Number card risk determination method and device, equipment, storage medium and product
By obtaining number card orders and delivery information, the comprehensive risk level of number card is calculated, and the problem of inaccurate risk judgment in the existing technology is solved, and accurate warning and prevention of number card fraud risks is achieved.
Patent Information
- Application Number
- CN202410920735.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2024-11-08
AI Technical Summary
The existing technology has low accuracy and reliability in risk judgment in terms of fraud prevention, and cannot effectively deal with the new types of fraud methods brought about by Internet-based services. It mainly relies on post-processing and static data interception, and cannot prevent the number card in advance to become a fraud tool.
By obtaining the order information and delivery information of the number card, the first risk level is calculated using the correspondence between the preset user characteristic value and the risk index, and the geographical location consistency during the delivery process is compared, and the second risk is determined based on the location comparison results. Level, the overall risk level of the final weighted calculation number card.
It improves the accuracy and reliability of card risk judgment, and can identify fraud risks in advance during card purchase and delivery, reducing the possibility that card will become a fraud resource.
Smart Images

Figure CN118921672A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information security technology, and in particular to a method, device, equipment, storage medium and product for determining risk of a number card. Background Art
[0002] With the rapid development of information technology and mobile Internet, telecom network fraud crimes continue to occur frequently. Therefore, telecom operators need to conduct a certain degree of telecom number control to counter telecom network fraud at the technical level.
[0003] In the existing technology, anti-fraud technology methods are mainly aimed at fraud methods in traditional scenarios, relying on blacklists to intercept fraud cases or blacklist users who have been complained, mainly for post-event disposal. The interception methods are mainly based on static data such as caller numbers and user ID information, which cannot cope with new fraud methods brought about by the development of Internet-based consumption and service methods, and the accuracy and reliability of risk judgment are low. Summary of the invention
[0004] The embodiments of the present application provide a method, device, equipment, storage medium and product for determining risk of a number card, which can improve the accuracy and reliability of risk judgment.
[0005] In a first aspect, the present application provides a method for determining risk of a number card, comprising:
[0006] Obtaining order information and delivery information of the number card, wherein the order information includes at least one user feature value of the user who purchased the number card order, and the delivery information is the positions corresponding to multiple nodes in the process from purchase to use of the number card;
[0007] Determining a target risk index corresponding to each user characteristic value from a correspondence between preset user characteristic values and risk indices;
[0008] Calculating the plurality of risk indices based on a target risk level calculation formula to determine a first risk level;
[0009] Comparing the consistency between each two positions among the positions corresponding to the multiple nodes respectively to obtain multiple position comparison results;
[0010] Determining a second risk level corresponding to the plurality of position comparison results according to a correspondence between preset position comparison results and risk levels;
[0011] The final risk level of the number card is determined according to the first risk level and the second risk level.
[0012] In some possible implementations, the positions corresponding to the multiple nodes in the process from purchase to use of the number card include a purchase position, an order delivery position, and a number card activation position, and the consistency between each two positions of the positions corresponding to the multiple nodes is compared to obtain multiple position comparison results, including:
[0013] The distances between each two positions among the order delivery position, the number card activation position and the purchase position are compared respectively to see whether they are within a preset deviation range, and corresponding multiple position comparison results are obtained.
[0014] In some possible implementations, determining the second risk level corresponding to the plurality of position comparison results according to the correspondence between the preset position comparison results and the risk level includes:
[0015] Obtaining a preset correspondence between the plurality of position comparison results and risk levels;
[0016] According to the number and type of inconsistencies in the multiple position comparison results, the preset corresponding relationship is searched to obtain the corresponding second risk level.
[0017] In some possible implementations, the target risk level calculation formula is a linear regression model.
[0018] In some possible implementations, the at least one user characteristic value includes at least one of user age, user gender, number card purchase frequency, number card purchase location, and user historical behavior.
[0019] In some possible implementations, determining the final risk level of the number card according to the first risk level and the second risk level includes:
[0020] Performing a weighted summation of the first risk level and the second risk level according to a preset weight to obtain a comprehensive risk value;
[0021] According to the correspondence between the preset comprehensive risk value and the risk level, the final risk level of the number card corresponding to the comprehensive risk value is determined.
