An internet mall management platform system

Abstract

The present application relates to platform management technical field, especially to a kind of internet mall management platform system.The system includes the following modules: trajectory acquisition module, trajectory clustering module, cognitive optimization module and conflict processing module, specifically, periodically collect user mouse coordinates, when the starting point and the end point distance of mouse trajectory in the preset range are detected to be less than the first threshold value and the total length of path is greater than the second threshold value, it is determined as whirlpool trajectory, whirlpool trajectory data is output;The whirlpool trajectories of multiple users in the preset time period are superimposed according to page position, when the trajectory overlap degree exceeds the preset overlap threshold, trajectory cluster is formed, and the geometric center of trajectory cluster is calculated as cognitive hot area based on whirlpool trajectory data;According to the number of user sources of cognitive hot area, group cognitive disorder point is determined.The present application can capture the cognitive confusion moment of user in real time through dynamic sampling frequency adjustment, and accurately distinguish group cognitive disorder and individual preference through multi-user trajectory superposition analysis.

Description

Technical Field

[0001] This invention relates to the field of platform management technology, and in particular to an internet e-commerce management platform system. Background Technology

[0002] The variety and quantity of goods on online shopping platforms are growing exponentially, making it increasingly difficult for users to find their target products amidst this vast sea of ​​goods. Existing shopping platform management systems primarily rely on search engines, recommendation algorithms, and category navigation to help users find products. However, these solutions have the following shortcomings: Traditional user behavior analysis techniques are mainly based on macro-level indicators such as click-through rate, dwell time, and bounce rate. These indicators only reflect the final result of user behavior and cannot capture the cognitive difficulties users experience during the decision-making process. For example, when a user hesitates between two similar product categories, traditional analysis methods can only record which option the user ultimately clicks, but cannot identify the confusion and hesitation the user experienced during the selection process. Existing page optimization solutions often employ methods such as A / B testing, requiring large samples and long testing periods to draw conclusions. Furthermore, the optimization results are often based on statistical averages, failing to accurately pinpoint specific cognitive obstacles. While heatmap tools can display areas of user attention, they cannot distinguish between normal browsing behavior and cognitive confusion behavior, resulting in a lack of targeted optimization. Summary of the Invention

[0003] Therefore, it is necessary for the present invention to provide an internet e-commerce management platform system to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, an internet e-commerce management platform system includes the following modules: The trajectory acquisition module is used to periodically collect the user's mouse coordinates. When it detects that the distance between the start and end points of the mouse trajectory within a preset range is less than a first threshold while the total path length is greater than a second threshold, it is determined to be a spiral trajectory and the spiral trajectory data is output. The trajectory clustering module is used to superimpose the circumference trajectories of multiple users within a preset time period according to the page position. When the trajectory overlap exceeds the preset overlap threshold, a trajectory cluster is formed. The geometric center of the trajectory cluster is calculated based on the circumference trajectory data as the cognitive hot zone. The cognitive optimization module is used to determine the cognitive barrier points of the group based on the number of users from the cognitive hot zone; calculate the similarity of page element pairs within the cognitive barrier points; and extract the difference keywords to generate optimization instructions when the similarity exceeds the preset similarity threshold. The conflict handling module receives optimization instructions, executes optimization strategies based on cognitive conflict types according to the time distribution characteristics of the spiral trajectory, and feeds back the trajectory change rate before and after optimization to the cognitive analysis module to form a closed-loop optimization.

[0005] This invention achieves accurate identification and dynamic optimization of page cognitive conflicts and operational obstacles through real-time acquisition and analysis of user mouse hovering trajectories. First, based on the analysis of displacement vectors and trajectory segments, it captures user behavior of lingering or repeatedly comparing on the page, thereby identifying potential hovering trajectories and overcoming the limitations of traditional click and dwell time statistics to more intuitively reflect user confusion. Second, mapping the trajectory to a virtual grid and calculating spatial and temporal similarity allows for aggregated analysis of hovering behavior, forming cognitive hotspots and accurately locating easily confused elements. Third, by calculating the hovering center, radius, and duration, the system quantifies the cognitive intensity of hotspots and, combined with weighted centers and outlier splitting, characterizes single-center or double-center hotspots, revealing the cognitive distribution of user groups. Furthermore, through analysis of the number of independent users, access frequency, and dispersion, it identifies group cognitive obstacle points and, combined with element similarity and difference attributes, automatically generates optimization instructions, proposing targeted improvement strategies, including immediate visual enhancement and delayed information supplementation. After optimization, the system monitors the trajectory change rate, compares the effects before and after optimization, and automatically solidifies or reverts to the strategy, forming a data-driven closed-loop optimization mechanism. This method not only identifies problems that traditional indicators struggle to capture but also outputs actionable improvement solutions, thereby significantly enhancing the clarity, efficiency, and user experience of page interactions. Attached Figure Description

[0006] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the module contents of the Internet e-commerce management platform system of the present invention; Figure 2 This is a schematic diagram of multi-user trajectory overlay and clustering according to an embodiment of the present invention; Figure 3 This is a comparison diagram of the user interface before and after optimization according to an embodiment of the present invention. Figure 4 This is a cognitive hotspot and obstacle point recognition map according to an embodiment of the present invention. Detailed Implementation

[0007] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0008] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0009] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0010] To achieve the above objectives, please refer to Figures 1 to 4 This invention provides an internet e-commerce platform system, comprising the following modules: S1: Trajectory acquisition module, used to periodically acquire user mouse coordinates. When it is detected that the distance between the start and end points of the mouse trajectory within a preset range is less than the first threshold while the total path length is greater than the second threshold, it is determined to be a spiral trajectory and the spiral trajectory data is output. S2: Trajectory clustering module, used to superimpose the circumference trajectories of multiple users within a preset time period according to page position. When the trajectory overlap exceeds the preset overlap threshold, a trajectory cluster is formed. The geometric center of the trajectory cluster is calculated based on the circumference trajectory data as the cognitive hot zone. S3: Cognitive Optimization Module, used to determine the group's cognitive obstacle points based on the number of users from the cognitive hot zone; calculate the similarity of page element pairs within the group's cognitive obstacle points; when the similarity exceeds a preset similarity threshold, extract the difference keywords to generate optimization instructions; S4: Conflict handling module, used to receive optimization instructions, execute optimization strategies based on cognitive conflict type according to the time distribution characteristics of the spiral trajectory, and feed back the trajectory change rate before and after optimization to the cognitive analysis module to form a closed-loop optimization.

