Application icon similarity detection method and device, equipment and storage medium

Abstract

The invention discloses an application icon similarity detection method and device, equipment and a storage medium. According to the method, the hash feature value of the to-be-detected application icon is segmented to obtain the multiple segments of first feature values, then the multiple segments of second feature values corresponding to the standard hash feature value of the standard application icon are obtained, and then feature value matching is conducted on the multiple segments of first feature values and the multiple segments of second feature values according to the segmented indexing mode. And carrying out similarity detection on the to-be-detected application icon and the standard application icon according to a matching result. Compared with the prior art that the Hamming distance between the to-be-detected application icon and the standard application icon needs to be calculated, the Hash feature value of the to-be-detected application icon and the standard Hash feature value of the standard application icon are segmented; and similarity detection is carried out according to a matching result between the multiple segments of first feature values and the multiple segments of second feature values, so that similarity detection is simply and effectively carried out on the application icons.

Description

Technical Field

[0001] The present invention relates to the field of application icon technology, and in particular to a method, device, equipment and storage medium for detecting similarity of application icons. Background Art

[0002] With the popularity of applications, more and more pirated applications have appeared on the market, which are used to confuse users and gain profits. In order to promptly discover some pirated similar applications on the market, similarity software is often used to identify whether there are similar applications, and users are alerted to make reasonable choices by informing them in advance or performing security interception. The current method of similarity judgment is to perform similarity retrieval through application names or icons. The method of similarity retrieval is to determine whether they are similar by calculating the Hamming distance between icons. If the number of icons is large, the calculation process will be more complicated. Therefore, how to simply and effectively perform similarity detection on application icons has become an urgent problem to be solved.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and storage medium for similarity detection of application icons, aiming to solve the technical problem of how to simply and effectively perform similarity detection on application icons.

[0005] To achieve the above object, the present invention provides a method for detecting similarity of application icons, the method comprising the following steps:

[0006] Segmenting the hash feature value of the application icon to be detected to obtain multiple segments of first feature values;

[0007] Obtain multiple segments of second feature values ​​corresponding to the standard hash feature value of the standard application icon;

[0008] Performing feature value matching on the multiple segments of first feature values ​​and the multiple segments of second feature values ​​in a segmented index manner;

[0009] A similarity check is performed on the application icon to be detected and the standard application icon according to the matching result.

[0010] Optionally, the step of segmenting the hash feature value of the application icon to be detected to obtain multiple segments of first feature values ​​specifically includes:

[0011] Obtaining a hash feature value corresponding to the application icon to be detected;

[0012] Determine the number of segments corresponding to the hash feature value;

[0013] The hash characteristic value is segmented according to the segment number to obtain a first characteristic value after multiple segments.

[0014] Optionally, the step of obtaining a hash feature value corresponding to the application icon to be detected specifically includes:

[0015] Determine, by a preset static analysis tool, a preset icon file set corresponding to an application icon in a preset database, wherein the application icons in the preset database include: the application icon to be detected and a standard application icon;

[0016] Determine a preset hash feature value set corresponding to the preset icon file set by using a simhash algorithm;

[0017] A hash feature value corresponding to the application icon to be detected is selected from the preset hash feature value set.

[0018] Optionally, the step of determining the number of segments corresponding to the hash feature value specifically includes:

[0019] Determine a preset bit set corresponding to all preset hash feature values ​​in the preset hash feature value set;

[0020] Selecting the number of bits corresponding to the hash characteristic value from the preset number of bits set;

[0021] Determine the number of paragraph digits according to each preset number of digits in the preset number of digits set and the number of digits;

[0022] The number of segments corresponding to the hash feature value is determined according to the number of paragraph bits.

[0023] Optionally, the step of determining the number of segments corresponding to the hash feature value specifically includes:

[0024] Obtain a set of preset icon sizes corresponding to all preset icon files in the preset icon file set;

[0025] Selecting an icon size corresponding to the application icon to be detected from the preset icon size set;

[0026] Determine a segment size according to each preset icon size in the preset icon size set and the icon size;

[0027] The number of segments corresponding to the hash feature value is determined according to the segment size.

[0028] Optionally, the step of obtaining a plurality of second feature values ​​corresponding to the standard hash feature value of the standard application icon specifically includes:

[0029] Selecting a standard hash feature value corresponding to the standard application icon from the preset hash feature value set;

[0030] Determine the standard segment number according to the segment number and the standard hash feature value;

[0031] The standard hash characteristic value is segmented according to the standard segment number to obtain multiple segments of second characteristic values.

[0032] Optionally, the step of performing feature value matching on the multiple segments of first feature values ​​and the multiple segments of second feature values ​​in a segmented index manner specifically includes:

[0033] The plurality of first characteristic values ​​are stored in segments, and an index set is created for the first characteristic values ​​stored in each segment;

[0034] Feature value matching is performed on the target first feature value corresponding to each index in the index set and the multiple segments of second feature values ​​respectively.

[0035] Optionally, the step of performing feature value matching on the target first feature value corresponding to each index in the index set with the multiple segments of second feature values ​​respectively comprises:

[0036] When any equal feature value exists between the target first feature value corresponding to each index in the index set and the plurality of second feature values, it is determined that the feature value matching is successful;

[0037] When there is no equal feature value in the target first feature value corresponding to each index in the index set and the plurality of second feature values, it is determined that the feature value matching fails.

[0038] Optionally, the step of performing similarity detection on the application icon to be detected and the standard application icon according to the matching result specifically includes:

[0039] When the matching result is that the feature value matching passes, selecting a corresponding target standard application icon from the standard application icons;

[0040] Determine a set of Hamming distances between the application icon to be detected and the target standard application icon;

[0041] A similar application icon corresponding to the application icon to be detected is selected from the target standard application icons according to the Hamming distance set.

[0042] Optionally, the step of determining a set of Hamming distances between the application icon to be detected and the target standard application icon specifically includes:

[0043] Selecting a target standard hash feature value corresponding to the target standard application icon from the preset hash feature value set;

[0044] A Hamming distance set between the application icon to be detected and the target standard application icon is determined according to the hash feature value and the target standard hash feature value.

