User group identification method and device, storage medium and electronic equipment

Abstract

The invention discloses a user group identification method and device, a storage medium and electronic equipment. The method relates to the field of computer software application, and comprises the following steps: acquiring user information of a plurality of users to be identified, and acquiring a plurality of user identification models; determining at least one target user identification model from a plurality of user identification models according to the risk user characteristics hit by the user information of the plurality of users; and for each target user identification model, screening the plurality of users according to the risk user features hit by the user information of the plurality of users in the target user identification model to obtain at least one risk user group belonging to a target user type, the target user type being a user type used for identification by the target user identification model. According to the invention, the technical problem of low identification accuracy of user groups with transaction risks in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of computer software applications, and in particular to a method, device, storage medium and electronic device for identifying a user group. Background Art

[0002] With the rapid development of the global economy, financial transactions have become more frequent and complex. Institutions are faced with the challenge of identifying and assessing customer transaction risks in order to prevent illegal activities and avoid financial losses. In the past, customer early warning systems could only detect early warnings for a single customer, but could not warn of illegal activities of an organization network or could only search for its accomplices based on the customer's transaction relationship, resulting in low accuracy in identifying user groups with transaction risks, making it difficult to prevent and stop illegal activities of such groups in a timely manner.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, storage medium and electronic device for identifying a user group, so as to at least solve the technical problem of low accuracy in identifying a user group with transaction risks in the related art.

[0005] According to one aspect of an embodiment of the present invention, a method for identifying a user group is provided, comprising: obtaining user information of a plurality of users to be identified, and obtaining a plurality of user identification models, wherein different user identification models are used to identify users in different types of user groups with transaction risks, and the user identification models include a plurality of risky user features; determining at least one target user identification model from the plurality of user identification models according to the risky user features hit by the user information of the plurality of users; for each target user identification model, screening a plurality of users according to the risky user features hit by the user information of the plurality of users in the target user identification model, to obtain at least one risky user group belonging to a target user type, wherein the target user type is a user type that the target user identification model is used to identify.

[0006] Furthermore, the method for identifying user groups also includes: for each user identification model, counting the number of features of risky user features hit by user information in the user identification model to obtain the target feature number; and determining the user identification model whose target feature number is greater than a preset threshold as the target user identification model.

[0007] Furthermore, the method for identifying user groups also includes: screening multiple users according to risk user features hit by user information of multiple users in a target user identification model to obtain a first user set, wherein user information of users in the first user set hits at least N risk user features in the target user identification model, where N is a positive integer; and determining at least one risk user group based on the first user set.

[0008] Furthermore, the method for identifying user groups also includes: for each user in the first user set, calculating the score of the user in the target user identification model according to the feature score calculation rules of each risk user feature, and obtaining the target score corresponding to the user; screening the users in the first user set according to the target score to obtain a second user set, wherein the target score of the users in the second user set is greater than a preset score; when the second user set is not empty, determining at least one risk user group according to the second user set.

[0009] Furthermore, the method for identifying user groups also includes: calculating the scores of each risk user feature hit by the user in the target user identification model based on the feature score calculation rules of each risk user feature; obtaining the calculation weight of each risk user feature; and calculating the target score corresponding to the user based on the calculation weight of each risk user feature and the score of each risk user feature hit by the user in the target user identification model.

[0010] Furthermore, the risk user characteristics in the target user identification model include target risk user characteristics, wherein the user group identification method also includes: determining whether there are users in the second user set whose user information hits the target risk user characteristics; if there are users in the second user set whose user information hits the target risk user characteristics, determining a third user set based on the users whose user information hits the target risk user characteristics; and determining at least one risk user group based on the third user set.

[0011] Furthermore, the method for identifying user groups also includes: determining the characteristic value of the target risk user feature of each user in the third user set; combining users with the same characteristic value of the target risk user feature in the third user set into a user group, and determining the combined user group as a risk user group.

[0012] According to another aspect of an embodiment of the present invention, a user group identification device is also provided, including: an acquisition module, used to acquire user information of multiple users to be identified, and acquire multiple user identification models, wherein different user identification models are used to identify users in different types of user groups with transaction risks, and the user identification model includes multiple risky user features; a determination module, used to determine at least one target user identification model from the multiple user identification models based on the risky user features hit by the user information of the multiple users; a processing module, used to screen multiple users for each target user identification model based on the risky user features hit by the user information of the multiple users in the target user identification model, to obtain at least one risky user group belonging to the target user type, wherein the target user type is the user type used to be identified by the target user identification model.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for identifying a user group when running.

[0014] According to another aspect of an embodiment of the present invention, an electronic device is also provided, which includes one or more processors; a memory for storing one or more programs, so that when the one or more programs are executed by the one or more processors, the one or more processors are implemented to run the programs, wherein the programs are configured to execute the above-mentioned method for identifying user groups when running.

[0015] In an embodiment of the present invention, a method of identifying a user group with transaction risks based on risk user features hit by users is adopted, by obtaining user information of multiple users to be identified and obtaining multiple user identification models, and then determining at least one target user identification model from multiple user identification models according to the risk user features hit by the user information of multiple users, so that for each target user identification model, multiple users are screened according to the risk user features hit by the user information of multiple users in the target user identification model, and at least one risk user group belonging to the target user type is obtained. Among them, different user identification models are used to identify users in different types of user groups with transaction risks, the user identification model includes multiple risk user features, and the target user type is the user type used to be identified by the target user identification model.

[0016] In the above process, since users belonging to the same user group will hit multiple risk user features in the same user identification model, at least one target user identification model is determined from multiple user identification models based on the risk user features hit by user information of multiple users, thereby achieving effective screening of user identification models corresponding to user groups of the type that may have transaction risks among multiple users. Since there is a certain correlation between the features of users belonging to the same user group, multiple users are screened based on the risk user features hit by user information of multiple users in the target user identification model to obtain at least one risk user group belonging to the target user type. Users with associated relationships can be accurately identified from multiple users, that is, users belonging to the same risk user group can be identified, thereby effectively improving the accuracy of identifying user groups with transaction risks.

[0017] It can be seen that the solution provided in the present application achieves the purpose of identifying user groups with transaction risks based on the risk user characteristics hit by users, thereby achieving the technical effect of improving the accuracy of identifying user groups with transaction risks, and further solving the technical problem of low accuracy in identifying user groups with transaction risks in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 is a schematic diagram of an optional method for identifying a user group according to an embodiment of the present invention;

[0020] Figure 2 is a schematic diagram of a hit situation of an optional user identification model according to an embodiment of the present invention;

[0021] Figure 3 is a schematic diagram of optional networking information according to an embodiment of the present invention;

[0022] Figure 4 is a schematic diagram of an optional device for identifying a user group according to an embodiment of the present invention;

[0023] Figure 5 is a schematic diagram of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] 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 for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0027] Example 1

[0028] According to an embodiment of the present invention, an embodiment of a method for identifying a user group is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Figure 1 is a schematic diagram of an optional method for identifying a user group according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0030] Step S101, obtaining user information of multiple users to be identified, and obtaining multiple user identification models, wherein different user identification models are used to identify users in different types of user groups with transaction risks, and the user identification models include multiple risky user features.

[0031] Optionally, electronic devices, application systems, servers and other devices may be used as the execution subject of the present application. In this embodiment, the target processing system is used as the execution subject to execute the method for identifying user groups.

[0032] In some embodiments, the target processing system may be a system in a financial institution, and the user may be a customer of the financial institution.

[0033] In some embodiments, the above user information includes but is not limited to the user's geographic location, the user's transaction information in financial institutions, etc. The user's transaction information includes but is not limited to the transaction object of each transaction of the user, the transaction amount of each transaction of the user, the transaction time of each transaction of the user, etc.

[0034] In some embodiments, the above-mentioned different types may be improper group transaction types, telecommunication fraud types, etc.

[0035] In some embodiments, the user identification model includes a plurality of risky user features, where the risky user features refer to features possessed by users in a user group with transaction risks.

[0036] In some embodiments, the risk user features in the target user identification model include target risk user features, which are used to identify users belonging to the same user group with transaction risks. For example, the feature values ​​of the target risk user features of users in the same user group with transaction risks are the same.

[0037] In some embodiments, the user identification model further includes a feature score calculation rule corresponding to each risky user feature in the user identification model, and the feature score calculation rule is used to calculate the score of the user in the risky user feature.

[0038] In some embodiments, the user identification model further includes a calculation weight corresponding to each risky user feature in the user identification model, and the calculation weight represents the importance of the risky user feature.

[0039] In some embodiments, the user identification model may also include partial identification logic for identifying whether the user is a user in a user group with transaction risks.

[0040] In some embodiments, the user identification model may also include a selection logic for the warning subject in the user group, wherein the warning subject may be understood as the user with the highest transaction risk in the user group.

[0041] For example, an optional user identification model includes the following:

[0042] (1) Target risk user characteristics: The customers (i.e. the above-mentioned users) are from the same region, that is, there are customers from the same region as the customer. (Weight value 40%, 100 points for high-risk regions, 80 points for medium-risk regions, and 50 points for low-risk regions);

[0043] (2) Risky user characteristics: The customer has no more than 5 trading counterparties (i.e. the trading objects mentioned above), and the number of transactions with each trading counterparty is ≥ 3. (Weight value 30%, 100 points for ≥ 10 transactions, 80 points for ≥ 5 transactions, and 50 points for ≥ 3 transactions);

[0044] (3) Risky user characteristics: The customer frequently (e.g., more than 300 transactions in one day) conducts small transactions, more than 90% of the transaction amounts are integer multiples of 10, and the total bilateral transaction amount in one day is more than 5,000 yuan. (Weight value 30%, 50 points for a bilateral total transaction amount ≥ 5,000, 80 points for a bilateral total transaction amount ≥ 10,000, and 100 points for a bilateral total transaction amount ≥ 50,000);

[0045] The triggering condition (i.e. part of the identification logic mentioned above) is: at least two risky user features are matched (including the target risky user features), and the total score must be ≥ 60 points;

[0046] Logic for selecting the warning subject: the customer with the highest total number of transactions.

[0047] Step S102: determining at least one target user identification model from a plurality of user identification models according to risky user features matched by user information of a plurality of users.

[0048] Optionally, for each user, the target processing system may determine risky user features that the user has encountered in multiple user identification models based on the user information of the user.

[0049] For example, after obtaining user information, the target processing system can determine the data involved in each risk user feature based on the user information, such as the number of transaction objects of the user, the number of transactions between the user and each transaction object, etc. Then, it is determined whether the user information of the user matches the risk user feature based on the obtained data.

[0050] Optionally, since users belonging to the same user group may hit multiple risky user features in the same user identification model, after determining the risky user features hit by the user information of each user, the target processing system may determine the user identification model with a relatively large number of hit features as the target user identification model.

[0051] Step S103, for each target user identification model, multiple users are screened according to risk user features hit by user information of multiple users in the target user identification model to obtain at least one risk user group belonging to the target user type, wherein the target user type is the user type used to identify by the target user identification model.

[0052] Since the features of users belonging to the same user group are somewhat related, the target processing system can screen multiple users to obtain at least one risk user group according to the risk user features hit by the user information of multiple users in the target user identification model.

[0053] For example, for each target user identification model, the target processing system can first screen out users who hit at least N risk user features in the target user identification model from multiple users, and then combine the screened users who have exactly the same risk user features hit in the target user identification model into a risk user group.

[0054] For another example, for each target user identification model, the target processing system may first screen out users who hit at least N risk user features in the target user identification model from multiple users, and then combine the screened users whose feature values ​​of the target risk user features in the target user identification model are the same into a risk user group.

[0055] Optionally, after determining at least one risky user group, the target processing system may update the financial transaction permissions of users in at least one risky user group in the above-mentioned financial institutions to limit the users' financial transactions in the above-mentioned financial institutions, such as reducing their maximum transaction amount, reducing the number of transactions, etc.

[0056] Optionally, after determining at least one risky user group, the target processing system may also send information about the risky user group to a risk analyst, who then performs analysis and control.

[0057] Based on the scheme defined in the above steps S101 to S104, it can be known that in the embodiment of the present invention, a method of identifying a user group with transaction risks based on risky user features hit by users is adopted, by obtaining user information of multiple users to be identified, and obtaining multiple user identification models, and then determining at least one target user identification model from multiple user identification models according to the risky user features hit by the user information of multiple users, so that for each target user identification model, multiple users are screened according to the risky user features hit by the user information of multiple users in the target user identification model, and at least one risky user group belonging to the target user type is obtained. Among them, different user identification models are used to identify users in different types of user groups with transaction risks, the user identification model includes multiple risky user features, and the target user type is the user type used to be identified by the target user identification model.

[0058] It is easy to notice that in the above process, since users belonging to the same user group will hit multiple risk user features in the same user identification model, therefore, by determining at least one target user identification model from multiple user identification models based on the risk user features hit by user information of multiple users, effective screening of user identification models corresponding to user groups of types that may have transaction risks among multiple users is achieved. Since there is a certain correlation between the features of users belonging to the same user group, therefore, by screening multiple users based on the risk user features hit by user information of multiple users in the target user identification model, at least one risk user group belonging to the target user type is obtained, and users with associated relationships can be accurately identified from multiple users, that is, users belonging to the same risk user group can be identified, thereby effectively improving the accuracy of identifying user groups with transaction risks.

[0059] It can be seen that the solution provided in the present application achieves the purpose of identifying user groups with transaction risks based on the risk user characteristics hit by users, thereby achieving the technical effect of improving the accuracy of identifying user groups with transaction risks, and further solving the technical problem of low accuracy in identifying user groups with transaction risks in related technologies.

[0060] In an optional embodiment, in the process of determining at least one target user identification model from multiple user identification models based on risky user features hit by user information of multiple users, the target processing system can, for each user identification model, count the number of features of the risky user features hit by user information in the user identification model to obtain the target feature number, and then determine the user identification model whose target feature number is greater than a preset threshold as the target user identification model.

[0061] Optionally, in this embodiment, the number of risky user features in the user identification model that are hit by the user information is determined based on whether the risky user features in the user identification model are hit, without considering the number of times the risky user features in the user identification model are hit by the user information. That is, in this embodiment, the number of target features in the user identification model is less than or equal to the total number of risky user features included in the user identification model.

[0062] Optionally, after determining the number of target features corresponding to each user identification model, the target processing system may determine a user identification model whose number of target features is greater than a preset threshold as a target user identification model.

[0063] For example, assuming the preset threshold is 2, Figure 2 is a schematic diagram of a hit situation of an optional user identification model according to an embodiment of the present invention, Figure 2 The "networking model 1" in is equivalent to the user identification model. Figure 2 "Characteristic Factor 1" - "Characteristic Factor 3" in is equivalent to the risk user characteristics. Figure 2 The "subject A"-"subject G" in is equivalent to the user, then Figure 2 The number of target features corresponding to the user identification model in is 3. Figure 2 The user identification model in is the target user identification model.

[0064] It should be noted that, through the above process, the target user identification model is accurately determined.

[0065] In an optional embodiment, in the process of screening multiple users according to the risk user features hit by user information of multiple users in the target user identification model to obtain at least one risk user group belonging to the target user type, the target processing system may screen multiple users according to the risk user features hit by user information of multiple users in the target user identification model to obtain a first user set, thereby determining at least one risk user group according to the first user set. The user information of users in the first user set hits at least N risk user features in the target user identification model, where N is a positive integer.

[0066] For example, Figure 2 The feature factor 1 in is hit by subjects (i.e. users) A, B, and C, the feature factor 2 is hit by subjects A, D, and F, and the feature factor 3 is hit by subjects A, C, and G. Assuming N is 2, we can determine Figure 2 The subject A and the subject C in are users in the first user set.

[0067] Optionally, after determining the first user set, the target processing system may determine at least one risk user group based on the first user set. For example, the users in the first user set are directly determined to belong to the same risk user group. For another example, at least one risk user group is determined based on the feature values ​​of the target risk user features of the users in the first user set.

[0068] Optionally, when the first user set is empty, it is determined that there is no risk user group of the target user type corresponding to the current target user identification model among the multiple users.

[0069] It should be noted that by eliminating users with relatively few risky user features, users with relatively low risk or no risk are effectively eliminated, thereby achieving accurate identification of risky user groups.

[0070] In an optional embodiment, in the process of determining at least one risk user group based on the first user set, the target processing system can calculate the score of each user in the first user set in the target user identification model according to the feature score calculation rules of each risk user feature, obtain the target score corresponding to the user, and then screen the users in the first user set according to the target score to obtain a second user set, wherein the target score of the users in the second user set is greater than a preset score, so that when the second user set is not empty, at least one risk user group is determined based on the second user set.

[0071] Optionally, for each user in the first user set, the target processing system may first calculate the scores of each risk user feature hit by the user in the target user identification model based on the feature score calculation rules of each risk user feature, and then calculate the target score corresponding to the user based on the scores of each risk user feature hit by the user in the target user identification model.

[0072] For example, if the risk user characteristic is "the customer has no more than 5 trading counterparts, and the number of transactions with each trading counterpart is ≥ 3", then the characteristic score calculation rule for the risk user characteristic may be "100 points for number of transactions ≥ 10, 80 points for number of transactions ≥ 5, and 50 points for number of transactions ≥ 3". Assuming that a user has 3 trading counterparts, and the number of transactions with the counterparties are 8, 11, and 12 respectively, then the user's score in the risk user characteristic is 80 points.

[0073] Optionally, the target processing system may add up the scores of each risky user feature hit by the user in the target user identification model to obtain the target score corresponding to the user. The target processing system may also perform weighted summation on the scores of each risky user feature hit by the user in the target user identification model to obtain the target score corresponding to the user. The target processing system may also calculate the target score based on a calculation formula other than addition and weighted summation.

[0074] After obtaining the target scores corresponding to each user, the target processing system can filter the users in the first user set according to the target scores to obtain the second user set. For example, assuming that the first user set includes Figure 2 For subjects A and C in the data set, the preset score is 60, the target score of subject A is 80, and the target score of subject C is 70, then the second user set includes subject A and subject C.

[0075] Optionally, the target processing system may determine at least one risk user group based on the second user set when the second user set is not empty. For example, the users in the second user set are directly determined to belong to the same risk user group. For another example, at least one risk user group is determined based on the feature values ​​of the target risk user features of the users in the second user set.

[0076] Optionally, when the second user set is empty, it is determined that there is no risk user group of the target user type corresponding to the current target user identification model among the multiple users.

[0077] It should be noted that by screening users based on their scores in the target user identification model, it is possible to more accurately eliminate users with relatively low risk or no risk, thereby further improving the accuracy of determining risky user groups.

[0078] In an optional embodiment, in the process of calculating the score of the user in the target user identification model according to the feature score calculation rules of each risk user feature to obtain the target score corresponding to the user, the target processing system can calculate the score of each risk user feature hit by the user in the target user identification model according to the feature score calculation rules of each risk user feature, and then obtain the calculation weight of each risk user feature, so as to calculate the target score corresponding to the user based on the calculation weights of each risk user feature and the score of each risk user feature hit by the user in the target user identification model.

[0079] Optionally, the calculation weight of each risk user feature is a preset value. For example, the target processing system can calculate the target score corresponding to the user based on the following formula:

[0080]

[0081] Where R represents the target score corresponding to the user, n represents the number of risky user features hit by the user in the target user identification model, and j i represents the weight of the i-th risk user feature, p i represents the score of the i-th risk user feature.

[0082] It should be noted that, through the above process, the target score corresponding to the user is accurately calculated.

[0083] In an optional embodiment, the risk user characteristics in the target user identification model include target risk user characteristics, wherein, in the process of determining at least one risk user group based on the second user set, the target processing system can determine whether there are users in the second user set whose user information hits the target risk user characteristics. If there are users in the second user set whose user information hits the target risk user characteristics, a third user set is determined based on the users whose user information hits the target risk user characteristics, and at least one risk user group is determined based on the third user set.

[0084] In some embodiments, the risk user features in the target user identification model include target risk user features, which are used to identify users in the same user group with transaction risks. For example, users in the same user group with transaction risks all hit the target risk user features.

[0085] For example, if the second user set includes Figure 2 In the subject A and subject C, assume that the target risk user characteristics are Figure 2 The characteristic factor in is 1, then we determine Figure 2 The subjects A and C in are users in the third user set. Assume that the target risk user characteristics are Figure 2 The characteristic factor in is 2, then we determine Figure 2 The subject A in is a user in the third user set.

[0086] After determining the third user set, the target processing system may determine at least one risk user group from the third user set. For example, the users in the third user set are directly determined to belong to the same risk user group. For another example, at least one risk user group is determined based on the feature values ​​of the target risk user features of the users in the third user set.

[0087] It should be noted that, through the above process, accurate determination of users with feature associations in the second user set is achieved, thereby further improving the accuracy of determining risky user groups.

[0088] In an optional embodiment, in the process of determining at least one risky user group from the third user set, the target processing system may determine the characteristic value of the target risk user characteristic of each user in the third user set, and then combine the users with the same characteristic value of the target risk user characteristic in the third user set into a user group, and determine the combined user group as the risky user group.

[0089] In some embodiments, the characteristic values ​​of the target risk user characteristics of users in the same user group with transaction risks are the same.

[0090] For example, assuming that the target risk user feature is "customers are from the same region", the corresponding feature value can be the user's geographical location. Assuming that the target risk user feature is "the customer's trading counterparties do not exceed 5, and the number of transactions with each trading counterparty is ≥ 3", the corresponding feature value can be the name of the user's trading counterparty. Assuming that the target risk user feature is "the customer frequently conducts small transactions within a day, more than 90% of the transaction amounts are integer multiples of 10, and the total bilateral transaction amount within a day is more than 5,000 yuan", the corresponding feature value can be the total transaction amount, or the transaction time, etc.

[0091] Optionally, the target processing system may combine users with the same characteristic value of the target risk user characteristic in the third user set into a user group, and determine the combined user group as the risk user group. Figure 2 The target risk user characteristics of subject A and subject C are Figure 2 In the feature factor 1, feature factor 1 is "customers belong to the same region", and it is determined that both subject A and subject C belong to region Y, then subject A and subject C can be combined into one user group, and this user group is determined as a risk user group. Further, assuming that the third user set also includes subject K and subject L, and subject K and subject L both belong to region T, then subject K and subject L can be combined into another user group, and this user group is also determined as a risk user group.

[0092] Optionally, after determining the risk user group, the target processing system may merge the information of users in the risk user group to obtain networking information. Optionally, the networking information at least includes a user identification model corresponding to the users in the risk user group, risk user features included in the user identification model, and a hit status of the user identification model.

[0093] For example, Figure 3 is a schematic diagram of an optional networking information according to an embodiment of the present invention, assuming that the risk user group includes Figure 2 In the subject A and subject C, such as Figure 3As shown, the networking information includes the networking model 1 corresponding to the subject A and the subject C, and includes the three characteristic factors in the networking model 1 and the users who hit the respective characteristic factors.

[0094] In some embodiments, the networking information may also include transaction information of the user.

[0095] In some embodiments, the warning subject can be determined from the risk user group according to the selection logic of the warning subject preset in the user identification model, and marked in the networking information, so as to facilitate the risk personnel to analyze.

[0096] It should be noted that by determining the risky user group from the third user set based on the characteristic value, the accuracy of the determined risky user group is further improved.

[0097] It can be seen that the solution provided in the present application achieves the purpose of identifying user groups with transaction risks based on the risk user characteristics hit by users, thereby achieving the technical effect of improving the accuracy of identifying user groups with transaction risks, and further solving the technical problem of low accuracy in identifying user groups with transaction risks in related technologies.

[0098] Example 2

[0099] According to an embodiment of the present invention, an embodiment of a device for identifying a user group is provided, wherein: Figure 4 is a schematic diagram of an optional user group identification device according to an embodiment of the present invention, such as Figure 4 As shown, the device comprises:

[0100] An acquisition module 401 is used to acquire user information of multiple users to be identified, and to acquire multiple user identification models, wherein different user identification models are used to identify users in different types of user groups with transaction risks, and the user identification models include multiple risky user features;

[0101] A determination module 402, configured to determine at least one target user identification model from a plurality of user identification models according to risk user features hit by user information of a plurality of users;

[0102] Processing module 403 is used to screen multiple users for each target user identification model according to risk user features hit by user information of multiple users in the target user identification model, and obtain at least one risk user group belonging to the target user type, wherein the target user type is the user type used to identify by the target user identification model.

[0103] It should be noted that the above-mentioned acquisition module 401, determination module 402 and processing module 403 correspond to steps S101 to S103 in the above-mentioned embodiment. The examples and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0104] Optionally, the determination module also includes: a statistical submodule, which is used to count the number of features of risk user features hit by user information in the user identification model for each user identification model, and obtain the target feature number; a first determination submodule, which is used to determine the user identification model whose target feature number is greater than a preset threshold as the target user identification model.

[0105] Optionally, the processing module also includes: a first processing sub-module, used to screen multiple users according to the risk user features hit by user information of multiple users in the target user identification model, to obtain a first user set, wherein user information of users in the first user set hits at least N risk user features in the target user identification model, where N is a positive integer; and a second determination sub-module, used to determine at least one risk user group based on the first user set.

[0106] Optionally, the second determination submodule also includes: a calculation unit, used to calculate the score of each user in the first user set in the target user identification model according to the feature score calculation rules of each risk user feature, and obtain the target score corresponding to the user; a first processing unit, used to screen the users in the first user set according to the target score, and obtain a second user set, wherein the target score of the users in the second user set is greater than a preset score; a first determination unit, used to determine at least one risk user group based on the second user set when the second user set is not empty.

[0107] Optionally, the calculation unit also includes: a first calculation subunit, used to calculate the scores of each risk user feature hit by the user in the target user identification model according to the feature score calculation rules of each risk user feature; an acquisition subunit, used to obtain the calculation weights of each risk user feature; and a second calculation subunit, used to calculate the target score corresponding to the user based on the calculation weights of each risk user feature and the scores of each risk user feature hit by the user in the target user identification model.

[0108] Optionally, the first determination unit also includes: a judgment subunit, used to judge whether there is a user in the second user set whose user information hits the target risk user characteristics; a first determination subunit, used to determine a third user set based on the users whose user information hits the target risk user characteristics if there is a user in the second user set whose user information hits the target risk user characteristics; and a second determination subunit, used to determine at least one risk user group based on the third user set.

[0109] Optionally, the second determination subunit also includes: a third determination subunit, used to determine the characteristic value of the target risk user characteristics of each user in the third user set; a processing subunit, used to combine users with the same characteristic value of the target risk user characteristics in the third user set into a user group, and determine the combined user group as a risk user group.

[0110] Example 3

[0111] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for identifying a user group when running.

[0112] Example 4

[0113] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, wherein: Figure 5 is a schematic diagram of an optional electronic device according to an embodiment of the present invention, such as Figure 5 As shown, the electronic device includes one or more processors; a memory for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to run the programs, wherein the programs are configured to execute the above-mentioned method for identifying user groups when running.

[0114] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0115] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0118] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0119] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0120] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for identifying a user group, characterized in that: include: Acquire user information of multiple users to be identified, and acquire multiple user identification models, wherein different user identification models are used to identify users in different types of user groups with transaction risks, and the user identification models include multiple risky user features; Determining at least one target user identification model from the multiple user identification models according to risky user features hit by the user information of the multiple users; For each target user identification model, the multiple users are screened according to risk user features hit by user information of the multiple users in the target user identification model to obtain at least one risk user group belonging to a target user type, wherein the target user type is the user type used to identify by the target user identification model.

2. The method according to claim 1, characterized in that Determining at least one target user identification model from the multiple user identification models according to risky user features hit by the user information of the multiple users includes: For each user identification model, count the number of risk user features hit by user information in the user identification model to obtain the target number of features; A user identification model whose target feature quantity is greater than a preset threshold is determined as the target user identification model.

3. The method according to claim 1, characterized in that: The plurality of users are screened according to risk user features hit by the user information of the plurality of users in the target user identification model to obtain at least one risk user group belonging to the target user type, including: According to the risk user features hit by the user information of the multiple users in the target user identification model, the multiple users are screened to obtain a first user set, wherein the user information of the users in the first user set hits at least N risk user features in the target user identification model, where N is a positive integer; The at least one risky user group is determined according to the first user set.

4. The method according to claim 3, characterized in that Determining the at least one risk user group according to the first user set includes: For each user in the first user set, the score of the user in the target user identification model is calculated according to the feature score calculation rule of each risk user feature to obtain a target score corresponding to the user; Filtering users in the first user set according to the target score to obtain a second user set, wherein the target scores of users in the second user set are greater than a preset score; When the second user set is not empty, the at least one risk user group is determined according to the second user set.

5. The method according to claim 4, characterized in that Calculating the score of the user in the target user identification model according to the feature score calculation rules of each risk user feature to obtain the target score corresponding to the user includes: According to the feature score calculation rule of each risky user feature, the score of each risky user feature hit by the user in the target user identification model is calculated; Obtain the calculation weight of each risk user feature; The target score corresponding to the user is calculated based on the calculation weights of the risky user features and the scores of the risky user features hit by the user in the target user identification model.

6. The method according to claim 4, characterized in that The risk user features in the target user identification model include target risk user features, wherein determining the at least one risk user group according to the second user set includes: Determine whether there is a user in the second user set whose user information matches the target risk user feature; If there are users whose user information matches the target risk user characteristics in the second user set, determining a third user set according to the users whose user information matches the target risk user characteristics; The at least one risk user group is determined based on the third user set.

7. The method according to claim 6, characterized in that Determining the at least one risk user group from the third user set includes: Determine a characteristic value of a target risk user characteristic of each user in the third user set; The users with the same characteristic value of the target risk user characteristic in the third user set are combined into a user group, and the combined user group is determined as the risk user group.

8. A device for identifying a user group, characterized in that: include: An acquisition module, used to acquire user information of multiple users to be identified, and to acquire multiple user identification models, wherein different user identification models are used to identify users in different types of user groups with transaction risks, and the user identification models include multiple risky user features; A determination module, configured to determine at least one target user identification model from the plurality of user identification models according to risk user features hit by the user information of the plurality of users; A processing module is used to screen the multiple users for each target user identification model according to the risk user features hit by the user information of the multiple users in the target user identification model, so as to obtain at least one risk user group belonging to the target user type, wherein the target user type is the user type used to identify by the target user identification model.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the method for identifying a user group as claimed in any one of claims 1 to 7 when running.

10. An electronic device, characterized in that: The electronic device includes one or more processors; A memory for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to run the programs, wherein the program is configured to execute the method for identifying a user group as described in any one of claims 1 to 7 when running.

Images