CN114881699A - Bank product delivery processing method and device based on regional clustering - Google Patents

Bank product delivery processing method and device based on regional clustering Download PDF

Info

Publication number
CN114881699A
CN114881699A CN202210549287.8A CN202210549287A CN114881699A CN 114881699 A CN114881699 A CN 114881699A CN 202210549287 A CN202210549287 A CN 202210549287A CN 114881699 A CN114881699 A CN 114881699A
Authority
CN
China
Prior art keywords
geographic area
customer
determining
client
potential
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
Application number
CN202210549287.8A
Other languages
Chinese (zh)
Inventor
朱江波
赵书祥
池振强
胡佳锋
马丽贤
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.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
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 Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202210549287.8A priority Critical patent/CN114881699A/en
Publication of CN114881699A publication Critical patent/CN114881699A/en
Pending legal-status Critical Current

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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0204—Market segmentation
    • G06Q30/0205—Location or geographical consideration

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Technology Law (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a bank product delivery processing method and device based on regional clustering, and relates to the technical field of data processing, wherein the method comprises the following steps: determining the corresponding position of each client in a preset geographic range; for each geographic area, determining a set formed by customers with the positions corresponding to the customers in the geographic area as a customer set corresponding to the geographic area; for each geographic area, determining a customer vector corresponding to the geographic area according to a customer set corresponding to the geographic area; clustering the geographic areas according to the customer vectors to obtain a plurality of geographic area sets; for each geographic area set, determining the transaction information of a customer set corresponding to the geographic area contained in the geographic area set as the transaction information corresponding to the geographic area set; and for each geographic area set, determining bank products corresponding to the geographic area set according to the transaction information corresponding to the geographic area set, and putting the bank products in the geographic area.

