A method, device, equipment and readable storage medium for picture risk assessment

Abstract

The present application discloses a method, device, equipment and readable storage medium for picture risk assessment. The method includes: applying a picture to be evaluated and verified to a rotating picture verification code, which is composed of a rotating graphic, a fixed graphic and a sliding bar. The rotating graphic is a graphic obtained by randomly rotating a circular area randomly cut from the picture to be evaluated and verified by a random angle, and the fixed graphic is a graphic of the remaining area after the picture to be evaluated and verified is cut; conducting a number of confrontation tests on the rotating picture verification code and counting the results of the confrontation tests. The confrontation test is to simulate the pulling of the sliding block in the sliding bar to make the rotating graphic and the fixed graphic match to form a complete verification picture; determining the risk level of the picture to be evaluated and verified according to the results of the confrontation tests. According to the risk level of the picture determined by the present application, pictures that are difficult to recognize can be assisted in being selected and applied to the rotating picture verification code, thereby improving the security and protection of the rotating picture verification code.

Description

Technical Field

[0001] The present application relates to the field of verification and identification, and more specifically, to a method, device, equipment and readable storage medium for picture risk assessment. Background Art

[0002] With the vigorous development of Internet technology, in order to prevent malicious batch operations and protect account security, verification code technology is often adopted. Users need to complete corresponding verification before logging in and querying before they can perform subsequent operations. Among them, picture verification is a relatively common verification method used in enterprise websites, APPs and other applications. Users need to identify pictures and perform operations according to requirements, and can use a certain function only after successful verification.

[0003] As shown in the attached Figure 1 When a user needs to publish an article or comment in a certain application, they must first complete the rotation picture verification code verification before they can perform the publishing operation. The specific operation is to pull the sliding block on the sliding bar to control the rotation of the central circular rotation picture. When the circular picture rotates to form a complete and matching picture with the fixed picture of the background, the picture verification is completed and the picture verification passes.

[0004] However, the pictures used in such verification codes are diverse, and factors such as the structure and color of different pictures are also different. For pictures with simple shape structures or common pictures, the generated rotation verification codes are often easy to be cracked, resulting in a reduction in the security of the rotation picture verification code protection.

[0005] Based on the above situation, providing a picture risk assessment scheme to assist in the selection of rotation picture verification codes and improve the security of rotation picture verification code protection has become an urgent technical problem to be solved. Summary of the Invention

[0006] In view of this, the present application provides a method, device, equipment and readable storage medium for picture risk assessment, which can determine the risk level of the verification picture and assist in selecting difficult-to-identify pictures for application in rotation picture verification codes, thereby improving the security and protection of rotation picture verification codes.

[0007] In order to achieve the above object, the following scheme is proposed:

[0008] A method for picture risk assessment, characterized by comprising:

[0009] Applying the verification picture to be evaluated to a rotation picture verification code, where the rotation picture verification code is composed of a rotation graphic, a fixed graphic and a sliding bar. The rotation graphic is a graphic obtained by randomly rotating a circular area randomly cut from the verification picture to be evaluated by a random angle, and the fixed graphic is a graphic of the remaining area after cutting the verification picture to be evaluated;

[0010] Perform several confrontation tests on the rotating picture verification code, and count the results of the confrontation tests. The confrontation test is to simulate pulling the sliding block in the sliding bar to make the rotating graphic and the fixed graphic match to form the complete verification picture;

[0011] Determine the risk level of the verification picture to be evaluated according to the results of the confrontation test.

[0012] Preferably, performing several confrontation tests on the rotating picture verification code and counting the results of the confrontation tests includes:

[0013] For one confrontation test:

[0014] Determine the angle value that the rotating graphic needs to rotate to the positive direction through picture feature matching. The positive direction is the direction of the rotating graphic when the rotating graphic and the fixed graphic are spliced to form the complete verification picture;

[0015] Determine the corresponding relationship between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic;

[0016] Determine the sliding distance corresponding to the rotating graphic rotating to the positive direction according to the corresponding relationship;

[0017] Move the sliding block in the sliding bar according to the sliding distance to determine the result of the confrontation test.

[0018] Preferably, determining the risk level of the verification picture to be evaluated according to the results of the confrontation test includes:

[0019] Determine the proportion of the number of times the test passes in all confrontation test times in the results of the confrontation test;

[0020] Determine the risk level based on the proportion, and the proportion is positively correlated with the risk level.

[0021] Preferably, determining the corresponding relationship between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic includes:

[0022] Obtain the maximum sliding distance of the sliding block on the sliding bar;

[0023] Obtain the maximum rotation angle allowed by the rotating graphic in the rotation model;

[0024] According to the maximum sliding distance and the maximum rotation angle, determine the corresponding matching value between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic through the equal ratio algorithm.

[0025] A picture risk assessment device includes:

[0026] An image application unit for applying the image to be evaluated and verified to a rotating image verification code, which consists of a rotating graphic, a fixed graphic, and a sliding bar. The rotating graphic is a graphic obtained by randomly rotating a circular graphic randomly cut from the image to be evaluated and verified by a random angle, and the fixed graphic is the remaining graphic after the image to be evaluated and verified is cut;

[0027] A testing unit for conducting a number of confrontation tests on the rotating image verification code and counting the results of the confrontation tests. The confrontation test is to simulate the pulling of the sliding block in the sliding bar to make the rotating graphic and the fixed graphic match to form the complete verification image;

[0028] An evaluation unit for determining the risk level of the image to be evaluated and verified based on the results of the confrontation tests.

[0029] Preferably, the testing unit includes:

[0030] A feature matching unit for determining the angle value that the rotating graphic needs to rotate to the positive direction through image feature matching. The positive direction is the direction of the rotating graphic when the rotating graphic and the fixed graphic are spliced to form the complete verification image;

[0031] A correspondence determination unit for determining the correspondence between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic;

[0032] A distance calculation unit for determining the sliding distance corresponding to the rotating graphic rotating to the positive direction based on the correspondence;

[0033] A movement simulation unit for moving the sliding block in the sliding bar according to the sliding distance to determine the results of the confrontation tests.

[0034] Preferably, the evaluation unit includes:

[0035] A statistics unit for counting the proportion of the number of times the confrontation test result is passed in the total number of confrontation tests;

[0036] A level determination unit for determining the risk level based on the proportion, and the proportion is positively correlated with the risk level.

[0037] Preferably, the correspondence determination unit includes:

[0038] A maximum distance acquisition unit for acquiring the maximum sliding distance of the sliding block on the sliding bar;

[0039] A maximum angle acquisition unit for acquiring the maximum rotation angle allowed for the rotating graphic in the rotation model;

[0040] A matching calculation unit, configured to determine a corresponding matching value between the sliding distance of a sliding block on a sliding bar and the rotation angle of a rotating graphic through a geometric ratio algorithm according to the maximum sliding distance and the maximum rotation angle.

[0041] An image risk assessment device, comprising a memory and a processor;

[0042] The memory is used for storing programs;

[0043] The processor is configured to execute the program to implement each step of the image risk assessment method as described above.

[0044] A readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each step of the image risk assessment method as described above is implemented.

[0045] As can be seen from the above technical solutions, an image risk assessment method, device, equipment, and readable storage medium provided by the embodiments of the present application apply a to-be-evaluated and verified image to a rotating image verification code, randomly generate a rotating image verification code, perform a number of confrontation tests on the rotating image verification code, and count the results of the confrontation tests. The process of the confrontation test is a process in which a machine automatically performs matching recognition on a rotating graphic and a fixed graphic and performs rotation pairing. Through the statistics of the results of multiple confrontation tests, it can be determined whether the to-be-evaluated and verified image belongs to an easily recognizable image or a difficult-to-recognize image for the machine, that is, according to the results of the confrontation test, the risk level of the to-be-evaluated and verified image is determined.

