Page content display method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a page content display method and device, electronic equipment and a storage medium, relates to the technical field of computers, and is suitable for the field of financial science and technology. The method comprises the steps of displaying a target page; wherein the target page displays a page block, and the page block is used for displaying one of the contents of the at least two candidate blocks; acquiring historical behavior feature information of the target user; determining at least one candidate display block content according to the similarity between the historical behavior feature information and the content feature information of the candidate block content; obtaining behavior data of the target user for each candidate display block content, and obtaining behavior data of the target block content; determining a target display probability according to the target block content behavior data and the auxiliary block content behavior data; and displaying the content of the candidate display block in the page block according to the target display probability. According to the embodiment of the invention, the page content can be adaptively adjusted, and the page content display flexibility is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and is applicable to the field of financial technology, and particularly to a method, apparatus, electronic device and storage medium for displaying page content. Background Technology

[0002] In user interface (UI) design, attracting users often relies on the content displayed on the user-facing page (such as marketing content). For example, in the insurance recommendation scenario within the fintech field, insurance marketing content, such as images or animations of coupon lucky draw wheels, can be displayed in certain areas of the insurance marketing page to entice users to purchase related insurance. However, current page layouts (such as the content displayed) are usually fixed in the initial page design phase. This means that when a user visits a completed page, the content displayed is difficult to change. This situation limits the flexibility of page content display, leading to a homogenized user experience.

[0003] Therefore, how to adjust the page content has become a pressing technical problem that needs to be solved. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, electronic device, and storage medium for displaying page content, which aims to adaptively adjust page content and improve the flexibility of page content display.

[0005] To achieve the above objectives, a first aspect of this application proposes a method for displaying page content, the method comprising:

[0006] Display the target page; wherein the target page displays page blocks, and the page blocks are used to display one of at least two candidate block contents;

[0007] Obtain historical behavioral characteristics information of the target user;

[0008] Based on the similarity between the historical behavior feature information and the content feature information of each candidate block content, at least one candidate display block content is determined from at least two candidate block contents.

[0009] Obtain the target user's behavior data for each candidate display block content to obtain the target block content behavior data;

[0010] Based on the target block content behavior data and the auxiliary block content behavior data, the display probability of the candidate display block content is determined to obtain the target display probability; wherein, the auxiliary block content behavior data is the behavior data of non-target users towards the candidate display block content;

[0011] The content of the candidate display block is displayed within the page block according to the target display probability.

[0012] In some embodiments, the auxiliary block content behavior data consists of at least two elements;

[0013] The step of determining the display probability of the candidate display block content based on the target block content behavior data and the auxiliary block content behavior data, to obtain the target display probability, includes:

[0014] The behavior occurrence time of each auxiliary block content behavior data is obtained, and a time decay factor is calculated based on the behavior occurrence time to obtain the time decay factor;

[0015] Weighted auxiliary behavior data is obtained by multiplying the content behavior data of each auxiliary block with the time decay factor.

[0016] Based on the target block content behavior data and the weighted auxiliary behavior data corresponding to the same candidate display block content, the user conversion effect is calculated to obtain the target user conversion effect value corresponding to each candidate display block content;

[0017] Based on the target user conversion effect value, the initial display probability of at least one of the candidate display blocks is updated to obtain the target display probability.

[0018] In some embodiments, the weighted auxiliary behavior data includes weighted auxiliary click count, weighted auxiliary return visit count, and weighted auxiliary conversion count, and the target block content behavior data includes target click count, target return visit count, and target conversion count;

[0019] The step of calculating user conversion effect based on the target block content behavior data and the weighted auxiliary behavior data corresponding to the same candidate display block content, to obtain the target user conversion effect value corresponding to each candidate display block content, includes:

[0020] The target user and the non-target user corresponding to the same candidate display block content are identified as the first user, and the number of the first users is identified as the total number of the first users;

[0021] The click-through rate is calculated by taking the ratio of the sum of the weighted auxiliary clicks and the target clicks of the first user, and the total number of the first users.

[0022] The retention rate is calculated by taking the ratio of the sum of the weighted auxiliary return visits and the target return visits of the first user, and the total number of the first users.

[0023] The conversion rate is calculated based on the sum of the weighted auxiliary conversion count and the target conversion count of the first user, as well as the total number of the first users.

[0024] The target user conversion effect value is obtained by weighted summation of the click-through rate, retention rate, and conversion rate for each candidate display block content; wherein the target user conversion effect value is inversely proportional to the click-through rate and directly proportional to the retention rate and conversion rate.

[0025] In some embodiments, the step of weighted summing of the click-through rate, retention rate, and conversion rate to obtain the target user conversion effect value corresponding to each candidate display block content includes:

[0026] The initial user conversion effect value is obtained by weighting and summing the click-through rate, retention rate, conversion rate and a preset initial weighting set; wherein, the initial weighting set is used to represent the combination of the weights of the click-through rate, retention rate and conversion rate.

[0027] Using a Bayesian optimization algorithm, the initial weight reorganization is updated based on the initial user conversion effect value and the initial display probability corresponding to the content of each candidate display block, to obtain the target weight reorganization;

[0028] The target user conversion effect value corresponding to each page block content is obtained by weighted summation based on the click-through rate, retention rate, conversion rate, and target weight.

