Device fingerprint feature screening method, device, electronic device and storage medium

Abstract

The embodiment of the present invention provides a device fingerprint feature screening method, apparatus, electronic device and storage medium, the method comprising: obtaining at least one device feature of a target device, forming a device feature pool from at least one device feature of the target device; determining the feature index of the device feature under different evaluation dimensions for any device feature in the device feature pool; determining the current scene, and determining the screening tendency of the device feature according to the current scene and the feature index; screening the target device feature from the device feature pool as the device fingerprint feature according to the screening tendency corresponding to each device feature in the device feature pool. By determining the screening tendency of each device feature in the device feature pool, the device fingerprint feature is screened based on the screening tendency to obtain the device fingerprint feature, and the device fingerprint feature is subsequently input into the matching model for device fingerprint matching, which can effectively improve the device fingerprint matching success rate of the matching model.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of information processing technologies, and in particular, to a method, apparatus, electronic device, and storage medium for screening device fingerprint features. Background Art

[0002] With the development and popularization of mobile Internet application technologies, device fingerprints, as identifiers that uniquely identify a device, are widely used in various industries related to Internet information security. Among them, various device features used to generate device fingerprints are important factors affecting the matching effect of device fingerprints, and the quality of device features determines the upper limit of device fingerprint technology.

[0003] In related technologies, most current device fingerprint technologies focus on the establishment of matching models and rarely conduct in-depth research on the selection of device features, while the selection of device features is directly related to the performance of the matching model. Currently, device features collected are usually input into a matching model for device fingerprint matching. However, this will ignore the possible conflict relationships between device features, resulting in a decrease in the success rate of device fingerprint matching of the matching model. Summary of the Invention

[0004] To solve the above technical problem that currently device features collected are usually input into a matching model for device fingerprint matching, but this will ignore the possible conflict relationships between device features, resulting in a decrease in the success rate of device fingerprint matching of the matching model, embodiments of the present invention provide a method, apparatus, electronic device, and storage medium for screening device fingerprint features.

[0005] In the first aspect of the embodiments of the present invention, first, a method for screening device fingerprint features is provided, and the method includes:

[0006] Obtain at least one device feature of a target device, and form a device feature pool from the at least one device feature of the target device;

[0007] For any one of the device features in the device feature pool, determine the feature indicators of the device feature under different evaluation dimensions;

[0008] Determine the current scenario, and determine the screening preference degree of the device feature according to the current scenario and the feature indicators;

[0009] According to the screening preference degrees corresponding to the respective device features in the device feature pool, screen target device features from the device feature pool as device fingerprint features.

[0010] In an optional implementation manner, the determining the feature indicators of the device feature under different evaluation dimensions includes:

[0011] Determine a target information entropy of the device feature under a first evaluation dimension;

[0012] Determine the maximum information coefficient of the device feature under the second evaluation dimension;

[0013] The number of categories of the device features under the third evaluation dimension is determined.

[0014] In an optional implementation, determining the target information entropy of the device feature under the first evaluation dimension includes:

[0015] Determine a first information entropy of the device feature between the same device, and determine a second information entropy of the device feature between different devices;

[0016] A difference between the second information entropy and the first information entropy is obtained, and the difference is determined to be a target information entropy of the device feature under the first evaluation dimension.

[0017] In an optional implementation, determining the number of categories of the device feature under the third evaluation dimension includes:

[0018] The total number of characteristic values ​​of the device characteristic is found, and the total number of characteristic values ​​is determined to be the number of categories of the device characteristic under the third evaluation dimension.

[0019] In an optional implementation, determining the screening tendency of the device feature according to the current scenario and the feature index includes:

[0020] Find the target information entropy, the maximum information coefficient, and the weights corresponding to the number of categories in the current scenario;

[0021] The screening tendency of the device feature is determined according to the target information entropy, the maximum information coefficient, the number of categories, and the corresponding weights.

