A slider verification method, device, storage medium and electronic device

Abstract

Embodiments of the present disclosure disclose a slider verification method and apparatus, as well as a storage medium and an electronic device. The method includes: obtaining an interface image of a slider verification interface; performing image recognition on the interface image by using a slider notch prediction model to obtain coordinate data for positioning the position of the slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; sending the obtained coordinate data to a client application so that the client application controls at least one slider in the slider verification interface to move to a corresponding image area according to the received coordinate data to implement slider verification.

Description

Technical Field

[0001] The present invention relates to the field of computer technologies, and in particular, to a slider verification method, device, storage medium, electronic device, and computer program product. Background Art

[0002] In practical application scenarios, client applications use verification code technologies including character recognition, slider drag recognition, etc. to prevent automatic login based on preset automated programs. Among the above-mentioned common verification code technologies, the sliding verification code technology (also known as the slider verification technology) is widely used because of its advantages of strong security and simple operation.

[0003] For the existing verification technology based on sliding verification codes, for each type of sliding verification code, for each type of slider and the verification position where the corresponding slider notch is to be slid to, pre-configuration is required, so that the existing verification method based on sliding verification codes is not universal and has low generalization performance.

[0004] How to improve the universality of the existing verification technology based on sliding verification codes and improve its generalization performance is a technical problem to be solved. Summary of the Invention

[0005] Based on this, in view of the problem that the existing sliding verification code verification method is not universal and has low generalization performance, it is necessary to provide a sliding verification code verification method, device, storage medium, and electronic device.

[0006] In a first aspect, an embodiment of the present disclosure provides a slider verification method, the method including: obtaining an interface image of a slider verification interface; performing image recognition on the interface image by using a slider notch prediction model to obtain coordinate data for positioning the position of a slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; sending the obtained coordinate data to a client application, so that the client application controls at least one slider in the slider verification interface to move to a corresponding image area to implement slider verification.

[0007] In a second aspect, an embodiment of the present disclosure provides a slider verification method, including: obtaining an interface image of a slider verification interface; performing image recognition on the interface image by using a slider notch prediction model to obtain coordinate data for positioning the position of a slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; based on the obtained coordinate data, controlling at least one slider in the slider verification interface to move to a corresponding image area to implement slider verification.

[0008] In a third aspect, embodiments of the present disclosure provide a slider verification method, including: obtaining coordinate data from a server, where the coordinate data is obtained by the server through obtaining an interface image of a slider verification interface and performing image recognition on the interface image by using a slider notch prediction model for positioning the position of a slider notch in the interface image, and the slider notch prediction model is pre-trained by a data set involving various types of slider notches; and controlling at least one slider in the slider verification interface to move to a corresponding image area according to the obtained coordinate data to implement slider verification.

[0009] In a fourth aspect, embodiments of the present disclosure provide a slider verification device, including: an obtaining unit configured to obtain an interface image of a slider verification interface; an image recognition unit configured to perform image recognition on the interface image by using a slider notch prediction model to obtain coordinate data for positioning the position of a slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; and a sending unit configured to send the obtained coordinate data to a client application so that the client application controls at least one slider in the slider verification interface to move to a corresponding image area according to the received coordinate data to implement slider verification.

[0010] In a fifth aspect, embodiments of the present disclosure provide a slider verification device, including: an obtaining unit configured to obtain an interface image of a slider verification interface; an image recognition unit configured to perform image recognition on the interface image by using a slider notch prediction model to obtain coordinate data for positioning the position of a slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; and a control unit configured to control at least one slider in the slider verification interface to move to a corresponding image area based on the obtained coordinate data to implement slider verification.

[0011] In a sixth aspect, embodiments of the present disclosure provide a slider verification device, including: an obtaining unit configured to obtain coordinate data from a server, where the coordinate data is obtained by the server through obtaining an interface image of a slider verification interface and performing image recognition on the interface image by using a slider notch prediction model for positioning the position of a slider notch in the interface image, and the slider notch prediction model is pre-trained by a data set involving various types of slider notches; and a control unit configured to control at least one slider in the slider verification interface to move to a corresponding image area according to the obtained coordinate data to implement slider verification.

[0012] In a seventh aspect, an embodiment of the present disclosure provides an electronic device, which includes: a processor; a memory for storing executable instructions executable by the processor; and the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the above method steps.

[0013] In an eighth aspect, an embodiment of the present disclosure provides a computer-readable storage medium storing a computer program for executing the above method steps.

[0014] In a ninth aspect, an embodiment of the present disclosure provides a computer program product including a computer program, which implements the above method steps when executed by a processor.

[0015] In an embodiment of the present disclosure, an interface image of a slider verification interface is obtained; the interface image is subjected to image recognition by using a slider notch prediction model to obtain coordinate data for positioning the position of the slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; and the obtained coordinate data is sent to a client application, so that the client application controls at least one slider in the slider verification interface to move to a corresponding image area according to the received coordinate data to implement slider verification. In the slider verification method provided by the embodiment of the present disclosure, because a slider notch prediction model is introduced and the slider notch prediction model is a general model, image recognition is performed on the interface images of different types of slider verification interfaces, so that the coordinate data of the position of the corresponding slider notch can be accurately predicted, and the coordinate data is sent to the client application for automatic slider verification. In this way, the versatility and generalization performance of slider verification can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By referring to the following drawings, the exemplary embodiments of the present invention can be more fully understood. The drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 FIG. is a flowchart of a slider verification method according to an exemplary embodiment of the present disclosure;

[0018] Figure 2 FIG. is a flowchart of another slider verification method according to an exemplary embodiment of the present disclosure;

[0019] Figure 3 FIG. is a flowchart of yet another slider verification method according to an exemplary embodiment of the present disclosure;

[0020] Figure 4 Schematic diagram of a slider verification device 400 provided according to an exemplary embodiment of the present disclosure;

[0021] Figure 5 Schematic diagram of another slider verification device 500 provided according to an exemplary embodiment of the present disclosure;

[0022] Figure 6 Schematic diagram of yet another slider verification device 600 provided according to an exemplary embodiment of the present disclosure;

[0023] Figure 7 Schematic diagram of an electronic device provided according to an exemplary embodiment of the present disclosure;

[0024] Figure 8 Schematic diagram of a computer-readable medium provided according to an exemplary embodiment of the present disclosure. Detailed implementation manners

[0025] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0026] It should be noted that unless otherwise specified, the technical terms or scientific terms used in the present disclosure should have the ordinary meanings understood by those skilled in the art to which the present disclosure belongs.

