A virtual technology-based commodity display system and method thereof

Abstract

The application discloses a commodity display system and method based on virtual technology, and belongs to the technical field of virtual commodity display, which comprises obtaining a user heat score calculated based on user interaction data and a content sensitivity score calculated based on content attribute analysis; based on the user heat score and the content sensitivity score, a coupling effect score of a virtual commodity display area is calculated through a preset coupling effect calculation model; the coupling effect score is introduced to realize accurate identification of composite risks, which is far superior to the single-dimensional evaluation of the prior art; based on the comparison between the coupling effect score and multiple intervention strategy thresholds, a differentiated and refined intervention strategy is realized, and the user experience is significantly optimized; by recording user feedback data and periodically updating model parameters, an adaptive optimization closed loop is constructed, and the long-term effectiveness and adaptability of the system are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of virtual commodity display, and particularly to a commodity display system based on virtual technology and a method thereof. BACKGROUND

[0002] With the rapid development of e-commerce, consumers increasingly tend to explore and purchase commodities in an online virtual environment; in order to improve user experience and promote sales, virtual commodity display systems are widely used in 3D model display, virtual reality or augmented reality shopping, etc. These systems strive to attract users to participate through highly immersive visual presentation and rich user interaction.

[0003] However, in a highly interactive virtual display environment, the balance between content safety and user experience becomes particularly important and challenging. For example, when a specific area of a commodity that is highly focused on by users (i.e., with high heat) happens to contain potentially sensitive or illegal information, existing content review or screening mechanisms may adopt a rather rough screening strategy. Such a strategy, although it may meet the requirements of content safety, directly blocks the user's interaction behavior in the focus area, bringing a poor experience to the user. More seriously, if the user's participation heat is high, the experience hindrance caused by "screening" will be amplified by the user's emotions, thus producing a kind of "negative coupling effect". That is, the higher the user's participation and focus, the more intense the user experience loss caused by the conflict between the content in the area and the sensitive content. The existing technology faces the dilemma of being difficult to improve user participation while ensuring content safety and not damaging the overall user experience in response to the key failure mode of display interruption and user experience loss caused by the conflict between the user's high focus area and sensitive content.

[0004] The present application is dedicated to providing a technical solution that can accurately identify and dynamically manage the negative coupling effect between content safety and user experience in virtual commodity display, in order to minimize the damage to user experience while ensuring content compliance, and avoid the user experience from being unexpectedly reduced significantly due to the coincidence of focus points and conflict points.

[0005] The above information disclosed in the above BACKGROUND section is only intended to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The present application aims to provide a commodity display system based on virtual technology and a method thereof to solve the problems raised in the above BACKGROUND.

[0007] A virtual technology-based commodity display method: comprising obtaining a user heat score calculated based on user interaction data, and a content sensitivity score calculated based on content attribute analysis;

[0008] Based on the user heat score and the content sensitivity score, a coupling effect score of a virtual commodity display area is calculated through a preset coupling effect calculation model;

[0009] The coupling effect score is compared with a plurality of preset intervention strategy thresholds to determine a specific intervention strategy for the display area;

[0010] According to the specific intervention strategy, the display area is dynamically adjusted in the content presentation mode of the user interface.

[0011] Preferably, the calculation of the user heat score comprises:

[0012] Based on a preset event weight rule, the screen stay time, zoom operation amplitude, and view angle rotation trajectory contained in the user interaction data are weighted and quantized to obtain a plurality of weighted quantization values;

[0013] The plurality of weighted quantization values are summed to obtain an aggregated value;

[0014] The aggregated value is processed by a preset standardization function to generate the user heat score.

[0015] Preferably, the calculation of the content sensitivity score comprises:

[0016] Based on a preset content risk rule library, the quantifiable content features in the texture map, geometric details, and associated text description contained in the content attribute are calculated to obtain a plurality of risk scores;

[0017] The plurality of risk scores are comprehensively processed by a preset aggregation function to generate the content sensitivity score.

