CN114971912A

CN114971912A - Account characteristic analysis method, system and storage medium in fund transaction

Info

Publication number: CN114971912A
Application number: CN202210760653.4A
Authority: CN
Inventors: 王丰年; 陈明友
Original assignee: Xiamen Meiya Pico Information Co Ltd
Current assignee: Xiamen Meiya Pico Information Co Ltd
Priority date: 2022-06-29
Filing date: 2022-06-29
Publication date: 2022-08-30

Abstract

The application provides an account characteristic analysis method in fund transaction, which comprises the following steps: s1, calculating a feature ratio, namely, obtaining the outflow total amount and the inflow total amount of the account, and calculating the feature ratio, wherein the feature ratio is a feature amount/account flowing total amount, and the feature amount is the account outflow total amount, account inflow total amount or | account inflow total amount-account outflow total amount |; and S2, judging the account characteristics, including: judging the degree of the account according with the characteristics of the fund source account according to the account outflow total amount/account running total amount; judging the degree of the account according with the characteristics of the fund transfer account according to the total amount of account inflow-total amount of account outflow/total amount of account flowing; and judging the degree of the account according with the characteristics of the fund deposition account according to the account inflow total amount/the account running total amount. The invention can effectively and accurately lock the suspicious account from a large amount of data, and is beneficial to quickly tracking the fund source and destination in the fund transaction analysis.

Description

Account characteristic analysis method, system and storage medium in fund transaction

Technical Field

The application belongs to the technical field of data analysis, and particularly relates to an account characteristic analysis method, system and storage medium in fund transaction.

Background

The fund violation may be analyzed from the transaction data of the account. With the rapid development of various technologies such as mobile internet and the like, various transaction means such as fund exchange among various online banks, payment treasures, WeChat and other payment tools are developed, fund transactions among individuals become rapid and various, and the individuals own a plurality of bank cards, so that the daily transaction times and fund amount are increased. The resulting transaction data has become increasingly voluminous as a result of time accumulation. The more transaction data, the more economic behavior of a person can be reflected, but the more difficult the data analyst can extract the characteristics of the transaction account.

In the prior art, an account characteristic analysis method generally analyzes the property of an account only according to transaction amount, is limited to the maximum transaction amount of the account and the maximum transaction times of a specified account within statistical analysis time, or counts the transfer-in frequency, the transfer-out frequency and other characteristics of the account, and manually matches characteristic values of screened accounts according to the characteristics to analyze the transaction habits of the accounts, thereby performing typing judgment on the accounts. The process is inefficient and tedious, and is more difficult to analyze under the conditions of a large amount of account data, cases of different scales, multiple complex bidirectional transfer transactions and the like.

Disclosure of Invention

In order to solve the above problem, the present application provides a method for analyzing account characteristics in a fund transaction, including:

s1, calculating a feature ratio, namely, obtaining the outflow total amount and the inflow total amount of the account, and calculating the feature ratio, wherein the feature ratio is a feature amount/account flowing total amount, and the feature amount is the account outflow total amount, account inflow total amount or | account inflow total amount-account outflow total amount |;

and the number of the first and second groups,

s2, judging the account characteristics, including:

judging the degree of the account according with the characteristics of the fund source account according to the account outflow total amount/the account running total amount;

judging the degree of the account according with the characteristics of the fund transfer account according to the total amount of account inflow-total amount of account outflow/total amount of account flowing;

and the number of the first and second groups,

and judging the degree of the account according with the characteristics of the fund settlement account according to the account inflow total amount/the account running total amount.

The invention designs the characteristic ratio calculated by the method as the basis of account definition and classification based on key information and logic in fund transaction. The method can effectively and accurately lock the suspicious account from a large amount of data, and is favorable for quickly tracking the fund source and destination in the fund transaction analysis.

Preferably, a range of feature ratios is set, and accounts falling within the range are screened as feature accounts.

Further, the method comprises the steps of:

s31, object filtering, wherein the card number, person or organization is used as object filtering data;

s32, data statistics, wherein the statistical data comprises inflow funds, outflow funds and total running amount;

s33, calculating characteristics, namely calculating the characteristic ratio of the fund source, the characteristic ratio of the fund transfer or the characteristic ratio of the fund deposition;

s34, integrating data, matching account and characteristic ratio, and analyzing the transaction record of the account in a designated time period, wherein the transaction record comprises total income funds, total outflow funds and total running amount;

and S35, displaying the result, and displaying the analysis result through a visual interface.