[0027] In addition, terms such as "first" and "second" are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0028] The embodiments of the present disclosure provide a slider verification method and device, an electronic device, and a computer-readable medium, which will be described below with reference to the accompanying drawings.

[0029] Please refer to Figure 1 , which shows a flowchart of a slider verification method provided by some embodiments of the present disclosure. The slider verification method is applied to a server, as Figure 1 shown, the slider verification method may include the following steps:

[0030] Step S101: Obtain the interface image of the slider verification interface.

[0031] In the embodiments of the present disclosure, there are no specific restrictions on the content shown in the interface image of the slider verification interface, the number and shape of the sliders in the interface image, and the number and shape of the slider gaps corresponding to the sliders. According to the requirements of different application scenarios, the above content can be configured and adjusted accordingly, which will not be elaborated here.

[0032] In a possible implementation manner, obtaining the interface image of the slider verification interface includes the following steps:

[0033] Obtain the interface image of the slider verification interface that includes at least one slider gap.

[0034] In the embodiments of the present disclosure, there are no specific restrictions on the number and shape of the slider gaps in the above interface image.

[0035] Step S102: Use the slider gap prediction model to perform image recognition on the interface image to obtain coordinate data for positioning the positions of the slider gaps in the interface image, where the slider gap prediction model is pre-trained by a data set involving various types of slider gaps.

[0036] In a possible implementation manner, the slider gap prediction model is trained through the following operations:

[0037] Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data. Each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating multiple key points of each slider gap in at least one slider gap in the corresponding first interface image;

[0038] Traverse the training sample set, and perform a first operation once for each traversed first interface image to iteratively train a predetermined model until the slider gap prediction model is trained. The first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model. In this way, through the above iterative training process, the model can be optimized, so that the finally output result is more accurate, and the predicted coordinate data of the positions of the predicted slider gaps is closer to the annotated coordinate data of the actual positions of the slider gaps.

[0039] In the embodiments of the present disclosure, there are no specific limitations on the multiple key points for each slider notch. Based on the different shapes of each slider notch, the corresponding multiple key points are different. However, for each slider notch, the multiple key points at least include the upper left corner key point, the lower left corner key point, the upper right corner key point, and the lower right corner key point corresponding to the smallest rectangular region determined based on the respective boundary points of the current slider notch; wherein, the smallest rectangular region is the region that just frames the current slider notch.

[0040] In a possible implementation manner, comparing the output with the corresponding labeled data to determine whether to continue iterative training of the model includes: when the interface image includes a slider notch,

[0041] Based on the output, determining the predicted image region corresponding to the slider notch in the interface image;

[0042] Based on the corresponding labeled data, determining the actual image region corresponding to the slider notch in the interface image;

[0043] Based on the intersection over union between the predicted image region and the actual image region, determining whether to continue iterative training of the model.

[0044] In an actual application scenario, when the interface image includes a slider notch, it is possible to determine whether to continue iterative training of the model through the intersection over union between the predicted image region corresponding to the slider notch and the actual image region.

[0045] In an actual application scenario, if the intersection over union between the predicted image region and the actual image region for pre-configuring the stop of iterative training of the model is greater than or equal to a first preset value, and the number of test samples in the test set that meet the foregoing condition of the intersection over union (the intersection over union between the preset image region of the slider notch and the actual image region is greater than or equal to the first preset value) is greater than or equal to a second preset value, then it is determined to stop iterative training of the model; otherwise, continue iterative training of the model until the above conditions are met.

[0046] Exemplarily, in a specific application scenario, the first preset value is configured as 0.95, and the second preset value is also configured as 0.95. Then, when the current intersection over union between the predicted image region and the actual image region corresponding to the current slider notch is greater than or equal to 0.95, and at least 950 of the test samples in the test set (for example, the number of test samples in the test set is 1000) have the intersection over union between the predicted image region and the actual image region corresponding to the sliding notch in the interface image that meets the condition that its intersection over union is greater than or equal to 0.95, then it is determined to stop iterative training of the model; otherwise, continue iterative training of the above model until the above conditions are met.

[0047] In the embodiments of the present disclosure, during the above model iterative training process, no specific limitations are imposed on the specific values of the first preset value and the second preset value. In actual application scenarios, the larger the first preset value and the second preset value are, the higher the accuracy of the slider notch prediction model obtained by training, and the more accurately the coordinates of the slider notch in the interface image can be predicted, so that the client application can perform accurate and automatic sliding verification based on the received coordinates of the slider notch position.

[0048] In a possible implementation manner, comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model includes: when the interface image includes multiple slider notches,

[0049] Based on the output, determining the predicted image regions corresponding to the multiple slider notches in the interface image respectively;

[0050] Based on the corresponding annotation data, determining the actual image regions corresponding to the multiple slider notches in the interface image respectively;

[0051] Based on the intersection over union of the predicted image regions and the corresponding actual image regions of the multiple slider notches, determining whether to continue iteratively training the model.