[0018] Preferably, the calculation of the coupling effect score specifically comprises:

[0019] The user heat score is multiplied by a first preset weight coefficient to obtain a heat independent influence value;

[0020] The content sensitivity score is multiplied by a second preset weight coefficient to obtain a sensitivity independent influence value;

[0021] The product of the user heat score and the content sensitivity score is multiplied by a third preset weight coefficient to obtain a first-order interaction influence value;

[0022] determining a second-order cross-influence value, if the user heat score and the content sensitivity score exceed preset user heat threshold and content sensitivity threshold respectively, multiplying the part of the user heat score exceeding its threshold with the part of the content sensitivity score exceeding its threshold, multiplying the result with a fourth preset weight coefficient to obtain the second-order cross-influence value, otherwise, the second-order cross-influence value is zero;

[0023] adding the heat independent influence value, the sensitivity independent influence value, the first-order interaction influence value and the second-order cross-influence value to generate the coupling effect score.

[0024] Preferably, the first, second, third and fourth preset weight coefficients, the user heat threshold and the content sensitivity threshold are obtained based on the retrospective analysis of historical user interaction data and content security events, and are calibrated by a machine learning optimization algorithm.

[0025] Preferably, the determination of the specific intervention strategy further comprises:

[0026] if the coupling effect score is lower than a first preset intervention strategy threshold, determining the specific intervention strategy as no intervention strategy;

[0027] if the coupling effect score is greater than or equal to the first preset intervention strategy threshold and less than a second preset intervention strategy threshold, determining the specific intervention strategy as a warning prompt strategy, wherein the warning prompt strategy is to superimpose a semi-transparent warning icon on the edge of the display area;

[0028] if the coupling effect score is greater than or equal to the second preset intervention strategy threshold and less than a third preset intervention strategy threshold, determining the specific intervention strategy as a slight blur strategy, wherein the slight blur strategy is to apply a low-intensity blur filter to the display area;

[0029] if the coupling effect score is greater than or equal to the third preset intervention strategy threshold, determining the specific intervention strategy as a complete shielding strategy, wherein the complete shielding strategy is to replace the display area with a preset general placeholder.

[0030] Preferably, the method further comprises:

[0031] recording user feedback data generated after the specific intervention strategy is executed;

[0032] based on the user feedback data, periodically updating the weight coefficients and thresholds used by the coupling effect calculation model, and the plurality of preset intervention strategy thresholds, to form an adaptive optimization closed loop.

[0033] Preferably, the user interaction data includes the user's dwell time on the screen, the number and amplitude of zoom operations, the rotation and translation trajectory of the viewing angle, and the click event signal for a specific area.

[0034] Preferably, the content attributes include the texture map, surface geometric details of the model itself, and the product title, detailed description and label associated therewith.

[0035] Preferably, a virtual technology-based product display system comprises:

[0036] A score acquisition module is configured to acquire a user popularity score calculated based on user interaction data and a content sensitivity score calculated based on content attribute analysis;

[0037] A coupling effect calculation module is configured to calculate a coupling effect score of a virtual product display area based on the user popularity score and the content sensitivity score through a preset coupling effect calculation model;

[0038] An intervention strategy determination module is configured to compare the coupling effect score with a plurality of preset intervention strategy thresholds to determine a specific intervention strategy for the display area;

[0039] A content presentation adjustment module is configured to dynamically adjust the content presentation mode of the display area in the user interface according to the specific intervention strategy.

[0040] The present application improves a virtual technology-based product display system and method thereof, which has the following improvements and advantages compared with the prior art:

[0041] 1. By introducing the coupling effect score, the accurate identification of the composite risk is realized, which is far superior to the single-dimensional evaluation of the prior art;

[0042] 2. Based on the comparison of the coupling effect score and the plurality of intervention strategy thresholds, the differentiated and refined intervention strategy is realized, which significantly optimizes the user experience;

[0043] 3. By recording user feedback data and periodically updating model parameters, an adaptive optimization closed loop is constructed, ensuring the long-term effectiveness and adaptability of the system. BRIEF DESCRIPTION OF DRAWINGS

[0044] The present application will be further explained in conjunction with the accompanying drawings and examples:

[0045] Figure 1 is a flowchart of a virtual technology-based product display system and method thereof. DETAILED DESCRIPTION

[0046] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with specific examples.