[0029] In some embodiments, the number of non-target users is at least two;

[0030] Before calculating the user conversion effect based on the target block content behavior data and the weighted auxiliary behavior data corresponding to the same candidate display block content, and obtaining the target user conversion effect value corresponding to each candidate display block content, the method further includes:

[0031] The historical behavioral feature information of the target user is determined as the first historical behavioral feature information, and the second historical behavioral feature information of each non-target user is obtained;

[0032] Based on the first historical behavior feature information and the second historical behavior feature information, a similarity calculation is performed to obtain the behavior feature similarity of each non-target user.

[0033] If the similarity of the behavioral features of the non-target user is less than or equal to a preset similarity threshold, the weighted auxiliary behavioral data of the non-target user is deleted.

[0034] In some embodiments, the step of calculating the similarity based on the first historical behavior feature information and the second historical behavior feature information to obtain the behavioral feature similarity of each non-target user includes:

[0035] The first historical behavior feature information is hashed to obtain the first behavior feature hash value, and the second historical behavior feature information is hashed to obtain the second behavior feature hash value.

[0036] The hash similarity is calculated based on the first behavioral feature hash value and each of the second behavioral feature hash values ​​to obtain the behavioral feature similarity of each non-target user.

[0037] In some embodiments, the historical behavior feature information includes historical block content access records, and at least two of the candidate block contents have different block types;

[0038] The step of determining at least one candidate display block content from at least two candidate block contents based on the similarity between the historical behavior feature information and the content feature information of each candidate block content includes:

[0039] The access block type is determined based on the access records of the historical block content, thus obtaining the historical access block type;

[0040] From at least two candidate block contents, find the candidate block contents that belong to the historical access block type to obtain at least one target type block content;

[0041] Based on the historical behavior feature information and the similarity with the content feature information of each target type block content, at least one candidate display block content is determined from at least one target type block content.

[0042] To achieve the above objectives, a second aspect of this application provides a page content display device, the device comprising:

[0043] A page display module is used to display a target page; wherein the target page displays page blocks, and the page blocks are used to display one of at least two candidate block contents;

[0044] The historical information acquisition module is used to acquire historical behavioral characteristic information of the target user;

[0045] The block content determination module is used to determine at least one candidate display block content from at least two candidate block contents based on the similarity between the historical behavior feature information and the content feature information of each candidate block content;

[0046] The behavior data acquisition module is used to acquire the behavior data of the target user for each candidate display block content, and obtain the target block content behavior data;

[0047] The display probability determination module is used to determine the display probability of the candidate display block content based on the target block content behavior data and the auxiliary block content behavior data, so as to obtain the target display probability; wherein, the auxiliary block content behavior data is the behavior data of non-target users towards the candidate display block content;

[0048] The block content display module is used to display the candidate display block content within the page block according to the target display probability.

[0049] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0050] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0051] The page content display method, apparatus, electronic device, and storage medium proposed in this application display a target page to show candidate block content within its page blocks, while simultaneously acquiring historical behavioral characteristic information of the target user for subsequent initial screening of block content based on the target user's personalized characteristics. Based on the similarity between historical behavioral characteristics and the content characteristic information of each candidate block content, at least one candidate block content is determined from multiple candidates. This allows for initial screening of personalized content for the target user, improving the alignment between the displayed block content and user preferences. Then, behavioral data of the target user and non-target users regarding the candidate block content are acquired, namely, target block content behavioral data and auxiliary block content behavioral data, and the display probability of the candidate block content is determined by combining these two types of behavioral data. This allows for dynamic adjustment of the block content display probability based on feedback from the target user and the user group's behavioral feedback, rather than fixing the displayed content at the initial page design stage. This adaptive adjustment of page content improves the flexibility of page content display and enhances its personalization. Attached Figure Description

[0052] Figure 1 This is a flowchart of the page content display method provided in the embodiments of this application;

[0053] Figure 2yes Figure 1 The flowchart for step 103 in the text;

[0054] Figure 3 yes Figure 1 The flowchart for step 105 in the document;

[0055] Figure 4 yes Figure 3 The flowchart for step 303 in the document;

[0056] Figure 5 yes Figure 4 The flowchart for step 405 in the document;

[0057] Figure 6 This is a flowchart of a page content display method provided in another embodiment of this application;

[0058] Figure 7 yes Figure 6 The flowchart for step 602 in the document;

[0059] Figure 8 This is a schematic diagram illustrating a specific implementation of an application example provided in this application embodiment;

[0060] Figure 9 This is a schematic diagram of the structure of the page content display device provided in the embodiments of this application;

[0061] Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0065] First, let's analyze some of the terms used in this application:

[0066] Artificial Intelligence (AI) is a new technical science that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI attempts to understand the essence of intelligence and produce intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can be a simulation of the information processes of human consciousness and thought. It can also be the theory, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operating / interactive systems, and mechatronics. AI software technologies mainly include computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning. This application can acquire and process relevant data based on AI technology.

[0067] The Multi-Armed Slot (MAB) algorithm is a balanced approach that combines exploration and exploitation. In MAB algorithms, the arm with the highest upper confidence bound is typically selected. The upper confidence bound is the estimated expected reward plus a confidence level inversely proportional to the number of selections. The confidence level is used to weigh the exploration of unknown high-reward arms against the exploitation of known high-reward arms. A high confidence level increases the number of explorations to gather more information about the reward distribution of each arm. Conversely, a low confidence level reduces exploration and utilizes known information more to select high-reward arms.

[0068] The page content display method, apparatus, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the page content display method in this application embodiment is described.

