CN115271926A - Financial big data automatic intelligent analysis control system and method based on cloud computing - Google Patents
Financial big data automatic intelligent analysis control system and method based on cloud computing Download PDFInfo
- Publication number
- CN115271926A CN115271926A CN202210931716.8A CN202210931716A CN115271926A CN 115271926 A CN115271926 A CN 115271926A CN 202210931716 A CN202210931716 A CN 202210931716A CN 115271926 A CN115271926 A CN 115271926A
- Authority
- CN
- China
- Prior art keywords
- data
- financial
- account
- risk
- monitoring
- 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
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
Abstract
The invention discloses a financial big data automatic intelligent analysis control system and method based on cloud computing, belonging to the field of data automatic analysis control; the method comprises the steps of obtaining monitoring values by performing simultaneous integration on transaction data of accounts in different monitoring periods, analyzing the overall condition of account transaction based on the monitoring values and classifying to obtain target objects and non-target objects, and performing differentiated automatic analysis on accounts with different transaction risks by classifying; monitoring and counting financial transaction information sources through financial software, providing reliable data support for automatic intelligent analysis of financial big data based on data in the aspect of conversation, and realizing automatic intelligent analysis and control of financial big data from different dimensionalities by performing simultaneous integration on risk weight in the aspect of conversation and data in the aspect of subsequent transaction transfer; the method is used for solving the technical problem that the whole effect of automatic analysis and control of the financial big data in the existing scheme is poor.
Description
Technical Field
The invention relates to the field of data automatic analysis control, in particular to a financial big data automatic intelligent analysis control system and method based on cloud computing.
Background
Big data finance is based on cloud computing, and the cloud computing is an ultra-large-scale distributed computing technology; through a preset program, the big data financial cloud computing can search, compute and analyze various data of a client; the automatic analysis of the financial big data is beneficial to the data demand party to analyze the credit state of the other party in time and control and prevent the transaction risk.
When an existing financial big data automatic analysis control scheme is implemented, training and assessment are generally carried out through an algorithm model, risks possibly existing are evaluated, early warning prompt is carried out, or the existing financial risks are assessed and controlled manually through experience, objects of financial big data are not classified to achieve differentiated monitoring analysis, and information sources of financial transactions are not monitored and traced, so that monitoring analysis of the financial big data is incomplete, and the overall effect of automatic analysis and control of the financial big data is influenced.
Disclosure of Invention
The invention aims to provide a financial big data automatic intelligent analysis control system and method based on cloud computing, which are used for solving the technical problem that the overall effect of financial big data automatic analysis and control in the existing scheme is poor.
The purpose of the invention can be realized by the following technical scheme:
the financial big data automatic intelligent analysis control system based on cloud computing comprises a financial back end; the financial back end comprises an account evaluation module, a behavior mining module and an analysis control module;
the account evaluation module is used for screening the target objects and comprises the following steps:
in a preset monitoring period, acquiring the transaction condition of each account, and monitoring in real time to obtain transaction monitoring data, wherein the transaction monitoring data comprises the collection amount, the collection times, the payment account, the withdrawal amount, the withdrawal times and the withdrawal account at different moments of the account;
when the feature extraction and the marking calculation are carried out on the transaction monitoring data, the time interval weight corresponding to the monitoring time interval is obtained and marked as SQ;
respectively marking the collection amount, the collection times, the withdrawal amount and the withdrawal times in the monitoring time period as SJ, SC, CJ and CC;
obtaining a payment account and carrying out risk evaluation to obtain corresponding risk weights and marking the risk weights as DQ and CQ;
extracting numerical values of all marked data, performing simultaneous operation, and calculating to obtain a monitoring value JG corresponding to the account through a formula; the formula is:
in the formula, j1 and j2 are different proportionality coefficients, j1 is more than 0 and less than j2, when the corresponding accounts are classified according to the monitored value JG, the account corresponding to the monitored value JG which is more than the monitored threshold value is set as a target object, and the monitoring times of the account are increased by one;
the behavior mining module is used for preprocessing and mining information source data in the monitored financial monitoring set to obtain a data mining set;
the analysis control module is used for tracking the financial behavior of the marked object according to the data mining set to obtain a data tracking set, and dynamically controlling the financial behavior of the marked object according to the data tracking set.
