An e-commerce platform UI generation method and system supporting personalized interface customization

Abstract

The application discloses an e-commerce platform UI generation method and system supporting personalized interface customization, and relates to the technical field of e-commerce interface customization. The method comprises the following steps: step one, collecting active setting data sets and passive behavior data sets of e-commerce platform users, and preprocessing; step two, converting the preprocessed active setting data sets into structured UI basic parameters to form a UI basic scheme; meanwhile, comprehensively analyzing the preprocessed passive behavior data sets to obtain evaluation adjustment values; step three, based on the UI basic scheme and the evaluation adjustment values. The application constructs a UI basic scheme based on user active settings, generates evaluation adjustment values by combining user behavior preferences, optimizes and quantitatively screens potential UI schemes, simultaneously realizes dynamic evolution of the UI scheme, solves the problems of traditional e-commerce UI customization, such as staticization and inability to fit real-time use habits of users, and realizes personalized customization and continuous dynamic adaptation of e-commerce UI.

Description

Technical Field

[0001] This invention relates to the field of e-commerce interface customization technology, specifically to a method and system for generating e-commerce platform UIs that supports personalized interface customization. Background Technology

[0002] Currently, most e-commerce platform UI personalization is a one-time user-initiated setting mode. Once the UI design is generated, it remains fixed and cannot be dynamically adjusted according to the user's subsequent usage behavior and preferences. This makes it difficult to continuously adapt to the user's usage habits, resulting in a gradual decline in interface adaptability over time. Consequently, it fails to meet users' actual needs for personalized and dynamic interfaces. Therefore, this paper proposes a UI generation method and system for e-commerce platforms that supports personalized interface customization to solve these problems. Summary of the Invention

[0003] Technical problems to be solved To address the shortcomings of existing technologies, this invention provides a method and system for generating UI for e-commerce platforms that supports personalized interface customization, thus solving the problems mentioned in the background section.

[0004] Technical solution To achieve the above objectives, the present invention provides the following technical solution: a method for generating UI for an e-commerce platform that supports personalized interface customization, comprising the following steps: Step 1: Collect active settings and passive behavior datasets from e-commerce platform users and preprocess them; Step 2: Transform the preprocessed active setting dataset into structured UI basic parameters to form a basic UI scheme; at the same time, conduct a comprehensive analysis of the preprocessed passive behavior dataset to obtain evaluation and adjustment values; Step 3: Based on the basic UI design and the evaluation adjustment value, generate several potential UI designs that meet the constraints of the basic design; perform a comprehensive analysis on each potential UI design to obtain the comprehensive evaluation value corresponding to each potential UI design; sort all potential UI designs according to the comprehensive evaluation value, select the optimal UI design with the highest comprehensive evaluation value, and generate it. Step 4: Synchronize the generated optimal UI solution to all e-commerce platform terminals bound to the user, continuously collect and preprocess the passive behavior dataset of the user using the optimal UI solution, and continuously fine-tune the optimal UI solution to realize the dynamic evolution of the UI solution according to the user's usage habits.

[0005] Preferably, the actively configured dataset includes: theme color data, layout structure data, and component style data; The passive behavior dataset includes: operational behavior data, preference feedback behavior data, and scenario behavior data.

[0006] Preferably, the specific steps for forming the basic UI solution are as follows: The preprocessed active setup dataset is subjected to structured parsing, which transforms the user's visual operation instructions into standardized data that the system can recognize. Standardized data is integrated to form a basic UI solution; This basic UI design serves as a hard constraint for subsequent UI design adjustments; all subsequent UI design adjustments must not deviate from the data range of this basic UI design.

[0007] Preferably, the specific steps for obtaining the evaluation adjustment value are as follows: The preprocessed passive behavior dataset is cleaned to remove all invalid data that is not from actual user operations, and retain the valid behavior data. Feature extraction is performed on the cleaned and effective behavioral data to extract user behavior preference features corresponding to the basic UI parameters; The extracted behavioral preference features are dynamically weighted, and a dual weighting mechanism combining time decay weight and behavioral importance weight is adopted to assign corresponding weights to behavioral preference features of different times and types. The adjusted evaluation value is obtained based on the weighted behavioral preference characteristics.

[0008] Preferably, the specific steps for generating several potential UI schemes that conform to the constraints of the basic scheme are as follows: Using the data from various dimensions of the basic UI design and the corresponding evaluation and adjustment values ​​as input, several potential UI designs that do not deviate from the constraints of the basic UI design are generated.