[0069] The page content display method provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms; the software can be an application that implements the page content display method, but is not limited to the above forms.

[0070] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0071] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0072] In the fields of digital and user experience design, especially in user-facing page design, it's crucial to attract users through content displayed in specific page sections (such as marketing content). For example, an insurance marketing page could display coupon giveaways in sections like a tic-tac-toe grid, a spinning wheel, or a gashapon machine. Currently, the common approach to page content display is to fix the user interface (UI) layout and interactive elements of specific sections on the page during the early stages of development. The drawback of this method is that it severely limits the flexibility and personalization of page content display. Specifically, it restricts the page's ability to present diverse content to different users simultaneously, leading to a homogenized user experience and failing to meet the personalized needs of different users.

[0073] Based on this, embodiments of this application provide a page content display method, apparatus, electronic device, and storage medium, aiming to achieve intelligent dynamic optimization of page block content by integrating big data analysis and real-time content optimization technologies, adaptively adjusting page content, improving the flexibility of page content display, and enhancing the attractiveness of page content to users.

[0074] Figure 1 This is an optional flowchart of the page content display method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps 101 to 106.

[0075] Step 101: Display the target page; wherein the target page displays page blocks, and the page blocks are used to display one of the contents of at least two candidate blocks;

[0076] Step 102: Obtain the target user's historical behavioral characteristics information;

[0077] Step 103: Based on the similarity between historical behavior feature information and the content feature information of each candidate block, determine at least one candidate display block content from at least two candidate block contents.

[0078] Step 104: Obtain the target user's behavior data for each candidate display block content to obtain the target block content behavior data;

[0079] Step 105: Based on the target block content behavior data and the auxiliary block content behavior data, determine the display probability of the candidate display block content to obtain the target display probability; wherein, the auxiliary block content behavior data is the behavior data of non-target users towards the candidate display block content.

[0080] Step 106: Display the content of the candidate display blocks within the page blocks according to the target display probability.

[0081] The beneficial effects of this application's embodiments include, but are not limited to: displaying the target page to show candidate block content within its page blocks, while simultaneously acquiring the target user's historical behavioral characteristic information, so as to subsequently perform initial screening of block content based on the target user's personalized characteristics. Based on the similarity between historical behavioral characteristics and the content characteristic information of each candidate block content, at least one candidate block content is determined from multiple candidates. This allows for the initial screening of personalized content for the target user, improving the alignment between the displayed block content and user preferences. Then, behavioral data of the target user and non-target users regarding the candidate block content are acquired, namely, target block content behavioral data and auxiliary block content behavioral data, and the display probability of the candidate block content is determined by combining these two types of behavioral data. This allows for dynamic adjustment of the block content display probability based on the feedback of the target user and the behavioral feedback of the user group, rather than fixing the content displayed on the page in the initial page design stage. This enables adaptive adjustment of page content, thereby improving the flexibility of page content display and enhancing the personalization of page content display.

[0082] In step 101 of some embodiments, the target page is an interactive page displayed to the target user. Specifically, the target page can be a webpage or a mobile app (application) page. It should be noted that the page block is the information display area of ​​the target page.

[0083] In some embodiments, areas at different locations on the target page may include a navigation bar, status bar, title bar, information display area, etc. A page block may be a block within the information display area of ​​the target page (such as the central area of ​​the page).

[0084] In some embodiments, candidate block content refers to content displayed within a page block. Different candidate block contents can be displayed in the page block of the target page for different users. For example, in a car insurance marketing scenario within the fintech field, candidate block content may include car insurance discount recommendations, vehicle coupon recommendations (such as chauffeur service coupons), and so on. Furthermore, the block types for multiple candidate block contents may include, but are not limited to, a 3x3 grid, a spinning wheel, or a gashapon machine. It should be noted that the content format of candidate block content may include any one or more of text, images, and animations; this embodiment does not limit this.

[0085] In step 102 of some embodiments, the historical behavior feature information may include any one or more of the following: historical interaction data of the target user on the page (such as browsing duration, click frequency, conversion path, etc.) and the target user's historical browsing preferences (such as frequently browsing car insurance-related content).

[0086] It should be noted that the conversion path refers to the sequential record of a series of interactive behaviors (such as browsing key pages and clicking) that a user goes through from the moment they come into contact with a page (such as entering the website homepage) to the moment they finally complete a specific target action (also known as the conversion goal, such as placing an order, submitting a form, downloading a file, etc.).

[0087] In another embodiment, historical behavioral characteristic information may also include the target user's geographical location, the time of the behavior, etc.

[0088] In step 103 of some embodiments, candidate block content with a similarity greater than or equal to a preset similarity threshold can be selected as candidate display block content. Specifically, the similarity between historical behavioral feature information and the content feature information of each candidate block content can be calculated using a cosine similarity algorithm. Similarity can also be calculated in other ways, and is not limited to these.

[0089] In step 104 of some embodiments, target block content behavior data refers to the behavior data of the target user towards the candidate display block content. For example, target block content behavior data includes, but is not limited to, browsing duration, click frequency, and conversion path. For instance, in a car insurance marketing scenario within the fintech field, assuming the candidate display block content is a car insurance discount wheel lottery, the number of times the user clicks the button and subsequent conversion information (such as purchasing an insurance policy) can be collected to obtain target block content behavior data. In some embodiments, in response to a target user's contact with the candidate display block content (e.g., performing clicks, browsing, or other operations on the block content), user behavior data (i.e., target block content behavior data) can be collected.

