CN111639967A - Method and system for mining potential customers of product - Google Patents

Method and system for mining potential customers of product Download PDF

Info

Publication number
CN111639967A
CN111639967A CN202010436751.3A CN202010436751A CN111639967A CN 111639967 A CN111639967 A CN 111639967A CN 202010436751 A CN202010436751 A CN 202010436751A CN 111639967 A CN111639967 A CN 111639967A
Authority
CN
China
Prior art keywords
customer
client
information
similarity
historical
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.)
Granted
Application number
CN202010436751.3A
Other languages
Chinese (zh)
Other versions
CN111639967B (en
Inventor
陈志泉
彭正强
刘亚飞
陈浩然
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industrial and Commercial Bank of China Ltd ICBC
Original Assignee
Industrial and Commercial Bank of China Ltd ICBC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Industrial and Commercial Bank of China Ltd ICBC filed Critical Industrial and Commercial Bank of China Ltd ICBC
Priority to CN202010436751.3A priority Critical patent/CN111639967B/en
Publication of CN111639967A publication Critical patent/CN111639967A/en
Application granted granted Critical
Publication of CN111639967B publication Critical patent/CN111639967B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03—Data mining
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention provides a method and a system for mining potential customers of a product. The product potential customer mining method comprises the following steps: acquiring current product information, and determining a current product client corresponding to the current product information; determining the client similarity between the current product client and the client in the client group where the current product client is located; when the customer similarity is larger than a preset threshold value, judging whether a customer corresponding to the customer similarity is a current product customer; and when the client corresponding to the client similarity is not the current product client, taking the client as the potential client of the current product. The method can accurately and quickly excavate potential target customers of the product and meet the individual requirements of the customers.