Preferably, the step of performing a risk assessment comprises:
respectively matching the debit account and the debit account with a blacklist account marked in a pre-constructed risk database, and setting a risk label corresponding to the debit account or the debit account as a first level if the debit account or the debit account belongs to the blacklist account marked in the risk database;
if the payment account or the withdrawal account belongs to the first transaction, setting the risk label corresponding to the payment account or the withdrawal account as a second level;
if the account for making a money or the account for drawing a money belongs to a non-primary transaction or a public account, setting a risk label corresponding to the account for making a money or the account for drawing a money as a third level;
the transaction risks corresponding to the first-level label, the second-level label and the third-level label are sequentially reduced, and a corresponding risk weight is associated with each label.
Preferably, the preprocessing and mining of the information source data in the financial monitoring set includes:
extracting and marking the characteristics of the information source data in the financial monitoring set;
acquiring the call type of a call party, setting different call types to correspond to a different call type value, and matching the acquired call type with all the call types to acquire a corresponding call type value;
matching the call type value with a preset call type threshold, and if the call type value is greater than the call type threshold, setting a corresponding call type label to be 1; otherwise, setting the corresponding call type label to 0; and mark the call type label as TL.
Preferably, the call duration is counted and matched with a preset call duration threshold, if the pass duration is greater than the pass duration threshold, the corresponding call duration label is set to 1, otherwise, the corresponding call duration label is set to 0; marking the call duration label as TS;
respectively acquiring call type weights and call duration weights corresponding to the call type labels and the call duration labels, and respectively marking the call type weights and the call duration weights as T1 and T2;
and mining and analyzing the relation among the marked data to obtain a data mining set.
Preferably, the relationship between the marked items of data is mined and analyzed, including:
extracting numerical values corresponding to various data of the marks, and calculating and combining the numerical values through a formula WG = T1 xTL + T2 xTS to obtain a clearance value WG; and when the potential financial risk of the call object is analyzed according to the clearance threshold value WG, matching evaluation is carried out on the clearance threshold value WG and a preset clearance threshold value WGY.
Preferably, if the dig-close value WG < dig-close threshold value WGY, determining that the potential financial risk of the call object is low and generating a wind-low signal;
if the cut-off threshold value WGY is not less than the cut-off threshold value WGY x k%, and k is a real number larger than one hundred, determining that the potential financial risk of the call object is medium, generating a wind signal, and performing primary risk marking on the identity of the call object according to the wind signal;
if the cut-off value WG is larger than a cut-off threshold value WGY x k%, judging that the potential financial risk of the call object is high, generating a wind height signal, and carrying out secondary risk marking on the identity of the call object according to the wind height signal;
the wind low signal, the wind medium signal and the first-level risk flag, the wind high signal and the second-level risk flag form a data mining set.
Preferably, tracking the financial behavior of the tagged object according to the data mining set comprises:
tracking the financial behavior of a call object in a preset tracking time period according to wind signals and wind height signals in the data mining set;
acquiring a transfer amount and a transfer account of a call object in a preset tracking period; extracting the value of the transfer amount and marking as ZJ; acquiring a risk weight corresponding to the transfer account and marking the risk weight as FQ;
acquiring risk weights JQ corresponding to risk marks of different levels; combining the marked data and calculating by a formula JK = JQ x (g 1 XZJ + g2 XFQ) to obtain an intersection control value JK; wherein g1 and g2 are different proportionality coefficients and 1 < g2.
Preferably, the transaction corresponding to the traffic control value larger than the traffic control threshold value is judged as a risk transaction and a control instruction is generated; judging the transaction corresponding to the traffic control value not greater than the traffic control threshold value as a normal transaction and generating a prompt instruction; and the control value, the control instruction and the prompt instruction form a data tracking set.
Preferably, the system further comprises a financial front end, wherein the financial front end comprises a data acquisition module, and the data acquisition module is used for monitoring the transaction and the information source of the financial object to obtain a financial monitoring set comprising transaction monitoring data and information source data.