Description

Bank product delivery processing method and device based on regional clustering
Technical Field
The invention relates to the technical field of data processing, in particular to a bank product delivery processing method and device based on geographical clustering.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
In the daily operation process of the bank, the putting of bank products is relatively fixed; moreover, for some banks, the amount of transactions and data in the bank is small for customers in some areas. Therefore, effective digital marketing can not be performed for the customers in the areas.
In view of the above, a technical solution that can overcome the above-mentioned defects, effectively analyze customers in different areas, and accurately deliver products is needed.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a bank product delivery processing method and device based on regional clustering.
In a first aspect of the embodiments of the present invention, a method for processing delivery of bank products based on regional clustering is provided, including:
determining the corresponding position of each client in a preset geographic range;
for each geographic area, determining a set formed by customers with the positions corresponding to the customers in the geographic area as a customer set corresponding to the geographic area;
for each geographic area, determining a customer vector corresponding to the geographic area according to a customer set corresponding to the geographic area;
clustering the geographic areas according to the customer vectors to obtain a plurality of geographic area sets;
for each geographic area set, determining the transaction information of a customer set corresponding to the geographic area contained in the geographic area set as the transaction information corresponding to the geographic area set;
and for each geographic area set, determining bank products corresponding to the geographic area set according to the transaction information corresponding to the geographic area set, and putting the bank products in the geographic area.
In a second aspect of the embodiments of the present invention, a device for processing putting of bank products based on regional clustering is provided, including:
the position determining module is used for determining the position corresponding to each client in a preset geographic range;
the client set determining module is used for determining a set formed by clients with positions corresponding to the clients in the geographic area as a client set corresponding to the geographic area for each geographic area;
the client vector determining module is used for determining a client vector corresponding to each geographic area according to the client set corresponding to the geographic area;
the clustering module is used for clustering the geographic areas according to the customer vectors to obtain a plurality of geographic area sets;
the transaction information determining module is used for determining the transaction information of the customer set corresponding to the geographic area contained in each geographic area set as the transaction information corresponding to the geographic area set;
and the releasing module is used for determining bank products corresponding to the geographical region set according to the transaction information corresponding to the geographical region set for each geographical region set, and releasing the bank products in the geographical region.
In a third aspect of the embodiments of the present invention, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements a bank product delivery processing method based on regional clustering when executing the computer program.
In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements a bank product delivery processing method based on regional clustering.
In a fifth aspect of the embodiments of the present invention, a computer program product is provided, where the computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements a bank product delivery processing method based on regional clustering.
The bank product delivery processing method and device based on regional clustering provided by the invention determine the corresponding position of each customer in a preset geographic range; for each geographic area, determining a set formed by customers with the positions corresponding to the customers in the geographic area as a customer set corresponding to the geographic area; for each geographic area, determining a customer vector corresponding to the geographic area according to a customer set corresponding to the geographic area; clustering the geographic areas according to the customer vectors to obtain a plurality of geographic area sets; for each geographic area set, determining the transaction information of a customer set corresponding to the geographic area contained in the geographic area set as the transaction information corresponding to the geographic area set; for each geographic area set, determining bank products corresponding to the geographic area set according to the transaction information corresponding to the geographic area set, and putting the bank products in the geographic area.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a bank product delivery processing method based on regional clustering according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart illustrating a specific process of determining a customer vector corresponding to a geographic area according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a process of clustering geographic areas according to an embodiment of the present invention.
Fig. 4 is a schematic flowchart of a specific process of determining a bank product corresponding to a set of geographic areas according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of an architecture of a bank product delivery processing apparatus based on regional clustering according to an embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given only to enable those skilled in the art to better understand and to implement the present invention, and do not limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
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.
According to the embodiment of the invention, a bank product delivery processing method and device based on regional clustering are provided, and the method and device relate to the technical field of data processing.
The principles and spirit of the present invention are explained in detail below with reference to several representative embodiments of the invention.
Fig. 1 is a schematic flow chart of a bank product delivery processing method based on regional clustering according to an embodiment of the present invention. As shown in fig. 1, the method includes:
s1, determining the corresponding position of each client in the preset geographic range;
s2, for each geographic area, determining a set formed by the customers with the corresponding positions in the geographic area as a customer set corresponding to the geographic area;
s3, for each geographic area, determining a customer vector corresponding to the geographic area according to the customer set corresponding to the geographic area;
s4, clustering the geographical areas according to the customer vectors to obtain a plurality of geographical area sets;
s5, for each geographic area set, determining the transaction information of the customer set corresponding to the geographic area contained in the geographic area set as the transaction information corresponding to the geographic area set;
and S6, for each geographic area set, determining the bank products corresponding to the geographic area set according to the transaction information corresponding to the geographic area set, and putting the bank products in the geographic area.
According to the invention, through analyzing the customers in each geographic area, targeted bank products are put in different geographic areas, so that the precise putting of the bank products is realized, and the bank can carry out effective digital marketing, thereby meeting the financial requirements of the customers, improving the customer experience and improving the bank operation efficiency.
In order to explain the above bank product delivery processing method based on regional clustering more clearly, the following detailed description is made with reference to each step.
At S1, determining the corresponding location of each customer within the predetermined geographic range includes:
if the bank database stores the address information or the work address of the customer, determining the address information or the work unit address as the position corresponding to the customer; otherwise, the address with the largest transaction number in the transaction addresses (namely, the addresses of the transaction opponents) corresponding to the payment transaction data of the customer is determined as the position corresponding to the customer.
In S2, for each geographic area, the set of customers whose locations correspond to the customers in the geographic area is determined as the set of customers corresponding to the geographic area.
