Customized furniture marketing and ordering transaction system fused with AR scene

Abstract

The invention belongs to the technical field of e-commerce, and discloses a customized furniture marketing and ordering transaction system fused with an AR scene. The method comprises the following steps of: accurately constructing a microscopic interest attenuation curve by collecting an interaction track and visual staying data of a user in an AR environment, and realizing dynamic quantification of purchase intention; the transaction path fracture node is innovatively identified, the conversion resistance index is calculated, the seamless transaction trigger point map is automatically generated, and smooth conversion from experience to transaction is realized. According to the invention, the physical attributes of the furniture are mapped into digital right parameters, and a mixed transaction mode containing two channels of real object purchase and digital asset subscription is constructed, so that the furniture value is transferred and added among different users. Especially in a hotel scene, a digital asset bidding transaction channel between an original guest and a new guest is established, temporary use experience is converted into continuous commercial value, and industrial ecology of efficient utilization of resources and co-creation of multi-party value is realized.

Description

Technical Field

[0001] This invention relates to the field of e-commerce technology, and more specifically, to a customized furniture marketing and ordering system that integrates AR scenarios. Background Technology

[0002] Augmented reality (AR) technology, as a key driver of digital transformation, has seen widespread adoption in the furniture industry in recent years. Through AR, consumers can visually preview furniture placement in their actual spaces, assess size compatibility, and experience style harmony, significantly improving the accuracy and confidence of their purchasing decisions. Major e-commerce platforms and furniture manufacturers have launched AR display applications, making virtual furniture try-ons a standard part of the shopping process.

[0003] However, the current AR furniture marketing and transaction field suffers from a serious problem of experience-conversion disconnect and value locking dilemma. In practical application scenarios, users can often smoothly experience virtual furniture placement, size measurement, and style matching through AR applications. However, when a purchase intention is generated, the system fails to accurately capture this conversion opportunity, forcing users to exit the immersive AR environment and search, compare, and place orders again in traditional e-commerce interfaces. This break in the conversion path from "seeing-experiencing" to "decision-purchasing" results in potential conversion loss. Taking the hotel scenario as an example, after guests appreciate and interact with the furniture in the room through AR applications, even if they develop a strong purchase intention, they face a complex and cumbersome inquiry process—contacting the front desk, obtaining product information, and finding external purchasing channels, among other conversion obstacles. More importantly, existing technologies have failed to build accurate interest models based on users' micro-interactions in AR scenarios, and cannot identify the best transaction trigger time in real time. Marketing information is often pushed out only after the peak of user interest has passed, missing the conversion window. At the same time, the traditional furniture transaction model has always been a single paradigm of physical ownership transfer, ignoring the diverse needs of modern consumers for usage rights, experience rights, and asset liquidity. In hotel settings, guests lack flexible ways to acquire value from temporarily used furniture they like, failing to transform their brief experience into sustainable value. The furniture's value is also locked in a single physical form due to a lack of digital asset attributes, failing to achieve value transfer and appreciation between different users. This lack of a value transfer mechanism not only restricts the commercial potential of furniture products but also results in a double waste of resources—idleness and a fragmented user experience. When a business traveler who appreciates the designer furniture in a hotel suite checks out, the emotional connection and user experience they built with that furniture immediately vanishes, unable to be continued or transferred through a reasonable mechanism. This value break severely restricts business model innovation and customer relationship maintenance in the furniture industry.

[0004] In view of this, the present invention proposes a customized furniture marketing and order transaction system that integrates AR scenarios to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution: a customized furniture marketing and order transaction system integrating AR scenes, comprising: The data acquisition module is used to acquire user interaction trajectory data and visual dwell data of furniture objects in AR scenes; The intention assessment module is used to construct a micro-interest decay curve for furniture objects based on the interaction trajectory data and the visual dwell data, and generate a purchase intention intensity matrix based on the inflection point distribution of the micro-interest decay curve. The path analysis module is used to collect characteristic data of user operation interruption events in AR scenes, identify transaction path break nodes, and calculate the conversion resistance index of each transaction path break node. The graph generation module is used to generate a seamless transaction trigger point map based on the conversion resistance index and the purchase intention strength matrix. The element rendering module is used to dynamically render transaction guidance elements at the positions marked on the seamless transaction trigger point bitmap. The visual salience of the transaction guidance elements is adaptively adjusted according to the real-time value of the purchase intention intensity matrix. The fluctuation monitoring module is used to monitor the user's response delay time and interaction completion rate to the transaction guidance elements, and to identify the fluctuation characteristics of the user's real-time transaction intention. The mapping model construction module is used to construct a digital asset mapping model for furniture objects based on the fluctuation characteristics of the real-time transaction intentions, and to transform the physical attributes of furniture into digital rights parameters including the duration of the right to use, the upper limit of the number of transfers, and the appreciation coefficient. The transaction option generation module is used to generate hybrid transaction options for hotel guests based on the digital asset mapping model. The hybrid transaction options include a physical purchase channel and a digital asset subscription channel. The digital asset binding module is used to bind the digital asset of the furniture object to the guest's identity identifier after the guest selects the digital asset subscription channel and completes the subscription. The premium calculation module is used to collect AR interaction data of subsequent guests on the same furniture object in real time, and calculate the premium coefficient of the digital asset based on the density change of the AR interaction data. The transaction channel construction module is used to push an asset transfer premium prompt to the original guest holding the digital asset when it is detected that the purchase intention of a new guest for the furniture object is higher than a preset threshold, and to construct a digital asset bidding transaction channel between the original guest and the new guest. The integrated output module is used to dynamically calculate the optimal transaction price for asset transfer based on the bidding sequence and time decay factor in the digital asset auction trading channel, complete the transaction, and achieve a seamless connection from AR experience to transaction closed loop.

[0006] The technical effects and advantages of this invention, which integrates AR scenarios into a customized furniture marketing and order transaction system, are as follows: This invention upgrades the furniture selection experience from passive display to active perception by capturing subtle changes in user focus and interest, making the process intuitive, immersive, and personalized. On a business level, the system constructs a seamless channel from appreciation to ownership, eliminating multiple experiential gaps in traditional models. This allows each peak in user interest to naturally lead to a potential sale, improving the return on investment of marketing resources. This invention breaks through the traditional boundaries of furniture product value realization, introducing a new concept of digital rights, making furniture not just a physical commodity, but a transferable and appreciating digital asset. This transformation is particularly significant in the hotel setting—the temporary interaction between guests and furniture is no longer a fleeting experience, but a sustainable value connection, creating new revenue streams for the hotel and satisfying guests' emotional need to materialize their preferences. By establishing a value bridge between guests, this invention activates the potential value of idle assets, forming a virtuous cycle of efficient resource circulation. Attached Figure Description

[0007] Figure 1 This is a schematic diagram of the customized furniture marketing and order transaction system that integrates AR scenes according to the present invention. Detailed Implementation

[0008] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0009] Please see Figure 1 In this embodiment of the invention, the customized furniture marketing and order transaction system integrating AR scenes includes: The data acquisition module is used to acquire user interaction trajectory data and visual dwell data on furniture objects in AR scenes. Interaction trajectory data includes gesture trigger sequences, viewpoint rotation trajectories, and spatial movement paths; visual dwell data includes user gaze duration and gaze frequency, collected in real time through the AR device's sensor network. Interaction trajectory data directly reflects the user's operational intentions and interest direction regarding the furniture, while visual dwell data characterizes the user's attention allocation. This data provides a foundation for interest decay analysis and purchase intention assessment, ensuring the accuracy and effectiveness of marketing strategies.

[0010] The intent assessment module constructs a micro-interest decay curve for furniture items based on interaction trajectory data and visual dwell time data, and generates a purchase intent intensity matrix based on the inflection point distribution of the micro-interest decay curve. The micro-interest decay curve quantifies the persistence of users' interest in furniture, directly impacting the likelihood of transaction conversion. This curve is calculated through time-series analysis of visual dwell time data and changes in interaction frequency, ensuring that marketing strategies match users' actual interests.

[0011] The path analysis module collects characteristic data of user operation interruptions in AR scenarios, identifies transaction path breakpoints, and calculates the conversion resistance index for each breakpoint. The operation interruption event characteristic data includes the interaction depth before the interruption, the interface hierarchy at the time of the interruption, and the frequency of return after the interruption. Analyzing this data identifies obstacles in the user's transaction path, providing a basis for subsequent guidance strategies.

[0012] The graph generation module generates a seamless transaction trigger point map based on the conversion resistance index and the purchase intention strength matrix. This trigger point map determines the most suitable locations and timing for displaying transaction guidance elements within the AR scene, providing spatial mapping for a seamless transaction experience.

[0013] The element rendering module dynamically renders transaction guidance elements at the locations marked on the seamless transaction trigger point map. The visual salience of these elements adaptively adjusts based on real-time values ​​from the purchase intention intensity matrix. These transaction guidance elements are key interface components connecting the AR experience and transaction decisions; their salience dynamically changes with the user's interest level, providing a natural and smooth transaction entry point.

[0014] The volatility monitoring module is used to monitor the user's response delay and interaction completion rate to trading guidance elements, and to identify the fluctuation characteristics of the user's immediate trading intention. By analyzing the user's response patterns to trading guidance, the module assesses the strength and trend of their current trading intention.

[0015] The mapping model construction module is used to build a digital asset mapping model for furniture objects based on the fluctuation characteristics of real-time transaction intentions. This model transforms the physical attributes of furniture into digital equity parameters, including usage right duration, maximum number of transfers, and appreciation coefficient. The digital asset mapping model serves as a bridge connecting physical furniture and digital equity, providing a theoretical basis for subsequent hybrid trading options.

[0016] The transaction option generation module generates hybrid transaction options for hotel guests based on a digital asset mapping model. These options include both physical purchase channels and digital asset subscription channels. The hybrid transaction options provide users with diversified transaction methods to meet the needs of different use cases.

[0017] The digital asset binding module is used to bind the digital assets of a furniture item to the guest's identity identifier after the guest selects and completes the digital asset subscription channel. Identity binding ensures the unique ownership of digital asset rights and lays the foundation for subsequent transfer transactions.