[0022] In an optional implementation, determining the screening tendency of the device feature according to the target information entropy, the maximum information coefficient, the number of categories, and the weights corresponding to each of them includes:

[0023] The target information entropy, the maximum information coefficient, the weighted sum of the number of categories and the weights corresponding to each other are obtained to obtain the screening tendency of the device feature.

[0024] In an optional implementation, the screening of target device features from the device feature pool as device fingerprint features according to the screening tendency corresponding to each of the device features in the device feature pool includes:

[0025] sorting the device features in the device feature pool according to the screening tendency corresponding to each of the device features in the device feature pool;

[0026] From the ranking results of the device features in the device feature pool, the target device features ranked in the top N% are selected as device fingerprint features.

[0027] In a second aspect of an embodiment of the present invention, a device fingerprint feature screening apparatus is provided, the apparatus comprising:

[0028] A feature acquisition module, used for acquiring at least one device feature of a target device, and forming a device feature pool by the at least one device feature of the target device;

[0029] An indicator determination module, used for determining, for any device feature in the device feature pool, a feature indicator of the device feature under different evaluation dimensions;

[0030] A tendency determination module, used to determine a current scene, and determine a screening tendency of the device feature according to the current scene and the feature index;

[0031] The feature screening module is used to screen target device features from the device feature pool as device fingerprint features according to the screening tendency corresponding to each device feature in the device feature pool.

[0032] In a third aspect of an embodiment of the present invention, there is further provided an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0033] Memory, used to store computer programs;

[0034] The processor is used to implement the device fingerprint feature screening method described in the first aspect when executing the program stored in the memory.

[0035] In a fourth aspect of an embodiment of the present invention, a storage medium is further provided, wherein instructions are stored in the storage medium, and when the instructions are executed on a computer, the computer executes the device fingerprint feature screening method described in the first aspect above.

[0036] In a fifth aspect of the embodiments of the present invention, a computer program product comprising instructions is also provided. When the computer program product is run on a computer, the computer executes the device fingerprint feature screening method described in the first aspect.

[0037] The technical solution provided by the embodiment of the present invention obtains at least one device feature of the target device, forms a device feature pool with at least one device feature of the target device, determines the feature index of the device feature under different evaluation dimensions for any device feature in the device feature pool, determines the current scene, determines the screening tendency of the device feature according to the current scene and the feature index, and screens the target device feature from the device feature pool as the device fingerprint feature according to the screening tendency corresponding to each device feature in the device feature pool. By obtaining at least one device feature of the target device to form a device feature pool, determines the feature index of the device feature under different evaluation dimensions for any device feature in the device feature pool, determines the current scene, determines the screening tendency of the device feature according to the current scene and the feature index, and thus screens each device feature in the device feature pool based on the screening tendency to obtain the device fingerprint feature, and subsequently inputs the device fingerprint feature into the matching model for device fingerprint matching, which can effectively improve the device fingerprint matching success rate of the matching model. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0040] Figure 1 It is a schematic diagram of an implementation process of a device fingerprint feature screening method shown in an embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of an implementation flow of a method for determining a characteristic index of a device characteristic under different evaluation dimensions shown in an embodiment of the present invention;

[0042] Figure 3 It is a schematic diagram of an implementation flow of a method for determining a screening tendency corresponding to each device feature in a device feature pool shown in an embodiment of the present invention;

[0043] Figure 4 It is a structural schematic diagram of a device fingerprint feature screening apparatus shown in an embodiment of the present invention;

[0044] Figure 5 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 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 are within the scope of protection of the present invention.

[0046] 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.

[0047] like Figure 1 FIG. 1 is a schematic diagram of an implementation flow of a device fingerprint feature screening method provided by an embodiment of the present invention. The method is applied to a processor and may specifically include the following steps:

[0048] S101, obtaining at least one device feature of a target device, and forming a device feature pool by using the at least one device feature of the target device.

[0049] In the embodiment of the present invention, for a target device, at least one device feature of the target device is obtained, thereby forming a device feature pool based on the at least one device feature of the target device. The device feature here can be various device features of the target device, and specifically, at least one device feature of the target device can be obtained by event collection, which is not limited in the embodiment of the present invention.