Preferably, the method further comprises the step of constructing a data warehouse, wherein the data acquired in the data statistics step are stored in the data warehouse; the feature calculation and data integration step queries data from the data warehouse. The data warehouse is stored in the memory, and when a user dynamically sets the screening rule, the data is acquired from the data warehouse without acquiring the data from the database for analysis again, so that the rapid analysis of the data such as the characteristic value can be realized, and the analysis time is shortened.

Further, in the visual interface, when the corresponding account is selected, the specific transaction flow details are inquired, so that the original transaction record of the clue can be conveniently found.

In a second aspect, the present invention provides an account characteristic analysis system in fund transaction, including:

the characteristic ratio calculating unit is configured to obtain the outflow total amount and the inflow total amount of the account, and calculate a characteristic ratio, wherein the characteristic ratio is a characteristic amount/account running total amount, and the characteristic amount is the account outflow total amount, the account inflow total amount or | account inflow total amount-account outflow total amount |;

and the number of the first and second groups,

an account characteristic determination unit configured to:

and (c) a second step of,

Further, the system includes:

an object filtering module configured to filter data with a card number, a person, or an organization as an object;

a data statistics module configured to count data including inflow funds, outflow funds, and running total;

a characteristic calculation module configured to calculate the fund source characteristic ratio, the fund transfer characteristic ratio or the fund deposition characteristic ratio;

the data integration module is configured for matching the account and the characteristic ratio and analyzing a transaction record of the account in a specified time period, wherein the transaction record comprises total inflow funds, total outflow funds and total running amount;

preferably, the system further comprises a data warehouse module, and the data warehouse stores the data acquired by the data statistics module.

In a third aspect, the present invention provides a computer readable storage medium for account profiling in funds transactions, having stored thereon one or more computer programs which, when executed by a computer processor, implement any of the methods described above.

The scheme provided by the invention can analyze various fund data, analyze the characteristics of the fund account, infer the type of the account according to the transaction rule, find valuable clues therein and guide analysts to analyze and judge directions in the next step.

Drawings

The accompanying drawings assist in a further understanding of the present application. For convenience of description, only portions related to the related invention are shown in the drawings.

FIG. 1 is a flow diagram of fund transaction data analysis in one embodiment;

FIG. 2 is a diagram illustrating the construction and operation of a data warehouse, according to one embodiment;

FIG. 3 is a diagram illustrating analysis results of a funding source account in an embodiment;

FIG. 4 is a diagram illustrating analysis results of a fund transfer account according to an embodiment;

FIG. 5 is a diagram illustrating results of a funding account analysis in accordance with an embodiment;

FIG. 6 is a diagram of a conditional screening user interface, according to an embodiment;

FIG. 7 is a diagram of a result interface for a feature ratio dimension analysis of a funding source account, under an embodiment;

FIG. 8 is a diagram illustrating a result interface of an analysis of an amount dimension of a transfer account for funds in accordance with an embodiment;

FIG. 9 is a diagram illustrating a result interface of a transaction number dimension analysis for a funds settlement account, in accordance with an embodiment;

FIG. 10 is a diagram illustrating an exemplary system for analyzing account characteristics during a funds transaction;

FIG. 11 is a block diagram of an account profiling system for use in funding transactions, according to an embodiment.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention.

In one embodiment, the billing data is obtained from financial institutions such as banks, imported by the import module provided by the system in this embodiment, and stored in the relational database. The main billing fields are account name, account number, card number, holder, debit/credit mark, access type, transaction time, transaction amount, balance, opponent account name, opponent account number, opponent card issuer, transaction institution, attribution group, etc.