[0045] Optionally, the step of selecting a similar application icon corresponding to the application icon to be detected from the target standard application icons according to the Hamming distance set specifically includes:

[0046] Determine a minimum Hamming distance in the Hamming distance set, and select a target application icon corresponding to the minimum Hamming distance from the target standard application icons;

[0047] When the number of icons corresponding to the target application icon is greater than a preset number, obtaining a target application corresponding to the target application icon and an application to be detected corresponding to the application icon to be detected;

[0048] A similar application icon corresponding to the application icon to be detected is selected from the target application icon according to the target application and the application to be detected.

[0049] Optionally, the step of selecting a similar application icon corresponding to the application icon to be detected from the target application icon according to the target application and the application to be detected specifically includes:

[0050] Acquire the historical number of interactions between the target application and the user and the target process corresponding to the target application;

[0051] Obtaining the process to be detected corresponding to the application to be detected;

[0052] When the number of historical interactions is greater than a preset number, performing process matching on the target process and the process to be detected;

[0053] A similar application icon corresponding to the application icon to be detected is selected from the target application icon according to the process matching result.

[0054] In addition, to achieve the above-mentioned purpose, the present invention further provides a similarity detection device for application icons, the similarity detection device for application icons comprising:

[0055] A feature value segmentation module, used to segment the hash feature value of the application icon to be detected to obtain multiple segments of first feature values;

[0056] The feature value segmentation module is further used to obtain multiple segments of second feature values ​​corresponding to the standard hash feature value of the standard application icon;

[0057] A feature value matching module, used for performing feature value matching on the multiple segments of the first feature values ​​and the multiple segments of the second feature values ​​in a segmented index manner;

[0058] The similarity detection module is used to perform similarity detection on the application icon to be detected and the standard application icon according to the matching result.

[0059] Optionally, the feature value segmentation module is further used to obtain a hash feature value corresponding to the application icon to be detected; determine the number of segments corresponding to the hash feature value; and segment the hash feature value according to the number of segments to obtain multiple segments of first feature values.

[0060] Optionally, the feature value segmentation module is also used to determine a preset icon file set corresponding to the application icons in a preset database through a preset static analysis tool, wherein the application icons in the preset database include: the application icons to be detected and standard application icons; determine a preset hash feature value set corresponding to the preset icon file set through a simhash algorithm; and select a hash feature value corresponding to the application icon to be detected from the preset hash feature value set.

[0061] Optionally, the feature value segmentation module is also used to determine a preset bit set corresponding to all preset hash feature values ​​in the preset hash feature value set; select the number of bits corresponding to the hash feature value from the preset bit set; determine the number of paragraph bits according to each preset bit number in the preset bit set and the number of bits; determine the number of segment segments corresponding to the hash feature value according to the paragraph bit number.

[0062] Optionally, the feature value segmentation module is also used to obtain a preset icon size set corresponding to all preset icon files in the preset icon file set; select an icon size corresponding to the application icon to be detected from the preset icon size set; determine a segment size based on each preset icon size in the preset icon size set and the icon size; and determine the number of segments corresponding to the hash feature value based on the segment size.

[0063] Optionally, the feature value segmentation module is also used to select the standard hash feature value corresponding to the standard application icon from the preset hash feature value set; determine the number of standard segmentation segments according to the number of segmentation segments and the standard hash feature value; segment the standard hash feature value according to the standard number of segmentation segments to obtain multiple segments of second feature values.

[0064] In addition, to achieve the above-mentioned purpose, the present invention also proposes a similarity detection device for application icons, the similarity detection device for application icons comprising: a memory, a processor, and a similarity detection program for application icons stored in the memory and executable on the processor, the similarity detection program for application icons being configured to implement the steps of the similarity detection method for application icons as described above.

[0065] In addition, to achieve the above objectives, the present invention also proposes a storage medium, on which a similarity detection program for application icons is stored, and when the similarity detection program for application icons is executed by a processor, the steps of the similarity detection method for application icons as described above are implemented.

[0066] The present invention obtains multiple first feature values ​​by segmenting the hash feature value of the application icon to be detected, and then obtains multiple second feature values ​​corresponding to the standard hash feature value of the standard application icon, and then matches the feature values ​​of the multiple first feature values ​​and the multiple second feature values ​​in a segmented indexing manner, and then performs similarity detection on the application icon to be detected and the standard application icon according to the matching results. Compared with the existing method that requires calculating the Hamming distance between the application icon to be detected and the standard application icon, the above method of the present invention segments the hash feature value of the application icon to be detected and the standard hash feature value of the standard application icon respectively, and performs similarity detection based on the matching results between the multiple first feature values ​​and the multiple second feature values, thereby simply and effectively performing similarity detection on the application icons and improving the efficiency of similarity detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a structural schematic diagram of a similarity detection device for application icons of a hardware operating environment involved in an embodiment of the present invention;

[0068] Figure 2 It is a flow chart of a first embodiment of a similarity detection method for application icons of the present invention;

[0069] Figure 3 It is a flow chart of a second embodiment of a similarity detection method for application icons of the present invention;

[0070] Figure 4 It is a flow chart of a third embodiment of a similarity detection method for application icons of the present invention;

[0071] Figure 5 It is a structural block diagram of the first embodiment of the similarity detection device for application icons of the present invention.

[0072] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0073] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0074] Reference Figure 1 , Figure 1 It is a schematic diagram of the structure of a similarity detection device for application icons in a hardware operating environment involved in an embodiment of the present invention.

[0075] like Figure 1 As shown, the similarity detection device for the application icon may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0076] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the device for detecting similarity of application icons, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0077] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a similarity detection program for application icons.

[0078] exist Figure 1 In the application icon similarity detection device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the application icon similarity detection device of the present invention can be set in the application icon similarity detection device, and the application icon similarity detection device calls the application icon similarity detection program stored in the memory 1005 through the processor 1001, and executes the application icon similarity detection method provided by the embodiment of the present invention.

[0079] Based on the above-mentioned similarity detection device for application icons, an embodiment of the present invention provides a similarity detection method for application icons, referring to Figure 2 , Figure 2 It is a flow chart of the first embodiment of the similarity detection method of application icons of the present invention.