[0090] In step 105 of some embodiments, the target display probability is the display probability of candidate display block content. For example, assuming multiple candidate display block content includes block content A1 and block content A2, then the target display probability of block content A1 can be 30%, and the target display probability of block content A2 can be 70%. It should be noted that non-target users refer to users other than the target users. Auxiliary block content behavior data refers to the behavior data of non-target users towards candidate display block content, such as the number of clicks and return visits. Determining the display probability of block content based on the behavior data of target and non-target users can increase the display probability of block content that is more attractive to users, adaptively adjust the content displayed on the page, and improve the marketing effectiveness of the page.

[0091] In step 106 of some embodiments, one of the candidate display block contents can be randomly selected from multiple candidate display block contents based on the target display probability of each candidate display block content, so as to fairly and randomly display the block content to the target user. Specifically, the candidate display block content can be dynamically rendered when the user visits or refreshes the page.

[0092] Please see Figure 2 In some embodiments, historical behavior feature information includes historical block content access records, and at least two candidate block contents have different block types;

[0093] Step 103 may include, but is not limited to, steps 201 through 203:

[0094] Step 201: Determine the access block type based on the historical block content access records to obtain the historical access block type;

[0095] Step 202: From at least two candidate block contents, search for candidate block contents belonging to the historical access block type to obtain at least one target type block content;

[0096] Step 203: Based on the historical behavior feature information and the similarity with the content feature information of each target type block, determine at least one candidate display block content from at least one target type block content.

[0097] The advantage of this embodiment lies in determining the type of historically accessed blocks based on historical block access records. This identifies the types of blocks browsed by the user, providing a basis for type filtering in subsequent block content display. By searching for candidate block content belonging to the historically accessed block type from at least two candidate block contents, candidate content consistent with the user's historically accessed block types can be prioritized, improving type matching accuracy. Then, based on the similarity between historical behavioral feature information and the content feature information of each target type block content, candidate display block content is determined. This enables accurate recommendations based on the similarity between user behavioral features and content features, thereby improving the flexibility and personalization of page content display.

[0098] In step 201 of some embodiments, the historical access block type is the block type that the target user has accessed. Specifically, the block type may include, but is not limited to, any of the following: 3x3 grid, spinning wheel, gashapon machine, etc.

[0099] In step 202 of some embodiments, the target type block content is candidate block content belonging to the historical access block type. For example, in the insurance marketing scenario in the fintech field, assuming the historical access block type is car insurance, then the type of the target type block content is car insurance.

[0100] In step 203 of some embodiments, target type block content with a similarity greater than a preset threshold between historical behavior feature information and content feature information can be selected to obtain candidate display block content. In another embodiment, candidate display block content can also be determined in other ways, and is not limited thereto.

[0101] Please see Figure 3 In some embodiments, the auxiliary block content behavior data is at least two; step 105 may include, but is not limited to, steps 301 to 304:

[0102] Step 301: Obtain the behavior occurrence time of the content behavior data of each auxiliary block, and calculate the time decay factor based on the behavior occurrence time to obtain the time decay factor;

[0103] Step 302: Calculate the weighted auxiliary behavior data by multiplying the content behavior data of each auxiliary block with the time decay factor.

[0104] Step 303: Calculate the user conversion effect based on the target block content behavior data and weighted auxiliary behavior data corresponding to the same candidate display block content, and obtain the target user conversion effect value corresponding to each candidate display block content.

[0105] Step 304: Update the initial display probability of at least one candidate display block content based on the target user conversion effect value to obtain the target display probability.

[0106] The advantage of this embodiment lies in acquiring the behavior occurrence time of each auxiliary block content behavior data and calculating a time decay factor based on the behavior occurrence time. This allows the introduction of the time decay factor as a dynamic weighting coefficient, thereby quantifying the timeliness of the behavior data. Weighted auxiliary behavior data is obtained by multiplying each auxiliary block content behavior data by the time decay factor, which gives recent behavior data a higher influence and more accurately reflects real-time changes in user interests. The target user conversion effect value is calculated based on the target block content behavior data and weighted auxiliary behavior data corresponding to the same candidate display block content. This allows for the comprehensive quantification of the attractiveness of each candidate display block content to users by combining individual real-time behavior and group weighted behavior data. Then, the initial display probability of the candidate display block content is updated based on the target user conversion effect value. For example, the higher the target user conversion effect value, the higher the target display probability. This dynamically increases the exposure priority of highly attractive content, thereby improving the real-time performance and accuracy of personalized recommendations and adaptively optimizing page content.

[0107] In step 301 of some embodiments, the time decay factor is negatively correlated with the time of the behavior occurrence; for example, the earlier the behavior occurs (i.e., the earlier the behavior), the larger the time decay factor. This allows for assigning higher weight to recent operational behavior data, dynamically strengthening the impact of recent behaviors on probability updates, and improving the real-time performance of personalized recommendations. Specifically, the time decay factor of auxiliary block content behavior data can be calculated based on the behavior occurrence time using a time decay algorithm. Other methods can also be used to calculate the time decay factor, and are not limited to these.

[0108] In step 302 of some embodiments, the weighted auxiliary behavior data is the product of auxiliary block content behavior data and a time decay factor.

[0109] In step 303 of some embodiments, a multi-armed slot machine (MAB) algorithm, such as the Upper Confidence Bound (UCB) algorithm, can be used to calculate the target user conversion effect value based on the target block content behavior data and weighted auxiliary behavior data. In another embodiment, the target user conversion effect value can be calculated by combining the multi-armed slot machine algorithm and the Bayesian optimization algorithm.

