Account identification method and device, computer equipment and storage medium
By obtaining historical business data in the financial business system and identifying related account collections, filtering target filter accounts and scoring to filter out target related account collections, the problem of low accuracy and accuracy of account group identification in the existing technology is solved, and more efficient account identification screening is achieved.
Patent Information
- Application Number
- CN202411742459.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-29
- Publication Date
- 2025-03-18
AI Technical Summary
The existing technology lacks accurate identification and screening of account groups in the financial business system, resulting in low recognition accuracy and accuracy.
By obtaining the historical business data of the target object, identifying and obtaining the associated account collection, filtering the target filter accounts according to the preset account filtering conditions, and filtering out the target related account collection through the comprehensive set score.
It improves the comprehensiveness, accuracy and accuracy of account identification and screening, and can more effectively identify potential abnormal accounts and account groups.
Smart Images
Figure CN119648430A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet technology, and in particular to an account identification method, apparatus, computer equipment, storage medium and computer program product. Background Art
[0002] In some financial business systems, in order to ensure account security, it is necessary to identify and screen abnormal accounts.
[0003] The current related technologies lack the identification and screening of account groups, and have problems of low precision and accuracy. Summary of the invention
[0004] Based on this, it is necessary to provide an account identification method, apparatus, computer device, storage medium and computer program product to address the above technical issues.
[0005] In a first aspect, the present application provides an account identification method. The method comprises:
[0006] Acquire historical business data of the target object, and acquire at least one associated account set of the target object based on the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts;
[0007] According to the historical business data, determining the associated accounts that meet the preset account screening conditions among the multiple associated accounts in each associated account set as target screening accounts;
[0008] Obtaining a comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets;
[0009] According to the comprehensive score of the set, a target associated account set is screened out from at least one of the associated account sets.
[0010] In one embodiment, the associated account set corresponds to an associated resource transfer business order; obtaining at least one associated account set of the target object based on the historical business data includes: obtaining multiple resource transfer business orders contained in the historical business data; determining at least one associated account corresponding to each of the resource transfer business orders; and determining the associated account set based on at least one of the associated accounts.
[0011] In one of the embodiments, the associated account set corresponds to multiple associated resource transfer business orders; obtaining at least one associated account set of the target object based on the historical business data includes: obtaining multiple resource transfer business orders included in the historical business data; determining multiple associated resource transfer business orders based on the multiple resource transfer business orders; multiple associated resource transfer business orders have the same associated account; and determining the associated account set based on the multiple associated accounts corresponding to the multiple associated resource transfer business orders.
[0012] In one of the embodiments, determining, according to the historical business data, the associated account that meets the preset account screening condition among the multiple associated accounts in each of the associated account sets as the target screening account includes: acquiring at least one account feature of each of the associated accounts according to the historical business data; judging whether the corresponding associated account meets the preset account screening condition according to the at least one account feature; and determining the associated account as the target screening account if the associated account meets the preset account screening condition.
[0013] In one of the embodiments, obtaining a comprehensive set score of each of the associated account sets based on the number of the target filtered accounts in each of the associated account sets includes: obtaining a proportion of filtered accounts occupied by the target filtered accounts in each of the associated account sets based on the number of the target filtered accounts in each of the associated account sets; and obtaining the comprehensive set score of each of the associated account sets based on the proportion of filtered accounts.
[0014] In one of the embodiments, screening out a target associated account set from at least one of the associated account sets according to the set comprehensive score includes: determining the associated account set whose set comprehensive score is greater than a preset score threshold as the target associated account set.
[0015] In a second aspect, the present application provides an account identification device. The device comprises:
[0016] an acquisition module, configured to acquire historical business data of a target object, and acquire at least one associated account set of the target object according to the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes a plurality of associated accounts;
[0017] A first screening module, configured to determine, according to the historical business data, the associated accounts in each associated account set that meet a preset account screening condition as target screening accounts;
[0018] A scoring module, configured to obtain a comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets;
[0019] The second screening module is used to screen out a target associated account set from at least one of the associated account sets according to the comprehensive score of the set.
[0020] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
[0021] Acquire historical business data of the target object, and acquire at least one associated account set of the target object based on the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts;
[0022] According to the historical business data, determining the associated accounts that meet the preset account screening conditions among the multiple associated accounts in each associated account set as target screening accounts;
[0023] Obtaining a comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets;
[0024] According to the comprehensive score of the set, a target associated account set is screened out from at least one of the associated account sets.