[0052] When the interface image includes multiple slider notches, through the above iterative training process, a slider notch prediction model capable of accurately positioning the coordinates of the slider notch in the interface image can be obtained.

[0053] In actual application scenarios, different from the application scenario where the interface image includes one slider notch, for the application scenario where the interface image includes multiple slider notches, the intersection over union of all sliders in the current interface image can be judged by calculating the weighted average, or each intersection over union can also be judged separately whether it meets the preset conditions. Specifically, taking the calculation of the weighted average as an example, if the weighted average threshold of the intersection over union of multiple sliders in the currently configured interface image is the third preset value, and the number of intersections over union corresponding to the test samples meeting the above conditions in the test set is greater than or equal to the fourth preset value, it is determined to stop iteratively training the model; otherwise, continue iteratively training the model until the above conditions are met.

[0054] Exemplarily, in a specific application scenario, the third preset value is configured to be 0.8 and the fourth preset value is configured to be 0.8. If the weighted average of the intersection over union of multiple sliders in the current interface image is greater than or equal to 0.8, and the weighted average of the intersection over union corresponding to the sliding notches in at least 800 interface images among the test samples in the test set (for example, the number of test samples in the test set is 1000) satisfies that its intersection over union is greater than or equal to 0.8, then it is determined to stop the iterative training of the model; otherwise, continue the iterative training of the above model until the above conditions are met.

[0055] In the embodiments of the present disclosure, during the iterative training of the above model, no specific limitations are imposed on the specific values of the third preset value and the fourth preset value. In actual application scenarios, the larger the third preset value and the fourth preset value are, the higher the accuracy of the trained slider notch prediction model is, and the more accurately the coordinates of the position of the slider notch in the interface image can be predicted, so that the application at the application end can perform accurate and automatic sliding verification based on the received coordinates of the position of the slider notch.

[0056] Step S103: Send the obtained coordinate data to the client application, so that the client application controls at least one slider in the slider verification interface to move to the corresponding image area according to the received coordinate data to implement slider verification.

[0057] In the embodiments of the present disclosure, an interface image of the slider verification interface is obtained; the slider notch prediction model is used to perform image recognition on the interface image to obtain coordinate data for positioning the position of the slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; and the obtained coordinate data is sent to the client application, so that the client application controls at least one slider in the slider verification interface to move to the corresponding image area according to the received coordinate data to implement slider verification. The slider verification method provided by the embodiments of the present disclosure, because the slider notch prediction model is introduced and the slider notch prediction model is a general model, can perform image recognition on the interface images of different types of slider verification interfaces, accurately predict the coordinate data of the position of the corresponding slider notch, and send the coordinate data to the client application for automatic slider verification. In this way, the versatility and generalization performance of slider verification can be improved.

[0058] Please refer to Figure 2 , which shows a flowchart of another slider verification method provided by some embodiments of the present disclosure. This slider verification method is applied to a client application. As Figure 2 shown, the slider verification method may include the following steps:

[0059] Step S201: Obtain the interface image of the slider verification interface.

[0060] In the embodiments of the present disclosure, there are no specific limitations on the content shown in the interface image of the slider verification interface, the number and shape of the sliders in the interface image, and the number and shape of the slider gaps corresponding to the sliders. According to the requirements of different application scenarios, the above content can be configured and adjusted accordingly, which will not be elaborated here.

[0061] Step S202: Use the slider gap prediction model to perform image recognition on the interface image to obtain coordinate data for positioning the position of the slider gap in the interface image, where the slider gap prediction model is pre-trained by a data set involving various types of slider gaps.

[0062] In a possible implementation manner, the slider gap prediction model is trained through the following operations:

[0063] Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data. Each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating multiple key points of each slider gap in at least one slider gap in the corresponding first interface image;

[0064] Traverse the training sample set, and perform a first operation each time a first interface image is traversed to iteratively train a predetermined model until the slider gap prediction model is trained. The first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model; in this way, through the above iterative training process, the model can be optimized, so that the finally output result is more accurate, and the predicted coordinate data of the position of the predicted slider gap is closer to the annotated coordinate data of the position of the actually annotated slider gap.

[0065] For the iterative training process of the slider gap prediction model in the above steps, refer to the description of the same or similar parts above, which will not be elaborated here.

[0066] Step S203: Based on the obtained coordinate data, control at least one slider in the slider verification interface to move to the corresponding image area to implement slider verification. In this way, the client application automatically locates the position of the slider gap and controls the slider to move to the positioning position to implement slider verification. Compared with Figure 1For the server to locate the position of the slider and the client to perform automatic slider verification based on the positioning information provided by the server, the slider verification method in this embodiment can reduce the interaction with the server, thereby achieving fast response, automatic and fast verification, effectively avoiding possible delay phenomena, and ultimately improving the user experience.

[0067] Please refer to Figure 3 , which shows a flowchart of another slider verification method provided by some embodiments of the present disclosure. This slider verification method is applied to a client application, such as Figure 3 shown, and the slider verification method may include the following steps:

[0068] Step S301: Obtain coordinate data from the server. Among them, the coordinate data is obtained by the server by acquiring the interface image of the slider verification interface and using a slider notch prediction model to perform image recognition on the interface image to locate the position of the slider notch in the interface image. The slider notch prediction model is pre-trained by a dataset involving various types of slider notches.

[0069] In a possible implementation manner, the slider notch prediction model is trained through the following operations:

[0070] Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data. Each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating multiple key points of at least one slider notch in the corresponding first interface image;

[0071] Traverse the training sample set, and perform a first operation each time a first interface image is traversed to iteratively train a predetermined model until the slider notch prediction model is trained. Among them, the first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model. In this way, through the above iterative training process, the model can be optimized, so that the finally output result is more accurate, and the predicted coordinate data of the position of the predicted slider notch is closer to the annotated coordinate data of the actual position of the slider notch.