[0110] In step 304 of some embodiments, the target display probability is the updated initial display probability. In some embodiments, for example, the target user conversion effect values ​​of multiple candidate display block contents can be sorted from largest to smallest, and the initial display probability of the candidate display block contents can be increased according to the sorting order of the target user conversion effect values, and then normalized to obtain the target display probability. In another embodiment, the display probability can also be updated by other methods, and is not limited to this.

[0111] Please see Figure 4 In some embodiments, the weighted auxiliary behavior data includes weighted auxiliary clicks, weighted auxiliary return visits, and weighted auxiliary conversions, while the target block content behavior data includes target clicks, target return visits, and target conversions.

[0112] Step 303 may include, but is not limited to, steps 401 to 405:

[0113] Step 401: The target users and non-target users corresponding to the same candidate display block content are identified as the first users, and the number of first users is identified as the total number of first users;

[0114] Step 402: Calculate the click-through rate by taking the ratio of the sum of the weighted auxiliary clicks and the target clicks of the first user and the total number of the first users;

[0115] Step 403: Calculate the retention rate by taking the ratio of the sum of the weighted auxiliary return visits of the first user and the target return visits, and the total number of the first user.

[0116] Step 404: Calculate the conversion rate based on the sum of the weighted auxiliary conversion count and the target conversion count of the first user, as well as the total number of the first users;

[0117] Step 405: Perform a weighted summation of click-through rate, retention rate, and conversion rate to obtain the target user conversion effect value corresponding to each candidate display block content; wherein, the target user conversion effect value is inversely proportional to the click-through rate, and the target user conversion effect value is directly proportional to the retention rate and conversion rate.

[0118] The advantage of this embodiment lies in its calculation of the click-through rate (CTR) by dividing the sum of weighted auxiliary clicks and target clicks for the same candidate display block content (target users and non-target users, i.e., the first user) by the total number of first users. The retention rate is calculated by dividing the sum of weighted auxiliary return visits and target return visits by the total number of first users. Simultaneously, the conversion rate is calculated by dividing the sum of weighted auxiliary conversions and target conversions by the total number of first users. This allows for a more comprehensive quantification of the user appeal of the block content by multi-dimensional behavioral data (such as clicks, return visits, and conversions). Then, the target user conversion effect value is obtained by weighted summing of the CTR, retention rate, and conversion rate. The target user conversion effect value is inversely proportional to the CTR, preventing over-recommendation of already exposed content with high CTR and avoiding local optima. This helps recommend undisplayed block content to users, thus balancing the exploration of unknown high-reward (i.e., target user conversion effect value) block content with the display of known high-reward block content, thereby improving the adaptive adjustment capability and personalization of page content display.

[0119] In step 401 of some embodiments, the first user refers to the user (including target users and non-target users) who are shown the same candidate display block content.

[0120] In step 402 of some embodiments, if the first user is a target user, the target click count for the first user is obtained; if the first user is not a target user, the weighted auxiliary click count for the first user is obtained. Then, the sum of the weighted auxiliary click count and the target click count is calculated, and then the ratio of this sum of click counts to the total number of first users is calculated to obtain the click-through rate.

[0121] In step 403 of some embodiments, if the first user is a target user, the target number of return visits for the first user is obtained; if the first user is not a target user, the weighted auxiliary number of return visits for the first user is obtained.

[0122] In step 404 of some embodiments, if the first user is a target user, the target conversion count of the first user is obtained; if the first user is not a target user, the weighted auxiliary conversion count of the first user is obtained.

[0123] In step 405 of some embodiments, the target user conversion effect value is a weighted sum of click-through rate, retention rate, and conversion rate. Specifically, the target user conversion effect value can be calculated using a Multi-Armed Slots (MAB) algorithm, where retention rate and conversion rate are used as reward signals. Other methods can also be used to calculate the target user conversion effect value, and this is not a limitation.

[0124] Please see Figure 5 In some embodiments, step 405 may include, but is not limited to, steps 501 to 503:

[0125] Step 501: Perform a weighted summation based on the click-through rate, retention rate, conversion rate, and a preset initial weighting set to obtain the initial user conversion effect value; wherein, the initial weighting set is used to represent the combination of the weights of the click-through rate, retention rate, and conversion rate.

[0126] Step 502: Using a Bayesian optimization algorithm, based on the initial user conversion effect value and initial display probability corresponding to the content of each candidate display block, the initial weight reorganization is updated to obtain the target weight reorganization.

[0127] Step 503: Perform a weighted summation based on click-through rate, retention rate, conversion rate, and target weight to obtain the target user conversion effect value corresponding to each page block content.

[0128] The advantage of this embodiment lies in obtaining the initial user conversion effect value by weighted summation based on click-through rate, retention rate, conversion rate, and a preset initial weighting, thus providing input for subsequent optimization. Using a Bayesian optimization algorithm, the initial weighting is updated to obtain the target weighting based on the initial user conversion effect value and initial display probability corresponding to each candidate display block content. This allows for dynamic adjustment of the weight allocation of click-through rate, retention rate, and conversion rate, avoiding the drawback of using fixed weights that cannot adapt to changes in content attractiveness. Then, the target user conversion effect value is obtained by weighted summation based on click-through rate, retention rate, conversion rate, and the target weighting. This allows the Bayesian-optimized weights to be applied to effect evaluation, improving the accuracy of the target user conversion effect value and thus enhancing the adaptive adjustment capability and flexibility of page content display.

