Method, device, storage medium and terminal for identifying a counterfeit application

Abstract

The embodiment of the application provides a counterfeit application identification method and device, a storage medium and a terminal, the method comprises the following steps: obtaining the similarity between a target application icon and each sample application icon in a sample application icon library based on the target application, thereby obtaining a plurality of similarities; obtaining one or more sub-sample application icon libraries based on the similarity ranking of all the similarities and the sample application icon library, and obtaining the sub-similarity between the target application icon and each sample application icon in the one or more sub-sample application icon libraries, thereby obtaining one or more sub-similarities; and identifying whether the target application is a counterfeit application based on the plurality of similarities and the one or more sub-similarities. The application calculates the similarity between the target application icon and the sample application icon through multiple algorithms, reduces the errors of a single algorithm in calculating the similarities of multiple types of icons, improves the accuracy of the icon similarity, and thus improves the accuracy of identifying the counterfeit application.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and particularly relates to a counterfeit application identification method and device, a storage medium and a terminal. BACKGROUND

[0002] At present, bank and financial applications on the market involve a large number of money transactions, and some groups can easily use counterfeit applications with bank and financial icons to induce consumers, especially the elderly, to perform behaviors such as transferring money and consuming on the application, implement fraud, and also exist behaviors such as privacy theft and malicious promotion that infringe the interests of consumers. Therefore, how to identify these counterfeit applications is an important means for us to protect consumers.

[0003] Identifying counterfeit applications through application icons is a common method at present, but the current picture detection and identification method uses a picture similarity algorithm phash and dhash algorithm, and some use an image matching algorithm SIFT algorithm. The traditional dhash and phash algorithms have relatively high accuracy for pictures of similar sizes, but the accuracy is relatively low for pictures involving scaling or rotation. The SIFT algorithm has relatively high accuracy for low-pixel pictures, but the accuracy is low for high-latitude pictures. SUMMARY

[0004] The embodiments of the present application provide a counterfeit application identification method, device, storage medium and terminal, which uses multiple algorithms to calculate the similarity of the target application icon and the sample application icon, improves the accuracy of the icon similarity, and thus improves the accuracy of identifying counterfeit applications.

[0005] In a first aspect, the embodiments of the present application provide a counterfeit application identification method, comprising:

[0006] Based on a target application, the similarity of a target application icon and each sample application icon in a sample application icon library is obtained, thereby obtaining a plurality of similarities;

[0007] Based on the sorting of all similarities and the sample application icon library, one or more sub-sample application icon libraries are obtained, and the sub-similarity of the target application icon and each sample application icon in the one or more sub-sample application icon libraries is obtained, thereby obtaining one or more sub-similarities;

[0008] Based on the plurality of similarities and the one or more sub-similarities, it is determined whether the target application is a counterfeit application.

[0009] In a second aspect, the embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the method steps of the first aspect.

[0010] In a third aspect, an embodiment of the present application provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method steps of the first aspect when executing the computer program.

[0011] The application embodiment provides the counterfeit application identification method, device, storage medium and terminal, which has the following technical effects:

[0012] The application obtains the similarity of the target application icon and each sample application icon in the sample application icon library based on the target application, thereby obtaining a plurality of similarities; obtains one or more sub-sample application icon libraries based on the similarity ranking and the sample application icon library, and respectively obtains the sub-similarity of the target application icon and each sample application icon in the one or more sub-sample application icon libraries, thereby obtaining one or more sub-similarities; and identifies whether the target application is a counterfeit application based on the plurality of similarities and the one or more sub-similarities. The application calculates the similarity of the target application icon and the sample application icon through multiple algorithms, reduces the errors of a single algorithm in calculating the similarities of multiple types of icons, improves the accuracy of the icon similarity, and thereby improves the accuracy of identifying the counterfeit application. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0014] Figure 1 A counterfeit application identification method flowchart is provided for the application embodiment.

[0015] Figure 2 A structural schematic diagram of a counterfeit application identification device is provided for the application embodiment.

