CN117808601B - Capital tracing method and system based on big data - Google Patents
Capital tracing method and system based on big data Download PDFInfo
- Publication number
- CN117808601B CN117808601B CN202410217985.7A CN202410217985A CN117808601B CN 117808601 B CN117808601 B CN 117808601B CN 202410217985 A CN202410217985 A CN 202410217985A CN 117808601 B CN117808601 B CN 117808601B
- Authority
- CN
- China
- Prior art keywords
- transaction
- fund
- user
- fluctuation
- tracing
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims description 35
- 230000000694 effects Effects 0.000 claims description 21
- 238000010586 diagram Methods 0.000 claims description 16
- 238000012546 transfer Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000010365 information processing Effects 0.000 claims description 2
- 230000006399 behavior Effects 0.000 abstract description 15
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000004900 laundering Methods 0.000 description 4
- 230000008520 organization Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a capital tracing method and a system based on big data, in particular to the technical field of big data, and the capital tracing method and the system comprise a multi-source data acquisition module, a data preprocessing module, a capital flow chart database storage module, a data processing module, a capital flow real-time monitoring module, a capital tracing execution module and a tracing result output module; the fund flow chart database storage module is used for storing the preprocessed data and constructing a fund flow chart of a user, so that analysis and tracing of fund paths are facilitated; integrating a plurality of transaction records through a data processing module, and calculating related data, thereby providing deep insight into user behaviors; calculating a risk fluctuation index through a fund flow real-time monitoring module, and sending out alarm information; and receiving the alarm information through a fund tracing execution module, executing the fund tracing operation and generating a fund tracing report, and revealing the complete flow path of the fund and the associated transaction information.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a fund tracing method and a fund tracing system based on big data.
Background
In the current financial field, the flow of funds and transaction data is enormous. To ensure the safety and compliance of funds, efficient monitoring and management of such data is required.
The existing fund tracing methods mainly depend on the traditional database and data processing technology, have low efficiency when processing a large amount of data, and are difficult to realize real-time monitoring and rapid fund tracing; fund tracing generally faces the problems of data island, incomplete information, insufficient analysis capability and the like, so that the fund flow direction cannot be quickly and accurately traced; in addition, the existing fund tracing method often cannot effectively integrate multi-source data, so that the fund flow direction is unclear, and the supervision difficulty is increased; therefore, a method and a system for tracing funds based on big data are urgently needed, which can efficiently process and analyze a large amount of financial data and realize real-time monitoring and rapid tracing of funds.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a large data-based fund tracing method and a large data-based fund tracing system, which are characterized in that transaction data of all users are collected from the fields of banks, securities and insurance finance through a multi-source data collection module, a comprehensive data set is provided for the system, and all possible fund flowing paths can be traced; the data preprocessing module is used for cleaning, de-duplicating and formatting the acquired data and preprocessing the characteristic engineering, so that the quality and consistency of the data are ensured, and accurate and reliable data are provided for analysis; the fund flow chart database storage module is used for storing the preprocessed data and constructing a fund flow chart of a user, so that the fund path can be conveniently analyzed and traced, and the data retrieval process is accelerated; the data processing module integrates a plurality of transaction records, calculates related data, provides deep insight into user behaviors, and is helpful for identifying abnormal modes and risk behaviors; the fund flow is monitored in real time through the fund flow real-time monitoring module, the risk fluctuation index is calculated, the risk fluctuation index is judged and compared with a preset risk fluctuation index threshold value, and alarm information is sent to the fund tracing execution module, so that possible illegal activities or fraudulent behaviors are responded in real time, and loss is reduced; the fund tracing execution module is used for immediately executing the fund tracing operation after receiving the alarm information transmitted by the fund flow real-time monitoring module, searching from the fund flow to the graph database storage module, generating a fund tracing report, revealing the complete flow path of the fund and the associated transaction information, and providing a powerful tool for a supervision institution and a financial institution to fight money laundering and other financial crimes; the traceability result is displayed in a network diagram through the traceability result output module, so that a supervision organization is helped to understand a complex fund relation network and make corresponding decisions, and the targeted supervision measures are helped to be formulated; to solve the problems set forth in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions: a big data based funds traceback system comprising:
a multi-source data acquisition module: for collecting transaction data of all users from banking, securities and insurance finance fields, including personal transfer records, stock transaction records, application records, and consumption records;
And a data preprocessing module: the method is used for cleaning, de-duplicating and formatting the acquired data and performing characteristic engineering pretreatment operation;
the fund flow chart database storage module: the system is used for storing the preprocessed data and constructing a fund flow diagram of the user;
And a data processing module: for carrying out preliminary processing on the preprocessed data at the local server, integrating a plurality of transaction records, calculating the transaction times, average transaction amount, transaction time interval and accumulated transaction amount of each user in a given time window, the number of counter-parties is traded, and the number and the frequency of different transaction types of each user in each time window are transmitted to the fund flow real-time monitoring module;
The fund flow real-time monitoring module comprises a data calculation unit, a risk fluctuation index calculation unit and a risk judgment unit, and is used for carrying out real-time monitoring on fund flow through a real-time data analysis technology, calculating a risk fluctuation index, judging and comparing the risk fluctuation index with a preset risk fluctuation index threshold value, and sending alarm information to be transmitted to a fund tracing execution module;
And the fund tracing execution module: the system comprises a fund flow real-time monitoring module, a fund tracing operation, a diagram database storage module, a fund tracing report, a fund flow real-time monitoring module and a transaction information processing module, wherein the fund flow real-time monitoring module is used for receiving the alarm information transmitted by the fund flow real-time monitoring module, immediately executing the fund tracing operation, retrieving from the fund flow to the diagram database storage module, generating the fund tracing report and revealing the complete flow path of the fund and the associated transaction information;
a traceability result output module: the method is used for displaying the traceability result in a network diagram, helping the supervision authorities understand the complex fund relation network and making corresponding decisions.