In an actual application scenario, for a predetermined geographic range, the predetermined geographic range may be divided into a plurality of geographic areas, and then according to the positions corresponding to the customers, the customers in each geographic area are respectively grouped into a customer set corresponding to each geographic area.
Specifically, the geographic area may be divided according to the street information, and in an actual application scenario, other similar area division modes may be adopted, so that a plurality of geographic areas may be divided.
In S3, referring to fig. 2, for each geographic area, according to the customer set corresponding to the geographic area, a specific method for determining the customer vector corresponding to the geographic area is as follows:
s301, classifying all clients in a preset geographic range to obtain a plurality of client categories;
in particular, the customer categorization method may be based on multi-dimensional data (such as funding amounts and revenue) of the customer.
S302, for each geographic area, determining the client category to which each client belongs in the client set corresponding to the geographic area;
and determining a client vector corresponding to the geographic area, wherein components of the client vector correspond to the client categories one by one, and the component value of each component is equal to the number of clients belonging to the client category corresponding to the component in the client set corresponding to the geographic area.
In S4, referring to fig. 3, the specific method for clustering geographic areas according to the customer vector to obtain a plurality of geographic area sets includes:
s401, determining a distance function corresponding to a geographic area according to the customer vector, wherein the distance function determines the distance between any two geographic areas as the distance between the customer vectors corresponding to the two geographic areas;
s402, clustering the geographical areas according to the distance functions corresponding to the geographical areas to obtain a plurality of geographical area sets.
In one embodiment, K-means is selected to cluster the geographic regions to obtain a plurality of geographic region sets.
Specifically, (S402) clustering the geographic areas according to the distance function corresponding to the geographic areas to obtain a plurality of geographic area sets includes:
selecting a plurality of geographical areas from all geographical areas of a preset geographical area as a set center, wherein each set center corresponds to a geographical area set, and the initial elements of the geographical area sets only comprise the corresponding set centers;
repeatedly executing the following steps on each geographic area and each geographic area set until the variation of the customer vectors of all the set centers is smaller than a set threshold value, thereby obtaining a plurality of geographic area sets:
the following steps A, B and C are performed for each geographic area in turn:
a, calculating the distance between each set center and a geographic area based on a distance function corresponding to the geographic area;
b, selecting a plurality of set centers consistent with the main transaction types of the geographic area from all the set centers; taking the minimum value in the distances between the selected multiple set centers and the geographic area as a first distance corresponding to the geographic area, and taking the geographic area set corresponding to the set center corresponding to the minimum value as a geographic area set corresponding to the geographic area; taking the minimum value of the distances between the unselected multiple set centers and the geographic area as a second distance corresponding to the geographic area;
c, if the first distance corresponding to the geographic area is smaller than or equal to the second distance corresponding to the geographic area, or the absolute value of the difference between the first distance corresponding to the geographic area and the second distance corresponding to the geographic area is smaller than a specified threshold, dividing the geographic area into a geographic area set corresponding to the geographic area; otherwise, a set center is newly built based on the geographic area, the newly built set center corresponds to a new geographic area set, and the initial elements of the new geographic area set only comprise the geographic area;
after the steps are executed for all the geographic areas, the following steps are executed for each geographic area set in sequence:
updating the customer vectors of the set center corresponding to the geographic area set into the average value of the customer vectors of all geographic areas of the geographic area set; and updating the main transaction type of the set center corresponding to the geographic area set into the data value with the largest quantity in the plurality of data values of the main transaction type of all the areas of the geographic area set.
It should be noted that the main transaction types of the geographic area can be determined as follows:
and taking the transaction type with the maximum transaction quantity in the transaction information of the customer set corresponding to the geographic area as the main transaction type of the geographic area.
In S5, for each geographic area set, the transaction information of the customer set corresponding to the geographic area included in the geographic area set is determined as the transaction information corresponding to the geographic area set.
In S6, referring to fig. 4, for each geographic area set, according to the transaction information corresponding to the geographic area set, the specific method for determining the bank product corresponding to the geographic area set includes:
s601, acquiring bank products contained in the transaction information corresponding to the geographic area set, and determining the acquired bank products as potential products corresponding to the geographic area set;
s602, determining risk indexes of each dimension corresponding to each potential product according to the transaction information corresponding to the geographical area set;
wherein the dimensions at least comprise a customer category, a transaction scenario, a time interval, and the like.
S603, determining a partial order of the potential products according to the risk indexes corresponding to all dimensions, wherein the partial order is used for determining whether a first potential product is superior to a second potential product in any two potential products;
s604, determining a maximum potential product in the potential products corresponding to the geographical area set according to the partial order of the potential products, wherein the maximum potential product is a maximum element of the partial order;
s605, determining the maximum potential product as a bank product corresponding to the geographical area set, and putting the bank product in the geographical area.
In one embodiment, (S602) determining risk indicators for each potential product corresponding to each dimension according to the transaction information corresponding to the set of geographic areas includes:
for each dimension, screening out transaction data corresponding to the dimension from the transaction information of the potential product corresponding to the geographical area set;
dividing the transaction data corresponding to each dimension into a plurality of transaction data subsets corresponding to each dimension according to the time sequence, wherein the transaction quantity contained in each transaction data subset is greater than a set value;
for each dimension, determining the proportion of the transaction data related to the risk in each transaction data subset corresponding to the dimension as a risk index sample of the dimension;
determining the variance of the risk indicator of each dimension based on the risk indicator sample of each dimension;
setting an index error upper bound value beta;
determining
Figure BDA0003653949660000071
A magnitude relation with β, wherein σ i Is the variance of the risk indicator of the ith dimension, n i Is the number of risk indicator samples for the ith dimension;
if it is not
Figure BDA0003653949660000072
The following steps are executed in a loop until the conditions are satisfied
Figure BDA0003653949660000073
Wherein m is i Is the number of all risk indicator samples for the ith dimension that have been obtained:
acquiring new transaction information of the potential product corresponding to the geographic area set (or acquiring transaction information of the potential product corresponding to a similar geographic area set of the geographic area set);
for each dimension, screening new transaction data corresponding to the dimension from the new transaction information corresponding to the potential product in the geographic area set;
