Multi-batch waterfall layout method and system fusing interest and visual balance

Abstract

The present application relates to a multi-batch waterfall layout method and system that fuses interest and visual balance, multiple interested data are divided into multiple interested data sets based on the respective data height and interest degree of the multiple interested data, and the priority of the multiple interested data sets is obtained, and subsequent waterfall adaptive layout optimization is performed on the multiple interested data sets in turn according to the priority, and the fitness function used in the optimization involves the interest score and the waterfall layout score. Through the division of the interested data set, the layout optimization of all interested data is avoided at one time, and the data processing amount is reduced; the data set division method based on the data height and the interest degree lays the foundation for subsequent priority pushing of the interested data with high interest degree and high page layout visual balance; the fitness function involves the interest score and the waterfall layout score, so that the user interest and the page layout visual balance of the interested data set in the front-end page are comprehensively optimal.

Description

Technical Field

[0001] The embodiments in this specification relate to the field of waterfall layout technology, specifically to a multi-batch waterfall layout method and system that integrates interest and visual balance. Background Technology

[0002] In today's internet information recommendation and display scenarios, the waterfall layout has become the mainstream display method for many content platforms due to its ability to efficiently utilize screen space and support infinite scrolling. However, existing waterfall layout schemes mainly adopt a relatively simple strategy: presenting data of interest one by one according to their level of interest, usually arranged from left to right and from top to bottom. While this traditional sequential arrangement ensures that highly interesting content is exposed first, the difference in height between different pieces of data can easily lead to uneven visual effects on the front-end page during actual rendering. This disrupts the balance of the page layout and may affect the user's browsing experience and interaction continuity.

[0003] Therefore, there is an urgent need for a waterfall-style adaptive layout method that can balance the accuracy of content recommendation with the visual balance of page layout. Summary of the Invention

[0004] This specification provides a multi-batch waterfall layout method and system that integrates interest and visual balance, and can take into account both the accuracy of content recommendation and the visual balance of page layout.

[0005] The technical solution is as follows:

[0006] Firstly, the embodiments of this specification provide a multi-batch waterfall layout method that integrates interest level and visual balance, including:

[0007] Obtain the data height and degree of interest for each of the multiple data points that the user is interested in;

[0008] Based on the data height and degree of interest of each of the multiple data points of interest, the data points of interest are divided into multiple datasets of interest, and the priority of the multiple datasets of interest is obtained;

[0009] Based on page layout constraints and the data height and degree of interest of each of the multiple data points of interest in the highest priority dataset, the waterfall flow adaptive layout scheme corresponding to the highest priority dataset of interest is obtained.

[0010] When the amount of data of interest that the user has viewed in the current priority dataset of interest reaches the preset condition, the adaptive layout scheme of the waterfall flow corresponding to the next priority dataset of interest is obtained by solving the following based on the page layout constraints, the bottom height of each column in the waterfall flow after the current priority dataset of interest is laid out with its corresponding waterfall flow adaptive layout scheme, and the data height and interest degree of each of the multiple data of interest in the next priority dataset of interest.

[0011] Repeat the previous step until the user finishes browsing;

[0012] The fitness function used in solving the adaptive layout scheme of the waterfall flow involves interest score and waterfall layout score. Interest score is obtained based on the degree of interest of each of the multiple data of interest in the interest dataset and their layout position in the waterfall flow. Waterfall layout score is obtained based on the bottom data height information of each of the multiple data rows occupied by the interest dataset in the waterfall flow. The bottom data height information of the data row includes the bottom data height of the data row on multiple data columns.

[0013] As a preferred embodiment, the step of dividing the multiple data of interest into multiple datasets of interest based on the data height and degree of interest corresponding to each of the multiple data of interest, and obtaining the priority of the multiple datasets of interest, includes:

[0014] Based on the data height and degree of interest of each of the multiple data points of interest, a clustering operation is performed on the multiple data points of interest to divide them into multiple initial datasets;

[0015] Obtain the preset data height dispersion threshold;

[0016] Obtain the data height dispersion of all data of interest within each of multiple initial datasets;

[0017] Based on the data height dispersion and data height dispersion threshold of all data of interest corresponding to each of the multiple initial datasets, each initial dataset is classified as a dataset of interest or a dataset to be divided.

[0018] Based on the data high dispersion threshold, each dataset to be divided is divided into at least two datasets of interest, thereby ultimately achieving the division of multiple datasets of interest into multiple datasets of interest.

[0019] As a preferred approach, based on a data dispersion threshold, the dataset to be partitioned is divided into at least two datasets of interest, including:

[0020] A. Obtain the average data height of all data of interest in the dataset to be divided;

[0021] B. Based on the average data height and the data height corresponding to each of the data of interest in the dataset to be divided, the dataset to be divided is divided into two secondary partition datasets.

[0022] C. Based on the data high dispersion threshold, classify the secondary partitioned dataset into a dataset of interest or a new dataset to be partitioned, and return to step A for the new dataset to be partitioned until no further partitioning is generated and a new dataset to be partitioned is generated.