[0072] For the iterative training process of the slider notch prediction model in the above steps, refer to the description of the same or similar parts above, and details will not be repeated here.

[0073] Step S302: According to the obtained coordinate data, control at least one slider in the slider verification interface to move to the corresponding image area to achieve slider verification.

[0074] In a possible implementation, according to the obtained coordinate data, controlling at least one slider in the slider verification interface to move to the corresponding image area to implement slider verification includes: when there is one slider in the slider verification interface,

[0075] In response to determining that the slider needs to slide along the horizontal slider bar towards the slider notch on the slider verification interface, extracting the corresponding abscissa data from the obtained coordinate data;

[0076] Based on the abscissa data and the initial position information of the slider, determining the first offset distance for the slider to slide along the horizontal slider bar;

[0077] Based on the first offset distance, controlling the slider to slide along the horizontal slider bar to the image area where the slider notch is located to implement slider verification.

[0078] In the embodiments of the present disclosure, no specific limitation is imposed on the first offset distance in the above steps. By controlling the current slider to slide left or right along the horizontal slider bar from the initial position by the first offset distance to the image area where the slider notch is located according to the abscissa data in the obtained coordinate data in the horizontal direction, slider verification is implemented.

[0079] In a possible implementation, according to the obtained coordinate data, controlling at least one slider in the slider verification interface to move to the corresponding image area to implement slider verification includes: when there is one slider in the slider verification interface,

[0080] In response to determining that the slider needs to slide along the vertical slider bar towards the slider notch on the slider verification interface, extracting the corresponding ordinate data from the obtained coordinate data;

[0081] Based on the ordinate data and the initial position information of the slider, determining the second offset distance for the slider to slide along the vertical slider bar;

[0082] Based on the second offset distance, controlling the slider to slide along the vertical slider bar to the image area where the slider notch is located to implement slider verification.

[0083] In the embodiments of the present disclosure, no specific limitation is imposed on the second offset distance in the above steps. By controlling the current slider to slide up or down along the vertical slider bar from the initial position by the second offset distance to the image area where the slider notch is located according to the ordinate data in the obtained coordinate data in the vertical direction, slider verification is implemented. Compared with the existing slider verification methods, the above-mentioned method of sliding up or down along the vertical slider bar in the vertical direction enriches the existing single-direction sliding verification method.

[0084] In a possible implementation, according to the obtained coordinate data, at least one slider in the slider verification interface is controlled to move to the corresponding image area to implement slider verification, including: when there are multiple sliders in the slider verification interface, for each of the sliders,

[0085] Based on the obtained coordinate data, determine the slider notch that matches the slider;

[0086] In response to determining that the slider needs to slide along the horizontal slider bar towards the slider notch on the slider verification interface, extract the corresponding abscissa data from the obtained coordinate data;

[0087] Based on the abscissa data and the initial position information of the slider, determine the third offset distance for the slider to slide along the horizontal slider bar;

[0088] Based on the third offset distance, control the slider to slide along the horizontal slider bar to the image area where the slider notch is located to implement slider verification.

[0089] In a possible implementation, based on the obtained coordinate data, determining the slider notch that matches the slider includes the following steps:

[0090] Based on the obtained coordinate data, determine the ordinate data corresponding to each slider notch; and

[0091] Obtain the ordinate data of the slider;

[0092] By comparing the ordinate data of the slider with the ordinate data corresponding to each slider notch, determine the slider notch that matches the slider among each slider notch.

[0093] In an actual application scenario, when the interface image of the slider verification interface includes multiple sliders and corresponding slider notches, during the slider verification process of sliding a specific distance to the left or right along the horizontal slider bar, through the above steps, each slider and the corresponding slider notch can be determined one by one.

[0094] In the embodiments of the present disclosure, no specific limitation is imposed on the third offset distance in the above steps. Compared with the case where there is one slider in the slider verification interface, in the case where there are multiple sliders in the slider verification interface, it is similar to the slider verification method with one slider mentioned above. The difference is that in the case where there are multiple sliders in the slider verification interface and each of the multiple sliders is a real slider that needs to be verified, it is necessary to traverse each of the multiple sliders in the slider verification interface. For each slider, the third offset distance is slid along the horizontal slider to the image area where the slider notch is located for separate verification through the above method. Only when all sliders pass the verification can the verification be finally passed; in this way, automatic verification can be performed for complex slider verification scenarios, increasing the possible applicable scenarios of this slider verification method.

[0095] In an actual application scenario, in the case where there are multiple sliders and corresponding slider notches in the slider verification interface, in addition to the application scenario where all of the above multiple sliders are valid and need to pass the verification, there is also a case where although there are multiple sliders and corresponding slider notches in the slider verification interface, only one is a valid slider. The verification is specifically achieved through the following steps: The client application receives the coordinate data of multiple slider notches and the coordinate data of the valid slider. Based on the fact that only one slider notch is valid, based on the ordinate data in the coordinate data of the valid slider, for the ordinate data corresponding to the coordinate data of the multiple slider notches received one by one based on this ordinate data, a comparison is made one by one, and the slider notch whose ordinate is consistent with that of the valid slider is determined as the target slider notch. And based on the abscissa data in the coordinate data of this target slider notch, a specific offset distance is slid along the horizontal slider to the image area where this slider notch is located for verification; as long as this target slider notch passes the verification; in this way, not only can automatic verification be performed for complex slider verification scenarios, but also the speed of passing the verification is improved.