[0080] In this embodiment, the similarity detection method of application icons includes the following steps:

[0081] Step S10: segmenting the hash feature value of the application icon to be detected to obtain multiple segments of first feature values;

[0082] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a mobile phone, a tablet computer, a personal computer, etc., or an electronic device or an application icon similarity detection device that can realize the above functions. The following takes the application icon similarity detection device as an example to illustrate this embodiment and the following embodiments.

[0083] It is understandable that the application icon to be detected refers to an application icon that needs to be tested for similarity, that is, it is necessary to determine whether there is an application icon similar to the application icon to be detected.

[0084] It should be understood that the hash feature value is the simhash feature value, and the hash feature value corresponding to the application icon to be detected can be determined by the simhash algorithm. Since the hash feature value is a binary value and has a long number of bits, the present embodiment can segment the hash feature value to obtain multiple segments of the first feature value. For example, when the hash feature value is 64 bits, it can be divided into 4 segments, each of which includes 16 bits, or it can be divided into 8 segments, each of which includes 8 bits. This embodiment does not impose specific restrictions on this.

[0085] Step S20: Acquire multiple second feature values ​​corresponding to the standard hash feature value of the standard application icon;

[0086] It should be noted that the standard application icon refers to an application icon that needs to be tested for similarity with the application icon to be detected, that is, it is necessary to determine whether there is an application icon in the standard application icons that has a large similarity with the application icon to be detected.

[0087] It can be understood that for the standard hash feature value of the standard application icon, the standard hash feature value can also be segmented. In this embodiment, the number of segments of the standard hash feature value segmentation can be set to be consistent with the number of segments of the above-mentioned hash feature value segmentation. Since for the same device, such as a mobile phone, computer, etc., the number of bits of the hash feature value of the application icon is basically the same, the number of segments of all application icon segments can be set to the same value, and the number of bits of each segment is also the same.

[0088] Step S30: performing feature value matching on the multiple segments of first feature values ​​and the multiple segments of second feature values ​​in a segmented indexing manner;

[0089] It should be understood that after the hash feature value of the application icon to be detected is segmented, an index can be created for each segment of the first feature value, for example, the index of the first segment of the first feature value is set to 1, and the index of the second segment of the first feature value is set to 2.

[0090] In a specific implementation, feature value matching can be performed on multiple segments of first feature values ​​and multiple segments of second feature values ​​in segments. Specifically, each segment of first feature value can be matched with each segment of second feature value, and the existence of parts of multiple segments of first feature values ​​that are not matched with feature values ​​can be avoided according to the segment indexing method. For example, the first feature value of the first segment is A, the first feature value of the second segment is B, the first feature value of the third segment is C, and the first feature value of the fourth segment is D. The second feature value of the first segment is a, the second feature value of the second segment is b, the second feature value of the third segment is c, and the second feature value of the fourth segment is d. A can be matched with a, b, c, and d respectively, B can be matched with a, b, c, and d respectively, C can be matched with a, b, c, and d respectively, and D can be matched with a, b, c, and d respectively.

[0091] Furthermore, in order to effectively perform feature value matching, in the present embodiment, the step S30 includes: storing the multiple segments of first feature values ​​in segments, and creating an index set for the first feature values ​​stored in each segment; and performing feature value matching on the target first feature value corresponding to each index in the index set with the multiple segments of second feature values, respectively.

[0092] It can be understood that this embodiment can store multiple segments of first feature values ​​and create an index for the first feature values ​​stored in each segment. The first feature values ​​of all segments constitute an index set. For example, the application icon to be detected is A, and the index of the corresponding first segment first feature value is set to A1, the index of the second segment first feature value is set to A2, the index of the third segment first feature value is set to A3, and the index of the fourth segment first feature value is set to A4. The index set corresponding to the application icon A to be detected is {A1, A2, A3, A4}.

[0093] It should be understood that the target first eigenvalue corresponding to each index in the index set can be matched with multiple segments of second eigenvalues ​​respectively. Specifically, the target first eigenvalue corresponding to index A1, that is, the first segment first eigenvalue mentioned above, can be determined first, and then the first segment first eigenvalue can be matched with multiple segments of second eigenvalues ​​respectively. It is also necessary to match the second segment first eigenvalue corresponding to index A2 with multiple segments of second eigenvalues ​​respectively, and it is also necessary to match the third segment first eigenvalue corresponding to index A3 with multiple segments of third eigenvalues ​​respectively, and so on.

[0094] Further, in order to determine whether the feature value matching is successful, in the present embodiment, the step of performing feature value matching on the target first feature value corresponding to each index in the index set and the multiple segments of the second feature value, respectively, specifically includes: when there is any equal feature value among the target first feature value corresponding to each index in the index set and the multiple segments of the second feature value, it is determined that the feature value matching is successful; when there is no equal feature value among the target first feature value corresponding to each index in the index set and the multiple segments of the second feature value, it is determined that the feature value matching fails.

[0095] In a specific implementation, feature value matching can be performed on the target first feature value and multiple segments of second feature values ​​corresponding to each index in the index set. For example, the multiple segments of second feature values ​​include a, b, c, and d. The first segment first feature value corresponding to the above-mentioned index A1 can be matched with a, b, c, and d respectively, the second segment first feature value corresponding to index A2 can be matched with a, b, c, and d respectively, the third segment first feature value corresponding to index A3 can be matched with a, b, c, and d respectively, and the fourth segment first feature value corresponding to index A4 can be matched with a, b, c, and d respectively. If there is any equal hash feature value, the feature value matching is determined to be successful. For example, when the first segment first feature value corresponding to index A1 is equal to b or the second segment first feature value corresponding to index A2 is equal to a, the feature value matching is determined to be successful. If there is no equal hash feature value, the feature value matching is determined to be unsuccessful.

[0096] Step S40: performing similarity detection on the application icon to be detected and the standard application icon according to the matching result.

[0097] It can be understood that a similarity check can be performed on the application icon to be detected and the standard application icon based on the matching results, that is, it is determined whether there is an application icon similar to the application icon to be detected among the standard application icons. Specifically, all standard application icons whose matching results are feature value matching can be used as similar application icons of the application icon to be detected. The standard application icons that pass the feature value matching can also be screened, and the screened standard application icons can be used as similar application icons of the application icon to be detected.