In a preferred embodiment, the specific processing procedure of the data processing module is as follows:
A1, dividing the preprocessed data according to n time windows T, and sequentially numbering Mj, j=1, 2,3 … … n;
A2, combining the personal transfer record, the stock trade record, the insurance application record and the consumption record into one record according to all the trade records of the same participant to obtain k trade records of m participants in n time windows; the transaction record comprises transaction time, transaction times, transaction types and transaction amounts;
A3, counting the transaction number of each user in a given time window and recording as Cai;
a4, calculating the average transaction amount Pei of each user in a given time window,
Where k represents the total number of transaction records, zeiv represents the transaction amount of the v-th transaction record for party i, and Cai represents the number of transactions for party i;
A5, counting transaction time intervals Tyi of each user in a given time window;
A6, calculating the accumulated transaction amount Lei of each user in a given time window, Where k represents the total number of transaction records, zeiv represents the transaction amount of the v-th transaction record for party i, and Cai represents the number of transactions for party i;
a7, counting the number of transaction counter-parties of each user in a given time window and recording as Dsi;
A8, counting the number of different transaction types of each user in each time window to be Zsi, calculating the frequency, Where Cai represents the number of transactions by party i.
In a preferred embodiment, the specific calculation process of the fund flow real-time monitoring module is as follows:
B1, calculating transaction liveness, transaction diversity index, average transaction scale and network connectivity;
And B2, calculating a trade activity fluctuation mean value, a trade diversity index fluctuation mean value, an average trade scale fluctuation mean value and a network connectivity fluctuation mean value of each user in all time windows.
In a preferred embodiment, the calculation formula of the transaction activity Hy is: where Cai represents the number of transactions by party i and Tyi represents the transaction time interval for party i;
The calculation formula of the transaction diversity index Dy is as follows: Where pi represents the proportion of the ith transaction type and M represents the type of transaction type;
The calculation formula of the average transaction scale Gm is as follows: Where Cai represents the number of transactions by party i and Lei represents the cumulative transaction amount for party i;
The network connectivity Ld is calculated according to the number of nodes and edges by constructing a network graph, wherein the nodes are users, the edges are transaction relations, and the network connectivity Ld is calculated according to the number of the nodes and the edges: Where Sx represents the number of edges connected to node x and U represents the total number of nodes in the network.
In a preferred embodiment, the transaction liveness fluctuation average PHy has a calculation formula as follows: wherein Hyj represents transaction activity of the user in the j-th time window, hy j+1 represents transaction activity of the user in the j+1th time window, and n represents the number of time windows;
The calculation formula of the trade diversity index fluctuation mean PDy is as follows:
Wherein Dyj represents the transaction diversity index of the user in the j-th time window, dy j+1 represents the transaction diversity index of the user in the j+1th time window, and n represents the number of time windows;
the calculation formula of the fluctuation mean PGm of the average transaction scale is as follows:
Wherein Gmj represents the average trade size of the user in the j-th time window, gm j+1 represents the average trade size of the user in the j+1th time window, and n represents the number of time windows;
the calculation formula of the network connectivity fluctuation mean PLd is as follows: Wherein Ldj represents the network connectivity of the user in the j-th time window, ld j+1 represents the network connectivity of the user in the j+1th time window, and n represents the number of time windows.
In a preferred embodiment, the risk fluctuation index calculation unit is configured to calculate a risk fluctuation index, and the specific calculation process is:
The method comprises the following steps of C1, carrying out standardized processing on a trade activity fluctuation average value, a trade diversity index fluctuation average value, an average trade scale fluctuation average value and a network connectivity fluctuation average value;
C2, calculating a risk fluctuation index Qz according to the standardized fluctuation average value PHy of transaction liveness, the fluctuation average value PDy of transaction diversity index, the fluctuation average value PGm of average transaction scale and the fluctuation average value PLd of network connectivity, Wherein γ1, γ2, γ3, γ4 denote the scaling factors of the individual terms.
