CN111767319A - Customer mining method and device based on fund flow direction - Google Patents
Customer mining method and device based on fund flow direction Download PDFInfo
- Publication number
- CN111767319A CN111767319A CN202010571434.2A CN202010571434A CN111767319A CN 111767319 A CN111767319 A CN 111767319A CN 202010571434 A CN202010571434 A CN 202010571434A CN 111767319 A CN111767319 A CN 111767319A
- Authority
- CN
- China
- Prior art keywords
- mining
- fund
- account
- customer
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a customer mining method and device based on fund flow direction. The method comprises the following steps: acquiring basic information of a customer, basic information of an account, capital flow direction information and affiliated relationship information; carrying out data cleaning processing on the customer basic information, the account basic information, the fund flow direction information and the affiliated relationship information; constructing a fund transaction map by taking the basic information of the customer and the basic information of the account after the data cleaning and processing as points and the fund flow direction information and the belonging relation information after the data cleaning and processing as sides; and mining and analyzing according to the fund transaction map. According to the invention, by collecting and processing related data, the data accuracy is ensured, the fund transaction map of the customer is constructed for mining analysis, specific business rules do not need to be compiled, the potential customer is quickly mined and analyzed, the work of analysts is greatly reduced, the efficient, accurate and real-time customer information mining analysis effect is achieved, the accurate recommendation is realized, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of customer mining, in particular to a customer mining method and device based on capital flow direction.
Background
In financial systems, potential customer mining has been a very important topic. With the rapid development of internet technology and mobile support, payment and account transfer are electronized, a large amount of client payment information is recorded, and client behavior information is more and more abundant. In traditional potential customer mining, analysis mining is usually performed on static information of customers based on social relations of customer managers, however, the social relations of the customer managers are very limited, the customer information is generally very expensive to obtain, and the customers can change continuously with the development of time, and the analyzed potential customers are often poor in effect. The existing internet recommendation systems generally include three types: content recommendation, collaborative filtering and hybrid recommendation. Content recommendation mainly searches for similar commodity recommendations according to the past commodities purchased by users. The main idea of collaborative filtering is to mine users with similar hobbies according to past purchasing records of the users, and then recommend commodities of the similar users to target customers. The mixing method mainly combines content filtering and collaborative filtering, and combines the two recommendations for recommendation. The problems of inaccurate recommendation caused by inaccurate mining and analysis of customer information, low efficiency and invalid static customer information exist in the existing product recommendation process.
Disclosure of Invention
The embodiment of the invention mainly aims to provide a customer mining method and device based on capital flow direction, which construct a customer capital transaction map through accurate data acquisition and processing, achieve efficient, accurate and good-instantaneity customer information mining analysis effect, realize accurate recommendation and improve user experience.
In order to achieve the above object, an embodiment of the present invention provides a method for mining a customer based on a fund flow direction, where the method includes:
acquiring basic information of a customer, basic information of an account, capital flow direction information and affiliated relationship information;
carrying out data cleaning processing on the customer basic information, the account basic information, the fund flow direction information and the affiliated relationship information;
constructing a fund transaction map by taking the basic information of the customer and the basic information of the account after the data cleaning and processing as points and the fund flow direction information and the belonging relation information after the data cleaning and processing as sides;
and mining and analyzing according to the fund transaction map.
Optionally, in an embodiment of the present invention, the method further includes: and recommending products by using the mining analysis result.
Optionally, in an embodiment of the present invention, the mining and analyzing according to the fund transaction graph includes: and according to the fund transaction graph, performing at least one of social relationship mining, channel account mining, community mining and similar client mining.
Optionally, in an embodiment of the present invention, the mining the channel account according to the fund transaction map includes: determining the single-month fund inflow value and the single-month fund outflow value of the account according to the fund transaction map; and determining the channel account according to the account monthly fund inflow value and the account monthly fund outflow value.
