CN109767314A - Trade company's risk management and control method, device, computer equipment and storage medium - Google Patents
Trade company's risk management and control method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109767314A CN109767314A CN201811532336.7A CN201811532336A CN109767314A CN 109767314 A CN109767314 A CN 109767314A CN 201811532336 A CN201811532336 A CN 201811532336A CN 109767314 A CN109767314 A CN 109767314A
- Authority
- CN
- China
- Prior art keywords
- trade company
- impact factor
- instruction
- decision
- risk
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 47
- 238000011156 evaluation Methods 0.000 claims abstract description 38
- 230000004044 response Effects 0.000 claims abstract description 15
- 238000004590 computer program Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 230000000306 recurrent effect Effects 0.000 claims description 12
- 230000009471 action Effects 0.000 claims description 5
- 238000012502 risk assessment Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 108010094028 Prothrombin Proteins 0.000 description 1
- AGVAZMGAQJOSFJ-WZHZPDAFSA-M cobalt(2+);[(2r,3s,4r,5s)-5-(5,6-dimethylbenzimidazol-1-yl)-4-hydroxy-2-(hydroxymethyl)oxolan-3-yl] [(2r)-1-[3-[(1r,2r,3r,4z,7s,9z,12s,13s,14z,17s,18s,19r)-2,13,18-tris(2-amino-2-oxoethyl)-7,12,17-tris(3-amino-3-oxopropyl)-3,5,8,8,13,15,18,19-octamethyl-2 Chemical compound [Co+2].N#[C-].[N-]([C@@H]1[C@H](CC(N)=O)[C@@]2(C)CCC(=O)NC[C@@H](C)OP(O)(=O)O[C@H]3[C@H]([C@H](O[C@@H]3CO)N3C4=CC(C)=C(C)C=C4N=C3)O)\C2=C(C)/C([C@H](C\2(C)C)CCC(N)=O)=N/C/2=C\C([C@H]([C@@]/2(CC(N)=O)C)CCC(N)=O)=N\C\2=C(C)/C2=N[C@]1(C)[C@@](C)(CC(N)=O)[C@@H]2CCC(N)=O AGVAZMGAQJOSFJ-WZHZPDAFSA-M 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves a kind of trade company's risk management and control method, device, computer equipment and storage medium based on big data.By the way that trade company's risk evaluation result and risk are inputted decision model with reference to assessment factor, obtain decision instruction, impact factor is calculated according to the influence information of trade company and decision instruction, control instruction is obtained according to impact factor, response control instruction carries out alignment processing to trade company's account.This method carries out risk management and control to trade company using system, improves the real-time control ability to trade company, improves the efficiency of risk management and control.
Description
Technical field
This application involves Internet technical fields, set more particularly to a kind of trade company's risk management and control method, device, computer
Standby and storage medium.
Background technique
With the fast development of mobile payment, the trade company of payment platform access is more and more.And the risk management of trade company, it is
Bank card accepts the guarantee of healthy development of market.For payment platform, the risk of fraud of trade company is assessed in time and carries out pipe
Control, can prevent financial risk.
Traditional trade company's risk management and control uses manually-operated mode, low efficiency.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of risk management and control side, trade company that can improve control efficiency
Method, device, computer equipment and storage medium.
A kind of trade company's risk management and control method, which comprises
It obtains trade company's risk evaluation result and risk refers to assessment factor；
Trade company's risk evaluation result and the risk are inputted into decision model with reference to assessment factor, pass through the decision
Model obtains the decision instruction to trade company；
Impact factor is calculated according to the influence information of the trade company and the decision instruction；
Control instruction is obtained according to the impact factor；
The control instruction is responded, alignment processing is carried out to trade company's account.
In another embodiment, the step of impact factor is calculated according to the influence information of the trade company and the decision instruction
Suddenly, comprising:
Corresponding first impact factor of the influence information for calculating the trade company from default dimension；
Corresponding second impact factor of the decision instruction is calculated from default dimension；
Obtain the first weight of first impact factor and the second weight of second impact factor；
According to first weight, the second weight, the first impact factor and the second impact factor, weighting obtain influencing because
Son.
In another embodiment, described the step of control instruction is obtained according to the impact factor, comprising:
The decision instruction is adjusted according to the impact factor, obtains control instruction.
In another embodiment, the step of decision instruction being adjusted according to the impact factor, obtaining control instruction,
Include:
When the impact factor is greater than, and threshold value is turned up, the rank of the decision instruction is turned up, obtains control instruction；
When the impact factor, which is less than, turns down threshold value, the rank of the decision instruction is turned down, obtains control instruction.