[0023] As a preferred approach, prioritizing multiple datasets of interest includes:

[0024] Obtain the data height dispersion and the average interest level of all data within each of multiple datasets of interest.

[0025] Based on the data height dispersion of all data of interest corresponding to each of the multiple datasets of interest, the average degree of interest of all data of interest within each dataset, and the priority of the multiple datasets of interest is obtained through the superior-inferior solution distance algorithm.

[0026] As a preferred approach, an interest score is obtained based on the degree of interest of each of the multiple data points of interest in the dataset of interest and their layout position in the waterfall layout, including:

[0027] Obtain the position score of each of the multiple data points of interest in the dataset of interest, corresponding to their respective layout positions in the waterfall flow;

[0028] An interest score is obtained by considering the degree of interest of each data point in the dataset of interest and its position in the waterfall layout.

[0029] As a preferred approach, the waterfall layout score is obtained based on the bottom data height information corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall layout, including:

[0030] Based on the bottom data height information corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall flow, obtain the row height dispersion corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall flow;

[0031] The waterfall layout score is obtained based on the row height dispersion of each data row occupied by the dataset of interest in the waterfall layout.

[0032] As a preferred approach, the row height dispersion of the data rows is obtained, including:

[0033] Based on the bottom data height of each of the multiple data columns in the bottom data height information corresponding to the data row, obtain the average height of the bottom waterfall flow corresponding to the data row;

[0034] Based on the bottom data height of each data column in the bottom data height information corresponding to the data row, and the average height of the bottom waterfall flow corresponding to the data row, the standard deviation of the row height corresponding to the data row is obtained and used as the row height dispersion of the data row.

[0035] As a preferred embodiment, the process of obtaining the waterfall layout score based on the row height dispersion of each of the multiple data rows occupied by the dataset of interest in the waterfall layout includes:

[0036] Based on the row height dispersion of each of the multiple data rows occupied by the dataset of interest in the waterfall flow, the average dispersion of row height is obtained;

[0037] Based on the row height dispersion and average row height dispersion of the data rows occupied by the dataset of interest in the waterfall flow, the standard deviation of the waterfall flow is obtained.

[0038] The waterfall layout score is obtained based on the row height dispersion and standard deviation of the waterfall layout corresponding to the multiple data rows occupied by the dataset of interest in the waterfall layout.

[0039] As a preferred embodiment, the adaptive waterfall layout scheme for the next priority dataset of interest is obtained by solving the following methods based on page layout constraints, the bottom height of each column in the waterfall layout after the current priority dataset of interest is laid out with its corresponding adaptive waterfall layout scheme, and the data height and degree of interest of each of the multiple data points of interest in the next priority dataset of interest:

[0040] Obtain the user's historical browsing data for data they are interested in;

[0041] Based on the user's historical browsing data for data of interest, the degree of interest for each of the multiple data points in the next priority data set is adjusted to obtain the adjusted degree of interest for each of the multiple data points in the next priority data set.

[0042] Based on page layout constraints, the bottom height of each column in the waterfall flow after the current priority dataset of interest is laid out in the waterfall flow with its corresponding waterfall flow adaptive layout scheme, the data height and adjustment degree of each data in the next priority dataset of interest, the waterfall flow adaptive layout scheme corresponding to the next priority dataset of interest is obtained.

[0043] Secondly, embodiments of this specification provide a multi-batch waterfall layout system that integrates interest level and visual balance, based on the multi-batch waterfall layout method for integrating interest level and visual balance described in the first aspect of the embodiments, including:

[0044] The first acquisition module acquires the data height and degree of interest for each of the multiple data points that the user is interested in.

[0045] The second acquisition module divides the multiple data of interest into multiple datasets of interest based on the data height and degree of interest corresponding to each of the multiple data of interest, and obtains the priority of the multiple datasets of interest;

[0046] The solution module, based on page layout constraints and the data height and degree of interest of each of the multiple data points of interest in the highest priority dataset, solves for the waterfall adaptive layout scheme corresponding to the highest priority dataset of interest.

[0047] The solution module, when the amount of data of interest that the user has viewed in the current priority data set reaches the preset condition, solves the waterfall adaptive layout scheme corresponding to the next priority data set based on the page layout constraints, the bottom height of each column in the waterfall after the current priority data set is laid out in the waterfall with its corresponding waterfall adaptive layout scheme, and the data height and interest degree of each of the multiple data sets of interest in the next priority data set.

[0048] The fitness function used in the solution module to solve the adaptive layout scheme of the waterfall flow involves interest score and waterfall layout score. The interest score is obtained based on the degree of interest of each of the multiple data of interest in the interest dataset and their layout position in the waterfall flow. The waterfall layout score is obtained based on the bottom data height information of each of the multiple data rows occupied by the interest dataset in the waterfall flow. The bottom data height information of the data row includes the bottom data height of the data row on multiple data columns.

