Verification operation identification method and device, electronic equipment and storage medium

Abstract

The invention discloses a verification operation identification method and device, electronic equipment and a storage medium. The method comprises the following steps: in response to a trigger operation on a verification interface, detecting first information of the verification interface, and judging whether a plurality of reference operation positions have continuous changes or not; second information corresponding to the verification interface is obtained according to the first information, the second information comprises first track attribute information and first operation attribute information, or the second information comprises second operation attribute information; the reference trajectory attribute is used for indicating a trajectory feature formed by an operation position triggered by executing a page interaction operation on the verification interface after the verification interface is triggered, and the operation attribute information is used for indicating an operation feature generated after the operation position triggered by the page interaction operation for the verification interface enters a verification area; and determining whether the page interaction operation of the verification interface is real user operation according to the second information. According to the technical scheme, the accuracy of identifying the real user through the verification operation is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of recognition, and in particular, to a verification operation recognition method and device, an electronic device, and a storage medium. BACKGROUND

[0002] Currently, a picture verification method can be used to identify whether a page interaction operation is performed by a real user or a script simulation user. Since a script can obtain the content on the verification picture from the verification interface, and by identifying and analyzing the page interaction operation, the verification content corresponding to the verification picture can be obtained, and the verification can be passed successfully, resulting in low accuracy of the method of identifying a real user by picture verification. SUMMARY

[0003] The present application provides a verification operation recognition method and device, an electronic device, and a storage medium to solve the problem of low accuracy of identifying a real user by verification operation.

[0004] According to an aspect of the present application, a verification operation recognition method is provided, which includes:

[0005] In response to a triggering operation on the verification interface, first information of the verification interface is detected, the first information being used to indicate whether there is a continuity change in a plurality of reference operation positions, the plurality of reference operation positions being sequentially triggered operation positions of the page interaction operation performed on the verification interface;

[0006] Second information corresponding to the verification interface is obtained according to the first information; wherein the second information includes first trajectory attribute information and first operation attribute information, or the second information includes second operation attribute information, the trajectory attribute information being used to indicate a trajectory feature formed by the operation positions triggered by performing the page interaction operation on the verification interface after the verification interface is triggered, the operation attribute information being used to indicate an operation feature generated after the operation position triggered by the page interaction operation on the verification interface enters a verification area, the first operation attribute information and the second operation attribute information each including operation attribute content types, whether there is a continuity change in the plurality of reference operation positions, and a verification type adopted in the verification area of the verification interface;

[0007] It is determined whether the page interaction operation of the verification interface is a real user operation according to the second information.

[0008] According to an aspect of the present application, a verification operation recognition device is provided, which includes:

[0009] The first information detection module is configured to detect first information of the verification interface in response to a triggering operation of the verification interface, the first information being used to indicate whether there is a continuity change in a plurality of reference operation positions sequentially triggered by page interaction operations performed on the verification interface.

[0010] The second information acquisition module is configured to acquire second information corresponding to the verification interface according to the first information, wherein the second information includes first trajectory attribute information and first operation attribute information, or the second information includes second operation attribute information, the trajectory attribute information being used to indicate a trajectory feature formed by operation positions triggered by page interaction operations performed on the verification interface after the verification interface is triggered, the operation attribute information being used to indicate an operation feature generated after operation positions triggered by page interaction operations on the verification interface enter the verification area, the first operation attribute information and the second operation attribute information each including operation attribute content types, and the operation attribute content types being associated with whether there is a continuity change in the plurality of reference operation positions and a verification type adopted by a verification area in the verification interface.

[0011] The verification operation identification module is configured to determine whether the page interaction operation of the verification interface is a real user operation according to the second information.

[0012] According to another aspect of the present application, an electronic device is provided, and the electronic device includes:

[0013] at least one processor; and

[0014] a memory connected to the at least one processor in communication; wherein

[0015] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the verification operation identification method according to any one of the embodiments of the present application.

[0016] According to another aspect of the present application, a computer readable storage medium is provided, and the computer readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the verification operation identification method according to any one of the embodiments of the present application when the processor executes the computer instructions.

[0017] According to another aspect of the present application, a computer program product is provided, and the computer program product includes a computer program, and the computer program is used to implement the verification operation identification method according to any one of the embodiments of the present application when the computer program is executed by a processor.

[0018] The technical scheme of the embodiment of the present application can distinguish the two interactive operation modes of continuous movement and discrete clicking of the cursor in the verification interface by verifying the continuity change of the reference operation position in the interface, can provide a basis for selecting differentiated operation attribute information subsequently, and can significantly reduce the risk of faking the type of external input device through a script; the second information corresponding to the verification interface is adaptively acquired according to the continuity judgment result and the verification type of the verification area in the verification interface, so that the acquired second information is always accurately matched with the verification type of the current verification area and the current interactive operation mode, the interference of redundant information is reduced, and the distinguishability of real users and simulated users is improved; based on the second information extracted in a differentiated manner, it is determined whether the page interactive operation of the verification interface is a real user operation, the automatic script or machine simulation behavior can be quickly filtered, the smooth experience of real users is ensured, and the security and attack resistance of the verification operation are improved. Based on the above technical scheme, the continuity of the interactive operation mode is judged after the verification operation is triggered, only the attribute information matched with the current interactive operation mode and the verification type is acquired, the script cannot reproduce the space-time coupling relationship in the real interactive process of the verification operation, and therefore, the situation that the script acquires the page information and reversely cracks to simulate the user is avoided, and the accuracy of the verification operation in identifying real users is improved.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is a flowchart of a verification operation identification method according to an embodiment of the present application;

[0022] Figure 2 is a structural schematic diagram of a verification operation identification device according to an embodiment of the present application;

[0023] Figure 3 is a structural schematic diagram of an electronic device for implementing the verification operation identification method of the embodiment of the present application. DETAILED DESCRIPTION

[0024] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work should belong to the protection scope of the present application.

[0025] It should be noted that the terms "first", "second", and the like in the specification of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" 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 does not necessarily have to include only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to the process, method, product or device.

[0026] Figure 1 A flowchart of a verification operation identification method provided by an embodiment of the present application is provided. The embodiment can be applied to a case where it is necessary to identify whether a user operation is real through verification operation identification. The method can be executed by a verification operation identification device, which can be implemented in the form of hardware and / or software, and can be configured in any electronic device with network communication function.

[0027] As shown in Figure 1 The verification operation identification method provided by the embodiment of the present application can include the following processes.

[0028] S110, in response to a triggering operation on the verification interface, detecting first information of the verification interface, the first information being used to indicate whether there is a continuity change in a plurality of reference operation positions, the plurality of reference operation positions being each operation position sequentially triggered in performing a page interaction operation on the verification interface.

[0029] The verification interface can refer to a visual page used to present and receive interactive actions in the identity verification or human-computer discrimination process. The triggering operation can refer to an operation that first activates the verification interface by clicking, swiping, pressing, or other input methods. The first information can refer to a state indicator used to describe whether the plurality of reference operation positions present a continuity change. The reference operation position can refer to a spatial sampling point that is sequentially activated by page interaction operations in time sequence within the verification interface. The continuity change can refer to a situation that must pass through adjacent reference positions to reach non-adjacent reference positions from the current reference position. The page interaction operation can refer to an operation actively triggered on the verification interface by an input device, which will leave a detectable position trace in the verification interface. The input device can refer to a cursor-controllable external device such as a mouse, a touchpad, etc., or a device or tool for clicking touch such as a capacitive pen, or various input-enabled devices or tools simulated by scripts, etc.