[0050] For example, in an embodiment of the present invention, for the target device A, the device characteristics of the target device A are obtained through event collection, wherein the name and corresponding meaning of each device characteristic are shown in Table 1 below, thereby a device characteristic pool can be formed based on the device characteristics of the target device A.

[0051] Device feature name Meaning of device characteristics ip ip address TCPTS TCP timestamp session_id Session ID tcp_source_port TCP sender port user_agent User Agent ip_geo Geographic Information device_model Device Model resolution Screen resolution tcp_initial_window TCP initial window size cr Operator Information appversion app version number accpet_encoding Accept-Encoding accpet_language Accept Language ns Network Services

[0052] Table 1

[0053] S102: For any device feature in the device feature pool, determine a feature index of the device feature under different evaluation dimensions.

[0054] S103, determining a current scene, and determining a screening tendency of the device feature according to the current scene and the feature index.

[0055] In the embodiment of the present invention, for any device feature in the device feature pool, the feature index of the device feature under different evaluation dimensions is determined, the current scene is determined, and the screening tendency of the device feature is determined according to the current scene and the feature index. In this way, the corresponding screening tendency can be obtained for each device feature in the device feature pool.

[0056] It should be noted that the scenarios involved in the present invention may specifically be any scenario such as H5, APP, WeChat applet, etc., or may be cross-scenario, for example, spanning H5, APP, etc. The embodiments of the present invention are not limited to this.

[0057] For example, in an embodiment of the present invention, for the device features of "ip" in the device feature pool, the feature index of the device features of "ip" in different dimensions is determined, and the current scene, such as the H5 scene, is determined. According to the current scene and the feature index, the screening tendency of the device features of "ip" is determined. For the remaining device features in the device feature pool, the processing is similar to the above, and the embodiment of the present invention will not be repeated here. In this way, for each device feature in the device feature pool, the corresponding screening tendency can be obtained.

[0058] Among them, the final evaluation criteria for the quality of device fingerprints are generally uniqueness (high accuracy, device fingerprints generated by different devices are guaranteed not to be repeated, ensuring the uniqueness of device fingerprint generation) and stability (device fingerprints will not change when the device system is upgraded or a small number of parameters are changed). Based on uniqueness and stability, the embodiment of the present invention is based on three commonly used evaluation methods in high-classification matching problems to determine the characteristic indicators of device features under different evaluation dimensions. Specifically, Figure 2 As shown, the following steps may be specifically included:

[0059] S201, determining the target information entropy of the device feature under the first evaluation dimension.

[0060] In the embodiment of the present invention, the average uncertainty of the information should be the single symbol uncertainty - logP i The statistical average value of can be called information entropy, that is, Another way to understand it is that information entropy can be used as a measure of the complexity of a system. If a system is more complex and has more different situations, its information entropy is relatively large. If a system is simpler and has fewer situations (in the extreme case, there is only one situation, then the corresponding probability is 1, and the corresponding information entropy is 0), then the information entropy is small.

[0061] As for the final judging criteria of the quality of device fingerprints, namely stability and consistency, for a certain device feature collected by an embodiment of the present invention on the same device, in the most ideal case, the embodiment of the present invention hopes that this device feature remains unchanged in different time periods, different locations, and different network environments, that is, the information entropy is zero. Correspondingly, when looking at this device feature between different devices, the embodiment of the present invention hopes that this device feature can have obvious differences, that is, the larger the information entropy, the better.

[0062] Based on this idea, in an embodiment of the present invention, any device feature in the device feature pool is evaluated from the information entropy dimension, that is, for any device feature in the device feature pool, the first information entropy of the device feature between the same device (i.e., the target device) is determined, the second information entropy of the device feature between different devices (i.e., the target device and the remaining devices) is determined, the difference between the second information entropy and the first information entropy is obtained, and the difference is determined as the target information entropy of the device feature under the first evaluation dimension (i.e., the information entropy dimension). In this way, for each device feature in the device feature pool, the corresponding target information entropy can be obtained.

