Product output method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, can be applied to business system platforms such as financial science and technology, and discloses a product output method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining user features of a target user according to behavior data of the target user for a product output page in a target time period; according to the product data in the to-be-output product library, obtaining product features and constraint condition features of the to-be-output product; based on the user features, the product features and the constraint condition features, generating a product output result through a pre-trained product output model; displaying the product output result to the target user in a designated area of the product output page; therefore, the accuracy and feasibility of product output can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a product output method and device, computer equipment and computer readable storage medium. BACKGROUND

[0002] At present, with the rapid development of the Internet and e-commerce, product output systems play an increasingly important role in improving user experience and promoting sales. Traditional product output systems mainly rely on user historical purchase records and browsing behavior data, and output products through simple association rules or collaborative filtering algorithms. However, these methods have some limitations and cannot meet the increasingly complex and diverse user needs. That is, the product output method in the prior art has the following deficiencies: 1. Lack of dynamicity: User needs and preferences change over time and context, and traditional product output systems cannot capture these changes in real time, resulting in poor accuracy of product output results.

[0003] 2. Lack of constraints: In practical applications, product output systems need to consider various constraints such as budget limitations, compliance requirements, etc. However, traditional product output systems often ignore these constraints, resulting in poor feasibility of product output results and not meeting actual business needs.

[0004] In the field of financial technology, product output systems need to consider the compliance, risk level and financial status of users, etc. For example, some financial products may only be suitable for users with specific risk tolerance or income levels, and traditional product output systems may not accurately identify these constraints, resulting in the output of financial products that do not meet the user's financial status.

[0005] Therefore, how to provide a product output method, device, computer equipment and computer readable storage medium that can effectively improve the accuracy and feasibility of product output is a problem that needs to be solved by the technical personnel in the field. SUMMARY

[0006] In view of the above deficiencies of the prior art, the present application aims to provide a product output method, device, computer equipment and computer readable storage medium, which can effectively improve the accuracy and feasibility of product output.

[0007] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides a product output method, comprising: obtaining user features of a target user according to behavior data of the target user on a product output page in a target time period; According to product data in a product library to be output, product features and constraint condition features of a product to be output are acquired; Based on the user features, the product features and the constraint condition features, a product output result is generated through a pre-trained product output model; The product output result is displayed to the target user in a specified area of the product output page.

[0008] In a second aspect, the present application provides a product output device, comprising: A first acquisition module is configured to acquire user features of a target user according to behavior data of the target user on a product output page within a target time period; A second acquisition module is configured to acquire product features and constraint condition features of a product to be output according to product data in a product library to be output; A result generation module is configured to generate a product output result based on the user features, the product features and the constraint condition features through a pre-trained product output model; A result display module is configured to display the product output result to the target user in a specified area of the product output page.

[0009] In a third aspect, the present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the product output method as described above when executing the computer program.

[0010] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable by a processor to implement the product output method as described above.

[0011] Compared with the prior art, the present application provides a product output method, device, computer device and computer readable storage medium, wherein user features of a target user are acquired according to behavior data of the target user on a product output page within a target time period; product features and constraint condition features of a product to be output are acquired according to product data in a product library to be output; a product output result is generated based on the user features, the product features and the constraint condition features through a pre-trained product output model; and the product output result is displayed to the target user in a specified area of the product output page; thereby the accuracy and feasibility of product output can be effectively improved through the present application. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only represent some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0013] Figure 1 An application environment schematic diagram of a product output method provided by an embodiment of the present application.

[0014] Figure 2 A flowchart of a product output method provided by an embodiment of the present application.

[0015] Figure 3 A program module schematic diagram of a product output device provided by an embodiment of the present application.

[0016] Figure 4 A structure schematic diagram of a computer device provided by an embodiment of the present application.

[0017] Figure 5 Another structure schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort fall within the scope of the present application.

[0019] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0020] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0021] As used in the description of the application and the appended claims, the term "if' can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the described condition or event]" or "in response to detecting [the described condition or event]."

[0022] In addition, the description in the description of the application and the appended claims, the terms "first", "second", "third" and the like are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0023] In the description of the application, the reference "one embodiment" or "some embodiments" and the like means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in further some embodiments" and the like appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized.

[0024] It should be understood that the size of the serial number of each step in the following embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the application.

[0025] In order to illustrate the technical solutions of the application, the following specific embodiments are described.

[0026] An embodiment of the application provides a product output method, which can be applied to, for example Figure 1In the illustrated application environment, the client and the server communicate through a network. The client includes, but is not limited to, a palm computer, a desktop computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud computer device, a personal digital assistant (PDA), and the like computer device. The server can be a standalone server or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, and the like basic cloud computing services.

[0027] Referring to Figure 2 An embodiment of the present application provides a product output method, wherein the method comprises the following steps: S100, obtaining user characteristics of a target user according to behavior data of the target user on a product output page in a target time period; S200, obtaining product characteristics and constraint condition characteristics of a product to be output according to product data in a product library to be output; S300, generating a product output result based on the user characteristics, the product characteristics, and the constraint condition characteristics through a pre-trained product output model; S400, displaying the product output result to the target user in a specified area of the product output page.

[0028] In specific implementation, the product output method of the embodiment can effectively improve the accuracy and feasibility of product output by comprehensively considering user characteristics, product characteristics, and constraint condition characteristics, and generating a product output result by using a pre-trained product output model. The specific analysis is as follows: 1. Comprehensive acquisition of user characteristics: by analyzing the behavior data of the target user on the product output page in the target time period, the user characteristics are obtained. This not only includes the basic information of the user (such as age, gender, occupation, etc.), but also covers the dynamic data such as the user's historical purchase record, browsing behavior, and clicking behavior. This comprehensive user characteristic acquisition method can more accurately capture the real-time needs and preference changes of the user, thereby providing a basis for generating accurate product output results.

[0029] 2. Comprehensive consideration of product features and constraint conditions: Obtain product features and constraint condition features from the product library to ensure that the output results meet user needs and actual business requirements. Product features include basic information such as price, category, and sales, while constraint condition features include budget limits, compliance requirements, and inventory conditions. This comprehensive consideration ensures the feasibility and effectiveness of the output results in actual applications, avoiding the output of products that do not meet business rules.

[0030] 3. Intelligent output of pre-trained models: Based on user features, product features, and constraint condition features, generate product output results through pre-trained product output models. Pre-trained models use advanced machine learning or deep learning algorithms to automatically learn the complex relationship between users and products, generating more accurate product output results. In addition, pre-trained models can be updated in real time through online learning mechanisms, further improving the timeliness and accuracy of product output results.

[0031] 4. Display of output results: Display product output results in designated areas of the product output page, and improve user engagement and experience through optimized product display strategies. Product display strategies include page layout, style design, and interactive functions, which can dynamically adjust the display of product output results according to user preferences and behaviors. This optimized product display strategy not only attracts user attention but also improves user trust and acceptance of product output results.

[0032] Through the above steps, the method can achieve the following technical effects: 1. Improve output accuracy: By comprehensively obtaining user features and product features, combined with the intelligent output of pre-trained models, it can more accurately match user needs and product characteristics, thereby improving the accuracy of product output results.

[0033] 2. Enhance output feasibility: By considering constraint condition features, ensure that product output results meet actual business requirements, avoid output of products that do not meet business rules, thereby enhancing the feasibility of product output results.

[0034] 3. Improve user experience: Through optimized product display strategies, product output results can be displayed to users in a more attractive way, improving user engagement and experience, and further improving the overall effectiveness of the product output system.

[0035] That is, by comprehensively considering user features, product features, and constraint condition features, using pre-trained output models, and combining optimized product display strategies, the method can effectively improve the accuracy and feasibility of product output, suitable for various business scenarios and user groups.

[0036] Understandably, the product output method provided by the embodiments of the present application can also be applied to product output scenarios related to the field of financial technology. The following is a specific example: Suppose there is a financial technology platform that provides various financial products such as wealth management products, insurance products, and credit cards. The goal of the platform is to provide personalized product output to users to improve user experience and promote sales. The following is a specific application of the embodiments of the present application in this scenario: 1. Comprehensive acquisition of user characteristics The platform acquires user characteristics by analyzing the behavior data of target users on the product output page within the target time period. The specific steps are as follows: User basic information: Acquire the user's age, gender, occupation, income level, risk tolerance, and other basic information.

[0037] Historical behavior data: Analyze the user's historical purchase records, browsing behavior, click behavior, dwell time, and other dynamic data. For example, the user has browsed the wealth management product page multiple times in the past month but has not made a purchase.

[0038] Real-time behavior data: Real-time monitoring of user behavior on the platform, such as currently browsing pages, search keywords, etc. For example, the user is currently searching for low-risk wealth management products.

[0039] 2. Comprehensive consideration of product characteristics and constraint conditions The platform acquires product characteristics and constraint condition characteristics from the product library to be output, and the specific steps are as follows: Product characteristics: Acquire the basic information of the product to be output, such as the product period, yield, risk level of wealth management products; the scope of protection, premium, and protection period of insurance products.

[0040] Constraint condition characteristics: Consider actual business needs, such as budget constraints, compliance requirements, product inventory, etc. For example, some wealth management products may only be suitable for users with specific risk tolerance, and some insurance products may need to meet specific compliance requirements.

[0041] 3. Intelligent output of pre-trained model Based on user characteristics, product characteristics, and constraint condition characteristics, generate product output results through a pre-trained output model, and the specific steps are as follows: Model training: Use historical user data, product data, and constraint condition data to train a deep learning model (such as a neural network). This model can learn the complex relationship between users and products combined with constraint conditions to generate personalized product output results.

[0042] Product output: Based on the user's user characteristics, product characteristics and constraint characteristics, generate product output results, and ensure that the product output results meet all the constraints when generating the product output results. For example, the output financial products must meet the user's budget limit and risk tolerance.

[0043] 4. Optimized product display strategy Display the product output results in the designated area of the product output page, and improve the user's participation and experience through the optimized product display strategy. The specific steps are as follows: Page layout: dynamically adjust the display position of the product output results according to the user's preferences and behavior history. For example, display the output financial products in the page area that the user browses most frequently.

[0044] Style design: automatically generate personalized output text and display layout based on user behavior data. For example, if the user pays more attention to the yield, the yield information of the product can be highlighted.

[0045] Interactive function: provide user interaction functions such as clicking, sliding, viewing details, etc. For example, the user can click on the output financial products to view detailed product information and purchase process.

[0046] Through the product output method provided by the present application, the platform can provide accurate, feasible and business demand conforming financial product output for users, and can improve user experience and purchase conversion rate.

[0047] Further, in one embodiment, the product output method, wherein the user characteristics of the target user are obtained according to the behavior data of the target user on the product output page in the target time period, specifically comprising the steps of: Collect the behavior data of the target user on the product output page in the target time period; Preprocess the behavior data, and extract features from the preprocessed behavior data to obtain the initial user characteristics of the target user; Verify whether the initial user characteristics meet the format input requirements of the product output model, and when the initial user characteristics meet the format input requirements, use the initial user characteristics as the user characteristics of the target user.

[0048] In specific implementation, the specific implementation process of the steps of the present embodiment is approximately as follows: 1. Collecting behavior data In the target time period, the behavior data of the target user is collected in real time through the front-end and back-end systems of the product output page. These behavior data include the user's basic information, browsing history, click behavior, dwell time, search keywords, purchase records, etc. Using the front-end JavaScript tracking code and the back-end log recording system, various behavior data of the user on the page are collected and stored in the server's database.

[0049] 2. Preprocessing behavior data The collected behavior data is cleaned and formatted to remove invalid or duplicate data records, ensuring data quality and consistency. Data cleaning tools such as the Pandas library are used to remove duplicates, fill missing values, and convert data formats, etc. For example, convert the timestamp to a uniform format.

[0050] 3. Feature extraction Feature extraction is performed on the preprocessed behavior data to extract features that reflect user behavior patterns and preferences. Machine learning algorithms such as clustering analysis and decision trees or deep learning algorithms such as neural networks are used to analyze behavior data and extract key features.

[0051] 4. Verify feature format Verify whether the extracted initial user features meet the input format requirements of the product output model. This includes checking the type, dimension, range, etc. of the features to ensure they meet the model's expectations. Write a verification script to check whether the feature data format meets the model's input requirements. For example, ensure that the feature data is numerical or categorical, and that the dimension and range meet the model's input specifications.