Optionally, in an embodiment of the present invention, the performing community mining according to the fund transaction graph includes: carrying out community division on the fund transaction map by utilizing a community division mode based on connectivity; feature encoding each point in the fund transaction map; and calculating the similarity of each point after the characteristic coding, and clustering the communities according to the similarity of each point.
Optionally, in an embodiment of the present invention, the mining similar customers according to the fund transaction graph includes: feature encoding each point in the fund transaction map; and calculating the similarity of each point after the feature coding, and determining similar customers according to the similarity of each point.
An embodiment of the present invention further provides a customer mining device based on a capital flow direction, where the device includes:
the data acquisition module is used for acquiring basic information of a client, basic information of an account, capital flow direction information and affiliated relationship information;
the data processing module is used for cleaning and processing the customer basic information, the account basic information, the fund flow direction information and the affiliated relationship information;
the map building module is used for building a fund transaction map by taking the customer basic information and the account basic information after the data cleaning and processing as points and the fund flow direction information and the affiliated relationship information after the data cleaning and processing as sides;
and the mining analysis module is used for mining analysis according to the fund transaction map.
Optionally, in an embodiment of the present invention, the apparatus further includes a product recommendation module, configured to perform product recommendation by using a result of the mining analysis.
Optionally, in an embodiment of the present invention, the mining analysis module is further configured to perform at least one of social relationship mining, channel account mining, community mining, and similar customer mining according to the fund transaction map.
Optionally, in an embodiment of the present invention, the mining analysis module includes: the channel account mining unit is used for determining the single-month fund inflow value and the single-month fund outflow value of the account according to the fund transaction map; and determining the channel account according to the account monthly fund inflow value and the account monthly fund outflow value.
Optionally, in an embodiment of the present invention, the mining analysis module further includes: the community mining unit is used for carrying out community division on the fund transaction map by utilizing a community division mode based on connectivity; feature encoding each point in the fund transaction map; and calculating the similarity of each point after the characteristic coding, and clustering the communities according to the similarity of each point.
Optionally, in an embodiment of the present invention, the mining analysis module further includes: the similar customer mining unit is used for carrying out feature coding on each point in the fund transaction map; and calculating the similarity of each point after the feature coding, and determining similar customers according to the similarity of each point.
The invention also provides an electronic 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 when executing the program.
The present invention also provides a computer-readable storage medium storing a computer program for executing the above method.
According to the invention, by collecting and processing related data, the data accuracy is ensured, the fund transaction map of the customer is constructed for mining analysis, specific business rules do not need to be compiled, the potential customer is quickly mined and analyzed, the work of analysts is greatly reduced, the efficient, accurate and real-time customer information mining analysis effect is achieved, the accurate recommendation is realized, and the user experience is improved.
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 customer mining based on flow direction of funds in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of a funds transaction map in an embodiment of the present invention;
FIG. 3 is a flow chart of channel account mining in an embodiment of the present invention;
FIG. 4 is a flow chart of community mining in an embodiment of the present invention;
FIG. 5 is a flow chart of similar client mining in an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a customer mining device based on fund flow direction according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a customer mining method and device based on fund flow direction.
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.
Fig. 1 is a flowchart of a customer mining method based on fund flow direction according to an embodiment of the present invention, where the method includes:
step S1, collecting the basic information of the customer, the basic information of the account, the capital flow information and the information of the affiliated relationship. The basic information of the customer comprises a customer id, a customer name, a customer gender, a customer age and the like, the basic information of the account comprises an account id, an account name, account properties, an account opening area and the like, the fund flow direction information comprises a fund lending direction, a fund amount and fund properties, and the affiliated relationship information comprises the affiliated relationship between the customer and the account, particularly whether a certain account belongs to a certain customer. The basic information of the customer, the basic information of the account, the capital flow information and the affiliation information can be collected in real time by a business system such as a bank, and the collected data can be stored by using a big data distributed database (such as hadoop).
And step S2, performing data cleaning processing on the customer basic information, the account basic information, the fund flow direction information and the affiliation information. The data cleaning and processing includes data splicing, data format conversion, abnormal data processing and the like. In addition, the data cleaning and processing also comprises data preprocessing, wherein the data preprocessing comprises structures of points and edges of the trading map, the preprocessed and processed data conform to a map data format required by construction of the fund trading map, and the map data format is the structures of the points and the edges.
And step S3, constructing a fund transaction map by taking the customer basic information and the account basic information after the data cleaning processing as points and the fund flow direction information and the affiliation information after the data cleaning processing as sides. In the fund transaction map, points are transaction subjects and comprise basic customer information and basic account information. The sides are relations, namely the fund flow information and the affiliated relation information, including loan direction, transaction amount, transaction time and the like. And importing the data subjected to data cleaning processing into a graph database to construct a fund transaction graph. The schematic diagram of the fund transaction map is shown in fig. 2, wherein the fund transaction map can be updated along with changes of data such as customer basic information, account basic information, fund flow direction information and affiliation information, and subsequent mining analysis is accurate and has good real-time performance.
And step S4, performing mining analysis according to the fund transaction map. And after the construction of the fund transaction map is completed, mining analysis can be carried out to obtain a mining analysis result. The mining analysis result can embody the product types suitable for the customers, for example, the customers with small fund flow and more fund deposition are more suitable for recommending the robust financing product to the customers.
As an embodiment of the present invention, product recommendations are made using the results of mining analysis. In particular, the excavation analysis may be customized excavation based on different excavation directions. After the analysis and mining, product recommendation can be performed according to the mining result, for example, corresponding financial products are recommended to potential customers with financial requirements.
As an embodiment of the invention, mining analysis according to a fund transaction graph comprises the following steps: and according to the fund transaction map, performing at least one of social relationship mining, channel account mining, community mining and similar client mining.
In the social relationship mining, the social relationship between the clients can be obtained through the fund transaction graph, for example, if an enterprise fund account gives out wages, the clients who give out wages from the same enterprise account are often in a colleague relationship. Thus, similar products can be recommended for similar customers according to the social relationship of the customers.
In this embodiment, as shown in fig. 3, the mining of the channel account according to the fund transaction map comprises:
and step S31, determining the single-month fund inflow value and the single-month fund outflow value of the account according to the fund transaction map. According to the fund transaction map, all account information of the customer and fund flow direction information of each account can be obtained, so that the monthly fund inflow value and the monthly fund outflow value of the account of the customer can be determined.
And step S32, determining the channel account according to the account monthly fund inflow value and the account monthly fund outflow value. The channel account refers to account fund fast-forwarding and fast-releasing with less fund deposition, the determination method of the channel account is that the monthly fund-releasing amount of the customer divided by the fund-releasing amount is greater than a preset parameter, and the preset parameter can be obtained according to business experience or statistical analysis, for example, preferably, the preset parameter can be set to 0.8. If the account of a certain customer is determined as a channel account, which indicates that the fund deposition of the account is less, product recommendation can be performed according to the fund flow direction of the account, such as financial products and the like, specifically, the account can be analyzed to transfer out the fund usage, and products in rows are recommended according to the usage.
In this embodiment, as shown in fig. 4, the community mining according to the fund transaction graph includes:
and step S41, carrying out community division on the fund transaction graph by using a community division mode based on connectivity.
The community mining mainly utilizes a community discovery algorithm, generally, the community discovery algorithm is a division method based on connectivity, and the more the number of the two nodes is, the more easily the two nodes belong to the same community. What this approach tends to consider is more of a two-party transaction, but does not consider the information of both parties to the transaction. In the fund transaction map, the central points connected with the communities are usually merchants, and the number of individual and personal transactions is relatively small, so that the communities tend to the merchants based on the community division of connectivity.
The invention adopts a similarity calculation method for calculating two nodes to perform clustering on the basis of the traditional community discovery algorithm. Firstly, a community division method based on connectivity, such as a label propagation algorithm, is used for carrying out community division based on the connectivity, and then the similarity of two communities is calculated for carrying out community clustering.
Step S42, each point in the fund transaction map is subjected to feature coding. Before calculating the similarity of the two communities, feature coding is required, and the coding method mainly comprises text vector coding, numerical vector coding and graph feature coding. The text vector coding method can adopt a word2vec method and can use the existing trained method. The numerical vector coding is firstly subjected to discretization, the processing method generally adopts log taking on numerical values and then positive taking or box dividing processing according to experience, and the box dividing refers to interval division on numerical variables. For example, transaction amounts less than 10000, 10000 to 500000, 500000 to 1000000, more than 1000000 are divided into four boxes labeled 1, 2, 3, 4. And carrying out vector coding on the discrete numerical values according to a one-hot mode. The one-hot method is a vector coding mode for classification characteristics, for example, gender is male and female, agriculture, forestry, animal husbandry, fishery and the like exist in the industry, and areas are in various cities. The gender feature may be coded as 01 for male and 10 for female. Similarly, assuming that there are 10 industries, agriculture can be coded as 1000000000 and forestry as 0100000000. And processing the feature vector after feature coding, wherein the processing step comprises vector splicing. For example, if the gender of the customer a is male and the academic story is the subject, the gender feature code is 01, the academic story 001 is 01001 after feature coding and vector splicing, and similarly, feature coding and vector splicing can be performed on other features to obtain vector coding.
And step S43, calculating the similarity of each point after feature coding, and clustering communities according to the similarity of each point. The community division can be more accurate by clustering the divided communities according to the similarity, so that the effect of accurate recommendation of customers in the community can be realized, and the specific recommendation method is to analyze community characteristics such as average age, academic distribution, work distribution and purchased product condition analysis of the community and recommend hot products suitable for the community according to business experience.
In the present embodiment, as shown in FIG. 5, conducting similar customer mining according to the fund transaction graph includes:
step S51, each point in the fund transaction map is subjected to feature coding. Similar to community mining, similar client mining needs feature coding, and the coding method is the same as the community mining process.
And step S52, calculating the similarity of each point after feature coding, and determining similar clients according to the similarity of each point. After vector encoding, similar nodes can be searched for and potential similar customers can be mined. Further, similar products of the same type may be recommended for similar customers.
According to the invention, by collecting and processing related data, the data accuracy is ensured, the fund transaction map of the customer is constructed for mining analysis, specific business rules do not need to be compiled, the potential customer is quickly mined and analyzed, the work of analysts is greatly reduced, the efficient, accurate and real-time customer information mining analysis effect is achieved, the accurate recommendation is realized, and the user experience is improved.
Fig. 6 is a schematic structural diagram of a customer mining device based on fund flow direction according to an embodiment of the present invention, where the device includes:
the data acquisition module 10 is used for acquiring basic customer information, basic account information, capital flow direction information and affiliation information; the basic information of the customer comprises a customer id, a customer name, a customer gender, a customer age and the like, the basic information of the account comprises an account id, an account name, account properties, an account opening area and the like, the fund flow direction information comprises a fund lending direction, a fund amount and fund properties, and the affiliated relationship information comprises the affiliated relationship between the customer and the account, particularly whether a certain account belongs to a certain customer. The basic information of the customer, the basic information of the account, the capital flow information and the affiliation information can be collected in real time by a business system such as a bank, and the collected data can be stored by using a big data distributed database (such as hadoop).
The data processing module 20 is used for cleaning and processing the customer basic information, the account basic information, the fund flow direction information and the affiliated relationship information; the data cleaning and processing includes data splicing, data format conversion, abnormal data processing and the like. In addition, the data cleaning and processing also comprises data preprocessing, wherein the data preprocessing comprises structures of points and edges of the trading map, the preprocessed and processed data conform to a map data format required by construction of the fund trading map, and the map data format is the structures of the points and the edges.
The map construction module 30 is configured to construct a fund transaction map by taking the customer basic information and the account basic information after the data cleaning and processing as points and the fund flow direction information and the affiliation information after the data cleaning and processing as sides; in the fund transaction map, points are transaction subjects and comprise basic customer information and basic account information. The sides are relations, namely the fund flow information and the affiliated relation information, including loan direction, transaction amount, transaction time and the like. And importing the data subjected to data cleaning processing into a graph database to construct a fund transaction graph. The schematic diagram of the fund transaction map is shown in fig. 2, wherein the fund transaction map can be updated along with changes of data such as customer basic information, account basic information, fund flow direction information and affiliation information, and subsequent mining analysis is accurate and has good real-time performance.
And the mining analysis module 40 is used for mining analysis according to the fund transaction map. After the construction of the fund transaction map is completed, mining analysis can be performed, and particularly, the mining analysis can be customized mining according to different mining directions. After the analysis and mining, product recommendation can be performed according to the mining result, for example, corresponding financial products are recommended to potential customers with financial requirements.
In this embodiment, the customer mining apparatus based on the fund flow direction further includes: the basic information storage module is used for storing data and storing the acquired source data, and the storage module can use a big data distributed database such as: hadoop.
In this embodiment, the map construction module includes a transaction map data import tool, a transaction map construction tool, and a fund transaction map storage unit, and the map construction module mainly stores fund transaction map data and mainly uses a map database.
The mining analysis module comprises a feature storage unit, a graph database is also adopted, the storage mode is equal to that of a fund transaction graph storage unit, but the storage content is changed into processed feature coded data.
As an embodiment of the invention, the device further comprises a product recommendation module for recommending products by using the result of the mining analysis.
As an embodiment of the present invention, the mining analysis module is further configured to perform at least one of social relationship mining, channel account mining, community mining, and similar customer mining according to the fund transaction map.
In this embodiment, the mining analysis module includes: the channel account mining unit is used for determining the single-month fund inflow value and the single-month fund outflow value of the account according to the fund transaction map; and determining the channel account according to the account monthly fund inflow value and the account monthly fund outflow value.
In this embodiment, the mining analysis module further includes: the community mining unit is used for carrying out community division on the fund transaction map by utilizing a community division mode based on connectivity; feature encoding each point in the fund transaction map; and calculating the similarity of each point after the characteristic coding, and clustering the communities according to the similarity of each point.
In this embodiment, the mining analysis module further includes: the community mining unit is used for carrying out community division on the fund transaction map by utilizing a community division mode based on connectivity; feature encoding each point in the fund transaction map; and calculating the similarity of each point after the characteristic coding, and clustering the communities according to the similarity of each point.
Based on the same application concept as the customer mining method based on the fund flow direction, the invention also provides the customer mining device based on the fund flow direction. Because the principle of solving the problems of the customer mining device based on the fund flow direction is similar to that of a customer mining method based on the fund flow direction, the implementation of the customer mining device based on the fund flow direction can refer to the implementation of the customer mining method based on the fund flow direction, and repeated parts are not described again.
According to the invention, by collecting and processing related data, the data accuracy is ensured, the fund transaction map of the customer is constructed for mining analysis, specific business rules do not need to be compiled, the potential customer is quickly mined and analyzed, the work of analysts is greatly reduced, the efficient, accurate and real-time customer information mining analysis effect is achieved, the accurate recommendation is realized, and the user experience is improved.
The invention also provides an electronic 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 when executing the program.
The present invention also provides a computer-readable storage medium storing a computer program for executing the above method.
As shown in fig. 7, the electronic device 600 may further include: communication module 110, input unit 120, audio processing unit 130, display 160, power supply 170. It is noted that the electronic device 600 does not necessarily include all of the components shown in fig. 7; furthermore, the electronic device 600 may also comprise components not shown in fig. 7, which may be referred to in the prior art.
As shown in fig. 7, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, an LCD display, but is not limited thereto.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142, and the application/function storage section 142 is used to store application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging application, address book application, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132 to implement general telecommunications functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 130 is also coupled to the central processor 100, so that recording on the local can be enabled through a microphone 132, and so that sound stored on the local can be played through a speaker 131.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, 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, apparatus (systems), 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.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (14)
1. A method for customer mining based on flow of funds, the method comprising:
acquiring basic information of a customer, basic information of an account, capital flow direction information and affiliated relationship information;
carrying out data cleaning processing on the customer basic information, the account basic information, the fund flow direction information and the affiliated relationship information;
constructing a fund transaction map by taking the basic information of the customer and the basic information of the account after the data cleaning and processing as points and the fund flow direction information and the belonging relation information after the data cleaning and processing as sides;
and mining and analyzing according to the fund transaction map.
2. The method of claim 1, further comprising: and recommending products by using the mining analysis result.
3. The method of claim 1, wherein the mining analysis according to the funding transaction graph comprises: and according to the fund transaction graph, performing at least one of social relationship mining, channel account mining, community mining and similar client mining.
4. The method of claim 3, wherein the conducting channel account mining according to the funding transaction graph comprises:
determining the single-month fund inflow value and the single-month fund outflow value of the account according to the fund transaction map;
and determining the channel account according to the account monthly fund inflow value and the account monthly fund outflow value.
5. The method of claim 3, wherein the community mining according to the funding transaction graph comprises:
carrying out community division on the fund transaction map by utilizing a community division mode based on connectivity;
feature encoding each point in the fund transaction map;
and calculating the similarity of each point after the characteristic coding, and clustering the communities according to the similarity of each point.
6. The method of claim 3, wherein the conducting similar customer mining according to the funding transaction graph comprises:
feature encoding each point in the fund transaction map;
and calculating the similarity of each point after the feature coding, and determining similar customers according to the similarity of each point.
7. A customer mining device based on flow direction of funds, the device comprising:
the data acquisition module is used for acquiring basic information of a client, basic information of an account, capital flow direction information and affiliated relationship information;
the data processing module is used for cleaning and processing the customer basic information, the account basic information, the fund flow direction information and the affiliated relationship information;
the map building module is used for building a fund transaction map by taking the customer basic information and the account basic information after the data cleaning and processing as points and the fund flow direction information and the affiliated relationship information after the data cleaning and processing as sides;
and the mining analysis module is used for mining analysis according to the fund transaction map.
8. The apparatus of claim 7, further comprising a product recommendation module for utilizing results of the mining analysis for product recommendation.
9. The apparatus of claim 7, wherein the mining analysis module is further configured to perform at least one of social relationship mining, channel account mining, community mining, and similar customer mining based on the fund transaction graph.
10. The apparatus of claim 9, wherein the mining analysis module comprises: the channel account mining unit is used for determining the single-month fund inflow value and the single-month fund outflow value of the account according to the fund transaction map; and determining the channel account according to the account monthly fund inflow value and the account monthly fund outflow value.
11. The apparatus of claim 9, wherein the mining analysis module further comprises: the community mining unit is used for carrying out community division on the fund transaction map by utilizing a community division mode based on connectivity; feature encoding each point in the fund transaction map; and calculating the similarity of each point after the characteristic coding, and clustering the communities according to the similarity of each point.
12. The apparatus of claim 9, wherein the mining analysis module further comprises: the similar customer mining unit is used for carrying out feature coding on each point in the fund transaction map; and calculating the similarity of each point after the feature coding, and determining similar customers according to the similarity of each point.
13. An electronic 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 one of claims 1 to 6 when executing the program.
14. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010571434.2A CN111767319A (en) | 2020-06-22 | 2020-06-22 | Customer mining method and device based on fund flow direction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010571434.2A CN111767319A (en) | 2020-06-22 | 2020-06-22 | Customer mining method and device based on fund flow direction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111767319A true CN111767319A (en) | 2020-10-13 |
Family
ID=72721461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010571434.2A Pending CN111767319A (en) | 2020-06-22 | 2020-06-22 | Customer mining method and device based on fund flow direction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111767319A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112463893A (en) * | 2020-11-13 | 2021-03-09 | 中科金审(北京)科技有限公司 | Intelligent analysis system and method for network fund |
| CN112967130A (en) * | 2021-03-18 | 2021-06-15 | 中国工商银行股份有限公司 | Method and device for identifying enterprise association relationship |
| CN113379529A (en) * | 2021-06-07 | 2021-09-10 | 广发银行股份有限公司 | Collaborative decision engine application framework |
| CN113538137A (en) * | 2021-07-29 | 2021-10-22 | 中国工商银行股份有限公司 | Capital flow monitoring method and device based on double-spectrum fusion calculation |
| CN113554463A (en) * | 2021-07-21 | 2021-10-26 | 中国农业银行股份有限公司南海分行 | Capital flow direction analysis method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832964A (en) * | 2017-11-21 | 2018-03-23 | 江苏神威云数据科技有限公司 | Bank client relation loop analysis method and system |
-
2020
- 2020-06-22 CN CN202010571434.2A patent/CN111767319A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832964A (en) * | 2017-11-21 | 2018-03-23 | 江苏神威云数据科技有限公司 | Bank client relation loop analysis method and system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112463893A (en) * | 2020-11-13 | 2021-03-09 | 中科金审(北京)科技有限公司 | Intelligent analysis system and method for network fund |
| CN112967130A (en) * | 2021-03-18 | 2021-06-15 | 中国工商银行股份有限公司 | Method and device for identifying enterprise association relationship |
| CN112967130B (en) * | 2021-03-18 | 2024-08-09 | 中国工商银行股份有限公司 | Method and device for identifying enterprise association relationship |
| CN113379529A (en) * | 2021-06-07 | 2021-09-10 | 广发银行股份有限公司 | Collaborative decision engine application framework |
| CN113554463A (en) * | 2021-07-21 | 2021-10-26 | 中国农业银行股份有限公司南海分行 | Capital flow direction analysis method and system |
| CN113538137A (en) * | 2021-07-29 | 2021-10-22 | 中国工商银行股份有限公司 | Capital flow monitoring method and device based on double-spectrum fusion calculation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111767319A (en) | Customer mining method and device based on fund flow direction | |
| KR102322845B1 (en) | Method, device and system for deriving brand marketing strategy based on artificial intelligence | |
| CN111666304B (en) | Data processing device, data processing method, storage medium, and electronic apparatus | |
| CN111951052B (en) | Method and device for acquiring potential clients based on knowledge graph | |
| CN112037038B (en) | Bank credit risk prediction method and device | |
| CN111046192A (en) | Identification method and device for bank case-involved account | |
| CN111695938B (en) | Product pushing method and system | |
| CN111783873B (en) | User portrait method and device based on increment naive Bayes model | |
| CN112070615A (en) | Financial product recommendation method and device based on knowledge graph | |
| CN113034246A (en) | Financial product recommendation method and device | |
| CN110555749B (en) | Credit behavior prediction method and device based on neural network | |
| Münnix et al. | A random matrix approach to credit risk | |
| CN112116454B (en) | Credit evaluation method and device | |
| Ranganathan et al. | Dynamics of investor spanning trees around dot-com bubble | |
| Hosseini et al. | Identifying multi-channel value co-creator groups in the banking industry | |
| CN115409518A (en) | User transaction risk early warning method and device | |
| CN116467525A (en) | Recommendation method, device, equipment and storage medium of business products | |
| Giczi et al. | Official Statistics and Big Data | |
| CN115660814A (en) | Risk prediction method and device, computer readable storage medium and electronic equipment | |
| CN115905472A (en) | Business opportunity service processing method, business opportunity service processing device, business opportunity service processing server and computer readable storage medium | |
| CN116028975A (en) | Data processing and classification prediction method and equipment for logistic regression model | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN112307334A (en) | Information recommendation method, information recommendation device, storage medium and electronic equipment | |
| CN112101950A (en) | Suspicious transaction monitoring model feature extraction method and device | |
| Kondareddy et al. | Incremental response modeling based on segmentation approach using uplift decision trees |
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 |