[0063] For example, for the device feature of “ip” in the device feature pool, determine the first information entropy (H(U)) of the device feature of “ip” between the target device A and the target device A. 同一设备间 ), determine the second information entropy (H(U)) of the device feature of "ip" between the target device A and device B 不同设备间 ), obtain the difference (informationEntropy) between the second information entropy and the first information entropy, as shown below, and determine the target information entropy of the device feature with the difference "ip" under the first evaluation dimension. For the remaining device features in the device feature pool, the processing is similar to the above, and the embodiments of the present invention will not be repeated here. In this way, for each device feature in the device feature pool, the corresponding target information entropy under the first evaluation dimension can be obtained, as shown in Table 2 below.

[0064] information Entropy=H(U) 不同设备间 -H(U) 同一设备间 .

[0065]

[0066]

[0067] Table 2

[0068] S202: Determine the maximum information coefficient of the device feature in the second evaluation dimension.

[0069] In the embodiment of the present invention, the maximum information coefficient belongs to the maximum information-based nonparametric exploration (MINE), which is used to measure the degree of association between two variables X and Y, the strength of linear or nonlinearity, and is often used for feature selection in machine learning.

[0070] The maximum information coefficient can help the embodiment of the present invention obtain the correlation between device features in the device feature pool. The embodiment of the present invention hopes that the device feature pool can fully reflect various types of information of the target device, including network information, hardware information, software information, etc. Therefore, the embodiment of the present invention hopes that the correlation between a certain device feature and other device features needs to be as low as possible.

[0071] Based on this idea, in the embodiment of the present invention, any device feature in the device feature pool is evaluated from the dimension of maximum information coefficient, that is, for any device feature in the device feature pool, the maximum information coefficient of the device feature under the second evaluation dimension is determined. Specifically, for any device feature in the device feature pool, the maximum information coefficient of the device feature under the second evaluation dimension can be calculated by the following formula.

[0072]

[0073] S203: Determine the number of categories of the device feature under the third evaluation dimension.

[0074] In the embodiment of the present invention, any device feature in the device feature pool is evaluated from the dimension of number of uniques, that is, for any device feature in the device feature pool, the number of uniques of the device feature under the third evaluation dimension is determined. For any device feature in the device feature pool, the total number of feature values ​​of the device feature is found, and the total number of uniques is determined as the number of uniques of the device feature under the third evaluation dimension.

[0075] For example, for the device feature of "ip" in the device feature pool, the total number of IP addresses of the device feature of "ip" is searched, that is, the number of values ​​of the device feature of "ip" here, for example, 250635, thereby determining the number of values ​​of the device feature of "ip" as the number of categories of the device feature of "ip" under the third evaluation dimension. For the remaining device features in the device feature pool, the processing is similar to the above, and the embodiments of the present invention will not be repeated here one by one. In this way, for each device feature in the device feature pool, the corresponding number of categories under the third evaluation dimension can be obtained, as shown in Table 3 below.

[0076]

[0077]

[0078] Table 3

[0079] After the above steps, for any device feature in the device feature pool, the corresponding target information entropy under the first evaluation dimension, the maximum information coefficient under the second evaluation dimension, and the number of categories under the third evaluation dimension can be obtained as the corresponding feature indicators under different evaluation dimensions. Among them, for the calculation of information entropy and maximum information coefficient, you can refer to the more mature algorithms on the market, and the embodiments of the present invention will not be described one by one here. In this way, the screening tendency corresponding to each device feature in the device feature pool can be determined, such as Figure 3 As shown, the following steps may be specifically included:

[0080] S301, finding the weights corresponding to the target information entropy, the maximum information coefficient, and the number of categories in the current scenario.

[0081] S302: Determine the screening tendency of the device feature according to the target information entropy, the maximum information coefficient, the number of categories, and the corresponding weights.