In a preferred embodiment, the risk judging unit is configured to judge and compare the risk fluctuation index with a preset risk fluctuation index threshold value, and send alarm information to the fund tracing execution module; judging and comparing the risk fluctuation index Qz with a preset risk fluctuation index threshold Qz, if Qz is more than or equal to the Qz threshold, indicating that the behavior of the user has higher risk, and sending out alarm information; and conversely, the behavior of the user is indicated to have lower risk.
In order to achieve the above purpose, the present invention provides the following technical solutions: a fund tracing method based on big data comprises the following steps:
Step S1, collecting transaction data of all users from the fields of banks, securities and insurance finance;
s2, cleaning, de-duplicating and formatting the acquired data, and preprocessing the characteristic engineering;
Step S3, storing the preprocessed data, and constructing a fund flow chart of the user;
Step S4, the preprocessed data are subjected to preliminary processing at the local server, a plurality of transaction records are integrated, and the transaction times, the average transaction amount, the transaction time interval and the accumulated transaction amount of each user in a given time window and the number of transaction counter parties are calculated, wherein the number and the frequency of different transaction types of each user in each time window are calculated;
s5, calculating a risk fluctuation index, judging and comparing the risk fluctuation index with a preset risk fluctuation index threshold value, and sending out alarm information;
S6, immediately executing fund tracing operation after receiving the alarm information, searching from a fund flow chart database storage module, and generating a fund tracing report;
and S7, displaying the traceability result by using a network diagram.
The invention has the technical effects and advantages that:
The invention collects the transaction data of all users from the fields of banks, securities and insurance finance through the multi-source data collection module, provides a comprehensive data set for the system, and ensures that all possible funds flow paths can be tracked; the data preprocessing module is used for cleaning, de-duplicating and formatting the acquired data and preprocessing the characteristic engineering, so that the quality and consistency of the data are ensured, and accurate and reliable data are provided for analysis; the fund flow chart database storage module is used for storing the preprocessed data and constructing a fund flow chart of a user, so that the fund path can be conveniently analyzed and traced, and the data retrieval process is accelerated; the data processing module integrates a plurality of transaction records, calculates related data, provides deep insight into user behaviors, and is helpful for identifying abnormal modes and risk behaviors; the fund flow is monitored in real time through the fund flow real-time monitoring module, the risk fluctuation index is calculated, the risk fluctuation index is judged and compared with a preset risk fluctuation index threshold value, and alarm information is sent to the fund tracing execution module, so that possible illegal activities or fraudulent behaviors are responded in real time, and loss is reduced; the fund tracing execution module is used for immediately executing the fund tracing operation after receiving the alarm information transmitted by the fund flow real-time monitoring module, searching from the fund flow to the graph database storage module, generating a fund tracing report, revealing the complete flow path of the fund and the associated transaction information, and providing a powerful tool for a supervision institution and a financial institution to fight money laundering and other financial crimes; the traceability result is displayed in a network diagram through the traceability result output module, so that a supervision organization is helped to understand a complex fund relation network and make corresponding decisions, and the targeted supervision measures are helped to be formulated; the invention can meet the requirements of the modern financial field on fund flow monitoring and tracing, and has high practical value and market prospect.
Drawings
Fig. 1 is a block diagram showing the overall structure of the present invention.