[0049] Thirdly, embodiments of this specification provide an electronic device, including a processor and a memory; the processor is connected to the memory; the memory is used to store executable program code; the processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to perform the steps described in the first aspect of the above embodiments.

[0050] Fourthly, embodiments of this specification provide a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the steps described in the first aspect of the above embodiments.

[0051] The beneficial effects of the technical solutions provided in some embodiments of this specification include at least the following:

[0052] Multiple datasets of interest are divided into several interest datasets based on their respective data height and interest level. The priorities of these datasets are then determined, and subsequent adaptive waterfall layout optimization is performed on each dataset according to priority. The fitness function used in the optimization incorporates both interest score and waterfall layout score. This initial division of interest datasets avoids performing layout optimization on all interest datasets at once (note: since users browse interest datasets in batches on the front-end page, and if they find the target data during browsing, they will not browse subsequent interest datasets, it is unnecessary to perform layout optimization on all interest datasets at once in practical applications), thus reducing data processing volume. Furthermore, the interest dataset division based on data height and interest level lays the foundation for prioritizing the push of interest datasets with high interest levels and high visual balance in the page layout. By further considering the fitness function based on interest score and waterfall layout score, adaptive waterfall layout optimization is performed on each interest dataset according to priority, ensuring that each interest dataset achieves the best overall user interest effect and visual balance in the front-end page.

[0053] When dividing the dataset of interest, clustering is used to obtain multiple initial datasets. Therefore, the data of interest in each initial dataset have similar levels of interest and data height, which lays the foundation for subsequent layout optimization and content push of multiple datasets of interest while taking into account both the accuracy of content recommendation and the visual balance of page layout.

[0054] To further ensure the visual balance of the page layout when each dataset of interest is presented on the front-end page, the height dispersion of all data points of interest in the dataset should be lower than a certain height dispersion threshold. Therefore, after clustering, this solution further divides the dataset a second or multiple times based on the height dispersion threshold and the average height of all data points of interest in the dataset. Moreover, this method of partitioning based on the average height requires less data processing compared to clustering methods that adaptively adjust clusters, making it more suitable for scenarios where users browse the front-end page quickly and need to rapidly push data of interest.

[0055] Based on the data height dispersion of all data of interest within each of the multiple datasets of interest, the average degree of interest of all data of interest within each dataset, and the priority of multiple datasets of interest through the superior-inferior solution distance algorithm, the foundation is laid for subsequent layout optimization and content push for datasets of interest with high content recommendation accuracy and high visual balance of page layout.

[0056] The average row height dispersion is obtained based on the row height dispersion of each data row occupied by the dataset of interest within the waterfall layout. The standard deviation of the waterfall layout is then calculated based on both the row height dispersion and the average row height dispersion. Finally, the waterfall layout score is obtained based on the row height dispersion and the standard deviation of the waterfall layout. In other words, when considering the waterfall layout score, not only the visual balance of each individual data row is considered, but also the overall visual balance formed by multiple data rows, further ensuring the visual balance of the page layout. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A flowchart illustrating a multi-batch waterfall layout method that integrates interest and visual balance according to some embodiments of this disclosure is shown.

[0059] Figure 2 A schematic diagram of the waterfall layout on the front-end page is shown;

[0060] Figure 3 A schematic diagram of a multi-batch waterfall layout system that integrates interest and visual balance is shown.

[0061] Figure 4 A schematic block diagram of an electronic device according to some embodiments of the present disclosure is shown. Detailed Implementation

[0062] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings.

[0063] The terms "first," "second," "third," etc., in the description, claims, and accompanying drawings are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0064] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the described elements without departing from the scope of this specification. Various processes or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.

[0065] Figure 1 A flowchart illustrating a multi-batch waterfall layout method that integrates interest and visual balance according to some embodiments of this disclosure is shown. Figure 1 As shown, a multi-batch waterfall layout method that integrates interest and visual balance can include at least:

[0066] Obtain the data height and degree of interest for each of the multiple data points that the user is interested in;

[0067] Based on the data height and degree of interest of each of the multiple data points of interest, the data points of interest are divided into multiple datasets of interest, and the priority of the multiple datasets of interest is obtained;

[0068] Based on page layout constraints (including but not limited to: no empty space for data on the page, the width of each data on the page is the same, and the vertical spacing between data on the page is consistent) and the data height and degree of interest of each of the multiple data of interest in the highest priority dataset, the waterfall flow adaptive layout scheme corresponding to the highest priority dataset of interest is obtained.

[0069] When the amount of data of interest that the user has viewed in the current priority dataset of interest reaches the preset condition, the adaptive layout scheme of the waterfall flow corresponding to the next priority dataset of interest is obtained by solving the following based on the page layout constraints, the bottom height of each column in the waterfall flow after the current priority dataset of interest is laid out with its corresponding waterfall flow adaptive layout scheme, and the data height and interest degree of each of the multiple data of interest in the next priority dataset of interest.