[0018] The premium calculation module collects real-time AR interaction data of subsequent guests interacting with the same furniture object, and calculates the premium coefficient of the digital asset based on the changes in the density of the AR interaction data. The premium coefficient reflects the market popularity and appreciation potential of the digital asset, providing a reference for asset transfer pricing.

[0019] The transaction channel construction module is used to push asset transfer premium prompts to existing guests holding digital assets when a new guest's purchase intention for furniture objects is detected to be higher than a preset threshold, and to establish a digital asset bidding transaction channel between the existing guest and the new guest. The premium prompt activates dormant assets, and the bidding channel facilitates the transaction between the two parties.

[0020] The integrated output module dynamically calculates the optimal transaction price for asset transfer based on the bidding sequence and time decay factor in the digital asset auction trading channel, completing the transaction and achieving a seamless connection from the AR experience to the transaction loop. The optimal transaction price balances the interests of both buyers and sellers, improving transaction success rate and satisfaction.

[0021] The modules are connected via wired and / or wireless means to enable data transmission between them.

[0022] In this embodiment of the invention, the detailed implementation steps for constructing a micro-interest decay curve for furniture objects and generating a purchase intention intensity matrix based on the inflection point distribution of the micro-interest decay curve include: The gaze duration of each furniture object in the visual persistence data was decomposed into a time series to extract the trend and fluctuation components of the gaze duration. Time series decomposition is a prerequisite for analyzing changes in interest, breaking down complex gaze behavior into basic trends and short-term fluctuations. The decomposition process uses the STL decomposition method to decompose the gaze duration series into three components: trend, seasonality, and residual. In the processed results, the trend component reflects the overall trend of user interest, while the fluctuation component reflects the fluctuation characteristics of short-term interest. For high-frequency gaze behavior, a small time window moving average preprocessing is used to eliminate eye-tracking noise; for low-frequency gaze behavior, trend extraction technology is used to identify the main changing patterns of gaze. This multi-scale preprocessing ensures the accuracy and representativeness of the gaze duration decomposition.

[0023] The first derivative of the trend component is calculated, and the negative interval of the first derivative is marked as the interest decay interval. The first derivative reflects the rate of change in attention interest, and the negative interval indicates that user interest is declining. The calculation process uses the central difference method to numerically differentiate the trend component, ensuring the stability and accuracy of the derivative calculation. The identification of the interest decay interval provides an important basis for subsequent inflection point analysis, marking the time period that needs to be focused on.

[0024] The rate of change in gesture trigger frequency within the interaction trajectory data during the interest decay interval is statistically analyzed. A positive abrupt change in the rate of change is marked as an inflection point in interest decay. The rate of change in gesture trigger frequency is a key indicator for assessing user interaction willingness; a positive abrupt change indicates that users still have interaction peaks during the decline in interest, which is usually an important signal of purchase intention. The rate of change is calculated using the sliding window method, comparing the total number of gesture triggers in adjacent time windows to calculate the relative change ratio. Inflection point identification is based on a mutation detection algorithm; when the rate of change exceeds a preset threshold and the direction is positive, that moment is marked as an inflection point in interest decay. These inflection points are key nodes for subsequently constructing the interest decay curve, accurately reflecting the turning points in user interest.

[0025] Using time as the horizontal axis and the normalized values ​​of the trend components as the vertical axis, a micro-interest decay curve for each furniture object is constructed by connecting the start point, inflection point, and end point of the interest decay interval. Normalization ensures the comparability of curves between different furniture objects, and piecewise cubic spline interpolation is used to connect the curves, ensuring their smoothness and continuity. The constructed micro-interest decay curve visually illustrates the dynamic changes in user interest, providing a foundational model for subsequent inflection point distribution feature extraction.

[0026] This study extracts the temporal location and curve slope of all interest decay inflection points from the micro-interest decay curve, constructing an inflection point distribution feature vector. This vector includes the number of inflection points, the average time interval between inflection points, and the magnitude of slope change at each inflection point. The inflection point distribution feature vector provides a quantitative description of the interest decay pattern, characterizing the features of user interest changes from multiple dimensions. The number of inflection points reflects the frequency of interest fluctuations, the time interval represents the persistence of interest, and the magnitude of slope change describes the intensity of interest shifts. The feature vector construction employs statistical calculation methods to systematically extract the location and characteristics of inflection points, forming a standardized feature expression. This feature vector provides a quantitative basis for subsequent interest recovery capability assessment.

[0027] Based on the inflection point distribution feature vector, the interest recovery capability coefficient of furniture objects is calculated. This coefficient is determined by multiplying the number of inflection points by the magnitude of the slope change at each inflection point. The interest recovery capability coefficient reflects the ability of furniture objects to re-attract user attention after a decline in interest, and is a key factor influencing the strength of purchase intention. The calculation formula is as follows: ; in, The interest recovery ability coefficient. The number of inflection points. This represents the magnitude of the slope change at the inflection point.

[0028] This coefficient, by comprehensively considering the number of inflection points and the magnitude of slope changes, reflects both the frequency and intensity of interest fluctuations, providing a reliable basis for assessing purchase intentions. A higher coefficient value indicates that the furniture item is more likely to re-attract user attention after interest wanes, thus increasing the likelihood of a purchase.

[0029] The product of the interest recovery rate coefficient and the total duration of visual dwell time is used as the initial value of the purchase intention intensity for the furniture object. This initial value serves as a basic assessment of the user's purchasing tendency, comprehensively considering both the interest recovery rate and overall attention level. The calculation process combines interest quality (recovery rate) and interest quantity (dwell time) to provide a more comprehensive intention assessment. The initial value calculation uses a simple product form for ease of implementation and understanding, while retaining the importance weights of both factors. This initial value provides the basis for subsequent spatial weighting, reflecting the user's initial level of interest in the furniture object.

[0030] The initial value of purchase intention intensity is weighted by spatial location. The spatial location weighting coefficient is determined based on the angle between the reachability distance of the furniture object in the AR scene and the user's viewpoint center. Spatial location weighting is an important step in considering the characteristics of the AR environment, incorporating the furniture's position in virtual space into the intention evaluation system. The weighting coefficient calculation formula is as follows: ; in, The spatial location weighting coefficient, The reachability distance from the furniture object to the user. The distance attenuation constant is The angle between the furniture object and the center of the user's viewpoint.

[0031] This formula uses an exponential decay function to reflect the influence of distance and a cosine function to reflect the influence of viewpoint centrality. Furniture objects that are closer and more centrally located receive a higher weighting coefficient, aligning with the spatial intuition of AR interaction. The weighted purchase intention intensity value more accurately reflects the impact of spatial factors on purchasing decisions, providing optimized data for the purchase intention intensity matrix.

[0032] The weighted purchase intention intensity values ​​are then filled into a two-dimensional matrix structure according to the category and spatial distribution of furniture objects, generating a purchase intention intensity matrix. This matrix provides a systematic representation of purchase intentions for all furniture objects in the AR scene, offering an intuitive reference for subsequent marketing strategies. The matrix construction process first determines appropriate dimensions, typically using furniture category and spatial location area as coordinate axes; then, the calculated purchase intention intensity values ​​are filled into the corresponding positions, forming a complete intention distribution map. Matrix visualization uses heatmap technology to intuitively display the spatial distribution patterns of purchase intentions, facilitating the identification of high-intention areas and product categories. The generated purchase intention intensity matrix provides crucial decision-making basis for seamless transaction trigger point design, guiding the system to display transaction guidance elements at the optimal time and location.

[0033] In this embodiment of the invention, the detailed implementation steps for collecting user operation interruption event feature data in AR scenes, identifying transaction path breakpoints, and calculating the conversion resistance index for each transaction path breakpoint include: The user operation event chain is constructed by arranging the feature data of operation interruption events in chronological order. This event chain is the fundamental data structure for analyzing the coherence of user interactions, reflecting the sequence of user behavior in the AR scene. The construction process first captures all interaction events, including clicks, swipes, gazes, and other operations, along with their timestamps and contextual information; then, they are sorted by timestamps to form an ordered sequence of events. The event chain not only records the operation itself but also includes the contextual environment before and after the operation, such as interface state and interactive objects, providing complete behavioral data for subsequent interruption analysis. The constructed operation event chain is a prerequisite for identifying interaction breakpoints, providing a temporal perspective on user behavior.

[0034] The number of operation steps between two consecutive interruption events in a user operation event chain is extracted and denoted as the interruption interval step. The interruption interval step is a direct indicator for evaluating the continuity of interaction, reflecting the depth of user interaction before the operation is interrupted. The extraction process first identifies interruption events in the event chain, including page exit, task abandonment, and prolonged inactivity; then, it calculates the total number of operation steps between adjacent interruptions to obtain the interruption interval step. The step calculation considers the complexity and functional value of the operation, assigning different weights to different types of operations to more accurately reflect the depth of interaction. The interruption interval step is the basic data for identifying breakpoints, indicating the locations of obstacles that users may encounter in the interaction path.

[0035] Interruption events with intervals shorter than a preset threshold are identified and marked as high-frequency breakage levels. These high-frequency breakage levels represent the most critical links in the transaction path that are most likely to lead to user churn and are a key area for marketing optimization. The statistical process sets an appropriate step threshold (typically 3-5 steps) to filter out interruption events with intervals shorter than the threshold and analyzes their corresponding interface level distribution. Level marking uses clustering to group interfaces with similar functions and structures into the same level, improving the generality of the analysis. The identification of high-frequency breakage levels provides target objects for subsequent breakage sensitivity calculations, clarifying the interface links that need to be prioritized for optimization.

[0036] Interaction complexity is assessed for high-frequency interruption levels, and the ratio of user return frequency to interaction complexity is calculated, denoted as interruption sensitivity. Interruption sensitivity is a key indicator quantifying users' tolerance for interaction obstacles, reflecting the risk of user churn at different interface levels. The assessment process first calculates the interaction complexity of each high-frequency interruption level, considering factors such as the number of operation steps, information density, and decision branches; then, it counts the number of return attempts after encountering an interruption, calculating the ratio of return frequency to complexity. This ratio reflects the strength of users' willingness to overcome interaction obstacles; a lower ratio indicates that users are more likely to abandon interaction at that level. Interruption sensitivity provides a quantitative basis for identifying key interruption nodes, guiding the system to prioritize highly sensitive interaction links.