FIG. 2 is a flow chart of the method steps of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides a large data-based fund tracing method and a large data-based fund tracing system as shown in fig. 1-2, wherein the large data-based fund tracing method and the large data-based fund tracing system comprise a multi-source data acquisition module, a data preprocessing module, a fund flow chart database storage module, a data processing module, a fund flow real-time monitoring module, a fund tracing execution module and a tracing result output module;
The multi-source data acquisition module is used for acquiring transaction data of all users from the fields of banks, securities and insurance finance, including personal account transfer records, stock transaction records, application records and consumption records; the personal transfer record comprises a transaction participant, an account number, a transfer amount and a transfer time; the stock transaction record comprises transaction price, transaction quantity, transaction time, number of holding houses and a profit and loss ratio; the insurance application records comprise the name of the insurance applicant, the insurance date, the insurance amount, the premium amount, the claim settlement amount and the claim settlement time; the consumption record includes a consumption type and a consumption amount;
the implementation needs to specifically explain that the acquisition mode of the multi-source data acquisition module is as follows: the collection of sensitive financial data of personal account transfer records, stock trade records and application records is realized by interfacing with systems of banks, securities and insurance financial institutions; the method comprises the steps of cooperating with a related consumption record provider, and acquiring consumption records through a data interface;
The data preprocessing module is used for cleaning, de-duplicating, formatting and characteristic engineering preprocessing operation on the acquired data so as to ensure the quality and consistency of the data and provide a reliable data basis for subsequent analysis; the operations of cleaning, de-duplication, formatting and preprocessing of the feature engineering are performed on the collected data, which belong to the prior art means, so the embodiment does not make a specific description;
The fund flow chart database storage module is used for storing the preprocessed data and constructing a fund flow chart of a user; wherein the construction of the fund flow diagram, in particular converting the transaction data into a graphic structure, the nodes representing transaction entities, such as users, bank accounts and securities accounts, the edges representing the fund flow;
It should be noted that the fund flow chart database storage module performs structured storage on the processed data so as to facilitate quick retrieval and analysis; by constructing a fund flow graph, the flow path of the user asset, including the source, destination, amount and time information of the funds, can be helped to be revealed;
the data processing module is used for carrying out preliminary processing on the preprocessed data at the local server, integrating a plurality of transaction records, calculating the transaction times, the average transaction amount, the transaction time interval and the accumulated transaction amount of each user in a given time window and the number of transaction counter parties, and transmitting the number and the frequency of different transaction types of each user in each time window to the fund flow real-time monitoring module;
the implementation needs to specifically explain that the specific processing procedure of the data processing module is as follows:
A1, dividing the preprocessed data according to n time windows T, and sequentially numbering Mj, j=1, 2,3 … … n;
A2, combining the personal transfer record, the stock trade record, the insurance application record and the consumption record into one record according to all the trade records of the same participant to obtain k trade records of m participants in n time windows; the transaction record comprises transaction time, transaction times, transaction types and transaction amounts;
A3, counting the transaction number of each user in a given time window and recording as Cai;
a4, calculating the average transaction amount Pei of each user in a given time window,
Where k represents the total number of transaction records, zeiv represents the transaction amount of the v-th transaction record for party i, and Cai represents the number of transactions for party i;
A5, counting transaction time intervals Tyi of each user in a given time window;
A6, calculating the accumulated transaction amount Lei of each user in a given time window, Where k represents the total number of transaction records, zeiv represents the transaction amount of the v-th transaction record of party i, and Cai represents the number of transactions of party i to analyze the trend of the user's transaction increase;
A7, counting the number of transaction counter-parties of each user in a given time window and recording as Dsi so as to analyze the transaction network and the associated party of the user;
A8, counting the number of different transaction types of each user in each time window to be Zsi, calculating the frequency, Where Cai represents the number of transactions by party i;
The fund flow real-time monitoring module comprises a data calculation unit, a risk fluctuation index calculation unit and a risk judgment unit, and is used for monitoring the fund flow in real time through a real-time data analysis technology, calculating a risk fluctuation index, judging and comparing the risk fluctuation index with a preset risk fluctuation index threshold value, and sending alarm information to be transmitted to a fund tracing execution module;
The implementation needs to be specifically described, the data calculation unit is configured to calculate a transaction activity fluctuation average value, a transaction diversity index fluctuation average value, an average transaction scale fluctuation average value, and a network connectivity fluctuation average value of each user in all time windows, where the specific calculation process is as follows:
B1, calculating transaction liveness, transaction diversity index, average transaction scale and network connectivity;
the calculation formula of the transaction liveness Hy is as follows: Where Cai represents the number of transactions by party i and Tyi represents the transaction time interval for party i; by analyzing the transaction liveness of an individual, nodes that are frequently transacted may be identified, which may be important monitoring objects, particularly where funds flow is rapid and frequent, abnormally high liveness may indicate a risk of money laundering or other illegal funds flow;
The calculation formula of the transaction diversity index Dy is as follows: Where pi represents the proportion of the ith transaction type and M represents the type of transaction type; the diversified transaction types may suggest that the user is conducting normal business, while abrupt changes or singularization of the transaction types may be directed to behavior that circumvents supervision; lack of transaction diversity may indicate that funds are used for specific illegal purposes or from specific criminal activities;