In another embodiment, described the step of control instruction is obtained according to the impact factor, comprising:
The decision instruction and the impact factor are sent to processing terminal, obtain the control of the processing terminal feedback
Instruction, the control instruction after response trigger action of the treatment people based on the decision instruction and the impact factor by sending out
Out.
In another embodiment, the step of decision instruction and the impact factor being sent to processing terminal, packet
It includes:
By the size order of the impact factor, the decision instruction and the impact factor are sent to processing terminal.
In another embodiment, the method also includes:
The sample data of decision instruction will be labelled with as training sample set；The sample data includes trade company's risk
Assessment result and the risk refer to assessment factor；
Training sample set input Recognition with Recurrent Neural Network is obtained into prediction result；
According to the parameter of the prediction result and mark adjustment Recognition with Recurrent Neural Network, goes directly and reach iteration stopping condition, obtain
To decision model.
A kind of trade company's risk management and control device, described device include:
Parameter acquisition module, for obtaining trade company's risk evaluation result and risk with reference to assessment factor；
Decision obtains module, for trade company's risk evaluation result and the risk to be inputted decision with reference to assessment factor
Model obtains the decision instruction to trade company by the decision model；
Impact factor computing module, for calculated according to the influence information of the trade company and the decision instruction influence because
Son；
Control obtains module, for obtaining control instruction according to the impact factor；
Processing module carries out alignment processing to trade company's account for responding the control instruction.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes the step of any one of the various embodiments described above the method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of method described in any one of the various embodiments described above is realized when row.
Above-mentioned trade company's risk management and control method, device, computer equipment and storage medium, by by trade company's risk evaluation result
And risk inputs decision model with reference to assessment factor, decision instruction is obtained, according to the influence information and decision instruction meter of trade company
Impact factor is calculated, control instruction is obtained according to impact factor, response control instruction carries out alignment processing to trade company's account.This method
Risk management and control is carried out to trade company using system, the real-time control ability to trade company is improved, improves the efficiency of risk management and control.
Detailed description of the invention
Fig. 1 is the application scenario diagram of trade company's risk management and control method in one embodiment；
Fig. 2 is the flow diagram of trade company's risk management and control method in one embodiment；
Fig. 3 is the structural block diagram of trade company's risk management and control device in one embodiment；
Fig. 4 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Trade company's risk management and control method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, it takes
Business device 102 is communicated by network with data sharing platform 104, transaction platform 106.Server 102 is from data sharing platform
104 and 106 pulling data of transaction platform, risk assessment is carried out to trade company and obtains the result of risk assessment.According to risk assessment knot
Fruit and risk refer to assessment factor, obtain the decision instruction to trade company, calculate shadow according to the influence information of trade company and decision instruction
The factor is rung, control instruction is obtained, response control instruction handles trade company's account.Server 102 can use independent service
The server cluster of device either multiple servers composition is realized.
In one embodiment, as shown in Fig. 2, providing a kind of trade company's risk management and control method, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
S202, obtains trade company's risk evaluation result and risk refers to assessment factor.
Wherein, trade company's risk evaluation result refers to by trade company's risk evaluating system, according to the login file information of trade company and
Trading situation, there are the assessment results of risk of fraud for the given trade company.Risk evaluation result may include multiple risk classes,
For indicating the different risk class of trade company.In one embodiment, risk evaluation result includes high risk, and low-risk is potential
Risk.Wherein, the grade highest of high risk, the grade of low risk level highest, potential risk are placed in the middle.
Risk is when carrying out risk management and control, other than risk evaluation result, to influence other ginsengs of decision with reference to assessment factor
Factor is examined, including whether trade company is reported and submitted by other acquirers to cheat trade company, if current row holder is reported and submitted by card sending mechanism
It trades there are arbitrage or pseudo- card transaction in the trade company, whether trade company legal person agency is by public security, procuratorate, and law court is included in insincere people
Member's list.
Trade company's risk evaluation result and risk are inputted decision model with reference to assessment factor, are obtained by decision model by S204
To the decision instruction to trade company.
Decision model refers to that the pre- mass data that first passes through is trained, for being joined according to trade company's risk evaluation result and risk
Examine the model that assessment factor provides decision instruction.Decision model can be established based on neural network structure.Decision model training when,
It is trained based on sample set, trade company's sample data of sample training collection includes the risk evaluation result and risk reference of trade company
Assessment factor, and mark the trade company decision instruction.Neural network is trained using sample training collection, obtains decision
Model.