[0025] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0026] Acquire historical business data of the target object, and acquire at least one associated account set of the target object based on the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts;
[0027] According to the historical business data, determining the associated accounts that meet the preset account screening conditions among the multiple associated accounts in each associated account set as target screening accounts;
[0028] Obtaining a comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets;
[0029] According to the comprehensive score of the set, a target associated account set is screened out from at least one of the associated account sets.
[0030] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0031] Acquire historical business data of the target object, and acquire at least one associated account set of the target object based on the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts;
[0032] According to the historical business data, determining the associated accounts that meet the preset account screening conditions among the multiple associated accounts in each associated account set as target screening accounts;
[0033] Obtaining a comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets;
[0034] According to the comprehensive score of the set, a target associated account set is screened out from at least one of the associated account sets.
[0035] In the above account identification method, device, computer equipment, storage medium and computer program product, historical business data of the target object is obtained, and at least one associated account set of the target object is obtained based on the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts; based on the historical business data, the associated accounts that meet the preset account screening conditions among the multiple associated accounts of each associated account set are determined as target screening accounts; based on the number of target screening accounts in each associated account set, the set comprehensive score of each associated account set is obtained; based on the set comprehensive score, the target associated account set is screened out from at least one associated account set. In the method provided in the embodiment of the present application, business processing experience and artificial intelligence are combined to identify and screen account groups in multiple dimensions, thereby improving the comprehensiveness, precision and accuracy of account identification and screening. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0037] Figure 1 A flowchart of an account identification method provided in an embodiment of the present application;
[0038] Figure 2A schematic diagram of a process for determining a set of associated accounts provided in an embodiment of the present application;
[0039] Figure 3 A schematic diagram of another process for determining a set of associated accounts provided in an embodiment of the present application;
[0040] Figure 4 A schematic diagram of a process of screening target and screening account provided in an embodiment of the present application;
[0041] Figure 5 A structural block diagram of an account identification device provided in an embodiment of the present application;
[0042] Figure 6 An internal structure diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0044] In an exemplary embodiment, Figure 1 As shown, an account identification method is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:
[0045] Step 102: Acquire historical business data of the target object, and acquire at least one associated account set of the target object based on the historical business data.
[0046] Among them, each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts. In this step, first, the historical business data of the target object can be obtained. The target object can be any financial business system, such as an insurance business system. The historical business data can include financial business data of the historical time period corresponding to the current time period, such as an insurance business system, and business processing data of the associated business system of the insurance business system, such as a user information database and a transaction record database in a group insurance business system. The user data contained therein, i.e., account data, can be obtained through the historical business data. The user data can include but is not limited to (1) basic user data, such as gender, age, and marital status; (2) resource transfer behavior information of the account corresponding to the user, taking insurance business as an example, such as basic behavior data such as user insurance behavior, claim reporting behavior, and annuity collection behavior; (3) associated user relationship information in group insurance business. Furthermore, the pre-built account recognition model can be used to obtain the basic characteristic data corresponding to each user based on the basic user information of each user (or account) and the resource transfer behavior information of the account corresponding to the user, such as the number of insurance policies purchased by the insured, the number of insured persons under the insured, and the number of claims reported by the user when the user is the insured. Further, at least one associated account set of the target object can be obtained according to the historical business data. This process can be understood as the group division of multiple accounts of the corresponding financial business system. Specifically, taking the insurance business system as an example, in a possible implementation, multiple resource transfer business orders can be determined according to the historical business data. The resource transfer business order can be an insurance policy. The insurance policy can correspond to at least one associated account, for example, the insured, the insured and the beneficiary. The insured, the insured and the beneficiary corresponding to the same policy can be divided into a group to form an associated account set, and the group identifier corresponding to the associated account set is set; in another possible implementation, multiple insurance policies can have the same associated account. For example, if multiple policies are associated with the same insured, the insured or the beneficiary, they are merged into one group, and a group identifier is set for each group. The division of groups is mainly based on the relationship between the insured, the insured and the beneficiary of the group insurance user. The insured, the insured and the beneficiary under one policy will be set as the same group; if multiple policies are associated with the same insured, the insured or the beneficiary, they are also merged into one group. For example, if a company purchases group insurance for its employees, the employees (insured persons) and the company (policyholder) in the policy form a group; if the company has the same employees or itself as the policyholder, insured, or beneficiary in other policies, these related persons will be merged into the same group. Group members in each group, i.e., associated accounts, will generate various behavioral data during the group insurance business process, such as insurance behavior, claim reporting behavior, annuity collection behavior, etc.When analyzing suspicious characteristics, the focus is on the performance of these group members in these business behaviors. For example, calculating the number of claims of each member of a group is to count the behavioral data of all policyholders, insured persons, and beneficiaries belonging to the group in terms of claims, in order to determine whether they meet aggregate characteristics such as "number of claims > 3 times". The behavioral characteristics of group members and their distribution within the group (that is, the proportion of group members who meet specific aggregate characteristics to the total number of group members) are important bases for measuring whether the entire group is suspected of money laundering. If a group has more members (satisfying a certain sharing ratio) who have certain suspicious behavioral characteristics (such as a high number of claims), the group's money laundering suspicion will increase accordingly.