The calculation formula of the average transaction scale Gm is as follows: Where Cai represents the number of transactions by party i and Lei represents the cumulative transaction amount for party i; high volume transactions may be of concern, particularly if the normal transaction patterns of the individual are not met; for funds traceback, analysis of the average transaction size helps identify focused flows of funds and abnormal transfers of large funds;
The network connectivity Ld is calculated according to the number of nodes and edges by constructing a network graph, wherein the nodes are users, the edges are transaction relations, and the network connectivity Ld is calculated according to the number of the nodes and the edges: Where Sx represents the number of edges connected to node x and U represents the total number of nodes in the network; the numerical value measures the direct contact quantity of one node and other nodes and reflects the activity degree and influence of the node in the network; in the background of fund tracing, the network connectivity reveals the degree of association between individuals and other individuals, which is helpful for drawing potential collusion networks or organization structures; highly connected nodes may play a critical role in the funding flow network and are therefore important for monitoring and investigation;
B2, calculating a trade activity fluctuation mean value, a trade diversity index fluctuation mean value, an average trade scale fluctuation mean value and a network connectivity fluctuation mean value of each user in all time windows;
The calculation formula of the transaction liveness fluctuation mean PHy is as follows: Wherein Hyj represents transaction activity of the user in the j-th time window, hy j+1 represents transaction activity of the user in the j+1th time window, and n represents the number of time windows; this value indicates the stability of the user's transaction frequency, and high volatility may indicate a discrepancy with normal business activity;
The calculation formula of the trade diversity index fluctuation mean PDy is as follows:
Wherein Dyj represents the transaction diversity index of the user in the j-th time window, dy j+1 represents the transaction diversity index of the user in the j+1th time window, and n represents the number of time windows; this value reflects the diversity and variability of user transaction types, which may be evidence of manipulation or fraud if one user typically makes multiple types of transactions, but only a few transactions between bursts;
the calculation formula of the fluctuation mean PGm of the average transaction scale is as follows:
Wherein Gmj represents the average trade size of the user in the j-th time window, gm j+1 represents the average trade size of the user in the j+1th time window, and n represents the number of time windows; the value displays the change degree of the transaction amount of the user, and the stable transaction scale possibly accords with the conventional business mode;
the calculation formula of the network connectivity fluctuation mean PLd is as follows: wherein Ldj represents the network connectivity of the user in the j-th time window, ld j+1 represents the network connectivity of the user in the j+1th time window, and n represents the number of time windows; frequently varying connectivity may indicate that a user is attempting to avoid being tracked or conducting suspicious transactions with multiple different individuals;
it should be noted that the mean value of these fluctuations is meant to help identify users whose behavior patterns are inconsistent or do not conform to normal business behavior, and in the funds tracing system, such behavior inconsistencies may be illegal activities, such as money laundering and fraudulent indicators, by monitoring fluctuations in these indicators, financial institutions and regulatory authorities can more effectively identify and prevent potential financial crimes, while improving transparency and compliance of the system;
the implementation needs to specifically explain that the risk fluctuation index calculating unit is used for calculating a risk fluctuation index, and the specific calculating process is as follows:
c1, carrying out standardized processing on a trade activity fluctuation mean value, a trade diversity index fluctuation mean value, an average trade scale fluctuation mean value and a network connectivity fluctuation mean value so as to ensure that comparison can be carried out on the same scale; the normalization processing belongs to the prior art means, so the embodiment does not make a specific description;
C2, calculating a risk fluctuation index Qz according to the standardized fluctuation average value PHy of transaction liveness, the fluctuation average value PDy of transaction diversity index, the fluctuation average value PGm of average transaction scale and the fluctuation average value PLd of network connectivity, Wherein γ1, γ2, γ3 and γ4 represent the proportionality coefficients of the terms, the size of the proportionality coefficients is a specific numerical value obtained by quantizing each parameter, the subsequent comparison is convenient, and the proportionality coefficients are only required to have no influence on the proportionality relationship between the parameters and the quantized numerical value;
the implementation needs to be specifically explained, the risk judging unit is used for judging and comparing the risk fluctuation index with a preset risk fluctuation index threshold value, and sending alarm information to the fund tracing execution module; judging and comparing the risk fluctuation index Qz with a preset risk fluctuation index threshold Qz, if Qz is more than or equal to the Qz threshold, indicating that the behavior of the user has higher risk, and sending out alarm information; otherwise, the behavior of the user is indicated to have lower risk; the preset risk fluctuation index threshold Qz can be set specifically according to specific conditions, and specific data are not limited specifically in the embodiment;
the fund tracing execution module is used for immediately executing the fund tracing operation after receiving the alarm information transmitted by the fund flow real-time monitoring module, retrieving the fund flow from the fund flow chart storage module, generating a fund tracing report and revealing the complete flow path of the fund and the associated transaction information; the fund tracing report records detailed information of each fund transaction, including the amount, time, both transaction sides and inflow and outflow nodes of the fund;
the traceability result output module is used for displaying traceability results in a network diagram, helping a supervision organization to understand a complex fund relation network and making corresponding decisions;
In this embodiment, it needs to be specifically described that a funds tracing method based on big data includes the following steps:
Step S1, collecting transaction data of all users from the fields of banks, securities and insurance finance;
s2, cleaning, de-duplicating and formatting the acquired data, and preprocessing the characteristic engineering;
Step S3, storing the preprocessed data, and constructing a fund flow chart of the user;
Step S4, the preprocessed data are subjected to preliminary processing at the local server, a plurality of transaction records are integrated, and the transaction times, the average transaction amount, the transaction time interval and the accumulated transaction amount of each user in a given time window and the number of transaction counter parties are calculated, wherein the number and the frequency of different transaction types of each user in each time window are calculated;