[0082] In an embodiment of the present invention, for the target information entropy, maximum information coefficient, number of categories, etc., corresponding different weights are set in different scenarios, so as to adjust the influence weights of the target information entropy, maximum information coefficient, number of categories, etc. on the final screening tendency according to the characteristics of different scenarios. For example, as shown in Table 4 below, for the target information entropy, maximum information coefficient, number of categories, etc., corresponding different weights are set in different scenarios.

[0083]

[0084]

[0085] Table 4

[0086] Based on this, in an embodiment of the present invention, for each device feature in the device feature pool, the corresponding feature indicators in different evaluation dimensions, that is, the target information entropy in the first evaluation dimension, the maximum information coefficient in the second evaluation dimension, and the number of categories in the third evaluation dimension, the weights corresponding to the target information entropy, the maximum information coefficient, and the number of categories in the current scenario are found, and the screening tendency of the device feature is determined according to the target information entropy, the maximum information coefficient, the number of categories, and the corresponding weights.

[0087] For example, for the target information entropy under the first evaluation dimension, the maximum information coefficient under the second evaluation dimension, and the number of categories under the third evaluation dimension corresponding to the device feature of "ip" in the device feature pool, find the corresponding weights of the target information entropy, the maximum information coefficient, and the number of categories in the H5 scenario, as shown in Table 4 above, that is, the weight W1 corresponding to the target information entropy is 0.7, the weight W2 corresponding to the maximum information coefficient is 0.2, and the weight W3 corresponding to the number of categories is 0.1. According to the target information entropy, the maximum information coefficient and the number of categories, and the corresponding weights, the screening tendency of the device feature of "ip" is determined. For the remaining device features in the device feature pool, the processing is similar to the above, and the embodiments of the present invention will not be repeated here one by one. In this way, for each device feature in the device feature pool, the corresponding screening tendency can be obtained.

[0088] Among them, in the embodiment of the present invention, for each of the characteristic indicators corresponding to each of the device characteristics in the device characteristic pool under different evaluation dimensions, that is, the target information entropy under the first evaluation dimension, the maximum information coefficient under the second evaluation dimension, and the number of categories under the third evaluation dimension, the weighted sum between the target information entropy, the maximum information coefficient, the number of categories and the corresponding weights is obtained to obtain the screening tendency of the device characteristic. Here, the screening tendency is embodied in the form of a specific score (Score), which is not limited in the embodiment of the present invention.

[0089] For example, for the target information entropy under the first evaluation dimension, the maximum information coefficient under the second evaluation dimension, and the number of categories under the third evaluation dimension corresponding to the device feature of "ip" in the device feature pool, obtain the weighted sum of the target information entropy, the maximum information coefficient, the number of categories and their corresponding weights, that is, the MIU evaluation function shown below, substitute the weighted sum of the target information entropy, the maximum information coefficient, the number of categories and their corresponding weights into the MIU evaluation function, and obtain the screening tendency (Score) of the device feature of "ip". For the remaining device features in the device feature pool, the processing is similar to the above, and the embodiments of the present invention will not be repeated here one by one. In this way, for each device feature in the device feature pool, the corresponding screening tendency can be obtained.

[0090] Score = W1*S (target information entropy) + (-W2*S (maximum information coefficient)) + W3*S (number of categories).

[0091] Here, the screening tendency can be specifically expressed in the form of a score, wherein the S(*) function is a standardized function to prevent a certain characteristic index from affecting the overall performance too much.

[0092] S104: Filter target device features from the device feature pool as device fingerprint features according to the screening tendency corresponding to each device feature in the device feature pool.

[0093] In the embodiment of the present invention, after the above steps, the screening tendency corresponding to each device feature in the device feature pool can be obtained, where the screening tendency can be specifically embodied in the form of a score, so that the target device feature can be screened from the device feature pool as the device fingerprint feature according to the screening tendency corresponding to each device feature in the device feature pool. Subsequently, the device fingerprint feature is input into the matching model for device fingerprint matching, which can effectively improve the device fingerprint matching success rate of the matching model.