In order to solve the problem, the invention also discloses a financial big data automatic intelligent analysis control method based on cloud computing, which comprises the following steps:
monitoring the transaction condition of each account in real time to obtain transaction monitoring data, and performing feature extraction and marking calculation on the transaction monitoring data to obtain a monitoring value corresponding to the account;
when the corresponding accounts are classified according to the monitoring values, the accounts corresponding to the monitoring values larger than the monitoring threshold value are set as target objects;
monitoring information sources of a target object and a non-target object before financial transaction to obtain information source data;
extracting and marking the characteristics of information source data, mining and analyzing the relation among various marked data to obtain a data mining set containing a wind low signal, a wind medium signal, a primary risk mark, a wind high signal and a secondary risk mark;
and tracking the financial behavior of the marked object according to the data mining set to obtain a data tracking set containing the traffic control value, the control instruction and the prompt instruction, and dynamically controlling the financial behavior of the marked object according to the data tracking set.
Compared with the prior scheme, the invention has the following beneficial effects:
according to the method, the transaction data of the accounts in different monitoring periods are simultaneously integrated to obtain the monitoring values, the overall condition of the transaction of the accounts is analyzed and classified based on the monitoring values to obtain the target object and the non-target object, differential automatic analysis can be performed on the accounts with different transaction risks through classification, and the overall effect of automatic intelligent analysis of financial big data can be improved.
According to the method, on the other hand, monitoring statistics of financial transaction information sources is carried out through financial software, reliable data support is provided for automatic intelligent analysis of financial big data based on data in the aspect of conversation, and the risk weight in the aspect of conversation and the data in the aspect of subsequent transaction transfer are integrated in a simultaneous mode, so that the automatic intelligent analysis and control of the financial big data from different dimensions are achieved, and the overall effect of analysis and control is effectively improved.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a block diagram of a financial big data automation intelligent analysis control system based on cloud computing.
Fig. 2 is a flow chart of the financial big data automation intelligent analysis control method based on cloud computing.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
As shown in fig. 1, the invention relates to a cloud computing-based financial big data automation intelligent analysis control system, which comprises a financial front end and a financial back end;
the financial front end comprises a data acquisition module, and the data acquisition module is used for monitoring the transaction and the information source of a financial object to obtain a financial monitoring set containing transaction monitoring data and information source data;
the financial back end comprises an account evaluation module, a behavior mining module and an analysis control module;
the account evaluation module is used for screening the target objects, and comprises:
in a preset monitoring period, the monitoring period can be divided by hours, the transaction condition of each account is monitored in real time respectively, and the collection amount, the collection times, the payment account, the withdrawal amount, the withdrawal times and the withdrawal account at different moments of the account are counted and combined in a permutation way to obtain transaction monitoring data;
performing feature extraction and marking calculation on the transaction monitoring data to obtain a monitoring value JG corresponding to the account, setting the account corresponding to the monitoring value JG which is greater than a monitoring threshold value as a target object when classifying the corresponding account according to the monitoring value JG, and adding one to the monitoring times of the account;
wherein, carry out feature extraction and mark calculation to transaction monitoring data, include:
acquiring a time interval weight corresponding to a monitoring time interval and marking the time interval weight as SQ; different monitoring periods respectively correspond to different period weights, so that digitization and differentiation representation of different monitoring periods can be realized, for example, the higher the financial risk transaction is, the higher the corresponding period weight is;
respectively marking the collection amount, the collection times, the withdrawal amount and the withdrawal times in the monitoring time period as SJ, SC, CJ and CC; the unit of the amount is ten thousand yuan;
obtaining a payment account and carrying out risk evaluation to obtain corresponding risk weights and marking the risk weights as DQ and CQ; wherein the step of performing risk assessment comprises:
respectively matching the debit account and the debit account with a blacklist account marked in a pre-constructed risk database, and setting a risk label corresponding to the debit account or the debit account as a first level if the debit account or the debit account belongs to the blacklist account marked in the risk database;
if the making account or the withdrawing account belongs to the first transaction, setting a risk label corresponding to the making account or the withdrawing account as a second level;
if the account for making a money or the account for drawing a money belongs to a non-primary transaction or a public account, setting a risk label corresponding to the account for making a money or the account for drawing a money as a third level; the public accounts can be various existing government-enterprise accounts;
the transaction risks corresponding to the first-level label, the second-level label and the third-level label are sequentially reduced, and are respectively associated with a corresponding risk weight, and the risk weights can be preset;
extracting numerical values of all marked data, performing simultaneous operation, and calculating to obtain a monitoring value JG corresponding to the account through a formula; the formula is:
in the formula, j1 and j2 are different proportionality coefficients, and j1 is greater than 0 and less than j2, the proportionality coefficients in the formula and the preset thresholds in the analysis process are set by those skilled in the art according to actual conditions or obtained by simulation of a large amount of data, for example, j1 may be 1.322, and j2 may be 3.437.
The monitoring value is a numerical value for integrally evaluating the transaction risk of the user by combining various data of different dimensions during transaction; in the embodiment of the invention, data processing, calculation and analysis in all aspects are realized on the basis of cloud computing, transaction risks are integrally evaluated and classified by combining transaction accounts, transaction funds and transaction frequency, and automated differential analysis of financial big data can be realized; in addition, the method and the device are different from the scheme that freezing and non-cabinet are carried out when the existing wind control is triggered, and accurate and efficient financial big data monitoring and analysis can be achieved.
The behavior mining module is used for preprocessing and mining information source data in the financial monitoring set to obtain a data mining set; the method comprises the following specific steps:
extracting and marking the characteristics of the information source data in the financial monitoring set;
acquiring the call type of a call party, setting different call types to correspond to a different call type value, and matching the acquired call type with all the call types to acquire a corresponding call type value; the call types can be distinguished according to the call number types of the opposite sides, including but not limited to the numbers of various areas in China, the numbers of foreign areas and the numbers of unknown areas;
matching the call type value with a preset call type threshold, and if the call type value is greater than the call type threshold, setting a corresponding call type label to be 1; otherwise, setting the corresponding call type label to 0; and marking the call type tag as TL;
counting the call duration and matching the call duration with a preset call duration threshold, if the pass duration is greater than the pass duration threshold, setting the corresponding call duration label to be 1, otherwise, setting the corresponding call duration label to be 0; marking the call duration label as TS; the unit of the passing time length is second;
respectively acquiring call type weights and call duration weights corresponding to the call type labels and the call duration labels, and respectively marking the call type weights and the call duration weights as T1 and T2; the call type weight and the call duration weight can be set based on the proportion of the call type and the call duration in the existing fraud big data;
mining and analyzing the relationship between the marked data items, including:
extracting numerical values corresponding to various data of the marks, and calculating and combining through a formula WG = T1 xTL + T2 xTS to obtain a clearance value WG; when the potential financial risk of the call object is analyzed according to the clearance value WG, the clearance value WG is matched and evaluated with a preset clearance threshold value WGY;
if the cut-off value WG is smaller than a cut-off threshold value WGY, judging that the potential financial risk of the call object is low and generating a wind low signal;
if the digging-closing threshold value WGY is not less than the digging-closing threshold value WGY x k%, and k is a real number greater than one hundred, and the value can be 125, judging that the potential financial risk of the call object is moderate, generating a wind signal, and performing primary risk marking on the identity of the call object according to the wind signal;
if the cut-off value WG is larger than a cut-off threshold value WGY x k%, judging that the potential financial risk of the call object is high, generating a wind height signal, and carrying out secondary risk marking on the identity of the call object according to the wind height signal;
the wind low signal, the wind medium signal and the first-level risk flag, the wind high signal and the second-level risk flag form a data mining set.
In the embodiment of the invention, the monitoring of the financial monitoring centralized information source data can be realized based on the authority which is applied for passing by the existing financial software, and reliable data support is provided for the automated intelligent analysis of financial big data based on the data in the aspect of conversation;
different from the existing third-party financial fraud recognition software and the manual judgment of financial tellers, on the basis of monitoring and counting financial data, the financial software is used for monitoring and evaluating in the aspect of conversation, so that the diversity and the comprehensiveness of the financial big data in the aspect of fraud recognition analysis and evaluation can be further improved, and the overall effect of the financial big data automatic intelligent analysis can be effectively improved.
The analysis control module is used for tracking the financial behavior of the marked object according to the data mining set to obtain a data tracking set and dynamically controlling the financial behavior of the marked object according to the data tracking set; the method comprises the following specific steps:
tracking the financial behavior of a call object in a preset tracking time period according to wind signals and wind height signals in the data mining set;
in a preset tracking time period, the tracking time period can be whether account transfer behaviors exist within 40 minutes after the call is ended, the online account transfer behaviors and the offline account transfer behaviors are included, and if the account transfer behaviors exist, the account transfer amount and the account transfer account of the call object are obtained; extracting the value of the transfer amount and marking as ZJ; acquiring a risk weight corresponding to the transfer account and marking the risk weight as FQ; here, the risk weight obtaining step is the same as above;
acquiring risk weights JQ corresponding to risk marks of different levels; the risk weight is preset based on the risk big data; combining the marked data and calculating by a formula JK = JQ x (g 1 XZJ + g2 XFQ) to obtain an intersection control value JK; in the formula, g1 and g2 are different proportionality coefficients, g1 is more than 1 and less than g2, g1 can be 1.628, and g2 can be 2.765;
it should be noted that the transaction control value is used for carrying out various data in the aspect of transaction risk; a numerical value that jointly evaluates the transaction status as a whole; through the simultaneous integration of the risk weight in the aspect of conversation and the data in the aspect of subsequent transaction transfer, the automatic intelligent analysis and control of financial big data from different dimensions are realized, and the overall effect of analysis and control is effectively improved.