[0070] Repeat the previous step until the user finishes browsing;

[0071] The fitness function used in solving the adaptive layout scheme of the waterfall flow involves interest score and waterfall layout score. Interest score is obtained based on the degree of interest of each of the multiple data of interest in the interest dataset and their layout position in the waterfall flow. Waterfall layout score is obtained based on the bottom data height information of each of the multiple data rows occupied by the interest dataset in the waterfall flow. The bottom data height information of the data row includes the bottom data height of the data row on multiple data columns.

[0072] As is understandable, in the embodiments of this specification, multiple data points of interest are divided into multiple datasets of interest based on their respective data height and degree of interest, and the priority of each dataset of interest is obtained. Subsequently, waterfall layout adaptive optimization is performed on each dataset of interest in sequence according to priority, and the fitness function used for optimization involves both interest score and waterfall layout score. It is evident that by dividing the datasets of interest in the early stage, layout optimization of all data points of interest can be avoided at once (note: since users browse data of interest in batches on the front-end page, and if they find the target data during browsing, they will not browse subsequent data of interest, it is unnecessary to optimize the layout of all data points of interest at once in practical applications), thereby reducing the amount of data processing. Furthermore, the method of dividing the datasets of interest based on data height and degree of interest also lays the foundation for prioritizing the push of data of interest with high degree of interest and high visual balance in the page layout. Further, by considering the fitness function of interest score and waterfall layout score, waterfall layout adaptive optimization is performed on each dataset of interest in sequence according to priority, so that the user interest effect and visual balance of the page layout of each dataset of interest on the front-end page are optimal.

[0073] For the waterfall flow described in the embodiments of this specification, please refer to... Figure 2 As shown, Figure 2 The waterfall layout in the example has five data columns. This layout can present different data content, including but not limited to clothing, home furnishings, and trendy toys, with each data content having a different height. Furthermore, it's important to note that the bottom height of each data row across multiple columns represents the height of the bottom of each data point of interest within the entire waterfall layout.

[0074] One approach is to use a genetic algorithm to solve the adaptive layout scheme for waterfall flow. A genetic algorithm is a search heuristic algorithm that simulates natural selection and genetics, used to solve optimization and search problems. In a genetic algorithm, each potential solution is represented as a "chromosome," and the fitness function is used to evaluate the fitness of each chromosome, i.e., the quality of the solution. Genetic algorithms are conventional algorithms and will not be elaborated upon here. The fitness function can be, but is not limited to, the following:

[0075] ;

[0076] in, This represents the fitness function value. , (It should be noted that,) The specific value can be set according to actual needs, but it must meet the above-mentioned size relationship. This represents the normalized score of interest. This represents the normalized waterfall layout score. The specific calculation methods for the interest score and the waterfall layout score will be introduced in the following content.

[0077] Furthermore, it is understandable that specific calculations can be assigned... , Different weighting coefficients are calculated, but the above calculation formula does not show the weighting coefficients for ease of illustration.

[0078] In the example of calculating the fitness function value given above, the larger the fitness function value, the better the solution.

[0079] In some embodiments of this specification, the step of dividing multiple pieces of data of interest into multiple datasets of interest based on their respective data height and degree of interest, and obtaining the priority of the multiple datasets of interest, includes:

[0080] Based on the data height and degree of interest corresponding to each of the multiple data of interest, a clustering operation is performed on the multiple data of interest (Note: In order to adapt to the scenario requirements of users browsing the front-end page quickly, the clustering operation with a fixed number of clusters is used in the embodiments of this specification) to divide the multiple data of interest into multiple initial datasets;

[0081] Obtain the preset data height dispersion threshold;

[0082] Obtain the data height dispersion of all data of interest within each of multiple initial datasets;

[0083] Based on the data height dispersion and data height dispersion threshold of all data of interest corresponding to each of the multiple initial datasets, each initial dataset is classified as a dataset of interest or a dataset to be divided.

[0084] Based on the data high dispersion threshold, each dataset to be divided is divided into at least two datasets of interest, thereby ultimately achieving the division of multiple datasets of interest into multiple datasets of interest.

[0085] Specifically, based on a data high dispersion threshold, the dataset to be divided is divided into at least two datasets of interest, including:

[0086] A. Obtain the average data height of all data of interest in the dataset to be divided;

[0087] B. Based on the average data height and the data height corresponding to each of the data of interest in the dataset to be divided, the dataset to be divided is divided into two secondary partition datasets.

[0088] C. Based on the data high dispersion threshold, classify the secondary partitioned dataset into a dataset of interest or a new dataset to be partitioned, and return to step A for the new dataset to be partitioned until no further partitioning is generated and a new dataset to be partitioned is generated.

[0089] When dividing the dataset of interest, clustering is used to obtain multiple initial datasets. Therefore, the data of interest in each initial dataset have similar levels of interest and data height, which lays the foundation for subsequent layout optimization and content push of multiple datasets of interest while taking into account both the accuracy of content recommendation and the visual balance of page layout.