[0047] Step 104: According to the historical business data, the associated accounts in each associated account set that meet the preset account screening condition are determined as target screening accounts.
[0048] Among them, according to the historical business data, at least one account feature of each associated account is obtained, and the account feature includes the user's basic feature; according to the at least one account feature, it is determined whether the corresponding associated account meets the preset account screening condition; if the associated account meets the preset account screening condition, the associated account is determined as the target screening account. In a possible implementation, the pre-built account recognition model can be used to obtain the basic feature data corresponding to each user according to the user basic information of each user (or associated account) and the resource transfer behavior information of the account corresponding to the user, such as the number of insurance policies purchased by the insured, the number of insured persons under the insured, and the number of claims declarations when the user is the insured. Next, the feature statistics of each account feature of the associated account can be calculated, such as frequency, summation and probability statistics. Specifically, the first step is data collection and sorting. First, data related to the basic features of the user can be extracted from the historical business data. These data sources include but are not limited to the user information database and transaction record database in the group insurance business system. For example, for features related to user insurance behavior, it is necessary to obtain the insurance records of all users, including detailed information such as the policy number, insurance time, and insurance amount of each insurance; for claims reporting when the user is the insured, it is necessary to collect data such as the time, amount, and reason of the claim reporting; for basic user information such as gender, age, marital status, etc., directly obtain it from the user basic information table. The second step is to determine the statistical features and corresponding data fields. According to the account features involved, such as user basic features, the content to be counted and the corresponding database fields are clearly defined. For example, for the feature "the number of insurance policies purchased by the insured", the corresponding database field is the "policy number" in the insurance record, and the number of insurances is counted by counting different policy numbers; for "the number of insureds under the insured", it is necessary to associate the relationship table between the insured and the insured, and count the number of insured records associated with it based on the insured ID; for "the number of claims reporting when the user is the insured", the corresponding field is the "insured ID" field in the claim reporting record, and the number of times the ID appears is counted. The third step is to calculate the number of statistical values: for each determined basic user feature, write a program or use a database query statement to count the number of times. For other similar features, such as the number of claims, a similar approach is used, except that the query conditions and statistical fields are adjusted according to the specific features. For calculating the summed statistical values: for some features that need to be summed, such as the total amount of insurance paid by the insured, after obtaining the insured amount field, use the corresponding summation function for calculation. For other features that may involve summation, such as the total amount obtained by the insured from claims, similar methods are used to perform summation calculations based on relevant data fields and query conditions.In a possible implementation, the calculated feature statistics of each user's basic features can be stored in a new data table to facilitate further analysis and processing of these data in subsequent steps. The data table can contain user identifiers (e.g., policyholder ID, insured ID, etc.) and columns for various statistical features, such as the number of insurance purchases, the number of claims filings, the total amount of insurance, etc.
[0049] Further, it is possible to determine whether the corresponding associated account meets the preset account screening condition according to the characteristic statistical value of each account characteristic of the associated account. The preset account screening condition can be set according to the specification in the business handling process, and the preset account screening condition can be used to identify and screen the abnormality of the associated account, for example, the number of claims>3 times and the number of surrendered policies>1, etc. Taking the characteristic of the number of claims as an example, the preset account screening condition includes the account characteristic "number of claims", then the associated business data of the account characteristic "number of claims" of each associated account are traversed to obtain the characteristic statistical value of the account characteristic "number of claims" of each associated account. If the characteristic statistical value of the account characteristic "number of claims" of each associated account is greater than the preset number threshold, for example, 3 times, it is determined that the corresponding associated account meets the preset account screening condition, and the associated account can be determined to be a potential abnormal account, that is, a target screening account; if the characteristic statistical value of the account characteristic "number of claims" of each associated account is less than or equal to the preset number threshold, for example, 3 times, it is determined that the corresponding associated account does not meet the preset account screening condition, and the associated account can be determined to be a non-potential abnormal account, that is, a non-target screening account.