Judging the transaction corresponding to the traffic control value larger than the traffic control threshold value as a risk transaction and generating a control instruction; judging the transaction corresponding to the traffic control value not greater than the traffic control threshold value as a normal transaction and generating a prompt instruction;
the control values, the control instructions and the prompt instructions form a data tracking set.
In the embodiment of the invention, the information source (in the aspect of conversation) generated by financial big data is analyzed and traced, so that omnibearing monitoring and real-time analysis and control can be implemented;
the formulas involved in the above are all numerical calculations by removing dimensions, and are one formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest real situation.
Example two
As shown in fig. 2, the invention relates to a cloud computing-based financial big data automated intelligent analysis control method, which comprises the following specific steps:
monitoring the transaction condition of each account in real time to obtain transaction monitoring data, and performing feature extraction and marking calculation on the transaction monitoring data to obtain a monitoring value corresponding to the account;
when the corresponding accounts are classified according to the monitoring values, the accounts corresponding to the monitoring values larger than the monitoring threshold value are set as target objects;
monitoring information sources of a target object and a non-target object before financial transaction to obtain information source data;
extracting and marking the characteristics of information source data, mining and analyzing the relation among all marked data to obtain a data mining set containing a wind low signal, a wind middle signal, a primary risk mark, a wind high signal and a secondary risk mark;
and tracking the financial behavior of the marked object according to the data mining set to obtain a data tracking set containing the traffic control value, the control instruction and the prompt instruction, and dynamically controlling the financial behavior of the marked object according to the data tracking set.
In the embodiments provided in the present invention, it should be understood that the disclosed system may be implemented in other ways. For example, the above-described embodiments of the invention are merely illustrative, and for example, a module may be divided into only one logic function, and another division may be implemented in practice.
Modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a mode of hardware and a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the essential attributes thereof.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. The financial big data automatic intelligent analysis control system based on cloud computing is characterized by comprising a financial back end; the financial back end comprises an account evaluation module, a behavior mining module and an analysis control module;
the account evaluation module is used for screening the target objects and comprises the following steps:
in a preset monitoring period, acquiring the transaction condition of each account, and monitoring in real time to obtain transaction monitoring data, wherein the transaction monitoring data comprises the collection amount, the collection times, the payment account, the withdrawal amount, the withdrawal times and the withdrawal account at different moments of the account;
when the feature extraction and the marking calculation are carried out on the transaction monitoring data, the time interval weight corresponding to the monitoring time interval is obtained and marked as SQ;
respectively marking the collection amount, the collection times, the withdrawal amount and the withdrawal times in the monitoring time period as SJ, SC, CJ and CC;
obtaining a payment account and carrying out risk evaluation to obtain corresponding risk weights and marking the risk weights as DQ and CQ;
extracting the numerical values of all marked data, performing simultaneous operation, and calculating to obtain a monitoring value JG corresponding to the account through a formula; the formula is:
in the formula, j1 and j2 are different proportionality coefficients, j1 is more than 0 and less than j2, when the corresponding accounts are classified according to the monitored value JG, the account corresponding to the monitored value JG which is more than the monitored threshold value is set as a target object, and the monitoring times of the account are increased by one;
the behavior mining module is used for preprocessing and mining information source data in the monitored financial monitoring set to obtain a data mining set;
the analysis control module is used for tracking the financial behavior of the marked object according to the data mining set to obtain a data tracking set, and dynamically controlling the financial behavior of the marked object according to the data tracking set.