[0090] To further ensure the visual balance of the page layout when each dataset of interest is presented on the front-end page, the height dispersion of all data points of interest in the dataset should be lower than a certain height dispersion threshold. Therefore, after clustering, this solution further divides the dataset a second or multiple times based on the height dispersion threshold and the average height of all data points of interest in the dataset. Moreover, this method of partitioning based on the average height requires less data processing compared to clustering methods that adaptively adjust clusters, making it more suitable for scenarios where users browse the front-end page quickly and need to rapidly push data of interest.

[0091] In some embodiments of this specification, the priority acquisition of multiple datasets of interest includes:

[0092] Obtain the data height dispersion and the average interest level of all data within each of multiple datasets of interest.

[0093] Based on the data height dispersion of all data of interest corresponding to each of the multiple datasets of interest, the average degree of interest of all data of interest within each dataset, and the priority of the multiple datasets of interest is obtained through the superior-inferior solution distance algorithm.

[0094] Based on the data height dispersion and average interest level of all data within each of the multiple datasets of interest, and using the superior-inferior solution distance algorithm, the priority of the multiple datasets of interest is obtained. That is, the datasets of interest with high average interest level and low data height dispersion are ranked higher, laying the foundation for subsequent layout optimization and content push for datasets of interest with high content recommendation accuracy and high visual balance of page layout.

[0095] The method involves prioritizing multiple datasets of interest based on the data height dispersion of all data of interest within each dataset, the average degree of interest of all data of interest within each dataset, and using a superior-inferior solution distance algorithm. This includes:

[0096] Based on the data height dispersion of all data of interest in each of the multiple datasets of interest and the average degree of interest of all data of interest in each dataset, the positive ideal solution and the negative ideal solution are determined.

[0097] Based on the data height dispersion of all internal data of interest in each of the multiple datasets of interest, the average degree of interest of all internal data of interest, the positive ideal solution, and the negative ideal solution, the relative closeness of each of the multiple datasets of interest is obtained.

[0098] Based on the relative proximity of multiple datasets of interest, the priority of multiple datasets of interest is obtained.

[0099] The relative closeness is calculated as follows:

[0100] ;

[0101] Indicates the first The relative proximity of a dataset of interest Indicates the first The distance between each dataset of interest and the negative ideal solution. Indicates the first The distance between each dataset of interest and the ideal solution.

[0102] Wherein: the negative ideal solution includes the maximum data height dispersion among the data height dispersions of each dataset of interest, and the minimum average interest among the average interest among the datasets of interest; the positive ideal solution includes the minimum data height dispersion among the data height dispersions of each dataset of interest, and the maximum average interest among the average interest among the datasets of interest.

[0103] ;

[0104] ;

[0105] in, The relative proximity weights corresponding to the degree of interest are calculated. The weights are calculated to represent the relative proximity corresponding to the high degree of dispersion of the data. Indicates the first The average level of interest corresponding to each dataset of interest This represents the average degree of interest in negative ideal solutions. Indicates the first The data high dispersion corresponding to each dataset of interest This indicates the high degree of data dispersion in negative ideal solutions. This represents the average degree of interest in the ideal solution. This indicates the high degree of data dispersion in the ideal solution.

[0106] Therefore, under this relative proximity calculation method, the dataset of interest with a larger relative proximity value has a higher priority.

[0107] In some embodiments of this specification, an interest score is obtained based on the degree of interest corresponding to each of the multiple data points of interest in the dataset of interest and their layout position in the waterfall flow, including:

[0108] Obtain the position score of each of the multiple data points of interest in the dataset of interest, corresponding to their respective layout positions in the waterfall flow;

[0109] An interest score is obtained by considering the degree of interest of each data point in the dataset of interest and its position in the waterfall layout.

[0110] Understandably, positions higher and further to the left in a waterfall layout should receive higher scores. The formula for calculating the score of interest can be, but is not limited to, the following:

[0111] ;

[0112] in, Indicates interest score. Indicates the first element in the dataset of interest. The degree of interest corresponding to each piece of data of interest Indicates the first element in the dataset of interest. The position of each piece of data of interest within the layout of the waterfall flow. This represents the total number of data points of interest in the dataset of interest.

[0113] In some embodiments of this specification, the waterfall layout score is obtained based on the bottom data height information corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall layout, including:

[0114] Based on the bottom data height information corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall flow, obtain the row height dispersion corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall flow;

[0115] The waterfall layout score is obtained based on the row height dispersion of each data row occupied by the dataset of interest in the waterfall layout.

[0116] Understandably, in the embodiments of this specification, the row height dispersion of each of the multiple data rows occupied by the dataset of interest in the waterfall layout is first obtained, then the visual balance of each of the multiple data rows occupied by the dataset of interest in the waterfall layout is obtained, and finally, based on the visual balance of each of the multiple data rows occupied by the dataset of interest in the waterfall layout, the waterfall layout score is obtained.