[0046] Therefore, in the process of updating and maintaining an image library applied to a rotating image verification code, easily recognizable images in the image library can be removed and difficult-to-recognize images can be added according to the risk level of the images determined by the present application to improve the security and protection of the rotating image verification code. Description of the Drawings

[0047] 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 required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0048] Figure 1 A schematic diagram of a rotating image verification code for the background technology of the present application;

[0049] Figure 2 A flowchart of an image risk assessment method disclosed in the present application;

[0050] Figure 3 The verification image to be evaluated for the rotation picture verification code disclosed in this application Figure 1 as shown;

[0051] Figure 4 A schematic diagram of the generation of a rotating graphic disclosed in this application

[0052] Figure 5 A schematic diagram of a fixed graphic disclosed in this application

[0053] Figure 6 A schematic diagram of the generated graphic for the confrontation test disclosed in this application

[0054] Figure 7 A structural block diagram of a picture risk assessment device disclosed in this application

[0055] Figure 8 A hardware structural block diagram of a picture risk assessment device disclosed in this application Detailed implementation manners

[0056] Next, the accompanying drawings in the embodiments of this application will be used to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0057] Next, the solutions of this application will be introduced. This application proposes the following technical solutions. For details, please refer to the following text.

[0058] Figure 1 A flowchart of a picture risk assessment method disclosed in an embodiment of this application, as Figure 1 shown. The method may include:

[0059] Step S1: Apply the verification image to be evaluated to the rotation picture verification code.

[0060] Specifically, the rotation picture verification code is composed of a rotating graphic, a fixed graphic, and a sliding bar. The rotating graphic is a graphic obtained by randomly rotating a circular area randomly cut from the verification image to be evaluated by a random angle. The fixed graphic is a graphic of the remaining area after the verification image to be evaluated is cut.

[0061] In this application, for the generation of the rotating picture verification code, the generation method is as follows: randomly cut a circular area from the to-be-evaluated verification graph, rotate the circular area by any angle, use the graph obtained after rotation as the rotating graph of the rotating picture verification code, and use the remaining area after cutting from the to-be-evaluated verification graph as the fixed graph of the rotating picture verification code.

[0062] It can be understood that the verification method of the rotating picture verification code is to drag the sliding block in the sliding bar, so as to control the rotation of the rotating graph. Generally, the sliding distance is in direct proportion to the rotation angle, that is, the farther the sliding distance, the larger the rotation angle. When the rotating graph rotates to a position where it can be spliced with the fixed graph to form a complete verification picture, that is, the complete picture composed of the rotating graph and the fixed graph after rotation is exactly the same as the original to-be-evaluated verification picture, it indicates that the rotating picture verification code is verified successfully.

[0063] For example, Figure 3 To form Figure 1 The to-be-evaluated verification picture of the rotating picture verification code shown, as Figure 4 shown, a circular area is randomly cut out from the to-be-evaluated verification picture and randomly rotated to obtain the rotating graph. Use the remaining area of the to-be-evaluated verification picture as the fixed graph. In this example, the remaining area after extraction is the fixed graph as Figure 5 , and the fixed graph Figure 5 has a circular vacancy left after cutting.

[0064] It can be understood that the types of to-be-evaluated verification pictures include but are not limited to the types in the above examples. At the same time, the cutting position, size of the circular area, and the rotation angle of the circular area are not limited to the methods in the above examples. The above example pictures are only an optional type for easy understanding. In actual applications, the process of the device generating the rotating picture verification code from the to-be-evaluated verification picture is automatically random, so as to obtain a more accurate risk level test result.

[0065] Step S2: Conduct a number of confrontation tests on the rotating picture verification code and count the results of the confrontation tests.

[0066] Specifically, the confrontation test is to simulate the pulling of the sliding block in the sliding bar to make the rotating graph and the fixed graph match to form the complete verification picture. The confrontation test is that the machine device automatically identifies and matches the rotating graph and the fixed graph in the rotating picture verification code, determines the angle value that the rotating graph needs to rotate according to the matching result, and simulates the pulling of the sliding block in the sliding bar.

[0067] However, for easily recognizable pictures with simple structures, the machine can obtain relatively accurate matching results, and the restored rotating graphic verification codes are often exactly the same as the original verification pictures and can pass the matching verification. For pictures with complex structures that are difficult to recognize, it is difficult for machine devices to capture their typical features, often unable to match or with a large error in the matching result. The restored rotating graphic verification codes are different from the original verification pictures, and thus cannot pass the matching verification.

[0068] The confrontation test is a process of automatically matching the generated rotating picture verification codes with machine devices and then restoring the rotating graphic verification codes based on the automatic matching results. After obtaining the restoration results, it is necessary to manually determine whether the restoration results are exactly the same as the original verification pictures to be evaluated. After a large number of confrontation tests, it is determined manually and the confrontation test results are statistically generated.

[0069] In addition, to improve the evaluation accuracy, the same verification picture to be tested can be randomly generated with rotating picture verification codes multiple times, and a large number of confrontation tests are respectively carried out on the rotating picture verification codes generated each time.

[0070] Step S3: Determine the risk level of the verification picture to be evaluated according to the confrontation test results.

[0071] Specifically, for verification pictures with a relatively high probability of passing the matching after being restored by machine devices, that is, easily recognizable pictures, it indicates that their risk level is relatively high, and the security protection of the corresponding generated rotating picture verification codes is relatively low. For verification pictures with a relatively low or failed matching after being restored by machine devices, that is, pictures that are difficult to recognize, it indicates that their risk level is relatively low, and the security protection of the corresponding generated rotating picture verification codes is relatively high.

[0072] After obtaining the confrontation test results, the verification pictures to be evaluated can be classified according to the confrontation test results to determine their belonging risk levels. For pictures classified as having a low risk and relatively high security protection, they can be applied to the actual setting of rotating picture verification codes. For pictures classified as having a high risk and relatively low security protection, they should not be applied to the actual setting of rotating picture verification codes.

[0073] During the process of updating and maintaining the picture library applied to rotating picture verification codes, for pictures classified as having a high risk and relatively low security protection, the pictures can be deleted and the proportion of the same type of pictures can be reduced. For pictures classified as having a low risk and relatively high security protection, the pictures can be retained and the same type of pictures can be appropriately filled to enrich the verification picture library.

[0074] As can be seen from the above technical solution, a picture risk assessment method provided by an embodiment of the present application applies a picture to be evaluated and verified to a rotating picture verification code, randomly generates a rotating picture verification code, performs a number of confrontation tests on the rotating picture verification code, and counts the results of the confrontation tests. The process of the confrontation test is a process in which a machine automatically matches and identifies a rotating graphic and a fixed graphic and performs rotational pairing. By counting the results of multiple confrontation tests, it can be determined whether the picture to be evaluated and verified is an easily recognizable picture or a difficult-to-recognize picture for the machine, that is, according to the results of the confrontation test, the risk level of the picture to be evaluated and verified is determined.

[0075] Therefore, in the process of updating and maintaining the picture library applied to the rotating picture verification code, according to the risk level of the picture determined by the present application, the easily recognizable pictures in the picture library can be removed, and difficult-to-recognize pictures can be added to improve the security and protection of the rotating picture verification code.

[0076] In some embodiments of the present application, the process of step S2, performing a number of confrontation tests on the rotating picture verification code and counting the results of the confrontation tests, is introduced. Taking one confrontation test as an example, specifically, it may include:

[0077] Step S21, determining the angle value that the rotating graphic needs to rotate to the positive direction through picture feature matching.

[0078] Specifically, the positive direction is the direction of the rotating graphic when the rotating graphic and the fixed graphic are spliced to form a complete verification picture. As Figure 4 shown, Figure 4 before rotation, the rotating graphic and the fixed graphic can be spliced to form a complete verification picture, that is, the direction of the rotating graphic before rotation is the positive direction. By using picture feature matching, the position and shape of the rotating graphic when it rotates to the positive direction can be determined. By comparing and using the feature displacement algorithm, the angle value that the rotating graphic needs to rotate to be spliced with the fixed graphic to form a complete verification picture, that is, the angle value that needs to be rotated to the positive direction, can be obtained.

[0079] Step S22, determining the correspondence between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic.

[0080] Specifically, after determining the angle value that the rotating graphic needs to rotate to the positive direction, it is necessary to further determine the correspondence between the sliding distance of the sliding block and the rotation angle of the rotating graphic in order to determine the sliding distance that needs to be slid for the current match. Generally, the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic are in a proportional relationship, that is, the larger the sliding distance, the larger the rotation angle of the rotating graphic.

[0081] Optionally, the process of determining the correspondence between the sliding distance of the sliding block on the slider and the rotation angle of the rotating graphic may include:

[0082] ① Obtain the maximum sliding distance of the sliding block on the slider.

[0083] ② Obtain the maximum rotation angle allowed for the rotating graphic in the rotation model.

[0084] ③ According to the maximum sliding distance and the maximum rotation angle, determine the corresponding matching value between the sliding distance of the sliding block on the slider and the rotation angle of the rotating graphic through a geometric ratio algorithm.

[0085] Specifically, first obtain the maximum sliding distance of the sliding block on the slider, then obtain the maximum rotation angle allowed for the rotating graphic in the rotation model, and determine the corresponding matching value between the sliding distance of the sliding block on the slider and the rotation angle of the rotating graphic through a geometric ratio algorithm, that is, obtain how many rotation angles correspond to each unit distance. The sliding distance of the sliding block on the slider is proportional to the rotation angle of the rotating graphic, and the corresponding matching value between the sliding distance and the rotation angle is the ratio between the maximum sliding distance and the maximum rotation angle.

[0086] For example, if the maximum sliding distance is 5 and the maximum rotation angle is 360°, then the rotation angle corresponding to each distance is 72°, that is, the corresponding matching value between the sliding distance and the rotation angle is 1 to 72.

[0087] Step S23: Determine the sliding distance corresponding to the rotation of the rotating graphic to the positive direction according to the corresponding relationship.

[0088] Specifically, after determining the angle value that the rotating graphic needs to rotate to the positive direction and the corresponding relationship, the sliding distance corresponding to the rotation of the rotating graphic to the positive direction can be obtained through the product of the angle value that needs to be rotated and the corresponding relationship, that is, the product of the angle value that needs to be rotated and the matching value.

[0089] For example, if the corresponding matching value between the sliding distance and the rotation angle is 1 to 60° and the angle value that the rotating graphic needs to rotate to the positive direction is 180°, then the sliding distance corresponding to the rotation of the rotating graphic to the positive direction can be calculated as 3.

[0090] Step S24: Move the sliding block in the slider according to the sliding distance and determine the countermeasure test result.

[0091] Specifically, according to the sliding distance, the sliding block in the slider is moved to control the corresponding rotation of the rotating graphic. When the sliding block slides the previously calculated sliding distance, the machine device defaults that the matching is completed at this time, that is, the current rotating graphic and the fixed graphic are completely matched, and the formed picture is exactly the same as the original verification picture. In fact, the picture composed of the current rotating graphic and the fixed graphic is not necessarily exactly the same as the original verification picture, and it is necessary to manually verify the picture generated by the sliding match, that is, to verify the graphic generated by the confrontation test to generate the confrontation test result.

[0092] As Figure 6 shown, the current sliding block has moved the corresponding sliding distance, but at this time, the picture composed of the rotating picture and the fixed graphic is not completely matched, that is, it is not exactly the same as the picture to be evaluated and verified. Therefore, the current confrontation test result should be a failure.

[0093] In some embodiments of the present application, the process of step S3, determining the risk level of the picture to be evaluated and verified according to the confrontation test result, is introduced. Specifically, it may include:

[0094] Step S31, determining the proportion of the number of passes in the confrontation test results in the total number of confrontation tests.

[0095] Specifically, determine the proportion of the number of passes in the statistically obtained confrontation test results in the total number of confrontation tests. The higher the proportion, the easier it is for the machine device to recognize and match the verification picture, the higher its risk level, and the lower the security protection of the generated rotating picture verification code.

[0096] Step S32, determining the risk level based on the proportion, and the proportion is positively correlated with the risk level.

[0097] Specifically, based on the proportion to determine the risk level, the risk level of the picture to be evaluated and verified can be determined. Generally, the proportion is positively correlated with the risk level. The risk level can be determined by means such as the risk level evaluation standard.

[0098] For example, before the test, a risk level evaluation standard can be preset as shown in Table 1 below. Through the proportion and the risk level evaluation standard, the risk level and picture type of the current picture to be evaluated and verified can be determined.

[0099] It can be understood that the higher the proportion of the number of passes in the confrontation test results in the total number of confrontation tests, the greater the risk degree represented by the corresponding risk level, and the lower the proportion of the number of passes in the confrontation test results in the total number of confrontation tests, the smaller the risk degree represented by the corresponding risk level.

[0100]

[0101] Table 1

[0102] The picture risk assessment device provided by the embodiment of the present application will be described below. The picture risk assessment device described below can be correspondingly referred to the picture risk assessment method described above.

[0103] See Figure 7 , Figure 7 which is a schematic structural diagram of a picture risk assessment device disclosed in the embodiment of the present application.

[0104] As Figure 7 shown, the device may include:

[0105] A picture application unit 110, configured to apply a picture to be evaluated and verified to a rotating picture verification code, where the rotating picture verification code is composed of a rotating graphic, a fixed graphic, and a sliding bar. The rotating graphic is a graphic obtained by randomly rotating a circular graphic randomly cut from the picture to be evaluated and verified by a random angle, and the fixed graphic is the remaining graphic after the picture to be evaluated and verified is cut;

[0106] A test unit 120, configured to perform several confrontation tests on the rotating picture verification code and count the results of the confrontation tests. The confrontation test is to simulate the pulling of a sliding square in the sliding bar to make the rotating graphic and the fixed graphic match to form a complete verification picture;

[0107] An evaluation unit 130, configured to determine the risk level of the picture to be evaluated and verified according to the results of the confrontation tests.

[0108] It can be seen from the above technical solutions that a picture risk assessment device provided by the embodiment of the present application applies the picture to be evaluated and verified to a rotating picture verification code, randomly generates a rotating picture verification code, performs several confrontation tests on the rotating picture verification code, and counts the results of the confrontation tests. The process of the confrontation test is a process in which the machine automatically matches and identifies the rotating graphic and the fixed graphic and performs rotation pairing. By statistically analyzing the results of multiple confrontation tests, it can be determined whether the picture to be evaluated and verified is an easy-to-recognize picture or a difficult-to-recognize picture for the machine, that is, the risk level of the picture to be evaluated and verified is determined according to the results of the confrontation tests.

[0109] Therefore, in the process of updating and maintaining the picture library applied to the rotating picture verification code, the easy-to-recognize pictures in the picture library can be removed and the difficult-to-recognize pictures can be added according to the risk level of the pictures determined by the present application to improve the security and protection of the rotating picture verification code.

[0110] Optionally, the test unit includes:

[0111] A feature matching unit, configured to determine the angle value that the rotating graphic needs to rotate to the positive direction through picture feature matching, where the positive direction is the direction of the rotating graphic when the rotating graphic and the fixed graphic are spliced to form the complete verification picture;

[0112] A corresponding relationship determining unit, configured to determine the corresponding relationship between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic;

[0113] A distance calculating unit, configured to determine the sliding distance corresponding to the rotating graphic rotating to the positive direction according to the corresponding relationship;

[0114] A movement simulation unit, configured to move the sliding block in the sliding bar according to the sliding distance to determine the result of the confrontation test.

[0115] Optionally, the evaluation unit includes:

[0116] A statistics unit, configured to count the proportion of the number of times the confrontation test result is passed in all the confrontation test times;

[0117] A risk level determining unit, configured to determine the risk level based on the proportion, and the proportion is positively correlated with the risk level.

[0118] Optionally, the corresponding relationship determining unit includes:

[0119] A maximum distance obtaining unit, configured to obtain the maximum sliding distance of the sliding block on the sliding bar;

[0120] A maximum angle obtaining unit, configured to obtain the maximum rotation angle allowed for the rotating graphic in the rotation model;

[0121] A matching calculation unit, configured to determine the corresponding matching value between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic through an equal ratio algorithm according to the maximum sliding distance and the maximum rotation angle.

[0122] The picture risk assessment device provided by the embodiment of the present application can be applied to picture risk assessment devices, such as PC terminals, cloud platforms, servers, server clusters, etc. Optionally, Figure 8 shows the hardware structure block diagram of the picture risk assessment device. Refer to Figure 8 , the hardware structure of the picture risk assessment device may include: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4;

[0123] In an embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 complete mutual communication through the communication bus 4;

[0124] The processor 1 may be a central processing unit (CPU), or a specific integrated circuit (ASIC) (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0125] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory;

[0126] Among them, the memory stores a program, and the processor can call the program stored in the memory. The program is used for:

[0127] Applying the picture to be evaluated and verified to a rotating picture verification code, the rotating picture verification code is composed of a rotating graphic, a fixed graphic, and a sliding bar. The rotating graphic is a graphic obtained by randomly rotating a circular area randomly cut from the picture to be evaluated and verified by a random angle, and the fixed graphic is a graphic of the remaining area after the picture to be evaluated and verified is cut;

[0128] Performing several confrontation tests on the rotating picture verification code and counting the results of the confrontation tests. The confrontation test is to simulate pulling the sliding block in the sliding bar to make the rotating graphic and the fixed graphic match to form the complete verification picture;

[0129] Determining the risk level of the picture to be evaluated and verified according to the results of the confrontation tests.

[0130] Optionally, the refined functions and extended functions of the program can be referred to the above description.

[0131] The embodiment of the present application also provides a readable storage medium, which can store a program suitable for execution by a processor. The program is used for:

[0132] Applying the picture to be evaluated and verified to a rotating picture verification code, the rotating picture verification code is composed of a rotating graphic, a fixed graphic, and a sliding bar. The rotating graphic is a graphic obtained by randomly rotating a circular area randomly cut from the picture to be evaluated and verified by a random angle, and the fixed graphic is a graphic of the remaining area after the picture to be evaluated and verified is cut;

[0133] Conduct several confrontation tests on the rotating picture verification code, and count the results of the confrontation tests. The confrontation test is to simulate the pulling of the sliding block in the sliding bar to make the rotating graphic and the fixed graphic match to form the complete verification picture;

[0134] Determine the risk level of the verification picture to be evaluated according to the results of the confrontation test.

[0135] Optionally, the refinement function and expansion function of the program can refer to the above description.

[0136] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0137] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0138] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for image risk assessment, characterized in that, Including: Applying the picture to be evaluated and verified to a rotating picture verification code, which is composed of a rotating graphic, a fixed graphic, and a sliding bar. The rotating graphic is a graphic obtained by randomly rotating a circular area randomly cut from the picture to be evaluated and verified by a random angle, and the fixed graphic is a graphic of the remaining area after the picture to be evaluated and verified is cut; Conducting several confrontation tests on the rotating picture verification code and counting the results of the confrontation tests. The confrontation test is to simulate pulling the sliding block in the sliding bar to make the rotating graphic and the fixed graphic match to form a complete verification picture; Determining the risk level of the picture to be evaluated and verified according to the results of the confrontation tests; Among them, for one confrontation test: Determining the angle value that the rotating graphic needs to rotate to the positive direction through picture feature matching. The positive direction is the direction of the rotating graphic when the rotating graphic and the fixed graphic are spliced to form a complete verification picture; Determining the corresponding relationship between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic; Determining the sliding distance corresponding to the rotating graphic rotating to the positive direction according to the corresponding relationship; Moving the sliding block in the sliding bar according to the sliding distance to determine the result of the confrontation test.

2. The method according to claim 1, wherein Determining the risk level of the picture to be evaluated and verified according to the results of the confrontation tests, including: Determining the proportion of the number of passed tests in the total number of confrontation tests in the results of the confrontation tests; Determining the risk level based on the proportion, and the proportion is positively correlated with the risk level.

3. The method according to claim 1, characterized in that, Determining the corresponding relationship between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic, including: Obtaining the maximum sliding distance of the sliding block on the sliding bar; Obtaining the maximum rotation angle allowed for the rotating graphic in the rotation model; According to the maximum sliding distance and the maximum rotation angle, determining the corresponding matching value between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic through an equal ratio algorithm.

4. A picture risk assessment device, characterized in that, Including: A picture application unit for applying the picture to be evaluated and verified to a rotating picture verification code, which is composed of a rotating graphic, a fixed graphic, and a sliding bar. The rotating graphic is a graphic obtained by randomly rotating a randomly cut circular graphic in the picture to be evaluated and verified by a random angle, and the fixed graphic is the remaining graphic after the picture to be evaluated and verified is cut; A test unit for conducting several confrontation tests on the rotating picture verification code and counting the results of the confrontation tests. The confrontation test is to simulate pulling the sliding block in the sliding bar to make the rotating graphic and the fixed graphic match to form a complete verification picture; An evaluation unit for determining the risk level of the picture to be evaluated and verified according to the results of the confrontation tests; Among them, the test unit includes: A feature matching unit for determining the angle value that the rotating graphic needs to rotate to the positive direction through picture feature matching. The positive direction is the direction of the rotating graphic when the rotating graphic and the fixed graphic are spliced to form a complete verification picture; A correspondence determination unit for determining the correspondence between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic; A distance calculation unit for determining the sliding distance corresponding to the rotating graphic rotating to the positive direction according to the correspondence; A movement simulation unit for moving the sliding block in the sliding bar according to the sliding distance to determine the confrontation test result.

5. The device according to claim 4, characterized in that, The evaluation unit includes: A statistics unit for counting the proportion of the number of times the confrontation test result is passed in all confrontation test times; A level determination unit for determining the risk level based on the proportion, and the proportion is positively correlated with the risk level.

6. The device according to claim 4, characterized in that The correspondence determination unit includes: A maximum distance acquisition unit for acquiring the maximum sliding distance of the sliding block on the sliding bar; A maximum angle acquisition unit for acquiring the maximum rotation angle allowed by the rotating graphic in the rotation model; A matching calculation unit for determining the corresponding matching value between the sliding distance of the sliding block on the sliding bar and the rotation angle of the rotating graphic through a geometric ratio algorithm according to the maximum sliding distance and the maximum rotation angle.

7. A picture risk assessment device, characterized in that, It includes a memory and a processor; The memory is used for storing programs; The processor is used for executing the program to implement each step of the picture risk assessment method as described in any one of claims 1-3.

8. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements each step of the picture risk assessment method as described in any one of claims 1-3.

Images