[0047] Embodiment 1

[0048] Please refer to Figure 1 The present application provides a virtual technology-based commodity display method, comprising: obtaining a user heat score calculated based on user interaction data, and a content sensitivity score calculated based on content attribute analysis;

[0049] Based on the user heat score and the content sensitivity score, a coupling effect score of a virtual commodity display area is calculated through a preset coupling effect calculation model;

[0050] The coupling effect score is compared with a plurality of preset intervention strategy thresholds to determine a specific intervention strategy for the display area;

[0051] According to the specific intervention strategy, the content presentation mode of the display area in the user interface is dynamically adjusted;

[0052] The virtual technology-based commodity display method provided in this embodiment is characterized in that a dynamic and quantitative decision framework is established to achieve an accurate balance between content security compliance and user immersive experience in a virtual shopping scene, such as 3D model interaction of an online automobile exhibition hall or a virtual clothing fitting application; the method discards the simple binary shielding logic in traditional content review, introduces a comprehensive coupling effect score, which can identify and quantify the compound risk generated when a region with high user attention overlaps with potential sensitive content, so as to execute differentiated and refined intervention strategies from no intervention, warning prompt to local blurring and even complete shielding according to the risk level; the fundamental purpose of this is to maximize the smoothness and integrity of user exploration while adhering to the bottom line of content security, avoid the reduction of user experience caused by unnecessary excessive intervention, and thus improve user satisfaction and the commercial competitiveness of the platform;

[0053] The prior art usually adopts an isolated and binary evaluation method when dealing with content security problems in virtual commodity display; for example, a content review system only judges whether the content is illegal, and a user behavior analysis system only evaluates the user interest, and the two are independent of each other; the fundamental defect of this method is that it cannot identify and quantify the compound risk generated when “high user interest” and “high content sensitivity” intersect in the same display area, which is much greater than the simple addition of the two;

[0054] The application solves this problem innovatively by constructing a coupling effect calculation model; the model not only considers the linear influence of the user heat score and the content sensitivity score independently, but also accurately calculates the coupling effect score by introducing a first-order product interaction term and a second-order cross-influence term; the practical significance of the score lies in that it is a comprehensive index that can quantify the risk of "negative experience cliff drop caused by the conflict between the user's high attention area and sensitive content"; for example, when the user heat and the content sensitivity both exceed the respective preset critical values, the second-order cross-influence term will be activated, causing the coupling effect score to rise sharply; this design can accurately identify the key conflict points that are most likely to trigger strong negative emotions of the user.

[0055] Embodiment 2

[0056] The calculation of the user heat score includes:

[0057] Based on the preset event weight rule, the screen stay time, the zoom operation amplitude, and the view rotation trajectory contained in the user interaction data are weighted and quantized to obtain a plurality of weighted quantization values;

[0058] The plurality of weighted quantization values are summed to obtain an aggregated value;

[0059] The aggregated value is processed by a preset standardization function to generate a user heat score;

[0060] The user interaction data includes the user's stay time on the screen, the number and amplitude of zoom operations, the rotation and translation trajectory of the view, and the click event signal for a specific area;

[0061] In this embodiment, the calculation of the user heat score aims to convert the degree of interest implied by the user in the virtual goods into a measurable numerical value; for example, in the user's interaction with a virtual watch model, the system not only records the user's behavior of clicking the crown, but also quantifies the zoom depth of repeatedly enlarging the watch face to view the tourbillon details and the behavior of long-time staying the view on the back of the watch; these original user interaction data are generated into a standardized heat score through a fine calculation process; the calculation process is defined by the following formula:

[0062]

[0063] This formula is derived from mature practices in the field of user behavior analysis, and its technical motivation lies in providing a key trigger premise for the "negative coupling effect" at the core of the application; only when the user's attention to a certain area is high enough, any intervention on the content of the area can trigger significant negative experience, therefore, the degree of user's interest must be accurately and reliably quantified.

[0064] In the formula,

[0065] representing the final user heat score of a region , whose value is mapped to a normalized interval, with higher value indicating deeper user attention or engagement on the region;

[0066] representing the set of all user interaction events happened on region within a specific time window;

[0067] representing a specific user interaction event in the set , such as a click, a zoom operation or a dwell;

[0068] representing the weight function assigned to a single interaction event ; the design of this function aims to reflect the difference in user interest implied by different behaviors; for example, this function can be designed as a piecewise function, where the weight of a behavior with dwell shorter than a preset minimum threshold is zero, while for longer dwell, a logarithmic function is used to calculate the weight to reflect the diminishing marginal utility of attention;