[0117] In some embodiments of this specification, the acquisition of row height dispersion corresponding to a data row includes:

[0118] Based on the bottom data height of each of the multiple data columns in the bottom data height information corresponding to the data row, obtain the average height of the bottom waterfall flow corresponding to the data row;

[0119] Based on the bottom data height of each data column in the bottom data height information corresponding to the data row, and the average height of the bottom waterfall flow corresponding to the data row, the standard deviation of the row height corresponding to the data row is obtained and used as the row height dispersion of the data row.

[0120] In some embodiments of this specification, obtaining the waterfall layout score based on the row height dispersion of each of the multiple data rows occupied by the dataset of interest in the waterfall layout includes:

[0121] Based on the row height dispersion of each of the multiple data rows occupied by the dataset of interest in the waterfall flow, the average dispersion of row height is obtained;

[0122] Based on the row height dispersion and average row height dispersion of the data rows occupied by the dataset of interest in the waterfall flow, the standard deviation of the waterfall flow is obtained.

[0123] The waterfall layout score is obtained based on the row height dispersion and standard deviation of the waterfall layout corresponding to the multiple data rows occupied by the dataset of interest in the waterfall layout.

[0124] Understandably, for a dataset of interest, it is presented centrally in the waterfall layout. Therefore, the row height dispersion of the multiple data rows occupied by the local waterfall layout corresponding to that dataset should be similar to ensure the visual smoothness of the local waterfall layout corresponding to the same dataset on the front-end page. That is, when considering the waterfall layout score, not only the visual balance of each individual data row is considered, but also the overall visual balance formed by multiple data rows, further ensuring the visual balance of the page layout.

[0125] The formula for calculating the score of a waterfall layout can be, but is not limited to, the following:

[0126] ;

[0127] ;

[0128] in, This indicates the score for the waterfall layout. Indicates and The relevant waterfall layout score calculation function, and The smaller the value, The larger the value, the better. Indicates the standard deviation of the waterfall flow. This represents the total number of rows occupied by the dataset of interest in the waterfall layout. This indicates the rank of the dataset of interest in the waterfall view. The row height dispersion corresponding to each row of data.

[0129] In some embodiments of this specification, the process of determining the adaptive waterfall layout scheme for the next priority dataset of interest based on page layout constraints, the bottom height of each column in the waterfall layout after the current priority dataset of interest is laid out with its corresponding adaptive waterfall layout scheme, and the data height and degree of interest of each of the multiple datasets of interest in the next priority dataset of interest, includes:

[0130] Obtain the user's historical browsing data for data they are interested in;

[0131] Based on the user's historical browsing data for data of interest, the degree of interest for each of the multiple data points in the next priority data set is adjusted to obtain the adjusted degree of interest for each of the multiple data points in the next priority data set.

[0132] Based on page layout constraints, the bottom height of each column in the waterfall flow after the current priority dataset of interest is laid out in the waterfall flow with its corresponding waterfall flow adaptive layout scheme, the data height and adjustment degree of each data in the next priority dataset of interest, the waterfall flow adaptive layout scheme corresponding to the next priority dataset of interest is obtained.

[0133] Understandably, the embodiments in this specification achieve real-time evolution of the recommendation strategy by dynamically adjusting the level of interest in subsequent data based on the user's historical browsing data (which may include, but is not limited to, data such as the user's browsing, clicks, and dwell time). This mechanism can accurately capture the shift in user interests, forming an efficient feedback loop and ensuring that subsequent layout optimization and content delivery closely align with the user's actual needs.

[0134] Figure 3 Schematic diagrams of a multi-batch waterfall layout system that integrates interest and visual balance according to some embodiments of this disclosure are shown. The various embodiments in this specification are described in a progressive manner, and similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of the multi-batch waterfall layout system that integrates interest and visual balance are basically similar to the embodiments of the multi-batch waterfall layout method that integrates interest and visual balance, so the description is relatively simple, and relevant parts can be referred to in the description of the multi-batch waterfall layout method embodiment.

[0135] like Figure 3 As shown, a multi-batch waterfall layout system that integrates interest and visual balance can include at least:

[0136] The first acquisition module acquires the data height and degree of interest for each of the multiple data points that the user is interested in.

[0137] The second acquisition module divides the multiple data of interest into multiple datasets of interest based on the data height and degree of interest corresponding to each of the multiple data of interest, and obtains the priority of the multiple datasets of interest;

[0138] The solution module, based on page layout constraints and the data height and degree of interest of each of the multiple data points of interest in the highest priority dataset, solves for the waterfall adaptive layout scheme corresponding to the highest priority dataset of interest.

[0139] The solution module, when the amount of data of interest that the user has viewed in the current priority data set reaches the preset condition, solves the waterfall adaptive layout scheme corresponding to the next priority data set based on the page layout constraints, the bottom height of each column in the waterfall after the current priority data set is laid out in the waterfall with its corresponding waterfall adaptive layout scheme, and the data height and interest degree of each of the multiple data sets of interest in the next priority data set.

[0140] The fitness function used in the solution module to solve the adaptive layout scheme of the waterfall flow involves interest score and waterfall layout score. The interest score is obtained based on the degree of interest of each of the multiple data of interest in the interest dataset and their layout position in the waterfall flow. The waterfall layout score is obtained based on the bottom data height information of each of the multiple data rows occupied by the interest dataset in the waterfall flow. The bottom data height information of the data row includes the bottom data height of the data row on multiple data columns.

[0141] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)).

[0142] Figure 4 A block diagram of an electronic device 400 that can implement various embodiments of the present disclosure is shown. For example... Figure 4 As shown, the electronic device 400 includes a processor 410, a disk drive 420, an input / output interface 430, a network interface 440, and a memory 450. The processor 410, disk drive 420, input / output interface 430, network interface 440, and memory 450 can communicate with each other via a communication bus 460.

[0143] The processor 410 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs and implement the technical solution provided in this application.

[0144] The memory 450 can be implemented in the form of ROM (Read Only Memory), RAM (Read Access Memory), static memory, dynamic storage devices, etc. The memory 450 can store the operating system 451 for controlling the operation of the electronic device 400, and the Basic Input / Output System 452 for controlling the low-level operations of the electronic device 400. Additionally, it can store a web browser 453, a data storage management system 454, etc. In summary, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 450 and executed by the processor 410.

[0145] Input / output interface 430 is used to connect input / output devices to enable information input and output. Input / output devices can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0146] Network interface 440 is used to connect network devices (not shown in the figure) to enable network communication between the device and other devices. The network devices can communicate via wired means (e.g., USB, Ethernet cable) or wireless means (e.g., mobile network, Wi-Fi, Bluetooth).

[0147] Bus 460 includes a pathway for transmitting information between various components of the device, such as processor 410, disk drive 420, input / output interface 430, network interface 440, and memory 450.

[0148] It should be noted that although the above-described device only shows the processor 410, disk drive 420, input / output interface 430, network interface 440, memory 450, bus 460, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the method of this application, and does not necessarily include all the components shown in the figures.

[0149] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0150] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. Furthermore, although operations are depicted in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in sequential order, or requiring that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0151] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A multi-batch waterfall layout method that integrates interest and visual balance, characterized in that, include: Obtain the data height and degree of interest for each of the multiple data points that the user is interested in; Based on the data height and degree of interest of each of the multiple data points of interest, the data points of interest are divided into multiple datasets of interest, and the priority of the multiple datasets of interest is obtained; Based on page layout constraints and the data height and degree of interest of each of the multiple data points of interest in the highest priority dataset, the waterfall flow adaptive layout scheme corresponding to the highest priority dataset of interest is obtained. When the amount of data of interest that the user has viewed in the current priority dataset of interest reaches the preset condition, the adaptive layout scheme of the waterfall flow corresponding to the next priority dataset of interest is obtained by solving the following based on the page layout constraints, the bottom height of each column in the waterfall flow after the current priority dataset of interest is laid out with its corresponding waterfall flow adaptive layout scheme, and the data height and interest degree of each of the multiple data of interest in the next priority dataset of interest. Repeat the previous step until the user finishes browsing; The fitness function used in solving the adaptive layout scheme of the waterfall flow involves interest score and waterfall layout score. Interest score is obtained based on the degree of interest of each of the multiple data of interest in the interest dataset and their layout position in the waterfall flow. Waterfall layout score is obtained based on the bottom data height information of each of the multiple data rows occupied by the interest dataset in the waterfall flow. The bottom data height information of the data row includes the bottom data height of the data row on multiple data columns.

2. The multi-batch waterfall layout method for integrating interest and visual balance according to claim 1, characterized in that, The process of dividing multiple pieces of data of interest into multiple datasets of interest based on their respective data height and degree of interest, and obtaining the priority of the multiple datasets of interest, includes: Based on the data height and degree of interest of each of the multiple data points of interest, a clustering operation is performed on the multiple data points of interest to divide them into multiple initial datasets; Obtain the preset data height dispersion threshold; Obtain the data height dispersion of all data of interest within each of multiple initial datasets; Based on the data height dispersion and data height dispersion threshold of all data of interest corresponding to each of the multiple initial datasets, each initial dataset is classified as a dataset of interest or a dataset to be divided. Based on the data high dispersion threshold, each dataset to be divided is divided into at least two datasets of interest, thereby ultimately achieving the division of multiple datasets of interest into multiple datasets of interest.

3. The multi-batch waterfall layout method for integrating interest and visual balance according to claim 2, characterized in that, Based on the data high dispersion threshold, the dataset to be divided is divided into at least two datasets of interest, including: A. Obtain the average data height of all data of interest in the dataset to be divided; B. Based on the average data height and the data height corresponding to each of the data of interest in the dataset to be divided, the dataset to be divided is divided into two secondary partition datasets. C. Based on the data high dispersion threshold, classify the secondary partitioned dataset into a dataset of interest or a new dataset to be partitioned, and return to step A for the new dataset to be partitioned, until no further partitioning is generated and a new dataset to be partitioned is generated.

4. The multi-batch waterfall layout method for integrating interest and visual balance according to claim 1, characterized in that, Prioritization of multiple datasets of interest, including: Obtain the data height dispersion and the average interest level of all data within each of multiple datasets of interest. Based on the data height dispersion of all data of interest corresponding to each of the multiple datasets of interest, the average degree of interest of all data of interest within each dataset, and the priority of the multiple datasets of interest is obtained through the superior-inferior solution distance algorithm.

5. The multi-batch waterfall layout method for integrating interest and visual balance according to claim 1, characterized in that, An interest score is obtained based on the degree of interest of each data point in the dataset of interest and its position in the waterfall layout. This score includes: Obtain the position score of each of the multiple data points of interest in the dataset of interest, corresponding to their respective layout positions in the waterfall flow; An interest score is obtained by considering the degree of interest of each data point in the dataset of interest and its position in the waterfall layout.

6. The multi-batch waterfall layout method for integrating interest and visual balance according to claim 1, characterized in that, The waterfall layout score is obtained based on the bottom data height information corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall layout. This score includes: Based on the bottom data height information corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall flow, the row height dispersion corresponding to each of the multiple data rows occupied by the dataset of interest in the waterfall flow is obtained. The waterfall layout score is obtained based on the row height dispersion of each data row occupied by the dataset of interest in the waterfall layout.

7. The multi-batch waterfall layout method for integrating interest and visual balance according to claim 6, characterized in that, The row height dispersion of data rows is obtained, including: Based on the bottom data height of each of the multiple data columns in the bottom data height information corresponding to the data row, obtain the average height of the bottom waterfall flow corresponding to the data row; Based on the bottom data height of each data column in the bottom data height information corresponding to the data row, and the average height of the bottom waterfall flow corresponding to the data row, the standard deviation of the row height corresponding to the data row is obtained and used as the row height dispersion of the data row.

8. The multi-batch waterfall layout method for integrating interest and visual balance according to claim 6, characterized in that, The waterfall layout score is obtained based on the row height dispersion of each data row in the waterfall layout corresponding to the dataset of interest, including: Based on the row height dispersion of each of the multiple data rows occupied by the dataset of interest in the waterfall flow, the average dispersion of row height is obtained; Based on the row height dispersion and average row height dispersion of the data rows occupied by the dataset of interest in the waterfall flow, the standard deviation of the waterfall flow is obtained. The waterfall layout score is obtained based on the row height dispersion and standard deviation of the waterfall layout corresponding to the multiple data rows occupied by the dataset of interest in the waterfall layout.

9. The multi-batch waterfall layout method for integrating interest and visual balance according to claim 1, characterized in that, The adaptive waterfall layout scheme for the next priority dataset of interest is obtained by considering the page layout constraints, the bottom height of each column in the waterfall layout after the current priority dataset is laid out with its corresponding adaptive waterfall layout scheme, and the data height and interest level of each data point in the next priority dataset of interest. This includes: Obtain the user's historical browsing data for data they are interested in; Based on the user's historical browsing data for data of interest, the degree of interest for each of the multiple data points in the next priority data set is adjusted to obtain the adjusted degree of interest for each of the multiple data points in the next priority data set. Based on page layout constraints, the bottom height of each column in the waterfall flow after the current priority dataset of interest is laid out in the waterfall flow with its corresponding adaptive waterfall layout scheme, the data height and adjustment degree of each data in the next priority dataset of interest, the adaptive waterfall layout scheme corresponding to the next priority dataset of interest is obtained.

10. A multi-batch waterfall layout system that integrates interest and visual balance, based on the multi-batch waterfall layout method that integrates interest and visual balance as described in any one of claims 1 to 9, characterized in that, include: The first acquisition module acquires the data height and degree of interest for each of the multiple data points that the user is interested in. The second acquisition module divides the multiple data of interest into multiple datasets of interest based on the data height and degree of interest corresponding to each of the multiple data of interest, and obtains the priority of the multiple datasets of interest; The solution module, based on page layout constraints and the data height and degree of interest of each of the multiple data points of interest in the highest priority dataset, solves for the waterfall adaptive layout scheme corresponding to the highest priority dataset of interest. The solution module, when the amount of data of interest that the user has viewed in the current priority data set reaches the preset condition, solves the waterfall adaptive layout scheme corresponding to the next priority data set based on the page layout constraints, the bottom height of each column in the waterfall after the current priority data set is laid out in the waterfall with its corresponding waterfall adaptive layout scheme, and the data height and interest degree of each of the multiple data sets of interest in the next priority data set. The fitness function used in the solution module to solve the adaptive layout scheme of the waterfall flow involves interest score and waterfall layout score. The interest score is obtained based on the degree of interest of each of the multiple data of interest in the interest dataset and their layout position in the waterfall flow. The waterfall layout score is obtained based on the bottom data height information of each of the multiple data rows occupied by the interest dataset in the waterfall flow. The bottom data height information of the data row includes the bottom data height of the data row on multiple data columns.

Images