2. The cloud computing-based financial big data automated intelligent analysis control system according to claim 1, wherein the step of performing risk assessment comprises:
respectively matching the debit account and the debit account with a blacklist account marked in a pre-constructed risk database, and setting a risk label corresponding to the debit account or the debit account as a first level if the debit account or the debit account belongs to the blacklist account marked in the risk database;
if the payment account or the withdrawal account belongs to the first transaction, setting the risk label corresponding to the payment account or the withdrawal account as a second level;
if the payment account or the payment account belongs to a non-primary transaction or a public account, setting a risk label corresponding to the payment account or the payment account to be in a third level;
the transaction risks corresponding to the first-level label, the second-level label and the third-level label are sequentially reduced, and a corresponding risk weight is associated with each label.
3. The cloud computing-based financial big data automated intelligent analysis control system according to claim 1, wherein preprocessing and mining information source data in financial monitoring sets comprises:
performing feature extraction and marking on information source data in the financial monitoring set;
acquiring the call type of a call party, setting different call types to correspond to a different call type value, and matching the acquired call type with all the call types to acquire a corresponding call type value;
matching the call type value with a preset call type threshold, and if the call type value is greater than the call type threshold, setting a corresponding call type label to be 1; otherwise, setting the corresponding call type label to 0; and mark the call type tag as TL.
4. The cloud-computing-based financial big data automated intelligent analysis control system according to claim 3, wherein the call duration is counted and matched with a preset call duration threshold, if the pass duration is greater than the pass duration threshold, the corresponding call duration label is set to 1, otherwise, the corresponding call duration label is set to 0; marking the call duration label as TS;
respectively acquiring call type weights and call duration weights corresponding to the call type labels and the call duration labels, and respectively marking the call type weights and the call duration weights as T1 and T2;
and mining and analyzing the relation among the marked data to obtain a data mining set.
5. The cloud computing-based financial big data automated intelligent analysis control system according to claim 4, wherein mining and analyzing relationships between tagged items of data comprises:
extracting numerical values corresponding to various data of the marks, and calculating and combining the numerical values through a formula WG = T1 xTL + T2 xTS to obtain a clearance value WG; and when the potential financial risk of the call object is analyzed according to the clearance value WG, the clearance value WG is matched and evaluated with a preset clearance threshold value WGY.
6. The cloud-computing-based financial big data automated intelligent analysis control system according to claim 5, wherein if the cut-off value WG < cut-off threshold WGY, it is determined that the potential financial risk of the call partner is low and a wind low signal is generated;
if the cut-off threshold value WGY is not more than the cut-off value WG is not more than the cut-off threshold value WGY x k%, and k is a real number larger than one hundred, judging that the potential financial risk of the call object is moderate, generating a wind signal, and performing primary risk marking on the identity of the call object according to the wind signal;
if the cut-off value WG is larger than a cut-off threshold value WGY x k%, judging that the potential financial risk of the call object is high, generating a wind height signal, and performing secondary risk marking on the identity of the call object according to the wind height signal;
the wind low signal, the wind medium signal and the first-level risk flag, the wind high signal and the second-level risk flag form a data mining set.
7. The cloud computing-based financial big data automated intelligent analysis control system according to claim 1, wherein tracking the financial behavior of the tagged objects according to the data mining set comprises:
tracking the financial behavior of a call object in a preset tracking time period according to wind signals and wind height signals in the data mining set;
acquiring a transfer amount and a transfer account of a call object in a preset tracking period; extracting the value of the transfer amount and marking as ZJ; acquiring a risk weight corresponding to the transfer account and marking the risk weight as FQ;
acquiring risk weights JQ corresponding to risk marks of different levels; combining the marked data and calculating by a formula JK = JQ x (g 1 XZJ + g2 XFQ) to obtain an intersection control value JK; wherein g1 and g2 are different proportionality coefficients and 1 < g2.
8. The cloud-computing-based financial big data automated intelligent analysis control system according to claim 7, wherein a transaction corresponding to a traffic control value greater than a traffic control threshold is determined as a risk transaction and a control instruction is generated; judging the transaction corresponding to the traffic control value not greater than the traffic control threshold value as a normal transaction and generating a prompt instruction; and the control value, the control instruction and the prompt instruction form a data tracking set.
9. The cloud computing-based financial big data automated intelligent analysis control system according to claim 1, further comprising a financial front end, wherein the financial front end comprises a data acquisition module, and the data acquisition module is configured to monitor transactions and information sources of financial objects to obtain a financial monitoring set comprising transaction monitoring data and information source data.