[0052] 5. Feature confirmation When the initial user features meet the input format requirements of the product output model, these features are used as the user features of the target user for subsequent product output model input. The verified feature data is stored in the required format for model input, such as JSON or CSV files, for subsequent model inference.

[0053] Through the above implementation process, the user features of the target user can be effectively obtained, providing high-quality data support for subsequent product output.

[0054] Further, in one embodiment, the product output method, wherein the product feature and constraint condition feature of the product to be output are obtained according to the product data in the product library to be output, specifically comprising the steps of: constructing a product library to be output according to the output content of the product output page; extracting initial product features and initial constraint condition features of the product to be output according to the product data in the product library to be output; verify whether the initial product features and the initial constraint condition features meet the format input requirements of the product output model, and when the initial product features and the initial constraint condition features meet the format input requirements, take the initial product features and the initial constraint condition features as the product features and the constraint condition features of the product to be output respectively.

[0055] In implementation, the specific implementation process of the embodiment steps is as follows: 1. Construct a product library According to the output content of the product output page, filter out products that meet the output theme and target, and construct a product library to be output. This step ensures that the products in the product library are related to the content of the output page, improving the relevance and pertinence of the output.

[0056] 2. Extract initial product features and constraint condition features Analyze the product data in the product library to be output, and extract the initial product features and the initial constraint condition features of each product. Product features include basic information of the product (such as price, category, yield, etc.), and constraint condition features include budget limits, compliance requirements, sales quotas, etc.

[0057] 3. Verify feature format Verify whether the extracted initial product features and initial constraint condition features meet the input format requirements of the product output model. This includes checking whether the type, dimension, range, etc. of the features meet the expectations of the model.

[0058] 4. Feature confirmation When the initial product features and the initial constraint condition features meet the input format requirements of the product output model, take these features as the product features and the constraint condition features of the product to be output respectively, which are used for the input of the subsequent product output model.

[0059] Through the above implementation process, the product features and the constraint condition features of the product to be output can be effectively obtained, providing high-quality data support for subsequent product output.

[0060] Further, in one embodiment, the product output method, wherein the product output result is generated based on the user features, the product features and the constraint condition features through a pre-trained product output model, specifically including steps of: Collect a plurality of historical samples related to product output, clean and label the plurality of historical samples to obtain a training data set; Train a pre-set deep learning model using the training data set, and when the trained deep learning model meets a pre-set performance indicator, obtain a product output model; inputting the user features, the product features, and the constraint features into the product output model to generate a product output result.

[0061] Further, the product output method, wherein the pre-set deep learning model is trained using the training data set, and when the trained deep learning model meets a pre-set performance indicator, a product output model is obtained, specifically including steps of: dividing the training data set into a training set, a validation set, and a test set, and training a pre-set deep learning model using the training set; evaluating the trained deep learning model on the validation set, and optimizing the deep learning model according to the evaluation result; testing the optimized deep learning model on the test set, and when the deep learning model meets a pre-set performance indicator, generating a product output model.

[0062] In specific implementation, the specific implementation process of the steps of the embodiment is approximately as follows: 1. Collecting historical samples Collecting a number of historical samples related to product output, which include historical user data, product data, constraint condition data, and feedback data (such as click rate, conversion rate, etc.) of product output result, etc.

[0063] 2. Data cleaning and labeling Cleaning the collected historical samples to remove invalid or duplicate data records, and ensuring the quality and consistency of the data.

[0064] Labeling the cleaned data, which includes user features, product features, constraint condition features, and labels (such as whether to click, whether to purchase, etc.) of product output result, etc.

[0065] 3. Dividing data set Dividing the cleaned and labeled training data set into a training set, a validation set, and a test set. The usual ratio can be 70% training set, 15% validation set, and 15% test set.

[0066] 4. Model training Training a pre-set deep learning model using the training set. Selecting a suitable deep learning framework (such as TensorFlow, PyTorch) and model architecture (such as neural network, convolutional neural network, recurrent neural network, etc.).

[0067] 5. Model evaluation and optimization Evaluating the trained deep learning model on the validation set, and the evaluation indicators can include accuracy, recall rate, F1 score, AUC, etc.

[0068] According to the evaluation results, optimize the model, adjust the structure or hyperparameters of the model to improve the performance of the model.

[0069] 6. Model testing and verification Test the optimized deep learning model on the test set to verify the final performance of the model.

[0070] When the model meets the preset performance indicators (such as accuracy higher than a certain threshold), confirm the model as a product output model.

[0071] 7. Input features Input user features, product features, and constraint condition features into the trained product output model.

[0072] 8. Generate output results The model generates product output results based on the input features, which can include the output product list and its ranking.

[0073] Through the above implementation process, the product output model can be effectively trained and optimized to generate high-quality product output results, improving the accuracy and feasibility of the product output system.

[0074] Further, in one embodiment, the product output method, wherein the product output result contains a plurality of target products to be output, and the product output result is displayed to the target user in a specified area of the product output page, specifically including the steps of: According to the preset product ranking strategy, the generated target products are sorted to generate a product output set; According to the preset product display strategy, the product output set is displayed to the target user in a specified area of the product output page.

[0075] Further, the product output method, wherein the product output result is displayed to the target user in a specified area of the product output page according to the preset product display strategy, specifically including the steps of: According to the product display requirements, a product display strategy is constructed in advance; According to the configuration information of the product output page, the generated product output set is standardized; According to the product display strategy, the standardized product output set is displayed to the target user in a specified area of the product output page.

[0076] In specific implementation, the specific implementation process of the steps of the present embodiment is as follows: 1. Product ranking According to the preset product sorting strategy (such as relevance, user preference, product popularity, etc.), the generated multiple target products are sorted and processed to generate a product output set.

[0077] 2. Building display strategy According to the product display requirements, a product display strategy is constructed in advance, including the layout, style, and interaction design of the product output set. For example, the display style (such as card type, list type), layout (such as front page output position, sidebar output position), and interaction function (such as click, slide, and detail view) of the product output set are defined.

[0078] 3. Standardization processing According to the configuration information of the product output page, the generated product output set is standardized. For example, the product output set is formatted to ensure that the data format (such as JSON, XML) and style (such as font, color) meet the page configuration.

[0079] 4. Product output set display According to the product display strategy, the standardized product output set is displayed to the target user in the specified area of the product output page. For example, the standardized product output set is dynamically displayed in the specified area of the product output page using front-end technology (such as HTML, CSS, JavaScript). Specifically, the output card can be dynamically generated using JavaScript and inserted into the output position of the product output page.

[0080] Through the above implementation process, the standardized product output set can be effectively displayed to the target user, and the user experience and output effect of the product output system can be improved.

[0081] As can be seen from the above method embodiments, the product output method provided by the present application includes: obtaining user characteristics of a target user according to behavior data of the target user in a target time period for a product output page; obtaining product characteristics and constraint condition characteristics of a product to be output according to product data in a product library to be output; generating a product output result based on the user characteristics, the product characteristics, and the constraint condition characteristics through a pre-trained product output model; and displaying the product output result to the target user in a specified area of the product output page. In this way, the method of the present application can effectively improve the accuracy and feasibility of product output.

[0082] It should be understood that although the present application provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps can be included based on routine or non-creative labor, and the operation steps are not necessarily executed in the order of the embodiments or flowcharts. The order of steps listed in the embodiments or flowcharts is only one of the many execution orders, and does not represent the only execution order. It should be noted that there is no certain sequence between the above steps, and those skilled in the art can understand from the description of the embodiments of the present application that the above steps can have different execution orders in different embodiments, that is, they can be executed in parallel, or they can be exchanged and executed, etc. Moreover, at least part of the steps in the embodiments or flowcharts can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation, alternation or synchronization with other steps or sub-steps or stages of other steps.

[0083] Based on the above method embodiments, please refer to Figure 3 Another embodiment of the present application also provides a product output device, wherein the device comprises: A first acquisition module 11 is configured to acquire user features of a target user according to behavior data of the target user on a product output page in a target time period; A second acquisition module 12 is configured to acquire product features and constraint condition features of a product to be output according to product data in a product library to be output; A result generation module 13 is configured to generate a product output result based on the user features, the product features and the constraint condition features through a pre-trained product output model; A result display module 14 is configured to display the product output result to the target user in a specified area of the product output page.