Decision model for inputting decision instruction, decision instruction refer to based on risk evaluation result and risk with reference to assessment because
The decision that element makes trade company, content of policy decision include: to stop payment, freeze, giving preferential, raising amount etc..The purpose of decision exists
In transaction risk brought by prevention merchant fraud risk, the fraud bonus for improving platform stops loss ability, reduces actual loss.
Therefore, it is high risk for trade company's risk evaluation result and refers to the trade company of assessment factor with high-risk risk,
Decision instruction is usually to stop payment and freeze.Wherein, high-risk risk includes trade company by other acquirer reports with reference to assessment factor
It send to cheat trade company, reporting and submitting current row holder in the trade company by card sending mechanism, there are arbitrage transaction or pseudo- card transaction, trade company legal persons
Agency is included in insincere staff list by public security, procuratorate, law court.And it is low-risk for trade company's risk evaluation result and does not have
There is high-risk risk to refer to the trade company of assessment factor, decision instruction is usually to give preferential and raising amount etc..
S206 calculates impact factor according to the influence information of trade company and decision instruction.
Wherein, the influence information of trade company includes indicating the information of the influence degree of trade company, the scale of operation including trade company, quotient
The well-known situation at family, the trading volume etc. of trade company.Trade company is well-known trade company, such as trade company legal person is famous person, the scale of operation of trade company
Greatly, the trading volume of trade company is big, these situations all show that the influence degree of trade company is higher.If the influence degree of trade company determines the quotient
There are risk of fraud at family, then the influence to transaction platform and consumer is bigger.
Different decision instructions has different influences, and decision instruction is more serious, shows the influence and urgent journey of the decision
Degree is bigger, bigger to transaction platform, trade company and the influence of consumer.Wherein, the severity and decision instruction of decision instruction
Corresponding measure influence degree is related, and the influence degree for such as freezing trade company is greater than the influence degree stopped payment.
Impact factor be it is jointly calculated according to the influence information of trade company and to the decision instruction of the trade company, indicate total shadow
The data of the degree of sound.
S208 obtains control instruction according to impact factor.
Control instruction is the final management and control measures made according to impact factor to trade company.Control instructs the shadow of the impacted factor
It rings, can be the adjustment made to decision instruction, or the final decision that allowed for influencing factors is made.
For example, system, which is provided with impact factor adjustment decision instruction, obtains the mode of control instruction, according to impact factor pair
Decision instruction is adjusted, and obtains control instruction, and the mode of adjustment can be the rank that decision instruction is turned up, and is obtained control and is referred to
It enables, or the rank for adjusting low decision instruction obtains control instruction.
In another example system, which is provided with the corresponding control mode of the Different Effects factor, directly obtains control according to impact factor
Instruction.
S210, response control instruction, carries out alignment processing to trade company's account.
In the present embodiment, final control is responded by server and is instructed, alignment processing is carried out to trade company's account automatically, is improved
The ability that trade company manages in real time reduces the probability that fraud occurs.
Above-mentioned trade company's risk management and control method, by inputting trade company's risk evaluation result and risk with reference to assessment factor
Decision model obtains decision instruction, calculates impact factor according to the influence information of trade company and decision instruction, is obtained according to impact factor
It is instructed to control, response control instruction carries out alignment processing to trade company's account.This method carries out risk pipe to trade company using system
Control, improves the real-time control ability to trade company, improves the efficiency of risk management and control.
In another embodiment, as shown in figure 3, calculating impact factor according to the influence information of trade company and decision instruction
Step, comprising:
S302 calculates corresponding first impact factor of influence information of trade company from default dimension.
The influence information of trade company includes indicating the information of the influence degree of trade company, the scale of operation including trade company, trade company
Well-known situation, the trading volume etc. of trade company.Default dimension can be importance, seriousness, urgency level and influence degree four dimensions
Degree.Specifically, from the importance of the influence information of trade company, seriousness, emergency procedure and the influence letter for influencing program calculating trade company
Cease corresponding first impact factor.Specifically, for each dimension, standards of grading are provided with, when the influence information of trade company is full
When the condition of the corresponding standards of grading of foot, corresponding score is obtained, the score for the four dimensions that add up obtains the influence information pair of trade company
The first impact factor answered.
Specifically, according to the influence information of trade company, the scoring rule of importance dimension is matched, obtains point of importance dimension
Value.According to the influence information of trade company, the scoring rule of seriousness dimension is matched, the score value of seriousness dimension is obtained.According to trade company
Influence information, match urgency level dimension computation rule, obtain the score value of urgency level dimension.Believed according to the influence of trade company
Breath matches the scoring rule of influence degree dimension, obtains the score value of influence degree dimension.It is the score value of cumulative importance dimension, tight
The score value of the score value of principal characteristic dimension, the score value of urgency level dimension and influence degree dimension, obtains the first impact factor.