Description

Method and system for mining potential customers of product
Technical Field
The invention relates to the technical field of customer mining, in particular to a method and a system for mining potential customers of products.
Background
At present, the number of customers managed by each customer manager of a bank mechanism reaches hundreds, so that the customer manager is difficult to comprehensively know each customer, but with the increasing development of social contact, the personalized requirements of the customers are more and more, and in addition, the retail product service of the bank mechanism is complicated, the customer manager is difficult to timely push the product to the customers according to the personalized requirements of the customers.
Under the background, each large financial institution can mine potential customers of products through data reports, expert experiences or single data models, and the methods cannot flexibly deal with different types of products, have poor accuracy and cannot meet the personalized requirements of customers.
Disclosure of Invention
The embodiment of the invention mainly aims to provide a method and a system for mining potential customers of products, so as to accurately and quickly mine potential target customers of the products and meet personalized requirements of the customers.
In order to achieve the above object, an embodiment of the present invention provides a method for mining potential customers of a product, including:
acquiring current product information, and determining a current product client corresponding to the current product information;
determining the client similarity between the current product client and the client in the client group where the current product client is located;
when the customer similarity is larger than a preset threshold value, judging whether a customer corresponding to the customer similarity is a current product customer;
and when the client corresponding to the client similarity is not the current product client, taking the client as the potential client of the current product.
The embodiment of the invention also provides a system for mining potential customers of products, which comprises:
the client determining unit is used for acquiring the current product information and determining the current product client corresponding to the current product information;
the first similarity determining unit is used for determining the client similarity between the current product client and the client in the client group where the current product client is located;
the judging unit is used for judging whether the client corresponding to the client similarity is the current product client or not when the client similarity is larger than a preset threshold value;
and the potential customer determining unit is used for taking the customer as the potential customer of the current product when the customer corresponding to the customer similarity is not the current product customer.
The embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the product potential customer mining method when executing the computer program.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the product potential customer mining method.
The method and the system for mining the potential customers of the product determine the current product customer corresponding to the current product information, and then determine the customer similarity between the current product customer and the customers in the customer group where the current product customer is located; when the client similarity is larger than the preset threshold and the client corresponding to the client similarity is not the current product client, the client is taken as the current product potential client, the potential target client of the product can be accurately and quickly mined, and the personalized requirements of the client are met.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for mining potential customers of a product in an embodiment of the invention;
FIG. 2 is a schematic diagram of a relationship between a client and historical information in an embodiment of the invention;
FIG. 3 is a block diagram of a product potential customer mining system according to an embodiment of the present invention;
fig. 4 is a block diagram of a computer device in the embodiment of 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.
As will be appreciated by one skilled in the art, embodiments of the present invention may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
In view of the fact that the prior art cannot flexibly deal with different types of products and cannot meet the personalized requirements of customers, the embodiment of the invention provides a method for mining potential customers of products, so that potential target customers of the products can be accurately and quickly mined, and the personalized requirements of the customers can be met. The present invention will be described in detail below with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method for mining potential customers of a product in an embodiment of the invention. As shown in fig. 1, the product potential customer mining method includes:
s101: and acquiring current product information, and determining a current product client corresponding to the current product information.
For example, the current product information is insurance products, and z current product customers purchase insurance products. Wherein z is a positive integer greater than 1.
S102: determining the customer similarity between the current product customer and the customers in the customer group of the current product customer.
For example, determine a customer group in which z current product customers are located; and determining the customer similarity between each current product customer and the customers in the customer group. For example, if there are w customers in the customer group of one current product customer, the current product customer corresponds to w-1 customer similarities.
S103: and when the customer similarity is larger than a preset threshold value, judging whether the customer corresponding to the customer similarity is the current product customer.
For example, if the preset threshold is 0.8, sequentially judging whether the similarity of w-1 clients is greater than 0.8; and when the customer similarity is more than 0.8, determining whether the customer with the customer similarity more than 0.8 belongs to the current product customer.
S104: and when the client corresponding to the client similarity is not the current product client, taking the client as the potential client of the current product.
Wherein the current product prospective customer may subsequently be presented to a customer manager, the current product customer not belonging to the current product prospective customer.
The execution subject of the product potential customer mining method shown in fig. 1 is a computer. As can be seen from the flow shown in fig. 1, the method for mining potential customers of a product according to the embodiment of the present invention determines a current product customer corresponding to current product information, and then determines a customer similarity between the current product customer and a customer in a customer group in which the current product customer is located; when the client similarity is larger than the preset threshold and the client corresponding to the client similarity is not the current product client, the client is taken as the current product potential client, the potential target client of the product can be accurately and quickly mined, and the personalized requirements of the client are met.