10. The cloud computing-based financial big data automatic intelligent analysis control method is applied to the cloud computing-based financial big data automatic intelligent analysis control system of any one of claims 1 to 9, and is characterized by comprising the following steps of:
monitoring the transaction condition of each account in real time to obtain transaction monitoring data, and performing feature extraction and marking calculation on the transaction monitoring data to obtain a monitoring value corresponding to the account;
when the corresponding accounts are classified according to the monitoring value, the accounts corresponding to the monitoring values larger than the monitoring threshold value are set as target objects;
monitoring information sources of a target object and a non-target object before financial transaction to obtain information source data;
extracting and marking the characteristics of information source data, mining and analyzing the relation among various marked data to obtain a data mining set containing a wind low signal, a wind medium signal, a primary risk mark, a wind high signal and a secondary risk mark;
and tracking the financial behavior of the marked object according to the data mining set to obtain a data tracking set containing the traffic control value, the control instruction and the prompt instruction, and dynamically controlling the financial behavior of the marked object according to the data tracking set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210931716.8A CN115271926A (en) | 2022-08-04 | 2022-08-04 | Financial big data automatic intelligent analysis control system and method based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210931716.8A CN115271926A (en) | 2022-08-04 | 2022-08-04 | Financial big data automatic intelligent analysis control system and method based on cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115271926A true CN115271926A (en) | 2022-11-01 |
Family
ID=83750178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210931716.8A Pending CN115271926A (en) | 2022-08-04 | 2022-08-04 | Financial big data automatic intelligent analysis control system and method based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115271926A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115760119A (en) * | 2022-11-28 | 2023-03-07 | 海口春帆网络科技有限公司 | Financial payment supervision system and method based on data processing and feature recognition |
-
2022
- 2022-08-04 CN CN202210931716.8A patent/CN115271926A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115760119A (en) * | 2022-11-28 | 2023-03-07 | 海口春帆网络科技有限公司 | Financial payment supervision system and method based on data processing and feature recognition |
| CN115760119B (en) * | 2022-11-28 | 2024-03-12 | 西安乐刷宝网络科技有限公司 | Financial payment supervision system and method based on data processing and feature recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492945A (en) | Business risk identifies monitoring method, device, equipment and storage medium | |
| TWI584215B (en) | Method of monitoring suspicious transactions | |
| CN102623009B (en) | Abnormal emotion automatic detection and extraction method and system on basis of short-time analysis | |
| CN107194803A (en) | A kind of P2P nets borrow the device of borrower's assessing credit risks | |
| CN112053221A (en) | Knowledge graph-based internet financial group fraud detection method | |
| CN110417721A (en) | Safety risk estimating method, device, equipment and computer readable storage medium | |
| CN109191283A (en) | Method for prewarning risk and system | |
| CN110415111A (en) | Merge the method for logistic regression credit examination & approval with expert features based on user data | |
| CN109034194A (en) | Transaction swindling behavior depth detection method based on feature differentiation | |
| CN108053318A (en) | It is a kind of to the method and device that is identified of merchandising extremely | |
| CN106157135A (en) | Antifraud system and method based on Application on Voiceprint Recognition Sex, Age | |
| CN115760119B (en) | Financial payment supervision system and method based on data processing and feature recognition | |
| CN109816509A (en) | Generation method, terminal device and the medium of scorecard model | |
| CN112053222A (en) | Knowledge graph-based internet financial group fraud detection method | |
| CN110348490A (en) | A kind of soil quality prediction technique and device based on algorithm of support vector machine | |
| CN109903053A (en) | A kind of anti-fraud method carrying out Activity recognition based on sensing data | |
| CN104850868A (en) | Customer segmentation method based on k-means and neural network cluster | |
| CN115271926A (en) | Financial big data automatic intelligent analysis control system and method based on cloud computing | |
| CN113962614B (en) | Intelligent examination method and device for business abnormity of listed company | |
| CN114254867A (en) | Telecommunication fraud victim risk assessment system and method | |
| CN115759640A (en) | Public service information processing system and method for smart city | |
| CN111191720A (en) | Service scene identification method and device and electronic equipment | |
| CN111222968A (en) | Enterprise tax risk management and control method and system | |
| CN110189170A (en) | Market sentiment analysis method and system | |
| CN116152001B (en) | Aggregate payment supervision system based on accounting data analysis |
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 |