[0098] This embodiment obtains multiple first feature values ​​by segmenting the hash feature value of the application icon to be detected, and then obtains multiple second feature values ​​corresponding to the standard hash feature value of the standard application icon, and then matches the feature values ​​of the multiple first feature values ​​and the multiple second feature values ​​in a segmented indexing manner, and then performs similarity detection on the application icon to be detected and the standard application icon based on the matching results. Compared with the existing method that requires calculating the Hamming distance between the application icon to be detected and the standard application icon, the above method of this embodiment segments the hash feature value of the application icon to be detected and the standard hash feature value of the standard application icon respectively, and performs similarity detection based on the matching results between the multiple first feature values ​​and the multiple second feature values, thereby simply and effectively performing similarity detection on the application icons and improving the efficiency of similarity detection.

[0099] refer to Figure 3 , Figure 3 It is a flow chart of the second embodiment of the similarity detection method of application icons of the present invention.

[0100] Based on the above first embodiment, in this embodiment, step S10 includes:

[0101] Step S101: Obtaining a hash feature value corresponding to the application icon to be detected;

[0102] Furthermore, in order to obtain the hash feature value corresponding to the application icon to be detected, in this embodiment, the step S101 includes: determining a preset icon file set corresponding to the application icon in a preset database through a preset static analysis tool, the application icons in the preset database including: the application icon to be detected and the standard application icon; determining a preset hash feature value set corresponding to the preset icon file set through a simhash algorithm; and selecting the hash feature value corresponding to the application icon to be detected from the preset hash feature value set.

[0103] It should be noted that the preset static analysis tool refers to a pre-set tool for converting an application icon into an icon file in png format.

[0104] It is understandable that the application icons in the preset database may include the above-mentioned application icons to be detected and standard application icons, and the preset icon files corresponding to each application icon in the preset database can be determined by a preset static analysis tool to form a preset icon file set.

[0105] It should be understood that the preset hash feature value corresponding to each preset icon file can be determined by the simhash algorithm to form a preset hash feature value set, and the hash feature value corresponding to the application icon to be detected is selected from the preset hash feature value set.

[0106] Step S102: Determine the number of segments corresponding to the hash feature value;

[0107] It is understandable that the number of segmentation segments refers to the number of segments into which the hash feature value is segmented. For example, when the number of segmentation segments is 4, the obtained hash feature value after segmentation has 4 segments.

[0108] Furthermore, in order to accurately determine the number of segmented segments, in this embodiment, the step S101 includes: determining a preset bit set corresponding to all preset hash feature values ​​in the preset hash feature value set; selecting the number of bits corresponding to the hash feature value from the preset bit set; determining the number of paragraph bit bits according to each preset bit number in the preset bit set and the bit number; determining the number of segmented segments corresponding to the hash feature value according to the paragraph bit number.

[0109] It should be noted that the preset bit number set is a set consisting of preset bit numbers corresponding to all preset hash feature values ​​in the preset hash feature value set, and the bit number corresponding to the hash feature value of the application icon to be detected can be selected from the preset bit number set.

[0110] It is understandable that the number of paragraph digits can be determined based on all preset digits and the number of digits corresponding to the application icon to be detected. Specifically, the average value of all preset digits can be determined, and then the average value can be compared with the number of digits corresponding to the application icon to be detected. If the two are the same, the number of paragraph digits can be set to a factor of the above digits. If the two are different, the number of paragraph digits can be set to a common factor of the above average value and the number of digits.

[0111] In a specific implementation, after obtaining the number of paragraph digits, the hash feature value may be divided by the number of paragraph digits to obtain the number of segment segments.

[0112] Furthermore, in order to accurately determine the number of segments, in this embodiment, the step S101 includes: obtaining a preset icon size set corresponding to all preset icon files in the preset icon file set; selecting an icon size corresponding to the application icon to be detected from the preset icon size set; determining a segment size based on each preset icon size in the preset icon size set and the icon size; and determining the number of segments corresponding to the hash feature value based on the segment size.

[0113] It should be noted that the preset icon size set is a set of preset icon sizes corresponding to all preset icon files in the preset icon file set, and the corresponding icon size of the application icon to be detected can be selected from the preset icon size set.

[0114] It is understandable that the segment size can be determined based on all preset icon sizes and the icon size corresponding to the application icon to be detected. Specifically, the average size of all preset icon sizes can be determined, and then the average size can be compared with the icon size corresponding to the application icon to be detected. If the two are the same, the segment size can be set as a factor of the above icon size. If the two are different, the segment size can be set as a common factor of the above average size and the icon size.

[0115] In a specific implementation, after obtaining the segment size, the icon size may be divided by the segment size to obtain the number of segments.

[0116] Step S103: segmenting the hash feature value according to the segment number to obtain multiple segments of first feature values.

[0117] It should be understood that the hash feature value can be evenly divided according to the number of segments. For example, if the number of segments is 4 and the number of bits of the hash feature value is 64, the hash feature value can be evenly divided into 4 parts, each part including 16 bits.

[0118] Further, in order to determine multiple segments of second characteristic values, in this embodiment, the step S20 includes: selecting a standard hash characteristic value corresponding to the standard application icon from the preset hash characteristic value set; determining the number of standard segment segments according to the number of segment segments and the standard hash characteristic value; segmenting the standard hash characteristic value according to the standard number of segment segments to obtain multiple segments of second characteristic values.

[0119] It is understandable that the standard hash feature value refers to the hash feature value corresponding to the standard application icon, which can be selected from a preset hash feature value set.

[0120] It should be understood that the standard segment number refers to the number of segments for segmenting the standard hash eigenvalue. Specifically, we can first determine whether the segment number is a factor of the standard number of bits corresponding to the standard hash eigenvalue. If so, the standard segment number of bits is the above-mentioned segment number. If not, we can first determine the number of bits of each segment in the multiple-segment first eigenvalues, and then divide the standard hash eigenvalue according to the number of bits of each segment. For example, the number of bits of each segment in the multiple-segment first eigenvalues ​​is 16 bits, and the standard number of bits corresponding to the standard hash eigenvalue is 63 bits. Then, a second eigenvalue with three segments of 16 bits and one segment of 15 bits can be obtained. If the standard number of bits corresponding to the standard hash eigenvalue is 32 bits, then a second eigenvalue with two segments of 16 bits can be obtained.

[0121] This embodiment obtains the hash feature value corresponding to the application icon to be detected, then determines the number of segments corresponding to the hash feature value, and then segments the hash feature value according to the number of segments to obtain multiple segments of the first feature value. This embodiment segments the hash feature value according to the number of segments to obtain multiple segments of the first feature value, and can segment the hash feature value, thereby improving the efficiency of subsequent similarity detection of application icons.

[0122] refer to Figure 4 , Figure 4 It is a flow chart of the third embodiment of the similarity detection method of application icons of the present invention.

[0123] Based on the above embodiments, in this embodiment, step S40 includes:

[0124] Step S401: when the matching result is that the feature value matching passes, selecting a corresponding target standard application icon from the standard application icons;

[0125] It can be understood that when the matching result is that the feature value match is passed, the corresponding target standard application icon can be selected from the standard application icons. For example, when the first feature value of the first segment corresponding to index A1 is equal to b or the first feature value of the second segment corresponding to index A2 is equal to a, it is determined that the feature value match is passed. At this time, the standard application icon including multiple segments of second feature values ​​of a, b, c, and d is the target standard application icon. When the first feature value of the first segment corresponding to index A1 is equal to e, the standard application icon including the second feature value of e is the target standard application icon.

[0126] Step S402: determining a set of Hamming distances between the application icon to be detected and the target standard application icon;

[0127] It should be understood that the Hamming distance set refers to a set consisting of the Hamming distances between the application icon to be detected and each target standard application icon.

[0128] Further, in order to accurately determine the Hamming distance set, in this embodiment, the step S402 includes: selecting the target standard hash feature value corresponding to the target standard application icon from the preset hash feature value set; determining the Hamming distance set between the application icon to be detected and the target standard application icon based on the hash feature value and the target standard hash feature value.

[0129] It is understandable that the target standard hash feature value refers to the hash feature value corresponding to the target standard application icon, which can be specifically selected from a preset hash feature value set.

[0130] In a specific implementation, the Hamming distance between the application icon to be detected and each target standard application icon can be determined according to the hash feature value and the target standard hash feature value, and a Hamming distance set can be formed. The specific calculation method can refer to the existing technology, and this embodiment will not elaborate on this.

[0131] Step S403: selecting a similar application icon corresponding to the application icon to be detected from the target standard application icons according to the Hamming distance set.

[0132] It should be understood that similar application icons refer to application icons that are substantially consistent with the application icon to be detected. Similar application icons can be determined based on a Hamming distance set, and specifically, an icon corresponding to the minimum value in the Hamming distance set can be used as a similar application icon.

[0133] Furthermore, in order to effectively select similar application icons corresponding to the application icon to be detected, in the present embodiment, the step S403 includes: determining the minimum Hamming distance in the Hamming distance set, and selecting the target application icon corresponding to the minimum Hamming distance from the target standard application icons; when the number of icons corresponding to the target application icon is greater than a preset number, obtaining the target application corresponding to the target application icon and the application to be detected corresponding to the application icon to be detected; selecting a similar application icon corresponding to the application icon to be detected from the target application icon according to the target application and the application to be detected.

[0134] It should be noted that the minimum Hamming distance refers to the minimum value in the Hamming distance set, and the target application icon refers to the application icon corresponding to the minimum Hamming distance in the target standard application icons.

[0135] It is understandable that the preset number in this embodiment can be set to 1. When the number of icons corresponding to the target application icon is 1, the target application icon can be directly used as the similar application icon corresponding to the application icon to be detected. When the number of icons corresponding to the target application icon is greater than 1, the target application corresponding to the target application icon and the application to be detected corresponding to the application icon to be detected can be obtained, and the similar application icon corresponding to the application icon to be detected is determined based on the target application and the application to be detected, so as to further screen the target application icon and obtain the application icon that is most similar to the application icon to be detected.

[0136] Furthermore, in order to filter similar application icons corresponding to the application icon to be detected from the target application icon, in this embodiment, the step of selecting similar application icons corresponding to the application icon to be detected from the target application icon based on the target application and the application to be detected specifically includes: obtaining the historical number of interactions between the target application and the user and the target process corresponding to the target application; obtaining the process to be detected corresponding to the application to be detected; when the historical number of interactions is greater than a preset number, performing process matching on the target process and the process to be detected; and selecting similar application icons corresponding to the application icon to be detected from the target application icon based on the process matching result.

[0137] It should be understood that the historical number of interactions refers to the number of interactions between the target application corresponding to the target application icon and the user in the historical time period, and the historical time period can be set to two days, three days, etc., and this embodiment does not impose specific restrictions on this. The target process refers to the process of the target application during operation, and the process to be detected refers to the process of the application to be detected during operation.

[0138] In a specific implementation, the preset number of times can be set to 2 times, 3 times, etc. When the number of historical interactions is greater than the preset number of times, it means that the user has used the target application more times. At this time, the target process and the process to be detected can be matched, and specifically, it can be determined whether the process type and process number of the target process and the process to be detected match. When the process matching is successful, it means that the user may use the target application icon that has passed the process matching as the application icon to be detected. At this time, the target application icon can be used as the similar application icon corresponding to the application icon to be detected.

[0139] In this embodiment, when the matching result is that the feature value matching is passed, the corresponding target standard application icon is selected from the standard application icons, and then the Hamming distance set between the application icon to be detected and the target standard application icon is determined, and then the similar application icon corresponding to the application icon to be detected is selected from the target standard application icon according to the Hamming distance set. In this embodiment, when the matching result is that the feature value matching is passed, the similar application icon corresponding to the application icon to be detected is selected from the target standard application icon according to the Hamming distance set, so as to further screen the target standard application icon, obtain the similar application icon corresponding to the application icon to be detected, and improve the accuracy of obtaining the similar application icon.

[0140] Reference Figure 5 , Figure 5 It is a structural block diagram of the first embodiment of the similarity detection device for application icons of the present invention.