[0084] Further, in one embodiment, the product output device, wherein the acquisition of the user features of the target user according to the behavior data of the target user on the product output page in the target time period comprises: Collecting behavior data of the target user on the product output page in the target time period; Preprocessing the behavior data and extracting features from the preprocessed behavior data to obtain initial user features of the target user; Verifying whether the initial user features meet the format input requirements of the product output model, and when the initial user features meet the format input requirements, taking the initial user features as the user features of the target user.

[0085] Further, in one embodiment, the product output device, wherein the product feature and the constraint condition feature of the product to be output are obtained according to the product data in the product library to be output, specifically comprising: constructing a product library to be output according to the output content of the product output page; extracting initial product features and initial constraint condition features of the product to be output according to the product data in the product library to be output; verifying whether the initial product features and the initial constraint condition features meet the format input requirements of the product output model, and when the initial product features and the initial constraint condition features meet the format input requirements, taking the initial product features and the initial constraint condition features as the product features and the constraint condition features of the product to be output respectively.

[0086] Further, in one embodiment, the product output device, wherein the product output result is generated by a pre-trained product output model based on the user features, the product features and the constraint condition features, specifically comprising: collecting a plurality of historical samples related to product output, cleaning and labeling the plurality of historical samples to obtain a training data set; training a preset deep learning model using the training data set, and obtaining a product output model when the trained deep learning model meets a preset performance index; inputting the user features, the product features and the constraint condition features into the product output model to generate a product output result.

[0087] Further, the product output device, wherein the training of the preset deep learning model using the training data set and the obtaining of the product output model when the trained deep learning model meets the preset performance index, specifically comprising: dividing the training data set into a training set, a validation set and a test set, and training the preset deep learning model using the training set; evaluating the trained deep learning model on the validation set, and optimizing the deep learning model according to the evaluation result; testing the optimized deep learning model on the test set, and generating a product output model when the deep learning model meets the preset performance index.

[0088] Further, in one embodiment, the product output device, wherein the product output result contains a plurality of target products to be output, and the displaying the product output result in the specified area of the product output page to the target user specifically includes: According to a preset product sorting strategy, the generated target products are sorted to generate a product output set; According to a preset product display strategy, the product output set is displayed in the specified area of the product output page to the target user.

[0089] Further, the product output device, wherein the displaying the product output set in the specified area of the product output page to the target user according to the preset product display strategy specifically includes: According to product display requirements, a product display strategy is constructed in advance; According to the configuration information of the product output page, the generated product output set is standardized; According to the product display strategy, the standardized product output set is displayed in the specified area of the product output page to the target user.

[0090] It should be noted that the information interaction, execution process, etc. between the above modules in the device embodiment of the application are based on the same concept as the method embodiment of the application, and the specific functions and technical effects brought by them can be referred to the method embodiment part described above, which will not be repeated here.

[0091] Based on the above method embodiment, another embodiment of the application further provides a computer device, which can be a server, and the internal structure diagram thereof can be as shown in Figure 4 The computer device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to realize the functions or steps of the product output method server side in any one of the above method embodiments.

[0092] Based on the above method embodiment, another embodiment of the application further provides a computer device, which can be a client, and the internal structure diagram thereof can be as shown in Figure 5As shown in the structural schematic diagram. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to realize the function or step of the product output method client side in any one of the above method embodiments.

[0093] Those skilled in the art can understand that, Figure 4 With Figure 5 The structural schematic diagram shown in the figure is only a schematic diagram of part of the structure related to the scheme of the application, and does not constitute a limitation on the computer device to which the scheme of the application is applied. A specific computer device can include more components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0094] The processor can be a CPU, and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0095] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory can be the memory of the computer device, and the internal memory provides an environment for the operating system and the computer readable instructions in the readable storage medium to run. The readable storage medium can be the hard disk of the computer device, and in other embodiments, it can also be the external storage device of the computer device, such as the plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Further, the memory can include both the internal storage unit of the computer device and the external storage device. The memory is used to store the operating system, application programs, boot loader, data and other programs, such as the program code of the computer program. The memory can also be used to temporarily store the data that has been output or will be output.

[0096] Based on the above method embodiments, another embodiment of the present application further provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the product output method in any one of the above method embodiments. The computer readable storage medium can be non-volatile or volatile.