s5, calculating a risk fluctuation index, judging and comparing the risk fluctuation index with a preset risk fluctuation index threshold value, and sending out alarm information;
S6, immediately executing fund tracing operation after receiving the alarm information, searching from a fund flow chart database storage module, and generating a fund tracing report;
and S7, displaying the traceability result by using a network diagram.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (5)
1. A big data based funds traceback system comprising:
a multi-source data acquisition module: for collecting transaction data of all users from banking, securities and insurance finance fields, including personal transfer records, stock transaction records, application records, and consumption records;
And a data preprocessing module: the method is used for cleaning, de-duplicating and formatting the acquired data and performing characteristic engineering pretreatment operation;
the fund flow chart database storage module: the system is used for storing the preprocessed data and constructing a fund flow diagram of the user;
And a data processing module: for carrying out preliminary processing on the preprocessed data at the local server, integrating a plurality of transaction records, calculating the transaction times, average transaction amount, transaction time interval and accumulated transaction amount of each user in a given time window, the number of counter-parties is traded, and the number and the frequency of different transaction types of each user in each time window are transmitted to the fund flow real-time monitoring module;
The fund flow real-time monitoring module comprises a data calculation unit, a risk fluctuation index calculation unit and a risk judgment unit, and is used for carrying out real-time monitoring on fund flow through a real-time data analysis technology, calculating a risk fluctuation index, judging and comparing the risk fluctuation index with a preset risk fluctuation index threshold value, and sending alarm information to be transmitted to a fund tracing execution module;
the specific calculation process of the fund flow real-time monitoring module is as follows:
B1, calculating transaction liveness, transaction diversity index, average transaction scale and network connectivity;
B2, calculating a trade activity fluctuation mean value, a trade diversity index fluctuation mean value, an average trade scale fluctuation mean value and a network connectivity fluctuation mean value of each user in all time windows;
the calculation formula of the transaction liveness Hy is as follows: where Cai represents the number of transactions by party i and Tyi represents the transaction time interval for party i;
The calculation formula of the transaction diversity index Dy is as follows: Where pi represents the proportion of the ith transaction type and M represents the type of transaction type;
The calculation formula of the average transaction scale Gm is as follows: Where Cai represents the number of transactions by party i and Lei represents the cumulative transaction amount for party i;
The network connectivity Ld is calculated according to the number of nodes and edges by constructing a network graph, wherein the nodes are users, the edges are transaction relations, and the network connectivity Ld is calculated according to the number of the nodes and the edges: Where Sx represents the number of edges connected to node x and U represents the total number of nodes in the network;
The calculation formula of the transaction liveness fluctuation mean PHy is as follows: wherein Hyj represents transaction activity of the user in the j-th time window, hy j+1 represents transaction activity of the user in the j+1th time window, and n represents the number of time windows;
The calculation formula of the trade diversity index fluctuation mean PDy is as follows:
Wherein Dyj represents the transaction diversity index of the user in the j-th time window, dy j+1 represents the transaction diversity index of the user in the j+1th time window, and n represents the number of time windows;
the calculation formula of the fluctuation mean PGm of the average transaction scale is as follows:
Wherein Gmj represents the average trade size of the user in the j-th time window, gm j+1 represents the average trade size of the user in the j+1th time window, and n represents the number of time windows;
the calculation formula of the network connectivity fluctuation mean PLd is as follows: Wherein Ldj represents the network connectivity of the user in the j-th time window, ld j+1 represents the network connectivity of the user in the j+1th time window, and n represents the number of time windows;
And the fund tracing execution module: the system comprises a fund flow real-time monitoring module, a fund tracing operation, a diagram database storage module, a fund tracing report, a fund flow real-time monitoring module and a transaction information processing module, wherein the fund flow real-time monitoring module is used for receiving the alarm information transmitted by the fund flow real-time monitoring module, immediately executing the fund tracing operation, retrieving from the fund flow to the diagram database storage module, generating the fund tracing report and revealing the complete flow path of the fund and the associated transaction information;
a traceability result output module: the method is used for displaying the traceability result in a network diagram, helping the supervision authorities understand the complex fund relation network and making corresponding decisions.
2. A big data based funds traceback system as defined in claim 1, wherein:
The specific processing procedure of the data processing module is as follows:
A1, dividing the preprocessed data according to n time windows T, and sequentially numbering Mj, j=1, 2,3 … … n;
A2, combining the personal transfer record, the stock trade record, the insurance application record and the consumption record into one record according to all the trade records of the same participant to obtain k trade records of m participants in n time windows; the transaction record comprises transaction time, transaction times, transaction types and transaction amounts;
A3, counting the transaction number of each user in a given time window and recording as Cai;
a4, calculating the average transaction amount Pei of each user in a given time window,
Where k represents the total number of transaction records, zeiv represents the transaction amount of the v-th transaction record for party i, and Cai represents the number of transactions for party i;
A5, counting transaction time intervals Tyi of each user in a given time window;
A6, calculating the accumulated transaction amount Lei of each user in a given time window, Where k represents the total number of transaction records, zeiv represents the transaction amount of the v-th transaction record for party i, and Cai represents the number of transactions for party i;
a7, counting the number of transaction counter-parties of each user in a given time window and recording as Dsi;
A8, counting the number of different transaction types of each user in each time window to be Zsi, calculating the frequency, Where Cai represents the number of transactions by party i.