In one embodiment, before executing S101, the method further includes:
firstly, dividing customers into n customer groups according to the historical customer information and the historical product information of the customers acquired in advance.
Wherein n is a positive integer greater than 1, and the historical product information includes historical product attributes.
For example, the historical customer information includes: gender, age, bank rating, occupation, academic calendar, total fund yield, itemized fund yield of each product, monthly average fund yield, daily average fund yield, bad loan total balance, transaction frequency, transaction amount of each product, total transaction amount of a plurality of time periods (such as total transaction amount in nearly 3, 6 and 12 months), inline transfer, offside transfer, in-place consumption, off-place consumption, in-place consumption, off-place consumption frequency, in-place consumption amount, off-place consumption amount, on-line consumption amount, off-line consumption amount, on-line consumption frequency, off-line consumption frequency, on-line consumption amount and off-line consumption amount;
the historical product attributes include: product name, product introduction, product sales region, product risk, profitability over multiple time periods (e.g., profitability over approximately 3, 6, 12 months), number of holders, frequency of transactions, and length of holding.
In particular implementation, dividing customers into n customer groups includes:
1. and combining one type of historical customer information and one type of historical product attribute of the same customer to obtain combined information of the customer.
Before the combination, the method can further comprise:
(1) and judging whether the historical customer information or the key attribute information in the historical product attribute corresponding to each customer is missing. And when the key attribute information is lost, deleting the historical client information or the historical product attribute corresponding to the client.
(2) Judging the number of missing values in the historical customer information or the historical product attribute corresponding to each customer; and when the number of the missing values is larger than the first preset value, deleting the historical customer information or the historical product attributes corresponding to the customer. And/or, calculating the average value of each historical customer information or historical product attribute; calculating the deviation degree between each type of historical customer information or historical product attribute and the corresponding mean value; and when the deviation degree is greater than a second preset value, deleting the historical client information or the historical product attributes, and filling the deleted historical client information or the historical product attributes with numerical values.
For example, the second preset value and the second preset value may be 75%, and the filled data may be special numbers such as 0,99, etc., or may be an average value or a median value of such historical customer information or historical product attributes.
(3) And (3) carrying out continuous processing on discrete values with practical significance in the historical customer information and the historical product attributes, and converting the time series data into discrete values or continuous values which can be used for calculation.
For example, characters such as high school, home, Master and doctor in the study calendar are converted into discrete numbers such as 0,1,2 and 3. The method comprises the steps of converting time sequence data of X ten thousand yuan of transaction amount of a certain product purchased by a certain customer in a certain period of time into total amount of purchasing the certain product in the last 3 months, and finally combining the academic calendar with the total amount of purchasing the certain product in the last 3 months to obtain the total amount of purchasing the certain product in the last 3 months by the customer in the academic calendar.
2. And clustering the customers according to the combination information, the historical customer information and the historical product information of the customers so as to divide the customers into n customer groups.
The step of dividing the customers into n customer groups is as follows:
(1) the number of the divided customer groups is preset to be m, m customers are randomly selected to be clustering centers, and then the clustering centers of the m customer groups are historical customer information of the m customers. Wherein m is a positive integer greater than 1.
(2) And respectively calculating the Euclidean distance from the data of each customer to each clustering center, and distributing the customers to the clustering centers closest to each clustering center. Wherein the data includes customer portfolio information, historical customer information, and historical product information. E.g. euclidean distance of customer x and cluster center y
Figure BDA0002502566130000051
xiI data, y for client xiIs the ith data of the clustering center y, and k is the total number of data.
(3) And determining the average value of all customer data in the m customer groups, and taking the average value as a new clustering center of the customer group. The new cluster center for each guest group is compared to the previous cluster center. And (5) if the cluster center is changed, returning to the step (2).
(4) When the clustering center does not change, determining the square (R) of the Euclidean distance between each customer and the clustering center of the customer group2) And accumulating the square sums to obtain the total square sum of the passenger group division schemes with the passenger group number of m.
(5) And (5) changing the value of m, returning to the step (1) to obtain the total square sum of the various guest group division schemes.
(6) And taking the guest group division scheme corresponding to the maximum value of the total square sum as a final guest group division scheme. And when the sum of the squares of the guest group division schemes with the number of the guest groups being n is the maximum value, dividing the guest groups into n guest groups.
And secondly, determining the client similarity between any two clients in the same client group according to the historical client information and the historical product information.
In specific implementation, determining the client similarity between any two clients in the same client group includes:
1. and acquiring an initial value of the client similarity.
FIG. 2 is a diagram illustrating a relationship between a client and history information according to an embodiment of the present invention. As shown in fig. 2, the history information includes historical customer information and historical product information, both the customer and the historical information are taken as nodes, and the node U1 and the node U2 represent the customer U1 and the customer U2, respectively. The node p1, the node p2 and the node p3 are history information of the client U1, and the node p2 and the node p4 are history information of the client U2. The client similarity, i.e. the similarity between the node U1 and the node U2, is expressed as s (U1, U2). Assuming that the initial value of the client similarity is 0.8, s (U1, U2) is 0.8.
Executing the following loop processing to a preset loop number:
2. determining the information similarity between the historical information of one client and the historical information of the other client according to the initial value of the client similarity, the number of the clients corresponding to the historical information of one client in the client group and the number of the clients corresponding to the historical information of the other client; wherein the historical information comprises historical customer information and historical product information.
For example, the information similarity between the history information of one client and the history information of another client includes: information similarity s between p1 and p2 (p1, p2), information similarity s between p1 and p4 (p1, p4), information similarity s between p2 and p2 (p2, p2), information similarity s between p2 and p4 (p2, p4), information similarity s between p3 and p2 (p3, p2), and information similarity s between p3 and p4 (p3, p 4).
Wherein s (p1, p2) × (s (U1, U1) + s (U1, U2))/(a1 × a 2); c is an attenuation coefficient, generally 0.8, a1 is the number of customers corresponding to p1, and a1 is 1; a2 is the number of clients corresponding to p2, and a2 is 2; s (U1, U1) is 1.
s (p1, p4) ═ c × s (U1, U2)/(a1 × a 4); a4 is the number of clients corresponding to p4, and a4 is 1.
s(p2,p2)＝1。
s(p2,p4)＝c×(s(U1,U2)+s(U2,U2))/(a2×a4)；s(U2,U2)＝1。
s (p3, p2) ═ c × s (U1, U1) + s (U1, U2))/(a3 × a 2); a3 is the number of clients corresponding to p3, and a3 is 1.
s(p3,p4)＝c×s(U1,U1)+s(U1,U2))/(a3×a4)。
3. And determining the quantity of the historical information corresponding to the two clients respectively.
For example, client U1 corresponds to 3 pieces of history information, and client U2 corresponds to 2 pieces of history information.
4. And determining a client similarity update value between the two clients according to the information similarity and the quantity of the historical information.
For example, the client similarity update value s' (U1, U2) is:
s' (U1, U2) × c/(b1 × b2) × (s (p1, p2) + s (p1, p4) + s (p2, p2) + s (p2, p4) + s (p3, p2) + s (p3, p 4)); b1 is the number of history information corresponding to the client U1, and b1 is 3; b2 represents the number of history information corresponding to the client U2, and b2 is 2.
5. And updating the initial value of the client similarity to an updated value of the client similarity.
For example, let s (U1, U2) be s' (U1, U2), return to step 2.
6. And when the preset cycle number is reached, taking the updated value of the client similarity as the client similarity.
For example, if the preset number of cycles is 5, the above steps 1 to 5 are executed 5 times, and then the updated value of the client similarity obtained in the 5 th cycle is the client similarity. The similarity between any two clients can be obtained.
The specific process of the embodiment of the invention is as follows:
1. and combining one type of historical customer information and one type of historical product attribute of the same customer to obtain combined information of the customer.
2. And clustering the customers according to the combination information, the historical customer information and the historical product information of the customers so as to divide the customers into n customer groups.
3. And acquiring an initial value of the client similarity.
4. And determining the information similarity between the historical information of one client and the historical information of the other client according to the initial value of the client similarity, the number of clients corresponding to the historical information of one client in the client group and the number of clients corresponding to the historical information of the other client.
5. And determining the quantity of the historical information corresponding to the two clients respectively, and determining a client similarity update value between the two clients according to the information similarity and the quantity of the historical information.
6. And (4) updating the initial value of the client similarity into an updated value of the client similarity, and returning to the step 4 until the preset cycle number is reached.
7. And when the preset cycle number is reached, taking the updated value of the client similarity as the client similarity.
8. And acquiring current product information, and determining a current product client corresponding to the current product information.
9. Determining the customer similarity between the current product customer and the customers in the customer group of the current product customer.
10. And when the customer similarity is larger than a preset threshold value, judging whether the customer corresponding to the customer similarity is the current product customer.
11. And when the client corresponding to the client similarity is not the current product client, taking the client as the potential client of the current product.
In summary, the method for mining the potential customers of the product according to the embodiment of the invention firstly determines the current product customer corresponding to the current product information, and then determines the customer similarity between the current product customer and the customers in the customer group where the current product customer is located; when the client similarity is larger than the preset threshold and the client corresponding to the client similarity is not the current product client, the client is taken as the current product potential client, the potential target client of the product can be accurately and quickly mined, and the personalized requirements of the client are met.
Based on the same inventive concept, the embodiment of the invention also provides a product potential customer mining system, and as the problem solving principle of the system is similar to the product potential customer mining method, the implementation of the system can refer to the implementation of the method, and repeated parts are not described again.
Fig. 3 is a block diagram of a product potential customer mining system according to an embodiment of the present invention. As shown in fig. 3, the product potential customer mining system includes:
the client determining unit is used for acquiring the current product information and determining the current product client corresponding to the current product information;
the first similarity determining unit is used for determining the client similarity between the current product client and the client in the client group where the current product client is located;
the judging unit is used for judging whether the client corresponding to the client similarity is the current product client or not when the client similarity is larger than a preset threshold value;
and the potential customer determining unit is used for taking the customer as the potential customer of the current product when the customer corresponding to the customer similarity is not the current product customer.
In one embodiment, the method further comprises the following steps:
the system comprises a guest group dividing unit, a customer group dividing unit and a customer service management unit, wherein the guest group dividing unit is used for dividing customers into n guest groups according to pre-acquired historical customer information and historical product information of the customers, and n is a positive integer greater than 1;
and the second similarity determining unit is used for determining the client similarity between any two clients in the same client group according to the historical client information and the historical product information.
In one embodiment, the second similarity determination unit is specifically configured to:
acquiring an initial value of the similarity of the clients;
executing the following loop processing to a preset loop number:
determining the information similarity between the historical information of one client and the historical information of the other client according to the initial value of the client similarity, the number of the clients corresponding to the historical information of one client in the client group and the number of the clients corresponding to the historical information of the other client; the historical information comprises historical customer information and historical product information;
determining the quantity of the historical information respectively corresponding to the two clients;
determining a client similarity update value between two clients according to the information similarity and the quantity of the historical information;
updating the initial value of the client similarity into an updated value of the client similarity;
and when the preset cycle number is reached, taking the updated value of the client similarity as the client similarity.
In one embodiment, the historical product information includes historical product attributes.
The guest group dividing unit is specifically configured to:
combining one of the historical customer information of the same customer with one of the historical product attributes to obtain combined information of the customer;
and clustering the customers according to the combination information, the historical customer information and the historical product information of the customers so as to divide the customers into n customer groups.
In summary, the product potential customer mining system of the embodiment of the present invention determines a current product customer corresponding to current product information, and then determines customer similarity between the current product customer and a customer in a customer group in which the current product customer is located; when the client similarity is larger than the preset threshold and the client corresponding to the client similarity is not the current product client, the client is taken as the current product potential client, the potential target client of the product can be accurately and quickly mined, and the personalized requirements of the client are met.
The embodiment of the invention also provides a specific implementation mode of computer equipment capable of realizing all the steps in the product potential customer mining method in the embodiment. Fig. 4 is a block diagram of a computer device in an embodiment of the present invention, and referring to fig. 4, the computer device specifically includes the following:
a processor (processor)401 and a memory (memory) 402.
The processor 401 is configured to call a computer program in the memory 402, and the processor executes the computer program to implement all the steps of the product potential customer mining method in the above embodiments, for example, the processor executes the computer program to implement the following steps:
acquiring current product information, and determining a current product client corresponding to the current product information;
determining the client similarity between the current product client and the client in the client group where the current product client is located;
when the customer similarity is larger than a preset threshold value, judging whether a customer corresponding to the customer similarity is a current product customer;
and when the client corresponding to the client similarity is not the current product client, taking the client as the potential client of the current product.
To sum up, the computer device of the embodiment of the present invention determines a current product customer corresponding to current product information, and then determines a customer similarity between the current product customer and a customer in a customer group where the current product customer is located; when the client similarity is larger than the preset threshold and the client corresponding to the client similarity is not the current product client, the client is taken as the current product potential client, the potential target client of the product can be accurately and quickly mined, and the personalized requirements of the client are met.
An embodiment of the present invention further provides a computer-readable storage medium capable of implementing all the steps in the product potential customer mining method in the foregoing embodiment, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements all the steps in the product potential customer mining method in the foregoing embodiment, for example, when the processor executes the computer program, the processor implements the following steps:
acquiring current product information, and determining a current product client corresponding to the current product information;
determining the client similarity between the current product client and the client in the client group where the current product client is located;
when the customer similarity is larger than a preset threshold value, judging whether a customer corresponding to the customer similarity is a current product customer;
and when the client corresponding to the client similarity is not the current product client, taking the client as the potential client of the current product.
To sum up, the computer-readable storage medium of the embodiment of the present invention determines a current product customer corresponding to current product information, and then determines a customer similarity between the current product customer and a customer in a customer group in which the current product customer is located; when the client similarity is larger than the preset threshold and the client corresponding to the client similarity is not the current product client, the client is taken as the current product potential client, the potential target client of the product can be accurately and quickly mined, and the personalized requirements of the client are met.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Those of skill in the art will further appreciate that the various illustrative logical blocks, units, and steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, elements, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.
The various illustrative logical blocks, or elements, or devices described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be located in a user terminal. In the alternative, the processor and the storage medium may reside in different components in a user terminal.
In one or more exemplary designs, the functions described above in connection with the embodiments of the invention may be implemented in hardware, software, firmware, or any combination of the three. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media that facilitate transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, such computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store program code in the form of instructions or data structures and which can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Additionally, any connection is properly termed a computer-readable medium, and, thus, is included if the software is transmitted from a website, server, or other remote source via a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wirelessly, e.g., infrared, radio, and microwave. Such discs (disk) and disks (disc) include compact disks, laser disks, optical disks, DVDs, floppy disks and blu-ray disks where disks usually reproduce data magnetically, while disks usually reproduce data optically with lasers. Combinations of the above may also be included in the computer-readable medium.

Claims (10)

1. A method for mining potential customers of a product, comprising:
acquiring current product information, and determining a current product client corresponding to the current product information;
determining customer similarity between the current product customer and a customer in a customer group in which the current product customer is located;
when the customer similarity is larger than a preset threshold value, judging whether a customer corresponding to the customer similarity is a current product customer;
and when the client corresponding to the client similarity is not the current product client, taking the client as the potential client of the current product.
2. The product prospective customer mining method of claim 1, further comprising:
dividing the customers into n customer groups according to the pre-acquired historical customer information and the historical product information of the customers, wherein n is a positive integer greater than 1;
and determining the customer similarity between any two customers in the same customer group according to the historical customer information and the historical product information.
3. The product potential customer mining method of claim 2, wherein determining customer similarity between any two customers in the same customer base comprises:
acquiring an initial value of the similarity of the clients;
executing the following loop processing to a preset loop number:
determining the information similarity between the historical information of one client and the historical information of the other client according to the initial value of the client similarity, the number of the clients corresponding to the historical information of one client in the client group and the number of the clients corresponding to the historical information of the other client; wherein the historical information comprises the historical customer information and the historical product information;
determining the quantity of the historical information respectively corresponding to the two clients;
determining a customer similarity update value between two customers according to the information similarity and the quantity of the historical information;
updating the initial value of the client similarity to an updated value of the client similarity;
and when the preset cycle number is reached, taking the updated value of the client similarity as the client similarity.
4. The method of product prospective customer mining of claim 2 wherein the historical product information comprises historical product attributes;
dividing the customer into n customer groups comprises:
combining one of the historical customer information of the same customer with one of the historical product attributes to obtain combined information of the customer;
clustering the customers according to the combination information of the customers, the historical customer information and the historical product information to divide the customers into n customer groups.
5. A product prospective customer mining system, comprising:
the client determining unit is used for acquiring current product information and determining a current product client corresponding to the current product information;
a first similarity determining unit, configured to determine a client similarity between the current product client and a client in a client group in which the current product client is located;
the judging unit is used for judging whether the client corresponding to the client similarity is the current product client or not when the client similarity is larger than a preset threshold value;
and the potential customer determining unit is used for taking the customer as the potential customer of the current product when the customer corresponding to the customer similarity is not the current product customer.
6. The product potential customer mining system of claim 5, further comprising:
the system comprises a guest group dividing unit, a customer group dividing unit and a customer service management unit, wherein the guest group dividing unit is used for dividing a customer into n guest groups according to pre-acquired historical customer information and historical product information of the customer, and n is a positive integer larger than 1;
and the second similarity determining unit is used for determining the customer similarity between any two customers in the same customer group according to the historical customer information and the historical product information.
7. The product potential customer mining system of claim 6, wherein the second similarity determination unit is specifically configured to:
acquiring an initial value of the similarity of the clients;
executing the following loop processing to a preset loop number:
determining the information similarity between the historical information of one client and the historical information of the other client according to the initial value of the client similarity, the number of the clients corresponding to the historical information of one client in the client group and the number of the clients corresponding to the historical information of the other client; wherein the historical information comprises the historical customer information and the historical product information;
determining the quantity of the historical information respectively corresponding to the two clients;
determining a customer similarity update value between two customers according to the information similarity and the quantity of the historical information;
updating the initial value of the client similarity to an updated value of the client similarity;
and when the preset cycle number is reached, taking the updated value of the client similarity as the client similarity.
8. The product prospective customer mining system of claim 6 wherein the historical product information comprises historical product attributes;
the guest group dividing unit is specifically configured to:
combining one of the historical customer information of the same customer with one of the historical product attributes to obtain combined information of the customer;
clustering the customers according to the combination information of the customers, the historical customer information and the historical product information to divide the customers into n customer groups.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the steps of the product potential customer mining method of any one of claims 1 to 4 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the product potential customer mining method of any one of claims 1 to 4.
CN202010436751.3A 2020-05-21 2020-05-21 Product potential customer mining method and system Active CN111639967B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010436751.3A CN111639967B (en) 2020-05-21 2020-05-21 Product potential customer mining method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010436751.3A CN111639967B (en) 2020-05-21 2020-05-21 Product potential customer mining method and system

Publications (2)

Publication Number Publication Date
CN111639967A true CN111639967A (en) 2020-09-08
CN111639967B CN111639967B (en) 2023-07-25

Family

ID=72328543

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010436751.3A Active CN111639967B (en) 2020-05-21 2020-05-21 Product potential customer mining method and system

Country Status (1)

Country Link
CN (1) CN111639967B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113704411A (en) * 2021-08-31 2021-11-26 平安银行股份有限公司 Word vector-based similar passenger group mining method, device, equipment and storage medium
CN115170178A (en) * 2022-06-27 2022-10-11 天翼爱音乐文化科技有限公司 Marketing method, system, equipment and storage medium based on call network

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106611344A (en) * 2015-10-23 2017-05-03 北京国双科技有限公司 Method and device for mining potential customers
CN108171553A (en) * 2018-01-17 2018-06-15 焦点科技股份有限公司 The potential customers' digging system and method for a kind of periodic service or product
WO2019153518A1 (en) * 2018-02-08 2019-08-15 平安科技（深圳）有限公司 Information pushing method and device, computer device and storage medium
CN110415002A (en) * 2019-07-31 2019-11-05 中国工商银行股份有限公司 Customer behavior prediction method and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106611344A (en) * 2015-10-23 2017-05-03 北京国双科技有限公司 Method and device for mining potential customers
CN108171553A (en) * 2018-01-17 2018-06-15 焦点科技股份有限公司 The potential customers' digging system and method for a kind of periodic service or product
WO2019153518A1 (en) * 2018-02-08 2019-08-15 平安科技（深圳）有限公司 Information pushing method and device, computer device and storage medium
CN110415002A (en) * 2019-07-31 2019-11-05 中国工商银行股份有限公司 Customer behavior prediction method and system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113704411A (en) * 2021-08-31 2021-11-26 平安银行股份有限公司 Word vector-based similar passenger group mining method, device, equipment and storage medium
CN113704411B (en) * 2021-08-31 2023-09-15 平安银行股份有限公司 Word vector-based similar guest group mining method, device, equipment and storage medium
CN115170178A (en) * 2022-06-27 2022-10-11 天翼爱音乐文化科技有限公司 Marketing method, system, equipment and storage medium based on call network

Also Published As

Publication number Publication date
CN111639967B (en) 2023-07-25

Similar Documents

Publication Publication Date Title
Christy et al. RFM ranking–An effective approach to customer segmentation
US10664923B2 (en) System and method for establishing a public ledger for gift card transactions
US8065227B1 (en) Method and system for producing custom behavior scores for use in credit decisioning
CN107766568A (en) Effective query processing is carried out using the histogram in columnar database
US7853503B2 (en) Transaction allocation
WO2020042764A1 (en) Amount settlement system and method
CN111667225A (en) Financial data processing method and device and computer system
CN111639967A (en) Method and system for mining potential customers of product
CN111861605A (en) Business object recommendation method
CN109886676A (en) Method of payment, calculating equipment, storage medium for block chain network
US7464008B2 (en) Methods and apparatus for selecting event sequences based on a likelihood of a user completing each event sequence
US20170061455A1 (en) Method and system for sizing of demographic markets
CN113326095A (en) Commission data processing method and device
US11562439B2 (en) Multi-way optimal reconciliation and recommendation
CN117094764A (en) Bank integral processing method and device
US20230222526A1 (en) Optimization of timeline of events for product-location pairs
CN109767333A (en) Select based method, device, electronic equipment and computer readable storage medium
CN111091218A (en) Method and device for generating bidding prediction model and automatically bidding advertisement delivery
US20220343234A1 (en) Method for hybrid machine learning for shrink prevention system
KR20130123304A (en) Server for calculating customer class and method thereof
CN114022246A (en) Product information pushing method and device, terminal equipment and storage medium
CN114782129A (en) Information recommendation method and device
Vu et al. Research on comparing Z-Score, O-Score and X-Score models in analyzing factors affecting financial risk in medical companies listed on Vietnam stock market
US20140156436A1 (en) System and Method for Product Deployment and Management
CN117455579B (en) Commodity recommendation intervention method, commodity recommendation intervention device, medium and equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant