CN113657892A - Method and device for controlling transaction in network-free state - Google Patents
Method and device for controlling transaction in network-free state Download PDFInfo
- Publication number
- CN113657892A CN113657892A CN202110918229.3A CN202110918229A CN113657892A CN 113657892 A CN113657892 A CN 113657892A CN 202110918229 A CN202110918229 A CN 202110918229A CN 113657892 A CN113657892 A CN 113657892A
- Authority
- CN
- China
- Prior art keywords
- risk
- transaction
- network
- probability
- state
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012954 risk control Methods 0.000 claims abstract description 57
- 230000006870 function Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012937 correction Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 230000000875 corresponding effect Effects 0.000 description 58
- 230000001276 controlling effect Effects 0.000 description 32
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004900 laundering Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
- G06Q20/3829—Payment protocols; Details thereof insuring higher security of transaction involving key management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a method and a device for controlling transaction in a network-free state, which relate to the technical field of big data, wherein the method comprises the following steps: when a mobile terminal of a user receives a transaction without a network, decrypting a risk early warning model which is pre-deployed on the mobile terminal and encrypted by using a public key by using a private key of the user to obtain a decrypted risk early warning model; predicting the risk type and the corresponding risk probability of the user's wireless transaction according to the decrypted risk early warning model; when the condition that the no-network state transaction of the user has risks is determined, the corrected risk probability is obtained according to the risk probability predicted by the risk early warning model and the risk coefficients of the no-network state transaction and the online state transaction; determining a risk control strategy of the wireless transaction according to the corrected risk probability, the risk probability and the relationship between the risk type and the risk control strategy; and controlling the wireless transaction of the user according to the risk control strategy corresponding to the wireless transaction. The invention can efficiently and safely control the non-network transaction.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a method and a device for controlling transaction in a network-free state.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The risk encountered when the bank carries out the business is everywhere, and the risk must be considered in each link of business handling. Especially in certain scenarios, the risk may be higher, such as non-network scenarios and non-human scenarios. At this time, better means for controlling the risk are needed to ensure the security of the non-network transaction.
Disclosure of Invention
The embodiment of the invention provides a transaction control method in a network-free state, which is used for efficiently and safely controlling network-free transactions and comprises the following steps:
when a mobile terminal of a user receives a transaction in a network-free state, decrypting a risk early warning model which is pre-deployed on the mobile terminal and encrypted by using a public key by using a private key of the user to obtain a decrypted risk early warning model; the risk early warning model is pre-established according to transaction sample data in a network state within a preset time period of a bank;
predicting the risk type and the corresponding risk probability of the network-free state transaction of the user according to the decrypted risk early warning model, and storing the risk type and the corresponding risk probability in a block chain of the mobile terminal;
when the risk of the network-free state transaction of the user is determined according to the risk type of the network-free state transaction and the corresponding risk probability, obtaining a corrected risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the network-free state and the risk coefficient of the network state, and storing the corrected risk probability in a block chain of the mobile terminal;
determining a risk control strategy corresponding to the non-network state transaction according to the corrected risk probability, the risk probability and the relationship between the risk type and the risk control strategy;
and controlling the network-free transaction of the user according to a risk control strategy corresponding to the network-free state transaction.
The embodiment of the invention also provides a transaction control device in a non-network state, which is used for efficiently and safely controlling non-network transactions and comprises:
the system comprises a decryption processing unit, a risk early warning module and a risk early warning module, wherein the decryption processing unit is used for decrypting a risk early warning module which is pre-deployed on a mobile terminal and encrypted by a public key by using a private key of a user when the mobile terminal of the user receives a transaction in a network-free state to obtain a decrypted risk early warning module; the risk early warning model is pre-established according to transaction sample data in a network state within a preset time period of a bank;
the prediction unit is used for predicting the risk type and the corresponding risk probability of the network-free state transaction of the user according to the decrypted risk early warning model and storing the risk type and the corresponding risk probability in a block chain of the mobile terminal;
the correction unit is used for obtaining a corrected risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the no-network state and the risk coefficient of the network state when the risk of the no-network state transaction of the user is determined according to the risk type of the no-network state transaction and the corresponding risk probability, and storing the corrected risk probability in a block chain of the mobile terminal;
the strategy determining unit is used for determining a risk control strategy corresponding to the network-free state transaction according to the corrected risk probability, the risk probability and the relationship between the risk type and the risk control strategy;
and the control unit is used for controlling the network-free transaction of the user according to the risk control strategy corresponding to the network-free state transaction.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the method for controlling the transaction in the network-free state is realized.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the method for controlling a transaction in a network-less state is stored in the computer-readable storage medium.