Specifically, scoring rule can be set to the influence information of trade company when including the corresponding content of scoring rule, obtain
The score answered.The corresponding content of scoring rule can be configured according to practical application, be not construed as limiting herein.
S304 calculates corresponding second impact factor of decision instruction from default dimension.
Different decision instructions has different influences.Default dimension can be importance, seriousness, urgency level and shadow
Ring degree four dimensions.Specifically, being calculated from the importance of decision instruction, seriousness, emergency procedure and influence program corresponding
Second impact factor.Specifically, for each decision instruction, score value, seriousness dimension provided with corresponding importance dimension
The score value of the score value of degree, the score value of urgency level dimension and influence degree dimension, the score value for the importance dimension that adds up, seriousness dimension
The score value of the score value of degree, the score value of urgency level dimension and influence degree dimension, obtains the second impact factor.
S306 obtains the first weight of the first impact factor and the second weight of the second impact factor.
Specifically, for the first impact factor and the second impact factor, weight is arranged in the size that can be influenced according to it, to adjust
The specific gravity that the influence information at integral quotient family and decision instruction calculate impact factor.Typically, decision instruction is comprehensive trade company's wind
What dangerous assessment result and risk were made with reference to assessment factor, shared by specific gravity it is bigger.
S308, according to the first weight, the second weight, the first impact factor and the second impact factor, weighting obtain influencing because
Son.
Specifically, the formula of the weighted influence factor are as follows:
A=m*B+n*C
Wherein, A is impact factor, and B is the first impact factor, and C is the second impact factor, and m is the first weight, n second
Weight.
In the present embodiment, after decision system provides decision instruction, from the important of the influence information of trade company and decision instruction
Property, seriousness, urgency level, influence degree etc. calculate impact factor, provide the foundation for final control instruction.
In another embodiment, the step of control instruction being obtained according to impact factor, comprising: adjusted according to impact factor
Decision instruction obtains control instruction.
Specifically, system is provided with impact factor adjustment decision instruction and obtains the mode of control instruction, according to impact factor
Decision instruction is adjusted, control instruction is obtained, the mode of adjustment can be the rank that decision instruction is turned up, and obtains control and refers to
It enables, or the rank for adjusting low decision instruction obtains control instruction.
Specifically, when impact factor is greater than, and threshold value is turned up, the rank of decision instruction is turned up, obtains control instruction, works as shadow
The factor is rung less than when turning down threshold value, turns down the rank of decision instruction, obtains control instruction.When impact factor between be turned up threshold value and
When turning down between threshold value, instructed decision instruction as control.In the present embodiment, height-regulating threshold value, which is greater than, turns down threshold value.
Specifically, decision instruction is divided into two classes according to the influence size to trade company for each decision instruction by system, each
Classification is respectively provided with rank.Specifically, a kind of is positive decision instruction, usually to the decision of low-risk trade company, Yi Zhongwei
Negative decision instruction, usually to the decision of high risk trade company.In a kind of embodiment, to influence sequence from big to small, bear
The rank of face decision instruction successively just sorts are as follows: freezes, stops payment, reduces amount.To influence sequence from big to small, front is determined
The rank height sequence of plan instruction is successively are as follows: improves amount and provides preferential.When impact factor is higher than threshold value, in same category
Between decision instruction is turned up, obtain control instruction.Impact factor is higher than threshold value, illustrates the processing to trade company to the safety of transaction platform
It influences greatly, by the way that decision instruction is turned up, either positive or negative decision can play the role of A clear guidance.For example, certain
The shop that trade company is opened by famous person, trading volume is larger, and decision model is to reduce amount to the decision instruction of the trade company.But it calculates
The trade company impact factor it is larger, be greater than and threshold value be turned up, in the present embodiment, the rank of the decision instruction of the trade company is turned up, adjust
To stop payment, the control instruction to the trade company is obtained, so that reducing well-known trade company carries out risk brought by fraudulent trading.For just
The decision in face is greater than and threshold value is turned up, the rank of the instruction of trade company is turned up if the impact factor calculated is larger, can rise to trade company
To the effect of front guiding.
On the contrary, trade company lesser for impact factor, turns down the rank of decision instruction, the work of risk prevention system is on the one hand played
With, on the other hand give trade company's indicating risk, play the role of front guiding.
In another embodiment, the step of control instruction being obtained according to impact factor, comprising: by decision instruction and influence
The factor is sent to processing terminal, obtains the control instruction of processing terminal feedback, and control instruction is based on certainly by response treatment people
It is issued after the trigger action of plan instruction and impact factor.