dividing the new transaction data corresponding to each dimension into a plurality of new transaction data subsets corresponding to each dimension according to the time sequence, wherein the transaction quantity contained in each new transaction data subset is greater than a set value;
for each dimension, determining the proportion of the transaction data related to the risk in each new transaction data subset corresponding to the dimension as a risk index sample of the dimension;
when in use
Figure BDA0003653949660000074
And then determining the risk indexes of the potential products corresponding to all dimensions as the mean value of the risk index samples of the dimensions.
Wherein the index error upper bound value beta can be set as epsilon 2 X P, epsilon is the allowable index error threshold, and P is the probability that the allowable index error is greater than epsilon.
In one embodiment, (S603) one of the methods for determining the partial order of potential products according to the risk indicators corresponding to the dimensions is:
for any two potential products, if for each risk dimension, the risk indicator of a first potential product corresponding to the dimension of the two potential products is less than or equal to the risk indicator of a second potential product corresponding to the dimension of the two potential products, and the risk indicator of the first potential product corresponding to each dimension is less than the indicator threshold, then it is determined that the first potential product is better than the second potential product.
In another embodiment, (S603) another method for determining the partial order of the potential products according to the risk indicators corresponding to the dimensions is:
acquiring a client set of each potential product, and determining the number of clients belonging to each client category in the client set; determining a customer vector corresponding to the potential product, wherein components of the customer vector correspond to customer categories one to one, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component in the customer set of the potential product;
according to the client category to which each client in the client set corresponding to the geographic area set belongs; determining a client vector corresponding to the geographic area set, wherein components of the client vector correspond to client categories one to one, and the component value of each component is equal to the number of clients belonging to the client category corresponding to the component in the client set corresponding to the geographic area set;
for each potential product, determining the distance between the customer vector corresponding to the potential product and the customer vector corresponding to the geographic area set as the customer distance corresponding to the potential product;
for any two potential products, if the customer distance corresponding to a first potential product of the two potential products is less than or equal to the customer distance corresponding to a second potential product of the two potential products, and the risk indexes of all dimensions corresponding to the first potential product are less than the index threshold, determining that the first potential product is better than the second potential product.
In one embodiment, (S604) the specific method for determining the largest potential product in the potential products corresponding to the geographic area set according to the partial order of the potential products is:
initializing a maximum authentication value corresponding to each potential product corresponding to the geographical area set to be 'pending' and initializing a comparison boolean value corresponding to each potential product to be 'yes';
selecting a dimension, and sequencing all potential products corresponding to the geographic area set according to the order of risk indexes of the dimension from small to medium;
sequentially executing the following steps on each potential product corresponding to the geographic area set according to the sorted sequence until all potential products corresponding to the geographic area set are executed, namely determining all the maximum potential products in the potential products corresponding to the geographic area set:
for each potential product, if the maximum authentication value corresponding to the potential product is 'pending', setting the potential product to be compared corresponding to the potential product as other potential products (except the potential product) with the corresponding comparison boolean value of 'yes' in the potential products corresponding to the geographical area set; otherwise, setting the potential product to be compared corresponding to the potential product to be empty;
and sequentially determining the partial order relation between the potential product and each corresponding potential product to be compared: if the potential product to be compared is better than the potential product, updating the maximum authentication value corresponding to the potential product to be "no"; if the potential product is better than the potential product to be compared, updating the maximum authentication value corresponding to the potential product to be compared to 'no', and determining the potential product to be compared as a secondary potential product of the potential product;
if all potential products to be compared corresponding to the potential product are determined not to be superior to the potential product, the potential product is determined as the maximum potential product in the potential products corresponding to the geographical area set, and the comparison Boolean value of all secondary potential products of the maximum potential product is updated to be 'NO'.
It should be noted that although the operations of the method of the present invention have been described in the above embodiments and the accompanying drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the operations shown must be performed, to achieve the desired results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
Having described the method of an exemplary embodiment of the present invention, a bank product delivery processing apparatus based on regional clustering according to an exemplary embodiment of the present invention will be described with reference to fig. 5.
The implementation of the bank product delivery processing device based on regional clustering can refer to the implementation of the method, and repeated details are not repeated. The term "module" or "unit" used hereinafter may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Based on the same inventive concept, the invention also provides a bank product delivery processing device based on regional clustering, as shown in fig. 5, the device comprises:
a location determination module 510 for determining a location corresponding to each customer within a predetermined geographic range;
a customer set determining module 520, configured to determine, for each geographic area, a set of customers whose locations correspond to the customers in the geographic area as a customer set corresponding to the geographic area;
a customer vector determining module 530, configured to determine, for each geographic area, a customer vector corresponding to the geographic area according to the customer set corresponding to the geographic area;
the clustering module 540 is configured to cluster the geographic areas according to the customer vectors to obtain a plurality of geographic area sets;
the transaction information determining module 550 is configured to determine, for each geographic area set, the transaction information of the customer set corresponding to the geographic area included in the geographic area set as the transaction information corresponding to the geographic area set;
and the releasing module 560 is configured to, for each geographic area set, determine a bank product corresponding to the geographic area set according to the transaction information corresponding to the geographic area set, and release the bank product in the geographic area.
In an embodiment, the location determining module is specifically configured to:
if the bank database stores the address information or the work address of the customer, determining the address information or the work unit address as the position corresponding to the customer; otherwise, determining the address with the largest transaction quantity in the plurality of transaction addresses corresponding to the payment transaction data of the customer as the position corresponding to the customer.
In an embodiment, the customer vector determination module is specifically configured to:
classifying all customers in a preset geographic range to obtain a plurality of customer categories;
for each geographic area, determining a client category to which each client belongs in a client set corresponding to the geographic area;
and determining a client vector corresponding to the geographic area, wherein components of the client vector correspond to the client categories one by one, and the component value of each component is equal to the number of clients belonging to the client category corresponding to the component in the client set corresponding to the geographic area.
In an embodiment, the clustering module is specifically configured to:
determining a distance function corresponding to the geographic area according to the customer vector, wherein the distance function determines the distance between any two geographic areas as the distance between the customer vectors corresponding to the two geographic areas;
and clustering the geographical areas according to the distance functions corresponding to the geographical areas to obtain a plurality of geographical area sets.
In an embodiment, the clustering module is specifically configured to:
selecting a plurality of geographical areas from all geographical areas of a preset geographical area as a set center, wherein each set center corresponds to a geographical area set, and the initial elements of the geographical area sets only comprise the corresponding set centers;
repeatedly executing the following steps on each geographic area and each geographic area set until the variation of the customer vectors of all the set centers is smaller than a set threshold value, thereby obtaining a plurality of geographic area sets:
the following steps A, B and C are performed for each geographic area in turn:
a, calculating the distance between each set center and a geographic area based on a distance function corresponding to the geographic area;
b, selecting a plurality of collection centers consistent with the main transaction type of the geographic area from all the collection centers; taking the minimum value in the distances between the selected multiple set centers and the geographic area as a first distance corresponding to the geographic area, and taking the geographic area set corresponding to the set center corresponding to the minimum value as a geographic area set corresponding to the geographic area; taking the minimum value in the distances between the unselected multiple set centers and the geographic area as a second distance corresponding to the geographic area;
c, if the first distance corresponding to the geographic area is smaller than or equal to the second distance corresponding to the geographic area, or the absolute value of the difference between the first distance corresponding to the geographic area and the second distance corresponding to the geographic area is smaller than a specified threshold, dividing the geographic area into a geographic area set corresponding to the geographic area; otherwise, a set center is newly built based on the geographic area, the newly built set center corresponds to a new geographic area set, and the initial elements of the new geographic area set only comprise the geographic area;
after the steps are executed for all the geographic areas, the following steps are executed for each geographic area set in sequence:
updating the customer vectors of the set center corresponding to the geographic area set into the average value of the customer vectors of all geographic areas of the geographic area set; and updating the main transaction type of the set center corresponding to the geographic area set into the data value with the largest quantity in the plurality of data values of the main transaction type of all the areas of the geographic area set.
In an embodiment, the delivery module is specifically configured to:
acquiring bank products contained in the transaction information corresponding to the geographic area set, and determining the acquired bank products as potential products corresponding to the geographic area set;
determining risk indexes of each potential product corresponding to each dimension according to the transaction information corresponding to the geographical area set;
determining a partial order of the potential products according to the risk indexes corresponding to the dimensions, wherein the partial order is used for determining whether a first potential product is superior to a second potential product in any two potential products;
determining a maximum potential product in the potential products corresponding to the geographical area set according to the partial order of the potential products, wherein the maximum potential product is a maximum element of the partial order;
and determining the extremely large potential product as a bank product corresponding to the geographical area set, and putting the bank product in the geographical area.
In an embodiment, the delivery module is specifically configured to:
for any two potential products, if for each risk dimension, the risk indicator of a first potential product corresponding to the dimension of the two potential products is less than or equal to the risk indicator of a second potential product corresponding to the dimension of the two potential products, and the risk indicator of the first potential product corresponding to each dimension is less than the indicator threshold, then it is determined that the first potential product is better than the second potential product.
In an embodiment, the delivery module is specifically configured to:
acquiring a client set of each potential product, and determining the number of clients belonging to each client category in the client set; determining a customer vector corresponding to the potential product, wherein components of the customer vector correspond to customer categories one to one, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component in the customer set of the potential product;
according to the client category to which each client in the client set corresponding to the geographic area set belongs; determining a client vector corresponding to the geographic area set, wherein components of the client vector correspond to client categories one to one, and the component value of each component is equal to the number of clients belonging to the client category corresponding to the component in the client set corresponding to the geographic area set;
for each potential product, determining the distance between the customer vector corresponding to the potential product and the customer vector corresponding to the geographic area set as the customer distance corresponding to the potential product;
for any two potential products, if the customer distance corresponding to a first potential product of the two potential products is less than or equal to the customer distance corresponding to a second potential product of the two potential products, and the risk indexes of all dimensions corresponding to the first potential product are less than the index threshold, determining that the first potential product is better than the second potential product.
It should be noted that although in the above detailed description several modules of the geo-clustering based banking product placement processing apparatus are mentioned, this division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the modules described above may be embodied in one module according to embodiments of the invention. Conversely, the features and functions of one module described above may be further divided into embodiments by a plurality of modules.
Based on the aforementioned inventive concept, as shown in fig. 6, the present invention further provides a computer device 600, which includes a memory 610, a processor 620 and a computer program 630 stored in the memory 610 and operable on the processor 620, wherein the processor 620 executes the computer program 630 to implement the aforementioned method for processing delivery of bank products based on regional clustering.
Based on the foregoing inventive concept, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the foregoing bank product delivery processing method based on regional clustering.
Based on the foregoing inventive concept, the present invention proposes a computer program product comprising a computer program which, when executed by a processor, implements a method for processing delivery of banking products based on regional clustering.
The bank product delivery processing method and device based on regional clustering provided by the invention determine the corresponding position of each customer in a preset geographic range; for each geographic area, determining a set formed by customers with the positions corresponding to the customers in the geographic area as a customer set corresponding to the geographic area; for each geographic area, determining a customer vector corresponding to the geographic area according to a customer set corresponding to the geographic area; clustering the geographic areas according to the customer vectors to obtain a plurality of geographic area sets; for each geographic area set, determining the transaction information of a customer set corresponding to the geographic area contained in the geographic area set as the transaction information corresponding to the geographic area set; for each geographic area set, determining bank products corresponding to the geographic area set according to the transaction information corresponding to the geographic area set, and putting the bank products in the geographic area.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (19)

1. A bank product delivery processing method based on regional clustering is characterized by comprising the following steps:
determining the corresponding position of each client in a preset geographic range;
for each geographic area, determining a set formed by customers with the positions corresponding to the customers in the geographic area as a customer set corresponding to the geographic area;
for each geographic area, determining a customer vector corresponding to the geographic area according to a customer set corresponding to the geographic area;
clustering the geographic areas according to the customer vectors to obtain a plurality of geographic area sets;
for each geographic area set, determining the transaction information of a customer set corresponding to the geographic area contained in the geographic area set as the transaction information corresponding to the geographic area set;
and for each geographic area set, determining bank products corresponding to the geographic area set according to the transaction information corresponding to the geographic area set, and putting the bank products in the geographic area.
2. The method of claim 1, wherein determining the location corresponding to each customer within a predetermined geographic area comprises:
if the bank database stores the address information or the work address of the customer, determining the address information or the work unit address as the position corresponding to the customer; otherwise, determining the address with the largest transaction quantity in the plurality of transaction addresses corresponding to the payment transaction data of the customer as the position corresponding to the customer.
3. The method of claim 1, wherein for each geographic area, determining the customer vector corresponding to the geographic area according to the customer set corresponding to the geographic area comprises:
classifying all customers in a preset geographic range to obtain a plurality of customer categories;
for each geographic area, determining a client category to which each client belongs in a client set corresponding to the geographic area;
and determining a client vector corresponding to the geographic area, wherein components of the client vector correspond to the client categories one to one, and the component value of each component is equal to the number of clients belonging to the client category corresponding to the component in the client set corresponding to the geographic area.
4. The method of claim 1, wherein clustering geographic regions according to customer vectors to obtain a plurality of geographic region sets comprises:
determining a distance function corresponding to the geographic area according to the customer vector, wherein the distance function determines the distance between any two geographic areas as the distance between the customer vectors corresponding to the two geographic areas;
and clustering the geographical areas according to the distance functions corresponding to the geographical areas to obtain a plurality of geographical area sets.
5. The method of claim 4, wherein clustering the geographic regions according to the distance functions corresponding to the geographic regions to obtain a plurality of geographic region sets comprises:
selecting a plurality of geographical areas from all geographical areas of a preset geographical area as a set center, wherein each set center corresponds to a geographical area set, and the initial elements of the geographical area sets only comprise the corresponding set centers;
repeatedly executing the following steps on each geographic area and each geographic area set until the variation of the customer vectors of all the set centers is smaller than a set threshold value, thereby obtaining a plurality of geographic area sets:
the following steps A, B and C are performed for each geographic area in turn:
a, calculating the distance between each set center and a geographic area based on a distance function corresponding to the geographic area;
b, selecting a plurality of collection centers consistent with the main transaction type of the geographic area from all the collection centers; taking the minimum value in the distances between the selected multiple set centers and the geographic area as a first distance corresponding to the geographic area, and taking the geographic area set corresponding to the set center corresponding to the minimum value as a geographic area set corresponding to the geographic area; taking the minimum value in the distances between the unselected multiple set centers and the geographic area as a second distance corresponding to the geographic area;
c, if the first distance corresponding to the geographic area is smaller than or equal to the second distance corresponding to the geographic area, or the absolute value of the difference between the first distance corresponding to the geographic area and the second distance corresponding to the geographic area is smaller than a specified threshold, dividing the geographic area into a geographic area set corresponding to the geographic area; otherwise, a set center is newly built based on the geographic area, the newly built set center corresponds to a new geographic area set, and the initial elements of the new geographic area set only comprise the geographic area;
after the steps are executed for all the geographic areas, the following steps are executed for each geographic area set in sequence:
updating the customer vectors of the set center corresponding to the geographic area set into the average value of the customer vectors of all geographic areas of the geographic area set; and updating the main transaction type of the set center corresponding to the geographic area set into the data value with the largest quantity in the plurality of data values of the main transaction type of all the areas of the geographic area set.
6. The method of claim 1, wherein for each set of geographic regions, determining the bank product corresponding to the set of geographic regions based on the transaction information corresponding to the set of geographic regions comprises:
acquiring bank products contained in the transaction information corresponding to the geographic area set, and determining the acquired bank products as potential products corresponding to the geographic area set;
determining risk indexes of each potential product corresponding to each dimension according to the transaction information corresponding to the geographical area set;
determining a partial order of the potential products according to the risk indexes corresponding to the dimensions, wherein the partial order is used for determining whether a first potential product is superior to a second potential product in any two potential products;
determining a maximum potential product in the potential products corresponding to the geographical area set according to the partial order of the potential products, wherein the maximum potential product is a maximum element of the partial order;
and determining the extremely large potential product as a bank product corresponding to the geographical area set, and putting the bank product in the geographical area.
7. The method of claim 6, wherein determining the partial order of potential products based on the risk indicators corresponding to the respective dimensions comprises:
for any two potential products, if for each risk dimension, the risk indicator of a first potential product corresponding to the dimension of the two potential products is less than or equal to the risk indicator of a second potential product corresponding to the dimension of the two potential products, and the risk indicator of the first potential product corresponding to each dimension is less than the indicator threshold, then it is determined that the first potential product is better than the second potential product.
8. The method of claim 6, wherein determining the partial order of potential products based on the risk indicators corresponding to the respective dimensions comprises:
acquiring a client set of each potential product, and determining the number of clients belonging to each client category in the client set; determining a customer vector corresponding to the potential product, wherein components of the customer vector correspond to customer categories one to one, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component in the customer set of the potential product;
according to the client category to which each client in the client set corresponding to the geographic area set belongs; determining a client vector corresponding to the geographic area set, wherein components of the client vector correspond to client categories one to one, and the component value of each component is equal to the number of clients belonging to the client category corresponding to the component in the client set corresponding to the geographic area set;
for each potential product, determining the distance between the customer vector corresponding to the potential product and the customer vector corresponding to the geographic area set as the customer distance corresponding to the potential product;
for any two potential products, if the customer distance corresponding to a first potential product of the two potential products is less than or equal to the customer distance corresponding to a second potential product of the two potential products, and the risk indexes of all dimensions corresponding to the first potential product are less than the index threshold, determining that the first potential product is better than the second potential product.
9. The utility model provides a bank product puts in processing apparatus based on regional clustering which characterized in that includes:
the position determining module is used for determining the position corresponding to each client in a preset geographic range;
the client set determining module is used for determining a set formed by clients with positions corresponding to the clients in the geographic area as a client set corresponding to the geographic area for each geographic area;
the client vector determining module is used for determining a client vector corresponding to each geographic area according to the client set corresponding to the geographic area;
the clustering module is used for clustering the geographic areas according to the customer vectors to obtain a plurality of geographic area sets;
the transaction information determining module is used for determining the transaction information of the customer set corresponding to the geographic area contained in each geographic area set as the transaction information corresponding to the geographic area set;
and the releasing module is used for determining bank products corresponding to the geographical region set according to the transaction information corresponding to the geographical region set for each geographical region set, and releasing the bank products in the geographical region.
10. The apparatus of claim 9, wherein the location determination module is specifically configured to:
if the bank database stores the address information or the work address of the customer, determining the address information or the work unit address as the position corresponding to the customer; otherwise, determining the address with the largest transaction quantity in the plurality of transaction addresses corresponding to the payment transaction data of the customer as the position corresponding to the customer.
11. The apparatus of claim 9, wherein the customer vector determination module is specifically configured to:
classifying all customers in a preset geographic range to obtain a plurality of customer categories;
for each geographic area, determining a client category to which each client belongs in a client set corresponding to the geographic area;
and determining a client vector corresponding to the geographic area, wherein components of the client vector correspond to the client categories one by one, and the component value of each component is equal to the number of clients belonging to the client category corresponding to the component in the client set corresponding to the geographic area.
12. The apparatus of claim 9, wherein the clustering module is specifically configured to:
determining a distance function corresponding to the geographic area according to the customer vector, wherein the distance function determines the distance between any two geographic areas as the distance between the customer vectors corresponding to the two geographic areas;
and clustering the geographical areas according to the distance functions corresponding to the geographical areas to obtain a plurality of geographical area sets.
13. The apparatus of claim 12, wherein the clustering module is specifically configured to:
selecting a plurality of geographical areas from all geographical areas of a preset geographical area as a set center, wherein each set center corresponds to a geographical area set, and the initial elements of the geographical area sets only comprise the corresponding set centers;
repeatedly executing the following steps on each geographic area and each geographic area set until the variation of the customer vectors of all the set centers is smaller than a set threshold value, thereby obtaining a plurality of geographic area sets:
the following steps A, B and C are performed for each geographic area in turn:
a, calculating the distance between each set center and a geographic area based on a distance function corresponding to the geographic area;
b, selecting a plurality of collection centers consistent with the main transaction type of the geographic area from all the collection centers; taking the minimum value in the distances between the selected multiple set centers and the geographic area as a first distance corresponding to the geographic area, and taking the geographic area set corresponding to the set center corresponding to the minimum value as a geographic area set corresponding to the geographic area; taking the minimum value in the distances between the unselected multiple set centers and the geographic area as a second distance corresponding to the geographic area;
c, if the first distance corresponding to the geographic area is smaller than or equal to the second distance corresponding to the geographic area, or the absolute value of the difference between the first distance corresponding to the geographic area and the second distance corresponding to the geographic area is smaller than a specified threshold, dividing the geographic area into a geographic area set corresponding to the geographic area; otherwise, a set center is newly built based on the geographic area, the newly built set center corresponds to a new geographic area set, and the initial elements of the new geographic area set only comprise the geographic area;
after the steps are executed for all the geographic areas, the following steps are executed for each geographic area set in sequence:
updating the customer vectors of the set center corresponding to the geographic area set into the average value of the customer vectors of all geographic areas of the geographic area set; and updating the main transaction type of the set center corresponding to the geographic area set into the data value with the largest quantity in the plurality of data values of the main transaction type of all the areas of the geographic area set.
14. The device of claim 9, wherein the delivery module is specifically configured to:
acquiring bank products contained in the transaction information corresponding to the geographic area set, and determining the acquired bank products as potential products corresponding to the geographic area set;
determining risk indexes of each potential product corresponding to each dimension according to the transaction information corresponding to the geographical area set;
determining a partial order of the potential products according to the risk indexes corresponding to the dimensions, wherein the partial order is used for determining whether a first potential product is superior to a second potential product in any two potential products;
determining a maximum potential product in the potential products corresponding to the geographical area set according to the partial order of the potential products, wherein the maximum potential product is a maximum element of the partial order;
and determining the extremely large potential product as a bank product corresponding to the geographical area set, and putting the bank product in the geographical area.
15. The apparatus of claim 14, wherein the delivery module is specifically configured to:
for any two potential products, if for each risk dimension, the risk indicator of a first potential product corresponding to the dimension of the two potential products is less than or equal to the risk indicator of a second potential product corresponding to the dimension of the two potential products, and the risk indicator of the first potential product corresponding to each dimension is less than the indicator threshold, then it is determined that the first potential product is better than the second potential product.
16. The apparatus of claim 14, wherein the delivery module is specifically configured to:
acquiring a client set of each potential product, and determining the number of clients belonging to each client category in the client set; determining a customer vector corresponding to the potential product, wherein components of the customer vector correspond to customer categories one to one, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component in the customer set of the potential product;
according to the client category to which each client in the client set corresponding to the geographic area set belongs; determining a client vector corresponding to the geographic area set, wherein components of the client vector correspond to client categories one to one, and the component value of each component is equal to the number of clients belonging to the client category corresponding to the component in the client set corresponding to the geographic area set;
for each potential product, determining the distance between the customer vector corresponding to the potential product and the customer vector corresponding to the geographic area set as the customer distance corresponding to the potential product;
for any two potential products, if the customer distance corresponding to a first potential product of the two potential products is less than or equal to the customer distance corresponding to a second potential product of the two potential products, and the risk indexes of all dimensions corresponding to the first potential product are less than the index threshold, determining that the first potential product is better than the second potential product.
17. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 8 when executing the computer program.
18. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 8.
19. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 8.
CN202210549287.8A 2022-05-20 2022-05-20 Bank product delivery processing method and device based on regional clustering Pending CN114881699A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210549287.8A CN114881699A (en) 2022-05-20 2022-05-20 Bank product delivery processing method and device based on regional clustering

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210549287.8A CN114881699A (en) 2022-05-20 2022-05-20 Bank product delivery processing method and device based on regional clustering

Publications (1)

Publication Number Publication Date
CN114881699A true CN114881699A (en) 2022-08-09

Family

ID=82677921

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210549287.8A Pending CN114881699A (en) 2022-05-20 2022-05-20 Bank product delivery processing method and device based on regional clustering

Country Status (1)

Country Link
CN (1) CN114881699A (en)

Similar Documents

Publication Publication Date Title
CN110955661A (en) Data fusion method and device, readable storage medium and electronic equipment
CN105359172A (en) Calculating a probability of a business being delinquent
CN113138990B (en) Data blood margin construction and tracing method, device and equipment
CN117194500A (en) Data index verification method, device, equipment and storage medium
CN113312259A (en) Interface testing method and device
CN112348657A (en) Method and device for determining target credit user, computer equipment and storage medium
CN114936921A (en) Loan risk control method and device
CN114881699A (en) Bank product delivery processing method and device based on regional clustering
CN114638693A (en) Method and system for determining service type range of bank outlets
CN115759742A (en) Enterprise risk assessment method and device, computer equipment and storage medium
CN114862108A (en) Self-service equipment address selection processing method and system
CN115269085A (en) Mobile bank page display method and device
CN114723145A (en) Method and system for determining number of intelligent counters based on transaction amount
CN110941601B (en) Method and device for determining standard caliber of index, electronic equipment and storage medium
CN114117052A (en) Method and device for classifying business data reports
CN113342681B (en) Regression testing method and device
CN114997269A (en) Face recognition processing method and system for bank outlets
US20230376977A1 (en) System for determining cross selling potential of existing customers
CN114781524A (en) Method and system for determining face recognition threshold value by analyzing transaction risk
CN114881764A (en) Transaction interface display method and device
CN114881785A (en) Service mode processing method and device for intelligent counter
CN113360511A (en) Method, device and equipment for processing credit investigation information
CN114926277A (en) Method and device for recommending business channel by bank
CN118379080A (en) Key guest group tracking method and device, storage medium and processor
CN114942877A (en) Method and device for determining user interface of bank system

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