Wherein, part of the related concepts are defined as:

analysis object or attribute of analysis object: the account name, the user card number, the holder, the bank of account, the transaction amount, the balance, the attribution group and other information of the bill;

transaction object or attributes of transaction object: the information of the account name of the opposite side, the card number of the opposite side, the holder of the opposite side, the attribution group of the opposite side, the account opening row of the opposite side card and the like of the bill;

interrelationships or attributes of interrelationships: transaction time, transaction amount, transaction type (roll-in, roll-out);

hierarchical relationship: an upstream card (a card into which an analysis target is transferred), and a downstream card (a card out of which an analysis target is transferred);

dimension of the object: the card number is used as a clue dimension, the man-made object is used as a person dimension, and the organization is used as an object as a group dimension.

Fig. 1 is a flow chart of the fund transaction data analysis in the embodiment, which includes:

object filtering, namely filtering data by taking a card number, a person or an organization as an object;

data statistics, wherein the statistical data comprises inflow fund, outflow fund and total amount of flow;

calculating characteristics, namely calculating the characteristic ratio of the fund source, the characteristic ratio of the fund transfer or the characteristic ratio of the fund deposition;

data integration, namely matching account and characteristic ratios, and analyzing transaction records of the account in a specified time period, wherein the transaction records comprise total income funds, total outflow funds and total running amount;

and displaying the result, namely displaying the analysis result through a visual interface.

In the process, the screening objects are selected by the user, the result data are displayed, and the data are subjected to statistics and calculation in multiple dimensions.

In a specific embodiment, the data warehouse is constructed for storing raw data and calculation results, and the required data set can be directly obtained through query operation on the data warehouse, and fig. 2 is a schematic diagram of the construction and operation process of the data warehouse. The functions of the device comprise:

1) counting all transaction records of the analysis object in a specified time period, wherein the transaction records comprise single maximum transaction, total inflow funds, total outflow funds, total running amount and the like;

2) recording the total number of the analysis objects after the object filtering, and screening out repeated personnel accounts;

3) counting transaction times of each transaction type;

4) analyzing the object upstream card, downstream card and the condition related to the total amount of funds.

In one embodiment, three types of feature ratios are defined to analyze account features:

1) sources of capital

Analyzing the fund transfer-out characteristic according to the fund flow condition, and taking the fund transfer-out characteristic as a fund source account according with the fund source characteristic, wherein the calculation rule of the fund source account is as follows: the feature ratio (N) is outflow total/running total. And default when the characteristic ratio is more than 80%, the account is used as a fund source account. FIG. 3 is a presentation of funding source account analysis results.

2) Transfer of funds

Analyzing the whole characteristics of the fund according to the fund flow condition, and taking the fund as a fund transfer account according with the fund transfer characteristics, wherein the calculation rule of the fund transfer account is as follows: the feature ratio (N) ═ inflow total-outflow total/running water total. And when the feature ratio is less than 5%, the fund transfer account is used as a default. FIG. 4 is a diagram showing the result of the fund transfer account analysis.

3) Capital precipitation

Analyzing the fund transfer characteristics according to the fund flow condition, and taking the fund transfer characteristics as a fund deposition account according with the fund deposition characteristics, wherein the calculation rules of the fund deposition account are as follows: the characteristic ratio (N) is inflow total/running total. And when the feature ratio is greater than 80%, the account is used as a fund settlement account by default. FIG. 5 is a presentation chart of results of a fund deposition account analysis.

The characteristic ratios all support the user to adjust according to actual conditions, and the flexibility and the accuracy of account characteristic analysis are improved.

In a specific embodiment, in consideration of the fact that the requirements of the users for the feature values are greatly different when the requirements of the users are different, condition screening is set on the user interface, and fig. 6 is a schematic diagram of the condition screening user interface in this embodiment.

Fig. 7 is a diagram of a result interface of feature ratio dimension analysis of the fund source account in an embodiment, in this embodiment, with 80% as a set threshold, 123 accounts are actually analyzed, and 2 fund source accounts meeting the features are screened.

Fig. 8 is a result interface diagram of the amount dimension analysis of the fund transfer account in the embodiment, in this embodiment, 97 accounts meeting the fund transfer characteristic ratio are obtained through analysis, and the information of the transfer amount and the transfer-out amount of all the accounts is analyzed and displayed.

Fig. 9 is a result interface diagram of a transaction number dimension analysis of the fund deposit accounts in an embodiment, in this embodiment, 4 accounts meeting the fund deposit feature ratio are obtained through analysis, and information of transfer-in times and transfer-out times of all the accounts is analyzed and displayed.