[0009] Preferably, the specific steps for obtaining the comprehensive evaluation value corresponding to each potential UI solution are as follows: Using the adaptability of the basic UI solution and the matching degree of the evaluation adjustment value as calculation indicators, a comprehensive analysis is conducted on each potential UI solution to obtain the comprehensive evaluation value corresponding to each potential UI solution.

[0010] Preferably, the specific steps for selecting and generating the optimal UI solution with the highest comprehensive evaluation value are as follows: Sort all potential UI designs from highest to lowest based on their overall evaluation score; select the potential UI design with the highest overall evaluation score to generate the optimal UI design.

[0011] Preferably, the importance weight of the behavior is preset with a fixed weight value based on the priority of the e-commerce operation; the e-commerce operation includes product search operation, product addition to shopping cart operation, and product order payment operation; the time decay weight is calculated using an exponential decay function.

[0012] A UI generation system for e-commerce platforms that supports personalized interface customization, comprising: The preprocessing module is used to collect and preprocess the active settings and passive behavior datasets of e-commerce platform users. The UI evaluation generation module is used to transform the preprocessed active setting dataset into structured UI basic parameters to form a basic UI scheme. At the same time, it performs a comprehensive analysis on the preprocessed passive behavior dataset to obtain evaluation adjustment values. The optimal UI generation module is used to generate several potential UI schemes that meet the constraints of the basic UI scheme based on the basic UI scheme and the evaluation adjustment value. It performs a comprehensive analysis on each potential UI scheme to obtain the comprehensive evaluation value corresponding to each potential UI scheme. It sorts all potential UI schemes according to the comprehensive evaluation value, selects the optimal UI scheme with the highest comprehensive evaluation value, and generates it. The synchronous evolution module is used to synchronize the generated optimal UI design to all e-commerce platform terminals bound to the user, continuously collect and preprocess the passive behavior dataset of the user using the optimal UI design, and continuously fine-tune the optimal UI design to realize the dynamic evolution of the UI design according to the user's usage habits.

[0013] Beneficial effects The present invention has the following beneficial effects: This invention relates to a method and system for generating UI for e-commerce platforms that supports personalized interface customization. By constructing a basic UI scheme based on user-initiated settings, and combining user behavior preferences to generate evaluation and adjustment values ​​to optimize and quantitatively screen potential UI schemes, it also enables the dynamic evolution of UI schemes. This solves the problems of static customization in traditional e-commerce UIs, which cannot adapt to users' real-time usage habits, and achieves personalized customization and continuous dynamic adaptation of e-commerce UIs.

[0014] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0015] Figure 1 This is a flowchart of a method and system for generating UI for an e-commerce platform that supports personalized interface customization, according to the present invention. Figure 2 This is a structural diagram of an e-commerce platform UI generation system that supports personalized interface customization according to the present invention. Detailed Implementation

[0016] 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.

[0017] This invention provides a technical solution: a method and system for generating UI for e-commerce platforms that supports personalized interface customization, such as... Figure 1 As shown, it includes the following steps: Step 1: Collect active settings data and passive behavior data from e-commerce platform users, and preprocess them.

[0018] The active setting dataset includes theme color data, layout structure data, and component style data; the passive behavior dataset includes operation behavior data, preference feedback behavior data, and scene behavior data. The active setting dataset is collected through the e-commerce platform's front-end visual interactive settings interface, representing the raw data corresponding to personalized configuration commands actively triggered by the user. The theme color data collects the user-selected interface primary color, secondary color, and text color value encoding; the layout structure data collects the user-selected interface module arrangement, module proportion, and display priority; and the component style data collects the visual style parameters of user-selected interface components such as buttons, input boxes, and cards. The passive behavior dataset is collected seamlessly through the e-commerce platform's backend full-link behavior tracking system, providing raw data on users' operational trajectories within the platform. The operation behavior data includes user actions such as clicking, swiping, searching, adding to cart, and paying, as well as the corresponding operation objects. The preference feedback behavior data includes user feedback actions such as collecting, liking, and negative reviews of products and interface modules. The scenario behavior data includes environmental data related to user operation time, login terminal, and operation scenario.

[0019] Preprocessing involves sequentially cleaning the two datasets by removing outlier data, filling in missing data, and deduplicating duplicate data. Then, unstructured text, color values, and operation trajectory data are converted into structured digital coded data that the system can recognize, thus completing the standardization and unification of the datasets. After standardization, all data values ​​are mapped to the range of 0-1 to ensure consistency in subsequent data parsing and calculation.