In the embodiment of the invention, the scheme for controlling the transaction in the network-free state comprises the following steps: when a mobile terminal of a user receives a transaction in a network-free state, decrypting a risk early warning model which is pre-deployed on the mobile terminal and encrypted by using a public key by using a private key of the user to obtain a decrypted risk early warning model; the risk early warning model is pre-established according to transaction sample data in a network state within a preset time period of a bank; predicting the risk type and the corresponding risk probability of the network-free state transaction of the user according to the decrypted risk early warning model, and storing the risk type and the corresponding risk probability in a block chain of the mobile terminal; when the risk of the network-free state transaction of the user is determined according to the risk type of the network-free state transaction and the corresponding risk probability, obtaining a corrected risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the network-free state and the risk coefficient of the network state, and storing the corrected risk probability in a block chain of the mobile terminal; determining a risk control strategy corresponding to the non-network state transaction according to the corrected risk probability, the risk probability and the relationship between the risk type and the risk control strategy; according to the risk control strategy corresponding to the non-network state transaction, the non-network transaction of the user is controlled, and the non-network transaction can be efficiently and safely controlled.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a flow chart illustrating a method for controlling transactions in a no network state according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a process of determining a risk factor of a no network state according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating a process of determining a risk factor with a network status according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart illustrating a process of predicting risk types and corresponding risk probabilities of a user's network-less state transactions according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus for controlling a transaction in a no-network state according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
Before describing the embodiments of the present invention, terms related to the embodiments of the present invention will be described.
Risk factor: the quantitative index is used for measuring the occurrence risk of the customer transaction under a certain scene.
The blockchain technology can ensure that the information is not falsifiable, true and traceable. The key data related to the transaction risk can be recorded by utilizing the block chain, so that the transaction risk control is ensured to be real and effective, and the risk can be reduced.
Because the wind control of the existing scene (network scene) is relatively mature and has a large amount of transaction data, the risk prediction of the non-network transaction can be carried out by using the wind control model of the existing scene for reference.
Therefore, the inventor proposes a scheme for controlling transaction in a network-free state, in which when a user (client) is in a network-free state, a wind control model (risk early warning model) of an existing scene is stored on a mobile terminal of the client, when the terminal of the client is in a network-free state, the client transaction in the network-free state is risk-controlled based on the wind control model, and transaction data in the network-free state is to be stored in a block chain of the mobile terminal of the client, so as to reduce the risk of tampering the transaction data.
Fig. 1 is a schematic flow chart of a method for controlling a transaction in a network-less state according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step 101: when a mobile terminal of a user receives a transaction in a network-free state, decrypting a risk early warning model which is pre-deployed on the mobile terminal and encrypted by using a public key by using a private key of the user to obtain a decrypted risk early warning model; the risk early warning model is pre-established according to transaction sample data in a network state within a preset time period of a bank;
step 102: predicting the risk type and the corresponding risk probability of the network-free state transaction of the user according to the decrypted risk early warning model, and storing the risk type and the corresponding risk probability in a block chain of the mobile terminal;
step 103: when the risk of the network-free state transaction of the user is determined according to the risk type of the network-free state transaction and the corresponding risk probability, obtaining a corrected risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the network-free state and the risk coefficient of the network state, and storing the corrected risk probability in a block chain of the mobile terminal;
step 104: determining a risk control strategy corresponding to the non-network state transaction according to the corrected risk probability, the risk probability and the relationship between the risk type and the risk control strategy;
step 105: and controlling the network-free transaction of the user according to a risk control strategy corresponding to the network-free state transaction.
The risk early warning model is an important digital asset of a bank and is usually deployed on a server of the bank. The network-free state transaction needs to send the risk early warning model to the mobile terminal of the client, and in order to prevent external lawless persons from seeing the digital assets, the invention uses the public key of the client for encryption. When the risk early warning model is needed to carry out risk prediction on the transaction of the client, the private key of the client can be used for decryption to obtain the decrypted risk early warning model. Therefore, the risk early warning model of the bank can not be leaked, and the network-free transaction risk of the customer can be controlled.
The bank server currently has a large amount of transaction data available, and these transaction data are basically transaction data in a network state. By utilizing the transaction data, a plurality of risk early warning models can be trained. Long-term practice shows that the transaction risk mechanism with the network state is mature, and the risk is basically controllable when the risk occurs. And the current transaction data without the network state is much less, which is not enough to train out a risk early warning model with accurate precision. Therefore, the bank can predict the transaction risk in the non-network state by using a risk early warning model trained by the transaction data in the network state, and then correct the prediction result based on the difference of risk quantification indexes in the two states so as to ensure that the risk of the non-network transaction is controllable.
Meanwhile, compared with the network state, the client mobile terminal in the non-network state cannot interact with the background server of the bank, so that the background server of the client cannot effectively manage and control the risk of the application of the mobile terminal of the client, and the client mobile terminal in the non-network state is considered to face greater uncertainty, namely the client mobile terminal in the non-network state may have greater risk. Risks in the non-network state and the network state are quantified through risk coefficients, risk gaps of customer transactions in the two states can be evaluated more accurately, the difference of risk probabilities in the two states can be calculated according to the risk gaps, and the risk probability in the non-network state is further obtained. Therefore, the conversion from the change of the quantitative index of the risk to the change of the risk probability is realized, and the digital risk control is realized. The method can ensure that the risk probability of the non-network state is closely related to the risk quantitative index of the non-network state, and different risk probabilities are correspondingly calculated by different risk indexes.
The method for controlling transaction in the network-free state in the embodiment of the invention can realize efficient and safe control of network-free transaction, and is described in detail below.
In one embodiment, in step 102, as shown in fig. 4, predicting the risk type and the corresponding risk probability of the network-less state transaction of the user according to the decrypted risk early warning model may include:
step 401: extracting transaction elements of the network-free state transaction;
step 402: and inputting the transaction elements of the non-network state transaction into the decrypted risk early warning model to obtain the risk types and the corresponding risk probabilities of the non-network state transaction.
The transaction element is key data of the transaction data and includes key information of the customer transaction information. The transaction elements are input into the risk early warning model for prediction, so that the prediction precision can be improved, and the occurrence of risks can be reduced; meanwhile, the time spent in prediction of the risk early warning model can be reduced, and the experience of customers is improved.
In specific implementation, the mode of predicting the risk type and the corresponding risk probability by using the risk early warning model can further improve the safety of controlling the non-network transaction. For the risk pre-warning model, see the description of the following embodiments.
In an embodiment, in step 103, when it is determined that the network-free transaction of the user has a risk according to the risk type of the network-free transaction and the corresponding risk probability, obtaining a modified risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the network-free transaction and the risk coefficient of the network-free transaction, which may include obtaining the modified risk probability according to the following formula:
p2＝max(p1×f(r2/r1),pmax)；
wherein p2 is the corrected risk probability, p1 is the risk probability predicted by the risk early warning model, r2 is the risk coefficient without network state, r1 is the risk coefficient with network state, pmax is a value between 0 and 1, and f is a monotonically increasing function. The above formula can ensure that the risk probability of the user in the no-network state is positively correlated with the risk of the no-network state, that is, the higher the risk of the no-network state is, the higher the risk probability corresponding to the risk category is.
Further, a plurality of probability values can be determined based on historical transaction data of the bank mobile terminal, then a risk data sample with the risk probability value of the current risk type being the probability value is obtained through sampling, then the corresponding risk coefficient and the risk comparison factor corresponding to the risk coefficient are confirmed according to the risk data sample, then the risk comparison factor is used as an independent variable, the corresponding risk probability value is used as a dependent variable, and a polynomial function is used for fitting to obtain a specific expression of the function f.
In specific implementation, the above embodiment of correcting the risk probability can establish a corresponding relationship between the risk quantitative index in the non-network state and the risk probability in the non-network state, thereby realizing digital risk control of the bank and ensuring the security of the user's wireless transaction.
In one embodiment, as shown in fig. 2, the method for controlling a transaction in a non-network state may further include determining a risk factor of the non-network state according to the following method:
step 201: acquiring risk transaction data in a network-free state in a preset time period before the current moment of a bank;
step 202: determining a risk coefficient and a probability of each risk type according to the risk transaction data;
step 203: determining a risk coefficient of a non-network state according to the risk coefficient of each risk type and the probability of each risk type;
step 204: storing the determined risk factors of the network-free state in a blockchain.
In one embodiment, as shown in fig. 3, the method for controlling a transaction in a non-network state may further include determining a risk factor of a network state according to the following method:
step 301: acquiring risk transaction data in a network state in a preset time period before the current moment of a bank;
step 302: determining a risk coefficient and a probability of each risk type according to the risk transaction data;
step 303: determining a risk coefficient with a network state according to the risk coefficient of each risk type and the probability of each risk type;
step 304: and storing the determined risk coefficients with the network state in a block chain.
In particular, the risk factor is used to measure a quantitative measure of the potential loss of a transaction to a customer, and the different types of risk affect the customer differently. The loss caused by the corresponding risk type to the client can be determined based on the data corresponding to each risk type, a large amount of data is stored in a bank database, the data can sufficiently reflect the rule that the risk causes the loss to the client according to the majority theorem, and the risk value corresponding to each risk type can be basically measured by the statistical average value. Meanwhile, the probability of each risk type also reflects the influence of the risk type on the client, and the larger the probability is, the larger the influence is. After the risk types, the risk coefficients for each risk type, and the probabilities for each risk type are determined, the risk coefficients for the presence or absence of a network condition can be determined. Such as directly set to: sum (log (ri × ni)) or sum (ri × ni), where ri is the risk coefficient of the ith risk type, ni is the probability of the ith risk type, sum is the summation function, and log is the logarithm function. An alternative approach is to replace the probability of each risk type described above with a number for each risk type. An improvement to the above scheme is: in addition to the risk factor and the probability of each risk type, the proportion t of the transaction risk data to the whole transaction data needs to be considered, and then the risk factor can be modified to be: t × sum (log (ri × ni)) or t × sum (ri × ni), so that the risk coefficients of various states can be evaluated more accurately.
In specific implementation, the implementation method for estimating the risk coefficient of the non-network state can more accurately estimate the risk quantitative indexes of the network state and the non-network state.
In an embodiment, in step 103, the method for controlling a transaction in the no-network state may further include: multiplying the corrected risk probability by a function taking the transaction risk coefficient of the user as an independent variable to obtain the final correction probability;
therefore, in the subsequent step 104, determining a risk control policy corresponding to the non-network-state transaction according to the corrected risk probability, the risk probability, and the relationship between the risk type and the risk control policy may include: and determining a risk control strategy corresponding to the non-network state transaction according to the final correction probability, the risk probability and the relationship between the risk type and the risk control strategy.
In particular implementations, the risk of the client itself is an important factor in the risk of the transaction. Under the same conditions, the transaction risks of customers with different risks are also slightly different. In order to satisfy the differentiation requirements, for example, for customers with different risks, the greater the risk of the customer, the greater the transaction risk, so when correcting the risk probability, the risk of the customer (the transaction risk coefficient is a quantitative index of the risk of the customer) may be considered, for example, the calculated corrected risk probability p2 may be multiplied by a function using the transaction risk coefficient of the customer as an argument to obtain a final correction probability, and then the accuracy of determining the risk control policy corresponding to the non-network state transaction may be further improved according to the final correction probability, so as to improve the security of the customer transaction in the non-network state. Details of the risk control strategy are provided in the following examples.
In specific implementation, the risk probability, the relationship between the risk type and the risk control strategy may be a table, in which the risk probability, the risk type and the corresponding risk control strategy are located, and after the corrected risk probability is obtained, the risk control strategy corresponding to the current corrected risk probability is obtained by matching and searching the table according to the corrected risk probability and the corresponding risk category.
In one embodiment, the function with the user's transaction risk factor as an argument is:
f(y)＝2/(1+exp(-y))；
wherein f (y) is a function with the transaction risk coefficient of the user as an argument, and y is the transaction risk coefficient of the user.
When the method is specifically implemented, the function can further improve the accuracy of calculating the transaction risk without the network state. The function is slightly larger than 1, which means that the function has a very limited effect on the risk probability of a network-free state. And the function is a monotone increasing function for the independent variable y, so that the higher risk of the client is ensured, and the risk probability after correction is higher.
To facilitate an understanding of how the invention may be practiced, an example is provided below.
1. Acquiring transaction sample data of an existing scene in a network state in a past period of a bank, wherein the data comprises: risk transaction data; and training a machine learning model based on the transaction sample data to obtain a risk early warning model. The risk early warning model can predict the risk type (the risk of stealing an account number and the risk of fraud) and the risk probability of each transaction based on the transaction elements of the transaction. The input of the risk early warning model can be a transaction element of the non-network state transaction, and the output can be a risk type of the non-network state transaction and a corresponding risk probability.
2. And encrypting the data of the wind control model (risk early warning model) of the bank by using a public key corresponding to the client and storing the encrypted data on the mobile terminal of the client. And when the mobile terminal of the client is in a network-free state, decrypting the data of the wind control model by using the private key of the client, and predicting the risk type and the risk probability of the network-free state transaction of the client by using the wind control model of the corresponding scene.
3. When the customer's transaction is deemed to be at risk, the risk probability of the transaction is modified by the chain of blocks' smart contracts. For example, the correction may be p2 ═ max (p1 xf (r2/r1), pmax), where p2 and p1 are risk probabilities after correction and risk probabilities predicted by the risk model, r2 and r1 are risk coefficients of no network state and network state, pmax is a fixed value with a value between 0 and 1, and f is a monotonically increasing function.
4. Acquiring a corresponding risk control method (risk control strategy) according to the risk probability corresponding to the transaction in the network-free state, for example, when the risk probability that the account number is stolen is greater than a P value, adopting a stronger identity verification means such as face recognition and the like; and when the probability of money laundering risk is larger than a certain value, collecting the biological characteristic information of the client, and uploading the information to a bank server when networking. According to the risk control method, the transaction of the client under the condition of no network is controlled, and the result data of the risk control is uploaded to the block chain. The wind control method refers to a risk control strategy in a network state and stores the risk control strategy in the client mobile terminal.
5. In order to satisfy the differentiated requirements, for example, for customers with different risks, the greater the risk of the customer, which means the greater the transaction risk, so when the risk probability is corrected, the risk of the customer may be considered, for example, the calculated p2 may be multiplied by a function with the risk of the customer (the transaction risk coefficient of the user) as an argument, and the function satisfies: for a client with higher risk, the function has a higher corresponding value, for example, the function may be: and f (y) is 2/(1+ exp (-y)), wherein y is the self risk quantitative value of the customer (the transaction risk coefficient of the user).
6. All transaction data without network status is recorded by the blockchain of the customer's mobile terminal. And after the mobile terminal of the client is networked, synchronizing the transaction data of the block chain to a server of the bank.
To sum up, the embodiment of the present invention obtains a risk early warning model based on transaction data of a reference scene, predicts a transaction without a network state by the risk early warning model, adjusts a predicted risk probability by risk coefficients of two scenes, and adjusts the risk probability by a risk quantization value of a client. And carrying out risk control on the transaction of the client according to the prediction result. And recording transaction data without network state based on the blockchain.
The embodiment of the invention also provides a device for controlling transaction in a network-free state, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to the method for controlling the transaction in the non-network state, the implementation of the device can refer to the implementation of the method for controlling the transaction in the non-network state, and repeated details are not repeated.
Fig. 5 is a schematic structural diagram of an apparatus for controlling a transaction in a network-less state according to an embodiment of the present invention, as shown in fig. 5, the apparatus includes:
the decryption processing unit 01 is configured to decrypt, by using a private key of a user, a risk early warning model which is pre-deployed on the mobile terminal and encrypted by using a public key when the mobile terminal of the user receives a transaction in a network-free state, so as to obtain a decrypted risk early warning model; the risk early warning model is pre-established according to transaction sample data in a network state within a preset time period of a bank;
the prediction unit 02 is used for predicting the risk type and the corresponding risk probability of the network-free state transaction of the user according to the decrypted risk early warning model and storing the risk type and the corresponding risk probability in a block chain of the mobile terminal;
the correcting unit 03 is configured to obtain a corrected risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the no-network state and the risk coefficient of the network state when it is determined that the no-network state transaction of the user has a risk according to the risk type of the no-network state transaction and the corresponding risk probability, and store the corrected risk probability in a block chain of the mobile terminal;
the strategy determining unit 04 is configured to determine a risk control strategy corresponding to the network-less state transaction according to the corrected risk probability, the risk probability, and a relationship between the risk type and the risk control strategy;
and the control unit 05 is used for controlling the network-free transaction of the user according to the risk control strategy corresponding to the network-free state transaction.
In an embodiment, the modifying unit is specifically configured to obtain a risk probability corresponding to the modified no-network-state transaction according to the following formula:
p2＝max(p1×f(r2/r1),pmax)；
wherein p2 is the corrected risk probability, p1 is the risk probability predicted by the risk early warning model, r2 is the risk coefficient without network state, r1 is the risk coefficient with network state, pmax is a value between 0 and 1, and f is a monotonically increasing function.
In an embodiment, the apparatus for controlling a transaction in a non-network state may further include a first risk factor determining unit, configured to determine a risk factor in the non-network state according to the following method:
acquiring risk transaction data in a network-free state in a preset time period before the current moment of a bank;
determining a risk coefficient and a probability of each risk type according to the risk transaction data;
determining a risk coefficient of a non-network state according to the risk coefficient of each risk type and the probability of each risk type;
storing the determined risk factors of the network-free state in a blockchain.
In an embodiment, the apparatus for controlling a transaction in a non-network state may further include a second risk factor determining unit, configured to determine a risk factor in a network state according to the following method:
acquiring risk transaction data in a network state in a preset time period before the current moment of a bank;
determining a risk coefficient and a probability of each risk type according to the risk transaction data;
determining a risk coefficient with a network state according to the risk coefficient of each risk type and the probability of each risk type;
and storing the determined risk coefficients with the network state in a block chain.
In one embodiment, the prediction unit is specifically configured to:
extracting transaction elements of the network-free state transaction;
and inputting the transaction elements of the non-network state transaction into the decrypted risk early warning model to obtain the risk types and the corresponding risk probabilities of the non-network state transaction.
In one embodiment, the apparatus for controlling transaction in the no network state may further include
The adjusting unit is used for multiplying the corrected risk probability by a function taking the transaction risk coefficient of the user as an independent variable to obtain the final correction probability;
the policy determining unit is specifically configured to: and determining a risk control strategy corresponding to the non-network state transaction according to the final correction probability, the risk probability and the relationship between the risk type and the risk control strategy.
In one embodiment, the function with the user's transaction risk factor as an argument is:
f(y)＝1/(1+exp(-y))；
wherein f (y) is a function with the transaction risk coefficient of the user as an argument, and y is the transaction risk coefficient of the user.
In summary, the device for controlling transaction in a network-free state provided by the embodiment of the invention can acquire a risk early warning model with more accurate prediction based on a large amount of historical transaction data of a reference scene, and then adjust risk probability based on a risk coefficient of the scene and a transaction risk coefficient of a client, thereby acquiring a corresponding risk control method. And recording transaction data without network state based on the blockchain. According to the method, risk control is carried out, and the safety of transaction can be better guaranteed.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the method for controlling the transaction in the network-free state is realized.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the method for controlling a transaction in a network-less state is stored in the computer-readable storage medium.
In the embodiment of the invention, the scheme for controlling the transaction in the network-free state comprises the following steps: when a mobile terminal of a user receives a transaction in a network-free state, decrypting a risk early warning model which is pre-deployed on the mobile terminal and encrypted by using a public key by using a private key of the user to obtain a decrypted risk early warning model; the risk early warning model is pre-established according to transaction sample data in a network state within a preset time period of a bank; predicting the risk type and the corresponding risk probability of the network-free state transaction of the user according to the decrypted risk early warning model; when the risk of the network-free state transaction of the user is determined according to the risk type of the network-free state transaction and the corresponding risk probability, obtaining a corrected risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the network-free state and the risk coefficient of the network state; determining a risk control strategy corresponding to the non-network state transaction according to the corrected risk probability and the relationship between the risk probability and the risk control strategy; according to the risk control strategy corresponding to the non-network state transaction, the non-network transaction of the user is controlled, and the non-network transaction can be efficiently and safely controlled.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (16)
1. A method for controlling transactions in a non-network state, comprising:
when a mobile terminal of a user receives a transaction in a network-free state, decrypting a risk early warning model which is pre-deployed on the mobile terminal and encrypted by using a public key by using a private key of the user to obtain a decrypted risk early warning model; the risk early warning model is pre-established according to transaction sample data in a network state within a preset time period of a bank;
predicting the risk type and the corresponding risk probability of the network-free state transaction of the user according to the decrypted risk early warning model, and storing the risk type and the corresponding risk probability in a block chain of the mobile terminal;
when the risk of the network-free state transaction of the user is determined according to the risk type of the network-free state transaction and the corresponding risk probability, obtaining a corrected risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the network-free state and the risk coefficient of the network state, and storing the corrected risk probability in a block chain of the mobile terminal;
determining a risk control strategy corresponding to the non-network state transaction according to the corrected risk probability, the risk probability and the relationship between the risk type and the risk control strategy;
and controlling the network-free transaction of the user according to a risk control strategy corresponding to the network-free state transaction.
2. The method of claim 1, wherein when determining that the network-free state transaction of the user has a risk according to the risk type of the network-free state transaction and the corresponding risk probability, obtaining a modified risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the network-free state and the risk coefficient of the network-free state, comprises obtaining the modified risk probability according to the following formula:
p2＝max(p1×f(r2/r1),pmax)；
wherein p2 is the corrected risk probability, p1 is the risk probability predicted by the risk early warning model, r2 is the risk coefficient without network state, r1 is the risk coefficient with network state, pmax is a value between 0 and 1, and f is a monotonically increasing function.
3. The method of controlling transactions in a non-network state of claim 1, further comprising determining a risk factor for the non-network state according to the following method:
acquiring risk transaction data in a network-free state in a preset time period before the current moment of a bank;
determining a risk coefficient and a probability of each risk type according to the risk transaction data;
determining a risk coefficient of a non-network state according to the risk coefficient of each risk type and the probability of each risk type;
storing the determined risk factors of the network-free state in a blockchain.
4. The method of controlling transactions in a non-networked state of claim 1, further comprising determining a risk factor for a networked state according to the following method:
acquiring risk transaction data in a network state in a preset time period before the current moment of a bank;
determining a risk coefficient and a probability of each risk type according to the risk transaction data;
determining a risk coefficient with a network state according to the risk coefficient of each risk type and the probability of each risk type;
and storing the determined risk coefficients with the network state in a block chain.
5. The method of claim 1, wherein predicting the risk type and corresponding risk probability of the network-less transaction of the user according to the decrypted risk early warning model comprises:
extracting transaction elements of the network-free state transaction;
and inputting the transaction elements of the non-network state transaction into the decrypted risk early warning model to obtain the risk types and the corresponding risk probabilities of the non-network state transaction.
6. The method of controlling transactions in a non-network state of claim 1, further comprising:
multiplying the corrected risk probability by a function taking the transaction risk coefficient of the user as an independent variable to obtain the final correction probability;
determining a risk control strategy corresponding to the transaction without the network state according to the corrected risk probability, the risk probability and the relationship between the risk type and the risk control strategy, wherein the risk control strategy comprises the following steps: and determining a risk control strategy corresponding to the non-network state transaction according to the final correction probability, the risk probability and the relationship between the risk type and the risk control strategy.
7. The method for controlling transaction under the network-free state according to claim 6, wherein the function with the transaction risk coefficient of the user as the argument is:
f(y)＝2/(1+exp(-y))；
wherein f (y) is a function with the transaction risk coefficient of the user as an argument, and y is the transaction risk coefficient of the user.
8. An apparatus for controlling a transaction in a non-network state, comprising:
the system comprises a decryption processing unit, a risk early warning module and a risk early warning module, wherein the decryption processing unit is used for decrypting a risk early warning module which is pre-deployed on a mobile terminal and encrypted by a public key by using a private key of a user when the mobile terminal of the user receives a transaction in a network-free state to obtain a decrypted risk early warning module; the risk early warning model is pre-established according to transaction sample data in a network state within a preset time period of a bank;
the prediction unit is used for predicting the risk type and the corresponding risk probability of the network-free state transaction of the user according to the decrypted risk early warning model and storing the risk type and the corresponding risk probability in a block chain of the mobile terminal;
the correction unit is used for obtaining a corrected risk probability according to the risk probability predicted by the risk early warning model, the risk coefficient of the no-network state and the risk coefficient of the network state when the risk of the no-network state transaction of the user is determined according to the risk type of the no-network state transaction and the corresponding risk probability, and storing the corrected risk probability in a block chain of the mobile terminal;
the strategy determining unit is used for determining a risk control strategy corresponding to the network-free state transaction according to the corrected risk probability, the risk probability and the relationship between the risk type and the risk control strategy;
and the control unit is used for controlling the network-free transaction of the user according to the risk control strategy corresponding to the network-free state transaction.
9. The apparatus for controlling transaction under the network-free state according to claim 8, wherein the modifying unit is specifically configured to obtain the risk probability corresponding to the modified transaction under the network-free state according to the following formula:
p2＝max(p1×f(r2/r1),pmax)；
wherein p2 is the corrected risk probability, p1 is the risk probability predicted by the risk early warning model, r2 is the risk coefficient without network state, r1 is the risk coefficient with network state, pmax is a value between 0 and 1, and f is a monotonically increasing function.
10. The apparatus for controlling transaction in non-network state according to claim 8, further comprising a first risk factor determining unit for determining the risk factor in non-network state according to the following method:
acquiring risk transaction data in a network-free state in a preset time period before the current moment of a bank;
determining a risk coefficient and a probability of each risk type according to the risk transaction data;
determining a risk coefficient of a non-network state according to the risk coefficient of each risk type and the probability of each risk type;
storing the determined risk factors of the network-free state in a blockchain.
11. The apparatus for controlling transaction in non-network state according to claim 8, further comprising a second risk factor determining unit for determining the risk factor with network state according to the following method:
acquiring risk transaction data in a network state in a preset time period before the current moment of a bank;
determining a risk coefficient and a probability of each risk type according to the risk transaction data;
determining a risk coefficient with a network state according to the risk coefficient of each risk type and the probability of each risk type;
and storing the determined risk coefficients with the network state in a block chain.
12. The device for controlling transactions in a network-less state according to claim 8, wherein the prediction unit is specifically configured to:
extracting transaction elements of the network-free state transaction;
and inputting the transaction elements of the non-network state transaction into the decrypted risk early warning model to obtain the risk types and the corresponding risk probabilities of the non-network state transaction.
13. The apparatus for controlling a transaction in a non-network state according to claim 8, further comprising:
the adjusting unit is used for multiplying the corrected risk probability by a function taking the transaction risk coefficient of the user as an independent variable to obtain the final correction probability;
the policy determining unit is specifically configured to: and determining a risk control strategy corresponding to the non-network state transaction according to the final correction probability, the risk probability and the relationship between the risk type and the risk control strategy.
14. The apparatus for controlling transaction under the network-less condition as claimed in claim 13, wherein the function with the transaction risk coefficient of the user as the argument is:
f(y)＝2/(1+exp(-y))；
wherein f (y) is a function with the transaction risk coefficient of the user as an argument, and y is the transaction risk coefficient of the user.
15. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when executing the computer program.
16. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110918229.3A CN113657892B (en) | 2021-08-11 | 2021-08-11 | Method and device for controlling transaction in network-free state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110918229.3A CN113657892B (en) | 2021-08-11 | 2021-08-11 | Method and device for controlling transaction in network-free state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113657892A true CN113657892A (en) | 2021-11-16 |
| CN113657892B CN113657892B (en) | 2024-10-11 |
Family
ID=78479487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110918229.3A Active CN113657892B (en) | 2021-08-11 | 2021-08-11 | Method and device for controlling transaction in network-free state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657892B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108564376A (en) * | 2018-04-20 | 2018-09-21 | 阿里巴巴集团控股有限公司 | Risk control method, device, server and readable storage medium storing program for executing |
| CN108985583A (en) * | 2018-06-27 | 2018-12-11 | 中国银行股份有限公司 | Finance data risk control method and device based on artificial intelligence |
| CN109034793A (en) * | 2018-07-05 | 2018-12-18 | 奇酷互联网络科技（深圳）有限公司 | Digital cash method of commerce and digital cash wallet hardware based on block chain |
| CN109493016A (en) * | 2018-10-24 | 2019-03-19 | 中国工商银行股份有限公司 | Offline electronic payment method, terminal based on digital cash and act on behalf of dispensing device |
| US20200394651A1 (en) * | 2019-06-13 | 2020-12-17 | Gridplus, Inc. | Dynamic off-chain digital currency transaction processing |
| CN113191769A (en) * | 2021-06-03 | 2021-07-30 | 中国银行股份有限公司 | Transaction data synchronization method, bank background system and transaction terminal |
-
2021
- 2021-08-11 CN CN202110918229.3A patent/CN113657892B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108564376A (en) * | 2018-04-20 | 2018-09-21 | 阿里巴巴集团控股有限公司 | Risk control method, device, server and readable storage medium storing program for executing |
| CN108985583A (en) * | 2018-06-27 | 2018-12-11 | 中国银行股份有限公司 | Finance data risk control method and device based on artificial intelligence |
| CN109034793A (en) * | 2018-07-05 | 2018-12-18 | 奇酷互联网络科技（深圳）有限公司 | Digital cash method of commerce and digital cash wallet hardware based on block chain |
| CN109493016A (en) * | 2018-10-24 | 2019-03-19 | 中国工商银行股份有限公司 | Offline electronic payment method, terminal based on digital cash and act on behalf of dispensing device |
| US20200394651A1 (en) * | 2019-06-13 | 2020-12-17 | Gridplus, Inc. | Dynamic off-chain digital currency transaction processing |
| CN113191769A (en) * | 2021-06-03 | 2021-07-30 | 中国银行股份有限公司 | Transaction data synchronization method, bank background system and transaction terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113657892B (en) | 2024-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108959934A (en) | Safety risk estimating method, device, computer equipment and storage medium | |
| KR20220066924A (en) | Computer-based systems, computing components, and computing objects configured to implement dynamic outlier bias reduction in machine learning models. | |
| CN110362999B (en) | Method and device for detecting account use abnormity | |
| CN113435770A (en) | Transaction risk assessment method and device based on block chain | |
| CN111553488B (en) | Risk recognition model training method and system for user behaviors | |
| CN105719033B (en) | Method and device for identifying object risk | |
| CN110795246A (en) | Resource utilization rate prediction method and device | |
| KR102359090B1 (en) | Method and System for Real-time Abnormal Insider Event Detection on Enterprise Resource Planning System | |
| CN111598425A (en) | Order flow control method and device | |
| CN112738098A (en) | Anomaly detection method and device based on network behavior data | |
| AU2021218217A1 (en) | Systems and methods for preventative monitoring using AI learning of outcomes and responses from previous experience. | |
| CN113436006A (en) | Loan risk prediction method and device based on block chain | |
| CN112905987B (en) | Account identification method, device, server and storage medium | |
| CN117572239A (en) | Energy storage battery state estimation method, system, equipment and medium | |
| CN113657892B (en) | Method and device for controlling transaction in network-free state | |
| CN106485521A (en) | User credit degree appraisal procedure and device | |
| KR102203617B1 (en) | Method for Preventing Forgery and Falsification of Prediction Modeling | |
| CN116681519A (en) | Breach prediction method, breach prediction apparatus, electronic device, medium, and program product | |
| CN113343577B (en) | Parameter optimization method, device, equipment and medium based on machine learning | |
| CN115564429A (en) | System for prepaid transaction monitoring and related methods and blockchains | |
| CN115204878A (en) | Order information evidence storing method, device and equipment | |
| CN112346995B (en) | Banking industry-based test risk prediction model construction method and device | |
| CN113627932B (en) | Method and device for controlling waiting time of terminal application account in network-free state | |
| CN112446578A (en) | Risk monitoring method and device | |
| CN113610633B (en) | Method and device for setting identity verification mode |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |