CN110875834A

CN110875834A - Wind control model creating method, wind control evaluation method and related device

Info

Publication number: CN110875834A
Application number: CN201811015239.0A
Authority: CN
Inventors: 廖家绪; 王能; 鹿凌华
Original assignee: Consumer Finance Ltd By Share Ltd
Current assignee: Consumer Finance Ltd By Share Ltd
Priority date: 2018-08-31
Filing date: 2018-08-31
Publication date: 2020-03-10

Abstract

The application discloses a wind control model creating method, a wind control evaluating method and a related device. The construction method comprises the following steps: acquiring user environment information of a sample IP address; determining the type of the sample IP address according to the user environment information; and constructing to obtain the wind control model by using the type of the sample IP address and the characteristic data of the sample IP address. Through the mode, the accuracy of wind control evaluation can be improved.

Description

Wind control model creating method, wind control evaluation method and related device

Technical Field

The present application relates to the field of information processing, and in particular, to a method for creating a wind control model, a method for evaluating wind control, and a related apparatus.

Background

At present, the internet financial industry is gradually rising along with the development of internet technology, which brings great convenience to credit of people. But at the same time, the generation of the internet financial industry has also lowered the credit threshold of the masses. Typically, a user only needs to fill in a small amount of personal data on an online credit system to apply for a loan, which increases the risk of credit to some extent. In order to ensure the stable development of the internet financial industry, an accurate internet wind control technology is very important.

Disclosure of Invention

The technical problem mainly solved by the application is to provide a method and a related device for creating a wind control model and evaluating wind control, and the accuracy of wind control evaluation can be improved.

In order to solve the above problem, a first aspect of the present application provides a method for creating a wind control model, where the method includes: acquiring user environment information of a sample IP address; determining the type of the sample IP address according to the user environment information; and constructing to obtain the wind control model by using the type of the sample IP address and the characteristic data of the sample IP address.

In order to solve the above problem, a second aspect of the present application provides a wind control evaluation method, including: receiving a service application request of a user, wherein the service application request comprises a target IP address adopted by the user; obtaining a type of the target IP address, wherein the type of the target IP address is determined by user environment information of the target IP address; and performing wind control evaluation on the service application request according to the type of the target IP address to obtain a wind control result of the service application request.

In order to solve the above problem, a third aspect of the present application provides a device for creating a wind control model, where the device includes an obtaining module, a determining module, and a constructing module; the acquisition module is used for acquiring user environment information of the sample IP address; the determining module is used for determining the type of the sample IP address according to the user environment information; the construction module is used for constructing and obtaining the wind control model by utilizing the type of the sample IP address and the characteristic data of the sample IP address.

In order to solve the above problem, a fourth aspect of the present application provides a wind control evaluation apparatus, which includes a receiving module, an obtaining module, and an evaluation module; the receiving module is used for receiving a service application request of a user, wherein the service application request comprises a target IP address adopted by the user; the obtaining module is configured to obtain a type of the target IP address, where the type of the target IP address is determined by user environment information of the target IP address; and the evaluation module is used for carrying out wind control evaluation on the service application request according to the type of the target IP address to obtain a wind control result of the service application request.

To solve the above problem, a fifth aspect of the present application provides a wind-controlled processing apparatus, including a memory and a processor; the processor is configured to execute the program instructions stored in the memory to perform the method for creating a wind control model as described above or to perform the method for evaluating wind control as described above.

In order to solve the above problem, a sixth aspect of the present application provides a storage device storing program instructions executable by a processor to perform the method for creating a wind control model as described above or to perform the method for evaluating wind control as described above.

In the scheme, the user environment information of the sample IP address is obtained, and the type of the sample IP address is determined according to the user environment information; the type of the determined sample IP address and the characteristic data of the sample IP address are used for constructing and obtaining the wind control model, and the sample IP address is divided according to the user environment information, so that the divided sample IP address can accurately reflect the user characteristics, and the wind control model which accurately reflects the reality can be constructed by utilizing the division of the sample IP address, so that the accuracy of wind control evaluation can be improved.

Drawings

FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a method for creating a wind control model according to the present application;

FIG. 2 is a schematic flow chart of step S120 shown in FIG. 1, which is included in another embodiment;

FIG. 3 is a schematic flow chart of step S227 shown in FIG. 2 included in a further embodiment;

FIG. 4 is a schematic flow chart illustrating a method for constructing a wind control model according to still another embodiment of the present disclosure;

FIG. 5 is a schematic flow chart diagram illustrating an embodiment of a wind control evaluation method according to the present application;

FIG. 6 is a schematic structural diagram of an embodiment of a creating apparatus for a wind control model according to the present application;

FIG. 7 is a schematic structural diagram of an embodiment of the wind control evaluation device of the present application;

FIG. 8 is a schematic structural diagram of an embodiment of a pneumatic control processing apparatus of the present application;

FIG. 9 is a schematic structural diagram of an embodiment of a memory device according to the present application.

Detailed Description

The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.

In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.

The terms "first" and "second" in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. While the term "and/or" is merely one type of association that describes an associated object, it means that there may be three types of relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. "poly" as referred to herein is greater than or equal to two.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

For the purpose of understanding the present application, a general description of some of the terms referred to herein will be provided:

IP address: i.e. Internet Protocol Address, is a digital identifier assigned to each device on the Internet, and may be specifically of IPv4 or IPv6 type.

Sample IP address: the IP addresses required to build the wind control model are called sample IP addresses.

Destination IP address: the IP address that needs to be windward evaluated is called the target IP address.

Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an embodiment of a method for creating a wind control model according to the present application. In this embodiment, the method is executed by a wind-controlled processing device, which may be any device with processing capability, such as a server, a personal computer, and the like. The method comprises the following steps:

s110: and acquiring the user environment information of the sample IP address.

In this embodiment, the user environment information may be any information that can be used to reflect the user characteristics, and may include at least one of the following: device connection information of the user, location information of the user, proximity WIFI information of the user, and the like.

Specifically, taking a sample IP address as a public IP address as an example, the sample IP address corresponds to multiple users, that is, all devices logged in by the multiple users use the sample IP address to access the network. The plurality of users may be users who used the sample IP address within a time period, or users who used the sample IP address at the same time. Correspondingly, the user environment information of the sample IP address includes environment information of the plurality of users, such as device connection information of the plurality of users, location information of the plurality of users, and the like.

S120: and determining the type of the sample IP address according to the user environment information.

Since the ue information may reflect characteristics of the relevant user, the sample IP address is classified using the ue information. In this embodiment, a plurality of IP address IP types are preset, and associated user environment information is preset for different IP address IP types. Thus, according to the associated information, the IP address IP type associated with the user environment information acquired in S110 is found as the type of the sample IP address.

Specifically, the preset IP address IP type may be classified according to different connection modes of the device, for example, the preset IP address IP type includes a base station IP type and a WIFI IP type. The user environment information corresponding to the base station IP type includes device connection information of the user, and in this embodiment, S120 may determine that the sample IP address is the base station IP type or the WIFI IP type according to the device connection information of the user. Specifically, for example, the environment information of the multiple users in S110 is used to determine the device connection mode of the different users of the sample IP address, and further determine whether the type of the sample IP address is the base station IP type or the WIFIIP type.

It can be understood that the IP address IP type is not limited to the base station IP type and the WIFI IP type, and may include other IP types according to actual situations, or further subdivide the IP types, which is not limited herein.

S130: and constructing to obtain a wind control model by using the type of the sample IP address and the characteristic data of the sample IP address.

In this embodiment, the types of the sample IP addresses and other feature data are respectively used as different dimensional information, and the different dimensional information is trained by using a preset algorithm to construct a wind control model. The preset algorithm may be an adaboost algorithm, a machine learning algorithm, or the like. The characteristic data of the sample IP address may be data to be considered when building the wind control model, and includes: sample service application cases for IP addresses. Further, the service application condition of the sample IP address may include at least one of the following: the credit application times of the sample IP address in the preset time, the number of application users of the sample IP address in the preset time, the login times of the user to the credit system of the sample IP address in the preset time, the overdue rate of the credit of the sample IP address in the preset time and the like. It should be noted that, in the technical solution provided in the present application, the expiration rate of the sample IP address in the preset time is: the proportion of the number of users who have not been paid out in excess of the appointed repayment time among the users corresponding to the sample IP address to the total number of users corresponding to the current sample IP address (in other embodiments, the overdue rate of the sample IP address in the preset time can be interpreted as the ratio of the overdue number of the sample IP address in the preset time to the credit application number of the sample IP address in the preset time), and the preset time is set and adjusted according to different embodiment requirements, specifically can be one day, one week, one month and the like, and is not limited herein.

Specifically, the S130 may include training the type of the sample IP address and the feature data of the sample IP address by using a preset algorithm, so as to determine reference feature data of different risk results corresponding to the type to which the sample IP address belongs, and determine the reference feature data as a model parameter of the wind control model. In an application scenario, the preset algorithm is a machine learning algorithm, the machine learning algorithm comprises a decision tree algorithm, different feature data of the sample IP address are classified by using the decision tree algorithm, and finally, the type of the sample IP address is decided to obtain reference feature data corresponding to different wind control results. For example, through the classification of the feature data of the sample IP addresses of a plurality of company IP types, the reference feature data which is determined to obtain the high-risk result corresponding to the company IP type comprises that the credit application frequency in 7 days is more than 200, the application user number in 7 days is more than 100, and the credit overdue rate in 1 month is more than 60%; the reference characteristic data of the company IP type corresponding to the risk result comprises that the credit application frequency within 7 days is 100 to 200, the number of application users within 7 days is 50 to 100, and the credit overdue rate within 1 month is more than 30 to 60 percent; the reference characteristic data of the company IP type corresponding to the low risk result comprises that the credit application frequency in 7 days is lower than 100, the application user number in 7 days is lower than 50, and the credit overdue rate in 1 month is lower than 30%. The reference characteristic data is a model parameter of the wind control model, and is used as a characteristic data judgment standard for a wind control result of the subsequent IP address of the type.

It is understood that the number of sample IP addresses for constructing the wind control model is one or more. For the embodiment with a plurality of sample IP addresses, the type of each sample IP address for constructing the wind control model is determined through steps S110 and S120, and then the wind control model is constructed and obtained by using the types of the plurality of sample IP addresses and the feature data corresponding to the plurality of sample IP addresses.

After the wind control model is constructed, the wind control model may be used to perform wind control evaluation on a service application (for example, a credit application on a credit system), which may be specifically described in the following embodiments related to the wind control evaluation method.

In this embodiment, after the types of the sample IP addresses are obtained in steps S110 and S120, the types of the obtained sample IP addresses are used, and a wind control model is constructed through a preset algorithm in combination with the feature data of the required sample IP addresses. The obtained wind control model can be used for carrying out credit wind control evaluation by combining other data related to the credit user when the credit system receives a credit application proposed by the user. In the process of building the wind control model, the behavior of the user in the real society is considered through the type of the sample IP address, so that an accurate wind control model can be built, the user can be accurately assessed in the wind control mode when the user applies for the internet credit, and the risk of the internet credit is reduced.

Referring to fig. 2, fig. 2 is a schematic flow chart of step S120 shown in fig. 1 in another embodiment. In this embodiment, the types of the sample IP addresses include a base station IP type and a WIFI IP type, and the WIFI IP type is further subdivided into a fixed WIFI IP type and a public WIFI IP type. The user environment information comprises device connection information of a plurality of users, the wind control processing device determines that the sample IP address is a base station IP type or a WIFI IP type according to the device connection information of the plurality of users, and if the sample IP address is the WIFI IP type, the sample IP address is further judged to be subdivided. Therefore, the step S120 may further include:

s221: and determining that the connection mode adopted by each user of the sample IP address is base station connection or WIFI connection according to the equipment connection information of each user.

The device connection information of the user refers to a network connection type and/or network parameter information of the user. The network connection type of the user may be: the user equipment is accessed to the network through the base station, or the user equipment is accessed to the network through WIFI; the network parameter information may be parameter information of an accessed base station or parameter information of an accessed WIFI, and the device connection information of the user may be any information that can be used to identify a network connection mode of the device, which is not limited herein.

By using the device connection information of each user, the connection mode adopted by each user can be determined to be base station connection or WIFI connection.

S222: and judging whether the number of the users connected by the base station is more than that of the users connected by the WIFI. If so, then S233 is performed, otherwise S234-S237 are performed.

In this embodiment, after the connection mode adopted by each user is determined, the number of users in various connection modes is counted, for example, the number of users whose sample IP addresses adopt base station connection and the number of users whose sample IP addresses adopt WIFI connection are counted. And then comparing the number of the users connected with the sample IP address by adopting the base station with the number of the users connected with the sample IP address by adopting the WIFI.

S223: and determining the sample IP address as the base station IP type.

And if the number of the users adopting the base station connection is more than that of the users adopting the WIFI connection, determining the sample IP address as the base station IP type.

S224: and acquiring WIFI data of the sample IP address.

And if the number of the users adopting the base station for connection is not more than that of the users adopting the WIFI connection, determining that the sample IP address is of the WIFI IP type. The WIFI IP type of the application is further subdivided into a fixed WIFI IP type and a public WIFI IP type. Therefore, if the number of users connected by the base station is not more than the number of users connected by the WIFI, S224-S227 are continuously executed to subdivide the WIFI IP types.

The WIFI data of the sample IP address is data of WIFI adopted by a user of the sample IP address, and may include historical WIFI data and current WIFI data, for example, the WIFI data adopted by the user of the sample IP address in a past period of time, or WIFI data reported by the user of the sample IP address received in real time when the current construction method is performed. Specifically, the WIFI data of the sample IP address includes at least one of: the number of users using WIFI, the number of fixed devices connected with WIFI, the number of mobile devices connected with WIFI, whether WIFI passwords and WIFI names exist or not and the average time of connecting WIFI in a preset time period. The fixed equipment connected with the WIFI is equipment with the WIFI connection frequency higher than the preset frequency (or the WIFI service time is higher than the preset time) within the set time, if the WIFI is connected within 5 days in a week, or if the WIFI is connected for more than 40 hours in a week, the fixed equipment can be judged as the fixed equipment, otherwise, the mobile equipment is judged as the mobile equipment.

S225: and judging whether the WIFI data of the sample IP address accord with preset fixed WIFI conditions or not. If not, S226 is executed, and if yes, S227 is executed.

Corresponding to the content included in the WIFI data in S224, the preset fixed WIFI condition may include at least one of the following: the number of users using WIFI does not exceed the preset number of users; the number of fixed devices is more than that of flowing devices; a WIFI password is provided; the WIFI name does not include a public place name; the average time for connecting WIFI is larger than a preset time threshold.

The number of users using WIFI is not more than the preset number of users: in this embodiment, the WIFI using the WIFI is a public WIFI when the number of users exceeding the preset threshold is, and the WIFI using the number of users less than or equal to the preset threshold is a fixed WIFI, where the preset threshold is set based on an empirical value, and the number of users using the WIFI in various application scenarios with the fixed WIFI may be considered comprehensively. Such as: a fixed number of WIFI users may be set according to empirical values to not exceed 200.

In the embodiment, the WIFI with the fixed equipment number larger than the mobile equipment number is fixed WIFI, and the WIFI with the fixed equipment number smaller than or equal to the mobile equipment number is public WIFI.

And a WIFI password is provided: in this embodiment, it is determined by default that WIFI with a WIFI password is fixed WIFI, and WIFI without a WIFI password is public WIFI.

WIFI names do not contain public place names: WIFI names do not contain any names about public places, including such things as: china net, a certain region, etc. The names of the public places can be preset and stored according to actual requests, after the WIFI names are obtained, the WIFI names and the public place names stored in advance are compared one by one, and if all comparison results are not matched, it is determined that the WIFI names do not contain the public place names.

The average WIFI connection time is greater than a preset time threshold value: the average time for connecting the WIFI can be the quotient of the total time for connecting the WIFI and the number of users used. And when the obtained average WIFI connection time is larger than a preset time threshold value, judging that the current sample IP address is a fixed WIFI IP type, otherwise, judging that the current sample IP address is a public WIFI IP type.

It can be understood that, when the preset fixed WIFI condition includes the plurality of conditions, that is, when the conditions at least have each condition of the preset number, it is determined that the preset fixed WIFI condition is met. For example, the preset number is 3, and when it is determined that the number of users using WIFI of the sample IP address does not exceed the preset number of users, the number of fixed devices connected to WIFI is greater than the number of mobile devices connected to WIFI, and the average time of connecting to WIFI is greater than a preset time threshold, it is determined that the sample IP address is a fixed WIFI IP type.

In addition, the sample IP address may include a plurality of users, and the WIFI data may be WIFI data used currently or in the past, so the WIFI data may include data of a plurality of WIFI, and at this time, the judgment on the above-mentioned conditional WIFI password and the WIFI name may be performed on each WIFI, so as to obtain a judgment result whether each WIFI has a password, and whether the WIFI name thereof contains a public place. And taking the judgment result of one of the WIFI judgment results with a large number in each condition as the final judgment result of the condition. For example, the WIFI data includes data of 10 pieces of WIFI, where 7 pieces of WIFI data have WIFI passwords, and 3 pieces of WIFI data do not have WIFI passwords, and it may be finally determined that the WIFI corresponding to the sample IP address has a WIFI password.

S226: and determining the sample IP address as a public WIFI IP type.

S227: and determining the sample IP address as a fixed WIFI IP type.

And when the WIFI data of the sample IP address are judged to accord with the preset fixed WIFI condition, determining that the sample IP address is the fixed WIFI IP type, otherwise, when the WIFI data of the sample IP address are judged to not accord with the preset fixed WIFI condition, determining that the sample IP address is the public WIFI IP type.

Referring to fig. 3, fig. 3 is a schematic flowchart illustrating a step S227 shown in fig. 2 according to another embodiment. In this embodiment, the types of the sample IP addresses include a base station IP type and a WIFI IP type, the WIFI IP type is further subdivided into a fixed WIFI IP type and a public WIFI IP type, and the fixed WIFI IP type is further subdivided into a plurality of address IP types, such as a residential area IP type, a company IP type, a school IP type, and the like. The user environment information includes device connection information of a plurality of users and location information of the plurality of users. Therefore, the step S227 may further include:

s3271: and determining the coverage range of the sample IP address according to the position information of the plurality of users.

In the present embodiment, the user environment information obtained in S110 further includes location information of multiple users, so that the coverage of the sample IP address can be determined according to the location information of the multiple users. For example, a range that may include the locations of the plurality of users or a range that includes the locations of some of the plurality of users is selected as the coverage of the sample IP address according to a preset algorithm. The location information of the user may be obtained directly by a positioning function in the user equipment, or may be obtained indirectly by other means, which will be described in detail in the following embodiment of fig. 4. The location information of the user may include historical location information and current location information, for example, location information of a user of a sample IP address in a past period of time, or location information directly or indirectly reported by the user of the sample IP address received in real time when the current construction method is performed.

In a particular application, the coverage area may include a coverage radius and a center position. Wherein, the calculation of the coverage radius and the center position can be specifically as follows: a plurality of users are corresponding to one sample IP address, and the coverage range and the central position of the sample IP address can be obtained through calculation according to the position information of the users. For example, a minimum circle that can cover all users or part of users can be made according to the location information of multiple users, the center of the circle is the center of the sample IP address, the area covered by the circle is the coverage of the sample IP address, and the coverage here is the coverage in an ideal state. In other embodiments, an error value of the distance may be preset according to an empirical value, and after the coverage range in the ideal state is obtained, the error value is further filtered to obtain a more accurate coverage range. Wherein the error of the distance is an empirical value.

S3272: and selecting a group of preset addresses with the same attribute in the coverage range of the sample IP address from the preset addresses of the plurality of users.

In this embodiment, each user in the sample IP address corresponds to at least one preset address, and the preset address may include at least one of the following: a user's residence address, a user's company address, a user's school address, etc. Each preset address has its attribute, for example, the attribute of the living address is a living attribute, the attribute of the company address is a company attribute, and the attribute of the school address is a school attribute. Correspondingly, the fixed WIFI IP type may further include: a residential IP type corresponding to a residential attribute, a corporate IP type corresponding to a corporate attribute, a school IP type corresponding to a school attribute. Of course, in other embodiments, the preset address of the user may also include preset addresses of other attributes. The fixed WIFI IP types may also include IP types of other attributes, which may all be set according to actual conditions. It can be understood that, in other embodiments, the preset address corresponding to the user may be identified and obtained by itself according to address information that is reserved when the user registers in a service system (e.g., a credit system), and may be sent to the user to confirm whether the address information is accurate.

In a specific application, the coverage area may include a coverage radius and a center position, and the S3272 may include: respectively calculating the distance between each preset address of each user of the sample IP address and the central position, and filtering the preset addresses of which the distances are greater than the coverage radius; and grouping the rest preset addresses according to attributes, and selecting a group of preset addresses with the largest number.

For example, after the coverage radius and the center position of the sample IP address are obtained, a distance calculation is performed between each preset address of each user in the IP address and the center position of the sample IP address to obtain a distance between each preset address of each user in the current sample IP address and the center position of the IP address. After the distance is obtained, comparing the distance between each preset address corresponding to each user in the obtained sample IP address and the central position of the sample IP address with the coverage radius of the IP address, leaving the preset address of the user with the obtained distance being less than or equal to the coverage radius, and filtering the preset address with the obtained distance being greater than the coverage radius. For example, the sample IP address corresponds to user a, user B, and user C. The coverage radius of the sample IP address is r and the center position is O. The distance between the living address of the user a and the center position O is a1, the distance between the work address and the center position O is a2, and the distance between the school address and the center position O is a 3. Since the user B does not have a school address, the distance between the living address of the user B and the center position O is B1, and the distance between the work address and the center position O is B2. The distance between the living address of the user C and the center position O is C1, the distance between the work address and the center position O is C2, and the distance between the school address and the center position O is C3. Wherein B2 and C3 are greater than r, so the work address of user B and the school address of user C are filtered out.

The filtered preset addresses of the remaining users are grouped according to attributes, for example, continuing the above example, the living addresses of the remaining users a, B and C are divided into a group of living attributes, the working addresses of the remaining users a and C are divided into a group of working attributes, and the school addresses of the remaining users a are individually used as a group of school attributes. And counting the number of the preset addresses of each group, comparing the number of the preset addresses of each group, and selecting a group of the preset addresses with the largest number. For example, the number of addresses of the living property group is counted as 3, the number of addresses of the working property group is counted as 2, and the number of addresses of the school property group is counted as 1, so that the preset address of the living property group is selected.

S3273: and determining the sample IP address as an address IP type corresponding to the attribute of the selected preset address.

As in the above example, the fixed WIFI addresses are further divided into a residential IP address, a working IP address, and a school IP address. After the preset address of the living attribute group is selected, the sample IP address can be determined as the living IP address.

It is understood that, in other embodiments, the type of the sample IP address may not be determined through the coverage of the sample IP address (S3271-S3273), for example, the distance between each preset address of the user and the location of the user may be directly determined according to the user location information of the sample IP address, the preset address with the shortest distance from the user location may be selected for each user, the preset addresses selected by each user are grouped according to attributes, and the sample IP address is determined as the address IP type corresponding to the attribute of the group of preset addresses with the largest number.

In this embodiment, whether the sample IP address is a base station IP address, a public WIFI IP type, or an address IP type under a fixed WIFI IP type can be accurately determined, so that the sample IP address can be accurately subdivided, and because the characteristics of the user groups corresponding to different types are also different, a more accurate basis can be provided for the subsequent S130 wind control model construction.

Referring to fig. 4, fig. 4 is a schematic flow chart of a method for constructing a wind control model according to another embodiment of the present application. In this embodiment, the method includes the steps of:

s410: device connection information of a plurality of users of the sample IP address, position information of the plurality of users and adjacent WIFI information of at least part of the users are obtained.

The description of S110 may be specifically adopted in this step. Wherein, this at least part of user can be the user who adopts the WIFI connected mode.

S421: and determining the sample IP address as a base station IP type or a WIFI IP type according to the equipment connection information of the plurality of users.

S422: and when the sample IP address is of a WIFI IP type, acquiring WIFI data of the sample IP address.

S423: and judging whether the WIFI data of the sample IP address accord with preset fixed WIFI conditions or not. If not, go to step S424, and if so, go to steps S425-S429.

S424: and determining the sample IP address as a public WIFI IP type.

S425: and when the position information of part of the WIFI users is not acquired, acquiring the positions of the parts of the WIFI users adjacent to the WIFI according to the adjacent WIFI information of the parts of the WIFI users.

The WIFI users are connected through WIFI, and can be determined through the device connection information of the WIFI users. In this embodiment, since there may be a case where some user devices connected by using WIFI cannot be directly located and uploaded via the location information, S410 may only obtain location information of some WIFI users, and at this time, the location of the WIFI user may be determined by the neighboring WIFI information of the WIFI user. Wherein, this adjacent WIFI information can include: the historical uploaded position information of the adjacent WIFI, or the registration information of the user of the adjacent WIFI, or other related information which can indirectly obtain the position information of the adjacent WIFI. The adjacent WIFI is a WIFI signal searched by the user equipment, but the number of WIFI which is not connected can be one or more.

S426: and obtaining the position information of the part of users according to the positions of the part of users adjacent to the WIFI.

After the positions of the partial WIFI users adjacent to the WIFI are obtained, the position information of the partial WIFI users can be determined according to the positions of the partial WIFI users adjacent to the WIFI. And calculating the position information of part of WIFI users according to the obtained position adjacent to the WIFI. Such as: if 5 pieces of position information (each piece of WIFI position information at least includes a center position and a coverage radius) of a WIFI user adjacent to WIFI are obtained, the position information of the current user can be obtained by using the collective knowledge and the signal strength therebetween based on the obtained center positions and coverage radii of the 5 pieces of WIFI.

The position information of each user of the sample IP address is obtained through the position information of a part of WIFI users obtained in S410 and the position information of the rest of WIFI users obtained in S425-S426.

S427: and determining the coverage range of the sample IP address according to the position information of the plurality of users.

S428: and selecting a group of preset addresses with the same attribute in the coverage range of the sample IP address from the preset addresses of the plurality of users.

S429: and determining the sample IP address as an address IP type corresponding to the attribute of the selected preset address.

S430: and constructing to obtain a wind control model by using the type of the sample IP address and the characteristic data of the sample IP address.

The above-mentioned steps S421 to S424 and S437 to S430 can refer to the relevant steps of the above-mentioned embodiments, and are not described herein again.

Referring to fig. 5, fig. 5 is a schematic flow chart of an embodiment of the wind control evaluation method of the present application. The wind control evaluation method provided by the application can be used for carrying out risk evaluation on the service application proposed by the user when the user proposes the service application (such as a credit service application). In the embodiment, the method may be executed by a wind-controlled processing device, which may be any device with processing capability, such as a server, a personal computer, and the like. The method comprises the following steps:

s510: and receiving a service application request of a user.

For example, the service application request of the user is specifically a credit application issued after the user equipment accesses the network by using the target IP address. The service application request includes a destination IP address employed by the user. It should be noted that the target IP address may be a public IP address, so that a plurality of users may access the network sequentially or simultaneously by using the same target IP address and apply for credit.

It is understood that the service application request may also include other information, such as credit service type, loan amount, and applicant information, without any limitation.

S520: the type of the destination IP address is obtained.

The type of the target IP address is determined by the user environment information of the target IP address, and the determination of the type of the target IP address is implemented by specifically referring to the step related to S120 in the foregoing embodiment. Specifically, the type determining process of the target IP address may be determined in real time according to the user environment information after receiving the service application request of the user, or may be determined and stored in advance according to the user environment information (for example, the IP address may be classified every day according to the user environment information of different IP addresses on the same day, so that when the service request is received every day, the IP address type may be obtained according to the classification condition of the IP address yesterday).

S530: and performing wind control evaluation on the service application request according to the type of the target IP address to obtain a wind control result of the service application request.

For example, the service application request may be analyzed and processed according to the type of the target IP address by using a preset evaluation algorithm, so as to obtain a wind control result.

Further, the wind control evaluation can be realized by utilizing a wind control model. The wind control model is constructed by utilizing types of a plurality of sample IP addresses and characteristic data of the plurality of sample IP addresses, and the types of the plurality of sample IP addresses are determined according to user environment information of the plurality of sample IP addresses respectively. Specifically, the wind control model can be obtained by constructing according to the embodiment of the construction method of the wind control model. The method further comprises obtaining feature data of the target IP address, which may specifically include the relevant description of the feature data regarding the sample IP address in the above embodiments. This S530 may specifically include: and analyzing the type and the characteristic data of the target IP address by using a wind control model to obtain a wind control result of the service application request.

For example, after the wind control model is constructed and obtained by the above method embodiment, the type and the characteristic data of the target IP address are input into the wind control model, and the input data are analyzed by using the wind control model, so as to obtain the risk result of the service application request. Specifically, the risk model determines the model parameters thereof through the above method, that is, the reference characteristic data of different risk results corresponding to different IP address types. Therefore, the wind control model can be used for judging reference characteristic data matched with the type and the characteristic data of the target IP address, and a risk result corresponding to the reference characteristic data is used as a wind control result of the service application request. For example, if the type of the target IP address is a company IP address type, and if the feature data of the target IP address is 250 credit application times within 7 days and 65% credit expiration rate for 1 month, the feature data falls into a reference feature data range of a high-risk result corresponding to the company IP type, it may be determined that the pneumatic control result of the service application request is high-risk; if the characteristic data of the target IP address is that the credit application frequency within 7 days is 10 and the credit overdue rate of 1 month is 15%, the characteristic data falls into the reference characteristic data range of the company IP type corresponding to the low-risk result, so that the wind control result of the service application request can be determined to be low risk.

Referring to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of a creating apparatus for a wind control model according to the present application. In the present embodiment, the apparatus 60 includes an obtaining module 61, a determining module 62, and a constructing module 63.

The obtaining module 61 is configured to obtain user environment information of the sample IP address. The determining module 62 is configured to determine the type of the sample IP address according to the user environment information. The building module 63 is configured to build the wind control model by using the type of the sample IP address and the feature data of the sample IP address.

In some embodiments, the sample IP address corresponds to a plurality of users, and the user environment information includes: device connection information of the plurality of users.

The determining module 62 is specifically configured to determine, according to the device connection information of the multiple users, that the sample IP address is a base station IP type or a WIFI IP type.

Further, the determining module 62 may include a connection determining unit and a first determining unit, where the connection determining unit is configured to determine, according to the device connection information of each user, that the connection mode adopted by each user of the sample IP address is base station connection or WIFI connection; the type determination unit is to: and if the number of users adopting base station connection for the sample IP address is more than that of users adopting WIFI connection for the sample IP address, determining that the sample IP address is of the base station IP type, otherwise, determining that the sample IP address is of the WIFI IP type.

Still further, the WIFI IP types may include a fixed WIFI IP type and a public WIFI IP type; the type determination unit may be specifically configured to, when determining that the sample IP address is a WIFI IP type: acquiring WIFI data of the sample IP address; judging whether the WIFI data of the sample IP address meet preset fixed WIFI conditions or not; and if so, determining that the sample IP address is a fixed WIFI IP type, otherwise, determining that the sample IP address is a public WIFI IP type.

Wherein the WIFI data of the sample IP address may include at least one of: the number of users using the WIFI, the number of fixed devices connected with the WIFI, the number of mobile devices connected with the WIFI, whether a WIFI password exists, a WIFI name exists, and the average time of connecting the WIFI are preset in a preset time period.

The preset fixed WIFI condition comprises at least one of the following conditions: the number of the users using the WIFI is not more than the preset number of the users; the number of the fixed devices is more than the number of the flowing devices; the WIFI password is possessed; the WIFI name does not include a public place name; and the average time for connecting the WIFI is greater than a preset time threshold value.

Still further, the fixed WIFI IP types may include a plurality of address IP types; the user environment information further includes location information of the plurality of users; each user corresponds to at least one preset address; when determining that the sample IP address is the fixed WIFI IP type, the type determining unit may further include: determining the coverage range of the sample IP address according to the position information of the plurality of users; selecting a group of preset addresses with the same attribute in the coverage range of the sample IP address from the preset addresses of the plurality of users; and determining the sample IP address as an address IP type corresponding to the attribute of the selected preset address.

Wherein the preset address may include at least one of: a residential address, a company address, and a school address; the address IP type may include at least one of: residential IP type, corporate IP type, and school IP type.

Wherein the coverage area may include a coverage radius and a center position; the type determining unit selects a group of preset addresses with the same attribute in the coverage range of the sample IP address from the preset addresses of the multiple users, and is specifically configured to: respectively calculating the distance between each preset address of each user of the sample IP address and the central position, and filtering the preset addresses of which the distances are greater than the coverage radius; and grouping the rest preset addresses according to attributes, and selecting a group of preset addresses with the largest number.

In addition, the environmental information of the user may further include neighboring WIFI information of the user; the device 60 further includes an obtaining module, configured to obtain, according to the adjacent WIFI information of the part of WIFI users, positions of adjacent WIFI of the part of WIFI users when position information of the part of WIFI users is not obtained, where the WIFI users are users connected through WIFI; and obtaining the position information of the part of WIFI users according to the positions of the part of WIFI users adjacent to the WIFI.

In some embodiments, the characteristic data of the sample IP address includes a service application condition of the sample IP address; the service application condition comprises at least one of the following conditions: the credit application times of the sample IP address in the preset time, the number of application users of the sample IP address in the preset time, the login times of the user to the credit system in the preset time of the sample IP address, and the credit overdue rate of the sample IP address in the preset time.

In certain embodiments, the sample IP address is a public network IP address.

The modules of the wind control model building device 60 are described in detail with reference to the relevant steps of the building method according to the above embodiment.

Referring to fig. 7, fig. 7 is a schematic structural diagram of an embodiment of a wind control evaluation device according to the present application. In the present embodiment, the apparatus 70 comprises a receiving module 71, an obtaining module 72 and an evaluating module 73.

The receiving module 71 is configured to receive a service application request of a user, where the service application request includes a target IP address adopted by the user. The obtaining module 72 is configured to obtain a type of the target IP address, where the type of the target IP address is determined by the ue information of the target IP address. The evaluation module 73 is configured to perform wind control evaluation on the service application request according to the type of the target IP address, so as to obtain a wind control result of the service application request.

In some embodiments, the obtaining module 72 is further configured to obtain characteristic data of the target IP address. The evaluation module 73 is specifically configured to analyze the type and the feature data of the target IP address by using a wind control model, so as to obtain a wind control result of the service application request. The wind control model is constructed by utilizing types of a plurality of sample IP addresses and characteristic data of the plurality of sample IP addresses, and the types of the plurality of sample IP addresses are determined according to user environment information of the plurality of sample IP addresses respectively.

The modules of the wind control evaluation device 70 are described in detail with reference to the related steps of the method according to the above embodiment.

Please refer to fig. 8, fig. 8 is a schematic structural diagram of an embodiment of a wind-controlled processing device according to the present application. In this embodiment, the apparatus 80 includes a memory 81 and a processor 82.

Wherein, each component of the wind control processing device 80 can be coupled together by a bus (not identified in the figure), or the processor 82 of the wind control processing device 80 is respectively connected with other components one by one. Specifically, the wind control processing device 80 may be any device with processing capability, such as a server, a computer, and the like.

The memory 81 is used for storing program instructions executed by the processor 82 and data of the processor 82 in the processing process, wherein the memory 81 comprises a nonvolatile storage part for storing the program instructions. In one embodiment, the memory 81 further stores a database for storing the related record information of each sample IP address. In another embodiment, the memory 81 may also store a resulting wind control model based on the sample IP address. It is understood that, in other embodiments, the storage 81 may not store the database, and the wind control processing device 80 may obtain the record information related to the sample IP address by communicating with an external database, so as to reduce the occupation of the memory by the wind control processing device 80, and at the same time, improve the calculation and analysis speed.

The processor 82 may also be referred to as a CPU (Central Processing Unit). The processor 82 may be an integrated circuit chip having signal processing capabilities. The processor 82 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

In the present embodiment, the processor 82 is configured to execute the creating method or the wind control evaluating method of the wind control model as set forth in any one of the above embodiments by calling the program instructions stored in the memory.

Referring to fig. 9, fig. 9 is a schematic structural diagram of a memory device 90 according to an embodiment of the present application. In this embodiment, the memory device 90 stores processor-executable program instructions 91 for performing the method of any of the above embodiments.

The storage device 90 may be a medium that can store program instructions, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, or may be a server that stores the program instructions, and the server may send the stored program instructions to other devices for operation, or may self-operate the stored program instructions.

The above embodiments are merely examples and are not intended to limit the scope of the present disclosure, and all modifications, equivalents, and flow charts using the contents of the specification and drawings of the present disclosure or those directly or indirectly applied to other related technical fields are intended to be included in the scope of the present disclosure.

Claims

1. A method for creating a wind control model, the method comprising:

acquiring user environment information of a sample IP address;

determining the type of the sample IP address according to the user environment information;

and constructing to obtain the wind control model by using the type of the sample IP address and the characteristic data of the sample IP address.

2. The method of claim 1, wherein the sample IP address corresponds to a plurality of users, and wherein the user context information comprises: device connection information of the plurality of users;

the determining the type of the sample IP address according to the user environment information includes:

and determining the sample IP address as a base station IP type or a WIFI IP type according to the equipment connection information of the users.

3. The method of claim 2,

the determining that the sample IP address is of a base station type or a WIFI type according to the device connection information of the plurality of users includes:

determining that the connection mode adopted by each user of the sample IP address is base station connection or WIFI connection according to the equipment connection information of each user;

and if the number of users adopting base station connection for the sample IP address is more than that of users adopting WIFI connection for the sample IP address, determining that the sample IP address is of the base station IP type, otherwise, determining that the sample IP address is of the WIFI IP type.

4. The method of claim 2 or 3, wherein the WIFI IP types include a fixed WIFI IP type and a public WIFI IP type;

the determining that the sample IP address is of a WIFI IP type further comprises:

acquiring WIFI data of the sample IP address;

judging whether the WIFI data of the sample IP address meet preset fixed WIFI conditions or not;

and if so, determining that the sample IP address is a fixed WIFI IP type, otherwise, determining that the sample IP address is a public WIFI IP type.

5. The method of claim 4, wherein the WIFI data for the sample IP address comprises at least one of:

the number of users using the WIFI, the number of fixed devices connected with the WIFI, the number of mobile devices connected with the WIFI, whether a WIFI password exists or not, a WIFI name and the average time for connecting the WIFI are determined in a preset time period;

the preset fixed WIFI condition comprises at least one of the following conditions:

the number of the users using the WIFI is not more than the preset number of the users;

the number of the fixed devices is more than the number of the flowing devices;

the WIFI password is possessed;

the WIFI name does not include a public place name;

and the average time for connecting the WIFI is greater than a preset time threshold value.

6. The method of claim 4, wherein the fixed WIFI IP type comprises a plurality of address IP types; the user environment information further includes location information of the plurality of users; each user corresponds to at least one preset address;

the determining that the sample IP address is a fixed WIFI IP type further comprises:

determining the coverage range of the sample IP address according to the position information of the plurality of users;

selecting a group of preset addresses with the same attribute in the coverage range of the sample IP address from the preset addresses of the plurality of users;

and determining the sample IP address as an address IP type corresponding to the attribute of the selected preset address.

7. The method of claim 6, wherein the coverage area comprises a coverage radius and a center position;

selecting a group of preset addresses with the same attribute in the coverage range of the sample IP address from the preset addresses of the plurality of users, wherein the group of preset addresses comprises:

respectively calculating the distance between each preset address of each user of the sample IP address and the central position, and filtering the preset addresses of which the distances are greater than the coverage radius;

and grouping the rest preset addresses according to attributes, and selecting a group of preset addresses with the largest number.

8. The method of claim 6, wherein the environmental information of the user further comprises neighboring WIFI information of the user; the method further comprises the following steps:

when the position information of a part of WIFI users is not acquired, acquiring the positions of the WIFI users adjacent to the part of WIFI users according to the adjacent WIFI information of the part of WIFI users, wherein the WIFI users are users adopting WIFI connection;

and obtaining the position information of the part of WIFI users according to the positions of the part of WIFI users adjacent to the WIFI.

9. The method of claim 6, wherein the preset address comprises at least one of: a residential address, a company address, and a school address; the address IP type includes at least one of: residential IP type, corporate IP type, and school IP type.

10. The method of claim 1, wherein the characteristic data of the sample IP address comprises a service application status of the sample IP address;

the service application condition comprises at least one of the following conditions: the credit application times of the sample IP address in the preset time, the number of application users of the sample IP address in the preset time, the login times of the user to the credit system of the sample IP address in the preset time, and the credit overdue rate of the sample IP address in the preset time; the sample IP address is a public network IP address; and/or

The constructing and obtaining the wind control model by using the type of the sample IP address and the characteristic data of the sample IP address comprises the following steps:

training the type of the sample IP address and the characteristic data of the sample IP address by adopting a preset algorithm to decide reference characteristic data of different risk results corresponding to the type of the sample IP address, and determining the reference characteristic data as the model parameters of the wind control model.

11. A method of wind control assessment, the method comprising:

receiving a service application request of a user, wherein the service application request comprises a target IP address adopted by the user;

obtaining a type of the target IP address, wherein the type of the target IP address is determined by user environment information of the target IP address;

and performing wind control evaluation on the service application request according to the type of the target IP address to obtain a wind control result of the service application request.

12. The method of claim 11, further comprising:

obtaining feature data of the target IP address;

the wind control evaluation of the service application request according to the type of the target IP address to obtain a wind control result of the service application request comprises the following steps:

analyzing the type and the characteristic data of the target IP address by using a wind control model to obtain a wind control result of the service application request;

wherein the wind control model is a wind control model constructed by the method of any one of claims 1 to 10.

13. The method of claim 12, wherein analyzing the type and feature data of the target IP address by using a wind control model to obtain a wind control result of the service application request comprises:

and judging reference characteristic data matched with the type and the characteristic data of the target IP address by using the wind control model, and taking a risk result corresponding to the reference characteristic data as a wind control result of the service application request, wherein different risk results of different IP address types correspond to different reference characteristic data.

14. The device for creating the wind control model is characterized by comprising an acquisition module, a determination module and a construction module; wherein the content of the first and second substances,

the acquisition module is used for acquiring user environment information of the sample IP address;

the determining module is used for determining the type of the sample IP address according to the user environment information;

the construction module is used for constructing and obtaining the wind control model by utilizing the type of the sample IP address and the characteristic data of the sample IP address.

15. The wind control evaluation device is characterized by comprising a receiving module, an obtaining module and an evaluation module;

the receiving module is used for receiving a service application request of a user, wherein the service application request comprises a target IP address adopted by the user;

the obtaining module is configured to obtain a type of the target IP address, where the type of the target IP address is determined by user environment information of the target IP address;

and the evaluation module is used for carrying out wind control evaluation on the service application request according to the type of the target IP address to obtain a wind control result of the service application request.

16. A wind-controlled processing apparatus, the apparatus comprising a memory and a processor; the processor is configured to execute the program instructions stored by the memory to perform the method of any of claims 1 to 10, or to perform the method of any of claims 11 to 13.

17. A storage device having stored thereon program instructions executable by a processor to perform a method according to any one of claims 1 to 10 or to perform a method according to any one of claims 11 to 13.