[0097] It should be noted that the functions or steps that the computer readable storage medium or the computer device can achieve and the technical effects brought by the functions / steps can be referred to the related description in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0098] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc. The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable type of memory.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, in the device embodiment of the present application, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the device can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here. The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium.

[0100] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0101] In the embodiments provided by the present application, it should be understood that the disclosed device / computer equipment and method can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, and the division of the modules or units is only a logical function division, and there can be another division in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or in other forms.

[0102] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0103] It should be noted that if non-company software tools or components appear in the embodiments of the present application, they are only used for example introduction and do not represent actual use. The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the foregoing embodiments of the present application have been described in detail, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A product output method, characterized in that, include: Based on the behavioral data of the target user on the product output page within the target time period, the user characteristics of the target user are obtained; Based on the product data in the product database, obtain the product characteristics and constraint characteristics of the products to be output. Based on the user characteristics, product characteristics, and constraint characteristics, product output results are generated through a pre-trained product output model; The product output results are displayed to the target user in a designated area of ​​the product output page.

2. The product output method according to claim 1, characterized in that, The step of obtaining the user characteristics of the target user based on the target user's behavior data on the product output page within a target time period includes: Collect behavioral data of target users on the product output page within the target time period; The behavioral data is preprocessed, and features are extracted from the preprocessed behavioral data to obtain the initial user features of the target user. Verify whether the initial user characteristics meet the format input requirements of the product output model. If the initial user characteristics meet the format input requirements, use the initial user characteristics as the user characteristics of the target user.

3. The product output method according to claim 1, characterized in that, The step of obtaining the product characteristics and constraint characteristics of the products to be output based on the product data in the product database includes: Based on the output content of the product output page, construct a product library to be output; Based on the product data in the product database to be output, extract the initial product features and initial constraint features of the products to be output. Verify whether the initial product features and the initial constraint features meet the format input requirements of the product output model. When the initial product features and the initial constraint features meet the format input requirements, use the initial product features and the initial constraint features as the product features and constraint features of the product to be output, respectively.

4. The product output method according to claim 1, characterized in that, The step of generating product output results based on the user characteristics, product characteristics, and constraint characteristics using a pre-trained product output model includes: Collect several historical samples related to product output, clean and label the historical samples to obtain a training dataset; The preset deep learning model is trained using the training dataset, and when the trained deep learning model meets the preset performance indicators, the product output model is obtained. The user characteristics, product characteristics, and constraint characteristics are input into the product output model to generate the product output result.

5. The product output method according to claim 4, characterized in that, The step of training a preset deep learning model using the training dataset, and obtaining a product output model when the trained deep learning model meets preset performance metrics, includes: The training dataset is divided into a training set, a validation set, and a test set, and the training set is used to train a preset deep learning model. The trained deep learning model is evaluated on the validation set, and the deep learning model is optimized based on the evaluation results. The optimized deep learning model is tested on the test set. When the deep learning model meets the preset performance indicators, a product output model is generated.

6. The product output method according to claim 1, characterized in that, The product output results include multiple target products to be output, and displaying the product output results to the target user in a designated area of ​​the product output page includes: According to the preset product sorting strategy, the generated multiple target products are sorted to generate a product output set; According to the preset product display strategy, the product output set is displayed to the target user in a designated area of ​​the product output page.

7. The product output method according to claim 6, characterized in that, The step of displaying the product output set to the target user in a designated area of ​​the product output page according to a preset product display strategy includes: Based on product display requirements, pre-build product display strategies; Based on the configuration information of the product output page, the generated product output set is standardized. According to the product display strategy, the standardized product output set is displayed to the target user in a designated area of ​​the product output page.

8. A product output device, characterized in that, include: The first acquisition module is used to acquire the user characteristics of the target user based on the target user's behavior data on the product output page within a target time period; The second acquisition module is used to acquire the product characteristics and constraint characteristics of the product to be output based on the product data in the product database. The result generation module is used to generate product output results based on the user characteristics, the product characteristics, and the constraint characteristics, using a pre-trained product output model. The results display module is used to display the product output results to the target user in a designated area of ​​the product output page.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the product output method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the product output method as described in any one of claims 1-7.

Images