Wherein the value of k is 1 to n, n is the total number of items of the transaction safety related data for judgment, and in table 1, the value of n is 11. W_kWeight corresponding to the k-th transaction safety-related data, X_kAnd scoring corresponding to the k-th transaction safety related data.

In the embodiment, when the first transaction risk score is calculated according to the transaction safety related data before the payment of the current network order of the user and the transaction safety related data of the historical network order of the user, each transaction safety related data before the payment of the current network order of the user is respectively compared with the transaction safety related data of the corresponding historical network order; determining the transaction risk score of the transaction safety related data of each item before the current network order of the user is paid according to the comparison result; and calculating a first transaction risk score according to the transaction risk score of each transaction safety related data before the current network order of the user is paid and a preset transaction risk score submodel, so that the calculated first transaction risk score is more accurate.

Table 1: transaction risk condition, score and weight corresponding to each transaction safety related data

And step 204, calculating a second transaction risk score according to the transaction safety related data when the previous network order of the user pays and the transaction safety related data of the historical network order of the user.

Further, in this embodiment, calculating the second transaction risk score according to the transaction safety related data of the previous network order paid by the user and the transaction safety related data of the historical network order of the user specifically includes:

firstly, comparing each item of transaction safety related data of the previous network order of the user when the user pays with the transaction safety related data of the corresponding historical network order.

And secondly, determining the transaction risk score of the transaction safety related data of each item when the previous network order of the user pays according to the comparison result.

And finally, calculating a second transaction risk score according to the transaction risk score of each transaction safety related data when the previous network order of the user is paid and a preset transaction risk score submodel.

Preferably, in this embodiment, the calculating a second transaction risk score according to the transaction risk score of each transaction security related data when the user pays the previous network order and a preset transaction risk score submodel specifically includes:

and inputting the transaction risk score of each transaction safety related data when the previous network order of the user is paid into a preset transaction risk score submodel for weighted summation calculation so as to obtain a second transaction risk score.

Similarly, in this embodiment, first, each transaction safety related data of the historical network order is counted, a situation of each transaction safety related data of the user in a recent preset time period is counted, then, each transaction safety related data when the previous network order of the user pays is compared with the transaction safety related data of the corresponding historical network order, whether each transaction safety related data when the previous network order pays satisfies a corresponding transaction risk condition is judged according to a comparison result, if a certain transaction safety related data satisfies the corresponding transaction risk condition, a transaction risk score of the transaction safety related data when the previous network order of the user pays is determined as a transaction risk hit score, and if a certain transaction safety related data does not satisfy the corresponding transaction risk condition, a transaction risk score of the transaction safety related data when the previous network order of the user pays is determined as a transaction risk non-hit score . And inputting the score corresponding to each transaction safety related data when the previous network order of the user is paid into a preset transaction risk score submodel for weighted summation calculation so as to obtain a second transaction risk score.

The transaction risk condition, hit score, non-hit score, weight and other information corresponding to each transaction safety-related data may be represented as shown in table 1. The preset transaction risk score submodel is represented by formula (1), and is not described in detail herein.

In this embodiment, when the second transaction risk score is calculated according to the transaction safety related data of the previous network order of the user when the user pays and the transaction safety related data of the historical network order of the user, each transaction safety related data of the previous network order of the user when paying is compared with the transaction safety related data of the corresponding historical network order; determining the transaction risk score of each transaction safety related data when the previous network order of the user pays according to the comparison result; and calculating a second transaction risk score according to the transaction risk score of each transaction safety related data when the previous network order of the user is paid and a preset transaction risk score submodel, so that the calculated second transaction risk score is more accurate.

Step 205, calculating the transaction risk score when the current network order is paid according to the first transaction risk score, the second transaction risk score and a preset transaction risk score model.

Preferably, in this embodiment, calculating the transaction risk score when the current network order is paid according to the first transaction risk score, the second transaction risk score and a preset transaction risk score model specifically includes:

and inputting the first transaction risk score and the second transaction risk score into a preset transaction risk score model for weighted summation calculation so as to obtain the transaction risk score when the current network order is paid.

The preset transaction risk score model can be expressed as shown in formula (2).

G(X′_end,X_start)＝F(X′_end)×α+F(X_start)×(1-α) (2)

Wherein,

wherein, F (X'_end) Is the second transaction risk score, α is the weight corresponding to the second transaction risk score, F (X)_start) Is the first transaction risk score, (1- α) is the weight corresponding to the first transaction risk score t_startTime of submission for current network order, X_startSubmitting a score, t ', of corresponding transaction security-related data for a current network order'_endTime at which Payment for the previous network order, X'_endScoring of transaction security related data when paying for a previous network order.

And step 206, determining whether to pay the current network order according to the transaction risk score when the current network order is paid.

Specifically, in this embodiment, after the transaction risk score when the current network order is paid is calculated, the risk level may be divided according to the transaction risk score when the current network order is paid, and whether to pay the current network order is determined according to the divided risk level.

The method for dividing the risk level according to the transaction risk score during the current network order payment can be used for setting a score range of each risk level, comparing the transaction risk score during the current network order payment with each score range, and determining the level information corresponding to the score range into which the transaction risk score during the current network order payment falls.

Determining whether to pay the current network order according to the risk level when the current network order is paid can be: and if the risk level of the current network order during payment is a low risk level, performing payment of the current network order. And if the risk level of the current network order during payment is a medium level or a high level, determining not to pay the current network order, namely rejecting the payment operation of the user equipment, and sending a prompt message or performing telephone confirmation to the user equipment.

Step 207, when each order state event before the current network order payment occurs, judging whether the safety related data of each transaction before the current network order payment of the user is updated, if so, executing step 208, otherwise, ending.

In the network taxi taking scene, each order state event before the current network order payment is respectively as follows: the event that the passenger gets on the bus, the event that the passenger gets off the bus and the event that the driver finishes carrying passengers. In this embodiment, when the passenger getting-on event, the passenger getting-off event, and the driver finish the passenger loading event, each transaction safety related data before the payment of the current network order is obtained again, each transaction safety related data before the payment of the current network order obtained again is compared with each transaction safety related data before the payment of the current network order obtained before, whether one or more transaction safety related data are updated is determined, and if yes, step 207 is executed.

Step 208, determining whether the first transaction risk score changes, if so, performing step 209, otherwise, ending.

Further, in this embodiment, if one or more transaction safety related data before the current network order is paid is updated, whether the hit result is the same as the original hit result is determined according to the corresponding transaction risk condition, and then whether the first transaction risk score is changed is determined according to the preset transaction risk score sub-model.

Step 209, update the transaction risk score at the time of payment of the current network order.

Further, in this embodiment, if the first transaction risk score changes, the transaction risk score when the current network order is paid is updated.

In the method for evaluating transaction risk provided by this embodiment, if it is monitored that the user equipment submits the current network order, the transaction security related data before payment of the current network order of the user and the transaction security related data when the previous network order of the user is paid are obtained, the transaction security related data of the historical network order of the user are obtained, the first transaction risk score is calculated according to the transaction security related data before payment of the current network order of the user and the transaction security related data of the historical network order of the user, the second transaction risk score is calculated according to the transaction security related data when payment of the previous network order of the user and the transaction security related data of the historical network order of the user, the transaction risk score when payment of the current network order is calculated according to the first transaction risk score, the second transaction risk score and a preset transaction risk score model, whether the payment of the current network order is carried out or not is determined according to the transaction risk score when the current network order is paid, so that the efficiency of transaction risk assessment can be greatly improved, and the accuracy of the transaction risk assessment can be improved because the transaction safety related data before the payment of the current network order of the user and the transaction safety related data when the payment of the previous network order of the user are respectively compared with the transaction safety related data of the historical network order of the user, and the transaction risk score when the payment of the current network order is carried out is calculated through a more optimized preset transaction risk score model.

In the transaction risk evaluation method provided by this embodiment, after the transaction risk score during the current network order payment is calculated according to the first transaction risk score, the second transaction risk score and the preset transaction risk score model, whether each transaction safety related data of the user before the current network order payment is updated when each order state event before the current network order payment occurs is judged, if yes, whether the first transaction risk score changes is judged, and if yes, the transaction risk score during the current network order payment is updated. The final transaction risk score can be more accurate as the transaction risk score is continuously updated.

EXAMPLE III

Fig. 4 is a schematic structural diagram of a transaction risk assessment device according to a third embodiment of the present invention, and as shown in fig. 4, the transactionrisk assessment device 30 according to the present embodiment includes: adata acquisition unit 31, ascore calculation unit 32, and apayment determination unit 33.

Thedata obtaining unit 31 is configured to, if it is monitored that the user equipment submits the current network order, obtain transaction safety related data of the user before payment of the current network order and transaction safety related data of the user when payment of a previous network order is performed. And thescore calculating unit 32 is configured to calculate a transaction risk score when the current network order is paid according to the transaction security related data before the current network order of the user is paid, the transaction security related data when the previous network order of the user is paid, and a preset transaction risk score model. And apayment determining unit 33, configured to determine whether to perform payment for the current network order according to the transaction risk score when the current network order is paid.

The device for transaction risk assessment provided in this embodiment may implement the technical solution of the method embodiment shown in fig. 1, and the implementation principle and technical effect are similar, which are not described herein again.

Example four

Fig. 5 is a schematic structural diagram of a transaction risk assessment apparatus according to a fourth embodiment of the present invention, and as shown in fig. 5, the transactionrisk assessment apparatus 40 according to the present embodiment further includes, on the basis of the first embodiment of the transaction risk assessment apparatus according to the present invention: a data update judging unit 41, a first scorechange judging unit 42, and a totalscore updating unit 43.

In this embodiment, the transaction security related data of the network order at least includes: user equipment network data of the network order, user region data of the network order and time data of the network order. Wherein, the user equipment network data of the network order at least comprises: the information of the user equipment code, the information of the user equipment model, the information of the user equipment communication number, the information of the IP address of the user equipment and the Wi-Fi information of the user equipment; the user territory data of the network order at least comprises: POI information of the user and city information of the user.

Further, thedata obtaining unit 31 is further configured to obtain transaction security related data of the historical network orders of the user.

Further, the score calculating unit specifically includes: a firstscore calculating module 321, a secondscore calculating module 322, and a totalscore calculating module 323.

The firstscore calculating module 321 is configured to calculate a first transaction risk score according to transaction security related data of a current network order of the user before payment and transaction security related data of a historical network order of the user. The secondscore calculating module 322 is configured to calculate a second transaction risk score according to the transaction security related data of the previous network order paid by the user and the transaction security related data of the historical network order of the user. And the totalscore calculating module 323 is used for calculating the transaction risk score when the current network order is paid according to the first transaction risk score, the second transaction risk score and a preset transaction risk score model.

Further, in this embodiment, the firstscore calculating module 321 specifically includes: afirst comparison sub-module 3211, afirst determination sub-module 3212, and a firstscore calculation sub-module 3213.

Thefirst comparison sub-module 3211 is configured to compare each item of transaction security related data of the current network order of the user before payment with transaction security related data of a corresponding historical network order. The first determiningsubmodule 3212 is configured to determine, according to the comparison result, a transaction risk score of each item of transaction safety-related data before payment of the current network order of the user. The firstscore calculating submodule 3213 is configured to calculate a first transaction risk score according to the transaction risk score of each item of transaction security related data before payment of the current network order of the user and a preset transaction risk score submodel.

Further, in this embodiment, the first score calculating sub-module 3213 is specifically configured to: and inputting the transaction risk score of each transaction safety related data before the current network order of the user is paid into a preset transaction risk score submodel for weighted summation calculation so as to obtain a first transaction risk score.

Further, in this embodiment, the second score calculating module specifically includes: asecond comparison sub-module 3221, asecond determination sub-module 3222, and a secondscore calculation sub-module 3223.

The second comparing sub-module 3221 is configured to compare the transaction security related data of each previous network order paid by the user with the transaction security related data of the corresponding historical network order. The second determining sub-module 3222 is configured to determine, according to the comparison result, a transaction risk score of each item of transaction safety-related data when the previous network order of the user is paid. The second score calculating sub-module 3223 is configured to calculate a second transaction risk score according to the transaction risk score of each item of transaction safety related data when the previous network order of the user pays and a preset transaction risk score sub-model.

Further, the second score calculating sub-module 3223 is specifically configured to: and inputting the transaction risk score of each transaction safety related data when the previous network order of the user is paid into a preset transaction risk score submodel for weighted summation calculation so as to obtain a second transaction risk score.

Further, in this embodiment, the totalscore calculating module 323 is specifically configured to: and inputting the first transaction risk score and the second transaction risk score into a preset transaction risk score model for weighted summation calculation so as to obtain the transaction risk score when the current network order is paid.

Further, the data updating and determining unit 41 is configured to determine whether each item of transaction security related data of the user before the current network order is paid is updated when each order status event before the current network order is paid occurs. The first scorechange determining unit 42 is configured to determine whether the first transaction risk score changes if one or more transaction security related data are updated before the current network order is paid. And a totalscore updating unit 43, configured to update the transaction risk score when the current network order is paid if the first transaction risk score changes.

The device for transaction risk assessment provided in this embodiment may implement the technical solution of the method embodiment shown in fig. 2, and the implementation principle and technical effect are similar, which are not described herein again.

EXAMPLE five

Fig. 6 is a schematic structural diagram of a network-side device according to a fifth embodiment of the present invention, and as shown in fig. 6, a network-side device 50 according to this embodiment includes: a memory 51, aprocessor 52 and a computer program.

Wherein the computer program is stored in the memory 51 and configured to be executed by theprocessor 52 to implement the method for transaction risk assessment provided by the first embodiment of the present invention or the method for transaction risk assessment provided by the second embodiment of the present invention.

The relevant description may be understood by referring to the relevant description and effect corresponding to the steps in fig. 1 to fig. 2, and redundant description is not repeated here.

EXAMPLE six

A sixth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for transaction risk assessment provided in the first embodiment of the present invention or the method for transaction risk assessment provided in the second embodiment of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit and a module is merely a logical division, and an actual implementation may have another division, for example, a plurality of units and modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units and modules, and may be in an electrical, mechanical or other form.

The units and modules described as separate parts may or may not be physically separate, and parts displayed as the units and modules may or may not be physical units and modules, may be located in one place, or may be distributed on a plurality of network units and modules. Some or all of the units and modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units and modules in the embodiments of the present invention may be integrated into one processing unit and module, or each unit and module may exist alone physically, or two or more units and modules may be integrated into one unit and module. The integrated units and modules can be realized in a hardware form, or in a form of hardware plus software functional units and modules.

Program code for implementing the methods of the present invention may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A method of transaction risk assessment, comprising:

2. The method of claim 1, wherein before the calculating the transaction risk score at the time of payment of the current network order according to the transaction safety related data before payment of the current network order of the user, the transaction safety related data at the time of payment of the previous network order of the user and a preset transaction risk score model, the method further comprises:

and acquiring related transaction safety data of the historical network orders of the user.

3. The method according to claim 2, wherein the calculating the transaction risk score when the current network order is paid according to the transaction safety related data before the current network order of the user is paid, the transaction safety related data when the previous network order of the user is paid and a preset transaction risk score model specifically comprises:

calculating a first transaction risk score according to the transaction safety related data before the current network order of the user is paid and the transaction safety related data of the historical network order of the user;

calculating a second transaction risk score according to the transaction safety related data of the user when the previous network order is paid and the transaction safety related data of the historical network order of the user;

and calculating the transaction risk score when the current network order is paid according to the first transaction risk score, the second transaction risk score and a preset transaction risk score model.

4. The method according to claim 3, wherein the transaction security related data of the network order comprises at least: user equipment network data of the network order, user region data of the network order and time data of the network order;

wherein the user equipment network data of the network order at least comprises: the information of the user equipment code, the information of the user equipment model, the information of the user equipment communication number, the information of the IP address of the user equipment and the Wi-Fi information of the user equipment; the user territory data of the network order at least comprises: POI information of the user and city information of the user.

5. The method according to claim 4, wherein calculating a first transaction risk score according to the transaction safety related data of the current network order of the user before payment and the transaction safety related data of the historical network order of the user specifically comprises:

comparing each item of transaction safety related data of the current network order of the user before payment with transaction safety related data of a corresponding historical network order;

determining the transaction risk score of each transaction safety related data of the user before the current network order payment according to the comparison result;

and calculating a first transaction risk score according to the transaction risk score of each transaction safety related data before the current network order of the user is paid and a preset transaction risk score submodel.

6. The method according to claim 5, wherein the calculating a first transaction risk score according to the transaction risk score of each transaction safety-related data before payment of the current network order of the user and a preset transaction risk score submodel specifically comprises:

and inputting the transaction risk score of each transaction safety related data before the current network order of the user is paid into the preset transaction risk score submodel for weighted summation calculation so as to obtain the first transaction risk score.

7. The method according to claim 4, wherein calculating a second transaction risk score according to the transaction safety-related data of the user when the previous network order was paid and the transaction safety-related data of the historical network order of the user comprises:

comparing each item of transaction safety related data of the user when the previous network order is paid with the transaction safety related data of the corresponding historical network order;

determining the transaction risk score of each transaction safety related data when the previous network order of the user pays according to the comparison result;

and calculating a second transaction risk score according to the transaction risk score of each transaction safety related data when the previous network order of the user is paid and a preset transaction risk score submodel.

8. The method according to claim 7, wherein the calculating a second transaction risk score according to the transaction risk score of each transaction safety-related data when the user pays the previous network order and a preset transaction risk score submodel specifically comprises:

and inputting the transaction risk score of each transaction safety related data when the previous network order of the user is paid into the preset transaction risk score submodel for weighted summation calculation so as to obtain the second transaction risk score.

9. The method according to claim 6 or 8, wherein the calculating the transaction risk score when the current network order is paid according to the first transaction risk score, the second transaction risk score and a preset transaction risk score model specifically comprises:

and inputting the first transaction risk score and the second transaction risk score into the preset transaction risk score model for weighted summation calculation so as to obtain the transaction risk score when the current network order is paid.

10. The method of claim 9, wherein after calculating the transaction risk score for the current network order payment according to the first transaction risk score, the second transaction risk score and a preset transaction risk score model, further comprising:

judging whether the related data of each transaction safety before the current network order payment of the user is updated when each order state event before the current network order payment occurs;

if one or more transaction safety related data before the current network order is paid is updated, judging whether the first transaction risk score is changed;

and if the first transaction risk score changes, updating the transaction risk score when the current network order is paid.

11. An apparatus for transaction risk assessment, comprising:

the score calculating unit is used for calculating a transaction risk score when the current network order is paid according to transaction safety related data before the current network order of the user is paid, transaction safety related data when the previous network order of the user is paid and a preset transaction risk score model;

12. The apparatus of claim 11, wherein the data obtaining unit is further configured to obtain transaction security related data of the historical network orders of the user.

13. The apparatus according to claim 12, wherein the score calculating unit specifically includes:

the first score calculating module is used for calculating a first transaction risk score according to the transaction safety related data before the payment of the current network order of the user and the transaction safety related data of the historical network order of the user;

the second score calculating module is used for calculating a second transaction risk score according to the transaction safety related data of the user when the previous network order is paid and the transaction safety related data of the historical network order of the user;

and the total score calculating module is used for calculating the transaction risk score when the current network order is paid according to the first transaction risk score, the second transaction risk score and a preset transaction risk score model.

14. The apparatus of claim 13, wherein the transaction security related data of the network order comprises at least: user equipment network data of the network order, user region data of the network order and time data of the network order;

15. The apparatus according to claim 14, wherein the first score calculating module specifically includes:

the first comparison sub-module is used for comparing each item of transaction safety related data of the current network order of the user before payment with the transaction safety related data of the corresponding historical network order;

the first determining submodule is used for determining the transaction risk score of the transaction safety related data of each item before the current network order of the user is paid according to the comparison result;

and the first score calculating submodule is used for calculating a first transaction risk score according to the transaction risk score of each transaction safety related data before the current network order of the user pays and a preset transaction risk score submodel.

16. The apparatus according to claim 15, wherein the first score computation submodule is configured to:

17. The apparatus according to claim 14, wherein the second score calculating module specifically includes:

the second comparison sub-module is used for comparing the transaction safety related data of the previous network order of the user during payment with the transaction safety related data of the corresponding historical network order;

the second determining submodule is used for determining the transaction risk score of the transaction safety related data of each item when the previous network order of the user is paid according to the comparison result;

and the second score calculating submodule is used for calculating a second transaction risk score according to the transaction risk score of each transaction safety related data when the previous network order of the user pays and a preset transaction risk score submodel.

18. The apparatus according to claim 17, wherein the second score computation sub-module is specifically configured to:

19. The apparatus according to claim 16 or 18, wherein the total score calculating module is specifically configured to:

20. The apparatus of claim 19, further comprising:

the data updating and judging unit is used for judging whether the related data of each transaction safety before the current network order payment of the user is updated when each order state event before the current network order payment occurs;

the first score change judging unit is used for judging whether the first transaction risk score changes or not if one or more transaction safety related data before the current network order is paid are updated;

and the total score updating unit is used for updating the transaction risk score when the current network order is paid if the first transaction risk score is changed.

21. A network-side device, comprising:

a memory, a processor, and a computer program;

wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-10.

22. A computer-readable storage medium, on which a computer program is stored, which computer program is executable by a processor to implement the method according to any one of claims 1-10.