[0129] In step 501 of some embodiments, the initial weighting includes a first initial weight for click-through rate, a second initial weight for retention rate, and a third initial weight for conversion rate.

[0130] In step 502 of some embodiments, the target weight refactoring is an updated initial weight refactoring. For example, the target weight refactoring includes a first target weight for click-through rate, a second target weight for retention rate, and a third target weight for conversion rate.

[0131] In some embodiments, a Bayesian optimization model, such as a Gaussian Process (GSP) model or a TPE model, can be trained based on the initial user conversion effect value and initial display probability corresponding to each candidate display block content. This Bayesian optimization model can then predict the probability distribution of user conversion effect values ​​under different display probabilities. Specifically, the initial weighting structure can be updated using the Bayesian optimization model's acquisition function, such as the Expected Improvement (EP) function, to find the optimal display ratio that maximizes the weighted benefits of click-through rate, retention rate, and conversion rate.

[0132] In step 503 of some embodiments, the target user conversion performance value is used to characterize the weighted revenue of click-through rate, retention rate, and conversion rate.

[0133] Please see Figure 6 In some embodiments, the number of non-target users is at least two; prior to step 303, the page content display method may also include, but is not limited to, steps 601 to 603:

[0134] Step 601: Determine the historical behavioral feature information of the target user as the first historical behavioral feature information, and obtain the second historical behavioral feature information of each non-target user.

[0135] Step 602: Calculate the similarity based on the first historical behavioral feature information and the second historical behavioral feature information to obtain the behavioral feature similarity of each non-target user.

[0136] Step 603: If the similarity of the behavioral features of non-target users is less than or equal to the preset similarity threshold, delete the weighted auxiliary behavioral data of non-target users.

[0137] The advantage of this embodiment lies in obtaining the second historical behavioral feature information of non-target users and calculating the similarity between the first historical behavioral feature information (i.e., the historical behavioral feature information of the target user) and the second historical feature information to obtain the behavioral feature similarity between the target user and each non-target user. This quantifies the degree of interest and preference matching between non-target users and the target user, accurately identifying user groups with similar interests. If the behavioral feature similarity is low (less than or equal to a preset threshold), the weighted auxiliary behavioral data of the non-target user is deleted. This filters out the behavioral data of non-target users with low similarity, preventing such data from interfering with subsequent conversion effect calculations. This allows only non-target user behavioral data that is highly similar to the behavioral features (such as content browsing preferences) of the target user to be retained for subsequent display probability updates, thereby improving the personalization of page block content display.

[0138] In step 601 of some embodiments, the first historical behavioral feature information refers to the historical behavioral feature information of the target user. The second historical behavioral feature information refers to the historical behavioral feature information of a non-target user. Specifically, the historical behavioral feature information may include, but is not limited to, the user's historical behavior, behavior time, user preferences, geographical location, etc.

[0139] In step 602 of some embodiments, the cosine similarity between the first historical behavioral feature information and the second historical behavioral feature information can be calculated to obtain the behavioral feature similarity. In some embodiments, the similarity between the hash value of the first historical behavioral feature information and the hash value of the second historical behavioral feature information can also be calculated to obtain the behavioral feature similarity.

[0140] In step 603 of some embodiments, if the similarity of the behavioral features of a non-target user is less than or equal to a preset similarity threshold, it indicates that the non-target user has a low similarity to the target user. Therefore, the weighted auxiliary behavioral data of the non-target user is deleted to avoid the data interfering with subsequent probability updates. It should be noted that the similarity threshold can be set or adjusted according to needs, and this application embodiment does not limit it in this regard.

[0141] Please see Figure 7 In some embodiments, step 602 may include, but is not limited to, steps 701 to 702:

[0142] Step 701: Encode the first historical behavior feature information using hash value to obtain the first behavior feature hash value, and encode the second historical behavior feature information using hash value to obtain the second behavior feature hash value;

[0143] Step 702: Calculate the hash similarity based on the hash value of the first behavioral feature and the hash value of each second behavioral feature to obtain the behavioral feature similarity of each non-target user.

[0144] The advantage of this embodiment lies in that by hashing the first historical behavioral feature information to obtain a first behavioral feature hash value, and by hashing the second historical behavioral feature information to obtain a second behavioral feature hash value, Locality Sensitive Hash (LSH) techniques such as MinHash can be used to compress high-dimensional behavioral features into low-dimensional hash values, reducing computational complexity. Hash similarity is calculated based on the first behavioral feature hash value and each second behavioral feature hash value to obtain the behavioral feature similarity for each non-target user. This allows for the quantification of the degree of similarity between the behavioral features of non-target users and target users using hash similarity, thereby accurately identifying user groups with similar interests and improving the personalization of page content display.

[0145] In step 701 of some embodiments, the user's feature information (such as first historical behavior feature information or second historical behavior feature information) can be encoded to obtain a feature vector. For example, the user's feature information can be converted into a numerical form of a feature vector using a one-hot encoding method or an embedding method. Then, a consistent hashing algorithm (such as the MD5 algorithm or the SHA-256 algorithm) can be used to perform a hash operation on the feature vector to generate a fixed-length hash value (such as the first row being the feature hash value or the second row being the feature hash value).