[0011] Furthermore, the trajectory acquisition module includes: The user's mouse coordinates are coarsely sampled at the first sampling frequency, and the displacement vector between consecutive coordinate points is recorded. In one embodiment, the system coarsely samples the user's mouse coordinates at a first sampling frequency. It periodically acquires the user's mouse position points on the page and calculates the difference between consecutive coordinate points as a displacement vector. This method generates a low-density trajectory sequence, which can be used to initially determine the user's mouse movement trend.

[0012] For example, when the first sampling frequency is set to 20 times per second, if the user moves the mouse along a winding path on the page, the system will record several key coordinate points and calculate the displacement direction and length between adjacent points, thereby obtaining a set of displacement vector sequences.

[0013] When the sum of the directional angles of three consecutive displacement vectors exceeds 180 degrees, the fine sampling mode is triggered, and the sampling frequency is increased to the second sampling frequency, which is greater than the first sampling frequency. In one embodiment, when the system detects that the sum of the directional angles of three consecutive displacement vectors exceeds 180 degrees, it determines that the user has engaged in relatively complex mouse trajectory behavior, thereby triggering a fine sampling mode. In fine sampling mode, the sampling frequency is increased from a first sampling frequency to a second sampling frequency in order to capture trajectory details more meticulously.

[0014] For example, when a user makes a fast circular drag on the page, the included angles between three consecutive displacement vectors may be 80 degrees, 70 degrees and 50 degrees respectively, and their sum is 200 degrees, which is greater than 180 degrees. The system immediately switches to a fine sampling frequency of 100 times per second, so as to accurately capture the curvature features of the trajectory.

[0015] It should be noted that this judgment method can effectively filter out normal straight lines or slow movements, thus increasing resolution only when complex trajectories occur, saving system resources.

[0016] In the fine sampling mode, the collected coordinate sequence is divided into a sliding window of length N, the start and end points of the trajectory within each window are determined, and the straight-line distance between the start and end points is calculated. In one embodiment, in fine sampling mode, the system divides the acquired high-frequency coordinate sequence into sliding windows of length N, with each window used for individual analysis. For each sliding window, the system extracts its start and end coordinates and calculates the straight-line distance between them to determine the overall shape of the trajectory segment.

[0017] For example, when N is set to 50, the coordinate sequence collected within a certain window starts at (100, 200) and ends at (105, 195). The system calculates that the straight-line distance between the start and end points is approximately 7 pixels. In this way, it is possible to quickly detect whether a trajectory segment exhibits a local closure or a spiraling trend.

[0018] When the straight-line distance between the start and end points is less than the first threshold, the path length verification is initiated, and the trajectory is determined to be a loop trajectory, and the loop trajectory data is output.

[0019] In one embodiment, when the straight-line distance between the start and end points of a sliding window is detected to be less than a first threshold, the system enters the path length verification stage, that is, calculates the actual path length of the trajectory segment. The actual path length is obtained by accumulating the distances between all adjacent coordinate points within the window. When the path length is greater than a second threshold, the segment can be determined to be a spiral trajectory.

[0020] For example, when the first threshold is set to 10 pixels and the second threshold is set to 100 pixels, if the straight-line distance between the start and end points of a trajectory window is only 5 pixels, but the cumulative path length reaches 150 pixels, it indicates that the trajectory has detoured multiple times within a small range. The system will eventually determine it as a spiral trajectory and output the corresponding data.

[0021] Furthermore, when the straight-line distance between the start and end points is less than the first threshold, the path length verification is initiated, and the trajectory is determined to be a loop trajectory. The loop trajectory data is then output as follows: For trajectory segments that meet the first threshold condition, calculate their actual total path length. The actual total path length is the sum of the distances between all adjacent coordinate points. When the total path length is greater than the second threshold, it is determined to be a preliminary spiral trajectory. In one embodiment, for a trajectory segment that meets the first threshold condition, its actual total path length can be calculated by point-by-point accumulation. Specifically, the straight-line distances between any two adjacent coordinate points in the trajectory segment are added sequentially until the entire trajectory segment is traversed, and the sum obtained is the total path length. If the total path length exceeds a preset second threshold, the trajectory segment is considered to be long enough to form a loop, and is therefore determined to be a preliminary loop trajectory.

[0022] For example, although the trajectory drawn by the user on the screen is generally inclined to an arc, it will only be considered a true preliminary spiral trajectory when the total length of the arc exceeds the set reference value.

[0023] Calculate the number of swings of the preliminary loop trajectory relative to the line connecting the starting point and the end point. When the number of times the trajectory crosses the line on both sides of the line exceeds the preset number, it is confirmed as a valid loop trajectory. In one embodiment, for a trajectory segment already determined to be a preliminary loop trajectory, further analysis can be performed to determine whether the trajectory oscillates back and forth on both sides of a reference straight line connecting the start and end points. Specifically, the positions of the trajectory points relative to the reference straight line are observed sequentially, and the distribution of the trajectory points on one side and the other side of the line is recorded. When it is found that the number of times the trajectory points cross back and forth on both sides exceeds a set threshold, it indicates that the trajectory has obvious back-and-forth oscillations on both sides of the reference straight line, and such a trajectory can be confirmed as a valid loop trajectory.

[0024] For example, if the mouse trajectory alternates between the left and right sides of the reference line multiple times when the user is drawing a trajectory, it means that the trajectory does indeed exhibit a spiraling characteristic.

[0025] It should be noted that, in order to avoid statistical errors caused by slight jitter, a certain offset range can be added when judging whether the trajectory crosses a straight line. Only when the trajectory significantly exceeds this range will it be counted as a crossing.

[0026] Extract the rotation center point, rotation radius, and rotation duration of the effective rotation trajectory, and encapsulate them with the coordinate sequence to form rotation trajectory data.

[0027] In one embodiment, for trajectory segments confirmed as valid loop trajectories, key feature information can be extracted, such as the location of the loop's center point, the approximate radius of the loop, and the duration of the loop. Specifically, the approximate central region around which the trajectory is envisioned is first calculated based on the overall distribution of the trajectory. Then, the average distance from the trajectory points to the central region is estimated as the loop radius. Simultaneously, the loop duration is determined by recording the start and end times of the trajectory. Finally, these features are packaged together with the original trajectory coordinate data to form complete loop trajectory data.