[0037] Interface layers with a break sensitivity exceeding a preset sensitivity threshold are identified as transaction path break nodes. These break nodes are critical points causing transaction process interruptions and are necessary intervention points for seamless transaction guidance. The identification process sets an appropriate sensitivity threshold (typically based on the upper quartile of historical data) and identifies interface layers with break sensitivity exceeding the threshold as break nodes. Node identification employs a two-stage verification mechanism, combining user survey feedback and behavioral data analysis to improve the accuracy and reliability of identification. The identified transaction path break nodes provide target objects for calculating the conversion resistance index, clarifying the key locations where compensation strategies need to be implemented.

[0038] Based on the interaction depth before the interruption of the trading path breakpoint, a depth decay function is constructed. The product of the depth decay function value at the breakpoint and the break sensitivity is used as the conversion resistance index. The conversion resistance index is a comprehensive indicator that quantifies the strength of obstacles in the trading path, reflecting the degree to which the breakpoint hinders trading conversion. The construction process first designs the depth decay function based on the interaction depth, typically using an exponential decay form: ; in, This represents the depth decay function value. The interaction depth before the interruption. This is the attenuation coefficient.

[0039] This function reflects the impact of interaction depth on user abandonment costs; the greater the depth, the higher the abandonment cost, and the less willing users are to easily interrupt the interaction. The formula for calculating the conversion resistance index is: ; in, To transform the resistance index, For fracture sensitivity.

[0040] This index comprehensively assesses the resistance strength of breakpoints by considering both interaction depth and breakpoint sensitivity. A higher index value indicates a more significant obstacle to transaction conversion at that node, requiring a stronger intervention strategy. The calculated conversion resistance index provides a priority basis for designing seamless transaction trigger points, guiding the system to rationally allocate guidance resources.

[0041] In this embodiment of the invention, the detailed implementation steps for generating a seamless transaction trigger point map based on the conversion resistance index and the purchase intention strength matrix include: Based on the purchase intent strength matrix, the top N furniture items with the highest purchase intent strength values ​​are extracted and denoted as the high-intent furniture set. The high-intent furniture set represents the target product group with the highest potential conversion rate and is the priority for triggering transactions. The extraction process sorts the purchase intent strength matrix and selects the furniture items corresponding to the top N highest values. The value of N is typically set based on scenario complexity and user capacity, usually 3-5 items. The selection criteria consider both the absolute value and relative difference in intent strength to ensure that the selected furniture items have a significant conversion advantage. Determining the high-intent furniture set provides a target range for subsequent trigger point settings, focusing system resources on the most potential conversion targets.

[0042] In the 3D spatial model of the AR scene, the geometric center coordinates of each furniture object in the set of highly intended furniture are marked. These geometric center coordinates serve as a reference point for determining the spatial location of trigger points, providing precise positioning of the furniture objects in AR space. The marking process is based on the 3D model data of the furniture, calculating the world coordinates of its geometric center point and performing real-time positioning within the AR scene. The coordinate calculation considers the shape characteristics and spatial orientation of the furniture; for irregular shapes, a weighted centroid algorithm is used to more accurately reflect the visual focus position. The marked geometric center coordinates provide a spatial reference for setting candidate trigger points, ensuring that guiding elements appear in visually reasonable positions.

[0043] Candidate transaction trigger points are set at a preset distance from the furniture surface, along the normal vector of the user's line of sight. These candidate trigger points are spatial locations where transaction guidance elements may be displayed, and their placement must consider visual comfort and ease of interaction. The setting process first determines the user's current line of sight vector, then calculates the intersection of this vector with the furniture surface, and sets the trigger point at a preset distance (usually 0.3-0.5 meters) along the line of sight normal vector. The distance setting considers the interactive characteristics of AR devices and the user's visual comfort zone; too close will cause visual strain, while too far will make it difficult to stimulate interaction. The set candidate trigger points provide spatial options for priority calculation, ensuring that guidance elements appear in an appropriate position within the user's field of vision.

[0044] The shortest path length between candidate transaction trigger points and transaction path breakpoints in the operation flowchart is calculated. The shortest path length is a key indicator for evaluating the correlation between trigger points and breakpoints, reflecting the operational distance from the trigger to the potential breakpoint. The calculation process abstracts the AR interaction flow into a directed graph structure, with trigger points and breakpoints as nodes and operation steps as edges. Dijkstra's algorithm is used to calculate the shortest path between the two points. The path length calculation considers not only the number of steps but also the operational complexity, assigning different weights to different types of operations. The calculated shortest path length provides an important parameter for priority weight calculation, reflecting the potential influence of the trigger point on the breakpoint.

[0045] The priority weight of candidate transaction trigger points is calculated based on the shortest path length and the reciprocal of the conversion resistance index. This priority weight is a comprehensive indicator for evaluating the value of trigger points, determining their display order and resource allocation. The calculation formula is as follows: ; in, Priority weights The shortest path length. This is the conversion resistance index.

[0046] This formula uses the reciprocal of the path length to reflect the proximity of the trigger point to the fracture node, and the reciprocal of the resistance exponent to reflect the severity of the fracture node. A higher weight value indicates that the trigger point can more effectively prevent critical fractures and should be given priority. The calculated priority weights provide a quantitative basis for trigger point selection, guiding the system to choose the most influential location to display guiding elements.

[0047] Priority weights are adjusted for visual occlusion, and the top M candidate transaction trigger points with the highest adjusted priority weights are selected. Visual occlusion adjustment is a crucial step in considering AR visual effects, ensuring the visibility and aesthetics of trigger points within the user's field of vision. The adjustment process first performs visual visibility detection to eliminate trigger points obstructed by other objects; then, it considers visual congestion to avoid excessive concentration of trigger points causing visual interference; finally, based on the adjusted priority weights, the top M optimal trigger points (typically M=2-3) are selected. The number of selected trigger points is kept within a reasonable range to avoid distracting the user while preserving sufficient guidance opportunities. The selected priority trigger points provide a spatial basis for time window allocation, ensuring that guiding elements are displayed in the optimal position.

[0048] Based on the average occurrence time of breakpoints in the trading path, a trigger time window is allocated to each trigger point. The trigger time window is a time parameter that controls the timing of the guiding element's appearance, ensuring that the guidance is displayed at the optimal moment. The allocation process analyzes the time distribution of breakpoints in historical data, calculates the average occurrence time and standard deviation, and then shifts forward an appropriate time (usually 20-30 seconds before the breakpoint) to set the start time of the trigger window. The window length is set according to user decision-making characteristics, typically 15-25 seconds, providing users with sufficient reaction time while maintaining the timeliness of the guidance. A staggered time window allocation strategy is used to avoid interference caused by multiple trigger points activating simultaneously, optimizing user attention allocation. The allocated trigger time window provides time control for seamless trading triggering, ensuring that the guiding element is presented at the optimal moment.

[0049] The spatial coordinates of trigger points, trigger time windows, and corresponding furniture object identifiers are integrated into a seamless transaction trigger point map. This map provides a complete representation of the guided element display strategy, offering precise control over both time and space. The integration process organizes the various parameters of the trigger points into standardized data structures, including three-dimensional spatial coordinates, time window parameters, associated furniture IDs, and priority weights. The bitmap is constructed using a hierarchical design, facilitating real-time querying and updates, and supporting dynamic adjustments to the trigger strategy. The integrated trigger point map provides comprehensive guidance for the dynamic rendering of transaction guided elements, ensuring that guidance is displayed at the optimal time and location, maximizing the possibility of transaction conversion.

[0050] In this embodiment of the invention, the detailed implementation steps of dynamically rendering transaction guidance elements at the locations marked on the seamless transaction trigger point map, and adaptively adjusting the visual salience of the transaction guidance elements based on the real-time values ​​of the purchase intention intensity matrix, include: Based on the seamless transaction trigger point map, the system continuously monitors whether the user's perspective enters the trigger time window. Time window detection is a prerequisite for activating onboarding elements, ensuring that the guidance is displayed at the optimal preset time. The detection process continuously monitors the system clock and user behavior; when the current moment enters the preset time window of a trigger point, that trigger point is marked as pending activation. Window judgment takes into account the user's current behavioral context; when the user is focused on interaction or making a critical decision, the window waiting time is appropriately extended to avoid undue interruption and negative experience. The real-time detection mechanism provides time control for the accurate activation of onboarding elements, ensuring that marketing information is delivered at the optimal time.

[0051] When the user's perspective enters the trigger time window, the 3D model of the transaction guidance element is initialized at the spatial coordinates of the transaction trigger point. Guidance element initialization is the first step in visual presentation, placing the designed 3D interface elements in AR space. The initialization process first searches the guidance element library, selecting appropriate element templates based on furniture type and user profile; then, it creates element instances at the precise coordinates of the trigger point, setting initial state parameters, including size, orientation, and transparency. Model placement considers the physical characteristics of AR space and the user's perspective, ensuring that elements face the user and do not penetrate physical objects. The initialized guidance elements provide rendering objects for visual saliency adjustments and serve as the concrete carrier of transaction guidance.

[0052] The system reads the current purchase intention strength value of the corresponding furniture object from the purchase intention strength matrix in real time. This purchase intention strength value is the core basis for adjusting the salience of guiding elements, reflecting the user's current purchasing tendency. The reading process queries the purchase intention strength matrix to extract the latest intention strength value of the furniture object associated with the current trigger point. Data acquisition employs a real-time update mechanism; the system continuously monitors user interaction behavior and dynamically adjusts intention assessments to ensure data timeliness and accuracy. The read intention strength value provides a key parameter for transparency calculation, guiding the system to adjust the visual prominence of guiding elements based on the user's real-time intentions.

[0053] Based on the current purchase intention strength value, the base transparency of the transaction guide element is calculated. Base transparency is the initial parameter for the visual salience of the guide element, determining its basic visibility. The calculation uses a mapping function to convert the purchase intention strength value into a transparency parameter: ; in, Based on the basic transparency (1 is completely opaque). This is the minimum transparency threshold (typically 0.3-0.4). This represents the current level of purchase intention. This represents the maximum reference value for purchase intention.