[0020] Step 2: Transform the preprocessed active setting dataset into structured UI basic parameters to form a basic UI scheme; Simultaneously, a comprehensive analysis of the preprocessed passive behavior dataset was conducted to obtain evaluation adjustment values.

[0021] The specific process of forming the UI basic scheme is as follows: the preprocessed active setting dataset is structured and parsed to convert the user's visual operation instructions into standardized data that the system can recognize. The standardized data is then integrated according to the interface module dimension to form a UI basic scheme that includes parameters of all dimensions such as theme color, layout structure, and component style. This UI basic scheme serves as a hard constraint for subsequent UI scheme adjustments, and all subsequent UI scheme adjustments will not deviate from the data range of this UI basic scheme.

[0022] The specific process for obtaining the evaluation adjustment value is as follows: cleaning the preprocessed passive behavior dataset, removing all invalid data that is not real user operation, and retaining the valid behavior data; extracting features from the cleaned valid behavior data, and refining the user behavior preference features corresponding to the UI basic parameters. The extracted behavioral preference features are dynamically weighted using a dual-weighting mechanism combining time decay weighting and behavioral importance weighting. Corresponding weights are assigned to behavioral preference features of different times and types. Based on the weighted behavioral preference features, an evaluation adjustment value is obtained. Specifically, the behavioral importance weighting has a fixed preset weight value based on the priority of e-commerce operations, while differentiated base weights are set for different core e-commerce operations. The time decay weighting is calculated using an exponential decay function, setting differentiated weights based on the time elapsed since the user's behavior occurred, highlighting the reference value of recent behaviors. The time decay weight is obtained as follows: In the formula, S is the time decay weight, r is the initial weight coefficient of the behavior, t is the time decay coefficient, and y is the time decay index. r is the base weight of the behavior feature, which is uniformly preset to a fixed value of 1; t is calculated based on the ratio of the duration of the behavior to the preset statistical period, and its value ranges from 0 to 1; y is the time decay rate adjustment index, which is preset to a fixed value of 2 and is used to adjust the rate at which the behavior weight decays over time.

[0023] The final weight of the behavioral feature is obtained by combining the importance weight of the behavior and the time decay weight. The two types of weights are set with a proportion coefficient, and the comprehensive weight value is obtained by merging them according to the proportion. The final weights of behavioral features are obtained as follows: In the formula, W is the final weight of the behavioral feature, u is the time decay weight ratio coefficient, o is the calculated value of the time decay weight, p is the behavioral importance weight ratio coefficient, and i is the base value of the behavioral importance weight. u and p are complementary coefficients, and their sum is 1. The ratio of the two types of weights can be flexibly adjusted according to the platform's operational needs. o is the result value calculated by the above time decay weight formula. i is the preset base value of the behavioral importance weight corresponding to the e-commerce operation behavior.

[0024] The final weight of the behavioral features is used to calculate the weighted value of the user's behavioral preference features to obtain the evaluation adjustment value. The assessment adjustment values ​​are obtained in the following ways: In the formula, K is the evaluation adjustment value. Assigning importance weight to product search behavior. Weight the importance of adding items to the shopping cart action. Weighting the importance of the order placement and payment process for goods. Quantify the characteristics of product search behavior preferences. Quantify the characteristics of preferences for adding items to the shopping cart. Quantification of preferences for order placement and payment behavior. , , The three values ​​are preset to a fixed weight value, and their sum is 1. This is a standardized result based on characteristics such as the frequency, duration, and keyword categories of user product searches. This is the result after standardizing the characteristics of users adding items to their cart, such as type, frequency, and quantity. The results are standardized based on the characteristics of user payment for goods, such as category, frequency, and amount. The values ​​of all three are in the range of 0-1.

[0025] Step 3: Based on the basic UI design and the evaluation adjustment value, generate several potential UI designs that meet the constraints of the basic design; perform a comprehensive analysis on each potential UI design to obtain the comprehensive evaluation value corresponding to each potential UI design; sort all potential UI designs according to the comprehensive evaluation value, select the optimal UI design with the highest comprehensive evaluation value, and generate it.

[0026] The specific process of generating several potential UI schemes that conform to the constraints of the basic scheme is as follows: taking the data of each dimension of the UI basic scheme and the corresponding evaluation adjustment value as the input basis, and taking the data range of the UI basic scheme as the constraint boundary, several potential UI schemes that do not deviate from the constraints of the UI basic scheme are generated through parameter iteration. During the iteration process, the adjustment range of each dimension parameter is quantitatively controlled by the evaluation adjustment value.

