CN109857373A - Business data processing method, device, computer equipment and storage medium - Google Patents
Business data processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109857373A CN109857373A CN201811553151.4A CN201811553151A CN109857373A CN 109857373 A CN109857373 A CN 109857373A CN 201811553151 A CN201811553151 A CN 201811553151A CN 109857373 A CN109857373 A CN 109857373A
- Authority
- CN
- China
- Prior art keywords
- decision
- risk
- face
- variable
- tree
- 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
Abstract
This application involves a kind of business data processing method, device, computer equipment and storage mediums.It is related to intelligent decision field.The described method includes: determining the corresponding business division of business application, the corresponding decision in the face of risk tree of the business division is obtained；Decision in the face of risk variable is orderly extracted from the decision in the face of risk tree, obtains the corresponding data source of each decision in the face of risk variable；Sequence is input in the decision in the face of risk tree in the first corresponding data source of the decision in the face of risk variable, obtains the hit results of the first decision rule, the hit results are rule hit and regular miss；The corresponding data source of next decision in the face of risk variable is input in the decision in the face of risk tree, until the obtained hit results are rule hit, exports the result of decision.Air control verification efficiency can be improved using this method.
Description
Technical field
This application involves field of computer technology, set more particularly to a kind of business data processing method, device, computer
Standby and storage medium.
Background technique
With the rapid development of computer and Internet technology, many business can carry out on network, to user with
Great convenience is carried out.At the same time, service provider has also taken on many risks, if service request is malice, if
Service provider directly receives the business of these users in the case where no precautionary measures, can suffer from losing.In order to reduce
Risk, service provider can for active user current business carry out decision in the face of risk, the result of decision be usually receive or
Refusal, and then can receive or refuse current business accordingly based upon the result of decision.
When traditional decision in the face of risk, then Developmental Engineer's redaction rule code makes in code level definition rule model
Service request is verified with rule model, rule needs to obtain strictly all rules corresponding verification data when verifying, and scale model will
The completion of strictly all rules complete verification can just obtain check results, therefore, there are air controls to verify low efficiency for traditional decision in the face of risk mode,
The time-consuming big defect of air control verification.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of business datum that can be improved air control verification efficiency
Processing method, device, computer equipment and storage medium.
A kind of business data processing method, which comprises
It determines the corresponding business division of business application, obtains the corresponding decision in the face of risk tree of the business division；
Decision in the face of risk variable is orderly extracted from the decision in the face of risk tree, and it is corresponding to obtain each decision in the face of risk variable
Data source；
Sequence is input in the decision in the face of risk tree in the first corresponding data source of the decision in the face of risk variable, is obtained
The hit results of the first decision rule, the hit results are rule hit and regular miss；
The corresponding data source of next decision in the face of risk variable is input in the decision in the face of risk tree until the life
Middle result is rule hit, obtains the result of decision.
In one embodiment, in the corresponding business division of the determining business application, it is corresponding to obtain the business division
Decision in the face of risk tree before, further includes:
The corresponding data on stock of the business division is obtained, the data on stock includes internal history data and external history
Data；
The first decision in the face of risk variable is determined from the internal history data, determines second from the external historical data
Decision in the face of risk variable；
The variable configuration information that regular configuration interface is submitted is received, each risk is generated according to the variable configuration information and is determined
The corresponding decision rule of plan variable；
It connects the decision rule and generates decision in the face of risk tree, wherein described in the first decision in the face of risk variable is corresponding certainly
Plan rule is located at the upstream of the decision in the face of risk tree, and the corresponding decision rule of the second decision in the face of risk variable is located at described
The downstream of decision in the face of risk tree.
In one embodiment, described orderly to extract decision in the face of risk variable from the decision in the face of risk tree, obtain each institute
State the corresponding data source of decision in the face of risk variable, comprising:
Decision in the face of risk variable is extracted from the decision in the face of risk tree, the decision in the face of risk variable includes that first risk is determined
Plan variable and the second decision in the face of risk variable；
Obtain the corresponding data source of the first decision in the face of risk variable；
If the corresponding data source of the first decision in the face of risk variable is not hit by the decision in the face of risk tree, described the is obtained
The corresponding data source of two decision in the face of risk variables.
In one embodiment, the connection decision rule generates decision in the face of risk tree, comprising:
Obtain the syntagmatic of decision in the face of risk variable predetermined；
The corresponding decision rule of the decision in the face of risk variable is combined according to the syntagmatic；
The orderly decision rule after connection combination, generates decision in the face of risk tree.
In one embodiment, it is orderly connected after the decision rule generates decision in the face of risk tree described, further includes:
Obtain the corresponding positive negative sample of the business division；
Risk anticipation is carried out to the positive negative sample based on the decision in the face of risk tree, obtains risk anticipation result；
Calculate the matching degree of the positive and negative attribute of the risk anticipation result and the positive negative sample；
If matching degree is less than given threshold, the erroneous judgement rule section that the erroneous judgement sample corresponds to the decision in the face of risk tree is obtained
Point.
In one embodiment, the method also includes:
Risks and assumptions are monitored, the risks and assumptions are the corresponding hot word of hot word set for being in advance the business division configuration
Public feelings information；
If the Long-term change trend of the hot word public feelings information reaches given threshold, the alarm of business division risk is generated, is based on
The risk alerts the decision in the face of risk tree corresponding to the business division and is adjusted.
A kind of service data processing apparatus, described device include:
Decision in the face of risk tree obtains module and obtains the business division pair for determining the corresponding business division of business application
The decision in the face of risk tree answered；
Data source extraction module obtains each institute for orderly extracting decision in the face of risk variable from the decision in the face of risk tree
State the corresponding data source of decision in the face of risk variable；
Decision-making module, for sequence to be input to the risk in the first corresponding data source of the decision in the face of risk variable
In decision tree, the hit results of the first decision rule are obtained, the hit results are rule hit and regular miss；
Result of decision output module, for the corresponding data source of next decision in the face of risk variable to be input to the wind
Until the hit results are rule hit in dangerous decision tree, the result of decision is obtained.
In one embodiment, described device further include:
Data on stock obtains module, and for obtaining the corresponding data on stock of the business division, the data on stock includes
Internal history data and external historical data；
Decision in the face of risk variant determination module, for determining the first decision in the face of risk variable from the internal history data, from
The second decision in the face of risk variable is determined in the external historical data；
Decision rule generation module, the variable configuration information submitted for receiving regular configuration interface, according to the variable
Configuration information generates the corresponding decision rule of each decision in the face of risk variable；
Decision in the face of risk tree generation module generates decision in the face of risk tree for connecting the decision rule, wherein first wind
The corresponding decision rule of dangerous decision variable is located at the upstream of the decision in the face of risk tree, and the second decision in the face of risk variable is corresponding
The decision rule be located at the downstream of the decision in the face of risk tree.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes method described above 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 above is realized when row.
Above-mentioned business data processing method, device, computer equipment and storage medium, the decision in the face of risk for air control decision
Decision rule in tree is the rule based on decision in the face of risk variable, is first obtained before carrying out risk verification by decision in the face of risk tree every
The corresponding data source of a decision in the face of risk variable, so that decision in the face of risk tree can directly verify data source code fo practice, without
Other data processings, and the verification mode that decision in the face of risk tree is exited using rule hit are done again, without verifying strictly all rules, because
This, the efficiency of air control verification is significantly improved.
Detailed description of the invention
Fig. 1 is the application scenario diagram of business data processing method in one embodiment；
Fig. 2 is the flow diagram of business data processing method in one embodiment；
Fig. 3 is one embodiment risk decision tree schematic illustration；
Fig. 4 is flow diagram involved in one embodiment risk decision tree generates；
Fig. 5 is flow diagram involved in one embodiment risk decision and control；
Fig. 6 is the structural block diagram of service data processing apparatus in one embodiment；
Fig. 7 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.
Business data processing method provided by the present application can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated with server 104 by network by network.Terminal 102 sends business application, service to server 104
Device 104 carries out decision in the face of risk to business application by decision in the face of risk tree, and judgement is currently also whether risk business, and refuses wind
Dangerous business.Wherein, terminal 102 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer
With portable wearable device, server 104 can use the server set of the either multiple server compositions of independent server
Group realizes.
In one embodiment, as shown in Fig. 2, providing a kind of business data processing method, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
Step 202, it determines the corresponding business division of business application, obtains the corresponding decision in the face of risk tree of business division.
It can be according to the financial product or financial product classifying and dividing business division of financial institution, different financial products
As different business divisions or the classification of different financial products as different business divisions.It can also be according to business application
People divides business division, and different business applicants is as different business divisions.Such as using enterprise A as a business division,
Enterprise B is as another financial subject.
After dividing business division, the corresponding decision in the face of risk tree of each business division is pre-defined.Decision in the face of risk tree is by extremely
The regular flow that few regular connection of two decisions in the face of risk is formed, wherein each decision in the face of risk rule corresponds to a decision in the face of risk
Variable.By taking business division is loan as an example, the decision in the face of risk rule of corresponding decision in the face of risk tree can be with applicant's age limit
(25-55)-decision in the face of risk variable be the age, loan number limitation-decision in the face of risk variable be loan number.It that is to say, this implementation
Decision in the face of risk tree in example is using top-down sequence, and the decision rule being made of decision in the face of risk variable is orderly built
Tree structure.
Financial product information to be transacted and service request people's information are included at least in business application, are extracted from business application
Characteristic information determines the corresponding business division of business application based on characteristic information.After determining business division, business division is obtained
Corresponding decision in the face of risk tree.
Step 204, decision in the face of risk variable is orderly extracted from decision in the face of risk tree, and it is corresponding to obtain each decision in the face of risk variable
Data source.
Decision in the face of risk variable is extracted from decision rule each in decision in the face of risk tree, and decision rule is determined decision tree in risk
Tree structure in sequence of the top-down position as decision in the face of risk variable.
As shown in figure 3, the right side of Fig. 3 is the top-down sequence of decision rule in decision in the face of risk tree, according to decision rule
With the one-to-one relationship of decision in the face of risk variable, the sequence of decision in the face of risk variable extracted in decision in the face of risk tree is obtained are as follows: risk
Decision variable 1 (sequence is the first)-decision in the face of risk variable 2 ... decision in the face of risk variable 5- decision in the face of risk variable 6.
After extracting decision in the face of risk variable, business datum relevant to current business application to be verified is obtained, from business number
The corresponding data source of each decision in the face of risk variable is extracted according to middle.The corresponding data source of decision in the face of risk variable includes decision in the face of risk variable
Example value or decision in the face of risk variant content or decision in the face of risk variable instance value and decision in the face of risk variant content.For example,
The corresponding data source of variable " applicant's age " is the applicant's age value extracted from applicant's information, such as 35 years old.
Step 206, sequence is input in decision in the face of risk tree in the first corresponding data source of decision in the face of risk variable, is obtained
The hit results of the first decision rule, hit results are rule hit and regular miss.
According to the sequence of decision in the face of risk variable, successively the corresponding data source of decision in the face of risk variable is input to and to be constructed in advance
In decision in the face of risk tree, decision rule corresponding with decision in the face of risk variable verifies the data source, and obtains being directed to the number
According to the hit results in source.Specifically, if example value or variant content described in data source decision in the face of risk rule rule
In range or outer, then data source hits decision in the face of risk rule.Such as the first decision in the face of risk rule is year in decision in the face of risk tree
Whether age is in (25-55) range, if it is not, then data source hits decision in the face of risk rule, after rule hit, no longer to other numbers
It is verified according to source, directly obtains regular check results.Regular check results are that business application is risk business application, and risk refers to
It is designated as the decision in the face of risk rule of hit.
Step 208, the corresponding data source of next decision in the face of risk variable is input in decision in the face of risk tree, until obtain
Hit results are rule hit, export the result of decision.
If decision in the face of risk variable corresponding data source in first place is not hit by the first decision in the face of risk rule, by next bit risk
The data source of decision variable, which is input in decision in the face of risk tree, carries out regular verification, until rule hit, obtains check results, or
Until all data sources are not hit by corresponding decision in the face of risk rule, and obtained regular check results, regular check results
It is regular traffic application for business application.
It is the rule based on decision in the face of risk variable for the rule in the decision in the face of risk tree of air control decision in the present embodiment,
The corresponding data source of each decision in the face of risk variable is first obtained before carrying out risk verification by decision in the face of risk tree, so that decision in the face of risk
Tree can directly verify data source code fo practice, without doing other data processings, data of the decision in the face of risk tree to input again
Source quick response obtains check results, improves the efficiency of air control verification, and decision in the face of risk tree is to exit using rule hit
It is time-consuming to further shorten air control verification without verifying strictly all rules for verification mode.
In one embodiment, the decision in the face of risk variable in decision in the face of risk tree includes the decision in the face of risk for being internally sourced data
Variable and decision in the face of risk variable from external data, and decision in the face of risk variable pair is determined according to the source of decision in the face of risk variable
Sequence of the decision rule answered in decision in the face of risk tree.Decision in the face of risk tree, which generates, to be included the following steps, it should be noted that risk is determined
Plan tree generation step should be implemented before business data processing method in the above-described embodiments.
As shown in figure 4, a kind of decision in the face of risk tree generation method includes:
Step 402, the corresponding data on stock of business division is obtained, data on stock includes internal history data and external history
Data.
The internal history data of business division refer to the business that can be got from local platform or group internal platform
The relevant historical data of main body.The external historical data of business division refers to other than local platform or group internal platform
The historical data relevant to business division that third-party platform obtains, third-party platform such as mobile operator platform, electric business platform.
More precisely, internal history data are not need the data that can get of payment, and external historical data is to need to pay ability
The data enough got, if the data of third-party platform are open source data, which is also classified as internal history data.
Step 404, the first decision in the face of risk variable is determined from internal history data, and second is determined from external historical data
Decision in the face of risk variable.
Internal history data and external historical data to acquisition carry out data processing, will determine from internal history data
Variable-definition out is the first decision in the face of risk variable, determines that the variable-definition of electric arc is that the second risk is determined from external historical data
Plan variable.Wherein, the first decision in the face of risk variable and the second decision in the face of risk variable include the variable directly determined out from data
With the variable being derived by Direct Variable.
First decision in the face of risk variable can be age, loan number, history application comparison etc.；Second decision in the face of risk variable can
To be talk times, phone number self-test of frequent contact etc., mobile communication state etc..
Step 406, the variable configuration information that regular configuration interface uploads is received, each wind is generated according to variable configuration information
The corresponding decision rule of dangerous decision variable.
After determining the corresponding first decision in the face of risk variable of business division and the second decision in the face of risk variable, by the first decision in the face of risk
Variable and the second decision in the face of risk variable association are into regular configuration interface.Then receive the variable configuration that regular configuration interface uploads
Information, variable configuration information include the configuration of the variable and the variable to selection of selection, and then according to the configuration information of variable
Generate the decision rule of corresponding decision in the face of risk variable.Wherein.
Variable configuration information includes specifying variable, Variable Conditions, condition distinguishing symbol, variate-value (range of variables), Mei Gebian
The corresponding result of decision of amount condition, variable configuration information include at least two Variable Conditions, and one Variable Conditions are hit variable
Condition, secondly condition be miss Variable Conditions.
Step 408, connection decision rule generates decision in the face of risk tree, wherein the corresponding decision rule of the first decision in the face of risk variable
Then it is located at the upstream of decision in the face of risk tree, the corresponding decision rule of the second decision in the face of risk variable is located at the downstream of decision in the face of risk tree.
After rule-based configuration interface generates multiple decision rules, multiple decision rules are connected into top-down tree-like
Structure generates decision in the face of risk tree.In the present embodiment, decision in the face of risk tree includes the corresponding decision rule of the first decision in the face of risk variable
Then decision rule corresponding with the second decision in the face of risk variable.When connecting decision rule, the first decision in the face of risk variable is corresponding certainly
The connection of plan rule is first, after the corresponding decision rule of the second decision in the face of risk variable is connected to.As shown in figure 3, decision rule 1- determines
Plan 3 corresponding decision in the face of risk variables of rule are the first decision in the face of risk variable, and the corresponding risk of decision rule 4- decision rule 6 is determined
Plan variable is the second decision in the face of risk variable.
It, can be first from industry to be verified when further, based on above-mentioned decision in the face of risk tree carry out business application risk verification
It is engaged in obtaining the corresponding data source of the first decision in the face of risk variable for being located at decision tree upstream in the internal data of application.And in order will
The corresponding data source of first decision in the face of risk variable, which is input in decision in the face of risk tree, carries out regular verification, if rule hit, is exited
Rule verification obtains the result of decision.Without obtaining external data from third-party platform, without obtaining the second decision in the face of risk variable
Corresponding data source reduces the acquisition probability of external data source, reduces data call cost.
If the corresponding data source of the first decision in the face of risk variable not by decision in the face of risk tree hit, from third-party platform obtain with
The relevant external data of business application obtains the corresponding data source of the second decision in the face of risk variable from external data, and by the second wind
The corresponding data source of dangerous decision tree is input to progress risk verification in decision in the face of risk tree, until obtaining the result of decision.
In the present embodiment, decision in the face of risk variable source is internal data and external data, and different sources makes risk determine
Plan rule is more abundant, different data sources determine decision rule in the sequence of decision in the face of risk tree, external source is corresponding
Decision in the face of risk rule setting reduces external decision and becomes in the downstream of decision in the face of risk tree, the verification mode that hit is exited in addition
The data source of amount participates in the probability of verification, thereby reduces the acquisition probability of external data source, reduces data call cost.
Further, by decision in the face of risk rule configuration interface in the present embodiment, decision rule can pass through configuration interface reality
Now flexibly convenient configuration and adjustment, improves the timeliness of rule deployment.
In one embodiment, step 308, connection decision rule generates decision in the face of risk tree, comprising: obtains predetermined
The syntagmatic of decision in the face of risk variable；According to the corresponding decision rule of syntagmatic constitution's risk decision variable；Orderly connection group
Decision rule after conjunction generates decision in the face of risk tree.
Specifically, it is right to search multiple decision in the face of risk rules after rule-based configuration interface configuration generates multiple decision rules
It whether there is syntagmatic between the decision in the face of risk variable answered, if so, obtaining syntagmatic.For example, decision to be connected
There is combination to close by the decision in the face of risk variables A and decision in the face of risk variable B that rule is related to, decision in the face of risk variables A and decision in the face of risk variable B
System, such as AB combination and A is before B1 (syntagmatic includes combination sequence).It is then according to syntagmatic, risk is corresponding according to variable is surveyed
Decision rule be combined, and then the decision rule after combination is advised with other decision rules or decision as a whole
Then combination is attached, and ultimately generates top-down decision in the face of risk tree.
It should be noted that syntagmatic includes between internal risks decision variable, is between Outer risks decision variable and interior
The combination of portion decision in the face of risk variable and Outer risks decision variable.
It in one embodiment, can when Outer risks decision variable and internal risks decision variable have syntagmatic
The decision rule combination corresponding with the combination of internal risks decision variable of Outer risks decision variable is placed in decision in the face of risk tree
Upstream or downstream.That is, since there are the upstreams of syntagmatic, decision in the face of risk tree can wrap containing Outer risks decision
The corresponding decision rule of variable, correspondingly, the downstream of decision in the face of risk tree also can wrap it is corresponding containing internal risks decision variable
Decision rule.
In one embodiment, as shown in figure 5, in step 406: after generating decision in the face of risk tree, further includes:
Step 502, the corresponding positive negative sample of business division is obtained.
Step 504, risk anticipation is carried out to positive negative sample based on decision in the face of risk tree, obtains risk anticipation result.
Sample is input in decision in the face of risk tree, decision in the face of risk tree is obtained and result is prejudged to the risk of each sample.Risk
Prejudging result includes risk sample and normal sample.
Step 506, the matching degree of the positive and negative attribute of calculation risk anticipation result and positive negative sample.
Risk sample matches with negative sample attribute, normal sample and positive sample attribute phase configuration.If sample is positive sample,
And decision in the face of risk tree is risk sample to the risk of sample anticipation result, then the positive and negative attribute of risk anticipation result and sample is not
Match, matching degree is calculated according to the accounting for the sample set that mismatches.
Step 508, if matching degree is less than given threshold, the erroneous judgement rule section that erroneous judgement sample corresponds to decision in the face of risk tree is obtained
Point.
Pre-defined matching degree threshold value, if the matching degree calculated is less than matching degree threshold value, the decision of decision in the face of risk tree is quasi-
Exactness is lower, needs to be adjusted decision in the face of risk tree, including adjusting the configuration of decision rule and the sequence of decision rule.
Specifically, the corresponding erroneous judgement rules results of erroneous judgement sample are obtained when the matching degree of calculating is less than matching degree threshold value,
Wherein, erroneous judgement sample is the preparatory result of risk and the sample that sample attribute does not match that.Judging regular node by accident is rule hit section
Point, wherein be mistaken for the rule hit node of risk sample.The case where being mistaken for normal sample if it exists can obtain the erroneous judgement
For the corresponding rule hit node of negative sample of normal sample.Preassign the corresponding rule hit node of negative sample.Namely
It says, the rule hit node for being mistaken for risk sample is exported by decision in the face of risk tree, is mistaken for the rule hit node of normal sample
It preassigns.
Erroneous judgement regular node is sent to terminal, the rule-based configuration interface of engineer matches the rule of erroneous judgement regular node
Set and node where position in decision in the face of risk tree be adjusted.New decision in the face of risk tree is generated according to information adjusted,
Until the risk anticipation result of decision in the face of risk tree and the positive and negative attributes match degree of positive negative sample are greater than given threshold.
In one embodiment, hot word set is configured for each business division in advance, and it is corresponding to monitor hot word public feelings information
Hot word public sentiment Long-term change trend (i.e. risks and assumptions).If hot word public sentiment trend dynamic change reaches given threshold, business is generated
Main body risk alarm, wherein include the clue letter extracted from hot word public sentiment trend multidate information in the alarm of business division risk
Breath is adjusted the corresponding decision in the face of risk tree of business division based on the alarm of business division risk.Specifically, being accused from business risk
Hint information is obtained in police, and based on the regular node of hint information positioning decision in the face of risk tree, the regular node of positioning is adjusted
It is whole.Such as know that there are credit high risks in somewhere, generate business division risk announcement after finding risk in time by correlation public sentiment
It is alert.
In the present embodiment by monitoring public feelings information find decision in the face of risk loophole, based on loophole carry out decision in the face of risk tree and
When adjust.
It should be understood that although each step in the flow chart of Fig. 2-5 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-5
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in fig. 6, providing a kind of service data processing apparatus, including
Decision in the face of risk tree obtains module 602 and obtains the business division for determining the corresponding business division of business application
Corresponding decision in the face of risk tree.
Data source extraction module 604 obtains each for orderly extracting decision in the face of risk variable from the decision in the face of risk tree
The corresponding data source of the decision in the face of risk variable.
Decision-making module 606, it is described for sequence to be input in the first corresponding data source of the decision in the face of risk variable
In decision in the face of risk tree, the hit results of the first decision rule are obtained, the hit results are rule hit and regular miss.
Result of decision output module 608, for the corresponding data source of next decision in the face of risk variable to be input to institute
It states in decision in the face of risk tree until the hit results are rule hit, obtains the result of decision.
In one embodiment, service data processing apparatus further include:
Data on stock obtains module, and for obtaining the corresponding data on stock of the business division, the data on stock includes
Internal history data and external historical data；Decision in the face of risk variant determination module, for being determined from the internal history data
First decision in the face of risk variable determines the second decision in the face of risk variable from the external historical data；Decision rule generation module is used
In the variable configuration information for receiving regular configuration interface submission, each decision in the face of risk variable is generated according to the variable configuration information
Corresponding decision rule；Decision in the face of risk tree generation module generates decision in the face of risk tree for connecting the decision rule, wherein institute
State the upstream that the corresponding decision rule of the first decision in the face of risk variable is located at the decision in the face of risk tree, second decision in the face of risk
The corresponding decision rule of variable is located at the downstream of the decision in the face of risk tree.
In one embodiment, data source extraction module 604 is also used to orderly extract risk from the decision in the face of risk tree
Decision variable, the decision in the face of risk variable include the first decision in the face of risk variable and the second decision in the face of risk variable；It obtains
The corresponding data source of the first decision in the face of risk variable；If the corresponding data source of the first decision in the face of risk variable is not by the wind
Dangerous decision tree hit, then obtain the corresponding data source of the second decision in the face of risk variable.
In one embodiment, decision in the face of risk tree generation module is also used to obtain decision in the face of risk variable predetermined
Syntagmatic；The corresponding decision rule of the decision in the face of risk variable is combined according to the syntagmatic；Orderly after connection combination
The decision rule generates decision in the face of risk tree.
In one embodiment, service data processing apparatus further include: decision in the face of risk tree adjusts module, described for obtaining
The corresponding positive negative sample of business division；Risk anticipation is carried out to the positive negative sample based on the decision in the face of risk tree, obtains risk
Prejudge result；Calculate the matching degree of the positive and negative attribute of the risk anticipation result and the positive negative sample；If the matching degree is small
In given threshold, then the corresponding erroneous judgement regular node of erroneous judgement sample is determined from the decision in the face of risk tree.
In one embodiment, decision in the face of risk tree adjusts module, is also used to monitor risks and assumptions, the risks and assumptions are institute
State the corresponding hot word public feelings information of hot word set of business division configuration；It is set if the Long-term change trend of the hot word public feelings information reaches
Determine threshold value, then generate the alarm of business division risk, the risk corresponding to the business division is alerted based on the risk and is determined
Plan tree is adjusted.
Specific about service data processing apparatus limits the limit that may refer to above for business data processing method
Fixed, details are not described herein.Modules in above-mentioned service data processing apparatus 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 7.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing decision in the face of risk tree.The network interface of the computer equipment is used to pass through net with external terminal
Network connection communication.To realize a kind of business data processing method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 7, 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 the corresponding business division of determining business application when executing computer program, obtain
Take the corresponding decision in the face of risk tree of the business division；Decision in the face of risk variable is orderly extracted from the decision in the face of risk tree, is obtained every
The corresponding data source of a decision in the face of risk variable；By sequence in the first corresponding data source input of the decision in the face of risk variable
To the hit results of the first decision rule in the decision in the face of risk tree, are obtained, the hit results are that rule is hit with rule not
Hit；The corresponding data source of next decision in the face of risk variable is input in the decision in the face of risk tree, until obtained institute
Hit results are stated as rule hit, export the result of decision.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains the business division
Corresponding data on stock, the data on stock include internal history data and external historical data；From the internal history data
Middle the first decision in the face of risk of determination variable determines the second decision in the face of risk variable from the external historical data；Receive rule configuration
The variable configuration information that interface is submitted generates the corresponding decision of each decision in the face of risk variable according to the variable configuration information and advises
Then；It connects the decision rule and generates decision in the face of risk tree, wherein the corresponding decision rule of the first decision in the face of risk variable
Positioned at the upstream of the decision in the face of risk tree, the corresponding decision rule of the second decision in the face of risk variable is located at the risk and determines
The downstream of plan tree.
In one embodiment, it also performs the steps of when processor executes computer program from the decision in the face of risk tree
In orderly extract decision in the face of risk variable, the decision in the face of risk variable includes the first decision in the face of risk variable and second risk
Decision variable；Obtain the corresponding data source of the first decision in the face of risk variable；If the corresponding number of the first decision in the face of risk variable
It is not hit by the decision in the face of risk tree according to source, then obtains the corresponding data source of the second decision in the face of risk variable.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains wind predetermined
The syntagmatic of dangerous decision variable；The corresponding decision rule of the decision in the face of risk variable is combined according to the syntagmatic；Orderly
The decision rule after connection combination, generates decision in the face of risk tree.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains the business division
Corresponding positive negative sample；Risk anticipation is carried out to the positive negative sample based on the decision in the face of risk tree, obtains risk anticipation result；
Calculate the matching degree of the positive and negative attribute of the risk anticipation result and the positive negative sample；If the matching degree is less than setting threshold
Value then determines the corresponding erroneous judgement regular node of erroneous judgement sample from the decision in the face of risk tree.
In one embodiment, monitoring risks and assumptions are also performed the steps of when processor executes computer program, it is described
Risks and assumptions are the corresponding hot word public feelings information of hot word set of business division configuration；If the hot word public feelings information becomes
Gesture variation reaches given threshold, then generates the alarm of business division risk, corresponding to the business division based on risk alarm
The decision in the face of risk tree be adjusted.
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 determining business application corresponding business division when being executed by processor, obtain the business division
Corresponding decision in the face of risk tree；Decision in the face of risk variable is orderly extracted from the decision in the face of risk tree, obtains each decision in the face of risk
The corresponding data source of variable；Sequence is input to the decision in the face of risk in the first corresponding data source of the decision in the face of risk variable
In tree, the hit results of the first decision rule are obtained, the hit results are rule hit and regular miss；By next institute
It states the corresponding data source of decision in the face of risk variable to be input in the decision in the face of risk tree, until the obtained hit results are rule
Hit exports the result of decision.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains the business master
The corresponding data on stock of body, the data on stock include internal history data and external historical data；From the internal history number
According to middle the first decision in the face of risk of determination variable, the second decision in the face of risk variable is determined from the external historical data；Rule is received to match
The variable configuration information for setting interface submission generates the corresponding decision of each decision in the face of risk variable according to the variable configuration information and advises
Then；It connects the decision rule and generates decision in the face of risk tree, wherein the corresponding decision rule of the first decision in the face of risk variable
Positioned at the upstream of the decision in the face of risk tree, the corresponding decision rule of the second decision in the face of risk variable is located at the risk and determines
The downstream of plan tree.
In one embodiment, it is also performed the steps of when computer program is executed by processor from the decision in the face of risk
Decision in the face of risk variable is orderly extracted in tree, the decision in the face of risk variable includes the first decision in the face of risk variable and second wind
Dangerous decision variable；Obtain the corresponding data source of the first decision in the face of risk variable；If the first decision in the face of risk variable is corresponding
Data source is not hit by the decision in the face of risk tree, then obtains the corresponding data source of the second decision in the face of risk variable.
In one embodiment, it is predetermined that acquisition is also performed the steps of when computer program is executed by processor
The syntagmatic of decision in the face of risk variable；The corresponding decision rule of the decision in the face of risk variable is combined according to the syntagmatic；Have
The decision rule after sequence connection combination, generates decision in the face of risk tree.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains the business master
The corresponding positive negative sample of body；Risk anticipation is carried out to the positive negative sample based on the decision in the face of risk tree, obtains risk anticipation knot
Fruit；Calculate the matching degree of the positive and negative attribute of the risk anticipation result and the positive negative sample；If the matching degree is less than setting
Threshold value then determines the corresponding erroneous judgement regular node of erroneous judgement sample from the decision in the face of risk tree.
In one embodiment, monitoring risks and assumptions, institute are also performed the steps of when computer program is executed by processor
State the corresponding hot word public feelings information of hot word set that risks and assumptions are business division configuration；If the hot word public feelings information
Long-term change trend reaches given threshold, then generates the alarm of business division risk, alerted based on the risk to the business division pair
The decision in the face of risk tree answered is adjusted.
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
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including 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 in a variety of forms may be used
, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM),
Enhanced SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) are 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.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of business data processing method, which comprises
It determines the corresponding business division of business application, obtains the corresponding decision in the face of risk tree of the business division；
Decision in the face of risk variable is orderly extracted from the decision in the face of risk tree, obtains the corresponding data of each decision in the face of risk variable
Source；
Sequence is input in the decision in the face of risk tree in the first corresponding data source of the decision in the face of risk variable, obtains first place
The hit results of decision rule, the hit results are rule hit and regular miss；
The corresponding data source of next decision in the face of risk variable is input in the decision in the face of risk tree, until obtaining described
Hit results are rule hit, export the result of decision.
2. the method according to claim 1, wherein being obtained in the corresponding business division of the determining business application
Before taking the corresponding decision in the face of risk tree of the business division, further includes:
The corresponding data on stock of the business division is obtained, the data on stock includes internal history data and external history number
According to；
The first decision in the face of risk variable is determined from the internal history data, determines the second risk from the external historical data
Decision variable；
The variable configuration information that regular configuration interface is submitted is received, each decision in the face of risk is generated according to the variable configuration information and is become
Measure corresponding decision rule；
It connects the decision rule and generates decision in the face of risk tree, wherein the corresponding decision of the first decision in the face of risk variable is advised
Then it is located at the upstream of the decision in the face of risk tree, the corresponding decision rule of the second decision in the face of risk variable is located at the risk
The downstream of decision tree.
3. according to the method described in claim 2, it is characterized in that, described orderly extract risk from the decision in the face of risk tree and determine
Plan variable obtains the corresponding data source of each decision in the face of risk variable, comprising:
Decision in the face of risk variable is orderly extracted from the decision in the face of risk tree, the decision in the face of risk variable includes that first risk is determined
Plan variable and the second decision in the face of risk variable；
Obtain the corresponding data source of the first decision in the face of risk variable；
If the corresponding data source of the first decision in the face of risk variable is not hit by the decision in the face of risk tree, second wind is obtained
The corresponding data source of dangerous decision variable.
4. according to the method described in claim 2, it is characterized in that, the connection decision rule generates decision in the face of risk tree,
Include:
Obtain the syntagmatic of decision in the face of risk variable predetermined；
The corresponding decision rule of the decision in the face of risk variable is combined according to the syntagmatic；
The orderly decision rule after connection combination, generates decision in the face of risk tree.
5. method according to claim 1-4, which is characterized in that orderly connect the decision rule life described
After risk decision tree, further includes:
Obtain the corresponding positive negative sample of the business division；
Risk anticipation is carried out to the positive negative sample based on the decision in the face of risk tree, obtains risk anticipation result；
Calculate the matching degree of the positive and negative attribute of the risk anticipation result and the positive negative sample；
If the matching degree is less than given threshold, the corresponding erroneous judgement rule section of erroneous judgement sample is determined from the decision in the face of risk tree
Point.
6. method according to claim 1-4, which is characterized in that the method also includes:
Risks and assumptions are monitored, the risks and assumptions are the corresponding hot word public feelings information of hot word set of business division configuration；
If the Long-term change trend of the hot word public feelings information reaches given threshold, the alarm of business division risk is generated, based on described
Risk alerts the decision in the face of risk tree corresponding to the business division and is adjusted.
7. a kind of service data processing apparatus, which is characterized in that described device includes:
Decision in the face of risk tree obtains module and it is corresponding to obtain the business division for determining the corresponding business division of business application
Decision in the face of risk tree；
Data source extraction module obtains each wind for orderly extracting decision in the face of risk variable from the decision in the face of risk tree
The corresponding data source of dangerous decision variable；
Decision-making module, for sequence to be input to the decision in the face of risk in the first corresponding data source of the decision in the face of risk variable
In tree, the hit results of the first decision rule are obtained, the hit results are rule hit and regular miss；
Result of decision output module is determined for the corresponding data source of next decision in the face of risk variable to be input to the risk
Until the hit results are rule hit in plan tree, the result of decision is obtained.
8. device according to claim 7, which is characterized in that described device further include:
Data on stock obtains module, and for obtaining the corresponding data on stock of the business division, the data on stock includes inside
Historical data and external historical data；
Decision in the face of risk variant determination module, for determining the first decision in the face of risk variable from the internal history data, from described
The second decision in the face of risk variable is determined in external historical data；
Decision rule generation module, the variable configuration information submitted for receiving regular configuration interface, configures according to the variable
Information generates the corresponding decision rule of each decision in the face of risk variable；
Decision in the face of risk tree generation module generates decision in the face of risk tree for connecting the decision rule, wherein first risk is determined
The corresponding decision rule of plan variable is located at the upstream of the decision in the face of risk tree, the corresponding institute of the second decision in the face of risk variable
State the downstream that decision rule is located at the decision in the face of risk tree.
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 6 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 6 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811553151.4A CN109857373A (en) | 2018-12-18 | 2018-12-18 | Business data processing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811553151.4A CN109857373A (en) | 2018-12-18 | 2018-12-18 | Business data processing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109857373A true CN109857373A (en) | 2019-06-07 |
Family
ID=66891389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811553151.4A Pending CN109857373A (en) | 2018-12-18 | 2018-12-18 | Business data processing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109857373A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110688400A (en) * | 2019-09-02 | 2020-01-14 | 深圳壹账通智能科技有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| CN111311136A (en) * | 2020-05-14 | 2020-06-19 | 深圳索信达数据技术有限公司 | Wind control decision method, computer equipment and storage medium |
| CN112163043A (en) * | 2020-09-27 | 2021-01-01 | 万汇互联(深圳)科技有限公司 | CopyTrade signal replication system |
| CN112348688A (en) * | 2020-11-26 | 2021-02-09 | 德联易控科技(北京)有限公司 | Vehicle insurance wind control analysis method and device, terminal equipment and storage medium |
| CN112669138A (en) * | 2020-12-23 | 2021-04-16 | 平安科技（深圳）有限公司 | Data processing method and related equipment |
| CN112817574A (en) * | 2021-01-14 | 2021-05-18 | 内蒙古蒙商消费金融股份有限公司 | Variable data processing method, variable data processing device, electronic device, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110191138A1 (en) * | 2010-02-01 | 2011-08-04 | Bank Of America Corporation | Risk scorecard |
| CN107067157A (en) * | 2017-03-01 | 2017-08-18 | 北京奇艺世纪科技有限公司 | Business risk appraisal procedure, device and air control system |
| CN107316134A (en) * | 2017-06-16 | 2017-11-03 | 深圳乐信软件技术有限公司 | A kind of risk control method, device, server and storage medium |
| CN107767021A (en) * | 2017-09-12 | 2018-03-06 | 阿里巴巴集团控股有限公司 | A kind of risk control method and equipment |
| CN107798239A (en) * | 2017-07-27 | 2018-03-13 | 上海壹账通金融科技有限公司 | Operational risk processing method, device, computer equipment and storage medium |
-
2018
- 2018-12-18 CN CN201811553151.4A patent/CN109857373A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110191138A1 (en) * | 2010-02-01 | 2011-08-04 | Bank Of America Corporation | Risk scorecard |
| CN107067157A (en) * | 2017-03-01 | 2017-08-18 | 北京奇艺世纪科技有限公司 | Business risk appraisal procedure, device and air control system |
| CN107316134A (en) * | 2017-06-16 | 2017-11-03 | 深圳乐信软件技术有限公司 | A kind of risk control method, device, server and storage medium |
| CN107798239A (en) * | 2017-07-27 | 2018-03-13 | 上海壹账通金融科技有限公司 | Operational risk processing method, device, computer equipment and storage medium |
| CN107767021A (en) * | 2017-09-12 | 2018-03-06 | 阿里巴巴集团控股有限公司 | A kind of risk control method and equipment |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110688400A (en) * | 2019-09-02 | 2020-01-14 | 深圳壹账通智能科技有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| CN111311136A (en) * | 2020-05-14 | 2020-06-19 | 深圳索信达数据技术有限公司 | Wind control decision method, computer equipment and storage medium |
| CN112163043A (en) * | 2020-09-27 | 2021-01-01 | 万汇互联(深圳)科技有限公司 | CopyTrade signal replication system |
| CN112348688A (en) * | 2020-11-26 | 2021-02-09 | 德联易控科技(北京)有限公司 | Vehicle insurance wind control analysis method and device, terminal equipment and storage medium |
| CN112669138A (en) * | 2020-12-23 | 2021-04-16 | 平安科技（深圳）有限公司 | Data processing method and related equipment |
| CN112669138B (en) * | 2020-12-23 | 2022-04-26 | 平安科技（深圳）有限公司 | Data processing method and related equipment |
| WO2022134466A1 (en) * | 2020-12-23 | 2022-06-30 | 平安科技（深圳）有限公司 | Data processing method and related device |
| CN112817574A (en) * | 2021-01-14 | 2021-05-18 | 内蒙古蒙商消费金融股份有限公司 | Variable data processing method, variable data processing device, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109857373A (en) | Business data processing method, device, computer equipment and storage medium | |
| CN109636607A (en) | Business data processing method, device and computer equipment based on model deployment | |
| US11074350B2 (en) | Method and device for controlling data risk | |
| CN108876133A (en) | Risk assessment processing method, device, server and medium based on business information | |
| CN109345374A (en) | Risk control method, device, computer equipment and storage medium | |
| CN110826071B (en) | Software vulnerability risk prediction method, device, equipment and storage medium | |
| CN109474578A (en) | Message method of calibration, device, computer equipment and storage medium | |
| CN109858737A (en) | Rating Model method of adjustment, device and computer equipment based on model deployment | |
| CN110009225A (en) | Risk evaluating system construction method, device, computer equipment and storage medium | |
| CN112100250B (en) | Data processing method and device | |
| CN109767320A (en) | Order checking method, device, computer equipment and storage medium | |
| CN109784703A (en) | Business data processing method, device, computer equipment and storage medium | |
| CN109656778A (en) | Data capture method, device, computer equipment and storage medium | |
| CN109815489A (en) | Collection information generating method, device, computer equipment and storage medium | |
| WO2021043076A1 (en) | Method and apparatus for processing network data to be published, and computer device and storage medium | |
| CN109949154A (en) | Customer information classification method, device, computer equipment and storage medium | |
| CN109523117A (en) | Risk Forecast Method, device, computer equipment and storage medium | |
| CN110490594A (en) | Business data processing method, device, computer equipment and storage medium | |
| CN110363645A (en) | Asset data processing method, device, computer equipment and storage medium | |
| CN109033150A (en) | Sensitive word verification method, device, computer equipment and storage medium | |
| CN110111208A (en) | Declaration form data processing method, device, computer equipment and storage medium | |
| CN109361628A (en) | Message assemble method, device, computer equipment and storage medium | |
| CN109214904A (en) | Acquisition methods, device, computer equipment and the storage medium of financial fraud clue | |
| CN113256408A (en) | Risk control method and system based on consumption finance and computer equipment | |
| CN110135943A (en) | Products Show method, apparatus, computer equipment and storage medium |
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 |