[0146] In step 702 of some embodiments, the behavioral feature similarity can be the Hamming distance between the first behavioral feature hash value and each second behavioral feature hash value. In another embodiment, the behavioral feature similarity can also be other types of similarity, such as Jaccard similarity, etc., and is not limited thereto.

[0147] Please see Figure 8 In one application example, the display probability of page block content can be updated using A / B testing. For instance, when multiple users access a target page, a hash algorithm can be used to group the overall traffic of these users (also known as traffic stratification). Specifically, traffic can be grouped based on the user's behavioral characteristic hash value; for example, the top 50% of users with the highest behavioral characteristic hash values ​​can be assigned to traffic 1, and the bottom 50% can be assigned to traffic 2. By using a hash algorithm, it can be ensured that the same user is always assigned to a fixed traffic group, avoiding interference from different traffic groups, and supporting differentiated display ratio strategies for different groups. Then, for users in each traffic group, block content can be allocated (i.e., displayed) to users based on the initial display probability. For example, for users in traffic 1, block content C1 from test group 1-A can be randomly displayed to 50% of users, and block content C2 from test group 1-B can be randomly displayed to the other 50% of users. For users in traffic 2, 50% of users can be randomly shown block content C3 from Experiment 2-A; and the other 50% of users can be randomly shown block content C4 from Experiment 2-B.

[0148] In some embodiments, it should be noted that the block content corresponding to each user in each traffic group is fixed. For example, the user of traffic group 1 can be shown block content C1 of test group 1-A or block content C2 of test group 1-B, but the user cannot be shown block content C3 of test group 2-A (e.g., ...). Figure 8 (As indicated by the red cross in the image).

[0149] It should be noted that A / B testing involves randomly dividing user traffic into multiple groups and displaying different versions of product design or content to each group. By collecting user behavior data (such as click-through rate and conversion rate), it verifies which version is more effective in achieving business goals. This application's embodiment uses A / B testing to display different content blocks in the same location on a target page (such as a car insurance promotion page), allowing for precise testing of the user conversion effects of various content types (such as marketing recommendations), thereby improving the refined operational capabilities of the campaign.

[0150] Please see Figure 9 This application also provides a page content display device that can implement the above-described page content display method. The device includes:

[0151] Page display module 901 is used to display the target page; wherein, the target page displays page blocks, and the page blocks are used to display one of the contents of at least two candidate blocks;

[0152] Historical information acquisition module 902 is used to acquire historical behavioral characteristic information of the target user;

[0153] The block content determination module 903 is used to determine at least one candidate display block content from at least two candidate block contents based on the similarity between historical behavior feature information and the content feature information of each candidate block content.

[0154] The behavior data acquisition module 904 is used to acquire the behavior data of the target user for each candidate display block content, and obtain the target block content behavior data;

[0155] The display probability determination module 905 is used to determine the display probability of candidate display block content based on the target block content behavior data and the auxiliary block content behavior data, so as to obtain the target display probability; wherein, the auxiliary block content behavior data is the behavior data of non-target users towards the candidate display block content;

[0156] The block content display module 906 is used to display candidate block content within a page block based on the target display probability.

[0157] In one embodiment, the page content display device further includes an auxiliary behavior data filtering module, configured to: determine the historical behavior feature information of the target user as the first historical behavior feature information, and obtain the second historical behavior feature information of each non-target user; perform similarity calculation based on the first historical behavior feature information and the second historical behavior feature information to obtain the behavior feature similarity of each non-target user; if the behavior feature similarity of the non-target user is less than or equal to a preset similarity threshold, delete the weighted auxiliary behavior data of the non-target user.

[0158] The specific implementation of the page content display device is basically the same as the specific implementation of the page content display method described above, and will not be repeated here.

[0159] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described page content display method. This electronic device can include any smart terminal such as a tablet computer or an in-vehicle computer.

[0160] Please see Figure 10 , Figure 10 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0161] The processor 1001 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0162] The memory 1002 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1002 and is called and executed by the processor 1001 to execute the page content display method of the embodiments of this application.

[0163] Input / output interface 1003 is used to implement information input and output;

[0164] The communication interface 1004 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0165] Bus 1005 transmits information between various components of the device (e.g., processor 1001, memory 1002, input / output interface 1003, and communication interface 1004);

[0166] The processor 1001, memory 1002, input / output interface 1003 and communication interface 1004 are connected to each other within the device via bus 1005.

[0167] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described page content display method.

[0168] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0169] It should be noted that the software tools or components not belonging to our company that appear in the embodiments of this application are merely examples and do not represent actual use.

[0170] The embodiments described in this application are intended to more clearly illustrate the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0171] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0172] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0173] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0174] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. 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 comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0175] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0176] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. The coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, or indirect coupling or communication connection between the apparatus or units, and may be electrical, mechanical, or other forms.

[0177] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0178] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0179] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0180] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for displaying page content, characterized in that, The method includes: Display the target page; wherein the target page displays page blocks, and the page blocks are used to display one of at least two candidate block contents; Obtain historical behavioral characteristics information of the target user; Based on the similarity between the historical behavior feature information and the content feature information of each candidate block content, at least one candidate display block content is determined from at least two candidate block contents. Obtain the target user's behavior data for each candidate display block content to obtain the target block content behavior data; Based on the target block content behavior data and the auxiliary block content behavior data, the display probability of the candidate display block content is determined to obtain the target display probability; wherein, the auxiliary block content behavior data is the behavior data of non-target users towards the candidate display block content; The content of the candidate display block is displayed within the page block according to the target display probability.

2. The method according to claim 1, characterized in that, The auxiliary block content behavior data consists of at least two elements; The step of determining the display probability of the candidate display block content based on the target block content behavior data and the auxiliary block content behavior data, to obtain the target display probability, includes: The behavior occurrence time of each auxiliary block content behavior data is obtained, and a time decay factor is calculated based on the behavior occurrence time to obtain the time decay factor; Weighted auxiliary behavior data is obtained by multiplying the content behavior data of each auxiliary block with the time decay factor. Based on the target block content behavior data and the weighted auxiliary behavior data corresponding to the same candidate display block content, the user conversion effect is calculated to obtain the target user conversion effect value corresponding to each candidate display block content; Based on the target user conversion effect value, the initial display probability of at least one of the candidate display blocks is updated to obtain the target display probability.

3. The method according to claim 2, characterized in that, The weighted auxiliary behavior data includes weighted auxiliary click count, weighted auxiliary return visit count, and weighted auxiliary conversion count; the target block content behavior data includes target click count, target return visit count, and target conversion count. The step of calculating user conversion effect based on the target block content behavior data and the weighted auxiliary behavior data corresponding to the same candidate display block content, to obtain the target user conversion effect value corresponding to each candidate display block content, includes: The target user and the non-target user corresponding to the same candidate display block content are identified as the first user, and the number of the first users is identified as the total number of the first users; The click-through rate is calculated by taking the ratio of the sum of the weighted auxiliary clicks and the target clicks of the first user, and the total number of the first users. The retention rate is calculated by taking the ratio of the sum of the weighted auxiliary return visits and the target return visits of the first user, and the total number of the first users. The conversion rate is calculated based on the sum of the weighted auxiliary conversion count and the target conversion count of the first user, as well as the total number of the first users. The target user conversion effect value is obtained by weighted summation of the click-through rate, retention rate, and conversion rate for each candidate display block content; wherein the target user conversion effect value is inversely proportional to the click-through rate and directly proportional to the retention rate and conversion rate.

4. The method according to claim 3, characterized in that, The step of weighted summation based on the click-through rate, retention rate, and conversion rate to obtain the target user conversion effect value corresponding to each candidate display block content includes: The initial user conversion effect value is obtained by weighting and summing the click-through rate, retention rate, conversion rate and a preset initial weighting set; wherein, the initial weighting set is used to represent the combination of the weights of the click-through rate, retention rate and conversion rate. Using a Bayesian optimization algorithm, the initial weight reorganization is updated based on the initial user conversion effect value and the initial display probability corresponding to the content of each candidate display block, to obtain the target weight reorganization; The target user conversion effect value corresponding to each page block content is obtained by weighted summation based on the click-through rate, retention rate, conversion rate, and target weight.

5. The method according to claim 2, characterized in that, The number of non-target users is at least two; Before calculating the user conversion effect based on the target block content behavior data and the weighted auxiliary behavior data corresponding to the same candidate display block content, and obtaining the target user conversion effect value corresponding to each candidate display block content, the method further includes: The historical behavioral feature information of the target user is determined as the first historical behavioral feature information, and the second historical behavioral feature information of each non-target user is obtained; Based on the first historical behavior feature information and the second historical behavior feature information, a similarity calculation is performed to obtain the behavior feature similarity of each non-target user. If the similarity of the behavioral features of the non-target user is less than or equal to a preset similarity threshold, the weighted auxiliary behavioral data of the non-target user is deleted.

6. The method according to claim 5, characterized in that, The step of calculating the similarity based on the first historical behavior feature information and the second historical behavior feature information to obtain the behavior feature similarity of each non-target user includes: The first historical behavior feature information is hashed to obtain the first behavior feature hash value, and the second historical behavior feature information is hashed to obtain the second behavior feature hash value. The hash similarity is calculated based on the first behavioral feature hash value and each of the second behavioral feature hash values ​​to obtain the behavioral feature similarity of each non-target user.

7. The method according to any one of claims 1 to 6, characterized in that, The historical behavior feature information includes historical block content access records, and at least two of the candidate block contents have different block types; The step of determining at least one candidate display block content from at least two candidate block contents based on the similarity between the historical behavior feature information and the content feature information of each candidate block content includes: The access block type is determined based on the access records of the historical block content, thus obtaining the historical access block type; From at least two candidate block contents, find the candidate block contents that belong to the historical access block type to obtain at least one target type block content; Based on the historical behavior feature information and the similarity with the content feature information of each target type block content, at least one candidate display block content is determined from at least one target type block content.

8. A page content display device, characterized in that, The device includes: A page display module is used to display a target page; wherein the target page displays page blocks, and the page blocks are used to display one of at least two candidate block contents; The historical information acquisition module is used to acquire historical behavioral characteristic information of the target user; The block content determination module is used to determine at least one candidate display block content from at least two candidate block contents based on the similarity between the historical behavior feature information and the content feature information of each candidate block content; The behavior data acquisition module is used to acquire the behavior data of the target user for each candidate display block content, and obtain the target block content behavior data; The display probability determination module is used to determine the display probability of the candidate display block content based on the target block content behavior data and the auxiliary block content behavior data, so as to obtain the target display probability; wherein, the auxiliary block content behavior data is the behavior data of non-target users towards the candidate display block content; The block content display module is used to display the candidate display block content within the page block according to the target display probability.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the page content display method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the page content display method according to any one of claims 1 to 7.

Images