[0094] Among them, in the embodiment of the present invention, according to the screening tendency corresponding to each device feature in the device feature pool, the device features in the device feature pool are sorted, and from the sorting results of each device feature in the device feature pool, the top N% of the target device features are selected as device fingerprint features. Subsequently, the device fingerprint features are input into the matching model for device fingerprint matching, which can effectively improve the device fingerprint matching success rate of the matching model.

[0095] For example, in an embodiment of the present invention, each device feature in the device feature pool is sorted according to the screening tendency corresponding to each device feature in the device feature pool, wherein the sorting results of each device feature in different scenarios are as shown in Table 5 below, and from the sorting results of each device feature in the device feature pool, the top 80% (here it can be adjusted according to the overall effect level of the device feature and the specific application scenario) of the target device features are selected as the device fingerprint features, and the device fingerprint features are subsequently input into the matching model for device fingerprint matching, which can effectively improve the device fingerprint matching success rate of the matching model, for example, by about 10% to 15%.

[0096]

[0097]

[0098] Table 5

[0099] Through the above description of the technical solution provided by the embodiment of the present invention, at least one device feature of the target device is obtained, and a device feature pool is composed of at least one device feature of the target device. For any device feature in the device feature pool, the feature index of the device feature under different evaluation dimensions is determined, and the current scene is determined. According to the current scene and the feature index, the screening tendency of the device feature is determined, and according to the screening tendency corresponding to each device feature in the device feature pool, the target device feature is screened from the device feature pool as the device fingerprint feature.

[0100] By acquiring at least one device feature of the target device, a device feature pool is formed. For any device feature in the device feature pool, the feature index of the device feature under different evaluation dimensions is determined, and the current scene is determined. According to the current scene and the feature index, the screening tendency of the device feature is determined, so as to screen each device feature in the device feature pool based on the screening tendency to obtain the device fingerprint feature. Subsequently, the device fingerprint feature is input into the matching model for device fingerprint matching, which can effectively improve the device fingerprint matching success rate of the matching model.

[0101] Corresponding to the above method embodiment, the embodiment of the present invention also provides a device fingerprint feature screening device, such as Figure 4 As shown, the device may include: a feature acquisition module 410, an indicator determination module 420, a tendency determination module 430, and a feature screening module 440.

[0102] A feature acquisition module 410 is used to acquire at least one device feature of a target device, and form a device feature pool by using at least one device feature of the target device;

[0103] An indicator determination module 420, configured to determine, for any device feature in the device feature pool, a feature indicator of the device feature under different evaluation dimensions;

[0104] The tendency determination module 430 is used to determine the current scene, and determine the screening tendency of the device feature according to the current scene and the feature index;

[0105] The feature screening module 440 is used to screen target device features from the device feature pool as device fingerprint features according to the screening tendency corresponding to each device feature in the device feature pool.

[0106] The embodiment of the present invention further provides an electronic device, such as Figure 5 As shown, it includes a processor 51, a communication interface 52, a memory 53 and a communication bus 54, wherein the processor 51, the communication interface 52, and the memory 53 communicate with each other through the communication bus 54.

[0107] A memory 53, for storing computer programs;

[0108] The processor 51 is used to execute the program stored in the memory 53 to implement the following steps:

[0109] Acquire at least one device feature of a target device, and form a device feature pool consisting of at least one device feature of the target device; determine the feature index of the device feature under different evaluation dimensions for any device feature in the device feature pool; determine a current scene, and determine a screening tendency of the device feature according to the current scene and the feature index; and screen the target device feature from the device feature pool as a device fingerprint feature according to the screening tendency corresponding to each device feature in the device feature pool.

[0110] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0111] The communication interface is used for communication between the above electronic device and other devices.

[0112] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0113] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0114] In another embodiment of the present invention, a storage medium is provided, in which instructions are stored. When the storage medium is run on a computer, the computer executes the device fingerprint feature screening method described in any of the above embodiments.

[0115] In another embodiment provided by the present invention, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the device fingerprint feature screening method described in any one of the above embodiments.

[0116] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a storage medium, or transmitted from one storage medium to another storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0117] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0118] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A device fingerprint feature screening method, It is characterized in that The method comprises: Acquire at least one device feature of a target device, and form a device feature pool by using at least one device feature of the target device; For any of the device features in the device feature pool, determining feature indicators of the device feature under different evaluation dimensions; Determine a current scene, and determine a screening tendency of the device feature according to the current scene and the feature indicator; According to the screening tendency corresponding to each of the device features in the device feature pool, screening target device features from the device feature pool as device fingerprint features; Wherein, determining the characteristic indicators of the device characteristics under different evaluation dimensions includes: Determine a target information entropy of the device feature under a first evaluation dimension; Determine the maximum information coefficient of the device feature under the second evaluation dimension; Determining the number of categories of the device characteristics under the third evaluation dimension; The determining, according to the current scenario and the feature index, the screening tendency of the device feature includes: Find the target information entropy, the maximum information coefficient, and the weights corresponding to the number of categories in the current scenario; Determining the screening tendency of the device feature according to the target information entropy, the maximum information coefficient, the number of categories, and the weights corresponding to each of them; The step of screening target device features from the device feature pool as device fingerprint features according to the screening tendency corresponding to each device feature in the device feature pool includes: sorting the device features in the device feature pool according to the screening tendency corresponding to each of the device features in the device feature pool; From the ranking results of the device features in the device feature pool, the target device features ranked in the top N% are selected as device fingerprint features.

2. The method according to claim 1, It is characterized in that The determining the target information entropy of the device feature under the first evaluation dimension includes: Determine a first information entropy of the device feature between the same device, and determine a second information entropy of the device feature between different devices; A difference between the second information entropy and the first information entropy is obtained, and the difference is determined to be a target information entropy of the device feature under the first evaluation dimension.

3. The method according to claim 1, It is characterized in that Determining the number of categories of the device feature under the third evaluation dimension includes: The total number of characteristic values ​​of the device characteristic is found, and the total number of characteristic values ​​is determined to be the number of categories of the device characteristic under the third evaluation dimension.

4. The method according to claim 1, It is characterized in that The determining the screening tendency of the device feature according to the target information entropy, the maximum information coefficient, the number of categories, and the weights corresponding to each of them includes: The target information entropy, the maximum information coefficient, the weighted sum of the number of categories and the weights corresponding to each other are obtained to obtain the screening tendency of the device feature.

5. A device fingerprint feature screening device, It is characterized in that The device comprises: A feature acquisition module, used for acquiring at least one device feature of a target device, and forming a device feature pool by the at least one device feature of the target device; An indicator determination module, used for determining, for any device feature in the device feature pool, a feature indicator of the device feature under different evaluation dimensions; A tendency determination module, used to determine a current scene, and determine a screening tendency of the device feature according to the current scene and the feature index; A feature screening module, configured to screen target device features from the device feature pool as device fingerprint features according to the screening tendency corresponding to each device feature in the device feature pool; Wherein, determining the characteristic indicators of the device characteristics under different evaluation dimensions includes: Determine a target information entropy of the device feature under a first evaluation dimension; Determine the maximum information coefficient of the device feature under the second evaluation dimension; Determining the number of categories of the device characteristics under the third evaluation dimension; The determining, according to the current scenario and the feature index, the screening tendency of the device feature includes: Find the target information entropy, the maximum information coefficient, and the weights corresponding to the number of categories in the current scenario; Determining the screening tendency of the device feature according to the target information entropy, the maximum information coefficient, the number of categories, and the weights corresponding to each of them; The step of screening target device features from the device feature pool as device fingerprint features according to the screening tendency corresponding to each device feature in the device feature pool includes: sorting the device features in the device feature pool according to the screening tendency corresponding to each of the device features in the device feature pool; From the ranking results of the device features in the device feature pool, the target device features ranked in the top N% are selected as device fingerprint features.

6. An electronic device, It is characterized in that It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, configured to implement the method according to any one of claims 1 to 4 when executing a program stored in a memory.

7. A storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images