[0016] Figure 3 A block diagram of a terminal is provided for the application embodiment. DETAILED DESCRIPTION

[0017] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0018] The following description refers to the accompanying drawings. Unless otherwise indicated, same or similar elements in different drawings have same or similar reference numerals. The implementations described in the following exemplary embodiments are not meant to represent all implementations consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0019] In the description of the present application, it should be understood that the terms "first", "second" and the like are used only for the purpose of description, and cannot be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0020] Currently, some groups can easily use counterfeit applications with bank financial icons and the like to induce consumers, especially the elderly, to perform behaviors such as transferring money and consuming on the application, implement fraud, and also exist behaviors such as privacy theft and malicious promotion that infringe the interests of consumers. Therefore, how to identify these counterfeit applications is an important means for us to protect consumers.

[0021] And the application icon is a common method for identifying counterfeit applications at present, but the current picture detection and identification method is partly using the picture similarity algorithm phash, dhash algorithm, and partly using the image matching algorithm SIFT algorithm. The traditional dhash and phash algorithms have relatively high accuracy for pictures of similar sizes, but the accuracy is relatively low for pictures involving scaling or rotation. The SIFT algorithm has relatively high accuracy for low-latitude pictures, but the accuracy is low for high-latitude pictures.

[0022] In view of the above problems, the present application provides a counterfeit application identification method, device, storage medium and terminal. Next, the steps of the counterfeit application identification method in the embodiments of the present application will be described in more detail with reference to the drawings and embodiments.

[0023] Figure 1 A counterfeit application identification method flowchart is provided for the embodiments of the present application. As shown in Figure 1 The method of the embodiments of the present application can include the following steps:

[0024] S101, based on the target application, obtaining the similarity between the target application icon and each sample application icon in the sample application icon library, thereby obtaining a plurality of similarities.

[0025] In the embodiment of the application, when identifying whether the target application is a counterfeit application, the information used is the icon of the application. Therefore, after determining the target application, the icon of the target application is further obtained, which can be obtained through network search, obtained through an application store, or downloaded from an existing icon library, without limitation.

[0026] Optionally, after obtaining the target application icon, the similarity between the target application icon and each sample application icon in the sample application icon library is calculated to obtain the similarity between the target application icon and each sample application icon in the sample application icon library. The sample application icon library is composed of the icons of a plurality of sample applications. Therefore, before obtaining the sample application icon library, a plurality of sample applications need to be determined. In actual situations, each application has its download volume and installation volume, indicating the size of its audience group. An application with a high installation volume has a larger audience group and can obtain greater benefits after being counterfeited, and therefore has a greater possibility of being counterfeited. Therefore, when determining the sample applications, applications with high installation volumes, such as Taobao, WeChat, Alipay, and Pinduoduo, can be selected. Specifically, a plurality of applications at the top of the installation volume ranking can be selected to form sample applications, such as the top 5000, 10000, or 15000 applications. Of course, the specific number and selection method can be freely set, without limitation. After determining a plurality of sample applications, the icon of each sample application is obtained to form a sample application icon library. After obtaining the sample application icon library, the similarity between the target application icon and each sample application icon in the sample application icon library is obtained, thereby obtaining a plurality of similarities. The specific steps include:

[0027] S101.1, based on the target application icon, obtaining a target feature vector.

[0028] Optionally, an icon is essentially a picture. Therefore, when calculating the similarity between icons, the similarity between pictures is essentially calculated. However, each icon may have differences in size and format, which is inconvenient for direct calculation. Therefore, each icon can be converted into a corresponding feature vector for similarity calculation. First, based on the target application icon, a target feature vector is obtained, that is, the target application icon is converted into a corresponding target feature vector. The specific steps include:

[0029] (1) restoring the target application icon to a pixel point to obtain a target vector matrix corresponding to the target application icon;

[0030] (2) reducing the dimension of the target vector matrix to obtain a target feature vector.

[0031] Optionally, when processing the picture corresponding to the target application icon, the icon information in the picture is mainly obtained, and therefore the ROI processing can be performed on the picture corresponding to the target application icon, the frame is removed and the main characteristic attribute, i.e., the icon, is retained. The icon is an image composed of red, green and blue three-channel pixels, and therefore the icon can be restored to a pixel point to obtain a target vector matrix. The matrix size can be freely set, such as 8*9, 9*9, etc., which is not limited herein.

[0032] Optionally, after the target application icon is converted into the target vector matrix, the vector matrix is not enough to directly describe the characteristics of the application icon, and it is also inconvenient to compare two application icons and determine the similarity. Therefore, the target vector matrix can be further reduced in dimension to convert the target vector matrix into a one-dimensional target feature vector. For example, the target vector matrix can be input into a trained neural network model, and after ONEHOT coding processing, a corresponding one-dimensional target feature vector is obtained. The format of the target feature vector can also be freely set, such as 1*2048, 1*4096, etc. The advantage of this method is that the target vector matrix can be reduced in dimension to a one-dimensional target feature vector, and the characteristics of the target vector matrix can also be retained. When two vector matrices are similar, the two feature vectors obtained according to this method are still similar. Of course, other methods can also be used to reduce the target vector matrix in dimension to a one-dimensional target feature vector, which is not limited herein.

[0033] S101.2, based on the sample application icon library, a sample feature vector corresponding to each sample application icon is obtained to form a sample feature vector library.

[0034] Optionally, after the target feature vector corresponding to the target application icon is obtained by the above method, the same method can be used to obtain the sample feature vector of each sample application icon in the sample application icon library to form a sample feature vector library. The specific steps include:

[0035] (1) each sample application icon in the sample application icon library is restored to a pixel point, and a sample vector matrix corresponding to each sample application icon is obtained;

[0036] (2) all sample vector matrices are reduced in dimension to obtain a sample feature vector corresponding to each sample vector matrix;

[0037] (3) all sample feature vectors are combined to form a sample feature vector library.

[0038] Optionally, the same as the processing method of the target application icon, first, the picture line ROI corresponding to each sample application icon in the sample application icon library is processed, and the frame is removed to retain the main characteristic attributes, and then each sample application icon in the sample application icon library is restored to a pixel point, so as to obtain a sample vector matrix corresponding to each sample application icon. It should be noted that, in order to facilitate subsequent unified calculation, the size of each sample vector matrix needs to be consistent with the target vector matrix.

[0039] Optionally, after converting each sample application icon in the sample application icon library into a corresponding sample vector matrix, the dimensionality of all sample vector matrices is reduced by using the method described above, so as to obtain a sample feature vector corresponding to each sample vector matrix. It should be noted that, in order to facilitate subsequent calculation, the format of each sample feature vector needs to be consistent with the target feature vector. Then, all sample feature vectors are combined to form a sample feature vector library. Since each sample feature vector is a one-dimensional vector with consistent length, all sample feature vectors can be saved as a matrix, and each row in the matrix is a sample feature vector.

[0040] S101.3, similarity calculation is performed between the target feature vector and each sample feature vector in the sample feature vector library, so as to obtain the similarity between the target application icon and each sample application icon in the sample application icon library, thereby obtaining a plurality of similarities.

[0041] Optionally, after obtaining the target feature vector and the sample feature vector library by the above method, similarity calculation is performed between the target feature vector and each sample feature vector in the sample feature vector library, so as to obtain the similarity between the target application icon and each sample application icon in the sample application icon library, thereby obtaining a plurality of similarities.

[0042] The similarity between two feature vectors can be calculated by using cosine similarity, and the calculation formula is as follows:

[0043]

[0044] Wherein, x1 represents the first group of feature vectors, x2 represents the second group of feature vectors, n represents that x1 and x2 both contain n elements, x 1k , x 2k respectively represent the kth element in x1 and x2, and θ represents the included angle between x1 and x2.

[0045] According to the above formula (1), assuming that there are two groups of feature vectors x1 and x2, both of which contain n elements, then x 1k , x 2krespectively represent the kth element in the eigenvectors x1, x2, and θ represents the angle between the two sets of eigenvectors x1 and x2. The cosine similarity represents that the smaller the angle is, the closer the cosine value is to 1, that is, the higher the similarity of the two sets of eigenvectors is, and vice versa, which tends to -1. Therefore, the similarity of the two sets of eigenvectors x1 and x2 can be calculated by using the cosine similarity calculation formula. Of course, other calculation methods can also be used to calculate the similarity between the eigenvectors, which is not limited here.