[0027] The specific process for obtaining the comprehensive evaluation value corresponding to each potential UI solution is as follows: the adaptability of the basic UI solution, the matching degree of the evaluation adjustment value, and the adaptability of e-commerce operation are used as the core calculation indicators. A fixed weight coefficient is preset for each indicator. Combining the quantitative value and weight coefficient of each indicator, a comprehensive analysis and calculation is performed on each potential UI solution to obtain the comprehensive evaluation value corresponding to each potential UI solution. The comprehensive evaluation value is obtained as follows: In the formula, M is the comprehensive evaluation value. The UI base solution adaptation weight coefficient, To evaluate the weighting coefficients for the matching degree of the adjusted values, Here, 'a' represents the weighting coefficient for e-commerce operation adaptability, 'b' represents the metric value for UI basic solution adaptability, 'c' represents the metric value for evaluation and adjustment value matching, and 'c' represents the quantified value for e-commerce operation adaptability. , , The three values ​​are 1, which are preset fixed weight coefficients. a is the standardized result of the dimensional parameter fit between the potential UI solution and the basic UI solution; b is the standardized result of the matching degree between the adjustment direction and magnitude of the potential UI solution and the evaluation adjustment value; c is the standardized result of the degree to which the potential UI solution conforms to the general operation logic and interface interaction habits of the e-commerce industry. The values ​​of the three values ​​are all in the range of 0-1.

[0028] The specific process of selecting and generating the optimal UI solution with the highest comprehensive evaluation value is as follows: using the comprehensive evaluation value as the sole sorting criterion, all potential UI solutions are sorted from high to low according to their comprehensive evaluation values ​​using a quick sorting algorithm, and the potential UI solution with the highest ranking is selected to complete the generation of the optimal UI solution.

[0029] Step 4: Synchronize the generated optimal UI solution to all e-commerce platform terminals bound to the user, continuously collect and preprocess the passive behavior dataset of the user using the optimal UI solution, and continuously fine-tune the optimal UI solution to realize the dynamic evolution of the UI solution according to the user's usage habits.

[0030] The optimal UI solution is transformed into UI configuration files adapted for each terminal through the cross-terminal synchronization interface of the e-commerce platform, and synchronized to all terminal devices such as mobile phones, tablets, and computers that users have bound to the platform, ensuring the consistency of the UI solution across all terminals. Continuous data collection involves collecting all passive behavior data of users during the process of using the optimal UI solution in a seamless and real-time manner through a background data tracking system. The collection frequency is synchronized with the user's operation actions, and the collected data is cleaned and standardized according to the preprocessing rules in step one. Continuous fine-tuning involves calculating the latest evaluation adjustment value from the preprocessed passive behavior data according to the rules in step two. Based on the latest evaluation adjustment value, small iterative adjustments are made to the parameters of each dimension of the optimal UI solution. The adjustment process always takes the original UI base solution as a hard constraint, so as to realize the dynamic and adaptive evolution of the UI solution according to the user's usage habits.

[0031] A UI generation system for e-commerce platforms that supports personalized interface customization, such as... Figure 2 As shown, it includes: The data acquisition and processing module is used to collect active setting datasets and passive behavior datasets from e-commerce platform users and to perform preprocessing. The UI evaluation module is used to transform the preprocessed active setting dataset into structured UI basic parameters to form a basic UI scheme. At the same time, it performs a comprehensive analysis on the preprocessed passive behavior dataset to obtain evaluation adjustment values. The optimal UI module is used to generate several potential UI schemes that meet the constraints of the basic UI scheme based on the basic UI scheme and the evaluation adjustment value. A comprehensive analysis is performed on each potential UI scheme to obtain a comprehensive evaluation value. The optimal UI scheme with the highest comprehensive evaluation value is selected and generated. The synchronous evolution module is used to synchronize the generated optimal UI design to all e-commerce platform terminals bound to the user, continuously collect and preprocess the passive behavior dataset of the user using the optimal UI design, and continuously fine-tune the optimal UI design to realize the dynamic evolution of the UI design according to the user's usage habits.

[0032] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0033] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for generating UI for an e-commerce platform that supports personalized interface customization, characterized in that, Includes the following steps: Step 1: Collect active settings and passive behavior datasets from e-commerce platform users and preprocess them; Step 2: Transform the preprocessed active setting dataset into structured UI basic parameters to form a basic UI scheme; Simultaneously, a comprehensive analysis of the preprocessed passive behavior dataset was performed to obtain evaluation adjustment values; Step 3: Based on the basic UI design and the evaluation adjustment values, generate several potential UI designs that meet the constraints of the basic design. A comprehensive analysis is performed on each potential UI solution to obtain a comprehensive evaluation value for each potential UI solution; all potential UI solutions are sorted according to their comprehensive evaluation values, and the optimal UI solution with the highest comprehensive evaluation value is selected and generated. Step 4: Synchronize the generated optimal UI solution to all e-commerce platform terminals bound to the user, continuously collect and preprocess the passive behavior dataset of the user using the optimal UI solution, and continuously fine-tune the optimal UI solution to realize the dynamic evolution of the UI solution according to the user's usage habits.

2. The e-commerce platform UI generation method supporting personalized interface customization according to claim 1, characterized in that, The actively configured dataset includes: theme color data, layout structure data, and component style data; The passive behavior dataset includes: operational behavior data, preference feedback behavior data, and scenario behavior data.

3. The e-commerce platform UI generation method supporting personalized interface customization according to claim 1, characterized in that, The specific steps for forming the basic UI solution are as follows: The preprocessed active setup dataset is subjected to structured parsing, which transforms the user's visual operation instructions into standardized data that the system can recognize. Standardized data is integrated to form a basic UI solution; This basic UI design serves as a hard constraint for subsequent UI design adjustments; all subsequent UI design adjustments must not deviate from the data range of this basic UI design.

4. The e-commerce platform UI generation method supporting personalized interface customization according to claim 1, characterized in that, The specific steps for obtaining the evaluation adjustment value are as follows: The preprocessed passive behavior dataset is cleaned to remove all invalid data that is not from actual user operations, and retain the valid behavior data. Feature extraction is performed on the cleaned and effective behavioral data to extract user behavior preference features corresponding to the basic UI parameters; The extracted behavioral preference features are dynamically weighted, and a dual weighting mechanism combining time decay weight and behavioral importance weight is adopted to assign corresponding weights to behavioral preference features of different times and types. The adjusted evaluation value is obtained based on the weighted behavioral preference characteristics.

5. The e-commerce platform UI generation method supporting personalized interface customization according to claim 1, characterized in that, The specific steps for generating several potential UI schemes that conform to the constraints of the basic scheme are as follows: Using the data from various dimensions of the basic UI design and the corresponding evaluation and adjustment values ​​as input, several potential UI designs that do not deviate from the constraints of the basic UI design are generated.

6. The e-commerce platform UI generation method supporting personalized interface customization according to claim 1, characterized in that, The specific steps for obtaining the comprehensive evaluation value corresponding to each potential UI solution are as follows: Using the adaptability of the basic UI solution and the matching degree of the evaluation adjustment value as calculation indicators, a comprehensive analysis is conducted on each potential UI solution to obtain the comprehensive evaluation value corresponding to each potential UI solution.

7. The e-commerce platform UI generation method supporting personalized interface customization according to claim 1, characterized in that, The specific steps for selecting and generating the optimal UI solution with the highest comprehensive evaluation value are as follows: Sort all potential UI designs from highest to lowest based on their overall evaluation score; select the potential UI design with the highest overall evaluation score to generate the optimal UI design.

8. The e-commerce platform UI generation method supporting personalized interface customization according to claim 4, characterized in that, The importance weight of the behavior is preset with a fixed weight value based on the priority of e-commerce operations; the e-commerce operations include product search, product addition to shopping cart, and product order payment; the time decay weight is calculated using an exponential decay function.

9. A UI generation system for e-commerce platforms supporting personalized interface customization, used to implement the e-commerce platform UI generation method supporting personalized interface customization as described in claim 1, characterized in that, include: The preprocessing module is used to collect and preprocess the active settings and passive behavior datasets of e-commerce platform users. The UI evaluation generation module is used to transform the preprocessed active setting dataset into structured UI basic parameters to form a basic UI scheme. At the same time, it performs a comprehensive analysis on the preprocessed passive behavior dataset to obtain evaluation adjustment values. The optimal UI generation module is used to generate several potential UI schemes that meet the constraints of the basic UI scheme based on the basic UI scheme and the evaluation adjustment value. It performs a comprehensive analysis on each potential UI scheme to obtain the comprehensive evaluation value corresponding to each potential UI scheme. It sorts all potential UI schemes according to the comprehensive evaluation value, selects the optimal UI scheme with the highest comprehensive evaluation value, and generates it. The synchronous evolution module is used to synchronize the generated optimal UI design to all e-commerce platform terminals bound to the user, continuously collect and preprocess the passive behavior dataset of the user using the optimal UI design, and continuously fine-tune the optimal UI design to realize the dynamic evolution of the UI design according to the user's usage habits.

Images