In the present embodiment, for the decision instruction that decision model provides, by manually being checked.And due to impact factor from
Importance, seriousness, urgency level, influence degree four dimensions obtain after calculating, and can react the importance, tight of decision instruction
Principal characteristic, urgency level, influence degree.It is sent to treatment people by will affect the factor and decision instruction and is audited.Handle people
Member is handled according to impact factor and decision instruction synthesis, provides final control instruction.In specifically embodiment, processing
Personnel reference may also be made to other public feelings informations about the trade company of data platform collection when carrying out manual review, and synthesis provides
Control instruction.
In the present embodiment, by the combined treatment mode of the system decision-making and manual review, the standard of control mode can be improved
Exactness improves the risk control capability of transaction platform, and carries out control processing to trade company automatically by system.
In another embodiment, the step of decision instruction and impact factor being sent to processing terminal, comprising: by influence
Decision instruction and impact factor are sent to processing terminal by the size order of the factor.
Specifically, decision instruction and impact factor are sent to by decision instruction according to the size order of impact factor
Processing terminal.It is obtained after being calculated due to impact factor from importance, seriousness, urgency level, influence degree four dimensions, it can
Importance, seriousness, urgency level, the influence degree of decision instruction are reacted, thus, in the present embodiment, it is bigger to will affect the factor
Decision instruction, preferentially issue processing terminal processing, can to importance, seriousness, urgency level, the decision of influence degree and
The processing response speed of trade company, to reduce the probability of risk generation.
In another embodiment, trade company's risk management and control method further comprises the training process of decision model.Specifically, certainly
The training process of plan model includes: sample data using decision instruction is labelled with as training sample set；Sample data includes quotient
Family risk evaluation result and risk refer to assessment factor, and training sample set input Recognition with Recurrent Neural Network is obtained prediction result, root
It is predicted that the parameter of result and mark adjustment Recognition with Recurrent Neural Network, goes directly and reaches iteration stopping condition, obtain decision model.
In the present embodiment, based on the decision model trained, the trade company's risk evaluation result and risk of trade company are referred to
Assessment factor inputs disaggregated model, obtains the decision instruction of trade company.By using neural network model, using big data to obtaining
To the decision of trade company, the efficiency of decision-making is improved.
In another embodiment, trade company's risk evaluation result and risk are inputted into decision model with reference to assessment factor, led to
Cross the step of decision model obtains the decision instruction to trade company, comprising: by trade company's risk evaluation result and risk with reference to assessment because
Element input decision model obtains the decision instruction to trade company by decision model according to each dimension impact factor of setting.
Specifically, trade company's risk evaluation result and risk reference are evaluated as the input information of two dimensions, each dimension
The impact factor for inputting information setting according to trade company's risk evaluation result and risk with reference to the particular content assessed, and influences
The factor, synthesis obtain decision instruction.Such as, blacklist trade company and trade company legal person agency are by public security, and procuratorate, law court is included in can not
Believe staff list, then decision instruction is to freeze merchant account.
It should be understood that although each step in the flow chart of Fig. 2 is successively shown according to the instruction of arrow, this
A little steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these steps
It executes there is no the limitation of stringent sequence, these steps can execute in other order.Moreover, at least part in Fig. 2
Step may include that perhaps these sub-steps of multiple stages or stage are executed in synchronization to multiple sub-steps
It completes, but can execute at different times, the execution sequence in these sub-steps or stage, which is also not necessarily, successively to be carried out,
But it can be executed in turn or alternately at least part of the sub-step or stage of other steps or other steps.
In one embodiment, as shown in figure 3, providing a kind of trade company's risk management and control device, comprising: parameter obtains mould
Block, decision obtain module, impact factor computing module, control acquisition module and processing module, in which:
Parameter acquisition module 302, for obtaining trade company's risk evaluation result and risk with reference to assessment factor.
Decision obtains module 304, for trade company's risk evaluation result and risk to be inputted decision model with reference to assessment factor,
The decision instruction to trade company is obtained by decision model.
Impact factor computing module 306, for calculating impact factor according to the influence information of trade company and decision instruction.
Control obtains module 308, for obtaining control instruction according to impact factor.
Processing module 310 carries out alignment processing to trade company's account for responding control instruction.
Above-mentioned trade company's risk management and control device, by the way that trade company's risk evaluation result and risk are determined with reference to assessment factor input
Plan model, obtains decision instruction, calculates impact factor according to the influence information of trade company and decision instruction, is obtained according to impact factor
Control instruction, response control instruction carry out alignment processing to trade company's account.This method carries out risk management and control to trade company using system,
The real-time control ability to trade company is improved, the efficiency of risk management and control is improved.
In another embodiment, impact factor computing module includes:
Factor I obtains module, for calculating corresponding first impact factor of influence information of trade company from default dimension.
Factor Ⅱ obtains module, for calculating corresponding second impact factor of decision instruction from default dimension.
Weight Acquisition module, for obtaining the first weight of the first impact factor and the second weight of the second impact factor.
Weighting block, for weighting according to the first weight, the second weight, the first impact factor and the second impact factor
To impact factor.
In another embodiment, control obtains module, for adjusting decision instruction according to impact factor, obtains control and refers to
It enables.
In another embodiment, module is managed, for decision instruction to be turned up when impact factor is greater than and threshold value is turned up
Rank obtains control instruction and turns down the rank of decision instruction when impact factor, which is less than, turns down threshold value, obtains control instruction.
In another embodiment, control obtains module, for decision instruction and impact factor to be sent to processing terminal,
The control instruction of processing terminal feedback is obtained, control instruction passes through response touching of the treatment people based on decision instruction and impact factor
It is issued after hair operation.
In another embodiment, control obtains module, for pressing the size order of impact factor, by decision instruction and shadow
It rings the factor and is sent to processing terminal.
In another embodiment, trade company's risk management and control device, further includes:
Sample set obtains module, for that will be labelled with the sample data of decision instruction as training sample set；Sample data
Assessment factor is referred to including trade company's risk evaluation result and risk.
Prediction module, for training sample set input Recognition with Recurrent Neural Network to be obtained prediction result.
Training module, for the parameter according to prediction result and mark adjustment Recognition with Recurrent Neural Network, the through iteration that reaches is stopped
Only condition obtains decision model.
Specific about trade company's risk management and control device limits the limit that may refer to above for trade company's risk management and control method
Fixed, details are not described herein.Modules in above-mentioned trade company's risk management and control device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 4.The computer equipment includes processor, memory and the network interface connected by system bus.
Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory of the computer equipment includes non-easy
The property lost storage medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and database.It should
Built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The computer equipment
Network interface be used to communicate with external terminal by network connection.To realize one when the computer program is executed by processor
Kind trade company's risk management and control method.
It will be understood by those skilled in the art that structure shown in Fig. 4, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of when executing computer program
It obtains trade company's risk evaluation result and risk refers to assessment factor；
Trade company's risk evaluation result and risk are inputted into decision model with reference to assessment factor, obtained by decision model to quotient
The decision instruction at family；
Impact factor is calculated according to the influence information of trade company and decision instruction；
Control instruction is obtained according to impact factor；
Response control instruction, carries out alignment processing to trade company's account.
In one embodiment, the step of impact factor being calculated according to the influence information of trade company and decision instruction, comprising:
Corresponding first impact factor of influence information of trade company is calculated from default dimension；
Corresponding second impact factor of decision instruction is calculated from default dimension；
Obtain the first weight of the first impact factor and the second weight of the second impact factor；
According to the first weight, the second weight, the first impact factor and the second impact factor, weighting obtains impact factor.
In one embodiment, the step of control instruction being obtained according to impact factor, comprising:
Decision instruction is adjusted according to impact factor, obtains control instruction.
In one embodiment, the step of decision instruction being adjusted according to impact factor, obtaining control instruction, comprising:
When impact factor is greater than, and threshold value is turned up, the rank of decision instruction is turned up, obtains control instruction；
When impact factor, which is less than, turns down threshold value, the rank of decision instruction is turned down, obtains control instruction.
In one embodiment, the step of control instruction being obtained according to impact factor, comprising:
Decision instruction and impact factor are sent to processing terminal, obtain the control instruction of processing terminal feedback, control refers to
It enables by being issued after response trigger action of the treatment people based on decision instruction and impact factor.
In one embodiment, the step of decision instruction and impact factor being sent to processing terminal, comprising:
By the size order of impact factor, decision instruction and impact factor are sent to processing terminal.
In one embodiment, it is also performed the steps of when processor executes computer program
The sample data of decision instruction will be labelled with as training sample set；Sample data includes trade company's risk evaluation result
Assessment factor is referred to risk；
Training sample set input Recognition with Recurrent Neural Network is obtained into prediction result；
According to the parameter of prediction result and mark adjustment Recognition with Recurrent Neural Network, goes directly and reach iteration stopping condition, determined
Plan model.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
It obtains trade company's risk evaluation result and risk refers to assessment factor；
Trade company's risk evaluation result and risk are inputted into decision model with reference to assessment factor, obtained by decision model to quotient
The decision instruction at family；
Impact factor is calculated according to the influence information of trade company and decision instruction；
Control instruction is obtained according to impact factor；
Response control instruction, carries out alignment processing to trade company's account.