[0096] In a possible implementation manner, according to the obtained coordinate data, controlling at least one slider in the slider verification interface to move to the corresponding image area to implement slider verification includes: in the case where there are multiple sliders in the slider verification interface, for each of them,

[0097] Based on the obtained coordinate data, determine the slider notch that matches this slider;

[0098] In response to determining that this slider needs to slide along the vertical slider to the slider notch on the slider verification interface, extract the corresponding ordinate data from the obtained coordinate data;

[0099] Based on the ordinate data and the initial position information of this slider, determine the fourth offset distance for this slider to slide along the vertical slider;

[0100] Based on the fourth offset distance, the slider is controlled to slide along the longitudinal slide bar to the image area where the slider gap is located to implement slider verification.

[0101] In a possible implementation, determining a slider gap matching the slider based on the acquired coordinate data includes the following steps:

[0102] Based on the acquired coordinate data, determining the horizontal coordinate data corresponding to each slider gap; and

[0103] Get the horizontal coordinate data of the slider;

[0104] By comparing the horizontal coordinate data of the slider with the horizontal coordinate data corresponding to each slider gap, the slider gap that matches the slider among the slider gaps is determined.

[0105] In actual application scenarios, when the interface image of the slider verification interface includes multiple sliders and corresponding slider gaps, during the slider verification process of sliding up or down a specific distance along the longitudinal sliding bar, the above steps can be used to determine each slider and its corresponding slider gap one by one.

[0106] In the disclosed embodiment, there is no specific restriction on the fourth offset distance in the above steps. Compared with the case where the slider verification interface includes one slider, the case where the slider verification interface includes multiple sliders is similar to the slider verification method of the aforementioned one slider, except that when the slider verification interface includes multiple sliders, and each of the multiple sliders is a real slider that needs to be verified, it is necessary to traverse each of the multiple sliders in the slider verification interface, and for each slider, slide the fourth offset distance along the longitudinal sliding bar to the image area where the slider notch is located to perform separate verification. Only when all sliders pass the verification can the verification be finally achieved. In this way, automatic verification can be performed for complex slider verification scenarios, increasing the possible applicable scenarios of the slider verification method.

[0107] In an actual application scenario, when there are multiple sliders and corresponding slider gaps in the slider verification interface, in addition to the above application scenarios where all the multiple sliders are valid and need to pass the verification, there is also a situation where although there are multiple sliders and corresponding slider gaps in the slider verification interface, only one slider is valid. The verification is specifically implemented through the following steps: The client application receives the coordinate data of multiple slider gaps and the coordinate data of the valid slider. If only one of the slider gaps is valid, based on the abscissa data in the coordinate data of the valid slider, for each abscissa data corresponding to the received coordinate data of the multiple slider gaps, perform a one-by-one comparison, and determine the slider gap whose abscissa is the same as that of the valid slider as the target slider gap. Then, based on the ordinate data in the coordinate data of the target slider gap, slide a specific offset distance along the vertical slider to the image area where the slider gap is located for verification; as long as the target slider gap passes the verification. In this way, not only can automatic verification be performed for complex slider verification scenarios, but also the verification passing speed is improved.

[0108] In a possible implementation manner, the slider verification method provided by the embodiments of the present disclosure further includes the following steps:

[0109] After controlling at least one slider in the slider verification interface to move to the corresponding image area, in response to at least one slider not returning to its respective initial position within a preset time period, it is determined that at least one slider has passed the verification; in this way, through the above feedback step, it can be determined whether the slider has passed the verification. If it is determined through the above feedback step that a certain slider has not passed the verification smoothly, re-verification is performed until the verification passes.

[0110] In the above embodiment, a slider verification method is provided. Correspondingly, the present disclosure also provides a slider verification device. The slider verification device provided by the embodiments of the present disclosure can implement the above slider verification method, and the slider verification device can be implemented in a software, hardware, or a combination of software and hardware manner. For example, the slider verification device can include integrated or separate functional modules or units to execute the corresponding steps in the above various methods.

[0111] Please refer to Figure 4 , which shows a schematic diagram of a slider verification device provided by some embodiments of the present disclosure. The device is applied to the server. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple. For the relevant parts, refer to the partial description of the method embodiment. The device embodiments described below are merely illustrative.

[0112] As Figure 4 shown, the slider verification device 400 may include:

[0113] An acquisition unit 401, configured to acquire an interface image of a slider verification interface;

[0114] An image recognition unit 402, configured to perform image recognition on the interface image by using a slider notch prediction model to obtain coordinate data for positioning the position of a slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches;

[0115] A sending unit 403, configured to send the acquired coordinate data to a client application, so that the client application controls at least one slider in the slider verification interface to move to a corresponding image area according to the received coordinate data to implement slider verification.

[0116] In some embodiments of the embodiments of the present disclosure, the acquisition unit 401 is configured to:

[0117] Acquire an interface image of a slider verification interface including at least one slider notch.

[0118] In some embodiments of the embodiments of the present disclosure, the device further includes:

[0119] A training unit (not shown in Figure 4 ), configured to:

[0120] Train a slider notch prediction model through the following operations:

[0121] Acquire a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data, each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating a plurality of key points of each slider notch in at least one slider notch in the corresponding first interface image;

[0122] Traverse the training sample set, and perform a first operation each time a first interface image is traversed to perform iterative training on a predetermined model until the slider notch prediction model is trained;

[0123] where the first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iterative training on the model.

[0124] In some embodiments of the embodiments of the present disclosure, the training unit is specifically configured to: when the interface image includes one slider notch,

[0125] Based on the output, determine a predicted image area corresponding to the slider notch in the interface image;

[0126] Based on the corresponding annotation data, determine an actual image area corresponding to the slider notch in the interface image;

[0127] Determine whether to continue iterative training of the model based on the intersection over union between the predicted image regions and the actual image regions.

[0128] In some embodiments of the present disclosure, the training unit is specifically configured to: when the interface image includes multiple slider notches,

[0129] Based on the output, determine the predicted image regions corresponding to the multiple slider notches in the interface image respectively;

[0130] Based on the corresponding annotation data, determine the actual image regions corresponding to the multiple slider notches in the interface image respectively;

[0131] Determine whether to continue iterative training of the model based on the intersection over union between the predicted image regions and the corresponding actual image regions of the multiple slider notches.

[0132] Please refer to Figure 5 , which shows a schematic diagram of another slider verification device provided by some embodiments of the present disclosure. The device is applied to a client application. Since the device embodiments are basically similar to the method embodiments, the description is relatively simple. For the related parts, please refer to the partial description of the method embodiments. The device embodiments described below are only illustrative.

[0133] As Figure 5 shown, the slider verification device 500 may include:

[0134] An acquisition unit 501, configured to acquire an interface image of a slider verification interface;

[0135] An image recognition unit 502, configured to perform image recognition on the interface image by using a slider notch prediction model to obtain coordinate data for positioning the positions of the slider notches in the interface image, where the slider notch prediction model is pre-trained by a data set involving multiple types of slider notches;

[0136] A control unit 503, configured to control at least one slider in the slider verification interface to move to the corresponding image region to implement slider verification based on the acquired coordinate data.

[0137] Please refer to Figure 6 , which shows a schematic diagram of yet another slider verification device provided by some embodiments of the present disclosure. The device is applied to a client application. Since the device embodiments are basically similar to the method embodiments, the description is relatively simple. For the related parts, please refer to the partial description of the method embodiments. The device embodiments described below are only illustrative.

[0138] An acquisition unit 601, configured to acquire coordinate data from a server, where the coordinate data is obtained by the server acquiring an interface image of a slider verification interface and performing image recognition on the interface image by using a slider notch prediction model to locate the position of a slider notch in the interface image, and the slider notch prediction model is pre-trained by a data set involving various types of slider notches; and

[0139] A control unit 602, configured to control at least one slider in the slider verification interface to move to a corresponding image area according to the acquired coordinate data to implement slider verification.

[0140] In some embodiments of the present disclosure, the control unit 602 is specifically configured to: when there is one slider in the slider verification interface,

[0141] in response to determining that the slider needs to slide along a horizontal slider bar towards the slider notch on the slider verification interface, extract corresponding abscissa data from the acquired coordinate data;

[0142] based on the abscissa data and the initial position information of the slider, determine a first offset distance for the slider to slide along the horizontal slider bar;

[0143] based on the first offset distance, control the slider to slide along the horizontal slider bar to the image area where the slider notch is located to implement slider verification.

[0144] In some embodiments of the present disclosure, the control unit 602 is specifically configured to: when there is one slider in the slider verification interface,

[0145] in response to determining that the slider needs to slide along a vertical slider bar towards the slider notch on the slider verification interface, extract corresponding ordinate data from the acquired coordinate data;

[0146] based on the ordinate data and the initial position information of the slider, determine a second offset distance for the slider to slide along the vertical slider bar;

[0147] based on the second offset distance, control the slider to slide along the vertical slider bar to the image area where the slider notch is located to implement slider verification.

[0148] In some embodiments of the present disclosure, the control unit 602 is specifically configured to: when there are multiple sliders in the slider verification interface, for each of the sliders,

[0149] based on the acquired coordinate data, determine a slider notch that matches the slider;

[0150] in response to determining that the slider needs to slide along a horizontal slider bar towards the slider notch on the slider verification interface, extract corresponding abscissa data from the acquired coordinate data;

[0151] Based on the abscissa data and the initial position information of the slider, determine a third offset distance for the slider to slide along the horizontal slider bar;

[0152] Based on the third offset distance, control the slider to slide along the horizontal slider bar to the image area where the slider notch is located to implement slider verification.

[0153] In some embodiments of the present disclosure, the control unit 602 is specifically configured to: in the case where there are multiple sliders in the slider verification interface, for each of the sliders,

[0154] Based on the acquired coordinate data, determine the slider notch that matches the slider;

[0155] In response to determining that the slider needs to slide along the vertical slider bar to the slider notch on the slider verification interface, extract the corresponding ordinate data from the acquired coordinate data;

[0156] Based on the ordinate data and the initial position information of the slider, determine a fourth offset distance for the slider to slide along the vertical slider bar;

[0157] Based on the fourth offset distance, control the slider to slide along the vertical slider bar to the image area where the slider notch is located to implement slider verification.

[0158] In some embodiments of the present disclosure, the control unit 602 is specifically configured to:

[0159] Based on the acquired coordinate data, determine the ordinate data corresponding to each slider notch; and

[0160] Acquire the ordinate data of the slider;

[0161] By comparing the ordinate data of the slider with the ordinate data corresponding to each slider notch, determine the slider notch that matches the slider among each slider notch.

[0162] In some embodiments of the present disclosure, the control unit 602 is specifically configured to:

[0163] Based on the acquired coordinate data, determine the abscissa data corresponding to each slider notch; and

[0164] Acquire the abscissa data of the slider;

[0165] By comparing the abscissa data of the slider with the abscissa data corresponding to each slider notch, determine the slider notch that matches the slider among each slider notch.

[0166] In some embodiments of the present disclosure, the device further includes:

[0167] A determination unit (not shown in Figure 6 ), after at least one slider in the control slider verification interface moves to the corresponding image area, determines that at least one slider has passed the verification in response to that at least one slider does not return to its respective initial position within a preset time period.

[0168] In some embodiments of the present disclosure, the slider verification devices 400, 500, and 600 provided by the embodiments of the present disclosure are based on the same inventive concept as the slider verification method provided by the foregoing embodiments of the present disclosure and have the same beneficial effects.

[0169] The present disclosure also provides an electronic device corresponding to the slider verification method provided by the foregoing embodiments. The electronic device may be an electronic device for a server, such as a server, including an independent server and a distributed server cluster, etc., to execute the above slider verification method; the electronic device may also be an electronic device for a client, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the above slider verification method.

[0170] Please refer to Figure 7 , which shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. As Figure 7 shown, the electronic device 40 includes: a processor 400, a memory 401, a bus 402, and a communication interface 403. The processor 400, the communication interface 403, and the memory 401 are connected through the bus 402; a computer program that can run on the processor 400 is stored in the memory 401, and when the processor 400 runs the computer program, it executes the foregoing slider verification method of the present disclosure.

[0171] Among them, the memory 401 may include a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 403 (which may be wired or wireless), a communication connection between this system network element and at least one other network element is realized, and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used.

[0172] The bus 402 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 401 is used to store a program. After receiving an execution instruction, the processor 400 executes the program, and the slider verification method disclosed in any of the foregoing embodiments of the present disclosure may be applied to the processor 400 or implemented by the processor 400.

[0173] The processor 400 may be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 400 or the instructions in the form of software. The above-mentioned processor 400 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute each method, step and logic block diagram disclosed in the embodiments of the present disclosure. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present disclosure can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 401, and the processor 400 reads the information in the memory 401 and combines its hardware to complete the steps of the above method.

[0174] The electronic device provided by the embodiments of the present disclosure and the slider verification method provided by the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by them.

[0175] The present disclosure also provides a computer-readable medium corresponding to the slider verification method provided in the foregoing embodiment. Please refer to Figure 8 , which shows that the computer-readable storage medium is an optical disc 50, on which a computer program (i.e., a program product) is stored. When the computer program is run by the processor, it will execute the foregoing slider verification method.

[0176] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here one by one.

[0177] The computer-readable storage medium provided by the above embodiments of the present disclosure and the slider verification method provided by the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0178] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to multiple embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0179] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0180] In several embodiments provided by the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed with each other may be through some communication interfaces, and the indirect couplings or communication connections of the devices or units may be in electrical, mechanical, or other forms.

[0181] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, the functional units in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

[0183] When the above-mentioned functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present disclosure. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0184] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present disclosure, and they should all be covered by the scope of the claims and the description of the present disclosure.

Claims

1. A slider verification method, comprising: Obtain the interface image of the slider verification interface; Train a slider notch prediction model through the following operations: Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data, each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating a plurality of key points of each slider notch in at least one slider notch in the corresponding first interface image; Traverse the training sample set, and perform a first operation once for each traversed first interface image to iteratively train a predetermined model until the slider notch prediction model is trained, where the first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model; Use the slider notch prediction model to perform image recognition on the interface image to obtain coordinate data for positioning the position of the slider notch in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; Send the obtained coordinate data to the client application, so that the client application controls at least one slider in the slider verification interface to move to the corresponding image area according to the received coordinate data to implement slider verification.

2. The method according to claim 1, wherein, The obtaining the interface image of the slider verification interface includes: Obtain the interface image of the slider verification interface including at least one slider notch.

3. The method according to claim 1, wherein, The comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model includes: when there is one slider notch in the interface image, based on the output, determine the predicted image area corresponding to the slider notch in the interface image; Based on the corresponding annotation data, determine the actual image area corresponding to the slider notch in the interface image; Based on the intersection over union between the predicted image area and the actual image area, determine whether to continue iteratively training the model.

4. The method according to claim 1, wherein, The comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model includes: when there are multiple slider notches in the interface image, based on the output, determine the predicted image areas corresponding to the multiple slider notches in the interface image respectively; Based on the corresponding annotation data, determine the actual image areas corresponding to the multiple slider notches in the interface image respectively; Based on the intersection over union between the predicted image areas of the multiple slider notches and the corresponding actual image areas, determine whether to continue iteratively training the model.

5. A slider verification method, comprising: Obtain the interface image of the slider verification interface; Train a slider notch prediction model through the following operations: Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data, each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating a plurality of key points of each slider notch in at least one slider notch in the corresponding first interface image; Traverse the training sample set, and perform a first operation each time a first interface image is traversed to iteratively train a predetermined model until the slider notch prediction model is obtained. The first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model; Use the slider notch prediction model to perform image recognition on the interface image to obtain coordinate data for positioning the position of the slider notch in the interface image. The slider notch prediction model is pre-trained from a data set involving various types of slider notches; Based on the obtained coordinate data, control at least one slider in the slider verification interface to move to the corresponding image area to achieve slider verification.

6. A slider verification method, comprising: The slider notch prediction model is obtained through the following operations: Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data. Each first interface image corresponds to an annotation data, and each annotation data is obtained by annotating multiple key points of each slider notch in at least one slider notch in the corresponding first interface image; Traverse the training sample set, and perform a first operation each time a first interface image is traversed to iteratively train a predetermined model until the slider notch prediction model is obtained. The first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model; Obtain coordinate data from the server. The coordinate data is for positioning the position of the slider notch in the interface image obtained by the server by acquiring the interface image of the slider verification interface and using the slider notch prediction model to perform image recognition on the interface image. The slider notch prediction model is pre-trained from a data set involving various types of slider notches; and According to the obtained coordinate data, control at least one slider in the slider verification interface to move to the corresponding image area to achieve slider verification.

7. The method according to claim 6, wherein, The controlling at least one slider in the slider verification interface to move to the corresponding image area to achieve slider verification according to the obtained coordinate data includes: when there is one slider in the slider verification interface, In response to determining that the slider needs to slide along the horizontal slider bar towards the slider notch on the slider verification interface, extract the corresponding abscissa data from the obtained coordinate data; Based on the abscissa data and the initial position information of the slider, determine the first offset distance for the slider to slide along the horizontal slider bar; Based on the first offset distance, control the slider to slide along the horizontal slider bar to the image area where the slider notch is located to achieve slider verification.

8. The method according to claim 6, wherein, Controlling at least one slider in the slider verification interface to move to a corresponding image area for slider verification according to the obtained coordinate data includes: when there is one slider in the slider verification interface, In response to determining that the slider needs to slide along the vertical slider bar towards the slider notch on the slider verification interface, extracting the corresponding ordinate data from the obtained coordinate data; Based on the ordinate data and the initial position information of the slider, determining a second offset distance for the slider to slide along the vertical slider bar; Based on the second offset distance, controlling the slider to slide along the vertical slider bar to the image area where the slider notch is located to achieve slider verification.

9. The method according to claim 6, wherein Controlling at least one slider in the slider verification interface to move to a corresponding image area for slider verification according to the obtained coordinate data includes: When there are multiple sliders in the slider verification interface, for each slider, determining a slider notch that matches the slider based on the obtained coordinate data; In response to determining that the slider needs to slide along the horizontal slider bar towards the slider notch on the slider verification interface, extracting the corresponding abscissa data from the obtained coordinate data; Based on the abscissa data and the initial position information of the slider, determining a third offset distance for the slider to slide along the horizontal slider bar; Based on the third offset distance, controlling the slider to slide along the horizontal slider bar to the image area where the slider notch is located to achieve slider verification.

10. The method according to claim 6, wherein Controlling at least one slider in the slider verification interface to move to a corresponding image area for slider verification according to the obtained coordinate data includes: when there are multiple sliders in the slider verification interface, for each slider, determining a slider notch that matches the slider based on the obtained coordinate data; In response to determining that the slider needs to slide along the vertical slider bar towards the slider notch on the slider verification interface, extracting the corresponding ordinate data from the obtained coordinate data; Based on the ordinate data and the initial position information of the slider, determining a fourth offset distance for the slider to slide along the vertical slider bar; Based on the fourth offset distance, controlling the slider to slide along the vertical slider bar to the image area where the slider notch is located to achieve slider verification.

11. The method according to claim 9, wherein Determining a slider notch that matches the slider based on the obtained coordinate data includes: Based on the obtained coordinate data, determining the ordinate data corresponding to each slider notch; and Obtaining the ordinate data of the slider; By comparing the ordinate data of the slider with the ordinate data corresponding to each slider notch, determining the slider notch that matches the slider among the various slider notches.

12. The method according to claim 10, wherein Determining a slider notch that matches the slider based on the obtained coordinate data includes: Based on the obtained coordinate data, determining the abscissa data corresponding to each slider notch; and Obtaining the abscissa data of the slider; By comparing the abscissa data of the slider with the abscissa data corresponding to each slider notch, determining the slider notch that matches the slider among the various slider notches.

13. The method according to claim 11, further comprising: After controlling at least one slider in the slider verification interface to move to the corresponding image area, in response to the at least one slider not returning to their respective initial positions within a preset time period, it is determined that the at least one slider has passed the verification.

14. A slider verification device, comprising: An acquisition unit, configured to acquire an interface image of the slider verification interface; The slider notch prediction model is trained through the following operations: Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data, each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating a plurality of key points of each slider notch in at least one slider notch in the corresponding first interface image; Traverse the training sample set, and perform a first operation each time a first interface image is traversed to iteratively train a predetermined model until the slider notch prediction model is trained. The first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model; An image recognition unit, configured to perform image recognition on the interface image by using the slider notch prediction model to obtain coordinate data for positioning the positions of the slider notches in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; A sending unit, configured to send the acquired coordinate data to a client application, so that the client application controls at least one slider in the slider verification interface to move to the corresponding image area according to the received coordinate data to implement slider verification.

15. A slider verification device, comprising: An acquisition unit, configured to acquire an interface image of the slider verification interface; The slider notch prediction model is trained through the following operations: Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data, each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating a plurality of key points of each slider notch in at least one slider notch in the corresponding first interface image; Traverse the training sample set, and perform a first operation each time a first interface image is traversed to iteratively train a predetermined model until the slider notch prediction model is trained. The first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model; An image recognition unit, configured to perform image recognition on the interface image by using the slider notch prediction model to obtain coordinate data for positioning the positions of the slider notches in the interface image, where the slider notch prediction model is pre-trained by a data set involving various types of slider notches; A control unit, configured to control at least one slider in the slider verification interface to move to the corresponding image area based on the acquired coordinate data to implement slider verification.

16. A slider verification device, comprising: An acquisition unit, configured to train the slider notch prediction model through the following operations: Obtain a training sample set, where the training sample set includes a plurality of first interface images and a plurality of annotation data, each first interface image corresponds to one annotation data, and each annotation data is obtained by annotating a plurality of key points of each slider notch in at least one slider notch in the corresponding first interface image; Traverse the training sample set, and perform a first operation once for each traversed first interface image to iteratively train a predetermined model until the slider notch prediction model is trained, where the first operation includes: using the currently traversed first interface image as the input of the predetermined model to obtain a corresponding output, and comparing the output with the corresponding annotation data to determine whether to continue iteratively training the model; Obtain coordinate data from a server, where the coordinate data is used by the server to locate the position of a slider notch in an interface image by obtaining an interface image of a slider verification interface and performing image recognition on the interface image using the slider notch prediction model, and the slider notch prediction model is pre-trained by a data set involving various types of slider notches; and A control unit, configured to control at least one slider in the slider verification interface to move to a corresponding image area according to the obtained coordinate data to implement slider verification.

17. An electronic device, characterized in that, The electronic device includes: A processor; A memory for storing executable instructions executable by the processor; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method according to any one of claims 1 to 13 above.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 13 above.

19. A computer program product, comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-13.

Images