[0046] Based on any of the above optional embodiments, in one optional embodiment, S102, one or more sub-sample application icon libraries are obtained based on all similarity rankings and the sample application icon library, and a sub-similarity of the target application icon and each sample application icon in the one or more sub-sample application icon libraries is obtained respectively, thereby obtaining one or more sub-similarities.

[0047] In the embodiment of the application, the similarity of the target application icon and each sample application icon in the sample application icon library is obtained by the above method, thereby obtaining a plurality of similarities. However, the accuracy of this algorithm is relatively high for pictures of similar sizes, and the accuracy is relatively low for pictures involving scaling or rotation. Therefore, the similarity of the target application icon and each sample application icon in the sample application icon library obtained may have certain errors. Therefore, in order to reduce the error of the algorithm for calculating the similarity of the picture, a plurality of methods can be used to calculate the similarity of the target application icon and each sample application icon in the sample application icon library.

[0048] Optionally, since the sample application icon library includes a large number of sample application icons, a large number of similarities are obtained, but most of the sample application icons in the sample application icon library are not similar to the target application icon, and the corresponding similarity is also relatively low. In order to reduce the calculation amount of calculating the similarity of the target application icon and each sample application icon in the sample application icon library by using a plurality of methods, one or more sub-sample application icon libraries can be selected from the sample application icon library according to the ranking of all similarities, and a sub-similarity of the target application icon and each sample application icon in the one or more sub-sample application icon libraries is obtained respectively, thereby obtaining one or more sub-similarities. The specific steps include:

[0049] S102.1, based on all similarity rankings, the first sub-sample application icon library is selected from the sample application icon library corresponding to the first n1 similarities, and the first sub-similarity of the target application icon and each sample application icon in the first sub-sample application icon library is obtained;

[0050] S102.2, based on all the first sub-similarity rankings, selecting the first n2 sample application icons corresponding to the first n2 sub-similarities to form a second sub-sample application icon library, and obtaining the second sub-similarity between the target application icon and each sample application icon in the second sub-sample application icon library;

[0051] S102.3, until all the m-1th sub-similarity rankings are sorted from high to low, and the first n m m-1 sample application icons corresponding to the first n m m-1 sub-similarities are selected to form the mth sub-sample application icon library, and the mth sub-similarity between the target application icon and each sample application icon in the mth sample application icon library is obtained.

[0052] Optionally, all the similarities are first sorted from high to low, and then the first n1 sample application icons corresponding to the first n1 similarities are selected to form a first sub-sample application icon library, wherein n1>0 and n1 is an integer. n1 can be freely set according to actual conditions, such as 500, 1000, 1500, etc., which are not limited here. However, it should be noted that n1 is less than or equal to the number of all similarities. After obtaining the first sub-sample application icon library, the first sub-similarity between the target application icon and each sample application icon in the first sub-sample application icon library can be further calculated using a first preset algorithm, which can be SIFT algorithm, SURF algorithm or ORB algorithm, etc., which are not limited here.

[0053] Optionally, in order to further narrow the range of sample application icons, all the first sub-similarities are sorted from high to low, and then the first n2 sample application icons corresponding to the first n2 sub-similarities are selected to form a second sub-sample application icon library, wherein n2>0 and n2 is an integer. n2 can be freely set according to actual conditions, such as 400, 8000, 1200, etc., which are not limited here. It should be noted that n2 is less than or equal to n1. After obtaining the second sub-sample application icon library, the second sub-similarity between the target application icon and each sample application icon in the second sub-sample application icon library can be further calculated using a second preset algorithm, which can be SIFT algorithm, SURF algorithm or ORB algorithm, etc., which are not limited here. However, it should be noted that the second preset algorithm is different from the first preset algorithm.

[0054] Until all the m-1th sub-similarities are sorted from high to low, and the first n m m-1 sample application icons corresponding to the first n m m-1 sub-similarities are selected to form the mth sub-sample application icon library, wherein n m >0 and n m is an integer. n m may be freely set according to actual conditions, such as 50, 100, 150, etc., which are not limited here. However, it should be noted that nm-1 After obtaining the mth sample application icon library, the mth preset algorithm can be further used to calculate the mth sub-similarity of the target application icon and each sample application icon in the mth sample application icon library. The mth preset algorithm can be SIFT algorithm, SURF algorithm or ORB algorithm, etc., which is not limited here. However, it should be noted that the mth preset algorithm is different from the first preset algorithm, the second preset algorithm, and the (m-1)th preset algorithm.

[0055] Based on any of the above optional embodiments, S103, based on the similarity and the one or more sub-similarities, identifying whether the target application is a fake application.

[0056] In the embodiments of the application, the similarity of the target application icon and each sample application icon in the sample application icon library, and the sub-similarity of the target application icon and each sample application icon in one or more sample application icon libraries are obtained, and then based on the above similarity and one or more sub-similarities, whether the target application is a fake application is identified. The specific steps include:

[0057] S103.1, based on each sample application icon in the mth sample application icon library, respectively, the similarity, the first sub-similarity, the second sub-similarity, and the mth sub-similarity corresponding to each sample application icon are weighted and summed to obtain the application similarity of the sample application corresponding to each sample application icon and the target application, thereby obtaining a plurality of application similarities;

[0058] S103.2, obtaining the highest application similarity in the plurality of application similarities, if the highest application similarity is greater than or equal to a preset threshold, the target application is a fake application of the sample application corresponding to the highest application similarity.

[0059] Optionally, the sample application icons are gradually reduced layer by layer using multiple algorithms, and when the mth sample application icon library is obtained, the mth sample application icon library is the final selected sample application icon library, which contains the sample application icons most similar to the target application icon, and each sample application icon in the mth sample application icon library has a corresponding similarity, first sub-similarity, second sub-similarity, and mth sub-similarity.

[0060] Optionally, the similarity, the first sub-similarity, the second sub-similarity, and the mth sub-similarity corresponding to each sample application icon in the mth sample application icon library are weighted and summed to obtain the application similarity of the sample application corresponding to each sample application icon and the target application. Since the mth sample application icon library can include a plurality of sample application icons, a plurality of application similarities can be obtained.

[0061] Specifically, if the second sub-sample application icon library is obtained, each sample application icon in the second sub-sample application icon library has a corresponding similarity, a first sub-similarity and a second sub-similarity, the weight of the similarity is set to 0.4, the weight of the first sub-similarity is set to 0.3, and the weight of the second sub-similarity is set to 0.3. If a certain sample application icon corresponds to a similarity of 0.8, a first sub-similarity of 0.8 and a second sub-similarity of 0.9, the application similarity of the target application and the sample application corresponding to the sample application icon is 0.8*0.4+0.8*0.3+0.9*0.3=0.83. Through the above method, the application similarity of the target application and the sample application corresponding to each sample application icon in the second sub-sample application icon library can be obtained, thereby obtaining a plurality of application similarities.

[0062] Optionally, the application is counterfeited by the icon, generally only one original application is selected as the object, and therefore the target application is generally a counterfeited application of a sample application. Therefore, the highest application similarity in the above plurality of application similarities is obtained, and if the highest application similarity is greater than or equal to a preset threshold, the target application is a counterfeited application of the sample application corresponding to the highest application similarity. The preset threshold can be set according to actual conditions, such as 0.7, 0.8, etc., which is not limited here.

[0063] In another optional embodiment, S102, one or more sub-sample application icon libraries are obtained based on all similarity rankings and the sample application icon library, and a sub-similarity of the target application icon and each sample application icon in the one or more sub-sample application icon libraries is obtained respectively, thereby obtaining one or more sub-similarities.

[0064] Optionally, in addition to using multiple algorithms to layer by layer reduce the sample application icon and obtain multiple sub-similarities, the sample application icon can also be directly reduced to a suitable number to obtain a sub-sample application icon library, and multiple algorithms are used to calculate the similarity of the target application icon and each sample application icon in the sub-sample application icon library respectively, thereby obtaining multiple sub-similarities. The specific steps include:

[0065] S102.1, based on all similarity rankings, a plurality of sample application icons corresponding to the first plurality of similarities are selected to form a sub-sample application icon library;

[0066] S102.2, the target application icon and each sample application icon in the sub-sample application icon library are calculated for similarity by a first preset algorithm, thereby obtaining a first sub-similarity of the target application icon and each sample application icon in the sub-sample application icon library;

[0067] S102.3, performing similarity calculation on the target application icon and each sample application icon in the sub-sample application icon library by a second preset algorithm to obtain a second sub-similarity between the target application icon and each sample application icon in the sub-sample application icon library;

[0068] S102.4, performing similarity calculation on the target application icon and each sample application icon in the sub-sample application icon library by an mth preset algorithm to obtain an mth sub-similarity between the target application icon and each sample application icon in the sub-sample application icon library.

[0069] Optionally, all the similarities are first sorted from high to low, and then a plurality of sample application icons corresponding to the top similarities are selected to form the sub-sample application icon library. The number of the selected sample application icons can be freely set according to actual conditions, such as 50, 100, 150, etc., which are not limited herein. However, it should be noted that the number of the sample application icons included in the sub-sample application icon library is less than or equal to the number of the sample application icons in the sample application icon library.

[0070] Optionally, after obtaining the sub-sample application icon library, similarity calculation is performed on the target application icon and each sample application icon in the sub-sample application icon library by a first preset algorithm to obtain a first sub-similarity between the target application icon and each sample application icon in the sub-sample application icon library. The first preset algorithm can be SIFT algorithm, SURF algorithm or ORB algorithm, etc., which are not limited herein.

[0071] Optionally, similarity calculation can be continuously performed on the target application icon and each sample application icon in the sub-sample application icon library by a second preset algorithm to obtain a second sub-similarity between the target application icon and each sample application icon in the sub-sample application icon library. The second preset algorithm can be SIFT algorithm, SURF algorithm or ORB algorithm, etc., which are not limited herein. However, it should be noted that the second preset algorithm is different from the first preset algorithm.

[0072] The similarity calculation is performed on the target application icon and each sample application icon in the sub-sample application icon library by an mth preset algorithm to obtain an mth sub-similarity between the target application icon and each sample application icon in the sub-sample application icon library. The mth preset algorithm can be SIFT algorithm, SURF algorithm or ORB algorithm, etc., which are not limited herein. However, it should be noted that the mth preset algorithm is different from the first preset algorithm, the second preset algorithm and the (m-1)th preset algorithm.

[0073] S103, identifying whether the target application is a counterfeit application based on the plurality of similarities and the one or more sub-similarities.

[0074] In the embodiment of the present application, the similarity of the target application icon and each sample application icon in the sample application icon library is obtained, and the sub-similarities of the target application icon and each sample application icon in the one or more sample application icon libraries are obtained, so that one or more sub-similarities are obtained. Based on the above similarity and the one or more sub-similarities, it is determined whether the target application is a fake application. The specific steps include:

[0075] In S103.1, based on each sample application icon in the sub-sample application icon library, the similarity, the first sub-similarity, the second sub-similarity, and the mth sub-similarity corresponding to each sample application icon are respectively weighted and summed to obtain the application similarity between the sample application corresponding to each sample application icon and the target application, so that a plurality of application similarities are obtained.

[0076] In S103.2, the highest application similarity in the plurality of application similarities is obtained. If the highest application similarity is greater than or equal to a preset threshold, the target application is a fake application of the sample application corresponding to the highest application similarity.

[0077] Optionally, the sample application icons are directly reduced to a proper number to obtain a sub-sample application icon library, and a plurality of algorithms are used to respectively calculate the similarity of the target application icon and each sample application icon in the sub-sample application icon library. The sub-sample application icon library is the final screening result, and each sample application icon in the sub-sample application icon library has a corresponding similarity, a first sub-similarity, a second sub-similarity, and an mth sub-similarity.

[0078] Optionally, the similarity, the first sub-similarity, the second sub-similarity, and the mth sub-similarity corresponding to each sample application icon in the sub-sample application icon library are respectively weighted and summed to obtain the application similarity between the sample application corresponding to each sample application icon and the target application. Since the sub-sample application icon library includes a plurality of sample application icons, a plurality of application similarities can be obtained.

[0079] Specifically, if two preset algorithms are used to calculate the similarity of the target application icon and each sample application icon in the sample application icon library, each sample application icon in the sample application icon library has a corresponding similarity, a first sub-similarity and a second sub-similarity, the weight of the similarity is set to 0.4, the weight of the first sub-similarity is set to 0.3, and the weight of the second sub-similarity is set to 0.3. If a sample application icon corresponds to a similarity of 0.8, a first sub-similarity of 0.8 and a second sub-similarity of 0.9, the application similarity of the target application and the sample application corresponding to the sample application icon is 0.8*0.4+0.8*0.3+0.9*0.3=0.83. Through the above method, the application similarity of the target application and each sample application icon in the sample application icon library can be obtained, thereby obtaining a plurality of application similarities.

[0080] The highest application similarity in the above plurality of application similarities is obtained, and if the highest application similarity is greater than or equal to a preset threshold, the target application is a cloned application of the sample application corresponding to the highest application similarity. The preset threshold can be set according to actual conditions, such as 0.7, 0.8, etc., which is not limited herein.

[0081] In summary, the embodiment of the present application provides a cloned application identification method. When it is necessary to identify a cloned application, the similarity of the target application icon and each sample application icon in the sample application icon library is obtained based on the target application, thereby obtaining a plurality of similarities. One or more sample application icon libraries are obtained based on the sorting of all similarities and the sample application icon library, and the sub-similarity of the target application icon and each sample application icon in the one or more sample application icon libraries is obtained, thereby obtaining one or more sub-similarities. Whether the target application is a cloned application is identified based on the plurality of similarities and the one or more sub-similarities. The present application calculates the similarity of the target application icon and the sample application icon by using multiple algorithms, which can reduce the errors of a single algorithm in calculating the similarity of multiple types of icons, improve the accuracy of the icon similarity, and thus improve the accuracy of identifying cloned applications.

[0082] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the method embodiment of the present application.

[0083] Please refer to Figure 2 The structure of a cloned application identification device provided by the embodiment of the present application is shown in the figure.

[0084] The cloned application identification device 200 in the embodiment of the present application comprises a similarity obtaining module 201, a sub-similarity obtaining module 202 and an identification module 203.

[0085] The similarity obtaining module is configured to obtain similarities between the target application icon and each sample application icon in the sample application icon library based on the target application, thereby obtaining a plurality of similarities.

[0086] The sub-similarity obtaining module is configured to obtain one or more sub-sample application icon libraries based on the all-similarity ranking and the sample application icon library, and obtain sub-similarities between the target application icon and each sample application icon in the one or more sub-sample application icon libraries, thereby obtaining one or more sub-similarities.

[0087] The identification module is configured to identify whether the target application is a fake application based on the plurality of similarities and the one or more sub-similarities.

[0088] It should be noted that the fake application identification device provided in the above embodiments is only used as an example for the division of the above functional modules when the fake application identification method is executed, and in actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the fake application identification device and the fake application identification method provided in the above embodiments belong to the same concept, so for the details not disclosed in the system embodiment of the present application, please refer to the above-mentioned embodiments of the fake application identification method of the present application, which will not be described here.

[0089] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0090] The embodiments of the present application also provide a computer readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the steps of the method of any of the preceding embodiments. The computer readable storage medium can include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0091] The embodiments of the present application also provide a terminal including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the steps of the method of any of the preceding embodiments.

[0092] Figure 3 A block diagram of a terminal provided by the embodiments of the present application is shown in FIG. 1. Figure 3The embodiment of the present application provides a terminal 300, comprising: a processor 301, a communications interface 302, a memory 303 and a communications bus 304, wherein the processor 301, the communications interface 302 and the memory 303 complete mutual communication through the communications bus 304. The processor 301 can call logical instructions in the memory 303 to execute the following method, comprising: obtaining similarity of a target application icon and each sample application icon in a sample application icon library based on the target application, thereby obtaining a plurality of similarities; obtaining one or more sub-sample application icon libraries based on all similarity rankings and the sample application icon library, and obtaining a sub-similarity of the target application icon and each sample application icon in the one or more sub-sample application icon libraries respectively, thereby obtaining one or more sub-similarities; and identifying whether the target application is a fake application based on the plurality of similarities and the one or more sub-similarities.

[0093] The terminal structure block diagram shown in the embodiment of the present application does not constitute a limitation on the terminal 300, and the terminal 300 can comprise more or fewer components than shown, or combine certain components, or adopt different component arrangements.

[0094] The embodiment of the present application discloses a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer can execute the method provided by each method embodiment, for example, comprising: obtaining similarity of a target application icon and each sample application icon in a sample application icon library based on the target application, thereby obtaining a plurality of similarities; obtaining one or more sub-sample application icon libraries based on all similarity rankings and the sample application icon library, and obtaining a sub-similarity of the target application icon and each sample application icon in the one or more sub-sample application icon libraries respectively, thereby obtaining one or more sub-similarities; and identifying whether the target application is a fake application based on the plurality of similarities and the one or more sub-similarities.

[0095] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying a counterfeit application, the method comprising: The method comprises the following steps: Based on the target application, the similarity between the target application icon and each sample application icon in the sample application icon library is obtained, thereby obtaining a plurality of similarities; Based on the similarity ranking and the sample application icon library, one or more sub-sample application icon libraries are obtained, and the sub-similarity between the target application icon and each sample application icon in the one or more sub-sample application icon libraries is obtained, thereby obtaining one or more sub-similarities; Based on the plurality of similarities and the one or more sub-similarities, it is determined whether the target application is a counterfeit application; The method comprises the following steps: Based on the similarity ranking, the first n similarities are selected to form a first sub-sample application icon library, and the first sub-similarity between the target application icon and each sample application icon in the first sub-sample application icon library is obtained; and the first sub-similarity between the target application icon and each sample application icon in the first sub-sample application icon library is calculated using a first preset algorithm; Based on the first sub-similarity ranking, the first n2 sub-similarities are selected to form a second sub-sample application icon library, and the second sub-similarity between the target application icon and each sample application icon in the second sub-sample application icon library is obtained; and the second sub-similarity between the target application icon and each sample application icon in the second sub-sample application icon library is calculated using a second preset algorithm; Until all the m-1th sub-similarity rankings are based on, the top n m m-1th sub-similarity corresponding to the sample application icon is applied to form the mth sub-sample application icon library, and the mth sub-similarity of the target application icon and each sample application icon in the mth sub-sample application icon library is obtained; the mth sub-similarity of the target application icon and each sample application icon in the mth sub-sample application icon library is calculated and obtained by using the mth preset algorithm.

2. The method of claim 1, wherein, The method comprises the following steps: Based on the target application icon, a target feature vector is obtained; Based on the sample application icon library, a sample feature vector corresponding to each sample application icon is obtained to form a sample feature vector library; The target feature vector and each sample feature vector in the sample feature vector library are subjected to similarity calculation to obtain the similarity between the target application icon and each sample application icon in the sample application icon library, thereby obtaining a plurality of similarities.

3. The method of claim 2, wherein, The method comprises the following steps: The target application icon is restored to a pixel point to obtain a target vector matrix corresponding to the target application icon; The target vector matrix is reduced in dimension to obtain a target feature vector.

4. The method of claim 2, wherein, The method comprises the following steps: Each sample application icon in the sample application icon library is restored to a pixel point to obtain a sample vector matrix corresponding to each sample application icon; All sample vector matrices are reduced in dimension to obtain a sample feature vector corresponding to each sample vector matrix; All sample feature vectors are combined to form a sample feature vector library.

5. The method according to any one of claims 1 to 4, characterized in that, The identifying whether the target application is a fake application based on the plurality of similarities and the one or more sub-similarities comprises: performing weighted summation on the similarity, the first sub-similarity, the second sub-similarity, and the mth sub-similarity corresponding to each sample application icon in the mth sample application icon library, respectively, to obtain an application similarity between a sample application corresponding to each sample application icon and the target application, thereby obtaining a plurality of application similarities; obtaining a highest application similarity in the plurality of application similarities, and if the highest application similarity is greater than or equal to a preset threshold, the target application is a fake application of a sample application corresponding to the highest application similarity.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the method of any one of claims 1 to 5.

7. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor, when executing the computer program, implements the method of any one of claims 1 to 5.

Images