In one embodiment, the step of impact factor being calculated according to the influence information of trade company and decision instruction, comprising:
Corresponding first impact factor of influence information of trade company is calculated from default dimension；
Corresponding second impact factor of decision instruction is calculated from default dimension；
Obtain the first weight of the first impact factor and the second weight of the second impact factor；
According to the first weight, the second weight, the first impact factor and the second impact factor, weighting obtains impact factor.
In one embodiment, the step of control instruction being obtained according to impact factor, comprising:
Decision instruction is adjusted according to impact factor, obtains control instruction.
In one embodiment, the step of decision instruction being adjusted according to impact factor, obtaining control instruction, comprising:
When impact factor is greater than, and threshold value is turned up, the rank of decision instruction is turned up, obtains control instruction；
When impact factor, which is less than, turns down threshold value, the rank of decision instruction is turned down, obtains control instruction.
In one embodiment, the step of control instruction being obtained according to impact factor, comprising:
Decision instruction and impact factor are sent to processing terminal, obtain the control instruction of processing terminal feedback, control refers to
It enables by being issued after response trigger action of the treatment people based on decision instruction and impact factor.
In one embodiment, the step of decision instruction and impact factor being sent to processing terminal, comprising:
By the size order of impact factor, decision instruction and impact factor are sent to processing terminal.
In one embodiment, it is also performed the steps of when processor executes computer program
The sample data of decision instruction will be labelled with as training sample set；Sample data includes trade company's risk evaluation result
Assessment factor is referred to risk；
Training sample set input Recognition with Recurrent Neural Network is obtained into prediction result；
According to the parameter of prediction result and mark adjustment Recognition with Recurrent Neural Network, goes directly and reach iteration stopping condition, determined
Plan model.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Instruct relevant hardware to complete by computer program, computer program to can be stored in a non-volatile computer readable
It takes in storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, this Shen
Please provided by any reference used in each embodiment to memory, storage, database or other media, may each comprise
Non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
Above embodiments only express the several embodiments of the application, and the description thereof is more specific and detailed, but can not
Therefore it is construed as limiting the scope of the patent.It should be pointed out that for those of ordinary skill in the art,
Under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection scope of the application.
Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of trade company's risk management and control method, which comprises
It obtains trade company's risk evaluation result and risk refers to assessment factor；
Trade company's risk evaluation result and the risk are inputted into decision model with reference to assessment factor, pass through the decision model
Obtain the decision instruction to trade company；
Impact factor is calculated according to the influence information of the trade company and the decision instruction；
Control instruction is obtained according to the impact factor；
The control instruction is responded, alignment processing is carried out to trade company's account.
2. the method according to claim 1, wherein according to the influence information and the decision instruction of the trade company
The step of calculating impact factor, comprising:
Corresponding first impact factor of the influence information for calculating the trade company from default dimension；
Corresponding second impact factor of the decision instruction is calculated from default dimension；
Obtain the first weight of first impact factor and the second weight of second impact factor；
According to first weight, the second weight, the first impact factor and the second impact factor, weighting obtains impact factor.
3. the method according to claim 1, wherein described obtain the step of control instruction according to the impact factor
Suddenly, comprising:
The decision instruction is adjusted according to the impact factor, obtains control instruction.
4. according to the method described in claim 3, it is characterized in that, being obtained according to the impact factor adjustment decision instruction
To the step of control instruction, comprising:
When the impact factor is greater than, and threshold value is turned up, the rank of the decision instruction is turned up, obtains control instruction；
When the impact factor, which is less than, turns down threshold value, the rank of the decision instruction is turned down, obtains control instruction.
5. the method according to claim 1, wherein described obtain the step of control instruction according to the impact factor
Suddenly, comprising:
The decision instruction and the impact factor are sent to processing terminal, the control for obtaining the processing terminal feedback refers to
It enables, the control instruction after response trigger action of the treatment people based on the decision instruction and the impact factor by sending out
Out.
6. according to the method described in claim 5, it is characterized in that, the decision instruction and the impact factor are sent to place
The step of managing terminal, comprising:
By the size order of the impact factor, the decision instruction and the impact factor are sent to processing terminal.
7. the method according to claim 1, wherein the method also includes:
The sample data of decision instruction will be labelled with as training sample set；The sample data includes trade company's risk assessment
As a result assessment factor is referred to the risk；
Training sample set input Recognition with Recurrent Neural Network is obtained into prediction result；
According to the parameter of the prediction result and mark adjustment Recognition with Recurrent Neural Network, goes directly and reach iteration stopping condition, determined
Plan model.
