ith online member account in the platform,expressed as the loyalty influence scaling factor, Δ A, corresponding to the membership grade of the ith online membership account in the platformiR is expressed as the difference value of the accumulated additional recharging amount in the ith online member account in the platform,expressed as standard recharging amount corresponding to the member level of the ith online member account in the platform, e is expressed as a natural number and is equal to 2.718, eta and alpha are respectively expressed as compensation coefficients of the influence of the account use duration and the member renewal time interval on the loyalty, Aik is expressed as the user usage time ratio of the ith online member account in the platform, delta a'it′jRepresented as the jth member renewal time interval in the ith online member account in the platform.
Specifically, the comprehensive loyalty degree estimation coefficients of the users in the online member accounts in the platform are calculated, and the comprehensive loyalty degree estimation coefficients are sequentially arranged and displayed from large to small, so that the users of the loyalty member groups in the platform can be visually displayed, the strengthened management of the loyalty member groups in the platform is realized, the viscosity of the users of the loyalty member groups in the platform is increased, the user loss of the loyalty member groups in the platform is avoided, the daily management requirements of the membership users on the platform are met, and the management level of the membership accounts on the platform is improved.
In a second aspect, the invention further provides an online member management system based on big data analysis, the detailed information acquisition module is respectively connected with the member level extraction module and the time extraction module, the member level extraction module is respectively connected with the recharge amount analysis module and the analysis server, the time extraction module is connected with the time interval analysis module, the recharge amount analysis module is respectively connected with the recharge amount statistic module, the storage database and the analysis server, and the analysis server is respectively connected with the time interval analysis module, the use duration acquisition module and the storage database.
In a third aspect, the present invention further provides a computer storage medium, where a computer program is burned into the computer storage medium, and when the computer program runs in a memory of a server, the online member management method based on big data analysis according to the present invention is implemented.
The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.