[0054] This formula establishes a direct correlation between intention intensity and transparency; the stronger the intention, the clearer and more prominent the guiding element. The calculation of base transparency provides a benchmark for dynamic transparency, ensuring that the initial visibility of the guiding element matches the user's level of interest.

[0055] Real-time differentiation is performed on the interaction trajectory data to obtain the user's gesture acceleration vector. The gesture acceleration vector is a dynamic indicator for evaluating the user's attention direction, reflecting the user's current intention in the interaction. The differentiation calculation employs the second-order central difference method, performing two numerical differentiations on the position data to obtain acceleration information. The vector calculation considers not only amplitude but also direction information, comprehensively describing the dynamic characteristics of the gesture. The calculation results are low-pass filtered to eliminate high-frequency noise interference and retain the main motion trend. The obtained acceleration vector provides dynamic input for the attention enhancement factor, enabling real-time interaction between the guiding elements and user behavior.

[0056] When the gesture acceleration vector points to the transaction guide element, the base transparency is multiplied by an attention enhancement factor to generate dynamic transparency. Dynamic transparency is a key parameter for achieving interactive responsiveness, enabling the guide element to sense and respond to user attention. The determination process calculates the angle between the acceleration vector and the vector connecting the user to the guide element. When the angle is less than a threshold (usually 30°), it is determined that the user's gesture is pointing at the element. The enhancement calculation formula is: ; in, For dynamic transparency, This is the enhancement factor (usually 0.2-0.4). The angle between the two vectors.

[0057] This formula achieves a smooth enhancement effect through the cosine function; the more precise the direction, the more significant the enhancement. Dynamic transparency generation provides real-time control over rendering parameter adjustments, enabling elements to intelligently respond to user actions and enhancing the natural smoothness of the interaction.

[0058] Based on dynamic transparency and current purchase intent strength, the rendering parameters and color scheme of the transaction guidance elements are adjusted, and the adjusted elements are rendered into the AR scene. Adjusting rendering parameters is the final step in visual presentation, ensuring the final effect of the guidance elements aligns with marketing strategies and user experience needs. The adjustment process sets the basic visibility of the elements based on dynamic transparency, while adjusting other visual attributes, including size scaling, halo effects, and animation speed, based on purchase intent strength. The color scheme adjustment employs emotional color mapping, using more vibrant and bright hues for high intent strength and softer, more subdued hues for lower intent strength. The final rendering effect is achieved through the AR device's graphics pipeline, considering ambient lighting, shadow casting, and spatial blending to ensure the guidance elements naturally integrate into the AR scene, attracting attention without causing visual interference. The adjusted guidance elements provide users with an intuitive transaction entry point, achieving seamless delivery of marketing information.

[0059] In this embodiment of the invention, the detailed implementation steps for monitoring the user's response delay time and interaction completion rate to transaction guidance elements, and identifying the fluctuation characteristics of the user's immediate transaction intention, include: The system records the moment the user's gaze first touches the trading guidance element and the moment the user performs their first touch operation, calculating the time difference between the two as the response latency. Response latency is a key indicator for evaluating the user's decision-making speed, reflecting the user's responsiveness to trading prompts. The recording process uses eye-tracking technology to capture the first intersection point between the user's gaze and the guidance element, while simultaneously monitoring the first valid touch operation captured by the gesture recognition system, calculating the precise time difference between the two. The time calculation takes into account system latency and sensor errors, and a calibration algorithm is used to ensure measurement accuracy. Response latency provides fundamental time-dimensional data for analyzing trading intention fluctuations, directly reflecting the decisiveness and intensity of user decision-making.

[0060] The transaction guidance elements are designed as a multi-step interactive process. The number of micro-interactions completed by users is counted, and the ratio of completed tasks to the total number of tasks is calculated as the interaction completion rate. Interaction completion rate is a quantitative indicator for evaluating the depth of user participation, reflecting the user's level of engagement in the transaction process. The process design breaks down the transaction into multiple small steps (usually 3-5 steps), each designed as an independent and quantifiable micro-interaction task, such as information confirmation, option selection, and parameter adjustment. The completion rate calculation uses a weighted method, assigning different weights based on the decision importance of each step, more accurately reflecting the progress of the transaction. Interaction completion rate provides key data for in-depth analysis of transaction intention, comprehensively assessing user engagement and decision-making determination.

[0061] A two-dimensional feature space is constructed, with response latency time as the horizontal axis and interaction completion rate as the vertical axis. This two-dimensional feature space forms the foundational framework for visualizing trading intentions, providing a standardized expression for intention analysis. The construction process maps these two key indicators to an orthogonal coordinate system, creating a two-dimensional representation of user states. The coordinate system design uses a normalized value obtained by taking the reciprocal of the response latency time, placing fast responses on the right and slow responses on the left; interaction completion rate is directly represented by the original ratio, with high completion rate at the top and low completion rate at the bottom. This mapping method allows the upper right corner to represent high intention states (fast response and high completion rate), and the lower left corner to represent low intention states (slow response and low completion rate). The constructed two-dimensional feature space provides the geometric basis for state division, enabling an intuitive and quantitative expression of trading intentions.

[0062] In a two-dimensional feature space, based on pre-defined classification rules for intention fluctuations, user states are divided into four zones: hesitant observation zone, rapid decision-making zone, in-depth exploration zone, and churn warning zone. This state zone division is a crucial step in categorizing transaction intentions, mapping a continuous two-dimensional space into discrete intention categories. The classification rules are based on professional marketing experience and data analysis, setting boundary conditions as follows: Quick Decision Zone: Short response latency and medium to high completion rate indicate that users make quick decisions and have a strong willingness to purchase. Deep Exploration Zone: Moderate response latency and high completion rate indicate that although users take a long time to consider, their participation is high and their purchase intention is stable. Hesitation and observation zone: Long response delay and moderate completion rate indicate that users have concerns and are uncertain about their purchase intention; Churn warning zone: Long response delays or low completion rates indicate insufficient user interest and weak purchase intention.

[0063] The region division adopts a fuzzy boundary design, allowing for a certain degree of state mixing at the region boundaries, which better reflects the continuous characteristics of the actual decision-making process. The divided state regions provide a reference system for judging the direction of fluctuations and clarify the type characteristics of users' trading intentions.

[0064] The process extracts the user's trajectory movement direction in a two-dimensional feature space, labeling upward and downward fluctuations in intention. Extracting the fluctuation direction is a crucial step in capturing the dynamic changes in intention, reflecting the psychological fluctuations during the user's decision-making process. The extraction process records the continuous positional changes of the user's state point in the feature space and calculates the displacement vector between adjacent time points. Direction determination is based on the azimuth angle of the vector, classifying 0°±45° (right) and 90°±45° (upward) as upward directions of intention, and 180°±45° (left) and 270°±45° (downward) as downward directions of intention. Fluctuation labeling considers not only direction but also amplitude; significant displacements are labeled as strong fluctuations, and small displacements as weak fluctuations. The extracted fluctuation directions provide temporal elements for constructing intention fluctuation features, capturing the dynamic changes in the user's decision-making process.

[0065] The temporal combination of rising and falling price fluctuations in trading intention is used as a feature of real-time trading intention fluctuation. This fluctuation feature is a temporal expression of user decision-making patterns, describing the changing patterns of trading intention over time. The combination process arranges the marked fluctuation directions in chronological order to form a fluctuation sequence, typically recording the 3-5 most recent significant fluctuations to ensure the timeliness and representativeness of the features. Sequence analysis employs a pattern matching algorithm to identify common decision-making fluctuation patterns, such as "continuous rise" indicating stable growth in interest, "rise followed by decline" indicating hesitation after impulsiveness, and "fluctuation followed by stabilization" indicating a trend towards stable decision-making. These patterns provide a psychological reference for digital asset mapping, helping the system understand users' decision-making characteristics and purchasing motivations. The constructed real-time trading intention fluctuation feature provides key input to the digital asset mapping model, guiding the system to optimize trading strategies based on users' real-time psychological states.

[0066] In this embodiment of the invention, based on the fluctuation characteristics of real-time transaction intentions, a digital asset mapping model for furniture objects is constructed. The detailed implementation steps for converting the physical attributes of furniture into digital rights parameters including usage right duration, maximum number of transfers, and appreciation coefficient include: The process involves acquiring physical attribute data for furniture objects, including material grade, design style tags, manufacturing costs, and market scarcity. This physical attribute data forms the foundation for digital asset valuation, reflecting the intrinsic value and market positioning of the furniture. The acquisition process involves querying detailed product information from the system database, including material grade (e.g., solid wood, particleboard, metal grade classifications), design style tags (e.g., Nordic, modern minimalist, classic styles), manufacturing costs (including raw materials, labor, and craftsmanship costs), and market scarcity (a scarcity index calculated based on production quantity and market demand). Data acquisition considers both completeness and accuracy, supplementing missing fields using similar products or expert evaluation. The acquired physical attribute data provides fundamental product information for market popularity calculations, ensuring that digital asset valuations are based on true physical value.

[0067] The market popularity index for this furniture item is calculated based on the cumulative number of upward fluctuations in real-time transaction intention characteristics. The market popularity index is a dynamic parameter quantifying product market attention, reflecting the overall interest level of the user group in the furniture. The calculation process involves counting the cumulative number of upward fluctuations in intention generated by all users during interactions with the furniture, using a time-decay weighting to give greater contribution from recent fluctuations and gradually reduce the influence of historical fluctuations. The calculation formula is as follows: ; in, As an indicator of market popularity, For the first The intensity of the fluctuation in secondary willingness. The time interval between this fluctuation and the current time. This is the time decay coefficient.

[0068] This metric reflects the market's real-time feedback on the product through the collective expression of user willingness, providing a market-dimensional assessment basis for the fundamental value anchor.

[0069] The fundamental value anchor for digital assets is determined by multiplying market popularity and market scarcity. This fundamental value anchor serves as the starting point for digital asset valuation, establishing a value mapping relationship between physical assets and digital rights. The determination process combines market supply and demand, considering both user demand (market popularity) and supply constraints (scarcity). The calculation formula is as follows: ; in, As a basic value anchor, As an indicator of market popularity, Due to market scarcity, This is the value conversion coefficient.

[0070] The value anchor, expressed in monetary units, serves as the benchmark for the initial pricing of digital assets, providing a value basis for subsequent conversion of equity parameters. The established basic value anchor provides a quantitative basis for mapping usage right duration, ensuring that digital asset pricing aligns with market value.

[0071] The underlying value anchor is mapped to an initial value for the usage right duration. The usage right duration is a core equity parameter of digital assets, defining the period for which a user can enjoy the asset. The mapping process employs the value amortization principle, allocating the underlying value anchor according to the furniture's expected lifespan. The calculation formula is: ; Where T is the initial value of the usage right duration. As a basic value anchor, The total value of the furniture, For the expected lifespan of furniture, This is the equity conversion factor (usually greater than 1, indicating the price advantage of digital usage rights compared to physical ownership).

[0072] The mapping results are expressed in days, months, or years, clearly defining the time dimension of digital asset rights. The initial usage right duration sets the time range for the basic rights of digital assets and serves as a fundamental parameter for subsequent transactions and transfers.

[0073] Based on physical attribute data, durability and popularity scores are calculated for furniture items. Durability and popularity scores are two key dimensions for assessing the long-term value of furniture, reflecting its physical lifespan and market lifespan, respectively. The scores are calculated based on a weighted combination of physical attributes; durability primarily considers material grade and manufacturing process, while popularity primarily considers design style and market feedback. The scores are standardized and converted into a 0-100 range for easy comparison and calculation. These two scores provide fundamental parameters for the number of resales and the appreciation coefficient, reflecting the furniture's enduring characteristics in both physical and market dimensions.

[0074] Based on durability scores, a maximum number of transfers for digital assets is set. This maximum number of transfers is a control parameter for the liquidity of digital assets, balancing asset liquidity and value stability. The setting process is based on durability scores, taking into account the physical depreciation characteristics of furniture. The calculation formula is as follows: ; in, This is the maximum number of transfers. For durability rating, This indicates rounding down to the nearest integer.

[0075] This formula adds one transfer opportunity for every 20 points increase in durability, ensuring that furniture in good physical condition has higher circulation value. The set limit on the number of transfers provides a constraint on the circulation management of digital assets, guaranteeing the long-term value of assets while avoiding the devaluation risk that may arise from unlimited transfers.

[0076] A value-added potential function is constructed based on a weighted sum of popularity score and market heat index, outputting an initial value for the value-added coefficient. The value-added coefficient is a quantitative expression of the appreciation potential of digital assets, reflecting the expected value change of the asset during the holding period. The construction process combines long-term market trends (popularity) and short-term heat to comprehensively assess the asset's appreciation potential. The calculation formula is as follows: in, This is the initial value of the increment coefficient. Score popularity As an indicator of market popularity, This is the maximum reference value for popularity. and The weighting coefficients are and satisfy the following conditions: , This is the value-added adjustment coefficient (usually 0.1-0.3).

[0077] An initial value greater than 1 indicates expected appreciation, equal to 1 indicates stable value, and less than 1 indicates potential depreciation (a rare occurrence). The constructed appreciation coefficient provides a quantitative reference for the expected value of digital assets, guiding users in asset appreciation assessment and investment decisions.

[0078] The usage right duration, maximum number of transfers, and initial value of the appreciation coefficient are encapsulated as digital equity parameters. These digital equity parameters are a complete expression of the core attributes of a digital asset, defining its use value and trading characteristics. The encapsulation process organizes these three key parameters into a standardized data structure, including detailed information such as numerical values, units, validity periods, and constraints. The parameters are expressed in a user-friendly manner, transforming technical details into intuitive and understandable descriptions of the rights, such as "12-month usage right, maximum 3 transfers, expected annual appreciation of 8%." The encapsulated digital equity parameters provide a standard output format for the asset mapping model, ensuring consistent understanding and processing of asset characteristics across all system components.

[0079] A mapping relationship is established between physical attribute data and digital rights parameters, and this mapping relationship is constructed into a digital asset mapping model. This model supports the dynamic generation of corresponding digital rights parameters based on the physical attribute data of furniture objects. The digital asset mapping model serves as a bridge between the physical world and digital rights, realizing a systematic mapping of the physical value of furniture to digital assets. The construction process employs machine learning methods, using historical mapping data as a training set to build a regression model, achieving automatic conversion from physical attributes to rights parameters. The gradient boosting decision tree algorithm is selected for the model, possessing strong nonlinear fitting ability and interpretability. Model training considers sample balance and feature importance, and cross-validation ensures predictive stability. The constructed mapping model provides algorithmic support for the generation of hybrid transaction options, realizing automated and personalized conversion from physical characteristics to digital rights, laying the technical foundation for the system's large-scale operation.

[0080] In this embodiment of the invention, based on a digital asset mapping model, a hybrid transaction option is generated for hotel guests. The detailed implementation steps of the hybrid transaction option, which includes a physical purchase channel and a digital asset subscription channel, include: The process involves calling a digital asset mapping model, inputting the physical attribute data of the target furniture object, and retrieving the corresponding digital equity parameters. Obtaining these equity parameters is a prerequisite for generating transaction options, providing core characteristic information about the digital asset. The process submits complete physical attribute data of the furniture to the mapping model, including factors such as material, design, cost, and scarcity. The model, based on a trained algorithm, calculates and outputs the corresponding digital equity parameters. Parameter retrieval employs a caching mechanism; frequently queried furniture object equity parameters are stored in memory, reducing computational overhead and improving response speed. The acquired digital equity parameters provide fundamental information for determining assetization conditions and are the basis for constructing subsequent transaction options.

[0081] Based on the usage right duration and maximum transfer frequency parameters in the digital rights parameters, it is determined whether the furniture meets the conditions for digital assetization. The conditions for digital assetization require that the usage right duration exceed a preset threshold and the maximum transfer frequency exceed a preset threshold. The assetization condition assessment is a necessary step to ensure the quality of digital assets, screening out high-value furniture suitable for digitization. The assessment process sets appropriate threshold conditions, typically requiring a usage right duration of no less than 6 months and a maximum transfer frequency of no less than 1 time, ensuring that the asset has basic use value and liquidity. The condition check uses a simple logical comparison; only when both threshold requirements are met simultaneously can the assetization process begin. This screening mechanism ensures the quality standards of digital assets, preventing low-value, short-term, or non-transferable items from entering the digital asset market and guaranteeing the healthy development of the overall trading ecosystem.

[0082] When the conditions for digital assetization are met, a dual-channel transaction interface is generated within the transaction guidance elements of the AR scene. The dual-channel interface is a visual representation of a hybrid transaction method, providing users with diverse purchasing options. The generation process is based on a preset interface template, creating an interactive interface containing two main areas in the AR space. The interface design follows spatial interaction principles, considering the perspective characteristics and ease of operation in the AR environment. Interface elements are of moderate size, clearly laid out, and interactive points are prominently displayed. A semi-transparent rendering effect is used to ensure that the interface does not completely obstruct the user's visual perception of the physical furniture, maintaining the continuity and immersion of the AR experience. The generated dual-channel interface provides parallel entry points for two transaction methods, meeting the diverse needs of different users.

[0083] On the left side of the dual-channel transaction interface, a physical purchase channel is constructed. This channel displays the physical delivery information of the furniture, including delivery time, ownership details, and after-sales service terms. The physical purchase channel is a continuation of traditional transaction methods, satisfying users' needs for physical ownership. The design incorporates intuitive visual elements and interactive flows, highlighting the core advantages and detailed information of physical purchases. The content display includes three key sections: delivery time indicating when users can receive the item; ownership details clarifying the scope and limitations of the user's rights; and after-sales service terms detailing the warranty period and service content. Information is presented in a hierarchical manner, with important information directly visible and detailed terms expanded by clicking, balancing information completeness with interface simplicity. This physical purchase channel provides traditional consumers with a familiar purchasing path, ensuring comprehensive coverage of transaction options and user-friendliness.

[0084] A digital asset subscription channel is constructed on the right side of the dual-channel trading interface, displaying detailed information about the digital rights parameters. This channel serves as the core entry point for this innovative trading method, guiding users to understand and participate in digital rights trading. The design incorporates technologically advanced visual elements and interactive feedback, highlighting the innovative characteristics and investment attributes of digital assets. The content presentation transforms complex rights parameters into intuitive and understandable visual representations: the usage right duration is displayed in calendar format; the maximum number of transfers is presented through a visual counter; and the appreciation coefficient is visually represented through a trend chart. The information organization emphasizes educational value, providing conceptual explanations and case studies for users new to digital assets, lowering the cognitive threshold. This constructed digital asset subscription channel offers innovative consumers a novel trading experience, expanding new avenues for realizing furniture value.

[0085] Based on the location code of the furniture object in the current hotel room, a unique asset identifier is generated for the digital asset. This asset identifier is associated with the future usage rights and revenue of the furniture object in a specific hotel room. The asset identifier serves as a unique identity for the digital asset, ensuring its traceability and exclusivity. The generation process employs a multi-factor combination algorithm, integrating the furniture ID, location coordinates, timestamp, and random factor to create a unique identifier string. The encoding format adopts a design that balances readability and security: the prefix indicates the asset type and the hotel it belongs to, the middle section contains location information, and the suffix is ​​a unique serial number. The identifier is integrated with blockchain technology, with each asset registered as a unique record on the chain, ensuring the transparency and immutability of ownership changes. The generated asset identifier provides the technological foundation for the confirmation and trading of digital rights and is a core supporting element of the digital asset system.

[0086] The subscription price of a digital asset is calculated by multiplying the physical price of the furniture by the proportion of the usage right duration to the furniture's total lifespan, and then multiplying by the digital asset discount factor. The subscription price is a key parameter in digital asset transactions, balancing value rationality and market attractiveness. The calculation formula is as follows: ; in, The subscription price for digital assets. This refers to the actual price of the furniture. For the duration of the right to use, For the expected lifespan of furniture, This is the discount factor for digital assets (typically 0.7-0.9).

[0087] This pricing model is based on the time-proportion principle, allocating the price of full ownership proportionally to the duration of use, and reflecting the price advantage of digital usage rights compared to physical ownership through a discount factor. The price calculation takes market acceptance into account, ensuring that the digital asset has significant economic appeal to users. The calculated subscription price provides a foundational value for revenue forecasting and serves as a starting point for assessing investment returns.

[0088] Within the digital asset subscription channel, a profit forecast curve is rendered. Based on the initial value of the appreciation coefficient and historical transaction data, this curve simulates the future premium trend of the digital asset. The profit forecast curve is a visual representation of the digital asset's investment value, helping users assess potential returns. The rendering process constructs a multi-scenario prediction model based on historical data and current parameters, typically including conservative, neutral, and optimistic scenarios. The curve is plotted using smooth spline technology, presenting the value change trend over the next 6-12 months, with the horizontal axis representing time and the vertical axis representing asset valuation. The visualization design highlights key nodes, such as expected turning points, maximum profit points, and recommended holding periods, helping users formulate optimal holding strategies. The rendered profit forecast curve provides an intuitive reference for users' investment decisions, enhancing the attractiveness of digital asset investment attributes.

[0089] The integration of physical asset purchase and digital asset subscription channels into a hybrid trading option, along with a channel switching control within the dual-channel trading interface, allows users to freely switch between and compare the two channels. This hybrid trading option integration is the final step in providing a comprehensive purchasing experience, ensuring users can easily compare and choose the most suitable transaction method. The integration process achieves seamless connectivity between the two channels at the interface level, featuring intuitive switching buttons and comparison views. The control design utilizes AR-friendly gesture controls, allowing users to switch between the two channels with simple swipes or clicks. The system automatically saves browsing progress, ensuring uninterrupted decision-making during switching. The comparison function provides a side-by-side display of core parameters, such as price comparisons, equity differences, and applicable scenario comparisons, helping users make informed choices. The integrated hybrid trading option offers users flexible and diverse purchasing methods, meeting the differentiated needs of different groups and maximizing the possibility of transaction conversion.

[0090] In this embodiment of the invention, the detailed implementation steps for collecting AR interaction data of subsequent guests on the same furniture object in real time and calculating the premium coefficient of digital assets based on the density change of AR interaction data include: The system records each new guest's AR interactions with furniture objects in the room, generating an interaction behavior log. This log is fundamental data for digital asset valuation, reflecting subsequent user engagement with the asset. The recording process captures all relevant user actions within the AR scene, including gaze duration, touch count, rotation, and information queries, while also recording precise timestamps and contextual information. Log generation employs non-intrusive monitoring technology, completing data collection without impacting user experience. Data storage adheres to privacy principles, anonymizing personally identifiable information and retaining only statistics related to asset valuation. The generated interaction behavior log provides raw data for subsequent analysis and serves as the foundation for intensive computation.

[0091] Cluster analysis was performed on interaction behavior logs to identify high-frequency interaction time periods and calculate the duration percentage of these periods. High-frequency time period analysis is a crucial method for evaluating interaction quality, identifying the time windows where user interest is most concentrated. The analysis process employed a time-series clustering algorithm, grouping interaction events by temporal proximity and density to identify time periods with significantly higher-than-average event density. The DBSCAN algorithm was used for clustering, as it is insensitive to outliers and suitable for discovering irregularly shaped time clusters. The percentage calculation compared the cumulative duration of high-frequency periods with the user's total time spent in the room to determine the time proportion of attention. This analysis provides a time dimension weight for density calculation, reflecting the concentration and persistence of user attention.

[0092] The number of different guests who interacted with the same furniture object within a pre-defined statistical period is recorded as the interactive guest base. The interactive guest base is a key indicator for assessing asset penetration, reflecting the breadth of the user group attracted to the furniture object. The statistical process sets an appropriate observation period (usually 7-14 days) and calculates the number of different users who effectively interacted with the target furniture during this period. Effective interaction is defined as behavior exceeding a minimum interaction threshold (e.g., gaze duration > 30 seconds or touch operations > 3 times) to ensure the significance of the statistics. The base calculation considers seasonal factors and occupancy rate fluctuations, and uses standardization to eliminate external interference. The statistically calculated interactive guest base provides user-dimensional data for density calculations, quantifying the group attractiveness of the furniture object.

[0093] The density of AR interaction data is calculated by multiplying the number of interacting guests by their interaction duration. Density is a core indicator for comprehensively evaluating asset popularity, integrating both the breadth and depth of interaction. This simple product achieves a comprehensive assessment of both dimensions: a large number of guests reflects a broad user base, while a high percentage indicates deep user engagement; the combination comprehensively reflects the asset's attractiveness. The density calculation results are standardized and converted into comparable standard scores for easy horizontal comparison and trend analysis. The calculated density value provides a key input for value-added assessment and serves as the basis for adjusting the premium coefficient.

[0094] The density of the current statistical period is differiated from that of the previous statistical period to obtain the change in density. Change analysis is a key step in capturing market dynamics, reflecting the changing trends in asset popularity. The difference calculation uses simple subtraction.

[0095] Positive difference results indicate increasing market interest, while negative results indicate decreasing market interest. The absolute value reflects the magnitude of the change. The calculation of the change takes into account statistical errors and random fluctuations; fluctuations below the minimum effective change threshold are considered insignificant. The density change of the difference provides trend data for determining the value increment level, reflecting the dynamic changes in asset market acceptance.

[0096] Based on preset asset appreciation trigger rules, the threshold range to which the density change belongs is determined, and the corresponding appreciation tier coefficient is extracted. Appreciation tier determination is a crucial step in premium coefficient calculation, mapping continuous changes to discrete appreciation levels. The determination process sets multiple threshold ranges, typically divided into 5-7 tiers, each corresponding to a different appreciation coefficient. when At that time, gear coefficient (Significant temperature drop); when At that time, gear coefficient (Slight temperature drop); when At that time, gear coefficient (Maintain stability); when At that time, gear coefficient (Slight temperature rise); when At that time, gear coefficient (Significant temperature rise); in, and The low and high thresholds are determined based on historical data statistics. This multi-level judgment mechanism enables the system to respond precisely to market changes, capturing significant shifts without overreacting to minor fluctuations. The extracted value-added tier coefficients provide adjustment ranges for the premium coefficient calculation, directly impacting asset valuation.

[0097] The premium coefficient is generated by multiplying the tiered value coefficient by the initial value coefficient and then adding a size adjustment factor based on the number of interacting customers. The premium coefficient is a dynamic assessment of the digital asset's market value, reflecting the asset's current appreciation potential. The calculation formula is as follows: ; in, This is the premium factor. This is the initial value of the increment coefficient. This is the gear ratio coefficient. Based on the number of interactive guests The scale correction function is usually defined as , For adjustment coefficients, This is the baseline number of users.

[0098] This formula achieves a dynamic fusion of initial expectations and market feedback: the initial value provides a benchmark expectation, the tier coefficient reflects short-term trend adjustments, and the scale correction factor considers the network effect brought about by the user group size. A premium coefficient greater than 1 indicates asset appreciation, equal to 1 indicates stable value, and less than 1 indicates depreciation. The generated premium coefficient provides a scientific pricing basis for asset transfers, guiding the system to assess the current market value of digital assets.

[0099] In this embodiment of the invention, when a new guest's purchase intention for furniture is detected to be higher than a preset threshold, a notification of asset transfer premium is sent to the original guest holding digital assets, and a digital asset bidding transaction channel is constructed between the original guest and the new guest. The detailed implementation steps include: The system monitors the purchase intention intensity value of new guests for each furniture item in the purchase intention intensity matrix in real time. Intention intensity monitoring is a prerequisite for triggering the transfer process, ensuring the activation of dormant assets at the optimal time. The monitoring process continuously tracks the interaction behavior of new guests, updates the purchase intention intensity matrix in real time, and assesses the user's purchase tendency for each furniture item. Data collection employs multi-sensor fusion technology, integrating eye tracking, gesture recognition, and dwell time analysis to comprehensively capture user interest signals. Intensity calculation uses a real-time weighted algorithm, giving higher weight to newly generated interactions to ensure the timeliness of the assessment. The monitoring mechanism provides real-time judgment criteria for triggering transfers, ensuring the system can capture the optimal time for transfer.

[0100] When a new customer's purchase intention for a particular furniture item exceeds a preset threshold, the asset ownership database is queried to identify the original customer who holds the digital asset. Confirming the asset holder is a crucial step in initiating the transfer process, identifying potential sellers. The query process accesses the system's asset ownership database, retrieving the furniture item's unique identifier to determine its current digital asset ownership record. The database query employs an efficient index structure to ensure rapid response even in large-scale user scenarios. The query results return the current asset holder's identity and contact information, providing targeted information for subsequent notifications. The confirmed holder identity provides the transaction entity for the transfer process and is a prerequisite for establishing a transaction channel.

[0101] The current market valuation of a digital asset is calculated based on the premium factor. Market valuation is the fundamental data for transfer pricing, providing a reference price for the asset's current value. The calculation formula is as follows: ; in, Based on current market valuation, The initial subscription price for the assets. This represents the current premium coefficient.

[0102] This formula achieves dynamic asset valuation by multiplying the initial price by a premium factor, reflecting the impact of market changes on prices. The valuation calculation considers the time value of money, applying appropriate time discounting to long-term held assets to reflect changes in value over the remaining useful life. The calculated market valuation provides a benchmark price for premium indications and is core data for conveying the value of asset transfers.

[0103] The system generates a transfer premium alert message containing the current market valuation and potential premium space, and pushes it to the communication account corresponding to the original resident's identity. The premium alert is key information for activating the willingness to transfer assets, showcasing the current transfer opportunity and potential returns to the holder. The generation process is based on market valuation and the strength of new user intent, constructing personalized alert content that highlights the potential returns and timing advantages of the transfer. The alert design employs behavioral economics principles, utilizing psychological effects such as loss aversion and opportunity cost to enhance the persuasiveness and appeal of the information. The push notification uses a multi-channel collaborative strategy, selecting the most appropriate communication method based on user preferences, such as app notifications, SMS, and email, to ensure effective information delivery. The pushed premium alert provides key information for the holder's decision-making, stimulating the willingness to transfer and initiating the seller's participation process.

[0104] Within an AR scene, a digital asset bidding interface is rendered for new guests, while simultaneously opening an asset transfer interface for existing guests. The bidding interface serves as the user-end entry point for the transaction channel, providing an interactive platform for both buyers and sellers. The rendering process is based on a pre-set transaction interface template, creating a spatially rich bidding area within the AR environment. The interface design highlights the digital rights information of the furniture object, including the remaining usage time, remaining transfer count, and historical appreciation data, helping buyers assess asset value. Operational elements are designed with AR interaction characteristics in mind, supporting gestures and voice commands, and providing intuitive price adjustment controls and confirmation mechanisms. Simultaneously, the system opens a corresponding transfer interface for existing guests, offering functions such as setting a reserve price, viewing bids, and confirming the transaction. Real-time synchronization technology is used for rendering both interfaces, ensuring the immediate updating and consistency of transaction data. The rendered transaction interface provides an interactive medium for the bidding channel, effectively connecting buyers and sellers.

[0105] A real-time data synchronization channel is established between the bidding interface for new customers and the asset transfer interface for existing customers, serving as the digital asset bidding and trading channel. This data synchronization channel is a core component of the trading system, ensuring the real-time transmission and consistency maintenance of transaction information. The establishment process employs secure peer-to-peer communication technology to create an encrypted data channel between buyers and sellers. The channel design utilizes an event-driven architecture; any operational change by either party immediately triggers data synchronization, achieving millisecond-level state updates. The synchronization mechanism includes full transaction processing capabilities, ensuring data consistency and integrity during the transaction process and preventing data loss or asynchrony. Channel security employs multi-layered protection, including data encryption, authentication, and operational auditing, guaranteeing the security and reliability of the transaction process. The established trading channel provides the data environment for calculating the optimal transaction price, supporting the system's real-time processing of transaction information and facilitating the final transaction.

[0106] In this embodiment of the invention, the detailed implementation steps for dynamically calculating the optimal transaction price for asset transfer based on the bidding sequence and time decay factor in the digital asset auction trading channel include: This system collects historical bid records submitted by new participants in the digital asset auction trading channel and constructs a bid sequence in chronological order. The bid sequence is a time-based representation of the trading dynamics, reflecting the bidding behavior patterns and price acceptance levels of new participants. The collection process involves real-time acquisition of each new participant's bid information through the digital asset auction trading channel's data interface, including the bid amount, bid timestamp, and bid validity status. To ensure data integrity, the system employs multi-level caching technology to guarantee the reliability of bid records even under network fluctuations; simultaneously, blockchain technology is used to record each bid, ensuring the immutability of transaction data. The bid sequence, arranged chronologically, forms a complete trajectory reflecting the evolution of new participants' bids, providing a foundational dataset for subsequent analysis. This time-series data collection method captures the dynamic behavior during the bidding process, helping to accurately predict users' bidding intentions and price ceilings.

[0107] Calculate the price increment between adjacent bids in the bid sequence and extract the mean of the price increments. Price increment analysis is a key step in understanding bidding behavior patterns. By quantifying the magnitude of changes between consecutive bids, it reveals the price sensitivity and psychological expectations of new customers. The calculation process first preprocesses the bid sequence to remove invalid bids and outliers to ensure data quality; then, it calculates the difference between adjacent valid bids to form the price increment sequence.

[0108] Price increment sequences typically exhibit a decreasing trend, reflecting increased bidding caution as prices approach their psychological upper limit. A weighted average method is used to calculate the mean of the price increment sequence, giving higher weight to the most recent bid increments to better reflect the current bidding state. The mean price increment is a quantitative expression of bidding momentum, providing a key parameter for predicting the upper limit of bids.

[0109] Based on the average price increment, predict the upper limit of new customers' bids. Predicting the upper limit of bids is a core technique for seizing trading opportunities, inferring the psychological price threshold of new customers through historical bidding behavior patterns. The prediction model is based on the assumption of decreasing increments, meaning that as the bid approaches the psychological upper limit, the increment gradually decreases. The model design considers the principles of price psychology, combining the average price increment with the latest bid to construct a prediction function. The prediction formula is: ; in, This is the predicted upper limit of the bid. This is the latest bid. The average price increment. For the number of bids already placed, It is a decreasing factor (usually taken as 0.15-0.25).

[0110] This model can accurately estimate the upper limit of a new customer's psychological price based on limited historical bidding data, providing a reference benchmark for determining the subsequent transaction price. The model's innovation lies in introducing an exponentially decreasing factor for the number of bids, which accurately captures the non-linear characteristics of bidding behavior and improves prediction accuracy.

[0111] The time difference between the moment a new bidder submits their first bid and the current time is recorded as the bidding duration. Bidding duration is a time-based measure of trading momentum, reflecting the urgency of the transaction and the decision-making speed of both parties. The recording process uses high-precision timestamp comparison to calculate the exact time interval from the moment a new bidder submits their first bid to the current system time. Time calculations take into account factors such as different time zones and daylight saving time to ensure global consistency and accuracy. Bidding duration is an input variable to the time decay function, directly affecting the dynamic adjustment of the transaction price. The introduction of this time dimension allows the trading mechanism to dynamically adjust its strategy based on the passage of time, balancing trading efficiency with price optimization.

[0112] A time decay function is constructed, whose output is a decay factor that decreases as the bidding duration increases. The time decay function is a mathematical expression of the timeliness of a transaction, quantifying the impact of time passage on the transaction value. The function design is based on the principle of diminishing marginal utility; as the bidding time lengthens, the urgency and expected value of the transaction gradually decrease. The function form employs an exponential decay model, which smoothly reflects the non-linear changes in value over time. The function expression is: ; in, The time decay factor, For the duration of the bidding, The preset base duration (usually 24 hours or the system's preset trading cycle). This is the decay rate parameter (usually taken as 0.5-1.5).

[0113] The decay rate parameter λ can be dynamically adjusted according to the market activity of different furniture categories. Popular categories use a higher λ value to reflect their faster transaction pace, while less popular categories use a lower λ value to allow for a longer transaction window. This adaptive time value of money assessment mechanism enables the system to maintain optimal transaction efficiency under different market conditions.

[0114] Multiplying the bid ceiling by a decay factor yields the time-adjusted price expectation. The price expectation is a comprehensive assessment of both time and price dimensions, balancing the dual objectives of price maximization and timely execution through a time-adjustment mechanism. The calculation process combines the predicted static bid ceiling with dynamic time factors to generate a dynamically adjusted price expectation over time. This time-adjustment mechanism allows the system to promote trades by lowering the price expectation even during prolonged periods of no trades. The time-adjusted price expectation provides a flexible reference standard for determining the final transaction price, considering both price maximization and timeliness requirements, demonstrating the system's trading intelligence.

[0115] When a new guest's current bid is not lower than the original guest's reserve price, and the difference between the current bid and the expected price is less than a preset difference threshold, the current bid is taken as the optimal transaction price. This is the core logic for automatic transaction completion, ensuring a balance of interests between the two parties through multi-condition joint evaluation. The determination process first confirms the basic condition—the bid must be higher than the reserve price to protect the original guest's basic rights; then it evaluates the degree of optimization of the bid, judging whether it is close to the theoretical optimal point by the difference from the expected value. The preset difference threshold is usually set at 5%-10% of the expected value, providing reasonable flexibility for the transaction. When both conditions are met, the system automatically confirms the current bid as the optimal transaction price, completing the transaction immediately and maximizing transaction efficiency. This multi-dimensional evaluation mechanism avoids one-sided decisions based solely on price or time, providing more comprehensive intelligent support for transactions.

[0116] If the above conditions are not met within the preset bidding period, the optimal transaction price is calculated based on the weighted average of the reserve price and the highest bid from the new customer. The weighting coefficient is determined by the ratio of the length of the bidding sequence to the duration of the bidding. This is an intelligent mechanism for handling transaction timeouts, ensuring that the system can still provide a reasonable transaction solution even if ideal conditions are not met. The preset bidding period is typically 3-7 days, representing the longest waiting time for the system to force a transaction decision. When the time limit is reached, the system no longer waits for better bids but instead makes the best estimate based on existing data. The optimal transaction price is calculated using a weighted average method: ; in, This is the optimal transaction price. The highest bid for a new guest. The base price set for existing guests, These are the weighting coefficients.

[0117] The determination of the weighting coefficient w is the innovative aspect of this mechanism. It is dynamically adjusted based on bidding activity (the ratio of the bid sequence length to the bidding duration), and the calculation formula is as follows: ; in, The length of the bid sequence. The duration of the bidding (in hours). To adjust the parameters (usually taken as 0.5-1).

[0118] This dynamic weighting mechanism ensures that when bidding is active, the final price is closer to the bid of new guests, reflecting strong market demand; while when bidding is sparse, the price is closer to the reserve price of existing guests, reflecting weaker market appeal. This mechanism ensures a relatively fair transaction outcome under various market conditions, maximizing the system's transaction completion rate and user satisfaction.

[0119] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0120] It should be noted that all formulas in this manual are calculated by removing dimensions and taking their numerical values. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0121] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A customized furniture marketing and ordering system integrating AR scenarios, characterized in that: include: The data acquisition module is used to acquire user interaction trajectory data and visual dwell data of furniture objects in AR scenes; The intention assessment module is used to construct a micro-interest decay curve for furniture objects based on the interaction trajectory data and the visual dwell data, and generate a purchase intention intensity matrix based on the inflection point distribution of the micro-interest decay curve. The path analysis module is used to collect characteristic data of user operation interruption events in AR scenes, identify transaction path break nodes, and calculate the conversion resistance index of each transaction path break node. The graph generation module is used to generate a seamless transaction trigger point map based on the conversion resistance index and the purchase intention strength matrix. The element rendering module is used to dynamically render transaction guide elements at the locations marked on the seamless transaction trigger point bitmap; The fluctuation monitoring module is used to monitor the user's response delay time and interaction completion rate to the transaction guidance elements, and to identify the fluctuation characteristics of the user's real-time transaction intention. The mapping model construction module is used to construct a digital asset mapping model for furniture objects based on the fluctuation characteristics of the real-time transaction intentions, and to transform the physical attributes of furniture into digital rights parameters including the duration of the right to use, the upper limit of the number of transfers, and the appreciation coefficient. The transaction option generation module is used to generate hybrid transaction options for hotel guests based on the digital asset mapping model. The digital asset binding module is used to bind the digital asset of the furniture object to the guest's identity identifier after the guest selects the digital asset subscription channel and completes the subscription. The premium calculation module is used to collect AR interaction data of subsequent guests on the same furniture object in real time, and calculate the premium coefficient of the digital asset based on the density change of the AR interaction data. The transaction channel construction module is used to push an asset transfer premium prompt to the original guest holding the digital asset when it is detected that the purchase intention of a new guest for the furniture object is higher than a preset threshold, and to construct a digital asset bidding transaction channel between the original guest and the new guest. The integrated output module is used to dynamically calculate the optimal transaction price for asset transfer based on the bidding sequence and time decay factor in the digital asset auction trading channel.

2. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, The interaction trajectory data includes gesture trigger sequence, view rotation trajectory, and spatial movement path; The process of constructing a micro-interest decay curve for furniture objects and generating a purchase intention intensity matrix based on the inflection point distribution of the micro-interest decay curve includes: The gaze duration of each furniture object in the visual persistence data is decomposed into a time series to extract the trend component and fluctuation component of the gaze duration. Calculate the first derivative of the trend component, and mark the negative range of the first derivative as the interest decay range; The rate of change of gesture trigger frequency in the interaction trajectory data within the interest decay interval is statistically analyzed. When the rate of change shows a positive abrupt change, that moment is marked as the interest decay inflection point. With time as the horizontal axis and the normalized value of the trend component as the vertical axis, connect the starting point of the interest decay interval, the inflection point of interest decay, and the ending point of the interest decay interval to construct the micro-interest decay curve of the furniture object. Extract the time position and curve slope of all interest decay inflection points in the micro-interest decay curve, and construct an inflection point distribution feature vector; Calculate the interest recovery coefficient of the furniture object based on the inflection point distribution feature vector; The product of the interest recovery ability coefficient and the total duration of visual dwell time is used as the initial value of the purchase intention intensity for the furniture object; the initial value of the purchase intention intensity is then weighted by spatial location. The weighted purchase intention intensity values ​​are filled into a two-dimensional matrix structure according to the category and spatial distribution of furniture objects to generate the purchase intention intensity matrix.

3. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, The operation interruption event feature data includes the interaction depth before the interruption, the interface hierarchy at the time of the interruption, and the return frequency after the interruption. The process of identifying transaction path breakpoints and calculating the conversion resistance index for each breakpoint includes: Arrange the operation interruption event feature data in chronological order to construct a user operation event chain; Extract the number of operation steps between two consecutive interrupt events in the user operation event chain, and denot it as the interrupt interval step size; The interruption events with an interruption interval step size less than a preset step size threshold are counted, and the corresponding interface levels are marked as high-frequency interruption levels. The interaction complexity of the high-frequency fracture level is evaluated, and the ratio of the user's return frequency to the interaction complexity is calculated and denoted as the fracture sensitivity. The interface level with a break sensitivity greater than a preset sensitivity threshold is determined as the break node of the transaction path; Based on the interaction depth before the interruption of the transaction path breakpoint, a depth decay function is constructed, and the product of the function value of the depth decay function at the breakpoint and the break sensitivity is used as the conversion resistance index.

4. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, The process of generating a seamless transaction trigger point map based on the conversion resistance index and the purchase intention strength matrix includes: Based on the purchase intention strength matrix, extract the top N furniture objects with the highest purchase intention strength values, and denote them as the set of high-intention furniture. In the 3D spatial model of the AR scene, mark the geometric center coordinates of each furniture object in the set of highly intended furniture; Candidate transaction trigger points are set at a preset distance from the furniture surface along the normal vector of the user's line of sight; the shortest path length between the candidate transaction trigger points and the transaction path breakpoint in the operation flowchart is calculated; The priority weights of the candidate transaction trigger points are calculated based on the shortest path length and the reciprocal of the conversion resistance index; the priority weights are corrected for visual occlusion, and the top M candidate transaction trigger points with the highest corrected priority weights are selected. Based on the average occurrence time of the transaction path breakpoints, a trigger time window is assigned to each trigger point. The spatial coordinates of the trigger point, the trigger time window, and the corresponding furniture object identifier are integrated into the seamless transaction trigger point map.

5. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, The dynamically rendered transaction guidance elements include: Based on the seamless transaction trigger point map, it is detected in real time whether the user's perspective enters the trigger time window; When the user's perspective enters the trigger time window, the 3D model of the transaction guidance element is initialized at the spatial coordinates of the transaction trigger point; Read the current purchase intention strength value of the corresponding furniture object in the purchase intention strength matrix in real time; Calculate the base transparency of the transaction guidance element based on the current purchase intention strength value; The interaction trajectory data is differentiated in real time to obtain the user's gesture acceleration vector; When the gesture acceleration vector points to the transaction guidance element, the base transparency is multiplied by the attention enhancement factor to generate dynamic transparency; Based on the dynamic transparency and the current purchase intention strength value, the rendering parameters and color scheme of the transaction guidance element are adjusted, and the adjusted transaction guidance element is rendered into the AR scene.

6. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, The identification of users' real-time transaction intention fluctuation characteristics includes: Record the moment when the user's gaze first touches the transaction guidance element and the moment when the user performs the first touch operation, and calculate the time difference between the two as the response delay time; The transaction guidance element is designed as a multi-step interactive process. The number of micro-interaction tasks completed by the user is counted, and the ratio of the number of completed tasks to the total number of tasks is calculated as the interaction completion rate. Construct a two-dimensional feature space with the response delay time as the horizontal axis and the interaction completion degree as the vertical axis; In the two-dimensional feature space, according to the preset intention fluctuation classification rules, the user state is divided into the hesitant and observing zone, the quick decision-making zone, the in-depth exploration zone, and the churn warning zone; Extract the user's trajectory movement direction in the two-dimensional feature space, and mark the upward and downward fluctuations of intention; The time sequence of the upward and downward fluctuations in trading intentions is combined to form the instantaneous trading intention fluctuation characteristic.

7. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, The digital asset mapping model for constructing furniture objects includes: Obtain the physical attribute data of the furniture object, including material grade, design style tag, manufacturing cost, and market scarcity. The market popularity index of the furniture object is calculated based on the cumulative number of upward fluctuations in the instant transaction willingness fluctuation characteristics. The fundamental value anchor of the digital asset is determined based on the product of the market popularity index and the market scarcity. Map the underlying value anchor point to an initial value for the duration of the right of use; Based on the physical attribute data, calculate the durability score and popularity score of the furniture object; Based on the durability score, a maximum number of transfers of the digital asset is set; Based on the weighted sum of the popularity score and the market heat index, a value-added potential function is constructed, and the initial value of the value-added coefficient is output. The duration of the right of use, the maximum number of transfers, and the initial value of the value-added coefficient are encapsulated as the digital rights parameters; Establish a mapping relationship between the physical attribute data and the digital rights parameters, and construct the mapping relationship into the digital asset mapping model.

8. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, The calculation of the premium coefficient of the digital asset based on the density change of the AR interactive data includes: Record the AR interaction behavior of each new guest with the furniture objects in the room and generate an interaction behavior log; Cluster analysis is performed on the interaction behavior logs to identify high-frequency interaction time periods and calculate the duration percentage of high-frequency interaction time periods. The number of different guests who interact with the same furniture object within a preset statistical period is recorded as the base number of interacting guests. The product of the number of interactive guests and the percentage of time spent is used as the density of AR interactive data. The density of the current statistical period is compared with the density of the previous statistical period to obtain the change in density. Based on the preset asset appreciation triggering rules, determine the threshold range to which the density change belongs, and extract the corresponding appreciation level coefficient. The premium coefficient is generated by multiplying the value-added tier coefficient by the initial value-added coefficient and adding a scale correction factor based on the number of interactive guests.

9. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, When a new guest's purchase intention for the furniture is detected to be higher than a preset threshold, an asset transfer premium notification is sent to the original guest holding the digital asset, and a digital asset bidding transaction channel is established between the original guest and the new guest, including: Real-time monitoring of the purchase intention intensity value of new guests corresponding to each furniture object in the purchase intention intensity matrix; When the purchase intention intensity of a new customer for a certain furniture item exceeds a preset threshold, the asset equity database is queried to determine the original customer identity of the current holder of the digital asset of that furniture item. Calculate the current market valuation of the digital asset based on the premium coefficient; Generate a transfer premium notification message containing the current market valuation and potential premium space, and push it to the communication account corresponding to the original resident's identity identifier; Render a digital asset bidding interface for the new guest in the AR scene, and simultaneously open an asset transfer operation interface for the original guest. A real-time data synchronization channel is established between the bidding interface of the new guest and the asset transfer operation interface of the original guest, serving as the bidding transaction channel for the digital asset.

10. The customized furniture marketing and ordering system integrating AR scenes according to claim 1, characterized in that, The process of dynamically calculating the optimal transaction price for asset transfer based on the bidding sequence and time decay factor in the digital asset auction trading channel includes: Collect historical bid records submitted by new guests in the digital asset auction trading channel and construct a bid sequence in chronological order; Calculate the price increment between adjacent bids in the bidding sequence, and extract the mean of the price increments; Based on the average of the price increments, predict the upper limit of the bid for the new guests; Record the time difference between the moment the new guest makes their first bid and the current moment, and denote it as the bidding duration; Construct a time decay function, the output of which is a decay factor that decreases as the duration of the bidding increases; Multiply the upper limit of the bid by the decay factor to obtain the time-corrected expected price value; When the new guest's current bid is not lower than the base price set by the original guest, and the difference between the current bid and the expected price is less than a preset difference threshold, the current bid will be taken as the optimal transaction price. If the above conditions are not met within the preset bidding time limit, the optimal transaction price is calculated based on the weighted average of the reserve price and the highest bid from the new customer.

Images