8. a kind of trade company's risk management and control device, which is characterized in that described device includes:
Parameter acquisition module, for obtaining trade company's risk evaluation result and risk with reference to assessment factor；
Decision obtains module, for trade company's risk evaluation result and the risk to be inputted decision model with reference to assessment factor
Type obtains the decision instruction to trade company by the decision model；
Impact factor computing module, for calculating impact factor according to the influence information of the trade company and the decision instruction；
Control obtains module, for obtaining control instruction according to the impact factor；
Processing module carries out alignment processing to trade company's account for responding the control instruction.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811532336.7A CN109767314A (en) | 2018-12-14 | 2018-12-14 | Trade company's risk management and control method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811532336.7A CN109767314A (en) | 2018-12-14 | 2018-12-14 | Trade company's risk management and control method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109767314A true CN109767314A (en) | 2019-05-17 |
Family
ID=66451878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811532336.7A Pending CN109767314A (en) | 2018-12-14 | 2018-12-14 | Trade company's risk management and control method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767314A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111967779A (en) * | 2020-08-19 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030130919A1 (en) * | 2001-11-20 | 2003-07-10 | Randy Templeton | Systems and methods for selectively accessing financial account information |
| CN105279691A (en) * | 2014-07-25 | 2016-01-27 | 中国银联股份有限公司 | Financial transaction detection method and equipment based on random forest model |
| CN108564386A (en) * | 2018-04-28 | 2018-09-21 | 腾讯科技（深圳）有限公司 | Trade company's recognition methods and device, computer equipment and storage medium |
-
2018
- 2018-12-14 CN CN201811532336.7A patent/CN109767314A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030130919A1 (en) * | 2001-11-20 | 2003-07-10 | Randy Templeton | Systems and methods for selectively accessing financial account information |
| CN105279691A (en) * | 2014-07-25 | 2016-01-27 | 中国银联股份有限公司 | Financial transaction detection method and equipment based on random forest model |
| CN108564386A (en) * | 2018-04-28 | 2018-09-21 | 腾讯科技（深圳）有限公司 | Trade company's recognition methods and device, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111967779A (en) * | 2020-08-19 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
| CN111967779B (en) * | 2020-08-19 | 2022-12-16 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI784941B (en) | A multi-sampling model training method and device | |
| CN106779755A (en) | A kind of network electric business borrows or lends money methods of risk assessment and model | |
| CN108053318A (en) | It is a kind of to the method and device that is identified of merchandising extremely | |
| TW201723968A (en) | Method of monitoring suspicious transactions | |
| CN111008896A (en) | Financial risk early warning method and device, electronic equipment and storage medium | |
| CN107705036A (en) | Dynamic credit estimation method and system based on multi-dimensional data | |
| CN111681102B (en) | Credit prediction method, apparatus, device and storage medium | |
| CN107895324A (en) | Insurance examination ＆ verification apparatus and method | |
| Wang et al. | Can gold hedge against oil price movements: Evidence from GARCH-EVT wavelet modeling | |
| CN113177839A (en) | Credit risk assessment method, device, storage medium and equipment | |
| CN109658256A (en) | Risk control method, device, equipment and readable storage medium storing program for executing | |
| CN112700321A (en) | Multi-rule anti-fraud prediction method and system based on user behavior data | |
| Shabbir et al. | Determinants of economic stability through female unemployment: Evidence from Pakistan | |
| CN111506876A (en) | Data prediction analysis method, system, equipment and readable storage medium | |
| CN109767314A (en) | Trade company's risk management and control method, device, computer equipment and storage medium | |
| Mohammed et al. | The reaction of the metal and gold resource planning in the post-COVID-19 era and Russia-Ukrainian conflict: Role of fossil fuel markets for portfolio hedging strategies | |
| CN110472956A (en) | Decouple pay behavior real-time detection method and device | |
| CN114139931A (en) | Enterprise data evaluation method and device, computer equipment and storage medium | |
| Cheng et al. | Surrender contagion in life insurance | |
| CN109858922A (en) | Improper taxpayer's recognition methods and device | |
| Ocal et al. | Corporate ratings and a model proposition for the manufacturing industry at Borsa Istanbul | |
| Raggad et al. | Gold and crude oil: A time-varying causality across various market conditions | |
| US11915313B2 (en) | Using email history to estimate creditworthiness for applicants having insufficient credit history | |
| Ma | Study on risk spillover effects of shadow banks on traditional banks in China | |
| Savadatti | Sectoral Analysis of Bombay Stock Exchange Application of GARCH Model |
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 |