[0022] In a second aspect, the present application further provides a number card risk determination device, the device comprising:
[0023] An acquisition module, used to acquire order information and delivery information of the number card, wherein the order information includes at least one user characteristic value of the user who purchased the number card order, and the delivery information is the positions corresponding to multiple nodes in the process from purchase to use of the number card;
[0024] A determination module, used to determine a target risk index corresponding to each user characteristic value from a correspondence relationship between preset user characteristic values and risk indices;
[0025] A calculation module, used to calculate the plurality of risk indexes based on a target risk level calculation formula to determine a first risk level;
[0026] A comparison module, used for comparing the consistency between each two positions among the positions corresponding to the multiple nodes, to obtain multiple position comparison results;
[0027] The determination module is further used to determine a second risk level corresponding to the plurality of position comparison results according to a correspondence between preset position comparison results and risk levels;
[0028] The determination module is also used to determine the final risk level of the number card according to the first risk level and the second risk level.
[0029] In the third aspect, the present application provides a number card risk determination device, the device comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the number card risk determination method as described above.
[0030] In a fourth aspect, the present application provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the number card risk determination method as described above.
[0031] In a fifth aspect, the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the number card risk determination method as described above.
[0032] The risk determination method, device, equipment, storage medium and product for a number card provided in the embodiments of the present application obtain the order information and delivery information of the number card, then extract the order risk information related to the risk of fraud from the order information of the number card, calculate the multiple risk indexes based on the preset target risk level calculation formula, and determine the first risk level. After that, the multiple positions in the delivery information are compared to see if they are consistent with each other, and the second risk level is obtained according to the preset correspondence between the position comparison result information and the second risk level. Thus, the final risk level of the number card is determined according to the first risk level and the second risk level. The comprehensive risk level of the number card can be determined from two aspects: the information in the actual order and the geographical location involved in the delivery stage of the number card order, which increases the accuracy and reliability of risk judgment. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The present application can be better understood from the following description of the specific embodiments of the present application in conjunction with the accompanying drawings, in which:
[0034] Other features, objects and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, in which the same or similar reference numerals represent the same or similar features.
[0035] Figure 1 This is a flow chart of a method for determining number card risk provided by an embodiment of the present application;
[0036] Figure 2 is a flow chart of a method for determining number card risk provided by another embodiment of the present application;
[0037] Figure 3 is a flow chart of a method for calculating a second risk level provided by an embodiment of the present application;
[0038] Figure 4 It is a structural diagram of a number card risk determination device provided by an embodiment of the present application;
[0039] Figure 5 It is a schematic diagram of the hardware structure of the number card risk determination device provided in the embodiment of the present application. DETAILED DESCRIPTION
[0040] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.
[0041] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0042] In the era of rapid development of information technology and mobile Internet, telecommunications network fraud crimes continue to occur frequently. To combat telecommunications fraud crimes, telecommunications operators need to continuously optimize scientific and technological information means and enhance their technical countermeasure capabilities. The current communication fraud prevention means are mainly post-processing, that is, numbers that have been involved in fraud cases or have been complained about are included in the blacklist for interception. The interception targets are static data such as the calling number and the ID card information of relevant personnel.
[0043] In the prior art, there is a method for real-time interception of fraudulent calls based on a clustering algorithm, which preliminarily identifies fraudulent calls by using clustering algorithm, and uses logistic regression to calculate the suspicious index to further filter the threshold. However, the interval range of each characteristic index is divided according to experience and needs to be adjusted repeatedly. All weight values and maximum likelihood values in logistic regression must also be tried repeatedly. Model training has many uncertain factors, is difficult, takes a long time to adjust, and has poor generalization performance. There is also a mobile phone anti-fraud and anti-harassment method based on the International Mobile Equipment Identity (IMEI) mark, which uses voice recognition technology for word segmentation and adds new communication network elements to record terminal serial numbers instead of related fraud and harassment information of the calling number. However, it is necessary to change the communication network structure, which is difficult and costly to transform, and it is impossible to ensure that the terminal serial number is obtained in real time, the serial number may be empty, and the interception effect is poor.
[0044] As fraudulent methods emerge in an endless stream and become increasingly covert, and the subsequent anti-fraud measures cannot timely curb fraud incidents before they occur, a method is needed to advance the anti-fraud time point and reduce the purchase of number cards that may become fraud tools from the root. As telecom operators' number card business is increasingly sold through Internet channels, users need to perform real-name authentication and fill in the delivery address when purchasing number cards. Based on the information that can be obtained, such as age, delivery location, purchase frequency, gender and other characteristics, abnormal judgments can be made, so as to quickly and accurately implement screening and identification, conduct early warning intervention, and minimize the number cards from becoming fraud resources.