Fig. 10 is a schematic structural diagram of an account characteristic analysis system 1000 in a fund transaction according to an embodiment, including:

a fund source account analysis unit 1001 configured to search a fund source account, where the fund source account conforms to a fund source characteristic, the fund source characteristic is that a fund source characteristic ratio is greater than a set first threshold, and the fund source characteristic ratio is a total account outflow amount/total account running amount;

a fund transfer account analysis unit 1002, configured to search a fund transfer account, where the fund transfer account meets a fund transfer characteristic, the fund transfer characteristic is that a fund transfer characteristic ratio is smaller than a set second threshold, and the fund transfer characteristic ratio is | a total amount of account inflow — a total amount of account outflow |/a total amount of account running water;

and a fund deposition account analysis unit 1003 configured to search for a fund deposition account, where the fund deposition account conforms to the fund deposition characteristic, the fund deposition characteristic is that a fund deposition characteristic ratio is greater than a set third threshold, and the fund deposition characteristic ratio is a total amount of account inflow/total amount of account running water.

FIG. 11 is a block diagram of an account profiling system 1100 for use in funding transactions, according to an embodiment, including:

an object filtering module 1101 configured to filter data with card numbers, people, or organizations as objects;

a data statistics module 1102 configured to count data including inflow funds, outflow funds, and running total;

a feature calculating module 1103 configured to calculate the fund origin feature ratio, the fund transfer feature ratio, or the fund deposition feature ratio;

and the data integration module 1104 is configured to match the account-to-feature ratios and analyze the transaction records of the accounts in a specified time period, wherein the transaction records comprise total inflow funds, total outflow funds and total running amount.

The invention realizes one-button automatic analysis. The user only needs to select an account to be analyzed, after a program extracts fields representing all characteristics of the transaction in a bill in the background and performs analysis statistics according to a built-in analysis model, all analysis result information is displayed on the same interface in a chart combination mode, an analyst can check the matching degree of the account and the characteristics in characteristic classification, the matching degree range is 0% -100%, 100% is the highest matching degree, and the higher the matching degree is, the account is more consistent with the characteristics. The method is simple to operate and high in analysis efficiency, and in actual measurement, the time spent for analyzing and displaying hundreds of thousands of data is within 1 s.

While this application has been particularly shown and described with references to preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the application as defined by the appended claims.

Claims

1. An account characteristic analysis method in fund transaction is characterized by comprising the following steps:

s1, calculating a feature ratio, obtaining the outflow total amount and the inflow total amount of the account, and calculating the feature ratio, wherein the feature ratio is a feature amount/account flowing total amount, and the feature amount is the account outflow total amount, the account inflow total amount or | account inflow total amount-account outflow total amount |;

and the number of the first and second groups,

s2, judging the account characteristics, including:

and the number of the first and second groups,

2. The method as claimed in claim 1, wherein a range of feature ratios is set, and the accounts falling within the range are screened as feature accounts.

3. The method of claim 1, comprising the steps of:

s34, integrating data, matching the account and the characteristic ratio, and analyzing the transaction records of the account in a specified time period, wherein the transaction records comprise total inflow funds, total outflow funds and total running amount;

4. The method as claimed in claim 3, further comprising constructing a data warehouse, wherein the data warehouse stores the data obtained in the data statistics step.

5. The method of claim 4, wherein the feature calculating and data integrating step queries data from the data repository.

6. The method according to claim 3, wherein the specific transaction flow details are queried when the corresponding account is selected in the visual interface.

7. An account characteristic analysis system in fund transaction, comprising:

and the number of the first and second groups,

an account characteristic determination unit configured to:

and the number of the first and second groups,

8. The system of claim 7, comprising:

and the data integration module is configured for matching the account and the characteristic ratio and analyzing the transaction record of the account in a specified time period, wherein the transaction record comprises total inflow funds, total outflow funds and total running amount.

9. The system of claim 7, further comprising a data warehouse module, wherein the data warehouse module stores the data obtained by the data statistics module.

10. A computer-readable storage medium for account profiling in funds transactions, having one or more computer programs stored thereon, wherein the one or more computer programs, when executed by a computer processor, implement the method of any of claims 1 to 6.