[0141] like Figure 5 As shown, the similarity detection device for application icons proposed in the embodiment of the present invention includes:

[0142] The feature value segmentation module 10 is used to segment the hash feature value of the application icon to be detected to obtain multiple segments of first feature values;

[0143] The feature value segmentation module 10 is further used to obtain multiple segments of second feature values ​​corresponding to the standard hash feature value of the standard application icon;

[0144] A feature value matching module 20, configured to perform feature value matching on the plurality of segments of first feature values ​​and the plurality of segments of second feature values ​​in a segmented indexing manner;

[0145] The similarity detection module 30 is used to perform similarity detection on the application icon to be detected and the standard application icon according to the matching result.

[0146] This embodiment obtains multiple first feature values ​​by segmenting the hash feature value of the application icon to be detected, and then obtains multiple second feature values ​​corresponding to the standard hash feature value of the standard application icon, and then matches the feature values ​​of the multiple first feature values ​​and the multiple second feature values ​​in a segmented indexing manner, and then performs similarity detection on the application icon to be detected and the standard application icon based on the matching results. Compared with the existing method that requires calculating the Hamming distance between the application icon to be detected and the standard application icon, the above method of this embodiment segments the hash feature value of the application icon to be detected and the standard hash feature value of the standard application icon respectively, and performs similarity detection based on the matching results between the multiple first feature values ​​and the multiple second feature values, thereby simply and effectively performing similarity detection on the application icons and improving the efficiency of similarity detection.

[0147] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0148] In addition, for technical details that are not described in detail in this embodiment, reference can be made to the similarity detection method for application icons provided in any embodiment of the present invention, and will not be repeated here.

[0149] Based on the first embodiment of the device for detecting similarity of application icons of the present invention, a second embodiment of the device for detecting similarity of application icons of the present invention is proposed.

[0150] In this embodiment, the feature value segmentation module 10 is further used to obtain the hash feature value corresponding to the application icon to be detected; determine the number of segments corresponding to the hash feature value; and segment the hash feature value according to the number of segments to obtain multiple segments of first feature values.

[0151] Furthermore, the feature value segmentation module 10 is also used to determine a preset icon file set corresponding to the application icons in a preset database through a preset static analysis tool, wherein the application icons in the preset database include: the application icons to be detected and standard application icons; determine a preset hash feature value set corresponding to the preset icon file set through a simhash algorithm; and select a hash feature value corresponding to the application icon to be detected from the preset hash feature value set.

[0152] Furthermore, the feature value segmentation module 10 is also used to determine a preset bit set corresponding to all preset hash feature values ​​in the preset hash feature value set; select the number of bits corresponding to the hash feature value from the preset bit set; determine the number of paragraph bits according to each preset bit set and the number of bits; determine the number of segment segments corresponding to the hash feature value according to the paragraph bit set.

[0153] Furthermore, the feature value segmentation module 10 is also used to obtain a preset icon size set corresponding to all preset icon files in the preset icon file set; select an icon size corresponding to the application icon to be detected from the preset icon size set; determine a segment size based on each preset icon size in the preset icon size set and the icon size; and determine the number of segments corresponding to the hash feature value based on the segment size.

[0154] Furthermore, the feature value segmentation module 10 is also used to select a standard hash feature value corresponding to the standard application icon from the preset hash feature value set; determine the number of standard segmentation segments according to the number of segmentation segments and the standard hash feature value; and segment the standard hash feature value according to the standard number of segmentation segments to obtain multiple segments of second feature values.

[0155] Furthermore, the feature value matching module 20 is also used to store the multiple segments of first feature values ​​in segments, and create an index set for the first feature values ​​stored in each segment; and perform feature value matching on the target first feature value corresponding to each index in the index set with the multiple segments of second feature values.

[0156] Furthermore, the feature value matching module 20 is also used to determine that the feature value matching is successful when there is any equal feature value among the target first feature value corresponding to each index in the index set and the multiple second feature values; and to determine that the feature value matching fails when there is no equal feature value among the target first feature value corresponding to each index in the index set and the multiple second feature values.

[0157] Furthermore, the similarity detection module 30 is also used to select a corresponding target standard application icon from the standard application icons when the matching result is a feature value match passed; determine a Hamming distance set between the application icon to be detected and the target standard application icon; and select a similar application icon corresponding to the application icon to be detected from the target standard application icon according to the Hamming distance set.

[0158] Furthermore, the similarity detection module 30 is also used to select a target standard hash feature value corresponding to the target standard application icon from the preset hash feature value set; and determine a Hamming distance set between the application icon to be detected and the target standard application icon based on the hash feature value and the target standard hash feature value.

[0159] Furthermore, the similarity detection module 30 is also used to determine the minimum Hamming distance in the Hamming distance set, and select the target application icon corresponding to the minimum Hamming distance from the target standard application icons; when the number of icons corresponding to the target application icon is greater than a preset number, obtain the target application corresponding to the target application icon and the application to be detected corresponding to the application icon to be detected; select a similar application icon corresponding to the application icon to be detected from the target application icon based on the target application and the application to be detected.

[0160] Furthermore, the similarity detection module 30 is also used to obtain the historical number of interactions between the target application and the user and the target process corresponding to the target application; obtain the process to be detected corresponding to the application to be detected; when the historical number of interactions is greater than a preset number, perform process matching on the target process and the process to be detected; and select a similar application icon corresponding to the application icon to be detected from the target application icon according to the process matching result.

[0161] Other embodiments or specific implementations of the device for detecting similarity of application icons of the present invention may refer to the above-mentioned method embodiments, which will not be described in detail here.

[0162] In addition, an embodiment of the present invention further proposes a storage medium, on which a similarity detection program for application icons is stored. When the similarity detection program for application icons is executed by a processor, the steps of the similarity detection method for application icons as described above are implemented.

[0163] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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 system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0164] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0165] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0166] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0167] The present invention discloses A1, a similarity detection method for application icons, the similarity detection method for application icons comprising the following steps:

[0168] Segmenting the hash feature value of the application icon to be detected to obtain multiple segments of first feature values;

[0169] Obtain multiple segments of second feature values ​​corresponding to the standard hash feature value of the standard application icon;

[0170] Performing feature value matching on the multiple segments of first feature values ​​and the multiple segments of second feature values ​​in a segmented index manner;

[0171] A similarity check is performed on the application icon to be detected and the standard application icon according to the matching result.

[0172] A2. In the similarity detection method for application icons as described in A1, the step of segmenting the hash feature value of the application icon to be detected to obtain multiple segments of first feature values ​​specifically includes:

[0173] Obtaining a hash feature value corresponding to the application icon to be detected;

[0174] Determine the number of segments corresponding to the hash feature value;

[0175] The hash characteristic value is segmented according to the segment number to obtain multiple segments of first characteristic values.

[0176] A3. In the method for detecting similarity of application icons as described in A2, the step of obtaining the hash feature value corresponding to the application icon to be detected specifically comprises:

[0177] Determine, by a preset static analysis tool, a preset icon file set corresponding to an application icon in a preset database, wherein the application icons in the preset database include: the application icon to be detected and a standard application icon;

[0178] Determine a preset hash feature value set corresponding to the preset icon file set by using a simhash algorithm;

[0179] A hash feature value corresponding to the application icon to be detected is selected from the preset hash feature value set.

[0180] A4. In the method for detecting similarity of application icons as described in A3, the step of determining the number of segments corresponding to the hash feature value specifically comprises:

[0181] Determine a preset bit set corresponding to all preset hash feature values ​​in the preset hash feature value set;

[0182] Selecting the number of bits corresponding to the hash characteristic value from the preset number of bits set;

[0183] Determine the number of paragraph digits according to each preset number of digits in the preset number of digits set and the number of digits;

[0184] The number of segments corresponding to the hash feature value is determined according to the number of paragraph bits.

[0185] A5. In the method for detecting similarity of application icons as described in A3, the step of determining the number of segments corresponding to the hash feature value specifically comprises:

[0186] Obtain a set of preset icon sizes corresponding to all preset icon files in the preset icon file set;

[0187] Selecting an icon size corresponding to the application icon to be detected from the preset icon size set;

[0188] Determine a segment size according to each preset icon size in the preset icon size set and the icon size;

[0189] The number of segments corresponding to the hash feature value is determined according to the segment size.

[0190] A6. In the similarity detection method for application icons as described in A3, the step of obtaining multiple segments of second feature values ​​corresponding to the standard hash feature value of the standard application icon specifically includes:

[0191] Selecting a standard hash feature value corresponding to the standard application icon from the preset hash feature value set;

[0192] Determine the standard segment number according to the segment number and the standard hash feature value;

[0193] The standard hash characteristic value is segmented according to the standard segment number to obtain multiple segments of second characteristic values.

[0194] A7. In the similarity detection method for application icons as described in A3, the step of matching the feature values ​​of the multiple segments of first feature values ​​and the multiple segments of second feature values ​​in a segmented index manner specifically comprises:

[0195] The plurality of first characteristic values ​​are stored in segments, and an index set is created for the first characteristic values ​​stored in each segment;

[0196] Feature value matching is performed on the target first feature value corresponding to each index in the index set and the multiple segments of second feature values ​​respectively.

[0197] A8. In the similarity detection method for application icons as described in A7, the step of matching the target first feature value corresponding to each index in the index set with the multiple segments of second feature values ​​respectively comprises:

[0198] When any equal feature value exists between the target first feature value corresponding to each index in the index set and the plurality of second feature values, it is determined that the feature value matching is successful;

[0199] When there is no equal feature value in the target first feature value corresponding to each index in the index set and the plurality of second feature values, it is determined that the feature value matching fails.

[0200] A9. In the method for similarity detection of application icons as described in A8, the step of performing similarity detection on the application icon to be detected and the standard application icon according to the matching result specifically comprises:

[0201] When the matching result is that the feature value matching passes, selecting a corresponding target standard application icon from the standard application icons;

[0202] Determine a set of Hamming distances between the application icon to be detected and the target standard application icon;

[0203] A similar application icon corresponding to the application icon to be detected is selected from the target standard application icons according to the Hamming distance set.

[0204] A10. In the method for detecting similarity of application icons as described in A9, the step of determining a set of Hamming distances between the application icon to be detected and the target standard application icon specifically comprises:

[0205] Selecting a target standard hash feature value corresponding to the target standard application icon from the preset hash feature value set;

[0206] A Hamming distance set between the application icon to be detected and the target standard application icon is determined according to the hash feature value and the target standard hash feature value.

[0207] A11. In the method for detecting similarity of application icons as described in A9, the step of selecting a similar application icon corresponding to the application icon to be detected from the target standard application icon according to the Hamming distance set specifically comprises:

[0208] Determine a minimum Hamming distance in the Hamming distance set, and select a target application icon corresponding to the minimum Hamming distance from the target standard application icons;

[0209] When the number of icons corresponding to the target application icon is greater than a preset number, obtaining a target application corresponding to the target application icon and an application to be detected corresponding to the application icon to be detected;

[0210] A similar application icon corresponding to the application icon to be detected is selected from the target application icon according to the target application and the application to be detected.

[0211] A12. In the method for detecting similarity of application icons as described in A11, the step of selecting a similar application icon corresponding to the application icon to be detected from the target application icon according to the target application and the application to be detected specifically comprises:

[0212] Acquire the historical number of interactions between the target application and the user and the target process corresponding to the target application;

[0213] Obtaining the process to be detected corresponding to the application to be detected;

[0214] When the number of historical interactions is greater than a preset number, performing process matching on the target process and the process to be detected;

[0215] A similar application icon corresponding to the application icon to be detected is selected from the target application icon according to the process matching result.

[0216] The present invention also discloses B13, a similarity detection device for application icons, the similarity detection device for application icons comprising:

[0217] A feature value segmentation module, used to segment the hash feature value of the application icon to be detected to obtain multiple segments of first feature values;

[0218] The feature value segmentation module is further used to obtain multiple segments of second feature values ​​corresponding to the standard hash feature value of the standard application icon;

[0219] A feature value matching module, used for performing feature value matching on the multiple segments of the first feature values ​​and the multiple segments of the second feature values ​​in a segmented index manner;

[0220] The similarity detection module is used to perform similarity detection on the application icon to be detected and the standard application icon according to the matching result.

[0221] B14. In the similarity detection device for application icons as described in B13, the feature value segmentation module is further used to obtain a hash feature value corresponding to the application icon to be detected; determine the number of segments corresponding to the hash feature value; and segment the hash feature value according to the number of segments to obtain multiple segments of first feature values.

[0222] B15. The similarity detection device for application icons as described in B14, wherein the feature value segmentation module is further used to determine a preset icon file set corresponding to the application icons in a preset database through a preset static analysis tool, wherein the application icons in the preset database include: the application icons to be detected and standard application icons; determine a preset hash feature value set corresponding to the preset icon file set through a simhash algorithm; and select a hash feature value corresponding to the application icon to be detected from the preset hash feature value set.

[0223] B16. In the similarity detection device for application icons as described in B15, the feature value segmentation module is further used to determine a preset bit set corresponding to all preset hash feature values ​​in the preset hash feature value set; select the number of bits corresponding to the hash feature value from the preset bit set; determine the number of paragraph bits according to each preset bit number in the preset bit set and the number of bits; determine the number of segment segments corresponding to the hash feature value according to the paragraph bit number.

[0224] B17. In the device for detecting similarity of application icons as described in B15, the feature value segmentation module is further used to obtain a preset icon size set corresponding to all preset icon files in the preset icon file set; select an icon size corresponding to the application icon to be detected from the preset icon size set; determine a segment size according to each preset icon size in the preset icon size set and the icon size; and determine the number of segments corresponding to the hash feature value according to the segment size.

[0225] B18. In the similarity detection device for application icons as described in B15, the feature value segmentation module is further used to select the standard hash feature value corresponding to the standard application icon from the preset hash feature value set; determine the number of standard segmentations according to the number of segmentations and the standard hash feature value; and segment the standard hash feature value according to the standard number of segmentations to obtain multiple segments of second feature values.

[0226] The present invention also discloses C19, a similarity detection device for application icons, the device comprising: a memory, a processor, and a similarity detection program for application icons stored in the memory and executable on the processor, the similarity detection program for application icons being configured to implement the steps of the similarity detection method for application icons as described in any one of A1 to A12.

[0227] The present invention also discloses D20, a storage medium, on which a similarity detection program for application icons is stored, and when the similarity detection program for application icons is executed by a processor, the steps of the similarity detection method for application icons described in any one of A1 to A12 are implemented.

Claims

1. A method for detecting similarity of application icons, characterized in that: The similarity detection method for application icons comprises the following steps: Segmenting the hash feature value of the application icon to be detected to obtain multiple segments of first feature values; Obtain multiple second feature values ​​corresponding to the standard hash feature value of the standard application icon; Performing feature value matching on the multiple segments of first feature values ​​and the multiple segments of second feature values ​​in a segmented index manner; A similarity check is performed on the application icon to be detected and the standard application icon according to the matching result.

2. The method for detecting similarity of application icons according to claim 1, wherein: The step of segmenting the hash feature value of the application icon to be detected to obtain multiple segments of first feature values ​​specifically includes: Obtaining a hash feature value corresponding to the application icon to be detected; Determine the number of segments corresponding to the hash feature value; The hash characteristic value is segmented according to the number of segments to obtain multiple segments of first characteristic values.

3. The method for detecting similarity of application icons according to claim 2, wherein: The step of obtaining the hash feature value corresponding to the application icon to be detected specifically includes: Determine, by a preset static analysis tool, a preset icon file set corresponding to an application icon in a preset database, wherein the application icons in the preset database include: the application icon to be detected and a standard application icon; Determine the preset hash feature value set corresponding to the preset icon file set by using the simhash algorithm; A hash feature value corresponding to the application icon to be detected is selected from the preset hash feature value set.

4. The method for detecting similarity of application icons according to claim 3, wherein: The step of determining the number of segments corresponding to the hash feature value specifically includes: Determine a preset bit set corresponding to all preset hash feature values ​​in the preset hash feature value set; Selecting the number of bits corresponding to the hash characteristic value from the preset number of bits set; Determining the number of paragraphs according to each preset number of bits in the preset number of bits set and the number of bits; The number of segments corresponding to the hash feature value is determined according to the number of paragraph bits.

5. The method for detecting similarity of application icons according to claim 3, wherein: The step of determining the number of segments corresponding to the hash feature value specifically includes: Obtain a preset icon size set corresponding to all preset icon files in the preset icon file set; Selecting an icon size corresponding to the application icon to be detected from the preset icon size set; determining a segment size according to each preset icon size in the preset icon size set and the icon size; The number of segments corresponding to the hash feature value is determined according to the segment size.

6. The method for detecting similarity of application icons according to claim 3, wherein: The step of obtaining multiple segments of second feature values ​​corresponding to the standard hash feature value of the standard application icon specifically includes: Selecting a standard hash feature value corresponding to the standard application icon from the preset hash feature value set; Determine the standard segment number according to the segment number and the standard hash feature value; The standard hash characteristic value is segmented according to the standard segment number to obtain multiple segments of second characteristic values.

7. The method for detecting similarity of application icons according to claim 3, wherein: The step of performing feature value matching on the multiple segments of first feature values ​​and the multiple segments of second feature values ​​in a segmented index manner specifically includes: The plurality of first eigenvalue segments are stored in segments, and an index set is created for the first eigenvalue stored in each segment; Feature value matching is performed on the target first feature value corresponding to each index in the index set and the multiple segments of second feature values.

8. A device for detecting similarity of application icons, characterized in that: The similarity detection device for application icons includes: A feature value segmentation module, configured to segment the hash feature value of the application icon to be detected to obtain a plurality of first feature values; The characteristic value segmentation module is further used to obtain multiple segments of second characteristic values ​​corresponding to the standard hash characteristic value of the standard application icon; A feature value matching module, configured to perform feature value matching on the multiple segments of first feature values ​​and the multiple segments of second feature values ​​in a segmented index manner; The similarity detection module is used to perform similarity detection on the application icon to be detected and the standard application icon according to the matching result.

9. A device for detecting similarity of application icons, characterized in that: The device includes: a memory, a processor, and an application icon similarity detection program stored in the memory and executable on the processor, wherein the application icon similarity detection program is configured to implement the steps of the application icon similarity detection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores an application icon similarity detection program, which, when executed by a processor, implements the steps of the application icon similarity detection method according to any one of claims 1 to 7.

Images