[0045] The inventor has studied the above problem and found that if the first risk level of card order fraud is determined when the user places an order, and the second risk level is determined by comparing the geographic location information during the subsequent order delivery and activation process, and a comprehensive index of fraud risk level is obtained after weighted calculation of the two, more accurate anti-fraud judgment can be achieved.
[0046] In order to solve the problems of the prior art, the embodiments of the present application provide a number card risk determination method, device, equipment, storage medium and product. The following first introduces the number card risk determination method provided by the embodiment of the present application. In this embodiment, the method can be executed by the above-mentioned number card risk determination device and number card risk determination device.
[0047] Figure 1 FIG. 1 is a flow chart showing a method for determining risk of a number card provided by an embodiment of the present application. Figure 1 As shown, the method includes the following steps S101 to S105.
[0048] Step S101: Obtain the order information and delivery information of the number card, the order information includes at least one user characteristic value of the user who purchased the order of the number card, and the delivery information is the positions corresponding to multiple nodes in the process from purchase to use of the number card.
[0049] In the specific implementation, when a user purchases a number card, he needs to fill in the necessary information in the order, so a related order will be generated and recorded, which includes the user feature value of the user who purchased the number card, that is, the information representing the user feature. In addition, the number card goes through multiple nodes from purchase to final use, such as shipment, mailing, and arrival at the destination. Each node corresponds to a location and status, and this information will be recorded and tracked in advance, which is the delivery information.
[0050] When it is necessary to determine the risk of a user's number card, the order information and delivery information corresponding to the number card can be queried in the relevant database through preset identification information, such as the phone number corresponding to the number card.
[0051] Step S102: Determine a target risk index corresponding to each of the above user characteristic values from the corresponding relationship between the preset user characteristic values and the risk index.
[0052] In the specific implementation, a large number of user feature values and the risk of users committing fraud are collected in advance, and the collected user feature values may be the user's age, gender, geographic location, income level, occupation and health status, etc. Based on the statistical relationship of the collected data, the corresponding relationship between the preset user feature value and the risk index is obtained.
[0053] After the user characteristic values are obtained in step S101, a search is performed according to the preset correspondence between the user characteristic values and the risk index, so that the target risk index corresponding to each user characteristic value can be obtained.
[0054] Step S103: Calculate the plurality of risk indices mentioned above based on the target risk level calculation formula to determine a first risk level.
[0055] In a specific implementation, a risk calculation formula is predefined, and the formula can calculate the overall risk level of the user based on multiple risk indices. For example, a weighted average or other combination method can be used to combine different risk indices to obtain the overall risk assessment result of the user.
[0056] As another example, for example, when using the weighted average method, the weight of each risk index needs to be determined first. The specific weight can be determined based on the importance of each risk index or determined through data analysis. Then, the first risk level is obtained by calculation based on the weight and the specific value of each risk index.
[0057] Step S104: respectively comparing the consistency between every two positions corresponding to the above-mentioned multiple nodes to obtain multiple position comparison results.
[0058] In a specific implementation, firstly, a plurality of location data records corresponding to the plurality of nodes are obtained. These location data may be represented by latitude and longitude coordinates, geographic location identifiers or other location description methods. For each node, all its location data records are compared in pairs to determine whether two different locations are in the same place, thereby obtaining a plurality of corresponding location comparison results.
[0059] As another example, evaluating the consistency between two locations may specifically use a distance metric such as Euclidean distance or Manhattan distance, or may be calculated using spherical geometry to obtain an actual geographic distance.
[0060] Step S105: Determine a second risk level corresponding to the plurality of position comparison results according to a preset correspondence relationship between the position comparison results and the risk level.
[0061] In a specific implementation, the correspondence between the preset position comparison result and the risk level is a preset table or other data structure, which lists the ranges of the comparison results of different positions and the corresponding risk levels. For multiple position comparison results, each comparison result can be traversed, and the correspondence between the preset position comparison result and the risk level can be found according to the specific consistency situation to obtain the corresponding second risk level.
[0062] Step S106: Determine the final risk level of the number card according to the first risk level and the second risk level.
[0063] In a specific implementation, the first and second risk levels of the number card are confirmed according to a preset final risk level confirmation logic to obtain the final risk level of the number card. The specific final risk level confirmation logic may be to take the higher level of the first risk level and the second risk level.
[0064] As another example, the final risk level confirmation logic may be a weighted average, that is, two levels are comprehensively calculated according to certain weights to obtain a final level.
[0065] The method for determining the risk of a number card provided in the embodiment of the present application obtains the order information and delivery information of the number card, then extracts the order risk information related to the risk of fraud from the order information of the number card, calculates the multiple risk indexes mentioned above based on the preset target risk level calculation formula, and determines the first risk level. After that, the multiple positions in the above delivery information are respectively compared to see if they are consistent with each other, and the second risk level is obtained according to the preset correspondence between the position comparison result information and the second risk level. Thus, the final risk level of the number card is determined according to the above first risk level and the above second risk level. The comprehensive risk level of the number card can be determined from two aspects: the information in the actual order and the geographical location involved in the delivery stage of the number card order, which increases the accuracy and reliability of risk judgment.
[0066] In order to avoid inaccurate risk judgment, in some embodiments, the locations corresponding to the multiple nodes in the process from purchase to use of the number card include the purchase location, the order delivery location and the number card activation location, and the above S104 may include:
[0067] The distances between each two of the order delivery locations, the number card activation locations, and the purchase locations are compared respectively to see whether they are within a preset deviation range, and corresponding multiple position comparison results are obtained.
[0068] The order delivery location may be the delivery location coordinates of each order, which may be latitude and longitude or other geographic coordinate system data. The card activation location may be the location coordinates recorded when each card is activated. The purchase location may be the location information provided by the user at the time of purchase in each order.
[0069] In the specific implementation, a preset deviation range is set in advance, which determines what kind of location difference is considered to be within an acceptable range. For example, it can be set that the distance deviation is within 100 meters and is considered consistent. For each pair of locations that need to be compared, that is, the order delivery location, the card activation location, and the purchase location, calculate the geographical distance between them. Compare the calculated distance with the preset deviation range. If the distance is within the preset range, the two locations are considered to be consistent or meet the standards; otherwise, they are considered inconsistent or do not meet the standards.
[0070] As another example, when calculating the geographic distance, spherical trigonometry or straight-line distance calculation method may be used to calculate the distance between two coordinate points according to the coordinate values.
[0071] In the above implementation of the embodiment of the present application, the positions corresponding to the multiple nodes in the process from purchase to use of the above-mentioned number card include the purchase position, the order delivery position and the number card activation position. By setting a preset deviation range, the distances between each two positions of the above-mentioned order delivery position, the above-mentioned number card activation position and the above-mentioned purchase position are compared respectively to see whether they are within the preset deviation range, allowing a certain degree of position deviation to avoid inaccurate risk judgment due to overly strict position judgment.
[0072] In order to accurately obtain the second risk level, in some implementations, the above S105 may include steps A1 to B1:
[0073] Step A1: Obtain the preset correspondence between the above-mentioned multiple position comparison results and risk levels.
[0074] In a specific implementation, the correspondence between multiple position comparison results and different risk levels is predefined. For example, the set correspondence may be: if all positions are consistent, the risk value is 0; if one position is inconsistent, the risk value is 2; if two or more positions are inconsistent, the risk value is 4. This preset correspondence may be stored in the corresponding database in the form of a key-value pair. When it is necessary to determine the second risk level, the preset correspondence between the multiple position comparison results and the risk level may be obtained from the database.
[0075] Step B1: According to the number and type of inconsistencies in the above-mentioned multiple position comparison results, the above-mentioned preset corresponding relationship is searched to obtain the corresponding second risk level.
[0076] In a specific implementation, after the comparison is completed, the number of inconsistent position pairs and the types of inconsistent positions are counted. The number of each type of inconsistency is counted, and then the preset corresponding relationship defined in step A1 is used to query the corresponding risk level according to the number and type of inconsistencies obtained by counting, and the corresponding second risk level is obtained.
[0077] As another example, the types of inconsistency may include inconsistency between the order delivery location and the number card activation location, inconsistency between the order delivery location and the purchase location, etc.
[0078] The above implementation of the embodiment of the present application first obtains the preset correspondence between multiple position comparison results and risk levels, and then searches for the preset correspondence according to the number and type of position comparison results with inconsistent results, so as to obtain the second risk level according to the correspondence. By searching according to the number and type of inconsistencies in the comparison results through the preset correspondence, the second risk level can be accurately obtained.
[0079] In order to accurately obtain the target risk index, in some embodiments, the target risk level calculation formula is a linear regression model.
[0080] Specifically, a linear regression model is a statistical model used to model the relationship between two or more variables. If there is a linear relationship between the first risk level and multiple influencing factors, the linear regression model can be used to obtain the first risk level.
[0081] In the above implementation of the embodiment of the present application, a linear regression model is used as a target risk level calculation formula to obtain a first risk level that is more in line with the actual situation.
[0082] In order to make the obtained target risk index more accurate, in some embodiments, the at least one user characteristic value includes at least one of user age, user gender, number card purchase frequency, number card purchase location, and user historical behavior.
[0083] For example, fraudsters usually buy a large number of number cards, while ordinary users generally only buy a small number of number cards they need. Therefore, the purchase frequency is an important judgment factor. The corresponding risk index can be set according to the number of number cards purchased by users in the system divided by the value of unit time. For example, if the purchase frequency is 1 time per year, the corresponding risk index can be set to 0; if the purchase frequency is 2 times per year, the corresponding risk index can be set to 1; if the purchase frequency is 3 times per year, the corresponding risk index can be set to 3; if the purchase frequency is 4 times per year, the corresponding risk index can be set to 6; if the purchase frequency is 5 times per year, the corresponding risk index can be set to 10.
[0084] In addition, the distribution of fraud cases in my country has obvious regional characteristics. For example, the southeastern coastal areas are the hardest hit areas for fraud, and the overall trend of cases is to decrease from the southeast to the north, central and western regions. According to the occurrence of relevant fraud cases, the regional risk level of the purchase location of the number card can be divided into ordinary risk level, medium risk level and high risk level, and the corresponding risk index can be set. For example, the risk index corresponding to the low-risk area is 1; the risk index corresponding to the medium-risk area is 2; and the risk index corresponding to the high-risk area is 5.
[0085] According to the age distribution of fraudsters in the existing statistical data, the relevant index of age factor can be set. For example, the age of 16-19 years old corresponds to a risk index of 0.5; the age of 20-29 years old corresponds to a risk index of 5; the age of 30-39 years old corresponds to a risk index of 4; the age of 40-49 years old corresponds to a risk index of 2; the age of 50-59 years old corresponds to a risk index of 1; the age of 60-90 years old corresponds to a risk index of 0.5.
[0086] According to the big data analysis of telecommunications fraud crimes, it can be seen that there is a certain concentration in the gender distribution of fraudsters, and thus the corresponding risk index is divided. For example, if the gender is male, the corresponding risk index is 3; if the gender is female, the corresponding risk index is 1.
[0087] Users need their ID card information when purchasing a number card, and the user's gender and age can be calculated based on the ID card number when the user purchases the number card.
[0088] If the user has been found to be involved in illegal activities such as fraud, or has been involved in relevant complaints, then the risk of purchasing a number card will be higher, so the corresponding risk index can be divided. For example, if there is a history of fraud, the corresponding risk index is 10; if there is no history of fraud, the corresponding risk index is 1.
[0089] The above implementation of the embodiment of the present application adds at least one of the user's age, user gender, number card purchase frequency, number card purchase location and user historical behavior to the user feature value, so that the obtained target risk index is more accurate.
[0090] In order to accurately obtain the second risk level, in some implementations, reference may be made to Figure 2 , the above S106 may include steps S201 to S202:
[0091] Step S201: performing weighted summation on the first risk level and the second risk level according to preset weights to obtain a comprehensive risk value.
[0092] In the specific implementation, the importance of each risk level in the comprehensive risk value is predefined to adjust the impact of different risk levels. According to the preset weights, the first risk level and the second risk level are weighted and summed accordingly. For example, if the weight of the first risk level is 0.7 and the weight of the second risk level is 0.3, then the comprehensive risk value is the result of multiplying the two risk levels by the corresponding weights and adding them together.
[0093] Step S202: According to the correspondence between the preset comprehensive risk value and the risk level, determine the final risk level of the number card corresponding to the above comprehensive risk value.
[0094] In the specific implementation, the correspondence between the comprehensive risk value and the final risk level is predefined. For example, according to the range of the comprehensive risk value, it can be mapped to different final risk levels such as low, medium, and high. Based on the actual situation, the range of comprehensive risk values for different final risk levels is determined. For example, 0-30 is defined as low risk, 31-60 as medium risk, and 61-100 as high risk. That is, when the comprehensive risk value is in the range of 0-30, the final risk level is low risk, when the comprehensive risk value is in the range of 31-60, the final risk level is medium risk, and when the comprehensive risk value is in the range of 61-100, the final risk level is high risk.
[0095] The above implementation of the embodiment of the present application performs weighted summation of the above first risk level and the above second risk level according to the preset weights to obtain a comprehensive risk value, and then determines the final risk level of the number card based on the corresponding relationship between the preset comprehensive risk value and the risk level. By performing weighted summation of the first risk level and the second risk level, the weights can be flexibly allocated according to the actual impact of the first risk level and the second risk level, thereby obtaining a more accurate final risk level of the number card.
[0096] In one embodiment of the present application, the user age, user gender, number card purchase frequency, number card purchase location and user historical behavior as described above can be obtained, and then the corresponding weights are given according to the importance of the above-mentioned user feature values. For example, the weight of purchase frequency P is 0.3; the weight of regional risk level D is 0.1; the weight of age A is 0.1; the weight of gender G is 0.05; the weight of historical behavior record H is 0.5. Then, a linear regression model is used, and the purchase frequency, regional risk level, age, gender and historical behavior record are used as input variables. The corresponding first risk level is calculated through the formula of the linear regression model: 0.3P+0.1D+0.1A+0.05G+0.5H+b. Among them, b is a parameter that is tuned considering other relevant data sources, such as user business handling records, regional crime rate data, regional economic development level and other information, in order to enrich the characteristics of the model and improve the prediction accuracy.
[0097] In the process of delivering the number card order according to the order delivery address information, refer to Figure 3 When the user activates the number card, first execute step S301 to enter the activation pre-page. Specifically, it is divided into, S3011: delivery according to the order delivery address information, record the delivery address information (X1, Y1), S3012: deliver the number card order, and obtain the actual delivery information (X2, Y2) according to the logistics order, S3013: real-time positioning in the page, obtain its pre-activated location information (X3, Y3).
[0098] Step S302: Determine whether the three are consistent. In the judgment process, a certain amount of deviation is allowed, for example, the district or county can be used as the judgment range. Step S303: If there is inconsistency, it means there is a certain risk. Specifically, the corresponding second risk level R2 can be obtained according to Table 1.
[0099] Table 1
[0100]
[0101] By fitting the risk level R1 based on the number card order information and the risk level R2 based on the order delivery and activation location information, the comprehensive risk value of the number card can be obtained. The specific calculation formula can be the weighted average, for example: R=0.6*R1+0.4*R2.
[0102] Afterwards, the final risk level of the number card is determined based on the size of the comprehensive risk value. For example, if R<1, the final risk level is low risk; if 1<=R<3, the final risk level is medium risk; if R>=3, the final risk level is high risk. The R1 and R2 weights and risk level thresholds are the best weight and threshold combination obtained by training multiple models with different weights on the data set and repeatedly verifying them. At the same time, in subsequent practice, cross-validation can be performed through manual verification and the actual use of subsequent number cards, and the parameters of the judgment model can be continuously tuned to achieve more accurate anti-fraud judgment.
[0103] After judging the risk level of the number card before it is officially used, corresponding disposal is required. For example, if the risk level of the number card is finally judged to be low risk on the activation pre-page, you can enter the activation page normally to activate the number card, and monitor the subsequent use of the number card normally according to the existing monitoring methods.
[0104] For medium-risk cards, the user will be prompted to undergo manual review on the activation pre-page. After manual review, if the card is judged to be for normal use, it can be released and enter the activation process normally. If there is indeed a risk, it will be blocked and the user will need to go to the offline business hall for subsequent disposal. High-risk cards will be automatically blocked by the system on the activation pre-page, preventing the user from entering the activation step. At the same time, clear feedback prompts are provided to users to explain the risks and provide a way to appeal.
[0105] During use, based on the above handling situations, a feedback loop mechanism is established to collect the results of manual review and actual risk event data, which are used to regularly retrain the model, adjust risk thresholds, and optimize early warning and blocking strategies.
[0106] This method proposes a fraud risk level judgment model based on number card order information, which introduces multiple factors such as purchase frequency, regional risk level, age, gender and historical records into the calculation. The multi-dimensional comprehensive formula model ensures the accuracy of the data results. It also ensures the consistency of the three points of ordering, delivery and activation. This method is based on the fact that geographic location information cannot be tampered with, which ensures the effectiveness of anti-fraud judgment.
[0107] Based on the number card risk determination method provided in the above embodiment, the present application also provides a specific implementation of the number card risk determination device. Please refer to the following embodiment.
[0108] See first Figure 4 The number card risk determination device 400 provided in the embodiment of the present application includes the following modules:
[0109] Acquisition module 401 is used to obtain the order information and delivery information of the number card. The above order information includes at least one user characteristic value of the user who purchased the order of the above number card, and the above delivery information is the positions corresponding to multiple nodes in the process from purchase to use of the above number card.
[0110] The determination module 402 is used to determine the target risk index corresponding to each of the above user characteristic values from the corresponding relationship between the preset user characteristic values and the risk index.
[0111] The calculation module 403 is used to calculate the multiple risk indexes mentioned above based on the target risk level calculation formula to determine the first risk level.
[0112] The comparison module 404 is used to compare the consistency between each two positions among the positions corresponding to the above-mentioned multiple nodes, and obtain multiple position comparison results.
[0113] The determination module 402 is further configured to determine a second risk level corresponding to the plurality of position comparison results according to a correspondence between preset position comparison results and risk levels.
[0114] The determination module 402 is further used to determine the final risk level of the number card according to the first risk level and the second risk level.
[0115] The number card risk determination device provided in the embodiment of the present application obtains the order information and delivery information of the number card, then extracts the order risk information related to the fraud risk from the number card order information, calculates the multiple risk indexes mentioned above based on the preset target risk level calculation formula, and determines the first risk level. After that, the multiple positions in the above delivery information are respectively compared to see if they are consistent with each other, and the second risk level is obtained according to the preset correspondence between the position comparison result information and the second risk level. Thus, the final risk level of the number card is determined according to the above first risk level and the above second risk level. The comprehensive risk level of the number card can be determined from two aspects: the information in the actual order and the geographical location involved in the delivery stage of the number card order, which increases the accuracy and reliability of risk judgment.
[0116] As an implementation of the present application, the number card risk determination device 400 may further include:
[0117] The comparison module is used to compare whether the distance between each two positions among the order delivery position, the number card activation position and the purchase position is within a preset deviation range, and obtain corresponding multiple position comparison results.
[0118] In the above implementation of the embodiment of the present application, the positions corresponding to the multiple nodes in the process from purchase to use of the above-mentioned number card include the purchase position, the order delivery position and the number card activation position. By setting a preset deviation range, the distances between each two positions of the above-mentioned order delivery position, the above-mentioned number card activation position and the above-mentioned purchase position are compared respectively to see whether they are within the preset deviation range, allowing a certain degree of position deviation to avoid inaccurate risk judgment due to overly strict position judgment.
[0119] As an implementation of the present application, the number card risk determination device 400 may further include:
[0120] The acquisition module is used to obtain the preset corresponding relationship between the above-mentioned multiple position comparison results and the risk level.
[0121] The search module is used to search for the preset corresponding relationship according to the number and type of inconsistencies in the above-mentioned multiple position comparison results to obtain the corresponding second risk level.
[0122] The above implementation of the embodiment of the present application first obtains the preset correspondence between multiple position comparison results and risk levels, and then searches for the preset correspondence according to the number and type of position comparison results with inconsistent results, so as to obtain the second risk level according to the correspondence. By searching according to the number and type of inconsistencies in the comparison results through the preset correspondence, the second risk level can be accurately obtained.
[0123] As an implementation method of the present application, in the number card risk determination device 400, the above-mentioned target risk level calculation formula is a linear regression model.
[0124] In the above implementation of the embodiment of the present application, a linear regression model is used as a target risk level calculation formula to obtain a first risk level that is more in line with the actual situation.
[0125] As an implementation method of the present application, in the number card risk determination device 400, the above-mentioned at least one user characteristic value includes at least one of user age, user gender, number card purchase frequency, number card purchase location and user historical behavior.
[0126] The above implementation of the embodiment of the present application adds at least one of the user's age, user gender, number card purchase frequency, number card purchase location and user historical behavior to the user feature value, so that the obtained target risk index is more accurate.
[0127] As an implementation of the present application, the number card risk determination device 400 may further include:
[0128] The summing module is used to perform weighted summation on the first risk level and the second risk level according to preset weights to obtain a comprehensive risk value.
[0129] The determination module is used to determine the final risk level of the above-mentioned number card corresponding to the above-mentioned comprehensive risk value based on the corresponding relationship between the preset comprehensive risk value and the risk level.
[0130] The above implementation of the embodiment of the present application performs weighted summation of the above first risk level and the above second risk level according to the preset weights to obtain a comprehensive risk value, and then determines the final risk level of the number card based on the corresponding relationship between the preset comprehensive risk value and the risk level. By performing weighted summation of the first risk level and the second risk level, the weights can be flexibly allocated according to the actual impact of the first risk level and the second risk level, thereby obtaining a more accurate final risk level of the number card.
[0131] The various modules in the number card risk determination device provided in the embodiment of the present application can implement the various steps in the above-mentioned number card risk determination method and achieve the corresponding effects. For the sake of concise description, they will not be repeated here.
[0132] Figure 5 A structural diagram of the number card risk determination hardware provided in an embodiment of the present application is shown.
[0133] The number card risk determination device may include a processor 501 and a memory 502 storing computer program instructions.
[0134] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0135] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.
[0136] The memory may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the number card risk determination method according to any one embodiment of the present disclosure.
[0137] The processor 501 implements any one of the number card risk determination methods in the above embodiments by reading and executing computer program instructions stored in the memory 502.
[0138] In one example, the number card risk determination device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.
[0139] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0140] Bus 510 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.
[0141] In addition, in combination with the method for determining the risk of a number card in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any method for determining the risk of a number card in the above embodiment is implemented.
[0142] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements any one of the methods for determining number card risk in the above embodiments.
[0143] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.
[0144] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.
[0145] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.
[0146] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.
[0147] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.
Claims
1. A method for determining number card risk, It is characterized in that include: Obtaining order information and delivery information of the number card, wherein the order information includes at least one user feature value of the user who purchased the number card order, and the delivery information is the positions corresponding to multiple nodes in the process from purchase to use of the number card; Determining a target risk index corresponding to each user characteristic value from a correspondence between preset user characteristic values and risk indices; Calculating the plurality of risk indices based on a target risk level calculation formula to determine a first risk level; Comparing the consistency between each two positions among the positions corresponding to the multiple nodes respectively to obtain multiple position comparison results; Determining a second risk level corresponding to the plurality of position comparison results according to a correspondence between preset position comparison results and risk levels; The final risk level of the number card is determined according to the first risk level and the second risk level.
2. The method for determining risk of a number card according to claim 1, It is characterized in that The positions corresponding to the multiple nodes in the process from purchase to use of the number card include a purchase position, an order delivery position, and a number card activation position. The consistency between each two positions of the positions corresponding to the multiple nodes is compared to obtain multiple position comparison results, including: The distances between each two positions among the order delivery position, the number card activation position and the purchase position are compared respectively to see whether they are within a preset deviation range, and corresponding multiple position comparison results are obtained.
3. The method for determining risk of a number card according to claim 1, It is characterized in that The determining, according to the correspondence between the preset position comparison results and the risk levels, a second risk level corresponding to the plurality of position comparison results comprises: Obtaining a preset correspondence between the plurality of position comparison results and risk levels; According to the number and type of inconsistencies in the multiple position comparison results, the preset corresponding relationship is searched to obtain the corresponding second risk level.
4. The method for determining risk of a number card according to claim 1, It is characterized in that The target risk level calculation formula is a linear regression model.
5. The method for determining risk of a number card according to claim 1, It is characterized in that The at least one user characteristic value includes at least one of user age, user gender, number card purchase frequency, number card purchase location and user historical behavior.
6. A method for determining risk of a number card according to any one of claims 1 to 5, It is characterized in that The determining the final risk level of the number card according to the first risk level and the second risk level includes: Performing a weighted summation of the first risk level and the second risk level according to a preset weight to obtain a comprehensive risk value; According to the correspondence between the preset comprehensive risk value and the risk level, the final risk level of the number card corresponding to the comprehensive risk value is determined.
7. A device for determining risk of a number card, It is characterized in that The device comprises: An acquisition module, used to acquire order information and delivery information of the number card, wherein the order information includes at least one user characteristic value of the user who purchased the number card order, and the delivery information is the positions corresponding to multiple nodes in the process from purchase to use of the number card; A determination module, used to determine a target risk index corresponding to each user characteristic value from a correspondence relationship between preset user characteristic values and risk indices; A calculation module, used to calculate the plurality of risk indexes based on a target risk level calculation formula to determine a first risk level; A comparison module, used for comparing the consistency between each two positions among the positions corresponding to the multiple nodes, to obtain multiple position comparison results; The determination module is further used to determine a second risk level corresponding to the plurality of position comparison results according to a correspondence between preset position comparison results and risk levels; The determination module is also used to determine the final risk level of the number card according to the first risk level and the second risk level.
8. A card risk determination device, It is characterized in that The device includes: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the number card risk determination method as described in any one of claims 1-6.
9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the number card risk determination method as described in any one of claims 1-6 is implemented.
10. A computer program product, It is characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the number card risk determination method as described in any one of claims 1-6.
Citation Information
Patent Citations
Fraud number identification method, device and equipment, and computer readable storage medium
CN109547942A
Method and device for identifying risk user
CN110147923A
Method, server and system for identifying risk telecommunication card based on activation position
CN113225740A
Telephone fraud person identification method and device, equipment and storage medium
CN114363463A
Fraud user identification method and device, electronic equipment and computer readable medium
CN114423009A