3. A big data based funds traceback system as defined in claim 1, wherein: the risk fluctuation index calculation unit is used for calculating a risk fluctuation index, and the specific calculation process is as follows:
The method comprises the following steps of C1, carrying out standardized processing on a trade activity fluctuation average value, a trade diversity index fluctuation average value, an average trade scale fluctuation average value and a network connectivity fluctuation average value;
C2, calculating a risk fluctuation index Qz according to the standardized fluctuation average value PHy of transaction liveness, the fluctuation average value PDy of transaction diversity index, the fluctuation average value PGm of average transaction scale and the fluctuation average value PLd of network connectivity, Wherein γ1, γ2, γ3, γ4 denote the scaling factors of the individual terms.
4. A big data based funds traceback system as defined in claim 1, wherein: the risk judging unit is used for judging and comparing the risk fluctuation index with a preset risk fluctuation index threshold value, sending alarm information and transmitting the alarm information to the fund tracing execution module; judging and comparing the risk fluctuation index Qz with a preset risk fluctuation index threshold Qz, if Qz is more than or equal to the Qz threshold, indicating that the behavior of the user has higher risk, and sending out alarm information; and conversely, the behavior of the user is indicated to have lower risk.
5. A big data based funds tracing method for implementing the big data based funds tracing system of any one of claims 1-4, comprising the steps of:
Step S1, collecting transaction data of all users from the fields of banks, securities and insurance finance;
s2, cleaning, de-duplicating and formatting the acquired data, and preprocessing the characteristic engineering;
Step S3, storing the preprocessed data, and constructing a fund flow chart of the user;
Step S4, the preprocessed data are subjected to preliminary processing at the local server, a plurality of transaction records are integrated, and the transaction times, the average transaction amount, the transaction time interval and the accumulated transaction amount of each user in a given time window and the number of transaction counter parties are calculated, wherein the number and the frequency of different transaction types of each user in each time window are calculated;
s5, calculating a risk fluctuation index, judging and comparing the risk fluctuation index with a preset risk fluctuation index threshold value, and sending out alarm information;
S6, immediately executing fund tracing operation after receiving the alarm information, searching from a fund flow chart database storage module, and generating a fund tracing report;
and S7, displaying the traceability result by using a network diagram.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410217985.7A CN117808601B (en) | 2024-02-28 | 2024-02-28 | Capital tracing method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410217985.7A CN117808601B (en) | 2024-02-28 | 2024-02-28 | Capital tracing method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117808601A CN117808601A (en) | 2024-04-02 |
| CN117808601B true CN117808601B (en) | 2024-05-24 |
Family
ID=90425849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410217985.7A Active CN117808601B (en) | 2024-02-28 | 2024-02-28 | Capital tracing method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808601B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015088037A (en) * | 2013-10-31 | 2015-05-07 | 株式会社日立ソリューションズ | Fund flow analysis device and method |
| CN104867055A (en) * | 2015-06-16 | 2015-08-26 | 咸宁市公安局 | Financial network doubtable money tracking and identifying method |
| CN109919608A (en) * | 2018-11-28 | 2019-06-21 | 阿里巴巴集团控股有限公司 | A kind of recognition methods, device and the server of high-risk transaction agent |
| JP2021149505A (en) * | 2020-03-19 | 2021-09-27 | 株式会社クリプタクト | Information processing system and information providing method |
| CN114119026A (en) * | 2022-01-26 | 2022-03-01 | 成都无糖信息技术有限公司 | Virtual currency transaction tracking and tracing method and system |
| CN114493864A (en) * | 2022-01-04 | 2022-05-13 | 中科金审(北京)科技有限公司 | Capital big data based anomaly detection system and method |
| CN114819965A (en) * | 2021-01-21 | 2022-07-29 | 成都链安科技有限公司 | Block chain virtual currency monitoring system |
| CN115439030A (en) * | 2022-11-09 | 2022-12-06 | 山东民昊健康科技有限公司 | Capital and current information management system based on big data analysis |
| CN115631042A (en) * | 2022-10-29 | 2023-01-20 | 复旦大学 | Account model block chain oriented risk transaction detection method |
| CN115631039A (en) * | 2019-09-26 | 2023-01-20 | 支付宝(杭州)信息技术有限公司 | Fund tracking method, device and equipment |
| WO2023109116A1 (en) * | 2021-12-14 | 2023-06-22 | 同济大学 | Rapid anti-money laundering detection method based on transaction graph |