[0069] representing a standard data preprocessing function, which aims to map the raw aggregated value after weighted summation to a unified and comparable scale; for example, the min-max normalization method can be used, which is calculated as (raw aggregated value - historical minimum aggregated value) / (historical maximum aggregated value - historical minimum aggregated value), thus eliminating the impact of interaction level differences between different users or different goods;

[0070] the calculated user heat score is one of the core inputs for subsequent coupling effect calculation; the technical effect lies in that it provides an objective and dynamically updated quantitative basis for the system to judge which regions on the virtual goods are high-attention regions for users, so that the system can accurately identify those key risk points that are most likely to cause a sharp decline in user experience due to content conflicts; the specific form of the function and the weight coefficient, as well as the statistical parameters used by the function, are all key adjustable parameters of the system; the initial values of these parameters can be set based on the experience of domain experts, and then continuously optimized through online A / B testing, by deploying test groups with different parameter configurations and monitoring the performance of each group in key performance indicators such as user retention rate and task completion rate, to iteratively optimize in a data-driven manner.

[0071] Embodiment 3

[0072] The calculation of content sensitivity score includes:

[0073] Based on the preset content risk rule library, the texture map, geometric details and the quantifiable content features in the associated text description contained in the content attributes are calculated to obtain a plurality of risk scores;

[0074] The plurality of risk scores are comprehensively processed by a preset aggregation function to generate a content sensitivity score;

[0075] The content attributes include the texture map, surface geometric details of the model itself, and the product title, detailed description and label associated therewith;

[0076] In the embodiment, the calculation of the content sensitivity score aims to quantify the potential compliance risk inherent in the content of the specific region of the virtual product; this process is independent of user behavior and is a static or quasi-static analysis of the content attributes of the product; for example, for a virtual T-shirt, the system will scan whether the inappropriate pattern exists on the chest print (texture map) and analyze whether the product description text (associated text) contains prohibited words; the calculation process of the score can be represented by the following formula:

[0077] ;

[0078] The construction of the formula draws on the multi-dimensional risk quantification and aggregation technology commonly used in the field of content security risk control; the technical motivation is to provide another key dimension of quantitative input for the subsequent coupling effect analysis, i.e., the inherent risk level of the content; this enables the system to distinguish different degrees of risk and lays the foundation for realizing differentiated intervention;

[0079] represents the comprehensive content sensitivity score of the region , and the value is also standardized, and the higher the numerical value, the higher the compliance risk or sensitivity of the content of the region;

[0080] refers to a specific region on the virtual product being analyzed;

[0081] represents a specific quantifiable content feature detected in the region ; for example, the number of occurrences of a specific sensitive word, the confidence score of a rule violation element identified by an image recognition model, or the negative sentiment intensity of a text analyzed by a natural language processing model;

[0082] represents the score obtained after risk assessment of a single content feature , and the assessment is based on the output of the preset rule library or content recognition model;

[0083] is a data aggregation function responsible for aggregating the risk scores of all detected content features in a region to form a single sensitivity score representing the overall risk of the region; for example, the function can be implemented as a max function to focus on the most serious risk item, or as a weighted average function to reflect the importance difference of different types of risks;

[0084] the calculated content sensitivity score together with the user heat score are sent into the coupling effect management module; the technical effect lies in providing an objective and standardized intrinsic risk measurement of content, which is a prerequisite for precise intervention; the scoring standard and The aggregation strategy in the function is the core strategy configuration of the system; the setting and optimization of these parameters are set by content strategy experts according to industry regulations and platform policies to set benchmark rules; through backtracking analysis of a large number of historical cases or using machine learning technology, the scoring threshold and aggregation weight are automatically adjusted, and the optimization goal is to maximize the detection rate of real risk events while minimizing the false positive rate of normal content.

[0085] Embodiment 4

[0086] The calculation of the coupling effect score specifically includes:

[0087] The user heat score is multiplied by a first preset weight coefficient to obtain a heat independent influence value;

[0088] The content sensitivity score is multiplied by a second preset weight coefficient to obtain a sensitivity independent influence value;

[0089] The product of the user heat score and the content sensitivity score is multiplied by a third preset weight coefficient to obtain a first-order interaction influence value;

[0090] A second-order cross-influence value is determined, if the user heat score and the content sensitivity score exceed preset user heat critical values and content sensitivity critical values respectively, the part of the user heat score exceeding the critical value is multiplied by the part of the content sensitivity score exceeding the critical value, and then the result is multiplied by a fourth preset weight coefficient to obtain the second-order cross-influence value, otherwise, the second-order cross-influence value is zero;

[0091] The heat independent influence value, the sensitivity independent influence value, the first-order interaction influence value and the second-order cross-influence value are added to generate the coupling effect score;

[0092] The first, second, third and fourth preset weight coefficients, the user heat critical value and the content sensitivity critical value are obtained based on backtracking analysis of historical user interaction data and content safety events, and are calibrated through a machine learning optimization algorithm;

[0093] In the present embodiment, the calculation of the coupling effect score is the technical core of the present application. It non-linearly fuses the data of the two dimensions of user heat and content sensitivity through a multi-component mathematical model to reveal the amplification risk generated when the two are coupled. The model is precisely defined by the following formula:

[0094]

[0095] The construction of this coupling effect score model is a direct solution to the key technical problem of the present application, i.e., the significant and sudden degradation of user experience caused by the conflict between high user attention areas and sensitive content. The technical motivation is to create a mathematical tool that can accurately quantify this compound risk. It must go beyond simple linear superposition to capture the synergistic negative effect of disproportionate risk growth when both user heat and content sensitivity reach high levels, thereby providing a decision basis for the system to take appropriate intervention measures that match the risk level.

[0096] The formula consists of four parts, representing the risk contribution at different levels:

[0097] In the formula, represents the final coupling effect score of the area , which is the direct basis for the system to make intervention decisions;

[0098] and are the user heat score and content sensitivity score calculated as described above, respectively;

[0099] represents the independent linear effect of user heat;

[0100] represents the independent linear effect of content sensitivity;

[0101] represents the first-order product interaction effect between the two, reflecting that when both exist, they will have a stronger associated effect than when they exist alone;

[0102] is the key part of the model, representing the second-order cross effect. This term is only activated when and both exceed their respective preset threshold values and , thereby highlighting the most dangerous compound risk scenario of "high heat + high sensitivity";

[0103] are four weight coefficients used to adjust the relative importance of each risk component;

[0104] and are the critical values of user heat and content sensitivity, which are the thresholds triggering the second-order cross effect.

[0105] the calculated coupling effect score is a comprehensive risk indicator, which is directly compared with a series of preset intervention strategy thresholds to map to specific intervention actions; the technical effect is to achieve accurate identification and classification of risks, which can clearly distinguish various scenarios such as "high heat but no content risk", "content sensitive but no one pays attention", and "high heat and content sensitive", so that the system can use the strongest intervention means only in the most needed place, thereby minimizing the damage to user experience on the premise of ensuring safety; the weight coefficient and the critical value are the core adjustable parameters of the model; as described above, the calibration process is data-driven, for example, by defining an objective function to minimize the difference between the model-predicted risk and the true risk label obtained from user complaints or manual review, and then searching for the optimal solution in the parameter space using algorithms such as Bayesian optimization;

[0106] The prior art often adopts a one-size-fits-all blunt shielding strategy after identifying potential risks, such as directly replacing the relevant area with a gray placeholder; although this approach ensures content safety, it severely damages user experience, especially in cases where users are highly interested in the area, and such abrupt shielding can cause great frustration and interruption of information acquisition;

[0107] The present application achieves fine classification of intervention measures by comparing the calculated coupling effect score with a plurality of preset intervention strategy thresholds; the system can determine and execute specific intervention strategies including no intervention strategy, warning prompt strategy, slight blur strategy, and complete shielding strategy according to different numerical intervals of the coupling effect score; for example, for an area with a medium coupling effect score, the system may only perform "slight blur", which reminds of the risk, preserves the context information of the content, and avoids unnecessary experience interruption; this progressive and strictly matched intervention method with risk level, on the premise of ensuring content compliance, maximizes the reduction of interference to normal exploration behavior of users, thereby significantly improving overall user satisfaction and the attractiveness of the platform.

[0108] Embodiment 5

[0109] The determination of the specific intervention strategy further comprises:

[0110] If the coupling effect score is lower than the first preset intervention strategy threshold, the specific intervention strategy is determined as no intervention strategy;

[0111] If the coupling effect score is greater than or equal to the first preset intervention strategy threshold and less than the second preset intervention strategy threshold, then the specific intervention strategy is determined to be a warning prompt strategy, wherein the warning prompt strategy is to overlay a semi-transparent warning icon on the edge of the display area.

[0112] If the coupling effect score is greater than or equal to the second preset intervention strategy threshold and less than the third preset intervention strategy threshold, then the specific intervention strategy is determined to be a slight blur strategy, wherein the slight blur strategy is to apply a low-intensity blur filter to the display area.

[0113] If the coupling effect score is greater than or equal to the third preset intervention strategy threshold, then the specific intervention strategy is determined to be the complete shielding strategy, where the complete shielding strategy is to replace the display area with a preset universal placeholder.

[0114] The method also includes:

[0115] Record user feedback data generated after implementing specific intervention strategies;

[0116] Based on user feedback data, the weight coefficients and critical values ​​used in the coupling effect calculation model, as well as multiple preset intervention strategy thresholds, are periodically updated to form an adaptive optimization closed loop.

[0117] In this embodiment, the determination of specific intervention strategies and the adaptive optimization closed loop constitute the complete process of this invention from decision-making to execution to learning; the system scores the calculated coupling effect. Through a clear, hierarchical threshold system, it can make precise responses and learn from the results of those responses to continuously evolve.

[0118] Specifically, when the coupling effect is scored Once calculated, the system will compare it with the preset intervention strategy threshold. Comparison; for example, in a virtual art exhibition, a section of a painting. Calculated The value is 0.6; assuming the preset threshold is... ,because The system will accurately map this situation to the "slight blur" strategy; the content display module then receives the instruction and applies a low-intensity Gaussian blur filter to a specific area of ​​the painting in real time, making the details difficult to discern, but the overall outline is still visible; this processing method reduces the potential visual impact risk and avoids the abruptness and information loss caused by directly replacing the painting with gray squares.

[0119] Furthermore, as described above, this invention constructs an adaptive optimization closed loop; the system continuously records user feedback data after implementing the intervention strategy, including direct and indirect feedback; this structured data is used to periodically calibrate the entire decision-making system; if the data shows that a large number of users choose to leave immediately after slight ambiguity processing, this may indicate that the current... If the threshold is set too low, the policy configuration module will use this information to automatically fine-tune it using an algorithm. The value; this continuous learning and optimization process ensures that the technical solution of the present invention can maintain its effectiveness and adaptability in the long term, dynamically find the best balance point in the ever-changing user preferences and content risk environment, thus forming a truly intelligent content display management system that can improve itself.

[0120] Existing content moderation rules and intervention strategies are usually static and require regular manual adjustments, making them difficult to adapt to rapidly changing market environments, user preferences, and new risks.

[0121] This invention introduces a feedback mechanism to construct a self-evolving intelligent system. The system continuously records user feedback data generated after the execution of specific intervention strategies. Based on this user feedback data, it periodically updates the weight coefficients and critical values ​​used in the coupling effect calculation model, as well as multiple preset intervention strategy thresholds. If the data shows that a certain intervention strategy leads to an excessively high user bounce rate, the system can automatically learn and adjust the corresponding thresholds or intervention parameters. The establishment of this adaptive optimization closed loop enables the method of this invention to continuously approach the optimal balance between content security and user experience, ensuring that the technical solution can maintain its efficiency and accuracy in the face of constantly changing external environments. This dynamic adaptability is not possessed by existing static rule systems.

[0122] In summary, this invention fundamentally changes the way content security and user experience are managed in virtual product displays by constructing a complete technical solution that includes coupling effect scoring calculation, hierarchical intervention strategy determination, and adaptive optimization closed loop. It replaces crude blocking with precise quantification and intelligent decision-making, thereby providing users with a smoother, more coherent, and more satisfying exploration experience while ensuring platform security and compliance, and has practical value and commercial prospects.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A virtual technology-based merchandise display method, characterized by: The method comprises: obtaining a user heat score calculated based on user interaction data and a content sensitivity score calculated based on content attribute analysis; based on the user heat score and the content sensitivity score, calculating a coupling effect score of a virtual product display area through a preset coupling effect calculation model; comparing the coupling effect score with a plurality of preset intervention strategy thresholds to determine a specific intervention strategy for the display area; dynamically adjusting the content presentation mode of the display area in the user interface according to the specific intervention strategy; the calculation of the coupling effect score specifically comprises: multiplying the user heat score by a first preset weight coefficient to obtain a heat independent influence value; multiplying the content sensitivity score by a second preset weight coefficient to obtain a sensitivity independent influence value; multiplying the product of the user heat score and the content sensitivity score by a third preset weight coefficient to obtain a first-order interaction influence value; determining a second-order cross-influence value, if the user heat score and the content sensitivity score exceed preset user heat critical value and content sensitivity critical value respectively, multiplying the part of the user heat score exceeding the critical value by the part of the content sensitivity score exceeding the critical value, and then multiplying the result by a fourth preset weight coefficient to obtain the second-order cross-influence value, otherwise, the second-order cross-influence value is zero; adding the heat independent influence value, the sensitivity independent influence value, the first-order interaction influence value and the second-order cross-influence value to generate the coupling effect score; the first, second, third and fourth preset weight coefficients, the user heat critical value and the content sensitivity critical value are obtained based on the retrospective analysis of historical user interaction data and content security events, and are calibrated through a machine learning optimization algorithm.

2. The virtual technology-based merchandise display method of claim 1, wherein, The calculation of the user heat score comprises: based on a preset event weight rule, weighting and quantifying the screen stay time, zoom operation amplitude and view rotation trajectory contained in the user interaction data to obtain a plurality of weighted quantization values; summing the plurality of weighted quantization values to obtain an aggregated value; processing the aggregated value through a preset standardization function to generate the user heat score.

3. The virtual technology-based merchandise display method of claim 1, wherein, The calculation of the content sensitivity score comprises: based on a preset content risk rule library, calculating a plurality of risk scores respectively from the quantifiable content features in the texture map, geometric details and associated text description contained in the content attribute; comprehensively processing the plurality of risk scores through a preset aggregation function to generate the content sensitivity score.

4. The virtual technology-based merchandise display method of claim 1, wherein, The determination of the specific intervention strategy further comprises: if the coupling effect score is lower than a first preset intervention strategy threshold, determining the specific intervention strategy as no intervention strategy; if the coupling effect score is greater than or equal to the first preset intervention strategy threshold and less than a second preset intervention strategy threshold, determining the specific intervention strategy as a warning prompt strategy, wherein the warning prompt strategy is to superimpose a semi-transparent warning icon on the edge of the display area. If the coupling effect score is greater than or equal to the second preset intervention strategy threshold and less than a third preset intervention strategy threshold, the specific intervention strategy is determined to be a slight blur strategy, wherein the slight blur strategy is to apply a low-intensity blur filter to the display area; If the coupling effect score is greater than or equal to the third preset intervention strategy threshold, the specific intervention strategy is determined to be a complete shielding strategy, wherein the complete shielding strategy is to replace the display area with a preset general placeholder.

5. The virtual technology based merchandise display method as claimed in claim 1, wherein, The method further comprises: Recording user feedback data generated after the specific intervention strategy is executed; Based on the user feedback data, periodically updating the weight coefficients and critical values used by the coupling effect calculation model, and the plurality of preset intervention strategy thresholds, to form an adaptive optimization closed loop.

6. The virtual technology based merchandise display method as claimed in claim 2, wherein, The user interaction data includes the user's stay time on the screen, the number and amplitude of zoom operations, the rotation and translation trajectories of the viewing angle, and the click event signals for specific areas.

7. The virtual technology based merchandise display method of claim 3, wherein, The content attributes include the model's own texture map, surface geometric details, and associated product title, detailed description, and label.

8. A virtual technology-based merchandise display system applying the virtual technology-based merchandise display method according to any one of claims 1 to 7, characterized by, Comprise: The score acquisition module is used for acquiring the user heat score calculated based on the user interaction data, and the content sensitivity score calculated based on the content attribute analysis; The coupling effect calculation module is used for calculating the coupling effect score of the virtual product display area based on the user heat score and the content sensitivity score through a preset coupling effect calculation model; The intervention strategy determination module is used for comparing the coupling effect score with a plurality of preset intervention strategy thresholds to determine the specific intervention strategy for the display area; The content presentation adjustment module is used for dynamically adjusting the content presentation mode of the display area in the user interface according to the specific intervention strategy.

Images