[0050] Step 106: Obtain a comprehensive score of each associated account set according to the number of target screening accounts in each associated account set.
[0051] Among them, each associated account set includes multiple associated accounts, and each associated account in the multiple associated accounts is judged as a target screening account, and then the number of target screening accounts included in each associated account set can be statistically obtained. Further, according to the number of target screening accounts included in each associated account set, the screening account proportion of the target screening account in each associated account set can be obtained, and the screening account proportion can be used to measure the potential abnormal probability of the corresponding associated account set. Therefore, according to the screening account proportion of the target screening account in each associated account set, the set comprehensive score of each associated account set can be obtained. The higher the screening account proportion of the target screening account in each associated account set, the higher the set comprehensive score of the corresponding associated account set; the lower the screening account proportion of the target screening account in each associated account set, the lower the set comprehensive score of the corresponding associated account set.
[0052] The target screening account is a potentially abnormal account, which can be understood as a suspicious account. The higher the screening account proportion of the target screening account included in the associated account set, the higher the set comprehensive score, indicating that the higher the degree of aggregation of the associated account set in terms of suspicious features, the higher the overall suspiciousness. Among them, the preset account screening condition can include multiple suspicious features. Based on the preset account screening condition, multiple associated accounts in each associated account set are evaluated, and the performance of each associated account set in multiple suspicious behaviors can be comprehensively evaluated, which provides an important basis for the subsequent calculation of the suspicious score of the group, that is, the associated account set, and the identification of anti-money laundering gangs.
[0053] Step 108: Filter out a target associated account set from at least one associated account set according to the comprehensive score of the set.
[0054] Among them, the associated account set whose set comprehensive score is greater than the preset score threshold can be determined as the target associated account set. In a possible implementation, a sorting algorithm can be used to sort the set comprehensive scores of at least one associated account set, for example, from large to small, and then a reference value can be determined as the preset score threshold, and the associated account set whose set comprehensive score is greater than the preset score threshold can be determined as the target associated account set. The target associated account set can be an abnormal associated account set.
[0055] In the method of this embodiment, historical business data of the target object is obtained, and at least one associated account set of the target object is obtained based on the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts; based on the historical business data, the associated accounts that meet the preset account screening conditions among the multiple associated accounts of each associated account set are determined as target screening accounts; based on the number of target screening accounts in each associated account set, the set comprehensive score of each associated account set is obtained; based on the set comprehensive score, the target associated account set is screened out from at least one associated account set. In the method provided in the embodiment of the present application, business processing experience and artificial intelligence are combined to identify and screen account groups in multiple dimensions, thereby improving the comprehensiveness, precision and accuracy of account identification and screening.
[0056] In an exemplary embodiment, Figure 2 As shown, obtaining at least one associated account set of the target object according to historical business data in step 102 may include steps 202 to 206. Among them:
[0057] Step 202: Acquire multiple resource transfer service orders included in the historical service data.
[0058] Step 204: determine at least one associated account corresponding to each resource transfer service order.
[0059] Step 206: Determine a set of associated accounts based on at least one associated account.
[0060] Among them, multiple resource transfer business orders can be determined based on the historical business data. The resource transfer business order can be an insurance policy. The insurance policy can correspond to at least one associated account, for example, the insured, the insured and the beneficiary. The insured, the insured and the beneficiary corresponding to the same policy can be divided into a group to form an associated account set, and a group identifier corresponding to the associated account set can be set.
[0061] In an exemplary embodiment, Figure 3 As shown, obtaining at least one associated account set of the target object according to historical business data in step 102 may include steps 302 to 306. Among them:
[0062] Step 302: Acquire multiple resource transfer service orders included in the historical service data.
[0063] Step 304: Determine multiple associated resource transfer service orders based on the multiple resource transfer service orders.
[0064] Multiple associated resource transfer business orders have the same associated account.
[0065] Step 306: Determine a set of associated accounts according to the multiple associated accounts corresponding to the multiple associated resource transfer service orders.
[0066] Multiple insurance policies can have the same associated account. For example, if multiple policies are associated with the same policyholder, insured, or beneficiary, they will be merged into one group, and a group identifier will be set for each group. The division of groups is mainly based on the relationship between the policyholder, insured, and beneficiary of group insurance users. The policyholder, insured, and beneficiary under one policy will be placed in the same group; if multiple policies are associated with the same policyholder, insured, or beneficiary, they will also be merged into one group. For example, a company purchases group insurance for its employees, and the employees (insured) and the company (policyholder) in the policy constitute a group; if the company involves the same employees in other policies or itself as the policyholder, insured, or beneficiary, these related personnel will be merged into the same group.
[0067] In the method of this embodiment, group division can be achieved based on historical business data, and further, multi-dimensional identification and screening of account groups can be achieved, thereby improving the comprehensiveness, precision and accuracy of account identification and screening.
[0068] In an exemplary embodiment, Figure 4 As shown, step 104 may include steps 402 to 406. Among them:
[0069] Step 402: Obtain at least one account feature of each associated account based on historical business data.
[0070] Step 404: determine whether the corresponding associated account meets a preset account screening condition based on at least one account characteristic.
[0071] Step 406: If the associated account meets the preset account screening condition, the associated account is determined as a target screening account.
[0072] The pre-built account identification model can be used to obtain the basic feature data corresponding to each user, such as the number of insurance policies purchased by the insured, the number of insured persons under the insured, and the number of claims reported when the user is the insured, based on the user basic information of each user (or associated account) and the resource transfer behavior information of the account corresponding to the user, such as the number of insurance policies purchased by the insured, the number of insured persons under the insured, and the number of claims reported when the user is the insured. Next, the feature statistics of each account feature of the associated account can be calculated, such as frequency, summation, and probability statistics. Specifically, the first step is data collection and collation. First, data related to the basic features of the user can be extracted from the historical business data. These data sources include but are not limited to the user information database and transaction record database in the group insurance business system. For example, for the features related to the user's insurance behavior, it is necessary to obtain the insurance records of all users, including detailed information such as the policy number, insurance time, and insurance amount of each insurance; for the claims reported when the user is the insured, it is necessary to collect data such as the time, amount, and reason of the claims report; for the basic information of the user, such as gender, age, marital status, etc., it is directly obtained from the user basic information table. The second step is to determine the statistical features and corresponding data fields. According to the account features involved, such as the basic user features, the content to be counted and the corresponding database fields are clearly defined. For example, for the feature of "the number of insurance policies purchased by the insured", the corresponding database field is the "policy number" in the insurance record. The number of insurance purchases is counted by counting different policy numbers; for "the number of insured persons under the insured", it is necessary to associate the relationship table between the insured and the insured, and count the number of insured records associated with it based on the insured ID; for "the number of claims reported when the user is the insured", the corresponding field is the "insured ID" field in the claim reporting record, and the number of times the ID appears is counted. The third step is to calculate the number of statistical values: for each determined basic user feature, write a program or use a database query statement to count the number of times. For other similar features, such as the number of claims reports, a similar approach is also used, except that the query conditions and statistical fields are adjusted according to the specific features. For calculating summed statistical values: For some features that need to be summed, such as the total amount of insurance paid by the policyholder, after obtaining the insurance amount field, use the corresponding summation function for calculation. For other features that may involve summation, such as the total amount of claims received by the insured, etc., similar methods are used to perform summation calculations based on relevant data fields and query conditions. In one possible implementation, the calculated feature statistics of each user's basic features can be stored in a new data table to facilitate further analysis and processing of these data in subsequent steps. The data table can contain user identifiers (for example, policyholder ID, insured ID, etc.) and columns for various statistical features, such as the number of insurances, the number of claims reports, the total amount of insurance, etc.
[0073] Further, it is possible to determine whether the corresponding associated account meets the preset account screening condition according to the characteristic statistical value of each account characteristic of the associated account. The preset account screening condition can be set according to the specification in the business handling process, and the preset account screening condition can be used to identify and screen the abnormality of the associated account, for example, the number of claims>3 times and the number of surrendered policies>1, etc. Taking the characteristic of the number of claims as an example, the preset account screening condition includes the account characteristic "number of claims", then the associated business data of the account characteristic "number of claims" of each associated account are traversed to obtain the characteristic statistical value of the account characteristic "number of claims" of each associated account. If the characteristic statistical value of the account characteristic "number of claims" of each associated account is greater than the preset number threshold, for example, 3 times, it is determined that the corresponding associated account meets the preset account screening condition, and the associated account can be determined to be a potential abnormal account, that is, a target screening account; if the characteristic statistical value of the account characteristic "number of claims" of each associated account is less than or equal to the preset number threshold, for example, 3 times, it is determined that the corresponding associated account does not meet the preset account screening condition, and the associated account can be determined to be a non-potential abnormal account, that is, a non-target screening account.
[0074] In the method of this embodiment, the business processing experience and artificial intelligence are combined to perform statistics on the feature statistics of the account features of the associated accounts, and the suspicious features are determined in combination with the business processing experience. By setting multiple primary suspicious features and secondary suspicious features, multiple associated accounts in each associated account set are evaluated. The performance of each associated account set in multiple suspicious behaviors can be comprehensively evaluated, and the accuracy of identifying and screening the associated account set can be improved.
[0075] In an exemplary embodiment, step 106 may include:
[0076] According to the number of target screening accounts in each associated account set, the proportion of the screening accounts in each associated account set is obtained; according to the proportion of the screening accounts, the set comprehensive score of each associated account set is obtained.
[0077] Among them, each associated account set includes multiple associated accounts, and each associated account in the multiple associated accounts is judged as a target screening account, and then the number of target screening accounts included in each associated account set can be statistically obtained. Further, according to the number of target screening accounts included in each associated account set, the screening account proportion of the target screening account in each associated account set can be obtained, and the screening account proportion can be used to measure the potential abnormal probability of the corresponding associated account set. Therefore, according to the screening account proportion of the target screening account in each associated account set, the set comprehensive score of each associated account set can be obtained. The higher the screening account proportion of the target screening account in each associated account set, the higher the set comprehensive score of the corresponding associated account set; the lower the screening account proportion of the target screening account in each associated account set, the lower the set comprehensive score of the corresponding associated account set.
[0078] The target screening account is a potentially abnormal account, which can be understood as a suspicious account. The higher the screening account proportion of the target screening account included in the associated account set, the higher the set comprehensive score, indicating that the higher the degree of aggregation of the associated account set in terms of suspicious features, the higher the overall suspiciousness. Among them, the preset account screening condition can include multiple suspicious features. Based on the preset account screening condition, multiple associated accounts in each associated account set are evaluated, and the performance of each associated account set in multiple suspicious behaviors can be comprehensively evaluated, which provides an important basis for the subsequent calculation of the suspicious score of the group, that is, the associated account set, and the identification of anti-money laundering gangs.
[0079] In an exemplary embodiment, step 108 may include:
[0080] The associated account set whose set comprehensive score is greater than the preset score threshold is determined as the target associated account set.
[0081] Among them, a sorting algorithm can be used to sort the set comprehensive scores of at least one associated account set, for example, from large to small, and then a reference value can be determined as a preset score threshold, and the associated account set whose set comprehensive score is greater than the preset score threshold can be determined as a target associated account set. The target associated account set can be an abnormal associated account set.
[0082] In the method of this embodiment, the target screening account is a potentially abnormal account, which can be understood as a suspicious account. The higher the screening account proportion of the target screening account included in the associated account set, the higher the set comprehensive score, indicating that the degree of aggregation of the associated account set in terms of suspicious features is higher, and the overall suspicion increases accordingly. By evaluating the corresponding associated account set with a higher screening account proportion of the target screening account included in the associated account set, the set comprehensive score is obtained, thereby improving the precision and accuracy of abnormal identification and screening of accounts and account groups.
[0083] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0084] Based on the same inventive concept, the embodiment of the present application also provides an account identification device for implementing the account identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more account identification device embodiments provided below can refer to the limitations on the account identification method above, and will not be repeated here.
[0085] In one embodiment, Figure 5 As shown, an account identification device is provided, including: an acquisition module 502, a first screening module 504, a scoring module 506 and a second screening module 508, wherein:
[0086] The acquisition module 502 is used to acquire historical business data of the target object, and acquire at least one associated account set of the target object according to the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts;
[0087] A first screening module 504, configured to determine, according to the historical business data, the associated accounts in each associated account set that meet a preset account screening condition as target screening accounts;
[0088] A scoring module 506, configured to obtain a set comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets;
[0089] The second screening module 508 is configured to screen out a target associated account set from at least one of the associated account sets according to the comprehensive score of the set.
[0090] In one embodiment, the associated account set corresponds to an associated resource transfer business order; the acquisition module 502 is also used to: obtain multiple resource transfer business orders included in the historical business data; determine at least one associated account corresponding to each of the resource transfer business orders; and determine the associated account set based on at least one of the associated accounts.
[0091] In one embodiment, the associated account set corresponds to multiple associated resource transfer business orders; the acquisition module 502 is also used to: obtain multiple resource transfer business orders included in the historical business data; determine multiple associated resource transfer business orders based on the multiple resource transfer business orders; multiple associated resource transfer business orders have the same associated account; determine the associated account set based on the multiple associated accounts corresponding to the multiple associated resource transfer business orders.
[0092] In one embodiment, the first screening module 504 is further used to: obtain at least one account feature of each of the associated accounts based on the historical business data; determine whether the corresponding associated account meets the preset account screening condition based on the at least one account feature; if the associated account meets the preset account screening condition, determine the associated account as the target screening account.
[0093] In one embodiment, the scoring module 506 is further used to: obtain the proportion of the target filtered accounts in each of the associated account sets according to the number of the target filtered accounts in each of the associated account sets; and obtain the set comprehensive score of each of the associated account sets according to the filtered account proportion.
[0094] In one embodiment, the second screening module 508 is further configured to: determine the associated account set whose set comprehensive score is greater than a preset score threshold as the target associated account set.
[0095] Each module in the above account identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0096] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store account identification related data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an account identification method is implemented.
[0097] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0098] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.
[0099] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0100] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0101] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0102] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0103] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0104] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. An account identification method, characterized in that: The method comprises: Acquire historical business data of the target object, and acquire at least one associated account set of the target object based on the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes multiple associated accounts; According to the historical business data, determining the associated accounts that meet the preset account screening conditions among the multiple associated accounts in each associated account set as target screening accounts; Obtaining a comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets; According to the comprehensive score of the set, a target associated account set is screened out from at least one of the associated account sets.
2. The method according to claim 1, characterized in that The associated account set corresponds to an associated resource transfer business order; The acquiring, according to the historical business data, at least one associated account set of the target object includes: Acquire multiple resource transfer business orders included in the historical business data; Determine at least one associated account corresponding to each of the resource transfer business orders; The associated account set is determined according to at least one of the associated accounts.
3. The method according to claim 1, characterized in that The associated account set corresponds to a plurality of associated resource transfer business orders; The acquiring, according to the historical business data, at least one associated account set of the target object includes: Acquire multiple resource transfer business orders included in the historical business data; Determining a plurality of associated resource transfer service orders according to the plurality of resource transfer service orders; wherein the plurality of associated resource transfer service orders have the same associated account; The associated account set is determined according to the multiple associated accounts corresponding to the multiple associated resource transfer business orders.
4. The method according to claim 1, characterized in that: The step of determining, according to the historical business data, the associated accounts that meet a preset account screening condition among the multiple associated accounts in each associated account set as target screening accounts includes: Acquire at least one account feature of each of the associated accounts according to the historical business data; According to the at least one account characteristic, determining whether the corresponding associated account meets the preset account screening condition; If the associated account meets the preset account screening condition, the associated account is determined as the target screening account.
5. The method according to claim 1, characterized in that The step of obtaining a comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets includes: According to the number of the target screening accounts in each of the associated account sets, obtaining the proportion of the screening accounts accounted for by the target screening accounts in each of the associated account sets; The comprehensive score of each associated account set is obtained according to the proportion of the screened accounts.
6. The method according to any one of claims 1 to 5, characterized in that: The step of selecting a target associated account set from at least one of the associated account sets according to the set comprehensive score includes: The associated account set whose set comprehensive score is greater than a preset score threshold is determined as the target associated account set.
7. An account identification device, characterized in that: The device comprises: an acquisition module, configured to acquire historical business data of a target object, and acquire at least one associated account set of the target object according to the historical business data; each associated account set corresponds to at least one associated resource transfer business order; each associated account set includes a plurality of associated accounts; A first screening module, configured to determine, according to the historical business data, the associated accounts in each associated account set that meet a preset account screening condition as target screening accounts; A scoring module, configured to obtain a comprehensive score of each of the associated account sets according to the number of the target screening accounts in each of the associated account sets; The second screening module is used to screen out a target associated account set from at least one of the associated account sets according to the comprehensive score of the set.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.