[0028] For example, when a user draws a circular trajectory on the screen, the system can record that the center of the circle is approximately in the middle of the screen, the radius is close to half the range of the user's mouse movement, and the duration is two seconds. This information, along with the trajectory coordinates, can be output as complete spiral trajectory data. Furthermore, the trajectory clustering module includes: The page is divided into a virtual grid, and the grid size is dynamically determined based on the minimum spacing between page elements; In one embodiment, the page is divided into a virtual grid, and the size of the grid is dynamically determined based on the minimum spacing between interactive elements on the page. That is, when the page elements are dense, the grid is refined to distinguish adjacent elements, and when the spacing between elements is large, a coarser grid is used to reduce the amount of computation.

[0029] For example, if the shortest distance between buttons or product cards on the page is small, the virtual grid will shrink accordingly to ensure that each grid contains only a small number of elements or a portion of an element.

[0030] Each spiral trajectory is mapped onto a virtual grid to record the grid sequence through which the trajectory passes, and the trajectory density value of each grid is calculated, where the density value is equal to the number of trajectory segments that pass through that grid. In one embodiment, each spiral trajectory is mapped onto a virtual grid and the grid sequence through which the trajectory passes is recorded. At the same time, the number of trajectory segments passing through each grid is counted to obtain the trajectory density value of that grid. Here, "passing through" is counted as one occurrence of the trajectory within the grid, and the density value only records the number of trajectory segments to reflect the intensity of attention given to the area.

[0031] For example, if the circling trajectories of multiple users cross the same grid at the same location on the page, the density of that grid will be higher, making it easier for subsequent clustering judgments.

[0032] Spatial position superposition is performed on the spiral trajectory after mesh mapping to obtain spatial overlap. In one embodiment, each spiral trajectory is mapped onto a virtual grid and the grid sequence through which the trajectory passes is recorded. At the same time, the number of trajectory segments passing through each grid is counted to obtain the trajectory density value of that grid. Here, "passing through" is counted as one occurrence of the trajectory within the grid, and the density value only records the number of trajectory segments to reflect the intensity of attention given to the area.

[0033] For example, if the circling trajectories of multiple users cross the same grid at the same location on the page, the density of that grid will be higher, making it easier for subsequent clustering judgments.

[0034] Temporal pattern superposition is performed on the spiral trajectory after grid mapping to obtain temporal similarity; In one embodiment, spatial position superposition is performed on the spiral trajectory after grid mapping to obtain spatial overlap. The method is to extract trajectory segments in each grid and compare the consistency of these segments in the grid's entry point, exit point, and overall direction. If the trajectory segments of different users are highly consistent in position and direction, these segments are considered to have high spatial overlap, thereby improving the spatial overlap index of the grid.

[0035] For example, if two users' trajectory segments within the same grid enter from the top left corner and exit from the bottom right corner, and their paths approximately overlap, then the spatial overlap between these two segments is high.

[0036] The product of spatial overlap and temporal similarity is used as the trajectory overlap. When the trajectory overlap exceeds the preset overlap threshold, the corresponding trajectory is marked as a cluster trajectory. In one embodiment, the spatial overlap of each grid is combined with its temporal similarity (conceptually taking the product of the two or other composite measures) to obtain the trajectory overlap, which reflects the strength of trajectory pairs that are both spatially overlapping and temporally synchronous at the same location; when the trajectory overlap is significantly higher than the surrounding level or exceeds a pre-set judgment standard, the corresponding trajectory is marked as belonging to the same cluster.

[0037] For example, if a group of trajectories not only overlap within the same grid but also appear at the same time after the page loads, their overlap will be high, thus they will be classified as clustered trajectories.

[0038] Perform density peak search on trajectories in the same cluster, starting from the grid with the highest trajectory density value and expanding outward to search adjacent density grids until the trajectory density value is less than half of the average trajectory density value, thus forming a connected trajectory cluster; In one embodiment, density peak search is performed on the trajectories already marked as belonging to the same cluster to form a connected trajectory cluster. The method is to start from the grid with the highest trajectory density in the cluster and expand to the surrounding adjacent grids layer by layer. Only when the trajectory density of the adjacent grid remains significantly higher than the surrounding environment or is comparable to the density of the starting point is it included in the cluster. When the density of the extended grid decreases significantly and is lower than the average level of the surrounding area, the expansion stops, thereby obtaining a connected trajectory cluster that gradually decays from the high-density region outward.

[0039] For example, if a central grid is repeatedly traversed by multiple trajectories, and several surrounding rings exhibit decreasing density distributions, these rings will be continuously contained until the density becomes sparse.

[0040] The geometric center of the trajectory cluster is calculated based on the spiral trajectory data as a cognitive hot zone.

[0041] In one embodiment, the geometric center of the obtained trajectory cluster is calculated and output as a cognitive hotspot. Specifically, the center positions of each spiral trajectory within the cluster are summarized and weighted according to the significance of each trajectory within the cluster (such as the intensity of attention reflected by the spiral duration or spiral range), and finally a geometric center point representing the overall attention position of the cluster is obtained. At the same time, the center, the boundary of the cluster, typical trajectories, etc. are output as cognitive hotspot information.

[0042] For example, if multiple trajectories within a cluster repeatedly circle around a point in the middle of the page for a relatively long period of time, the calculated geometric center will be located in that middle position and identified as a cognitive hotspot.

[0043] See Figure 2 The trajectory clustering module overlays and analyzes the circling trajectories of multiple users within a preset time period according to their page positions. For example... Figure 2 As shown, the system recorded six trajectory curves from different users on a 20×15 virtual grid, represented by solid lines in red, blue, green, orange, purple, and cyan, respectively. Through spatial location overlay and temporal pattern overlay calculations, the system identified multiple trajectory density regions: low-density regions were transparently covered with light blue, medium-density regions with transparent yellow, and high-density regions with transparent red. When the trajectory overlap exceeded a preset overlap threshold, the system automatically formed trajectory clusters, such as... Figure 2The area enclosed by the black dashed circle is shown. Based on the spiral trajectory data, the system calculates the geometric center of the trajectory cluster ( Figure 2 The solid black dot marks the core location of the cognitive heatmap. The legend section details the color correspondence of each trajectory, density level classification, and technical parameter settings.

[0044] Furthermore, the spatial position superposition of the mesh-mapped spiral trajectory to obtain the spatial overlap is specifically as follows: Extract the portion of the spiral trajectory within the grid after grid mapping as a trajectory segment, and record the coordinates of the entry and exit points of the segment; In one embodiment, the spiral trajectory mapped to the same grid is divided at the grid boundary, and the continuous coordinate sequence from the entry point to the exit point of each segment is extracted as a trajectory segment. The entry point and exit point coordinates of the segment and the necessary intermediate positions are recorded to fully describe the segment's direction.

[0045] For example, if a mouse trajectory enters from the upper left of the grid and leaves from the lower right, the entry point of the segment is the upper left intersection point, and the exit point is the lower right intersection point. Multiple sampling points within the segment are saved together for subsequent comparison.

[0046] It should be noted that multiple entries and exits by the same user within the same grid should be recorded as independent segments to distinguish between repetitive behavior and single long stays.

[0047] Calculate the spatial deviation between different user trajectory segments, where the spatial deviation is specifically the average distance between corresponding points of two segments; In one embodiment, the spatial deviation between trajectory segments of different users is calculated in pairs. The method is to match the two segments according to their travel order (for example, to obtain the corresponding point sequence by resampling according to relative progress or equidistant distance), measure the distance between the corresponding points point by point, and take the average value as the spatial deviation between the two segments to reflect the overall deviation of the two paths within the grid.

[0048] For example, if two segments enter from the left side of the grid and cross with similar curves, and the distance between corresponding points in each set is generally small, then their spatial deviation is also small.

[0049] It should be noted that when the segment lengths differ significantly, a resampling method based on progress can be used to make the correspondence comparable, thereby avoiding deviations caused by different numbers of points.

[0050] When the spatial deviation is less than a preset proportion of the grid diagonal length, the two trajectory segments are determined to be spatially overlapping. In one embodiment, spatial deviation is combined with grid scale to determine spatial overlap. That is, when the spatial deviation of two segments is less than a certain proportion of the length of the grid diagonal, they are determined to overlap in space, indicating that the two trajectories point in the same direction and position within the grid and have the possibility of the same hot spot of interest.

[0051] For example, two segments are considered to be spatially overlapping when they almost overlap within the grid and the average distance between corresponding points is much smaller than the grid size.

[0052] Count the number of spatially overlapping trajectory segments within each grid, and divide this number by the total number of all possible trajectory pairs within that grid to obtain the spatial overlap degree of that grid.

[0053] In one embodiment, the number of trajectory segment pairs that are judged to be spatially overlapping within each grid is counted, and this number is divided by the total number of all possible trajectory segment pairs within the grid to obtain the spatial overlap of the grid. This index reflects the prevalence of trajectories overlapping each other in space within the grid.

[0054] For example, if a grid contains multiple segments from different users and most of these segments overlap, the spatial overlap of that grid will be close to a high value, indicating that it is a spatial hotspot. It should be noted that deduplication strategies (such as whether to include duplicate segments from the same user) should be considered during statistical analysis, and weighted statistics can be used as needed to highlight overlapping pairs from independent users.

[0055] Furthermore, the process of performing time pattern superposition on the mesh-mapped spiral trajectory to obtain temporal similarity is specifically as follows: Extract the timestamp of each spiral trajectory after grid mapping and convert the timestamp into a relative time relative to the page load time; In one embodiment, the number of trajectory segment pairs that are judged to be spatially overlapping within each grid is counted, and this number is divided by the total number of all possible trajectory segment pairs within the grid to obtain the spatial overlap of the grid. This index reflects the prevalence of trajectories overlapping each other in space within the grid.

[0056] For example, if a grid contains multiple segments from different users and most of the segments overlap, the spatial overlap of the grid will be close to a high value, indicating that the area is a spatial hotspot.

[0057] The relative time is divided into equal time slices, and the number of trajectories appearing in each time slice is counted to form a time distribution vector. In one embodiment, timestamp information is obtained from the spiral trajectory segments within each grid and uniformly converted into relative time with respect to page load or page exposure, in order to eliminate the difference in absolute time between different sessions and make the time information of all trajectories comparable on the same time scale.

[0058] For example, if a page loads at a time of zero, the time of subsequent traces is expressed in seconds from that zero point. For instance, if a segment occurs two seconds after loading, it is recorded as a relative time of two seconds.

[0059] It should be noted that using relative time can more accurately compare different stages of user behavior within the page lifecycle (e.g., the difference between when the page is first loaded and when it remains on the page).

[0060] In one embodiment, the temporal distribution vectors of different trajectories within the same grid are compared for similarity. Temporal similarity is determined by measuring the degree of consistency between the two vectors in their distribution patterns (i.e., whether their distribution peaks and troughs are synchronized). If the high-frequency occurrence segments of the two trajectories are consistent in relative time, they are considered to have high temporal similarity.

[0061] For example, if multiple trajectories appear within a short period after the page loads, then the temporal distribution vectors of these trajectories are highly consistent, and their temporal similarity is relatively large.

[0062] The temporal similarity of the grid is obtained by averaging the cosine similarities of all trajectory pairs.

[0063] In one embodiment, the average temporal similarity of all trajectory pairs within the same grid is taken as the overall temporal similarity of the grid, representing the degree of consistency of the trajectories at that location in the time dimension; this temporal similarity can be used together with spatial overlap to measure the spatiotemporal aggregation between trajectories.

[0064] For example, if most trajectory pairs within a grid exhibit synchronous occurrence in time, the temporal similarity of that grid will tend to be high.

[0065] It should be noted that when the number of trajectories within a grid is small, the reliability of the average value will decrease, and it should be evaluated in conjunction with the sample size or confidence index.

[0066] Furthermore, the calculation of the geometric center of the trajectory cluster based on the spiral trajectory data as a cognitive hotspot includes: Extract the center point of rotation, radius of rotation, and duration of rotation from the rotation trajectory data in the trajectory cluster, and calculate the cognitive intensity value for each trajectory, where the cognitive intensity value is equal to the product of the duration of rotation and the radius of rotation; In one embodiment, key information for each loop trajectory is extracted from the trajectory cluster, including the center position of the loop, the approximate radius of the loop, and the duration of the loop, and the cognitive intensity of each trajectory is determined accordingly. Specifically, the "duration" and "loop range" can be combined as an indicator to measure the cognitive importance of the trajectory—that is, trajectories with longer durations and larger loop ranges are considered to have higher cognitive intensity.

[0067] For example, if a trajectory stays in the same position and moves around for a long time and covers a large area, the cognitive intensity of that trajectory will be significantly higher than that of a short and small-scale movement.

[0068] Using cognitive intensity values ​​as weights, a weighted average is taken from all the centroids to obtain the initial geometric center. In one embodiment, the positions of all spiral centers within the cluster are weighted and averaged using the aforementioned cognitive intensity as a weight to obtain the initial geometric center. That is, each spiral center contributes a different weight to the overall center position according to its cognitive intensity, with trajectories of higher intensity having a greater impact on the initial geometric center, thus making the final center more reflective of the most relevant region within the cluster.

[0069] For example, when most trajectories within a cluster are clustered at the top of the page, but one of them has a significantly longer duration and a larger range, the initial center obtained by the weighted average will be closer to the location surrounded by that trajectory.

[0070] Calculate the distance from the initial geometric center to each spiral center point. When the distance exceeds a preset number and is greater than twice the corresponding spiral radius, it is determined to be an outlier center. Perform center splitting to separate the spiral trajectories that are farthest from the initial geometric center by a preset proportion. Calculate the weighted geometric centers of the main cluster and the separated clusters respectively to obtain the cognitive hot zone of the dual centers.

[0071] In one embodiment, the distances between each spiral center within a cluster and the initial geometric center are evaluated based on the initial geometric center to determine whether outlier centers exist and to perform center splitting accordingly. Specifically, the distance from each spiral center to the initial center is first calculated and compared with the spiral's own spiral range. When a certain number of spiral centers are found to be significantly far from the initial center and their discrete distances are much greater than their own spiral ranges, these are identified as outlier centers and separated from the original cluster to form one or more separate clusters. Subsequently, the weighted geometric centers of the main cluster and the separate clusters are recalculated to obtain a bi-center (or multi-center) cognitive heatmap representation.

[0072] For example, if most tracks repeatedly circle around a point on the left side of the page, but a small number of tracks are concentrated in the lower right corner and are much farther from the center on the left than their respective circling ranges, then the tracks in the lower right corner can be separated to form a second hot zone, and the center positions of the two hot zones can be given respectively.

[0073] It should be noted that the determination of central split should be based on the overall situation of cluster dispersion (e.g., the proportion of discrete points and their relative size with their own rotation range), and the same confidence level assessment can be applied to the split clusters after the split to determine whether to ultimately retain the sub-clusters.

[0074] Furthermore, the cognitive optimization module includes: Receive the cognitive hotspot and generate a list of user IDs for that hotspot, and count the number of unique users and the number of times a user visits repeatedly; In one embodiment, the system receives cognitive hotspot information output from the trajectory clustering module, generates a list of user IDs for the hotspot based on trajectory data within the hotspot, and further counts the number of independent users in the list and the number of repeated visits by these users.

[0075] For example, if multiple visits from the same user within a hotspot are identified as several tracks, the system will group these entries together as belonging to the same user and record the number of times they are repeated, thereby distinguishing between new users and returning users.

[0076] Calculate the user dispersion index. When the user dispersion is greater than the preset dispersion threshold and the number of independent users exceeds the preset number of users, the cognitive hot zone is determined to be a group cognitive barrier point. In one embodiment, the system calculates a user dispersion index based on the distribution of users within a hot zone. This index reflects whether users' attention is concentrated in a few locations or dispersed across multiple locations within the hot zone. When a hot zone has both a large number of independent users and exhibits high dispersion, the system will identify the hot zone as a group cognitive barrier point.

[0077] For example, if users within a hot zone are not all concentrated in the same small area, but rather repeatedly circle around multiple page elements, and these behaviors come from many different users, it indicates that there may be collective cognitive confusion at that point, and it should be identified as an obstacle point.

[0078] It should be noted that dispersion judgment should be considered in conjunction with the number of independent users—dispersion conclusions are unreliable when the sample size is too small, so group problems should be confirmed when the sample size is sufficient.

[0079] By using coordinate matching, all interactive elements covered by the collective cognitive impairment points are determined, and the two elements closest to the center of the hot zone are extracted as the core element pair. In one embodiment, for a selected pair of core elements, the system calculates their multi-dimensional similarity, which mainly includes textual similarity (comparing the degree of semantic or keyword overlap between the element title and description), visual similarity (comparing appearance features such as size, color scheme, positional relationship, icon and visual weight), and functional similarity (comparing post-click behavior, jump purpose or interaction response type) to comprehensively evaluate the distinguishability of the two elements in the user's perception.

[0080] For example, if two elements have similar wording in their titles, similar button colors and sizes, and similar pop-up messages when clicked, their three-dimensional similarity will be high, indicating that users may have difficulty distinguishing between the two.

[0081] Calculate the multi-dimensional similarity of core element pairs, including textual similarity, visual similarity, and functional similarity; When the multidimensional similarity exceeds the preset similarity threshold, the difference keywords are extracted to generate optimization instructions.

[0082] In one embodiment, when multi-dimensional similarity indicates that the core elements are cognitively highly similar and may cause confusion, the system will further extract the difference keywords between the two elements and generate standardized optimization instructions. The optimization instructions include the target element identifier, representative difference keywords, and suggested display or interaction adjustment schemes (such as enhancing visual differentiation, supplementing comparison information, or strengthening functional labels), so that the conflict handling module can implement A / B type optimization according to the instructions and monitor the effect.

[0083] For example, if two product cards have similar titles but different specifications, the system can extract "specifications / sizes" as the key difference and suggest highlighting the specification comparison or adding function icons in the display.

[0084] Most importantly, the multi-dimensional similarity calculation is specifically as follows: The core element pairs are calculated with multi-dimensional similarity, including text similarity, visual similarity, and functional similarity. Text similarity is obtained by calculating the proportion of repeated characters in the element title and description text. Visual similarity is obtained by comparing the size, color, and positional relationship of the elements. Functional similarity is obtained by analyzing the click response type of the elements.

[0085] See Figure 4 The cognitive optimization module receives cognitive hotspot information and performs obstacle point analysis. For example... Figure 4 As shown, the system identified two main cognitive hotspots on the simulated e-commerce page: Hotspot 1 covers the product comparison area, displayed as a red semi-transparent area, with data indicating 23 unique users, 156 repeated visits, a dispersion of 0.78, and a high barrier level; Hotspot 2 covers the search area, displayed as a yellow semi-transparent area, with 45 unique users, 89 repeated visits, a dispersion of 0.52, and a medium barrier level. The system uses coordinate matching to determine the interactive elements covered by the cognitive hotspots, marking them with blue dashed borders. When the user dispersion exceeds a preset dispersion threshold (0.6) and the number of unique users exceeds a preset number of users (20), the system determines that the cognitive hotspot is a group cognitive barrier point and marks it with a red triangle warning icon.

[0086] Most importantly, the step of extracting difference keywords and generating optimization instructions when the multidimensional similarity exceeds a preset similarity threshold is specifically as follows: Obtain the DOM node ID of the core element pair as the target element identifier; In one embodiment, the system first matches the coordinate mapping with the page rendering structure to identify all interactive elements within the coverage hot zone, and reads the DOM node IDs of these elements as unique identifiers of the target elements for subsequent operations.

[0087] For example, when a hotspot covers both a product image and a purchase button, the system records the corresponding DOM node ID as the target identifier.

[0088] By comparing the attributes of the core element pairs, we obtain the difference attributes and categorize them into three types: numerical, descriptive, and identifier. In one embodiment, the system compares the attributes of the core element pairs item by item to find differences, and classifies the differences into three categories according to their nature: numerical (e.g., quantifiable information such as price, quantity, specifications, etc.), descriptive (e.g., semantic text such as titles, explanatory text, or functional descriptions), and identifier (e.g., colors, icons, styles, or visual identifiers).

[0089] For example, if two elements have different prices, they are numerical; if their descriptions are different, they are descriptive; and if their button colors or icons are similar, they are identifiers.

[0090] Perform dynamic validation for each difference attribute, add a temporary marker at the attribute location, and measure the change in the user's circumduction trajectory before and after the marker is added; In one embodiment, dynamic validation is performed on a per-item basis for each difference attribute—a non-intrusive temporary marker or enhancement is added briefly at the attribute location (e.g., highlighting price ranges, adding contrast labels, or temporary bolding / bordering), and the change in the cyclone trajectory index of the target area is compared before and after the marker is added to assess the actual impact of the attribute.

[0091] For example, you can temporarily add a "Price Range Comparison" tab to the price and then observe whether the number and duration of the swirling trajectories around that element decrease.

[0092] Based on the change in the user's circling trajectory, the attribute that causes the largest reduction in the circling trajectory is selected as the core difference, and difference keywords are extracted. In one embodiment, the system compares the contribution of each difference attribute to the reduction of the spiral trajectory based on the dynamic verification results of each difference attribute, selects the difference attribute that leads to the greatest improvement of the spiral trajectory as the core difference, and extracts keywords that can clearly express the difference points from the attribute as difference keywords for subsequent instruction generation.

[0093] For example, if the fluctuation significantly decreases after a temporary supplement to "Specifications Display", then "Specifications Comparison" is extracted as a difference keyword.

[0094] The display strategy is determined based on the type of difference: numerical differences are compared with ranges, descriptive differences are added with function icons, and symbolic differences are enhanced with visual distinctions. In one embodiment, a specific display strategy is determined based on the type of difference to guide the optimization implementation: for numerical differences, range or numerical comparison is preferred to highlight the difference; for descriptive differences, function icons or supplementary short comparative text are preferred to clarify the function or purpose; for identification differences, visual differentiation means (such as enhanced contrast, borders, size or prominent icons) are preferred to improve recognizability.

[0095] For example, price differences can be displayed as "from X–Y", functional differences can be added with icons and brief descriptions, and visual similarities can be distinguished by color contrast and borders.

[0096] Encapsulate target element identifiers, differentiating keywords, and display strategies into optimization instructions.

[0097] In one embodiment, the system combines the target element identifier, the identified differential keywords, and the recommended display strategy to form a standardized optimization instruction, which is then executed iteratively by the conflict handling module or the front end. The optimization instruction may also include experimental suggestions (such as traffic diversion display strategies, which loop indicators to monitor, evaluation period, and rollback conditions) for closed-loop verification and solidification.

[0098] For example, the final instruction would say, "For elements with DOM value X, highlight the keyword 'Specifications Comparison' and add a function icon, while comparing the number of rotations over two weeks, and reverting if the change is not significant."

[0099] It should be noted that optimization instructions should be issued in an executable and easily rollbackable form, and their actual effects should be verified in a small-scale experiment before deployment in the production environment.

[0100] Furthermore, the conflict resolution module includes: Receive optimization instructions and parse target element identifiers and difference keywords; In one embodiment, the conflict handling module receives an optimization instruction from the cognitive optimization module and parses out the target element identifier and difference keywords within the instruction. Then, it locates the corresponding element instance in the current page context for subsequent operations.

[0101] For example, if the target identifier in the instruction is the DOM node ID of a purchase button and the difference keyword is "specification comparison", the system will locate the button element on the page and use that element as the target of the optimization operation.

[0102] The time distribution of the circular trajectory relative to the page loading time is statistically analyzed, and the type of cognitive conflict is determined based on the time period in which the trajectory clusters appear, which is divided into immediate cognitive conflict and delayed cognitive conflict. In one embodiment, the system statistically analyzes the time distribution of the swirling trajectory within the target area relative to the page loading time. By uniformly mapping the trajectory occurrence time to the relative time axis of the page lifecycle and observing the time periods in which they occur densely, the type of cognitive conflict is determined.

[0103] For example, if most of the swirling trajectories appear within a short period after the page loads, it can be identified as an immediate cognitive conflict; if the trajectories appear repeatedly between elements after the user has browsed for a period of time, it can be identified as a delayed cognitive conflict.

[0104] Visual differentiation enhancements are applied to address immediate cognitive conflicts, including increasing color contrast between elements, increasing spacing between elements, and adding distinctive borders. In one embodiment, for cases where an immediate cognitive conflict is identified, the system prioritizes the implementation of a visual difference enhancement strategy. This strategy improves the recognizability between elements through a series of non-destructive display adjustments, such as enhancing color contrast between elements, appropriately increasing element spacing or margins, adding significant distinguishing borders or outlines to key elements, and adjusting text bolding or font size to highlight differences.

[0105] For example, if two buttons are similar in color and size and cause confusion, one of the buttons can be made to have a higher contrast color and a more prominent border to make them easier to distinguish.

[0106] To address delayed cognitive conflict, an information supplementation strategy is implemented, dynamically displaying comparative information when the mouse is detected moving back and forth between elements. In one embodiment, for cases deemed as delayed cognitive conflict, the system employs an information supplementation strategy. When the system detects the user's mouse moving back and forth between two or more elements, it dynamically displays comparative information or supplementary explanations to help the user quickly identify differences. This can be achieved by temporarily popping up a comparison panel, displaying parallel key information prompts between elements, or hovering short text / icons above the elements to emphasize the differences.

[0107] For example, when a user moves the mouse back and forth between product specifications and purchase options, a small specification comparison card can pop up between the two to visually show the differences.

[0108] After optimization, monitor the new circling trajectory of the target area and calculate the trajectory change rate before and after optimization; In one embodiment, after implementing optimization measures, the system will continuously monitor the new swirling trajectories in the target area and compare them with the trajectory indicators before optimization to calculate the trajectory change rate before and after optimization as a key indicator to measure the effect; the change rate can be expressed based on the relative change of indicators such as the number of swirling trajectories, average duration or density.

[0109] For example, if the average number of spins per session for the target area was four before optimization and it is reduced to one after optimization, then the number of spins is reduced by 75 percent, and this percentage is the rate of change.

[0110] When the trajectory change rate is higher than the preset improvement threshold, the optimization strategy is solidified; otherwise, a rollback is executed and alternative strategies are tried. In one embodiment, the system makes a processing decision on the optimization strategy based on the calculated trajectory change rate: if the change rate exceeds the predetermined improvement standard, the optimization strategy is solidified as a long-term display (e.g., the style change is written into the production style sheet and the deployment is expanded); otherwise, a rollback is executed and a pre-prepared alternative strategy is tried or the next round of dynamic verification is entered.

[0111] For example, if increased visual difference significantly reduces the swirling trajectory and user conversion is not negatively affected, the system will merge the change into the normal style; if there is no improvement, the change will be revoked and another information supplementation scheme will be implemented for retesting. The trajectory change rate and optimization parameters are fed back to the cognitive analysis module to adjust the obstacle judgment threshold, forming a closed-loop optimization.

[0112] In one embodiment, the system feeds back key indicators such as trajectory change rate, sample size, optimization parameters and confidence level to the cognitive analysis module to adjust the threshold and rules for cognitive impairment determination and improve the hot zone identification and optimization suggestions for the next round, thereby forming a closed-loop optimization.

[0113] For example, if multiple optimizations show that a certain type of visual enhancement is generally effective, the analysis module can reduce its sensitivity to this type of problem or directly prioritize recommending the corresponding strategy in subsequent hotspot determination.

[0114] See Figure 3 The conflict resolution module implements optimization strategies and verifies their effectiveness. For example... Figure 3 As shown on the left, before optimization, the original interface used the same blue color for both buttons, resulting in a noticeable circling motion by the user, with 4.2 circling times per session and a duration of 8.5 seconds. After detecting this immediate cognitive conflict pattern, the system implemented a visual difference enhancement strategy. (As shown...) Figure 3 As shown on the right under "Optimized," the main button remains blue with a thicker border for emphasis, while the secondary buttons are changed to orange to enhance differentiation. After the optimization, the user trajectory becomes a clear green straight path, the number of loops is reduced to 1.1 times per session, and the duration is reduced to 2.3 seconds. The system calculated the trajectory change rate to be -73%, exceeding the preset improvement threshold, therefore this optimization strategy is solidified.

[0115] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0116] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. An internet e-commerce platform system, characterized in that, Includes the following modules: The trajectory acquisition module is used to periodically collect the user's mouse coordinates. When it detects that the distance between the start and end points of the mouse trajectory within a preset range is less than a first threshold while the total path length is greater than a second threshold, it is determined to be a spiral trajectory and the spiral trajectory data is output. The trajectory clustering module is used to superimpose the circumference trajectories of multiple users within a preset time period according to the page position. When the trajectory overlap exceeds the preset overlap threshold, a trajectory cluster is formed. The geometric center of the trajectory cluster is calculated based on the circumference trajectory data as the cognitive hot zone. The trajectory clustering module includes: The page is divided into a virtual grid, and the grid size is dynamically determined based on the minimum spacing between page elements; Each spiral trajectory is mapped onto a virtual grid to record the grid sequence through which the trajectory passes, and the trajectory density value of each grid is calculated, where the density value is equal to the number of trajectory segments that pass through that grid. Spatial position superposition is performed on the spiral trajectory after mesh mapping to obtain spatial overlap. Temporal pattern superposition is performed on the spiral trajectory after grid mapping to obtain temporal similarity; The product of spatial overlap and temporal similarity is used as the trajectory overlap. When the trajectory overlap exceeds the preset overlap threshold, the corresponding trajectory is marked as a cluster trajectory. Perform density peak search on trajectories in the same cluster, starting from the grid with the highest trajectory density value and expanding outward to search adjacent density grids until the trajectory density value is less than half of the average trajectory density value, thus forming a connected trajectory cluster; The cognitive optimization module is used to determine the cognitive barrier points of the group based on the number of users from the cognitive hot zone; calculate the similarity of page element pairs within the cognitive barrier points; and extract the difference keywords to generate optimization instructions when the similarity exceeds the preset similarity threshold. The conflict handling module receives optimization instructions, executes optimization strategies based on cognitive conflict types according to the time distribution characteristics of the spiral trajectory, and feeds back the trajectory change rate before and after optimization to the cognitive analysis module to form a closed-loop optimization.

2. The internet e-commerce management platform system according to claim 1, characterized in that, The trajectory acquisition module includes: The user's mouse coordinates are coarsely sampled at the first sampling frequency, and the displacement vector between consecutive coordinate points is recorded. When the sum of the directional angles of three consecutive displacement vectors exceeds 180 degrees, the fine sampling mode is triggered, and the sampling frequency is increased to the second sampling frequency, which is greater than the first sampling frequency. In the fine sampling mode, the collected coordinate sequence is divided into a sliding window of length N, the start and end points of the trajectory within each window are determined, and the straight-line distance between the start and end points is calculated. When the straight-line distance between the start and end points is less than the first threshold, the path length verification is initiated, and the trajectory is determined to be a loop trajectory, and the loop trajectory data is output.

3. The internet e-commerce management platform system according to claim 2, characterized in that, When the straight-line distance between the start and end points is less than the first threshold, the path length verification is initiated, and the trajectory is determined to be a loop trajectory. The loop trajectory data is output as follows: For trajectory segments that meet the first threshold condition, calculate their actual total path length. The actual total path length is the sum of the distances between all adjacent coordinate points. When the total path length is greater than the second threshold, it is determined to be a preliminary spiral trajectory. Calculate the number of swings of the preliminary loop trajectory relative to the line connecting the starting point and the end point. When the number of times the trajectory crosses the line on both sides of the line exceeds the preset number, it is confirmed as a valid loop trajectory. Extract the rotation center point, rotation radius, and rotation duration of the effective rotation trajectory, and encapsulate them with the coordinate sequence to form rotation trajectory data.

4. The internet e-commerce management platform system according to claim 3, characterized in that, The spatial position superposition of the mesh-mapped spiral trajectory to obtain the spatial overlap is specifically as follows: Extract the portion of the spiral trajectory within the grid after grid mapping as a trajectory segment, and record the coordinates of the entry and exit points of the segment; Calculate the spatial deviation between different user trajectory segments, where the spatial deviation is specifically the average distance between corresponding points of two segments; When the spatial deviation is less than a preset proportion of the grid diagonal length, the two trajectory segments are determined to be spatially overlapping. Count the number of spatially overlapping trajectory segments within each grid, and divide this number by the total number of all possible trajectory pairs within that grid to obtain the spatial overlap degree of that grid.

5. The internet e-commerce management platform system according to claim 4, characterized in that, The process of performing time pattern superposition on the mesh-mapped spiral trajectory to obtain temporal similarity is as follows: Extract the timestamp of each spiral trajectory after grid mapping and convert the timestamp into a relative time relative to the page load time; The relative time is divided into equal time slices, and the number of trajectories appearing in each time slice is counted to form a time distribution vector. For different trajectories within the same grid, calculate the cosine similarity of their time distribution vectors; The temporal similarity of the grid is obtained by averaging the cosine similarities of all trajectory pairs.

6. The internet e-commerce management platform system according to claim 5, characterized in that, The geometric center of the trajectory cluster calculated based on the spiral trajectory data, as the cognitive hot zone, includes: Extract the center point of rotation, radius of rotation, and duration of rotation from the rotation trajectory data in the trajectory cluster, and calculate the cognitive intensity value for each trajectory, where the cognitive intensity value is equal to the product of the duration of rotation and the radius of rotation; Using cognitive intensity values ​​as weights, a weighted average is taken from all the centroids to obtain the initial geometric center. Calculate the distance from the initial geometric center to each spiral center point. When the distance exceeds a preset number and is greater than twice the corresponding spiral radius, it is determined to be an outlier center. Perform center splitting to separate the spiral trajectories that are farthest from the initial geometric center by a preset proportion. Calculate the weighted geometric centers of the main cluster and the separated clusters respectively to obtain the cognitive hot zone of the dual centers.

7. The internet e-commerce management platform system according to claim 6, characterized in that, The cognitive optimization module includes: Receive the cognitive hotspot and generate a list of user IDs for that hotspot, and count the number of unique users and the number of times a user visits repeatedly; Calculate the user dispersion index. When the user dispersion is greater than the preset dispersion threshold and the number of independent users exceeds the preset number of users, the cognitive hot zone is determined to be a group cognitive barrier point. By using coordinate matching, all interactive elements covered by the collective cognitive impairment points are determined, and the two elements closest to the center of the hot zone are extracted as the core element pair. Calculate the multi-dimensional similarity of core element pairs, including textual similarity, visual similarity, and functional similarity; When the multidimensional similarity exceeds the preset similarity threshold, the difference keywords are extracted to generate optimization instructions.

8. The internet e-commerce management platform system according to claim 7, characterized in that, The specific steps for extracting difference keywords and generating optimization instructions when the multidimensional similarity exceeds a preset similarity threshold are as follows: Obtain the DOM node ID of the core element pair as the target element identifier; By comparing the attributes of the core element pairs, we obtain the difference attributes and categorize them into three types: numerical, descriptive, and identifier. Perform dynamic validation for each difference attribute, add a temporary marker at the attribute location, and measure the change in the user's circumduction trajectory before and after the marker is added; Based on the change in the user's circling trajectory, the attribute that causes the largest reduction in the circling trajectory is selected as the core difference, and difference keywords are extracted. Determine the display strategy based on the type of difference: add range comparison for numerical differences, add function icons for descriptive differences, and strengthen visual differentiation for identifiable differences. Encapsulate target element identifiers, differentiating keywords, and display strategies into optimization instructions.

9. The internet e-commerce management platform system according to claim 8, characterized in that, The conflict resolution module includes: Receive optimization instructions and parse target element identifiers and difference keywords; The time distribution of the circular trajectory relative to the page loading time is statistically analyzed, and the type of cognitive conflict is determined based on the time period in which the trajectory clusters appear, which is divided into immediate cognitive conflict and delayed cognitive conflict. Visual differentiation enhancements are applied to address immediate cognitive conflicts, including increasing color contrast between elements, increasing spacing between elements, and adding distinctive borders. To address delayed cognitive conflict, an information supplementation strategy is implemented, dynamically displaying comparative information when the mouse is detected moving back and forth between elements. After optimization, monitor the new circling trajectory of the target area and calculate the trajectory change rate before and after optimization; When the trajectory change rate is higher than the preset improvement threshold, the optimization strategy is solidified; otherwise, a rollback is executed and alternative strategies are tried. The trajectory change rate and optimization parameters are fed back to the cognitive analysis module to adjust the obstacle judgment threshold, forming a closed-loop optimization.

Images