[0030] By instantaneously detecting the continuity change of the reference operation position within the verification interface, the two interactive operation modes of cursor continuous movement and discrete clicking can be effectively distinguished, i.e., when the first information indicates that the plurality of reference positions have a continuity change, it indicates that the current interactive operation mode uses cursor continuous movement; when the first information indicates that the plurality of reference positions do not have a continuity change, it indicates that the current interactive operation mode uses discrete clicking. Exemplarily, the interactive operation mode of cursor continuous movement includes moving the operation position on the verification interface by a mouse, and the cursor is continuously changed, and the cursor cannot directly reach a non-adjacent position from the current position without the transition of adjacent positions. Exemplarily, the interactive operation mode of discrete clicking includes moving the operation position on the verification interface by a touch, and the cursor can directly reach a non-adjacent position from the current position without the transition of adjacent positions.

[0031] The interactive operation mode of cursor continuous movement can obtain the spatiotemporal information sequence of the cursor continuous movement trajectory during the operation process, and then obtain the trajectory smoothness, direction preference, speed adjustment rule, and motion intention of the cursor movement from the obtained spatiotemporal information sequence, which is used to identify whether the verification operation is a real user operation. The interactive operation mode of discrete clicking can obtain discrete information such as position coordinates, timestamps, and click intervals during the operation process, and then obtain information such as click frequency, spatial preference, and operation rhythm from these discrete information, which is used to identify whether the verification operation is a real user operation. The differential information generated by the two interactive operation modes during the operation process provides a basis for the adaptive selection of subsequent attribute information, so that the information obtained during the verification operation can better fit the current interactive operation mode, significantly enhancing the distinguishability of real users and automated scripts in the interactive operation mode, thereby reducing the misjudgment rate of identifying whether the verification operation is a real user operation.

[0032] Optionally, the first information on the verification interface, including steps A1-A4:

[0033] Step A1: Detect the multiple reference operation positions that are sequentially triggered by the page interaction operations on the verification interface.

[0034] By continuously monitoring input events on the verification interface, each valid page interaction is mapped to a corresponding reference operation position, and these positions are organized into an ordered set based on trigger time. This transforms the dynamic operation flow into a measurable sequence of spatial reference operation positions. Input events can refer to event models used to process various input devices. These models can encapsulate and respond to currently active input signals in real time, completing the position mapping and temporal serialization of the input signals, thereby extracting the spatiotemporal information of page interactions. This process transforms originally transient and invisible page interactions into temporally labeled spatial data, providing a computational basis for subsequently determining whether multiple reference operation positions exhibit continuous changes, while preserving the original sequential relationships of the interactions and avoiding information loss.

[0035] Step A2: For sequentially adjacent reference operation positions among multiple reference operation positions, detect whether the distance between two consecutive sequentially adjacent reference operation positions is less than a preset distance.

[0036] Sequential adjacency refers to two time points that are immediately adjacent to each other and have no preceding interval in a time series consisting of reference operation positions. Preset distance refers to a pre-defined distance threshold used to determine whether adjacent reference operation positions are continuous.

[0037] For the obtained sequence of reference operation positions, the spatial interval between sequentially adjacent reference operation positions is calculated to quantify the spatial and temporal closeness between adjacent interactive operations. By comparing with a preset distance, it is possible to distinguish whether adjacent reference operation positions are continuous.

[0038] Step A3: In response to the fact that the distance between two consecutive sequentially adjacent reference operation positions is less than a preset distance, the first information is determined to be that there is a continuous change in multiple reference operation positions.

[0039] Continuous change refers to a coherent and uninterrupted movement trend in space during page interaction operations. When the distance between adjacent reference operation positions is less than a preset distance, it indicates that the current operation sequence remains closely continuous in space. That is, the current page interaction operation uses a continuous cursor movement interaction method. In subsequent verification and detection operations, the spatiotemporal information sequence of the continuous cursor movement trajectory can be obtained to obtain the characteristic information of the page interaction operation.

[0040] Step A4: In response to the fact that the distance between two consecutive sequentially adjacent reference operation positions is not less than a preset distance, the first information is determined to be that there is no continuous change among the multiple reference operation positions.

[0041] The absence of continuous change can refer to significant spatial positional changes in page interaction operations at adjacent moments, exhibiting a jump-like movement trend. When the distance between adjacent reference operation positions is detected to be no less than a preset distance, it indicates that the current operation sequence is spatially discrete, meaning that the current page interaction operation uses a discrete click interaction method. In subsequent verification and detection operations, the characteristic information of the page interaction operation can be obtained by acquiring discrete information such as the click position coordinates, timestamps, and click intervals.

[0042] By instantly detecting and verifying the continuous changes in the reference operation position within the interface, it is possible to quickly distinguish between two interaction operation modes: continuous cursor movement and discrete clicks. This significantly reduces the risk of spoofing external input device types through scripts. At the same time, by distinguishing between the two interaction operation modes, characteristic information that better matches the current interaction operation scenario can be obtained, avoiding interference from redundant information. This reduces the false positive rate of identifying whether the operation is genuine by verifying the operation.

[0043] S120. Obtain the second information corresponding to the verification interface based on the first information; wherein, the second information includes first trajectory attribute information and first operation attribute information, or the second information includes second operation attribute information, the trajectory attribute information is used to indicate the trajectory features formed by the operation position triggered by performing page interaction operation on the verification interface after the verification interface is triggered, the operation attribute information is used to indicate the operation features generated after the operation position triggered by the page interaction operation on the verification interface enters the verification area, and the operation attribute content type included in the first operation attribute information and the second operation attribute information are related to whether there is a continuous change in multiple reference operation positions and the verification type used in the verification area of ​​the verification interface.

[0044] The second information may refer to the set of attribute information adaptively obtained according to the interactive operation method indicated by the first information, which is used to describe the characteristics of the interactive operation during the verification operation.

[0045] Trajectory attribute information can refer to the trajectory features of a curve or path fitted by a sequence of consecutive operation positions, and can be used to reflect the spatiotemporal characteristics of the continuous movement trajectory of the cursor. For example, trajectory attribute information may include the curvature, turning angle, etc. of the curve or path fitted by the sequence of consecutive operation positions, and may also include the spatial location and acquisition time corresponding to the consecutive operation positions.

[0046] Operation attribute information refers to the characteristics of interactive operations generated during the verification process after entering the verification area through page interaction. For example, operation attribute information may include the characteristics of various interactive operations obtained when performing clicks, swipes, inputs, etc., within the verification area, such as click location, swipe trajectory, and input content.

[0047] In this embodiment, the first trajectory attribute information can refer to the set of trajectory features that reflect the spatiotemporal characteristics of the continuous movement trajectory of the cursor when multiple reference operation positions undergo continuous changes. The first operation attribute information can refer to the set of operation features that reflect the characteristics of the verification operation when the operation position triggered by the page interaction operation of the verification interface enters the verification area, and the corresponding verification operation is performed according to the verification type, when multiple reference operation positions undergo continuous changes. The second operation attribute information can refer to the set of operation features that reflect the characteristics of the verification operation when the operation position triggered by the page interaction operation of the verification interface enters the verification area, and the corresponding verification operation is performed according to the verification type, when multiple reference operation positions do not undergo continuous changes.

[0048] In this embodiment, the verification type can refer to the type of interaction judgment method adopted by the verification interface, including but not limited to input-type verification, point-based verification, and sliding verification. The verification area can refer to the pre-defined area in the verification interface used to perform the verification operation, and the definition of the verification area is related to the verification type. For example, when the verification type is input-type verification, the verification area is the input box area for entering answers, letters, Chinese characters, etc.; when the verification type is point-based verification, the verification area is the area where the verification content can be selected; when the verification type is sliding verification, the verification area is the image area containing a sliding slider.

[0049] Based on the continuity detection results provided by the first information, two interactive operation modes—continuous cursor movement and discrete clicks—can be quickly distinguished within the verification interface. For the continuous cursor movement interaction mode, the spatiotemporal sequence of the continuous cursor movement trajectory can be obtained during the page interaction process of the verification detection operation. Therefore, the first trajectory attribute information and the first operation attribute information are simultaneously collected as the second information. For the discrete click interaction mode, various discrete information generated by the click can be obtained during the page interaction process of the verification detection operation. Therefore, the second operation attribute information is collected as the second information. The first and second operation attribute information are adaptively adjusted according to the verification type currently used in the verification area to ensure that the acquired operation attribute information matches the verification type currently used by the verification interface.

[0050] The second information is obtained based on the interaction method and the verification type of the current verification interface. This ensures that the obtained second information is closely related to the current verification scenario, avoids interference from redundant information, improves the distinguishability of characteristic information between real users and simulated users, and enhances the accuracy of identifying whether the verification operation is performed by a real user.

[0051] Optionally, obtain the second information corresponding to the verification interface based on the first information, including steps B1-B3:

[0052] Step B1: In response to the first information that multiple reference operation positions have continuous changes, determine the reference trajectory formed by performing page interaction operations on the verification interface.

[0053] A reference trajectory can refer to an ordered sequence of spatial points formed by the sequential combination of reference operation positions left by continuous page interaction operations on the verification interface. The reference trajectory reflects the actual path of cursor movement on the verification interface.

[0054] When the initial information indicates that the current page interaction operation has continuous changes, the discrete and temporally sequenced reference operation positions are fitted into a continuous reference trajectory. This gives the originally isolated sampling points continuous geometric meaning, thus providing attribute information such as direction, extrema, and time. The reference trajectory not only preserves the spatiotemporal information of the original page interaction operation but also reduces the interference of noise points in the verification interface on subsequent calculations or operations.

[0055] Step B2: Determine the first and second parameters of the reference trajectory. The first parameter is the slope of the line segment formed by the starting and ending points of the reference trajectory. The second parameter includes a first result, a second result, and a third result. The first result includes the first trajectory point and its corresponding acquisition time. The second result includes the second trajectory point and its corresponding acquisition time. The third result includes the third trajectory point and its corresponding acquisition time. The first trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory. The second trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory along the horizontal axis. The third trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory along the vertical axis.

[0056] The first parameter can refer to the slope of the line segment formed by the start and end points of the reference trajectory, which can be used to quantify the direction of movement and overall intention of multiple page interactions on the verification interface. The second parameter can refer to the triplet data composed of key feature points of the reference trajectory in the spatial and temporal dimensions and their corresponding acquisition times; wherein, the first result is used to represent the spatiotemporal information of local peaks and valleys in the reference trajectory, the second result is used to represent the spatiotemporal information of the lateral span limit of the reference trajectory, and the third result is used to represent the spatiotemporal information of the longitudinal span limit of the reference trajectory.

[0057] Step B3: Determine the attribute information of the first trajectory based on the content of the first parameter and the content of the second parameter of the reference trajectory.

[0058] The first trajectory attribute information describes the global and local spatiotemporal characteristics of page interaction operations in the current verification interface. This first trajectory attribute information can reduce the risk of simulating users through script-based direction spoofing or amplitude compression, thus improving the security and stability of verification detection.

[0059] Since the display size of the verification interface varies between different terminals, optionally, the display size of the verification interface is obtained, the trajectory points contained in the second parameter are normalized according to the display size of the verification interface, and the first trajectory attribute information is determined according to the first parameter content of the reference trajectory and the normalized second parameter content, so as to eliminate the influence of device resolution differences on the trajectory attribute information.

[0060] Optionally, a reference trajectory is determined by performing page interaction operations on the verification interface, including steps C1-C2:

[0061] Step C1: Determine the first operation position and the second operation position. The first operation position is the first operation position triggered when performing page interaction operations on the verification interface after the verification interface is triggered. The second operation position is the operation position that first enters the verification area of ​​the verification interface among the various operation positions triggered sequentially when performing page interaction operations on the verification interface.

[0062] The first operation position refers to the first operation position triggered when the page interaction is first executed after the verification interface is triggered. The collection time corresponding to the first operation position is the earliest collection time in the entire reference operation position sequence. By listening to the input events of the verification interface, the starting position of the page interaction can be determined and taken as the first operation position. By continuing to listen to the input events of the verification interface, that is, tracking the operation positions triggered by the page interaction, until the operation position is detected to fall into the verification area, the operation position falling into the verification area is taken as the second operation position.

[0063] Step C2: Generate a reference trajectory by obtaining multiple operation positions sequentially triggered by performing page interaction operations on the verification interface from the first operation position to the second operation position.

[0064] The reference trajectory can refer to the sequence of reference operation positions left by continuous page interaction operations on the verification interface. It can be used to characterize the actual movement path of the cursor on the verification interface from the starting position triggered by the interaction operation to entering the verification area.

[0065] Optionally, obtain the second information corresponding to the verification interface based on the first information, including steps D1-D4:

[0066] Step D1: In response to the first information that there is a continuous change in multiple reference operation positions, detect the verification type used in the verification area of ​​the verification interface.

[0067] In response to the first information indicating continuous changes in multiple reference operation positions, it can be determined that a continuous cursor movement interaction method is adopted. During the page interaction process of the verification and detection operation, the spatiotemporal sequence of the continuous cursor movement trajectory can be obtained. That is, the first trajectory attribute information and the first operation attribute information can be simultaneously collected as the second information. Specifically, the collected first operation attribute information includes the correlation between the operation attribute content type and whether there are continuous changes in multiple reference operation positions, as well as the verification type used in the verification area of ​​the verification interface. Therefore, it is necessary to detect the verification type used in the verification area of ​​the verification interface. For example, detecting the verification type used in the verification area of ​​the verification interface can be achieved by detecting the component type in the page, listening to page events, and detecting page layout features.

[0068] Step D2: In response to the verification type being selected as point-based verification in the verification area, determine the first parameter result and, based on the first parameter result, determine the first operation attribute information. The first parameter result includes the slope and offset of each of the multiple reference verification targets. The multiple reference verification targets are the verification targets in the verification area of ​​the verification interface that need to be verified sequentially. The slope of each reference verification target is the slope of the line segment formed by the starting point and ending point of the trajectory of the reference verification target. The starting point of the trajectory of the reference verification target is the operation position point that first enters the verification area of ​​the verification interface through the sequential operation triggered by the page interaction operation in the verification interface, or the trajectory ending point of the reference verification target verified before the reference verification target. The trajectory ending point of the reference verification target is the operation position when the reference verification target is triggered by point-based verification during the page interaction operation in the verification interface. The offset of the reference verification target is the offset between the operation position when the reference verification target is triggered by point-based verification during the page interaction operation in the verification interface and the center position of the reference verification target.

[0069] The reference verification targets can refer to several icons, texts, or blocks that are highlighted or arranged sequentially in the verification area under the selected verification type. You need to click on the multiple reference verification targets in the verification area in the order indicated by the verification area in order to pass the verification test.

[0070] Offset refers to the geometric metric between the operation position when selecting a reference verification target and the geometric center of the reference verification target, and can be used to measure the selection accuracy. For example, offset can refer to the length and slope of the line segment formed by the operation position when selecting a reference verification target and the geometric center of the reference verification target. Since the size of the reference verification target affects the operation position when selecting it, optionally, the minimum bounding rectangle size of multiple reference verification targets can be obtained, and the geometric metric between the operation position when selecting the corresponding reference verification target and the geometric center of the corresponding reference verification target can be normalized based on the diagonal length of the minimum bounding rectangle of each reference verification target.

[0071] In response to the verification type adopted by the verification area being point-based verification, a series of operation positions from entering the verification area to each click are recorded in chronological order. The slope of the line segment formed between two adjacent operation positions is calculated segment by segment. At the same time, the offset of the operation position when the reference verification target is clicked is determined. The obtained slope and offset are determined as the first parameter result, and the first operation attribute information is generated based on the first parameter result.

[0072] Among them, the slope can characterize the cursor's movement intention during the verification operation, the offset can characterize the accuracy and stability of the selection operation, and the first parameter result can be used to reflect the cursor's movement pattern during the selection operation. Since simulated users usually generate straight trajectories and equidistant selections, while real users, based on human motion control patterns, will exhibit smooth trajectories and slight random jitter when selecting reference verification targets, the first operation attribute information generated based on the first parameter result can effectively improve the accuracy of verification detection in identifying real users.

[0073] Step D3: In response to the verification type adopted by the verification area being input verification type, determine the second parameter result and determine the first operation attribute information based on the second parameter result. The second parameter result includes the type of input content in the reference verification content input port, the input time corresponding to the input content, and the total time of all input content. The reference verification content input port is the interactive component in the verification area of ​​the verification interface used to receive verification content information.

[0074] Input validation type can refer to a text box displayed in the validation area, requiring users to enter specified content according to the prompts before passing the validation check. The content type can include characters, numbers, and Chinese characters, etc. Input time can refer to the time span recorded from the moment any valid character is received from the reference validation input port until that character is completely written and readable, representing the duration of a single input. The total time for all input content can refer to the total time span accumulated from the moment any valid character is received from the reference validation input port until the last character is entered, representing the overall duration of the specified content input process.

[0075] Responding to the input verification type adopted in the verification area, the system listens for keyboard events within the verification interface, obtains the type of input content in the reference verification input field, the corresponding input time, and the total time of all input content. This information is then encapsulated as a second parameter result, and a first operation attribute information is generated based on this result. The total time of all input content includes the input time of each individual input, reaction time, error rollback and correction time, and other durations of the entire input process. The type and corresponding input time of the input content reflect the single-field input operation characteristics of different input content types, while the corresponding input time and the total time of all input content reflect the operation characteristics of the complete input process. The second parameter result reflects the rhythmic distribution of the input operation. Since simulated users typically input specified content at uniform intervals and in a fixed order, while real users, based on human motion control principles, exhibit random intervals and error rollbacks, the first operation attribute information generated from the second parameter result effectively improves the accuracy of verification detection in identifying real users.

[0076] Step D4: In response to the verification type adopted by the verification area being sliding verification, determine the third parameter result and determine the first operation attribute information based on the third parameter result. The third parameter result includes the sliding time corresponding to the reference sliding block and the offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled. The reference sliding block is used to match the area to be filled in the verification area of ​​the verification interface by dragging to complete the verification. The sliding time corresponding to the reference sliding block is the time interval between the start time of dragging the reference sliding block and the end time of dragging the reference sliding block. The offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled is determined based on the ratio of the distance between the position of the center point of the sliding block at the end of the drag and the position of the center point of the area to be filled to the length of the area to be filled.

[0077] The sliding verification type can refer to a verification area with a gap or a draggable slider, where the slider needs to be dragged to fill the gap in order to pass the verification test.

[0078] Responding to the fact that the verification area uses a sliding verification type, the system listens for input events within the verification interface, obtains the complete sliding time of the reference sliding block from being clicked and selected to being released, and the offset of the reference sliding block's endpoint relative to the area to be filled. This information is then encapsulated as a third parameter result, and a first operation attribute information is generated based on this result. The third parameter result reflects the correlation between sliding speed and offset. Since simulated users typically exhibit uniform or single-segment uniform acceleration sliding operations with offsets approaching zero, while real users, based on human motion control principles, typically exhibit acceleration followed by deceleration, slight random jitter, and repeated fine-tuning of the sliding trajectory, the first operation attribute information generated based on the third parameter result effectively improves the accuracy of verification detection in identifying real users.

[0079] Optionally, obtain the second information corresponding to the verification interface based on the first information, including steps E1-E4:

[0080] Step E1: In response to the first information that there is no continuous change in multiple reference operation positions, the verification type used in the verification area of ​​the verification interface is detected.

[0081] Since the first information indicates that there is no continuous change in multiple reference operation positions, it can be determined that a discrete click interaction method is used. During the page interaction process of the verification and detection operation, various discrete information generated by clicks can be obtained, which can then be used to collect second operation attribute information as the second information. Specifically, the collected second operation attribute information includes the correlation between the operation attribute content type and whether there is a continuous change in multiple reference operation positions, as well as the verification type used in the verification area of ​​the verification interface. Therefore, it is necessary to detect the verification type used in the verification area of ​​the verification interface.

[0082] Step E2: In response to the verification type adopted by the verification area being point-based verification, determine the fourth parameter result and determine the second operation attribute information based on the fourth parameter result. The fourth parameter result includes the point-based verification time and the offset of each reference verification target among multiple reference verification targets. Multiple reference verification targets are multiple verification targets in the verification area of ​​the verification interface that need to be verified sequentially. The point-based verification time corresponding to the reference verification target is the time consumed when the reference verification target is triggered by clicking on it through page interaction operations in the verification interface. The offset of the reference verification target is the offset between the operation position and the center position of the reference verification target when the reference verification target is triggered by clicking on it through page interaction operations in the verification interface.

[0083] The selection time corresponding to the reference verification target is the time consumed when the reference verification target is triggered by performing a page interaction operation on the verification interface. For example, if there are three reference verification targets to be selected in the verification area, and the three targets are selected sequentially, the selection time for the first reference verification target is the time from the initial entry of the interaction into the verification area to the triggering of the first reference verification target; the selection time for the second reference verification target is the time from the triggering of the first reference verification target to the triggering of the second reference verification target; and the selection time for the third reference verification target is the time from the triggering of the second reference verification target to the triggering of the third reference verification target. Responding to the verification type used in the verification area being point-based verification, the operation position and selection time for each reference verification target are recorded, and the offset of the operation position when each reference verification target is selected is determined. The obtained selection time and offset are used as the fourth parameter result, and the second operation attribute information is generated based on the fourth parameter result. Among them, the selection time characterizes the operation time and reaction time during the verification process, the offset characterizes the accuracy and stability of the click operation, and the fourth parameter result can be used to reflect the selection pattern during the selection process. Since simulated users usually generate equidistant selections without delay or bias, while real users, based on human motion control laws, exhibit selection patterns with reaction delays and slight random jitter when selecting reference verification targets, the second operation attribute information generated based on the fourth parameter result can effectively improve the accuracy of verification detection in identifying real users.

[0084] Step E3: In response to the verification type adopted by the verification area being input verification type, determine the fifth parameter result and determine the second operation attribute information based on the fifth parameter result. The fifth parameter result includes the soft keyboard type corresponding to the input content in the reference verification content input port, the total time consumed when inputting all input content, and the time consumed when inputting different types of input content. The reference verification content input port is the interactive component in the verification area of ​​the verification interface used to receive verification content information.

[0085] The type of soft keyboard can refer to the keyboard layout presented in the verification area for the input stage, including full letter keyboard, nine-key keyboard, handwriting keyboard, randomized keyboard, etc.

[0086] In response to the verification type adopted in the verification area being input verification type, the soft keyboard type corresponding to the input content in the reference verification content input port, the total time consumed when inputting all input content, and the time consumed when inputting different types of input content are recorded. This recorded information is defined as the fifth parameter result, and the second operation attribute information is generated based on the fifth parameter result. The soft keyboard type reflects the credibility and consistency of the input environment; the total time consumed when inputting all input content reflects the overall efficiency and fluency of the input behavior; the time consumed when inputting different types of input content reflects the input rhythm distribution for different types of input content; and the fifth parameter result can be used to reflect the input patterns during the input operation process. Since simulated users typically generate input with a uniform delay, while real users, based on human movement patterns, exhibit input rhythm fluctuations according to keyboard type and character category when selecting the reference verification target, the introduction of keyboard type and classification time into the fifth parameter result ensures that even by replaying text to simulate users, it is impossible to simulate the input rhythm differences caused by real users searching for keys or switching keyboards. Therefore, the second operation attribute information generated based on the fifth parameter result can enhance the accuracy of verification detection in identifying real users.

[0087] Step E4: In response to the verification type adopted by the verification area being sliding verification, determine the sixth parameter result and determine the second operation attribute information based on the sixth parameter result. The sixth parameter result includes the sliding time corresponding to the reference sliding block and the offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled. The reference sliding block is used to match the area to be filled in the verification area of ​​the verification interface by dragging to complete the verification. The sliding time corresponding to the reference sliding block is the time period between the start time of dragging the reference sliding block and the end time of dragging the reference sliding block. The offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled is determined based on the ratio of the distance between the position of the center point of the sliding block at the end of the drag and the position of the center point of the area to be filled to the length of the area to be filled.

[0088] Responding to the fact that the verification area uses a sliding verification type, the system listens for input events within the verification interface, obtains the complete sliding time of the reference sliding block from being clicked and selected to being released, and the offset of the reference sliding block's endpoint relative to the area to be filled. This information is then encapsulated as a sixth parameter result, and a second operation attribute is generated based on this result. The sixth parameter result reflects the correlation between sliding speed and offset. Since simulated users typically exhibit uniform or single-segment uniform acceleration sliding operations with offsets approaching zero, while real users, based on human motion control principles, typically exhibit acceleration followed by deceleration, slight random jitter, and repeated fine-tuning of the sliding trajectory, the second operation attribute information generated from the sixth parameter result effectively improves the accuracy of verification detection in identifying real users.

[0089] S130. Determine whether the page interaction operation of the verification interface is a real user operation based on the second information.

[0090] Real user actions refer to interactive events directly generated by humans through input devices or tools, exhibiting bio-kinematic characteristics and cognitive reaction timing. The trajectory, latency, jitter, micro-pauses, and mechanical characteristics of real user actions conform to the laws of human motion control. Therefore, the motion control laws of real user actions cannot be reproduced by scripts, simulations, or robotic arms, and can be used to identify real user actions. Human motion control laws refer to the inherent kinematic constraints and statistical characteristics of the biological nervous system when performing goal-oriented actions, including but not limited to: higher trajectory curvature corresponds to lower movement speed; slight random jitter; smooth transitions at turning points; reaction delays; and long-distance movements being composed of multiple short-distance movements stitched together with minor recalibrations.

[0091] Using the second information as input, a preset or adaptive discrimination mechanism is used to evaluate the trajectory attribute information and operation attribute information contained in the second information, thereby determining whether the current page interaction operation conforms to the motion control law of real users, realizing the rapid filtering of automated scripts or machine simulation behavior, ensuring a smooth experience for legitimate users, and improving the security margin and anti-attack capability of the verification system.

[0092] Optionally, determine whether the page interaction operations on the verification interface are genuine user operations based on the second information, including:

[0093] The second information is input into the page interaction operation recognition model, and the page interaction operation recognition model outputs the operation recognition result. The operation recognition result is used to identify whether the operation performed on the verification interface is a real user operation. The page interaction operation recognition model is a neural network model trained based on the third information. The third information includes the second trajectory attribute information and the third operation attribute information, or the third information includes the fourth operation attribute information. The second trajectory attribute is obtained before the first trajectory attribute information and is used to indicate the trajectory features formed by the operation position triggered by performing the page interaction operation on the verification interface after the verification interface is triggered. The third operation attribute information and the fourth operation attribute information are operation attribute information obtained before the first operation attribute information and the second operation attribute information. The operation attribute content type included in the third operation attribute information and the fourth operation attribute information are related to whether there is a continuous change in multiple reference operation positions and the verification type used in the verification area of ​​the verification interface.

[0094] A page interaction operation recognition model can refer to a neural network model that has been trained using third-party information as training data. This model learns the motion control patterns of real user verification operations and possesses the ability to identify whether a verification operation is performed by a genuine user. Based on the input second-party information, the page interaction operation recognition model can be used to determine whether the interactive operation on the verification interface is performed by a genuine user.

[0095] The third information can refer to the training data of the page interaction operation recognition model collected before the second information. The third data includes data recorded by multiple real users performing multiple verification operations on multiple verification interfaces, including the second trajectory attribute information and the third operation attribute information or the fourth operation attribute information. The second trajectory attribute information and the third operation attribute information contain the trajectory characteristics and operation characteristics of performing various verification types of operations when the operation position changes continuously. The fourth operation attribute information contains the operation characteristics of performing various verification types of operations when the operation position changes discontinuously. The third information can be used to determine the feature boundaries of the motion control law of real user operations.

[0096] The second piece of information is input into the page interaction operation recognition model. Based on the learned motion control patterns of real user verification operations, the model calculates the confidence level that the verification operation corresponding to the second piece of information is a real user operation. When the obtained confidence level is greater than or equal to a preset confidence threshold, the operation recognition result is set to true, indicating that the verification operation corresponding to the second piece of information is a real user operation; when the obtained confidence level is less than the preset confidence threshold, the operation recognition result is set to false, indicating that the verification operation corresponding to the second piece of information is not a real user operation. The page interaction operation recognition model determines whether the page interaction operation on the verification interface is a real user operation based on the operation recognition result.

[0097] A single model can be used to determine whether a verification operation is performed by a real user, avoiding the complexity of setting multiple rules. The neural network model can automatically capture subtle motion control patterns that are difficult to model explicitly, and has high robustness against script spoofing, amplitude compression and other automated attacks. It can significantly enhance the stability and generalization ability of verification detection, and significantly improve the accuracy of determining whether a verification operation is performed by a real user.

[0098] The technical solution of this invention, by real-time detection of continuous changes in the reference operation position within the verification interface, can distinguish between two interactive operation modes: continuous cursor movement and discrete clicks. This provides a basis for subsequently selecting differentiated operation attribute information, significantly reducing the risk of forging external input device types through scripts. Based on the continuity judgment result and the verification type used in the verification area of ​​the verification interface, the second information corresponding to the verification interface is adaptively obtained. This ensures that the obtained second information always precisely matches the verification type used in the current verification area and the current interactive operation mode, reducing interference from redundant information and improving the distinguishability between real users and simulated users. Based on the differentiated extracted second information, it is determined whether the page interaction operation of the verification interface is a real user operation, enabling rapid filtering of automated scripts or machine-simulated behavior. While ensuring a smooth experience for real users, it also improves the security and anti-attack capabilities of the verification operation. Based on the above technical solution, the continuity of the interaction operation is judged after the verification operation is triggered. Only the attribute information that matches the current interaction operation method and verification type is obtained, so that the script cannot reproduce the spatiotemporal coupling relationship in the real interaction process of the verification operation. This avoids the situation of obtaining page information through scripts and reverse engineering to simulate users, and improves the accuracy of the verification operation in identifying real users.

[0099] Figure 2 This is a schematic diagram of a verification operation identification device provided in an embodiment of the present invention. This embodiment can be applied to situations where it is necessary to identify whether the operation is performed by a real user through verification operation. The verification operation identification device can be implemented in hardware and / or software and can be configured in any electronic device with network communication function.

[0100] like Figure 2 As shown, the verification operation identification device provided in this embodiment of the invention may include the following:

[0101] The first information detection module 210 is used to detect the first information of the verification interface in response to the trigger operation of the verification interface. The first information is used to indicate whether there is a continuous change in multiple reference operation positions. The multiple reference operation positions are the operation positions that are sequentially triggered when performing page interaction operations on the verification interface.

[0102] The second information acquisition module 220 is used to acquire second information corresponding to the verification interface based on the first information; wherein the second information includes first trajectory attribute information and first operation attribute information, or the second information includes second operation attribute information, the trajectory attribute information is used to indicate the trajectory features formed by the operation position triggered by performing a page interaction operation on the verification interface after the verification interface is triggered, the operation attribute information is used to indicate the operation features generated after the operation position triggered by the page interaction operation on the verification interface enters the verification area, and the operation attribute content type included in the first operation attribute information and the second operation attribute information is related to whether there is a continuous change in the multiple reference operation positions and the verification type used in the verification area of ​​the verification interface;

[0103] The verification operation identification module 230 is used to determine whether the page interaction operation of the verification interface is a real user operation based on the second information.

[0104] Based on the above embodiments, optionally, detecting the first information of the verification interface includes:

[0105] Detect multiple reference operation positions that are sequentially triggered by page interaction operations performed on the verification interface;

[0106] For sequentially adjacent reference operation positions among the plurality of reference operation positions, detect whether the distance between two consecutive sequentially adjacent reference operation positions is less than a preset distance;

[0107] In response to the fact that the distance between two consecutive sequentially adjacent reference operation positions is less than a preset distance, it is determined that the first information indicates that there is a continuous change in multiple reference operation positions;

[0108] In response to the fact that the distance between two consecutive sequentially adjacent reference operation positions is not less than a preset distance, it is determined that the first information indicates that there is no continuous change among the multiple reference operation positions.

[0109] Based on the above embodiments, optionally, obtaining second information corresponding to the verification interface according to the first information includes:

[0110] In response to the first information that multiple reference operation positions have continuous changes, a reference trajectory formed by performing page interaction operations on the verification interface is determined;

[0111] The first parameter content and the second parameter content of the reference trajectory are determined. The first parameter content is the slope of the line segment formed by the starting point and the ending point of the reference trajectory. The second parameter content includes a first result, a second result, and a third result. The first result includes a first trajectory point and the acquisition time corresponding to the first trajectory point. The second result includes a second trajectory point and the acquisition time corresponding to the second trajectory point. The third result includes a third trajectory point and the acquisition time corresponding to the third trajectory point. The first trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory. The second trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory along the horizontal axis. The third trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory along the vertical axis.

[0112] The first trajectory attribute information is determined based on the first parameter content and the second parameter content of the reference trajectory.

[0113] Based on the above embodiments, optionally, determining the reference trajectory formed by performing page interaction operations on the verification interface includes:

[0114] Determine a first operation position and a second operation position. The first operation position is the first operation position triggered when performing page interaction operations on the verification interface after the verification interface is triggered. The second operation position is the operation position that first enters the verification area of ​​the verification interface among the various operation positions triggered sequentially when performing page interaction operations on the verification interface.

[0115] A reference trajectory is generated by acquiring multiple operation positions sequentially triggered by performing page interaction operations on the verification interface from the first operation position to the second operation position.

[0116] Based on the above embodiments, optionally, obtaining second information corresponding to the verification interface according to the first information includes:

[0117] In response to the first information indicating a continuous change in multiple reference operation positions, the verification type used by the verification area of ​​the verification interface is detected;

[0118] In response to the verification type being point-based verification in the verification area, a first parameter result is determined, and the first operation attribute information is determined based on the first parameter result. The first parameter result includes the slope and offset of each of the multiple reference verification targets. The multiple reference verification targets are multiple verification targets in the verification area of ​​the verification interface that need to be verified sequentially. The slope of each reference verification target is the slope of the line segment formed by the starting point and ending point of the trajectory of the reference verification target. The starting point of the trajectory of the reference verification target is the operation position point that first enters the verification area of ​​the verification interface through the sequential operation triggered by the page interaction operation on the verification interface, or the trajectory ending point of the reference verification target verified before the reference verification target. The trajectory ending point of the reference verification target is the operation position when the reference verification target is triggered by point-based verification during the page interaction operation on the verification interface. The offset of the reference verification target is the offset between the operation position when the reference verification target is triggered by point-based verification during the page interaction operation on the verification interface and the center position of the reference verification target.

[0119] In response to the verification type adopted by the verification area being input verification type, the second parameter result is determined and the first operation attribute information is determined based on the second parameter result. The second parameter result includes the type of input content in the reference verification content input port, the input time corresponding to the input content, and the total time of all input content. The reference verification content input port is an interactive component in the verification area of ​​the verification interface used to receive verification content information.

[0120] In response to the verification type being a sliding verification type used in the verification area, a third parameter result is determined, and the first operation attribute information is determined based on the third parameter result. The third parameter result includes the sliding time corresponding to the reference sliding block and the offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled. The reference sliding block is used to match the area to be filled in the verification area of ​​the verification interface by dragging to complete the verification. The sliding time corresponding to the reference sliding block is the time interval between the start time of dragging the reference sliding block and the end time of dragging the reference sliding block. The offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled is determined based on the ratio of the distance between the position of the center point of the sliding block at the end of the drag and the position of the center point of the area to be filled to the length of the area to be filled.

[0121] Based on the above embodiments, optionally, obtaining second information corresponding to the verification interface according to the first information includes:

[0122] In response to the first information indicating that there is no continuous change in multiple reference operation positions, the verification type used by the verification area of ​​the verification interface is detected;

[0123] In response to the verification type adopted by the verification area being a point-based verification type, the fourth parameter result is determined and the second operation attribute information is determined based on the fourth parameter result. The fourth parameter result includes the point-based time corresponding to each of the multiple reference verification targets and the offset corresponding to the reference verification target. The multiple reference verification targets are multiple verification targets in the verification area of ​​the verification interface that need to be verified sequentially. The point-based time corresponding to the reference verification target is the time consumed when the reference verification target is triggered by point-based page interaction operation on the verification interface. The offset corresponding to the reference verification target is the offset between the operation position and the center position of the reference verification target when the reference verification target is triggered by point-based page interaction operation on the verification interface.

[0124] In response to the verification type adopted by the verification area being an input verification type, the fifth parameter result is determined and the second operation attribute information is determined based on the fifth parameter result. The fifth parameter result includes the soft keyboard type corresponding to the input content in the reference verification content input port, the total time consumed when inputting all input content, and the time consumed when inputting different types of input content. The reference verification content input port is an interactive component in the verification area of ​​the verification interface used to receive verification content information.

[0125] In response to the verification type being a sliding verification type used in the verification area, a sixth parameter result is determined, and the second operation attribute information is determined based on the sixth parameter result. The sixth parameter result includes the sliding time corresponding to the reference sliding block and the offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled. The reference sliding block is used to match the area to be filled in the verification area of ​​the verification interface by dragging it to complete the verification. The sliding time corresponding to the reference sliding block is the time interval between the start time of dragging the reference sliding block and the end time of dragging the reference sliding block. The offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled is determined based on the ratio of the distance between the position of the center point of the sliding block at the end of the drag and the position of the center point of the area to be filled to the length of the area to be filled.

[0126] Based on the above embodiments, optionally, determining whether the page interaction operation of the verification interface is a real user operation based on the second information includes:

[0127] The second information is input into the page interaction operation recognition model, and the page interaction operation recognition model outputs the operation recognition result. The operation recognition result is used to identify whether the operation of performing page interaction operation on the verification interface belongs to the real user operation. The page interaction operation recognition model is a neural network model obtained by model training based on the third information. The third information includes second trajectory attribute information and third operation attribute information, or the third information includes fourth operation attribute information. The second trajectory attribute is obtained before the first trajectory attribute information and is used to indicate the trajectory feature formed by the operation position triggered by performing page interaction operation on the verification interface after the verification interface is triggered. The third operation attribute information and the fourth operation attribute information are operation attribute information obtained before the first operation attribute information and the second operation attribute information. The operation attribute content type included in the third operation attribute information and the fourth operation attribute information are related to whether there is a continuous change in the multiple reference operation positions and the verification type used in the verification area of ​​the verification interface.

[0128] The technical solution of this invention, by real-time detection of continuous changes in the reference operation position within the verification interface, can distinguish between two interactive operation modes: continuous cursor movement and discrete clicks. This provides a basis for subsequently selecting differentiated operation attribute information, significantly reducing the risk of forging external input device types through scripts. Based on the continuity judgment result and the verification type used in the verification area of ​​the verification interface, the second information corresponding to the verification interface is adaptively obtained. This ensures that the obtained second information always precisely matches the verification type used in the current verification area and the current interactive operation mode, reducing interference from redundant information and improving the distinguishability between real users and simulated users. Based on the differentiated extracted second information, it is determined whether the page interaction operation of the verification interface is a real user operation, enabling rapid filtering of automated scripts or machine-simulated behavior. While ensuring a smooth experience for real users, it also improves the security and anti-attack capabilities of the verification operation. Based on the above technical solution, the continuity of the interaction operation is judged after the verification operation is triggered. Only the attribute information that matches the current interaction operation method and verification type is obtained, so that the script cannot reproduce the spatiotemporal coupling relationship in the real interaction process of the verification operation. This avoids the situation of obtaining page information through scripts and reverse engineering to simulate users, and improves the accuracy of the verification operation in identifying real users.

[0129] The verification operation identification device provided in the embodiments of the present invention can execute the verification operation identification method provided in any of the embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the verification operation identification method. For details, please refer to the relevant operations of the verification operation identification method in the foregoing embodiments.

[0130] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of the present invention.

[0131] Figure 3 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0132] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0133] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0134] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as verification operation recognition methods.

[0135] In some embodiments, the verification operation identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the verification operation identification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the verification operation identification method by any other suitable means (e.g., by means of firmware).

[0136] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0137] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0138] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0139] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0140] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0141] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0142] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0143] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A verification operation identification method, characterized in that, The method includes: In response to a triggering operation on the verification interface, first information of the verification interface is detected. The first information is used to indicate whether there is a continuous change in multiple reference operation positions. The multiple reference operation positions are the operation positions that are sequentially triggered when performing page interaction operations on the verification interface. The second information corresponding to the verification interface is obtained based on the first information; wherein, the second information includes first trajectory attribute information and first operation attribute information, or the second information includes second operation attribute information, the trajectory attribute information is used to indicate the trajectory features formed by the operation position triggered by performing page interaction operation on the verification interface after the verification interface is triggered, the operation attribute information is used to indicate the operation features generated after the operation position triggered by the page interaction operation on the verification interface enters the verification area, and the operation attribute content type included in the first operation attribute information and the second operation attribute information is related to whether there is a continuous change in the multiple reference operation positions and the verification type used in the verification area of ​​the verification interface; Based on the second information, determine whether the page interaction operation of the verification interface is a real user operation.

2. The method according to claim 1, characterized in that, The first information to be detected on the verification interface includes: Detect multiple reference operation positions that are sequentially triggered by page interaction operations performed on the verification interface; For sequentially adjacent reference operation positions among the plurality of reference operation positions, detect whether the distance between two consecutive sequentially adjacent reference operation positions is less than a preset distance; In response to the fact that the distance between two consecutive sequentially adjacent reference operation positions is less than a preset distance, it is determined that the first information indicates that there is a continuous change in multiple reference operation positions; In response to the fact that the distance between two consecutive sequentially adjacent reference operation positions is not less than a preset distance, it is determined that the first information indicates that there is no continuous change among the multiple reference operation positions.

3. The method according to claim 1, characterized in that, Based on the first information, the second information corresponding to the verification interface is obtained, including: In response to the first information that multiple reference operation positions have continuous changes, a reference trajectory formed by performing page interaction operations on the verification interface is determined; The first parameter content and the second parameter content of the reference trajectory are determined. The first parameter content is the slope of the line segment formed by the starting point and the ending point of the reference trajectory. The second parameter content includes a first result, a second result, and a third result. The first result includes a first trajectory point and the acquisition time corresponding to the first trajectory point. The second result includes a second trajectory point and the acquisition time corresponding to the second trajectory point. The third result includes a third trajectory point and the acquisition time corresponding to the third trajectory point. The first trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory. The second trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory along the horizontal axis. The third trajectory point includes the maximum and minimum values ​​of the curve formed by the trajectory points in the reference trajectory along the vertical axis. The first trajectory attribute information is determined based on the first parameter content and the second parameter content of the reference trajectory.

4. The method according to claim 3, characterized in that, Determining the reference trajectory formed by performing page interaction operations on the verification interface includes: Determine a first operation position and a second operation position. The first operation position is the first operation position triggered when performing page interaction operations on the verification interface after the verification interface is triggered. The second operation position is the operation position that first enters the verification area of ​​the verification interface among the various operation positions triggered sequentially when performing page interaction operations on the verification interface. A reference trajectory is generated by acquiring multiple operation positions sequentially triggered by performing page interaction operations on the verification interface from the first operation position to the second operation position.

5. The method according to claim 1, characterized in that, Based on the first information, the second information corresponding to the verification interface is obtained, including: In response to the first information indicating a continuous change in multiple reference operation positions, the verification type used by the verification area of ​​the verification interface is detected; In response to the verification type being point-based verification in the verification area, a first parameter result is determined, and the first operation attribute information is determined based on the first parameter result. The first parameter result includes the slope and offset of each of the multiple reference verification targets. The multiple reference verification targets are multiple verification targets in the verification area of ​​the verification interface that need to be verified sequentially. The slope of each reference verification target is the slope of the line segment formed by the starting point and ending point of the trajectory of the reference verification target. The starting point of the trajectory of the reference verification target is the operation position point that first enters the verification area of ​​the verification interface through the sequential operation triggered by the page interaction operation on the verification interface, or the trajectory ending point of the reference verification target verified before the reference verification target. The trajectory ending point of the reference verification target is the operation position when the reference verification target is triggered by point-based verification during the page interaction operation on the verification interface. The offset of the reference verification target is the offset between the operation position when the reference verification target is triggered by point-based verification during the page interaction operation on the verification interface and the center position of the reference verification target. In response to the verification type adopted by the verification area being input verification type, the second parameter result is determined and the first operation attribute information is determined based on the second parameter result. The second parameter result includes the type of input content in the reference verification content input port, the input time corresponding to the input content, and the total time of all input content. The reference verification content input port is an interactive component in the verification area of ​​the verification interface used to receive verification content information. In response to the verification type being a sliding verification type used in the verification area, a third parameter result is determined, and the first operation attribute information is determined based on the third parameter result. The third parameter result includes the sliding time corresponding to the reference sliding block and the offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled. The reference sliding block is used to match the area to be filled in the verification area of ​​the verification interface by dragging to complete the verification. The sliding time corresponding to the reference sliding block is the time interval between the start time of dragging the reference sliding block and the end time of dragging the reference sliding block. The offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled is determined based on the ratio of the distance between the position of the center point of the sliding block at the end of the drag and the position of the center point of the area to be filled to the length of the area to be filled.

6. The method according to claim 1, characterized in that, Based on the first information, the second information corresponding to the verification interface is obtained, including: In response to the first information indicating that there is no continuous change in multiple reference operation positions, the verification type used by the verification area of ​​the verification interface is detected; In response to the verification type adopted by the verification area being a point-based verification type, the fourth parameter result is determined and the second operation attribute information is determined based on the fourth parameter result. The fourth parameter result includes the point-based time corresponding to each of the multiple reference verification targets and the offset corresponding to the reference verification target. The multiple reference verification targets are multiple verification targets in the verification area of ​​the verification interface that need to be verified sequentially. The point-based time corresponding to the reference verification target is the time consumed when the reference verification target is triggered by point-based page interaction operation on the verification interface. The offset corresponding to the reference verification target is the offset between the operation position and the center position of the reference verification target when the reference verification target is triggered by point-based page interaction operation on the verification interface. In response to the verification type adopted by the verification area being an input verification type, the fifth parameter result is determined and the second operation attribute information is determined based on the fifth parameter result. The fifth parameter result includes the soft keyboard type corresponding to the input content in the reference verification content input port, the total time consumed when inputting all input content, and the time consumed when inputting different types of input content. The reference verification content input port is an interactive component in the verification area of ​​the verification interface used to receive verification content information. In response to the verification type being a sliding verification type used in the verification area, a sixth parameter result is determined, and the second operation attribute information is determined based on the sixth parameter result. The sixth parameter result includes the sliding time corresponding to the reference sliding block and the offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled. The reference sliding block is used to match the area to be filled in the verification area of ​​the verification interface by dragging it to complete the verification. The sliding time corresponding to the reference sliding block is the time interval between the start time of dragging the reference sliding block and the end time of dragging the reference sliding block. The offset degree of the sliding endpoint of the reference sliding block relative to the area to be filled is determined based on the ratio of the distance between the position of the center point of the sliding block at the end of the drag and the position of the center point of the area to be filled to the length of the area to be filled.

7. The method according to claim 1, characterized in that, Determining whether the page interaction operation of the verification interface is a real user operation based on the second information includes: The second information is input into the page interaction operation recognition model, and the page interaction operation recognition model outputs the operation recognition result. The operation recognition result is used to identify whether the operation of performing page interaction operation on the verification interface belongs to the real user operation. The page interaction operation recognition model is a neural network model obtained by model training based on the third information. The third information includes second trajectory attribute information and third operation attribute information, or the third information includes fourth operation attribute information. The second trajectory attribute is obtained before the first trajectory attribute information and is used to indicate the trajectory feature formed by the operation position triggered by performing page interaction operation on the verification interface after the verification interface is triggered. The third operation attribute information and the fourth operation attribute information are operation attribute information obtained before the first operation attribute information and the second operation attribute information. The operation attribute content type included in the third operation attribute information and the fourth operation attribute information are related to whether there is a continuous change in the multiple reference operation positions and the verification type used in the verification area of ​​the verification interface.

8. A verification operation identification device, characterized in that, The device includes: The first information detection module is used to detect the first information of the verification interface in response to the trigger operation of the verification interface. The first information is used to indicate whether there is a continuous change in multiple reference operation positions. The multiple reference operation positions are the operation positions that are sequentially triggered when performing page interaction operations on the verification interface. The second information acquisition module is used to acquire second information corresponding to the verification interface based on the first information; wherein the second information includes first trajectory attribute information and first operation attribute information, or the second information includes second operation attribute information, the trajectory attribute information is used to indicate the trajectory features formed by the operation position triggered by performing a page interaction operation on the verification interface after the verification interface is triggered, the operation attribute information is used to indicate the operation features generated after the operation position triggered by the page interaction operation on the verification interface enters the verification area, and the operation attribute content type included in the first operation attribute information and the second operation attribute information is related to whether there is a continuous change in the multiple reference operation positions and the verification type used in the verification area of ​​the verification interface; The verification operation identification module is used to determine whether the page interaction operation of the verification interface is a real user operation based on the second information.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the verification operation identification method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the verification operation identification method according to any one of claims 1-7.

Images