| CN116957598A (en) * | 2023-06-02 | 2023-10-27 | 华侨大学 | Suspicious fund flow direction tracing method and system based on path bundles |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030233319A1 (en) * | 2001-03-20 | 2003-12-18 | David Lawrence | Electronic fund transfer participant risk management clearing |
-
2024
- 2024-02-28 CN CN202410217985.7A patent/CN117808601B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015088037A (en) * | 2013-10-31 | 2015-05-07 | 株式会社日立ソリューションズ | Fund flow analysis device and method |
| CN104867055A (en) * | 2015-06-16 | 2015-08-26 | 咸宁市公安局 | Financial network doubtable money tracking and identifying method |
| CN109919608A (en) * | 2018-11-28 | 2019-06-21 | 阿里巴巴集团控股有限公司 | A kind of recognition methods, device and the server of high-risk transaction agent |
| CN115631039A (en) * | 2019-09-26 | 2023-01-20 | 支付宝(杭州)信息技术有限公司 | Fund tracking method, device and equipment |
| JP2021149505A (en) * | 2020-03-19 | 2021-09-27 | 株式会社クリプタクト | Information processing system and information providing method |
| CN114819965A (en) * | 2021-01-21 | 2022-07-29 | 成都链安科技有限公司 | Block chain virtual currency monitoring system |
| WO2023109116A1 (en) * | 2021-12-14 | 2023-06-22 | 同济大学 | Rapid anti-money laundering detection method based on transaction graph |
| CN114493864A (en) * | 2022-01-04 | 2022-05-13 | 中科金审(北京)科技有限公司 | Capital big data based anomaly detection system and method |
| CN114119026A (en) * | 2022-01-26 | 2022-03-01 | 成都无糖信息技术有限公司 | Virtual currency transaction tracking and tracing method and system |
| CN115631042A (en) * | 2022-10-29 | 2023-01-20 | 复旦大学 | Account model block chain oriented risk transaction detection method |
| CN115439030A (en) * | 2022-11-09 | 2022-12-06 | 山东民昊健康科技有限公司 | Capital and current information management system based on big data analysis |
| CN116957598A (en) * | 2023-06-02 | 2023-10-27 | 华侨大学 | Suspicious fund flow direction tracing method and system based on path bundles |
Non-Patent Citations (3)
| Title |
|---|
| TRacer: Scalable Graph-Based Transaction Tracing for Account-Based Blockchain Trading Systems;Wu, ZY等;《IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY》;20230612;第18卷;全文 * |
| 商业银行资金异常识别研究;刘璇;张朋柱;李嘉;陈智高;;系统管理学报;20130515(第03期);全文 * |
| 基于互联网金融的反洗钱模型探索;王达山;;金融电子化;20160315(03);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117808601A (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109461078B (en) | Abnormal transaction identification method and system based on fund transaction network | |
| CN109948704A (en) | A kind of transaction detection method and apparatus | |
| CN110852878B (en) | Credibility determination method, device, equipment and storage medium | |
| CN101236638A (en) | Web based bank card risk monitoring method and system | |
| CN111476660A (en) | Intelligent wind control system and method based on data analysis | |
| CN112116464B (en) | Abnormal transaction behavior analysis method and system based on event sequence frequent item set | |
| CN111553563A (en) | Method and device for determining enterprise fraud risk | |
| CN110675078A (en) | Marketing company risk diagnosis method, system, computer terminal and storage medium | |
| Zhang et al. | A study on SMIE credit evaluation model based on blockchain technology | |
| CN112581270A (en) | Risk account identification method and device, electronic equipment and storage medium | |
| CN117829994A (en) | Money laundering risk analysis method based on graph calculation | |
| CN117808601B (en) | Capital tracing method and system based on big data | |
| CN109919667A (en) | A kind of method and apparatus of the IP of enterprise for identification | |
| CN108198073A (en) | Management method and system after a kind of throwing of stock right financing | |
| KR20210155501A (en) | Receivable recovery support system for medium-small enterprise account receivable bond decrease and bad debt prevention based on big data | |
| KR101710649B1 (en) | System for providing evaluation service of enterprise value by automated network deduction | |
| CN109360085A (en) | A kind of bank client responsible investigation method and system | |
| CN115689564A (en) | Online payment information security management system and method based on big data | |
| CN114971912A (en) | Account characteristic analysis method, system and storage medium in fund transaction | |
| CN114493864A (en) | Capital big data based anomaly detection system and method | |
| CN114529402A (en) | Credit management method, device and medium based on big data wind control | |
| CN110738570A (en) | Information type manipulation automatic identification method based on multi-channel heterogeneous data | |
| Salhi et al. | Alarm system for credit losses impairment under IFRS 9 | |
| CN117688055B (en) | Insurance black product identification and response system based on correlation network analysis technology | |
| KR102566466B1 (en) | Alternative Credit Rating System for Evaluating Personal Credit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |