CN105744005A - Client positioning and analyzing method and server - Google Patents
Client positioning and analyzing method and server Download PDFInfo
- Publication number
- CN105744005A CN105744005A CN201610289448.9A CN201610289448A CN105744005A CN 105744005 A CN105744005 A CN 105744005A CN 201610289448 A CN201610289448 A CN 201610289448A CN 105744005 A CN105744005 A CN 105744005A
- Authority
- CN
- China
- Prior art keywords
- client
- class
- information
- data class
- label
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a client positioning and analyzing method. The method comprises following steps of extracting various service data corresponding to attribute data from multiple service servers according to client attribute data; according to an analyzing rule, dividing the extracted various service data into one or more data types; and according to a feature label extraction rule, carrying out feature label analysis to divided various data types, thus determining the feature labels of various data types of clients and positioning the clients. The invention also provides a server applicable to the method. According to the method and the server, potential clients can be positioned and analyzed, and the method and the server are convenient for realizing customized service pushing.
Description
Technical field
The present invention relates to data analysis assessment technology field, particularly a kind of client's method for positioning analyzing and server.
Background technology
At present, each company is when promotion business, it is common that adopt manual telephone system mode or instant message group sending pattern to lead referral or transmission service.
Such as, the telemarketing personnel of insurance company generally in the essential information obtaining client, after telephone number and name, will phone client and carry out insurance sales.It is likely to and does not know about the details of this client due to salesman, such as information such as the economic strength of client, preference, education landscapes, it is possible to make to promote effect as one wishes not to the utmost, and it would furthermore be possible to cause the dislike emotion of client.
Additionally, by the instant message group sending pattern mode to pushes customer business, the information received due to everyone is just as, it does not have being customized, so most of client is likely to can select directly to ignore message.
Therefore, the precision of above-mentioned promoting service is relatively low, relatively costly, and client's degree of dislike is higher.
Summary of the invention
In view of the foregoing, it is necessary to providing a kind of client's method for positioning analyzing, potential customers can be positioned analysis by it, in order to realize the service propelling customized.
A kind of client's method for positioning analyzing, the method includes:
From multiple service servers, the miscellaneous service data that attribute data is corresponding are extracted according to client properties data；
According to an analysis rule, the miscellaneous service data of extraction are divided into one or more data class；And
According to a feature tag extracting rule, the various data class divided are carried out feature tag analysis, to determine the feature tag of each data class of client, it is achieved user positions.
Preferably, the method also includes:
According to default feature tag and the mapping relations recommending class of business, obtain the recommendation class of business that the client characteristics label under each data class of determining is corresponding, for the recommendation class of business that the pushes customer under each data class of determining is corresponding.
Preferably, described business datum includes the use information of Financial Information, the ticket information of order, insurance information, job hunting information and immediate communication tool account.
Preferably, described analysis rule is cluster analysis rule.
Preferably, described feature tag extracting rule is: the business datum kind for various serial numbers arranges corresponding label threshold value；Miscellaneous service data class for discontinuous numerical value arranges corresponding label range；And the mapping relations according to the miscellaneous service data class of serial number with label threshold value, determine the label information that the business datum of the various serial numbers of each client is corresponding, and the mapping relations according to the non-miscellaneous service data class for serial number Yu label range, it is determined that go out the various non-label information corresponding for the business datum of serial number of each client.
In view of the foregoing, there is a need to provide a kind of server suitable in said method, potential customers can be positioned analysis by it, to realize the service propelling customized.
A kind of server, including storage device and processor, wherein:
Described storage device, is used for storing client's positioning analysis system；
Described processor, is used for calling and perform described client's positioning analysis system, to perform following steps:
From multiple service servers, the miscellaneous service data that attribute data is corresponding are extracted according to client properties data；
According to an analysis rule, the miscellaneous service data of extraction are divided into one or more data class；And
According to a feature tag extracting rule, the various data class divided are carried out feature tag analysis, to determine the feature tag of each data class of client, it is achieved user positions.
Preferably, described processor calls and performs described client's positioning analysis system, also executes the following steps:
According to default feature tag and the mapping relations recommending class of business, obtain the recommendation class of business that the client characteristics label under each data class of determining is corresponding, for the recommendation class of business that the pushes customer under each data class of determining is corresponding.
Preferably, described business datum includes the use information of Financial Information, the ticket information of order, insurance information, job hunting information and immediate communication tool account.
Preferably, described analysis rule is cluster analysis rule.
Preferably, described feature tag extracting rule is: the business datum kind for various serial numbers arranges corresponding label threshold value；Miscellaneous service data class for discontinuous numerical value arranges corresponding label range；And the mapping relations according to the miscellaneous service data class of serial number with label threshold value, determine the label information that the business datum of the various serial numbers of each client is corresponding, and the mapping relations according to the non-miscellaneous service data class for serial number Yu label range, it is determined that go out the various non-label information corresponding for the business datum of serial number of each client.
Client's method for positioning analyzing of the present invention and the server suitable in said method, by big data analysis, position client, to realize the service propelling that each potential customers perform customize.
Accompanying drawing explanation
Fig. 1 is the hardware environment figure of client's positioning analysis system first embodiment of the present invention.
Fig. 2 is the hardware environment figure of client's positioning analysis system the second embodiment of the present invention.
Fig. 3 is the functional block diagram of client's positioning analysis system preferred embodiment of the present invention.
Fig. 4 is the method implementing procedure figure of client's method for positioning analyzing the first preferred embodiment of the present invention.
Fig. 5 is the method implementing procedure figure of client's method for positioning analyzing the second preferred embodiment of the present invention.
Detailed description of the invention
Consult shown in Fig. 1, be the hardware environment figure of client's positioning analysis system first embodiment of the present invention.
In the present embodiment, described client's positioning analysis system 2 can install and run in a station server, such as big data analytics server 1.
Described big data analytics server 1 can be passed through communication module (not shown) and be connected with multiple stage service server 3 communication, for obtaining mass data from described multiple stage service server 3, to carry out big data analysis.Described service server 3 can include, but is not restricted to, for instance, bank server, credit card server, insurance server, security server, instant communication server, cad server, electricity business's server and/or recruitment service device etc..
Further, described big data analytics server 1 can also be passed through its communication module and be connected with the communication of at least one station terminal equipment 4, and the information for receiving terminal apparatus 4 inputs, and exports the analysis result obtained based on the input of described information to terminal unit 4.Described terminal unit 4 it may be that such as, the equipment such as PC, smart mobile phone, panel computer.Described terminal unit 4 includes the input equipment 40 for information input and the display device 41 for information output.
Described big data analytics server 1 can include processor and storage device (not shown).Described processor is arithmetic core (CoreUnit) and the control core (ControlUnit) of big data analytics server 1, for the data in interpretive machine instruction and process computer software.Described storage device can be one or more non-volatile memory cells, such as ROM, EPROM or FlashMemory (flash memory cell) etc..Described storage device can be built-in or be external in big data analytics server 1.
nullIn the present embodiment，Described client's positioning analysis system 2 can be a kind of computer software，It includes the executable program instruction code of computer，This program instruction code can be stored in described storage device，Under the execution of described processor，Realize following function: according to，The attribute data of the client as received from terminal unit 4，Including，Such as，Passport NO.，Phone number、Or the combination etc. of name and passport NO. and phone number，The miscellaneous service data that this client is corresponding are extracted from the multiple service servers 3 connected，Such as，Financial Information，Including the credit card accrediting amount and service condition information、Bank loan amount and refund situation information etc.，The ticket information ordered，Including the flight time、Starting point、Destination、The number of flights etc. of Preset Time，Insurance information，Including the industry，Sex、Age、Marital status、Occupation，Insurance buys ground，Insurance purchasing channel，Insure insurance kind，Type of service，Valid Policy number，Warrantee's number、The relation etc. of beneficiary and insurer，Job hunting information，Including hobby、Education experience、Work experience etc.，The use information of immediate communication tool account，Including，Landing time information、Information such as online hours etc.，According to an analysis rule，The miscellaneous service data of extraction are divided into one or more data class，According to a feature tag extracting rule，The various data class divided are carried out feature tag analysis，To determine the feature tag of each data class of client，Thus realizing the location to this user，With according to the feature tag preset and the mapping relations recommending class of business，Obtain the recommendation class of business that the client characteristics label under each data class determined is corresponding，For the recommendation class of business that the pushes customer under each data class of determining is corresponding.
nullWherein，Described feature tag includes basic feature information (such as，Affiliated region belongs to a line city、Well-educated、It is engaged in IT and belongs to management level etc.)、Preference habits information is (such as，Consume under customa-ry line、The online period of preference is 20:00-22:00、The contact channel of preference is immediate communication tool etc.)、Behavioural information is (such as，There is higher social network influence power、On line, liveness is high、Network viscosity is big、Driving infractions number of times is few、Number of times of seeking medical advice is few)、Financial risks information is (such as，Without promise breaking、Without swindle、It is not belonging to any blacklist etc.)、Transaction Information is (such as，Online trading is frequent、Off-line transaction liveness is high)、Individual value assessment information is (such as，Annual pay is high、The house property valuation having is high、Kai Haoche etc.) and/or social relations information is (such as，Social wide、Institute's exposed population group's consumption potentiality is big) etc..
In present pre-ferred embodiments, described feature tag extracting rule is: the business datum kind for various serial numbers arranges corresponding label threshold value；Miscellaneous service data class for discontinuous numerical value arranges corresponding label range；And the mapping relations according to the miscellaneous service data class of serial number with label threshold value, determine the label information that the business datum of the various serial numbers of each client is corresponding, and the mapping relations according to the non-miscellaneous service data class for serial number Yu label range, it is determined that go out the various non-label information corresponding for the business datum of serial number of each client.
Such as, annual pay and the business datum kind that online trading number of times etc. is serial number in the set time, it is possible to arranging label threshold value corresponding to annual pay can be 300,000 RMB, the label threshold value that online trading number of times in the set time is corresponding can be 10 times；When the annual pay of client exceedes label threshold value " such as, 300,000 RMB " of correspondence, representing label information corresponding to this client's annual pay is " high annual pay "；When the online trading number of times in the set time of client exceedes the label threshold value " such as, 10 times " of correspondence, then the label information representing the online trading of this client corresponding is " online trading is frequent ".
And for example, affiliated region, educational background etc. are the miscellaneous service data class of discontinuous numerical value, the label range that can arrange affiliated region corresponding includes: a line city gather, tier 2 cities set etc., when region belonging to client belongs to the city in a described line city gather, representing label information corresponding to region belonging to this client is " belonging to a line city "；Label range corresponding to client's educational background includes: higher education educational background set, secondary education educational background set and the education educational background set such as low, when client the most well educated belongs to described higher education educational background set, representing label information corresponding to this client's educational background is " being subject to high religion ".
In the present embodiment, described analysis rule can be cluster analysis rule.Described cluster analysis is also known as cluster analysis, and it is a kind of statistical analysis technique of data classification problem, is also an important algorithm of data mining simultaneously.Cluster analysis is based on similarity, and between the pattern in clustering at, ratio does not have more similarity between the pattern in same cluster.
In the present embodiment, described analysis rule can adopt the K-MEANS algorithm in cluster analysis, and its step includes: A, from miscellaneous service data, arbitrarily selects predetermined number, such as, K kind (K is the positive integer more than 2) business datum is as the first cluster centre；B, measure the remaining miscellaneous service data the first distance to each first cluster centre, remaining miscellaneous service data are divided into the class of the first closest cluster centre, to obtain K current data class；C, according to default computation rule, recalculate the second cluster centre of each described current data class；D, calculate the second cluster centre of each described current data class and the second distance of corresponding former first cluster centre, if second distance corresponding to each described current data class is respectively less than predetermined threshold value, then namely each described current data class is the data class of the second predetermined number to divide, or, if having second distance corresponding to described current data class be more than or equal to predetermined threshold value, then proceed to execution following step E, measure the miscellaneous service data the first distance to each second cluster centre, the miscellaneous service data of each client are divided into the class of the second closest cluster centre, to obtain K latest data class；F, according to default computation rule, recalculate current second cluster centre of each described latest data class；G, calculate current second cluster centre of each described latest data class and the second distance of corresponding former second cluster centre, if second distance corresponding to each described latest data class is respectively less than predetermined threshold value, then namely each described latest data class is the data class of the second predetermined number to divide, or, if having second distance corresponding to described latest data class be more than or equal to predetermined threshold value, then repeating above-mentioned steps E, F, G, the second distance corresponding until each described latest data class is respectively less than predetermined threshold value.
Wherein, described default computation rule is: the business datum of each client under data class is taken average, and namely described average is the second cluster centre of corresponding data class.
Consult shown in Fig. 2, be the hardware environment figure of client's positioning analysis system the second embodiment of the present invention.
In the present embodiment, described big data analytics server 1 is connected to network 5, such as WWW, to filter out the attribute data of client from described network 5, for instance, passport NO., the combination etc. of phone number or name and passport NO. and phone number.The described client's positioning analysis system 2 attribute data according to the described client screened, by performing above-mentioned functions, it is achieved the location to each client.
Consult shown in Fig. 3, be the functional block diagram of client's positioning analysis system preferred embodiment of the present invention.
The program code of described client's positioning analysis system 2 is according to its different function, it is possible to be divided into multiple functional module.In present pre-ferred embodiments, described client's positioning analysis system 2 can include client and choose module 20, data acquisition module 21, sort module 22, mark module 23 and pushing module 24.
Described client chooses module 20 for obtaining the attribute data of client.Described attribute data can include, for instance, passport NO., the combination etc. of phone number or name and passport NO. and phone number.In the present embodiment, the attribute data of described client can pass through passively to receive from a terminal unit 4, or a network 5, actively screening in WWW.
Described data acquisition module 21 for extracting the miscellaneous service data that this client is corresponding from multiple service servers 3.
Described business datum includes, such as, Financial Information, including the credit card accrediting amount and service condition information, bank loan amount and refund situation information etc., the ticket information ordered, including the flight time, starting point, destination, the number of flights etc. of Preset Time, insurance information, including the industry, sex, age, marital status, occupation, ground is bought in insurance, insurance purchasing channel, insure insurance kind, type of service, Valid Policy number, warrantee's number, the relation etc. of beneficiary and insurer, job hunting information, including hobby, education experience, work experience etc., the use information of immediate communication tool account, including, landing time information, information such as online hours etc..
Described sort module 22 is for according to an analysis rule, being divided into one or more data class by the miscellaneous service data of extraction.
In the present embodiment, described analysis rule can be cluster analysis rule.Described cluster analysis is also known as cluster analysis, and it is a kind of statistical analysis technique of data classification problem, is also an important algorithm of data mining simultaneously.Cluster analysis is based on similarity, and between the pattern in clustering at, ratio does not have more similarity between the pattern in same cluster.
In the present embodiment, described analysis rule can adopt the K-MEANS algorithm in cluster analysis, and its step includes: A, from miscellaneous service data, arbitrarily selects predetermined number, such as, K kind (K is the positive integer more than 2) business datum is as the first cluster centre；B, measure the remaining miscellaneous service data the first distance to each first cluster centre, remaining miscellaneous service data are divided into the class of the first closest cluster centre, to obtain K current data class；C, according to default computation rule, recalculate the second cluster centre of each described current data class；D, calculate the second cluster centre of each described current data class and the second distance of corresponding former first cluster centre, if second distance corresponding to each described current data class is respectively less than predetermined threshold value, then namely each described current data class is the data class of the second predetermined number to divide, or, if having second distance corresponding to described current data class be more than or equal to predetermined threshold value, then proceed to execution following step E, measure the miscellaneous service data the first distance to each second cluster centre, the miscellaneous service data of each client are divided into the class of the second closest cluster centre, to obtain K latest data class；F, according to default computation rule, recalculate current second cluster centre of each described latest data class；G, calculate current second cluster centre of each described latest data class and the second distance of corresponding former second cluster centre, if second distance corresponding to each described latest data class is respectively less than predetermined threshold value, then namely each described latest data class is the data class of the second predetermined number to divide, or, if having second distance corresponding to described latest data class be more than or equal to predetermined threshold value, then repeating above-mentioned steps E, F, G, the second distance corresponding until each described latest data class is respectively less than predetermined threshold value.
Described mark module 23 is for according to a feature tag extracting rule, carrying out feature tag analysis to the various data class divided, to determine the feature tag of each data class of client.
nullWherein，Described feature tag includes basic feature information (such as，Affiliated region belongs to a line city、Well-educated、It is engaged in IT and belongs to management level etc.)、Preference habits information is (such as，Consume under customa-ry line、The online period of preference is 20:00-22:00、The contact channel of preference is immediate communication tool etc.)、Behavioural information is (such as，There is higher social network influence power、On line, liveness is high、Network viscosity is big、Driving infractions number of times is few、Number of times of seeking medical advice is few)、Financial risks information is (such as，Without promise breaking、Without swindle、It is not belonging to any blacklist etc.)、Transaction Information is (such as，Online trading is frequent、Off-line transaction liveness is high)、Individual value assessment information is (such as，Annual pay is high、The house property valuation having is high、Kai Haoche etc.) and/or social relations information is (such as，Social wide、Institute's exposed population group's consumption potentiality is big) etc..
In present pre-ferred embodiments, described feature tag extracting rule is: the business datum kind for various serial numbers arranges corresponding label threshold value；Miscellaneous service data class for discontinuous numerical value arranges corresponding label range；And the mapping relations according to the miscellaneous service data class of serial number with label threshold value, determine the label information that the business datum of the various serial numbers of each client is corresponding, and the mapping relations according to the non-miscellaneous service data class for serial number Yu label range, it is determined that go out the various non-label information corresponding for the business datum of serial number of each client.
Such as, annual pay and the business datum kind that online trading number of times etc. is serial number in the set time, it is possible to arranging label threshold value corresponding to annual pay can be 300,000 RMB, the label threshold value that online trading number of times in the set time is corresponding can be 10 times；When the annual pay of client exceedes label threshold value " such as, 300,000 RMB " of correspondence, representing label information corresponding to this client's annual pay is " high annual pay "；When the online trading number of times in the set time of client exceedes the label threshold value " such as, 10 times " of correspondence, then the label information representing the online trading of this client corresponding is " online trading is frequent ".
And for example, affiliated region, educational background etc. are the miscellaneous service data class of discontinuous numerical value, the label range that can arrange affiliated region corresponding includes: a line city gather, tier 2 cities set etc., when region belonging to client belongs to the city in a described line city gather, representing label information corresponding to region belonging to this client is " belonging to a line city "；Label range corresponding to client's educational background includes: higher education educational background set, secondary education educational background set and the education educational background set such as low, when client the most well educated belongs to described higher education educational background set, representing label information corresponding to this client's educational background is " being subject to high religion ".
Described pushing module 24 is for according to the feature tag preset and the mapping relations recommending class of business, obtain the recommendation class of business that the client characteristics label under each data class of determining is corresponding, for the recommendation class of business that the pushes customer under each data class of determining is corresponding.
Consult shown in Fig. 4, be the method implementing procedure figure of client's method for positioning analyzing the first preferred embodiment of the present invention.Described in the present embodiment, client's method for positioning analyzing is not limited to step shown in flow chart, and in addition in step shown in flow chart, some step can be omitted, order between step can change.
Step S10, client is chosen module 20 and is received the attribute data obtaining client by a terminal unit 4.Described attribute data can include, for instance, passport NO., the combination etc. of phone number or name and passport NO. and phone number.
Step S11, data acquisition module 21 extracts the miscellaneous service data that this client is corresponding from multiple service servers 3.
Described business datum includes, such as, Financial Information, including the credit card accrediting amount and service condition information, bank loan amount and refund situation information etc., the ticket information ordered, including the flight time, starting point, destination, the number of flights etc. of Preset Time, insurance information, including the industry, sex, age, marital status, occupation, ground is bought in insurance, insurance purchasing channel, insure insurance kind, type of service, Valid Policy number, warrantee's number, the relation etc. of beneficiary and insurer, job hunting information, including hobby, education experience, work experience etc., the use information of immediate communication tool account, including, landing time information, information such as online hours etc..
Step S12, the miscellaneous service data of extraction, according to an analysis rule, are divided into one or more data class by sort module 22.
In the present embodiment, described analysis rule can be cluster analysis rule.Described cluster analysis is also known as cluster analysis, and it is a kind of statistical analysis technique of data classification problem, is also an important algorithm of data mining simultaneously.Cluster analysis is based on similarity, and between the pattern in clustering at, ratio does not have more similarity between the pattern in same cluster.
In the present embodiment, described analysis rule can adopt the K-MEANS algorithm in cluster analysis, and its step includes: A, from miscellaneous service data, arbitrarily selects predetermined number, such as, K kind (K is the positive integer more than 2) business datum is as the first cluster centre；B, measure the remaining miscellaneous service data the first distance to each first cluster centre, remaining miscellaneous service data are divided into the class of the first closest cluster centre, to obtain K current data class；C, according to default computation rule, recalculate the second cluster centre of each described current data class；D, calculate the second cluster centre of each described current data class and the second distance of corresponding former first cluster centre, if second distance corresponding to each described current data class is respectively less than predetermined threshold value, then namely each described current data class is the data class of the second predetermined number to divide, or, if having second distance corresponding to described current data class be more than or equal to predetermined threshold value, then proceed to execution following step E, measure the miscellaneous service data the first distance to each second cluster centre, the miscellaneous service data of each client are divided into the class of the second closest cluster centre, to obtain K latest data class；F, according to default computation rule, recalculate current second cluster centre of each described latest data class；G, calculate current second cluster centre of each described latest data class and the second distance of corresponding former second cluster centre, if second distance corresponding to each described latest data class is respectively less than predetermined threshold value, then namely each described latest data class is the data class of the second predetermined number to divide, or, if having second distance corresponding to described latest data class be more than or equal to predetermined threshold value, then repeating above-mentioned steps E, F, G, the second distance corresponding until each described latest data class is respectively less than predetermined threshold value.
Step S13, the various data class divided, according to a feature tag extracting rule, are carried out feature tag analysis, to determine the feature tag of each data class of client by mark module 23.
nullWherein，Described feature tag includes basic feature information (such as，Affiliated region belongs to a line city、Well-educated、It is engaged in IT and belongs to management level etc.)、Preference habits information is (such as，Consume under customa-ry line、The online period of preference is 20:00-22:00、The contact channel of preference is immediate communication tool etc.)、Behavioural information is (such as，There is higher social network influence power、On line, liveness is high、Network viscosity is big、Driving infractions number of times is few、Number of times of seeking medical advice is few)、Financial risks information is (such as，Without promise breaking、Without swindle、It is not belonging to any blacklist etc.)、Transaction Information is (such as，Online trading is frequent、Off-line transaction liveness is high)、Individual value assessment information is (such as，Annual pay is high、The house property valuation having is high、Kai Haoche etc.) and/or social relations information is (such as，Social wide、Institute's exposed population group's consumption potentiality is big) etc..
In present pre-ferred embodiments, described feature tag extracting rule is: the business datum kind for various serial numbers arranges corresponding label threshold value；Miscellaneous service data class for discontinuous numerical value arranges corresponding label range；And the mapping relations according to the miscellaneous service data class of serial number with label threshold value, determine the label information that the business datum of the various serial numbers of each client is corresponding, and the mapping relations according to the non-miscellaneous service data class for serial number Yu label range, it is determined that go out the various non-label information corresponding for the business datum of serial number of each client.
Such as, annual pay and the business datum kind that online trading number of times etc. is serial number in the set time, it is possible to arranging label threshold value corresponding to annual pay can be 300,000 RMB, the label threshold value that online trading number of times in the set time is corresponding can be 10 times；When the annual pay of client exceedes label threshold value " such as, 300,000 RMB " of correspondence, representing label information corresponding to this client's annual pay is " high annual pay "；When the online trading number of times in the set time of client exceedes the label threshold value " such as, 10 times " of correspondence, then the label information representing the online trading of this client corresponding is " online trading is frequent ".
And for example, affiliated region, educational background etc. are the miscellaneous service data class of discontinuous numerical value, the label range that can arrange affiliated region corresponding includes: a line city gather, tier 2 cities set etc., when region belonging to client belongs to the city in a described line city gather, representing label information corresponding to region belonging to this client is " belonging to a line city "；Label range corresponding to client's educational background includes: higher education educational background set, secondary education educational background set and the education educational background set such as low, when client the most well educated belongs to described higher education educational background set, representing label information corresponding to this client's educational background is " being subject to high religion ".
Step S14, pushing module 24 is according to default feature tag and the mapping relations recommending class of business, obtain the recommendation class of business that the client characteristics label under each data class of determining is corresponding, for the recommendation class of business that the pushes customer under each data class of determining is corresponding.
It may be that such as, this essential information, obtaining the essential information of client, after telephone number and name, is sent to big data analytics server 1 to the application scenarios of the present embodiment by the telemarketing personnel of insurance company.Described big data analytics server 1 is according to above-mentioned essential information, the miscellaneous service data of this client are obtained from miscellaneous service server 3, and analyze this client's characteristic of correspondence label accordingly, in order to according to this feature tag to the kind of insurance corresponding to lead referral, to improve probability of transaction.
Consult shown in Fig. 5, be the method implementing procedure figure of client's method for positioning analyzing the second preferred embodiment of the present invention.Described in the present embodiment, client's method for positioning analyzing is not limited to step shown in flow chart, and in addition in step shown in flow chart, some step can be omitted, order between step can change.
Step S20, client chooses module 20 from a network 5, filters out the attribute data of client in WWW.Described attribute data can include, for instance, passport NO., the combination etc. of phone number or name and passport NO. and phone number.
Step S21, data acquisition module 21 extracts the miscellaneous service data that each client is corresponding from multiple service servers 3.
Described business datum includes, such as, Financial Information, including the credit card accrediting amount and service condition information, bank loan amount and refund situation information etc., the ticket information ordered, including the flight time, starting point, destination, the number of flights etc. of Preset Time, insurance information, including the industry, sex, age, marital status, occupation, ground is bought in insurance, insurance purchasing channel, insure insurance kind, type of service, Valid Policy number, warrantee's number, the relation etc. of beneficiary and insurer, job hunting information, including hobby, education experience, work experience etc., the use information of immediate communication tool account, including, landing time information, information such as online hours etc..
Step S22, the miscellaneous service data of extraction, according to an analysis rule, are divided into one or more data class by sort module 22.
In the present embodiment, described analysis rule can be cluster analysis rule.Described cluster analysis is also known as cluster analysis, and it is a kind of statistical analysis technique of data classification problem, is also an important algorithm of data mining simultaneously.Cluster analysis is based on similarity, and between the pattern in clustering at, ratio does not have more similarity between the pattern in same cluster.
In the present embodiment, described analysis rule can adopt the K-MEANS algorithm in cluster analysis, and its step includes: A, from miscellaneous service data, arbitrarily selects predetermined number, such as, K kind (K is the positive integer more than 2) business datum is as the first cluster centre；B, measure the remaining miscellaneous service data the first distance to each first cluster centre, remaining miscellaneous service data are divided into the class of the first closest cluster centre, to obtain K current data class；C, according to default computation rule, recalculate the second cluster centre of each described current data class；D, calculate the second cluster centre of each described current data class and the second distance of corresponding former first cluster centre, if second distance corresponding to each described current data class is respectively less than predetermined threshold value, then namely each described current data class is the data class of the second predetermined number to divide, or, if having second distance corresponding to described current data class be more than or equal to predetermined threshold value, then proceed to execution following step E, measure the miscellaneous service data the first distance to each second cluster centre, the miscellaneous service data of each client are divided into the class of the second closest cluster centre, to obtain K latest data class；F, according to default computation rule, recalculate current second cluster centre of each described latest data class；G, calculate current second cluster centre of each described latest data class and the second distance of corresponding former second cluster centre, if second distance corresponding to each described latest data class is respectively less than predetermined threshold value, then namely each described latest data class is the data class of the second predetermined number to divide, or, if having second distance corresponding to described latest data class be more than or equal to predetermined threshold value, then repeating above-mentioned steps E, F, G, the second distance corresponding until each described latest data class is respectively less than predetermined threshold value.
Step S23, the various data class divided, according to a feature tag extracting rule, are carried out feature tag analysis, to determine the feature tag of each data class of each client by mark module 23.
nullWherein，Described feature tag includes basic feature information (such as，Affiliated region belongs to a line city、Well-educated、It is engaged in IT and belongs to management level etc.)、Preference habits information is (such as，Consume under customa-ry line、The online period of preference is 20:00-22:00、The contact channel of preference is immediate communication tool etc.)、Behavioural information is (such as，There is higher social network influence power、On line, liveness is high、Network viscosity is big、Driving infractions number of times is few、Number of times of seeking medical advice is few)、Financial risks information is (such as，Without promise breaking、Without swindle、It is not belonging to any blacklist etc.)、Transaction Information is (such as，Online trading is frequent、Off-line transaction liveness is high)、Individual value assessment information is (such as，Annual pay is high、The house property valuation having is high、Kai Haoche etc.) and/or social relations information is (such as，Social wide、Institute's exposed population group's consumption potentiality is big) etc..
In present pre-ferred embodiments, described feature tag extracting rule is: the business datum kind for various serial numbers arranges corresponding label threshold value；Miscellaneous service data class for discontinuous numerical value arranges corresponding label range；And the mapping relations according to the miscellaneous service data class of serial number with label threshold value, determine the label information that the business datum of the various serial numbers of each client is corresponding, and the mapping relations according to the non-miscellaneous service data class for serial number Yu label range, it is determined that go out the various non-label information corresponding for the business datum of serial number of each client.
Such as, annual pay and the business datum kind that online trading number of times etc. is serial number in the set time, it is possible to arranging label threshold value corresponding to annual pay can be 300,000 RMB, the label threshold value that online trading number of times in the set time is corresponding can be 10 times；When the annual pay of client exceedes label threshold value " such as, 300,000 RMB " of correspondence, representing label information corresponding to this client's annual pay is " high annual pay "；When the online trading number of times in the set time of client exceedes the label threshold value " such as, 10 times " of correspondence, then the label information representing the online trading of this client corresponding is " online trading is frequent ".
And for example, affiliated region, educational background etc. are the miscellaneous service data class of discontinuous numerical value, the label range that can arrange affiliated region corresponding includes: a line city gather, tier 2 cities set etc., when region belonging to client belongs to the city in a described line city gather, representing label information corresponding to region belonging to this client is " belonging to a line city "；Label range corresponding to client's educational background includes: higher education educational background set, secondary education educational background set and the education educational background set such as low, when client the most well educated belongs to described higher education educational background set, representing label information corresponding to this client's educational background is " being subject to high religion ".
Step S24, pushing module 24 is according to default feature tag and the mapping relations recommending class of business, obtain the recommendation class of business that each client characteristics label under each data class of determining is corresponding, for the recommendation class of business that each pushes customer under each data class of determining is corresponding.
The application scenarios of the present embodiment can be, such as, when adopting by instant message group sending pattern to the mode of pushes customer business, first the essential information of multiple client is filtered out from network 5, after ID (identity number) card No., telephone number, name or 1 its combination, this essential information is sent to big data analytics server 1.Described big data analytics server 1 is according to above-mentioned essential information, the miscellaneous service data of each client are obtained from miscellaneous service server 3, and analyze each client's characteristic of correspondence label accordingly, with the feature tag according to each client, the introduction to business of customization is provided, to improve the attention rate of client to each client.
It should be noted last that, above example is only in order to illustrate technical scheme and unrestricted, although the present invention being described in detail with reference to preferred embodiment, it will be understood by those within the art that, technical scheme can be modified or equivalent replacement, without deviating from the spirit and scope of technical solution of the present invention.
Claims (10)
1. client's method for positioning analyzing, it is characterised in that the method includes:
From multiple service servers, the miscellaneous service data that attribute data is corresponding are extracted according to client properties data；
According to an analysis rule, the miscellaneous service data of extraction are divided into one or more data class；And
According to a feature tag extracting rule, the various data class divided are carried out feature tag analysis, to determine the feature tag of each data class of client, it is achieved user positions.
2. the method for claim 1, it is characterised in that the method also includes:
According to default feature tag and the mapping relations recommending class of business, obtain the recommendation class of business that the client characteristics label under each data class of determining is corresponding, for the recommendation class of business that the pushes customer under each data class of determining is corresponding.
3. the method for claim 1, it is characterised in that described business datum includes the use information of Financial Information, the ticket information of order, insurance information, job hunting information and immediate communication tool account.
4. the method for claim 1, it is characterised in that described analysis rule is cluster analysis rule.
5. the method for claim 1, it is characterised in that described feature tag extracting rule is: the business datum kind for various serial numbers arranges corresponding label threshold value；Miscellaneous service data class for discontinuous numerical value arranges corresponding label range；And the mapping relations according to the miscellaneous service data class of serial number with label threshold value, determine the label information that the business datum of the various serial numbers of each client is corresponding, and the mapping relations according to the non-miscellaneous service data class for serial number Yu label range, it is determined that go out the various non-label information corresponding for the business datum of serial number of each client.
6. a server, it is characterised in that this server includes storage device and processor, wherein:
Described storage device, is used for storing client's positioning analysis system；
Described processor, is used for calling and perform described client's positioning analysis system, to perform following steps:
From multiple service servers, the miscellaneous service data that attribute data is corresponding are extracted according to client properties data；
According to an analysis rule, the miscellaneous service data of extraction are divided into one or more data class；And
According to a feature tag extracting rule, the various data class divided are carried out feature tag analysis, to determine the feature tag of each data class of client, it is achieved user positions.
7. server as claimed in claim 6, it is characterised in that described processor calls and performs described client's positioning analysis system, also executes the following steps:
According to default feature tag and the mapping relations recommending class of business, obtain the recommendation class of business that the client characteristics label under each data class of determining is corresponding, for the recommendation class of business that the pushes customer under each data class of determining is corresponding.
8. server as claimed in claim 6, it is characterised in that described business datum includes the use information of Financial Information, the ticket information of order, insurance information, job hunting information and immediate communication tool account.
9. server as claimed in claim 6, it is characterised in that described analysis rule is cluster analysis rule.
10. server as claimed in claim 6, it is characterised in that described feature tag extracting rule is: the business datum kind for various serial numbers arranges corresponding label threshold value；Miscellaneous service data class for discontinuous numerical value arranges corresponding label range；And the mapping relations according to the miscellaneous service data class of serial number with label threshold value, determine the label information that the business datum of the various serial numbers of each client is corresponding, and the mapping relations according to the non-miscellaneous service data class for serial number Yu label range, it is determined that go out the various non-label information corresponding for the business datum of serial number of each client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610289448.9A CN105744005A (en) | 2016-04-30 | 2016-04-30 | Client positioning and analyzing method and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610289448.9A CN105744005A (en) | 2016-04-30 | 2016-04-30 | Client positioning and analyzing method and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105744005A true CN105744005A (en) | 2016-07-06 |
Family
ID=56287902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610289448.9A Pending CN105744005A (en) | 2016-04-30 | 2016-04-30 | Client positioning and analyzing method and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105744005A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106789292A (en) * | 2016-12-29 | 2017-05-31 | 东方网力科技股份有限公司 | A kind of abnormal behaviour monitoring method and device |
| CN107657500A (en) * | 2016-12-03 | 2018-02-02 | 平安证券股份有限公司 | Stock recommends method and server |
| CN107767275A (en) * | 2016-08-22 | 2018-03-06 | 平安科技（深圳）有限公司 | Insure resource requirement analysis method and device |
| CN107909473A (en) * | 2017-12-27 | 2018-04-13 | 中国银行股份有限公司 | A kind of Web bank's marketing method and device based on user behavior analysis |
| WO2018202170A1 (en) * | 2017-05-05 | 2018-11-08 | 平安科技（深圳）有限公司 | Dynamic voice interaction system and menu generating method thereof |
| CN108831552A (en) * | 2018-04-09 | 2018-11-16 | 平安科技（深圳）有限公司 | electronic device, nasopharyngeal carcinoma screening analysis method and computer readable storage medium |
| CN108831553A (en) * | 2018-04-09 | 2018-11-16 | 平安科技（深圳）有限公司 | Electronic device, nasopharyngeal carcinoma risk method for early warning and computer readable storage medium |
| CN109246077A (en) * | 2018-08-01 | 2019-01-18 | 广州唯品会信息科技有限公司 | Distributed concurrent transaction method of calibration, device and computer storage medium |
| CN109447674A (en) * | 2018-09-03 | 2019-03-08 | 中国平安人寿保险股份有限公司 | Electronic device, insurance agent target service area determine method and storage medium |
| CN109657294A (en) * | 2018-11-29 | 2019-04-19 | 中国航空工业集团公司沈阳飞机设计研究所 | Test flight data automated analysis method and system based on characteristic parameter |
| CN109711950A (en) * | 2019-01-18 | 2019-05-03 | 深圳壹账通智能科技有限公司 | Recommended method, device, storage medium and the computer equipment of marketing product |
| CN110727699A (en) * | 2019-10-21 | 2020-01-24 | 中国民航信息网络股份有限公司 | Information request method, device, server and storage medium |
| CN111311420A (en) * | 2020-02-21 | 2020-06-19 | 深圳市思迪信息技术股份有限公司 | Business data pushing method and device |
| CN112632143A (en) * | 2020-12-30 | 2021-04-09 | 中国农业银行股份有限公司 | Data label generation method and device |
| CN112686764A (en) * | 2021-01-08 | 2021-04-20 | 北京虹信万达科技有限公司 | Channel management system based on insurance industry |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101192235A (en) * | 2007-04-11 | 2008-06-04 | 腾讯科技（深圳）有限公司 | Method, system and equipment for delivering advertisement based on user feature |
| US20090010410A1 (en) * | 2007-07-06 | 2009-01-08 | Van Anderson | Leads processing engine |
| CN101599164A (en) * | 2009-06-25 | 2009-12-09 | 阿里巴巴集团控股有限公司 | The method and system that the potential network client is passed judgment on |
| CN102118706A (en) * | 2010-12-14 | 2011-07-06 | 北京星源无限传媒科技有限公司 | Mobile phone advertising method based on subdivision of mobile phone advertisement users |
| CN102754110A (en) * | 2010-02-10 | 2012-10-24 | 微软公司 | Lead qualification based on contact relationships and customer experience |
| CN103559630A (en) * | 2013-10-31 | 2014-02-05 | 华南师范大学 | Customer segmentation method based on customer attribute and behavior characteristic analysis |
| CN103714139A (en) * | 2013-12-20 | 2014-04-09 | 华南理工大学 | Parallel data mining method for identifying a mass of mobile client bases |
-
2016
- 2016-04-30 CN CN201610289448.9A patent/CN105744005A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101192235A (en) * | 2007-04-11 | 2008-06-04 | 腾讯科技（深圳）有限公司 | Method, system and equipment for delivering advertisement based on user feature |
| US20090010410A1 (en) * | 2007-07-06 | 2009-01-08 | Van Anderson | Leads processing engine |
| CN101599164A (en) * | 2009-06-25 | 2009-12-09 | 阿里巴巴集团控股有限公司 | The method and system that the potential network client is passed judgment on |
| CN102754110A (en) * | 2010-02-10 | 2012-10-24 | 微软公司 | Lead qualification based on contact relationships and customer experience |
| CN102118706A (en) * | 2010-12-14 | 2011-07-06 | 北京星源无限传媒科技有限公司 | Mobile phone advertising method based on subdivision of mobile phone advertisement users |
| CN103559630A (en) * | 2013-10-31 | 2014-02-05 | 华南师范大学 | Customer segmentation method based on customer attribute and behavior characteristic analysis |
| CN103714139A (en) * | 2013-12-20 | 2014-04-09 | 华南理工大学 | Parallel data mining method for identifying a mass of mobile client bases |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107767275A (en) * | 2016-08-22 | 2018-03-06 | 平安科技（深圳）有限公司 | Insure resource requirement analysis method and device |
| CN107657500A (en) * | 2016-12-03 | 2018-02-02 | 平安证券股份有限公司 | Stock recommends method and server |
| CN107657500B (en) * | 2016-12-03 | 2022-04-29 | 平安证券股份有限公司 | Stock recommendation method and server |
| CN106789292A (en) * | 2016-12-29 | 2017-05-31 | 东方网力科技股份有限公司 | A kind of abnormal behaviour monitoring method and device |
| WO2018202170A1 (en) * | 2017-05-05 | 2018-11-08 | 平安科技（深圳）有限公司 | Dynamic voice interaction system and menu generating method thereof |
| CN107909473A (en) * | 2017-12-27 | 2018-04-13 | 中国银行股份有限公司 | A kind of Web bank's marketing method and device based on user behavior analysis |
| CN108831552A (en) * | 2018-04-09 | 2018-11-16 | 平安科技（深圳）有限公司 | electronic device, nasopharyngeal carcinoma screening analysis method and computer readable storage medium |
| CN108831553A (en) * | 2018-04-09 | 2018-11-16 | 平安科技（深圳）有限公司 | Electronic device, nasopharyngeal carcinoma risk method for early warning and computer readable storage medium |
| CN109246077B (en) * | 2018-08-01 | 2021-06-29 | 广州唯品会信息科技有限公司 | Distributed concurrent transaction verification method, device and computer storage medium |
| CN109246077A (en) * | 2018-08-01 | 2019-01-18 | 广州唯品会信息科技有限公司 | Distributed concurrent transaction method of calibration, device and computer storage medium |
| CN109447674A (en) * | 2018-09-03 | 2019-03-08 | 中国平安人寿保险股份有限公司 | Electronic device, insurance agent target service area determine method and storage medium |
| CN109657294A (en) * | 2018-11-29 | 2019-04-19 | 中国航空工业集团公司沈阳飞机设计研究所 | Test flight data automated analysis method and system based on characteristic parameter |
| CN109711950A (en) * | 2019-01-18 | 2019-05-03 | 深圳壹账通智能科技有限公司 | Recommended method, device, storage medium and the computer equipment of marketing product |
| CN110727699A (en) * | 2019-10-21 | 2020-01-24 | 中国民航信息网络股份有限公司 | Information request method, device, server and storage medium |
| CN111311420A (en) * | 2020-02-21 | 2020-06-19 | 深圳市思迪信息技术股份有限公司 | Business data pushing method and device |
| CN112632143A (en) * | 2020-12-30 | 2021-04-09 | 中国农业银行股份有限公司 | Data label generation method and device |
| CN112686764A (en) * | 2021-01-08 | 2021-04-20 | 北京虹信万达科技有限公司 | Channel management system based on insurance industry |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105744005A (en) | Client positioning and analyzing method and server | |
| CN111506801A (en) | Sequencing method and device for sub-applications in application App | |
| CN113627566A (en) | Early warning method and device for phishing and computer equipment | |
| CN112910953B (en) | Business data pushing method and device and server | |
| CN108681871A (en) | A kind of method of prompt message, terminal device and computer readable storage medium | |
| CN112766825A (en) | Enterprise financial service risk prediction method and device | |
| US10853763B1 (en) | Onboarding new service providers utilizing portable service provider attributes | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| KR102345949B1 (en) | Apparatus for recommending IT infrastructure system | |
| CN113077251A (en) | Abnormal behavior monitoring method and device in prepaid transaction scene | |
| CN112750043A (en) | Business data pushing method and device and server | |
| US11561963B1 (en) | Method and system for using time-location transaction signatures to enrich user profiles | |
| CN116304352A (en) | Message pushing method, device, equipment and storage medium | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN116361542A (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN116050359A (en) | Policy escrow entry method, system, terminal equipment and storage medium | |
| CN115375434A (en) | Interface layout adjusting method and related device | |
| US20220351269A1 (en) | Momentum blended recommendation engine | |
| CN114022184A (en) | Data management method and device, electronic equipment and storage medium | |
| CN113094595A (en) | Object recognition method, device, computer system and readable storage medium | |
| CN113393320A (en) | Enterprise financial service risk prediction method and device | |
| CN111882339A (en) | Prediction model training and response rate prediction method, device, equipment and storage medium | |
| CN112116253A (en) | Method, device and system for selecting central mesh point | |
| CN118096358B (en) | Intelligent enterprise credit report generation method and device | |
| US12093266B2 (en) | Machine learning model for recommending interaction parties |
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: 20160706 |
|
| RJ01 | Rejection of invention patent application after publication |