AI-based automatic test case dynamic generation method and system, electronic equipment and storage medium

Abstract

The invention provides an AI-based automatic test case dynamic generation method and system, electronic equipment and a storage medium, and relates to the technical field of augmented reality and virtual reality, and the method comprises the steps: obtaining a staring track and a gesture sequence through the behavior collection and processing of a user, and carrying out the integration to generate user interaction behavior information; performing AI-driven behavior association construction processing on the interaction behavior information to generate behavior interaction feature information; performing phase shift capture processing on the polarization state of the display screen to generate sub-pixel response delay information, and identifying rendering abnormal region information according to the sub-pixel response delay information; in combination with the behavior interaction feature information and the rendering abnormal region information, potential interaction intention information is generated through AI reverse deduction processing; and by taking the intention information as a dynamic generation target, constructing an automatic test case dynamic state and generating a dynamic test case set. An unknown interaction defect scene can be actively covered by fusing user interaction behaviors and physical-level rendering anomaly detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of augmented reality and virtual reality technology, in particular to an AI-based automatic test case dynamic generation method and system, an electronic device and a storage medium. BACKGROUND

[0002] In the field of augmented reality and virtual reality application testing, with the diversification of interactive modes, scenarios of triggering non-standard operation paths through gaze trajectories and gesture sequences are increasing. Such unknown interaction paths often cause logical conflicts due to physical layer abnormalities such as interface rendering ghosting obstruction and operation delay mutation. Traditional testing methods based on function coverage cannot actively discover such defects.

[0003] The current mainstream solution uses user operation log playback technology to construct a test script library by recording real user operation sequences, and uses trajectory clustering algorithm to filter high-frequency paths for automatic regression testing. Although this solution can reuse historical interaction data.

[0004] However, it has the following defects: the log playback is completely limited to the operations that have occurred, and cannot deduce potential paths that the user intended to execute but were interrupted due to physical abnormalities; it lacks the ability to perceive hardware-level defects such as rendering ghosting, resulting in a mismatch between the test script and the real physical environment; and the clustering process ignores the high-attention but non-triggered intent areas in the gaze trajectory, causing key defect scenarios to be missed. SUMMARY

[0005] The present application aims to provide an AI-based automatic test case dynamic generation method and system, an electronic device and a storage medium to solve the problem that the passive playback mode in the prior art cannot cover potential interaction paths interrupted by physical abnormalities.

[0006] To solve the above technical problems, in a first aspect, the present application provides an AI-based automatic test case dynamic generation method, comprising: Based on user behavior collection and processing, gaze trajectories and gesture sequences in augmented reality and virtual reality applications are obtained, the gaze trajectories and the gesture sequences are integrated, and user interaction behavior information is generated; The user interaction behavior information is subjected to AI-driven behavior correlation construction processing, and behavior interaction feature information is generated; The display screen polarization state of AI is subjected to phase shift capture processing, and sub-pixel response delay information is generated; The rendering abnormal area of the sub-pixel response delay information is identified, and rendering abnormal area information is generated; The behavior interaction feature information and the rendering abnormal area information are combined, and AI back-deduction processing is performed, and potential interaction intent information is generated; The potential interaction intention information is taken as a dynamic generation target to dynamically construct an automatic test case and generate a dynamic test case set.

[0007] Optionally, the AI back reasoning processing is performed in combination with the behavior interaction feature information and the rendering abnormal area information to generate the potential interaction intention information, including: The implicit causality between the user operation delay of the behavior interaction feature information and the visual attention degree of the behavior interaction feature information is constructed to generate behavior causality structure information; The virtual object display state in the behavior causality structure information is intervened to inject a condition to generate a back intervention parameter; The operation result of the non-gesture operation under the rendering abnormal area is deduced using the back intervention parameter to generate back operation result information; The potential interaction intention of the user is described and reconstructed based on the back operation result information to generate the potential interaction intention information.

[0008] Optionally, the AI-driven behavior association construction processing is performed on the user interaction behavior information to generate the behavior interaction feature information, including: The asynchronous coupling processing is performed on the pause interval in the gaze track of the user interaction behavior information and the operation conflict in the gesture sequence of the user interaction behavior information to generate behavior contradiction focus information; The visual attention accumulation area in the gaze track and the operation delay burst period in the gesture sequence are intention hesitation quantification processed based on the behavior contradiction focus information to generate interaction hesitation feature information; The hotspot area in the gaze track that is not triggered by the gesture is intention residual marked processed in combination with the interaction hesitation feature information to generate potential intention mark information; The interaction intention differentiation path of the user is topologically reconstructed using the potential intention mark information and the behavior contradiction focus information to generate the behavior interaction feature information.

[0009] Optionally, the potential interaction intention information is taken as a dynamic generation target to dynamically construct an automatic test case and generate a dynamic test case set, including: The virtual operation area to which the intention points in the potential interaction intention information is space coordinate conversion processed to generate intention space positioning information; The operation path in the intention space positioning information is space variation processed in combination with the rendering abnormal area information to generate variation operation path information; The gesture action sequence in the potential interaction intention information is subjected to conflict injection processing by using the variation operation path information, and a conflict-enhanced gesture sequence is generated. Based on the conflict-enhanced gesture sequence and the variation operation path information, a test case execution logic is dynamically synthesized to generate a dynamic test case set.

[0010] Optionally, in combination with the rendering abnormal area information, intervention condition injection processing is performed on the virtual object display state in the behavior cause-effect structure information to generate an anti-intervention parameter, including: The optical distortion degree of the ghosting area in the rendering abnormal area information is subjected to physical interference quantization processing to generate a ghosting interference strength parameter; The operation delay in the behavior cause-effect structure information and the cause-effect link of the visual attention degree in the behavior cause-effect structure information are subjected to state reconstruction processing by using the ghosting interference strength parameter to generate distortion cause-effect link information; In combination with the distortion cause-effect link information, dynamic simulation processing is performed on the visibility attenuation characteristics of the virtual object display state in the ghosting area to generate a display state attenuation model; Based on the display state attenuation model, intervention correction processing is performed on the operation feasibility of the unexecuted gesture operation under the distortion cause-effect constraint to generate an anti-intervention parameter.

[0011] Optionally, the interaction intention differentiation path of the user is subjected to topological reconstruction processing by using the potential intention mark information and the behavior contradiction focus information to generate behavior interaction feature information, including: The untriggered hotspot area in the potential intention mark information and the operation conflict area in the behavior contradiction focus information are subjected to intention splitting processing to generate split intention node information; Based on the split intention node information, operation detour path around the conflict area in the gaze trajectory is subjected to repulsion strength calculation processing to generate path repulsion parameters; The connection relationship between the split intention node information is subjected to dynamic attenuation processing by using the path repulsion parameters to generate intention connection attenuation information; In combination with the intention connection attenuation information, the spatial topological structure of the interaction intention differentiation path is subjected to evolution simulation processing to generate reconstructed topological path information; Based on the reconstructed topological path information, the differentiation characteristics of the behavior mode of the user are subjected to structured description processing to generate behavior interaction feature information.

[0012] Optionally, the operation result of the unexecuted gesture operation under the rendering abnormal area is subjected to reasoning processing by using the anti-intervention parameter to generate anti-operation result information, including: Constrained reconstruction is performed on the interaction response rule of the virtual object in the rendering abnormal area based on the anti-intervention parameter, and abnormal interaction constraint information is generated. Dynamic simulation is performed on the deformation process of the track form of the gesture operation not performed in the rendering abnormal area by using the abnormal interaction constraint information, and gesture deformation track information is generated. Evolution and deduction are performed on the state transition path of the virtual object under abnormal constraint by combining the gesture deformation track information, and object state evolution information is generated. Boundary positioning is performed on the critical condition of operation interruption and error triggering in the object state evolution information, and operation failure boundary information is generated. Complete integrity deduction is performed on the final interaction result of the gesture operation not performed in the rendering abnormal area by using the operation failure boundary information, and anti-operation result information is generated.

[0013] In a second aspect, the present application provides an AI-based automatic test case dynamic generation system, comprising: The behavior acquisition module is configured to acquire gaze tracks and gesture sequences in an augmented reality and virtual reality application based on user behavior acquisition processing, integrate the gaze tracks and the gesture sequences, and generate user interaction behavior information. The association construction module is configured to perform AI-driven behavior association construction processing on the user interaction behavior information, and generate behavior interaction feature information. The polarization capture module is configured to perform phase shift capture processing on the display screen polarization state of AI, and generate sub-pixel response delay information. The abnormality recognition module is configured to identify a rendering abnormal area of the sub-pixel response delay information, and generate rendering abnormal area information. The intention deduction module is configured to perform AI counter-deduction processing by combining the behavior interaction feature information and the rendering abnormal area information, and generate potential interaction intention information. The use case generation module is configured to construct an automatic test case dynamically with the potential interaction intention information as a dynamic generation target, and generate a dynamic test case set.

[0014] In a third aspect, the present application provides an electronic device, comprising: A memory is configured to store a computer program. A processor is configured to execute the computer program to implement the steps of the AI-based automatic test case dynamic generation method of the first aspect described above.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program, when executed by a processor, enables the steps of the AI-based automatic test case dynamic generation method according to the first aspect.

[0016] The AI-based automatic test case dynamic generation method provided by the present application acquires the gaze trajectory and gesture sequence in the augmented reality and virtual reality application through the behavior collection and processing based on the user, integrates the gaze trajectory and the gesture sequence to generate user interaction behavior information, performs AI-driven behavior correlation construction processing on the user interaction behavior information to generate behavior interaction feature information, performs phase shift capture processing on the display screen polarization state of AI to generate sub-pixel response delay information, identifies the rendering abnormal area of the sub-pixel response delay information to generate rendering abnormal area information, performs AI backtracking processing in combination with the behavior interaction feature information and the rendering abnormal area information to generate potential interaction intent information, and takes the potential interaction intent information as a dynamic generation target to construct an automatic test case dynamic to generate a dynamic test case set. The technical solution of the present application has the following beneficial effects: The user interaction behavior information is generated by integrating the gaze trajectory and the gesture sequence to construct a multi-modal interaction data basis. The AI-driven processing is used to actively construct the implicit correlation between the visual attention and the operation delay from the interaction behavior to form quantifiable behavior features. The sub-pixel level response delay information is generated based on the display screen polarization phase shift capture to realize the physical layer perception of the hardware rendering defects. The abnormal area in the response delay is identified to accurately locate the virtual object rendering ghosting defect. The behavior features and the rendering abnormalities are combined to perform backtracking to reveal the potential interaction path that the user intent executes but is interrupted due to physics. Finally, the unconventional operation test case is dynamically constructed using the potential intent to actively cover the defect scenarios that cannot be reached by traditional methods.

[0017] Further, the behavior causal structure is constructed based on the implicit causal relationship between the operation delay and the visual attention in the behavior interaction feature information, the anti-parameters are generated by injecting intervention conditions to the virtual object display state in combination with the rendering abnormal area, the operation result of the unexecuted gesture in the abnormal area is deduced using the parameters, and finally the potential interaction intent information is reconstructed. The dependence on the occurred operation in the traditional log playback is broken, the operation path corresponding to the interruption intent is actively generated through the backtracking under the physical abnormal intervention, the test environment mismatch problem caused by the rendering defect is solved, the hardware level abnormality is converted into a causal constraint condition, the operation failure boundary is located in the state evolution of the virtual object, and the unknown defect scenarios of the augmented reality and the virtual reality are accurately covered. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the accompanying drawings required to be used in the description of the embodiments or the prior art will be briefly introduced. Obviously, the accompanying drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0019] Figure 1 A flowchart of an AI-based automatic test case dynamic generation method provided by an embodiment of the present application; Figure 2 A specific implementation schematic diagram of an AI-based automatic test case dynamic generation method provided by an embodiment of the present application; Figure 3 A specific implementation schematic diagram of an AI-based automatic test case dynamic generation method provided by an embodiment of the present application; Figure 4 A structural schematic diagram of an AI-based automatic test case dynamic generation system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] Research finds that when users trigger non-standard interaction paths through gaze trajectories and gesture sequences in augmented reality and virtual reality application testing, logical conflicts are often caused by physical layer abnormalities such as interface rendering ghost blocking, operation delay mutation, etc. Traditional testing methods based on function coverage are difficult to actively capture such defects, while existing automation solutions use user operation log playback technology to generate test scripts by clustering high-frequency paths, but there are fundamental limitations: they completely rely on existing operation records and cannot infer potential user intentions interrupted by physical abnormalities; they lack the ability to perceive hardware-level defects such as display screen rendering ghosts, causing the test environment to be disconnected from the real physical state; and they ignore high-attention but non-triggered intention areas in gaze trajectories, resulting in missed detection of key defect scenarios.

[0021] To solve the above problems, the present application proposes an AI-based automatic test case dynamic generation method. Specifically, the optical property changes of the display screen are captured by polarization imaging technology and the rendering ghost area is identified, the behavior correlation model is constructed combining user gaze and gesture data, the potential interaction intention interrupted by physical abnormalities is actively reconstructed using back-inference technology, and finally the test case set containing irregular operation paths is dynamically generated based on the intention, which fundamentally solves the potential path missed detection problem caused by physical abnormalities: it realizes the collaborative perception of hardware rendering defects and software behavior, breaks through the limitations of passive playback of historical operations, and significantly improves the active defect discovery capability of augmented reality and virtual reality applications in dynamic virtual-real fusion environments.

[0022] For those skilled in the art to better understand the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0023] The core of the present application is to provide an AI-based automatic test case dynamic generation method, and a specific embodiment of the method is shown in the flowchart Figure 1 The method comprises: S101, based on the behavior acquisition and processing of the user, the gaze trajectory and gesture sequence in the augmented reality and virtual reality application are obtained, the gaze trajectory and the gesture sequence are integrated, and user interaction behavior information is generated; In this step, the gaze trajectory refers to the path data of the focus of the user's eyeball moving on the screen; The gesture sequence refers to the record formed by the operation action of the user's fingers in space in time sequence; The user interaction behavior information refers to the complete data set describing the user's operation intention formed by the spatiotemporal correlation and integration of the gaze trajectory and the gesture sequence.

[0024] In the embodiment of the present application, first, the infrared eye tracker captures the time points and coordinate positions of the user's gaze at different areas of the screen to form the original gaze path; second, the depth camera collects the moving direction and touch action of the user's fingers in three-dimensional space to form the basic gesture record; then, the time synchronization mechanism is established to align the time stamp of the gaze path with the time axis of the gesture action; finally, the two types of data are fused in the space-time dimension to generate the user interaction behavior information stream containing the operation focus and action correlation.

[0025] In an actual case, in a virtual reality education application, the user continuously gazes at the chemical experiment equipment icon but does not perform the grabbing action, and the system integrates the gaze trajectory and the missing gesture sequence to generate the interaction behavior information reflecting the operation contradiction.

[0026] S102, AI-driven behavior correlation construction processing is performed on the user interaction behavior information to generate behavior interaction feature information; In this step, the behavior interaction feature information refers to the implicit correlation model between visual attention intensity and operation response delay mined from the user interaction behavior information by artificial intelligence technology.

[0027] In the embodiment of the application, first, the user interaction behavior information is scanned to extract the visual focus area with a stay duration exceeding a regular threshold in the gaze track; second, the delay period of the operation instruction issuing burst in the gesture sequence is detected; then, the overlap ratio of the high visual attention area and the operation delay period in the spatial position is calculated; finally, the internal correlation between the visual attention accumulation and the operation delay burst is analyzed through the neural network to construct a quantifiable behavior interaction feature model.

[0028] Continuing the above case, the system of the previous example detects the high-intensity gaze of the user on the dangerous chemical equipment icon and the significant delay of the grabbing action to generate the behavior interaction feature information of the equipment danger cognition causing operation hesitation.

[0029] S103, phase shift capture processing is performed on the display screen polarization state of the AI to generate sub-pixel response delay information; In this step, the sub-pixel response delay information refers to the pixel unit rendering response time delay data caused by the abnormal polarization state of the liquid crystal molecules of the display screen.

[0030] In the embodiment of the application, first, a linearly polarized light source of a specific wavelength is projected onto the surface of the display screen; second, the polarization phase shift amount of the reflected light is received through the photonic crystal sensor array; then, the instantaneous rate of the polarization angle change of each sub-pixel unit is calculated; finally, the sub-pixel level thermal map reflecting the rendering delay degree of the local area of the screen is generated.

[0031] Continuing the above case, the polarization imaging device detects an abnormal phase shift in the intersection identification area in the augmented reality navigation interface to generate the sub-pixel response delay information of the area.

[0032] S104, a rendering abnormal area of the sub-pixel response delay information is identified to generate rendering abnormal area information; In this step, the rendering abnormal area information refers to the spatial position data set of the display ghosting of the virtual object caused by the sub-pixel response delay exceeding the safety threshold.

[0033] In the embodiment of the application, first, a physically tolerable response delay threshold value is set; second, the pixel blocks continuously exceeding the threshold in the sub-pixel response delay information are scanned; then, the virtual object contour boundary covered by the delay blocks is marked; finally, the rendering abnormal area coordinate set describing the abnormal position and range of the ghosting is generated.

[0034] Continuing the above case, the system of the previous example identifies the delay value of the intersection identification area continuously exceeding the threshold to generate the rendering abnormal area information of the intersection identification ghosting blocking the turning arrow.

[0035] S105, the behavior interaction feature information and the rendering abnormal area information are combined for AI backtracking processing to generate potential interaction intention information; In this step, the potential interaction intention information refers to the operation target description that the user may perform but is interrupted based on the physical abnormal constraint condition through the backtracking technology.

[0036] In the embodiment of the application, first, the behavior interaction feature information is analyzed to establish a causal association chain of visual attention intensity and operation response delay; second, the spatial coordinates of the rendering abnormal area are injected into the causal chain as external intervention factors; then, the complete path of the gesture operation after eliminating the rendering abnormal area is simulated; finally, the operation intention description framework that the user may complete in the barrier-free environment is deduced.

[0037] Continuing the above case, the system of the previous example deduces the potential interaction intention information that the user may perform the sliding operation to view the turning intersection road condition to generate the traffic information if there is no intersection identification residual image.

[0038] S106, dynamically generate a test case set with the potential interaction intention information as a dynamic generation target.

[0039] In this step, the dynamic test case set refers to an executable test script set containing a non-conventional operation instruction sequence generated with the potential interaction intention as a generation target.

[0040] In the embodiment of the application, first, the potential interaction intention information is parsed into a spatial coordinate operation sequence; second, a path distortion variable is injected into the coordinate range of the rendering abnormal area; then, an operation instruction stream that fuses the abnormal gesture combination and the non-conventional trajectory is generated; finally, it is compiled into an automatic test case set that can trigger the target scene.

[0041] Continuing the above case, the system constructs a test instruction set that triggers the road condition panel three times by quickly sliding in the intersection identification residual image area, which is used to verify the interface logic collapse defect caused by the residual image occlusion.

[0042] In summary, S101 to S106 break through the path dependence of traditional testing on historical operations through the deep collaboration of multi-source behavior data collection and physical signal perception, fuse the gaze focus movement and gesture action sequence in the data collection layer to build a user intention model, use the polarization phase shift capture technology to identify hardware rendering defects in the physical perception layer, adopt the anti-intervention mechanism to reconstruct the potential operation path interrupted by physics in the analysis and deduction layer, and finally dynamically generate a test case set that covers unknown defects in the virtual-real fusion scene. This method fundamentally solves the interaction logic missing detection problem caused by rendering abnormalities in augmented reality and virtual reality applications, and significantly improves the active discovery capability of defects in dynamic interaction scenes.

[0043] To solve the potential intention recognition problem in the physical interruption scene, in some embodiments, according to S105, the AI back reasoning processing is performed in combination with the behavior interaction feature information and the rendering abnormal area information to generate potential interaction intention information, including: S201, the implicit causal relationship between the user operation delay of the behavior interaction feature information and the visual attention degree of the behavior interaction feature information is constructed and processed to generate behavior causal structure information; In S201, the behavior causal structure information refers to the directional dependence network established by analyzing the spatial distribution of the visual attention accumulation area and the time sequence association of the operation delay burst period.

[0044] In the embodiments of the application, first, the gaze trajectory in the behavior interaction feature information is scanned to extract the visual focus block coordinates that exceed the conventional stay time; second, the delay period and its spatial positioning of the operation instruction burst before the gesture sequence is detected; third, the spatial overlap degree of the visual focus block and the operation delay area is calculated; finally, the directional dependence network in which the visual attention intensity change drives the operation delay response is constructed through the causal discovery algorithm.

[0045] S202, in combination with the rendering abnormal area information, the intervention condition injection processing is performed on the virtual object display state in the behavior causal structure information to generate a back intervention parameter; In S202, the back intervention parameter refers to the physical distortion feature of the rendering abnormal area being converted into a state intervention variable of the causal network node.

[0046] In the embodiments of the application, first, the virtual object display node in the behavior causal structure information that overlaps with the rendering abnormal area is located; second, the attenuation coefficient of the optical distortion degree of the abnormal area on the object visibility is analyzed; third, the attenuation coefficient is mapped to a correction factor of the causal dependence intensity; finally, the state transfer function of the target node is reconstructed to generate the intervention parameter set.

[0047] S203, using the back intervention parameter, the operation result under the rendering abnormal area without executing the gesture operation is deduced to generate a back operation result information; In S203, the back operation result information refers to the virtual object state migration path simulated under the physical intervention constraint and triggered by the missing gesture.

[0048] In the embodiments of the application, first, the object state evolution rule under the constraint of the back intervention parameter is loaded; second, the virtual gesture starting coordinates are set at the boundary of the rendering abnormal area; third, the gradual change trajectory of the object display attribute in the gesture movement process is deduced according to the state transfer rule; finally, the complete path features when the object state reaches the critical failure threshold are recorded.

[0049] S204, based on the reverse operation result information, the potential interaction intention of the user is described and reconstructed, and the potential interaction intention information is generated.

[0050] In S204, the potential interaction intention information refers to the user's expected operation target description framework inferred according to the object state migration path.

[0051] In the embodiments of the present application, first, the termination form features of the object state migration in the reverse operation result information are analyzed; second, the intention description template in the pre-defined interaction scene is matched; third, the intention execution intensity parameter is corrected according to the path turning point; and finally, the operation object identifier and the target action are fused to generate the structured intention description.

[0052] The following is a specific example: In the VR education experiment scene, the user continuously gazes at the corrosive chemical container (visual attention accumulation area) but does not perform the pouring operation (operation delay burst period), and the system establishes a causal dependence network of "paying attention to the container causing operation hesitation"; after detecting that there is a rendering residual image in the container label area, the decay coefficient of the residual image causing the label visibility to decrease by 60% is calculated, which is converted into a causal intervention parameter; the pouring gesture is simulated at the boundary of the residual image, and the path of the liquid injection into the test tube due to the label being invisible is deduced; according to the flow rate mutation characteristics before the liquid overflow, the intention template of "accurately adding 50ml solution" is matched, and the potential interaction intention of "pouring the corrosive solution into the standard scale" is reconstructed.

[0053] In summary, S201 to S204 establish a causal intervention mechanism between behavior characteristics and physical defects, first convert visual operation conflicts into a calculable dependence network, second quantify hardware rendering abnormalities as network node intervention variables, third deduce the object failure path of the unperformed operation under physical constraints, and finally reconstruct the operation target interrupted by the user. The process realizes the active mining of potential intentions in the physical abnormal scene and provides a core basis for generating test cases for virtual-real fusion defects.

[0054] In order to deeply analyze the implicit decision conflicts in the user interaction behavior, in some embodiments, according to S102, the user interaction behavior information is subjected to AI-driven behavior association construction processing to generate behavior interaction feature information, including: S301, asynchronous coupling processing is performed on the pause interval in the gaze trajectory of the user interaction behavior information and the operation conflict in the gesture sequence of the user interaction behavior information, and behavior contradiction focus information is generated; In S301, the behavior contradiction focus information refers to a set of associated abnormal points formed in the spatial and temporal dimensions by the visual focus staying period exceeding the regular time in the gaze trajectory and the sudden operation interruption action in the gesture sequence.

[0055] In the embodiment of the application, first, the gaze trajectory data stream in the user interaction behavior information is analyzed frame by frame, the visual focus staying period formed by the continuous multiple frames of line-of-sight locking the same space coordinate is detected, and the starting and ending time stamps and the space coordinate range of the period are marked; second, the gesture sequence data stream is traversed, the operation interruption area formed by the sudden stop or direction mutation of the action in the operation instruction execution process is identified, and the space coordinate and duration of the interrupted action are extracted; then, the space-time mapping coordinate system is established, the time window of the visual focus staying period is aligned with the time window of the operation interruption area, and the Euclidean distance and the time sequence offset of the space coordinates are calculated; finally, the associated points with the spatial distance exceeding the preset threshold and the time sequence offset below the critical value are screened, and the behavior contradiction focus information set with strong space-time correlation is aggregated and generated.

[0056] In S302, the interaction hesitation feature information refers to the operation decision uncertainty quantification atlas generated by coupling calculation of the spatial heat distribution of the visual focus accumulation area and the duration of the operation delay burst period. In S302, the interaction hesitation feature information refers to the operation decision uncertainty quantification atlas generated by coupling calculation of the spatial heat distribution of the visual focus accumulation area and the duration of the operation delay burst period.

[0057] In the embodiment of the application, first, the gaze trajectory data stream in the user interaction behavior information is analyzed frame by frame, the visual focus staying period formed by the continuous multiple frames of line-of-sight locking the same space coordinate is detected, and the starting and ending time stamps and the space coordinate range of the period are marked; second, the gesture sequence data stream is traversed, the operation interruption area formed by the sudden stop or direction mutation of the action in the operation instruction execution process is identified, and the space coordinate and duration of the interrupted action are extracted; then, the space-time mapping coordinate system is established, the time window of the visual focus staying period is aligned with the time window of the operation interruption area, and the Euclidean distance and the time sequence offset of the space coordinates are calculated; finally, the associated points with the spatial distance exceeding the preset threshold and the time sequence offset below the critical value are screened, and the behavior contradiction focus information set with strong space-time correlation is aggregated and generated.

[0058] In S303, the potential intention marking information refers to the visual focus space coordinate set in the gaze trajectory that is not associated with the effective gesture operation screened based on the high hesitation quantification atlas. In S303, the potential intention marking information refers to the visual focus space coordinate set in the gaze trajectory that is not associated with the effective gesture operation screened based on the high hesitation quantification atlas.

[0059] In the embodiment of the application, first, the quantification atlas in the interactive hesitation feature information is scanned, the peak area exceeding the decision uncertainty threshold is identified and its spatial boundary is extracted; second, the original visual line coordinate sequence in the corresponding time window in the gaze track data stream is traced back, the spatial movement path of the visual line focus in the period is reconstructed; then, a dynamic time window is set on the reconstructed path, whether an effective gesture trigger signal is generated in the window period is detected for each focus area; finally, the high attention focus area without detecting the gesture trigger is marked with spatial coordinates to form a set of spatial marker points of the intention residue.

[0060] In S304, the interactive intention differentiation path of the user is topologically reconstructed by using the potential intention marking information and the behavior contradiction focus information, and behavior interaction feature information is generated.

[0061] In S304, the behavior interaction feature information refers to the interactive decision differentiation network containing the main operation path and the potential branch path reconstructed by the intention residue marker points and the behavior contradiction focus points.

[0062] In the embodiment of the application, first, the set of spatial coordinate points of the potential intention marking information is mapped into the decision nodes in the topological network; second, the spatiotemporal offset parameters in the behavior contradiction focus information are extracted, and the strength weight values of the connection edges between the nodes are calculated; then, the network bifurcation points corresponding to the hesitation peak area in the interactive hesitation feature information are identified; finally, according to the distribution of the decision nodes, the weight of the connection edges and the position of the bifurcation points, the interactive intention differentiation network model containing the main operation path and the potential alternative path is reconstructed.

[0063] The following is a specific example: In the augmented reality industrial maintenance scene, the maintenance personnel continuously gaze at the equipment fault indicator light area to form an ultra-long visual focus stay period, and the gesture operation suddenly stops when executing the disassembly instruction; the system detects the spatiotemporal anomaly point to generate the behavior contradiction focus information; the spatial overlap rate of the visual attention heat map of the fault light area and the delay period of the disassembly action reaches 85%, and the high hesitation quantification atlas is output; it is found by tracing back that no gesture operation is triggered in the area, and the potential intention coordinate point is marked; finally, the differentiation decision network of the main path continuing disassembly and the potential path fault light is reconstructed, and the behavior interaction feature information reflecting the operation contradiction of the maintenance personnel is formed.

[0064] As described above, S301 to S304 realize the deep mining of implicit behavior features through a four-stage progressive processing mechanism, first, the spatiotemporal contradiction points of gaze and gesture are accurately captured; second, the coupling quantification model of visual attention and operation delay is established; then, the intention residue area without triggering the operation is located; finally, the decision differentiation network is reconstructed; a complete conversion link from the original behavior data to the computable feature structure is formed, which breaks through the dependence of traditional methods on explicit behavior correlation and provides high-value behavior pattern input for backtracking.

[0065] To construct the test case set that can trigger the physical defect scene, in some embodiments, according to S106, the target is dynamically generated with the potential interaction intention information, the dynamic automation test case is constructed, and the dynamic test case set is generated, including: S401, the virtual operation area pointed by the intention in the potential interaction intention information is subjected to spatial coordinate conversion processing to generate intention spatial positioning information; In S401, the intention spatial positioning information refers to a three-dimensional space key point sequence formed by mapping the operation target object identifier in the potential interaction intention description framework to the virtual scene coordinate system, which contains the accurate coordinate set of the starting point, the path turning point and the termination point.

[0066] In the embodiments of the application, first, the operation target object feature identifier in the potential interaction intention information is parsed; second, the three-dimensional model surface topological structure of the target object is retrieved from the virtual scene space database; then, the geometric center point and boundary feature point coordinates of the model interactive region are calculated; finally, the coordinate sequence containing the spatial position and orientation vector is generated in the order of the operation path.

[0067] S402, in combination with the rendering abnormal region information, the operation path in the intention spatial positioning information is subjected to spatial variation processing to generate variation operation path information; In S402, the variation operation path information refers to the non-continuous spatial trajectory after the original path is subjected to deformation disturbance based on the optical distortion parameters of the rendering abnormal region, which retains the original path topological structure but introduces the path distortion caused by physical defects.

[0068] In the embodiments of the application, first, the spatial overlapping section of the operation path of the intention spatial positioning information and the rendering abnormal region is detected; second, the distortion gradient distribution and direction vector field of the abnormal region are extracted; then, the deformation disturbance intensity and direction offset angle are calculated in the path overlapping section; finally, the deformation disturbance is applied along the path normal direction to generate a twisted trajectory with a fracture zone and a curvature mutation.

[0069] S403, using the variation operation path information, the gesture action sequence in the potential interaction intention information is subjected to conflict injection processing to generate a conflict enhanced gesture sequence; In S403, the conflict enhanced gesture sequence refers to the antagonistic adjustment instruction stream of the spatial twist features of the variation path converted into the gesture action parameters, which contains the speed mutation, force reversal and trajectory oscillation features.

[0070] In the embodiments of the present application, firstly, the deformation parameters of the variant operation path information are decomposed into the curvature change rate and the fracture gap value; secondly, the basic gesture force, speed and direction parameters in the potential interaction intention information are analyzed; then, the reverse action force vector and the speed attenuation coefficient are inserted at the peak point of the path deformation; and finally, the gesture action control sequence containing multiple conflict instructions is reconstructed.

[0071] In S404, based on the conflict-enhanced gesture sequence and the variant operation path information, a test case execution logic is dynamically synthesized to generate a dynamic test case set.

[0072] In S404, the dynamic test case set refers to an executable test script set that fuses the conflict gesture instruction and the variant space path, which encapsulates the environment initial state, the operation instruction sequence and the expected failure condition.

[0073] In the embodiments of the present application, firstly, a synchronous mapping relationship between the time stamp of the conflict-enhanced gesture sequence and the spatial coordinates of the variant operation path is established; secondly, the gesture conflict instruction is bound at the path turning point to generate a space-time coupled operation event stream; then, the event stream is compiled into a binary instruction sequence that can be parsed by the device; and finally, the virtual scene initial state parameters are encapsulated to generate a complete test case set.

[0074] The following is a specific example: In the AR device maintenance training scene, the system analyzes the potential interaction intention of "disassembling the overheated engine bolt", maps the bolt model to a three-dimensional space operation coordinate sequence; after detecting that there is a rendering residual image on the surface of the bolt, the disassembly path is distorted into an irregular trajectory with a fracture zone according to the residual image distortion gradient; the reverse screwing force and the operation pause instruction are injected at the path fracture point to generate a conflict gesture sequence containing sudden reverse rotation; and finally, a test case of "executing the conflict gesture along the fracture path to trigger tool jamming" is synthesized to verify the virtual tool system crash defect caused by rendering abnormalities.

[0075] In summary, S401 to S404 realize the active construction of test cases through a four-level dynamic conversion mechanism. Firstly, the intention description is mapped to an operable space path; secondly, physical deformation disturbance is applied to the path based on the hardware defect characteristics; thirdly, the spatial deformation is converted into an antagonistic conflict of gesture action; and finally, an executable test script is generated by fusing the space-time parameters; a complete closed loop from user intention to defect triggering is formed, which breaks the dependence on preset rules in traditional test case generation methods and significantly improves the defect detection rate of physical abnormal scenes.

[0076] In order to accurately model the intervention mechanism of hardware defects on interaction logic, in some embodiments, according to S202, the display state of the virtual object in the behavior causal structure information is subjected to intervention condition injection processing in combination with the rendering abnormal area information to generate anti-intervention parameters, including: S501, quantifying the optical distortion degree of the residual image area in the rendering abnormal area information by a physical interference, to generate a residual image interference intensity parameter; In S501, the residual image interference intensity parameter refers to a virtual object visibility attenuation coefficient calculated based on the polarization light phase shift amplitude and distribution density, which comprehensively reflects the profile blurring and color distortion degree caused by light distortion.

[0077] In the embodiments of the present application, first, the polarization phase shift amount heat map of the residual image block in the rendering abnormal area information is extracted; second, the maximum deviation value of the phase shift angle relative to the normal display reference is measured; third, the profile edge blur radius is calculated by analyzing the spatial gradient distribution of the phase shift angle; at the same time, the color phase deviation amplitude caused by the phase shift is detected; finally, the edge blur radius and the color phase deviation amplitude are fused to generate a normalized optical distortion interference intensity value.

[0078] S502, using the residual image interference intensity parameter, reconstructing the state of the operation delay in the behavior causal structure information and the causal link of the visual attention degree in the behavior causal structure information, to generate distortion causal link information; In S502, the distortion causal link information refers to a modified version of the state-dependent rule set formed after injecting the residual image interference intensity as an external intervention variable into the original causal transfer function.

[0079] In the embodiments of the present application, first, the causal nodes in the behavior causal structure information that spatially overlap with the residual image area are located; second, the state transition equation of the visual attention degree change to the operation delay response in the original causal link is analyzed; third, the residual image interference intensity parameter is mapped to the attenuation weight factor in the transition equation; finally, the causal state transition rule library containing the optical distortion constraint is reconstructed.

[0080] S503, combining the distortion causal link information, dynamically simulating the visibility attenuation characteristics of the virtual object display state in the residual image area, to generate a display state attenuation model; In S503, the display state attenuation model refers to a mathematical description framework of the visibility gradual change process of the virtual object with the spatial position moving under the constraint of the distortion causal rule.

[0081] In the embodiments of the present application, first, the state transition rule library in the distortion causal link information is loaded; second, the object display integrity parameter is initialized at the boundary of the residual image area; third, the visibility attenuation curve of the object moving process to the center of the residual image is deduced according to the transition rule; finally, a dynamic mathematical model containing the attenuation rate and the critical disappearance threshold is established.

[0082] S504, based on the display state attenuation model, intervening and correcting the operation feasibility of the non-executed gesture operation under the distortion causal constraint, to generate an anti-intervention parameter.

[0083] In S504, the anti-intervention parameter refers to the fusion of object visibility attenuation features and the feasibility constraint variable set of gesture operation space trajectory.

[0084] In the embodiments of the present application, first, the three-dimensional coordinates of the object critical disappearance point in the display state attenuation model are analyzed; second, the shortest spatial distance between the gesture operation path trajectory and the critical point is calculated; third, the maximum allowed time of gesture operation is dynamically adjusted according to the attenuation rate; and finally, the intervention parameter set containing the spatial distance tolerance and the time window threshold is generated.

[0085] The following is a specific example: In the AR museum tour scene, the system detects that there is a high-density polarization phase shift in the artifact display label area, and generates a strong interference intensity parameter; the parameter is injected into the causal link of "visual attention artifact label triggers operation delay", and the distortion causal rule of "operation is triggered only when gaze is prolonged in the presence of residual image" is reconstructed; based on the rule, the visibility attenuation process of the label in the residual image area is deduced, and a dynamic model of accelerated decline of label visibility when moving close to the critical disappearance point is established; according to the model, it is determined that the gesture operation needs to be completed within a certain distance from the critical disappearance point and the operation speed needs to be increased to a multiple of the baseline value, and an anti-intervention parameter set containing spatial distance limit and operation speed threshold is generated.

[0086] In summary, S501 to S504 realize accurate modeling of physical defects through a four-level cross-layer intervention mechanism. First, the optical distortion features are quantified into calculable parameters; second, the state transmission rules of the causal network are reconstructed; third, the object visibility dynamic attenuation model is established; and finally, the operation feasibility constraint parameters are generated; forming a closed-loop intervention chain from hardware signals to software logic, providing high-fidelity physical constraints for anti-inference, and breaking through the limitations of traditional methods for simplified modeling of hardware defects.

[0087] In order to finely reconstruct the differentiation features of the user decision path, according to S304, in some embodiments, the potential intention marking information and the behavior contradiction focus information are used to perform topological reconstruction processing on the user's interaction intention differentiation path, and behavior interaction feature information is generated, including: S601, performing intention splitting processing on the untriggered hot spot area in the potential intention marking information and the operation conflict area in the behavior contradiction focus information, to generate split intention node information; In S601, the split intention node information refers to a set of independent decision units formed by segmenting the intersection part of the untriggered hot spot area and the operation conflict area through spatial overlap analysis, each unit containing spatial boundary coordinates and initial intention intensity value.

[0088] In the embodiment of the application, firstly, a three-dimensional mapping relationship between an untriggered hotspot area space coordinate set of potential intention marking information and an operation conflict area space coordinate set of behavior contradiction focus information is established; secondly, a spatial intersection volume and a continuous distribution characteristic of the two coordinate sets are calculated; then, the overlapping area is divided into minimum decision unit blocks according to the spatial continuity principle; finally, a basic intention intensity value is assigned to each unit block to generate a split node set with a weight attribute.

[0089] In S602, the path repulsion parameter refers to a combined measurement index of the path curvature mutation amplitude and the avoidance distance threshold value generated when the gaze trajectory circumvents the split node boundary.

[0090] In the embodiment of the application, firstly, a three-dimensional space boundary model of each unit block in the split intention node information is extracted; secondly, the original line-of-sight movement path sequence of the adjacent node area in the gaze trajectory data stream is traced back; then, the minimum Euclidean distance between the line-of-sight path and the node boundary model and the path curvature change gradient are calculated; finally, the distance threshold value and the curvature change rate are fused to generate a spatial repulsion strength quantization parameter.

[0091] In S603, the intention connection attenuation information refers to a topology relationship correction data set obtained by implementing nonlinear attenuation on the initial connection weight of adjacent split nodes according to the spatial repulsion strength.

[0092] In the embodiment of the application, firstly, a full connection network framework of adjacent nodes in the split intention node information is constructed; secondly, a spatial repulsion strength distribution graph in the path repulsion parameter is loaded; then, a connection edge attenuation coefficient is calculated according to the product of the repulsion strength value and the node centroid distance; finally, an exponential attenuation model is applied to reconstruct a dynamic weight distribution graph of the nodes.

[0093] In S604, the reconstructed topology path information refers to a spatial trajectory network model containing a main path and a potential branch path generated by a path optimization algorithm based on the attenuation weight distribution graph.

[0094] ​​​In the embodiments of the present application, first, the dynamic weight distribution atlas in the intention connection attenuation information is loaded; second, the core path skeleton network formed by the high weight connection edges is identified; then, the spatial distribution of the branch point of the low weight connection region is detected; finally, the multi-level branch network is generated by simulating the evolution trajectory of the path extending from the core skeleton to the branch point through the minimum energy path algorithm.

[0095] In S605, the differentiation characteristics of the user's behavior mode are processed to generate behavior interaction feature information.

[0096] In S605, the behavior interaction feature information refers to converting the topological path network into a calculable decision framework containing the priority of the main operation flow and the trigger condition of the alternative operation flow.

[0097] In the embodiments of the present application, first, the core backbone path coordinate sequence in the reconstructed topological path information is parsed; second, the starting node and the terminal node spatial coordinates of each level branch path are extracted; then, the spatial deviation angle and the path length ratio of the branch path and the backbone path are quantified; finally, a structured feature description model containing the path selection probability distribution and the execution condition constraint is constructed.

[0098] The following is a specific example: In the VR space flight training scene, the user forms a high attention untriggered hot spot for the fuel valve icon, and there is a valve operation conflict in this area; the system divides the overlapping area into five split nodes and assigns an initial intensity; it is detected that the gaze trajectory bypasses the node three boundary with high curvature, and the repulsion parameter is calculated; the connection edge between node two and node three is exponentially attenuated according to the repulsion value; the differentiated topological network of the main path executing routine detection and the branch path emergency valve closing is reconstructed; and finally, the structured behavior feature model of the main path selection probability and the branch path temperature threshold is generated.

[0099] In summary, S601 to S605 realize the fine modeling of the decision path through a five-level topological evolution mechanism. First, the intention conflict is converted into a calculable node unit through spatial segmentation; second, the physical repulsion effect caused by the gaze bypass is quantified; then, the node connection weight is dynamically reconstructed; then, the multi-level path network evolution is simulated; finally, the structured behavior decision model is generated; forming a complete conversion chain from the original behavior contradiction to the calculable differentiated feature, breaking through the limitations of traditional linear behavior modeling, and providing a high-fidelity decision path input for backtracking.

[0100] In order to accurately simulate the interaction failure process caused by physical defects, in some embodiments, according to S203, the anti-intervention parameter is used to perform backtracking processing on the operation result of the unexecuted gesture operation under the rendering abnormal area to generate anti-operation result information, including: S701, based on the anti-intervention parameter, the interaction response rule of the virtual object in the rendering abnormal area is constrained and reconstructed, and abnormal interaction constraint information is generated; In S701, the abnormal interaction constraint information refers to converting the spatial distance tolerance of the anti-intervention parameter and the time window threshold into the set of spatial sensitivity decay function and state change acceleration rule of the virtual object responding to the gesture operation.

[0101] In the embodiment of the application, first, the minimum safe spatial distance limit parameter in the anti-intervention parameter is analyzed; second, the maximum allowed time threshold parameter is extracted; then the spatial distance limit is mapped to a non-linear function of the sensitivity of the object responding to the gesture approaching action decreasing with distance; at the same time, the time window threshold is converted into an acceleration factor function of the object state change rate increasing with operation time; finally, the two types of functions are fused to generate an interaction constraint rule library containing spatial sensitivity curve and time acceleration factor.

[0102] S702, using the abnormal interaction constraint information, the deformation process of the trajectory form of the gesture operation not performed in the rendering abnormal area is dynamically simulated, and gesture deformation trajectory information is generated; In S702, the gesture deformation trajectory information refers to a non-continuous spatial distortion path of the original gesture path under the constraint of spatial sensitivity decay; the path contains a fracture zone and a curvature mutation feature.

[0103] In the embodiment of the application, first, the spatial sensitivity decay function in the abnormal interaction constraint information is loaded; second, the initial spatial coordinates and direction vector of the gesture operation are set at the boundary of the rendering abnormal area; then the deformation gradient distribution of the normal direction of each point of the path is calculated according to the spatial sensitivity function; finally, the fracture zone and the curvature mutation are generated by applying displacement disturbance along the gradient direction to generate a distorted spatial trajectory.

[0104] S703, combining the gesture deformation trajectory information, the state migration path of the virtual object under abnormal constraint is evolved and deduced, and object state evolution information is generated; In S703, the object state evolution information refers to the complete migration path record of the change of the key attribute value of the virtual object with the operation process under the action of the gesture deformation trajectory combined with the time acceleration factor.

[0105] In the embodiment of the application, first, the accurate correspondence between the spatial coordinate points and the time stamps of the gesture deformation trajectory is established; second, the time acceleration factor function in the abnormal interaction constraint information is loaded; then the object state change rate is improved according to the acceleration factor at the curvature mutation point of the deformation trajectory; finally, the whole path attribute value change sequence of the object from the initial state to the critical failure state is continuously recorded.

[0106] S704, boundary positioning processing is performed on critical conditions of operation interruption and error triggering in the object state evolution information, and operation failure boundary information is generated; In S704, the operation failure boundary information refers to a set of accurate spatial position and time node markers of a function abnormality or operation interruption triggered in the object state migration path.

[0107] In the embodiments of the present application, first, the attribute value first derivative mutation points in the object state evolution information are scanned; second, the critical position coordinates of the attribute value exceeding the preset safety threshold are detected; third, the turning point of the irreversible state change is located; and finally, the three-dimensional spatial coordinates and accurate timestamp data pair of the failure trigger point are marked.

[0108] S705, using the operation failure boundary information, integrity deduction processing is performed on the final interaction result of the unexecuted gesture operation in the rendering abnormal area, and anti-operation result information is generated.

[0109] In S705, the anti-operation result information refers to a visual deduction report framework containing error triggering mechanism and abnormal terminal state reconstructed by failure boundary features.

[0110] In the embodiments of the present application, first, the spatial position coordinates and time node data in the operation failure boundary information are analyzed; second, the motion direction and speed parameters of the gesture deformation trajectory at the corresponding time are traced back; third, the gradual change process curve of the object state in the time window before and after the failure point is reconstructed; and finally, a three-dimensional visual deduction report containing error triggering position, failure mechanism diagram and state change curve is generated.

[0111] The following is a specific example: In virtual airplane maintenance training, the system generates a proximity sensitivity decay rule of the wrench operation based on the anti-interference parameters; the wrench trajectory deformation process is deduced in the engine component residual area; the bolt stress value is accelerated to rise under the simulation of the deformation trajectory; the critical point of thread gliding triggered by stress exceeding yield strength is detected; and finally, the complete operation result of "wrench trajectory offset leading to bolt failure" is reconstructed, and a visual three-dimensional report containing stress curve mutation and gliding position is generated.

[0112] In summary, S701 to S705 realize high-fidelity simulation of physical defect scenarios through a five-level precise deduction mechanism. First, the intervention parameters are converted into spatial sensitivity and time acceleration double constraint rules; second, the dynamic deformation process of the gesture path is deduced; third, the object state migration is simulated in combination with the time acceleration factor; fourth, the failure critical point is accurately located; and finally, the visual operation result is reconstructed; a closed-loop deduction chain from hardware defects to operation failure is formed, breaking through the limitations of traditional methods for simplified modeling of physical abnormal scenarios.

[0113] Figure 4A structural schematic diagram of one specific embodiment of an AI-based automatic test case dynamic generation system provided by an embodiment of the present application is shown in FIG. 1. Referring to FIG. 1, Figure 4 The system can include: A behavior collection module 41 configured to collect and process user behaviors to obtain gaze tracks and gesture sequences in an augmented reality and virtual reality application, integrate the gaze tracks and the gesture sequences, and generate user interaction behavior information. An association construction module 42 configured to perform AI-driven behavior association construction processing on the user interaction behavior information to generate behavior interaction feature information. A polarization capture module 43 configured to perform phase shift capture processing on a display screen polarization state of AI to generate sub-pixel response delay information. An anomaly identification module 44 configured to identify a rendering anomaly area of the sub-pixel response delay information and generate rendering anomaly area information. An intention deduction module 45 configured to perform AI reverse deduction processing in combination with the behavior interaction feature information and the rendering anomaly area information to generate potential interaction intention information. A test case generation module 46 configured to use the potential interaction intention information as a dynamic generation target to construct an automatic test case dynamic and generate a dynamic test case set.

[0114] The AI-based automatic test case dynamic generation system of the embodiment of the present application is used to implement the aforementioned AI-based automatic test case dynamic generation method, and thus the specific embodiments of the AI-based automatic test case dynamic generation system can refer to the embodiment part of the AI-based automatic test case dynamic generation method in the foregoing description, and will not be described herein again.

[0115] The present application also provides an electronic device including a memory configured to store a computer program and a processor configured to implement the steps of the AI-based automatic test case dynamic generation method described above when executing the computer program.

[0116] The present application also provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the AI-based automatic test case dynamic generation method described above.

[0117] In one exemplary embodiment, the computer readable storage medium described above can include, but is not limited to, a U disk, a read-only memory, a random access memory, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0118] The embodiment of the present application also provides a computer program product, the computer program product comprising a computer program, the computer program being executed by a processor to realize the steps in any of the AI-based automatic test case dynamic generation method embodiments.

[0119] Those skilled in the art will further appreciate that the functions of the examples described herein-based units and algorithm steps can be implemented using electronic hardware, computer software, or any combination thereof. When the functions are implemented in software, the functions can be stored on or transmitted over a computer-readable medium, such as an optical, magnetic or semiconductor storage medium. The steps of a method or algorithm can be implemented in an operating system, a program, or a piece of code that is executed to accomplish a specific logic function or a combination of the above. The embodiments described herein can be realized in a centralized fashion in one computer system or network, or in a distributed fashion where different elements are spread across several computer systems or sub-networks. Any kind of computer system, or other apparatus adapted for carrying out the methods described herein, is suited. A typical combination of hardware and software could be a general purpose computer system with a computer program that, when being loaded and executed, carries out the methods described herein. The present disclosure also relates to a computer program embodied on a carrier medium, comprising program instructions which, when executed by a computer, cause the computer to carry out the methods described herein.

[0120] The above provides a kind of based on AI's automatic test case dynamic generation method, system, electronic equipment and storage medium provided in the application have been introduced in detail.The principle and implementation mode of the present application are described in this paper, the above example is only used to help understanding the method of the present application and its core idea.It should be pointed out that, for the ordinary skilled in the art, without departing from the principle of the present application, the present application can be improved and modified, these improvements and modifications also fall within the scope of the present application.

Claims

1. A method for dynamically generating automated test cases based on AI, characterized in that: include: Based on the user's behavior collection and processing, the gaze trajectory and gesture sequence in augmented reality and virtual reality applications are obtained, and the gaze trajectory and gesture sequence are integrated to generate user interaction behavior information; Performing AI-driven behavior association construction processing on the user interaction behavior information to generate behavior interaction feature information; Perform phase shift capture processing on the polarization state of the AI ​​display screen to generate sub-pixel response delay information; Identifying a rendering abnormality region of the sub-pixel response delay information and generating rendering abnormality region information; Combining the behavioral interaction feature information and the rendering abnormal area information, AI reverse deduction processing is performed to generate potential interaction intention information; Taking the potential interaction intention information as the dynamic generation target, construct the automated test case dynamics and generate a dynamic test case set.

2. The method according to claim 1, characterized in that Combining the behavioral interaction feature information and the rendering abnormal area information, AI reverse deduction processing is performed to generate potential interaction intention information, including: constructing and processing the implicit causal relationship between the user operation delay of the behavioral interaction feature information and the visual attention of the behavioral interaction feature information to generate behavioral causal structure information; In combination with the rendering abnormal area information, performing intervention condition injection processing on the display state of the virtual object in the behavior causal structure information to generate anti-intervention parameters; Using the anti-intervention parameters, deducing and processing the operation results of the unexecuted gesture operation in the rendering abnormal area to generate anti-operation result information; Based on the reverse operation result information, the user's potential interaction intention is described and reconstructed to generate potential interaction intention information.

3. The method according to claim 1, characterized in that Performing AI-driven behavior association construction processing on the user interaction behavior information to generate behavior interaction feature information, including: performing asynchronous coupling processing on a pause interval in a gaze trajectory of the user interaction behavior information and an operation conflict in a gesture sequence of the user interaction behavior information to generate behavior conflict focus information; Based on the behavioral conflict focus information, performing intention hesitation quantification processing on the visual attention accumulation area in the gaze trajectory and the operation delay burst period in the gesture sequence to generate interaction hesitation feature information; In combination with the interaction hesitation feature information, performing intention residual marking processing on the hotspot area in the gaze trajectory where no gesture is triggered, to generate potential intention marking information; The potential intention mark information and the behavior conflict focus information are used to perform topological reconstruction processing on the user's interaction intention differentiation path to generate behavior interaction feature information.

4. The method according to claim 1, wherein Taking the potential interaction intention information as the dynamic generation target, constructing the automated test case dynamics and generating a dynamic test case set, including: Performing spatial coordinate conversion processing on the virtual operation area intended to be pointed at in the potential interaction intention information to generate intention space positioning information; In combination with the rendering abnormal area information, performing spatial variation processing on the operation path in the intended spatial positioning information to generate variation operation path information; Using the variant operation path information, performing conflict injection processing on the gesture action sequence in the potential interaction intention information to generate a conflict enhanced gesture sequence; Based on the conflict enhancement gesture sequence and the variation operation path information, the test case execution logic is dynamically synthesized to generate a dynamic test case set.

5. The method according to claim 2, characterized in that Combined with the rendering abnormal area information, intervention condition injection processing is performed on the display state of the virtual object in the behavior causal structure information to generate anti-intervention parameters, including: Performing physical interference quantification processing on the optical distortion degree of the afterimage area in the rendering abnormal area information to generate an afterimage interference intensity parameter; Using the afterimage interference intensity parameter, a state reconstruction process is performed on the causal link between the operation delay in the behavior causal structure information and the visual attention in the behavior causal structure information to generate distorted causal link information; In combination with the distortion causal link information, a dynamic simulation process is performed on the visibility attenuation characteristics of the display state of the virtual object in the afterimage area to generate a display state attenuation model; Based on the display state attenuation model, intervention correction processing is performed on the operational feasibility of the unexecuted gesture operation under the distortion causal constraint to generate anti-intervention parameters.

6. The method according to claim 3, characterized in that Using the potential intention tag information and the behavior conflict focus information, a topological reconstruction process is performed on the user's interaction intention differentiation path to generate behavior interaction feature information, including: Performing intention splitting processing on the untriggered hotspot area in the potential intention mark information and the operation conflict area in the behavior conflict focus information to generate split intention node information; Based on the split intention node information, performing repulsion strength calculation processing on the detour operation path surrounding the conflict area in the gaze trajectory to generate a path repulsion parameter; Using the path exclusion parameter, dynamically attenuate the connection relationship between the split intention node information to generate intention connection attenuation information; Combined with the intention connection attenuation information, an evolutionary simulation process is performed on the spatial topological structure of the interaction intention differentiation path to generate reconstructed topological path information; Based on the reconstructed topological path information, a structured description process is performed on the differentiation characteristics of the user's behavior pattern to generate behavior interaction feature information.

7. The method according to claim 2, characterized in that The anti-intervention parameter is used to deduce the operation result of the unperformed gesture operation in the rendering abnormal area to generate anti-operation result information, including: Based on the anti-intervention parameters, constrained reconstruction processing is performed on the interactive response rules of the virtual objects in the rendering abnormal area to generate abnormal interaction constraint information; Using the abnormal interaction constraint information, dynamically simulate the deformation process of the trajectory of the unperformed gesture operation in the rendering abnormal area to generate gesture deformation trajectory information; In combination with the gesture deformation trajectory information, an evolutionary deduction process is performed on the state migration path of the virtual object under abnormal constraints to generate object state evolution information; Performing boundary positioning processing on critical conditions of operation interruption and error triggering in the object state evolution information to generate operation failure boundary information; The operation failure boundary information is used to perform integrity deduction processing on the final interaction result of the unexecuted gesture operation in the rendering abnormal area to generate reverse operation result information.

8. An AI-based automated test case dynamic generation system, characterized in that: include: A behavior collection module is used to collect and process user behavior, obtain gaze tracks and gesture sequences in augmented reality and virtual reality applications, integrate the gaze tracks and gesture sequences, and generate user interaction behavior information; An association construction module, configured to perform AI-driven behavior association construction processing on the user interaction behavior information to generate behavior interaction feature information; Polarization capture module, used to perform phase shift capture processing on the polarization state of the AI ​​display screen to generate sub-pixel response delay information; An abnormality identification module, used to identify a rendering abnormality area of ​​the sub-pixel response delay information and generate rendering abnormality area information; An intention deduction module is used to combine the behavioral interaction feature information and the rendering abnormal area information to perform AI reverse deduction processing to generate potential interaction intention information; The use case generation module is used to construct automated test case dynamics based on the potential interaction intention information and generate a dynamic test case set.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the method for dynamically generating automated test cases based on AI as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, can implement the AI-based automatic test case dynamic generation method according to any one of claims 1 to 7.

Images