CN112148352A - Component configuration method, device, equipment and computer readable medium - Google Patents

Abstract

The present application relates to a component configuration method, apparatus, device, and computer-readable medium. The method includes: acquiring first behavior data of a target object, where the first behavior data is generated by the operation of the target object on an Internet platform; determining a first behavior feature of the target object according to the first behavior data; configuring matching with the first behavior feature The target component of the , and display the target component to the target object. The application can intelligently analyze the user's preference characteristics according to the behavior data generated by the user on the e-commerce platform, and then intelligently display the page components that match the user's preference characteristics, which solves the problem that the component configuration mode is single and does not match the user's needs, which leads to the user's click conversion. low rate problem.

Description

Component configuration method, apparatus, device, and computer-readable medium

technical field

The present application relates to the field of Internet technologies, and in particular, to a component configuration method, apparatus, device, and computer-readable medium.

Background technique

With the rapid development of Internet technology, e-commerce shopping platforms have become the main way for many users to purchase goods. In order to attract users, the e-commerce shopping platform not only needs to recommend products to meet the user's preferences, but also needs to provide different users with page components that are enough to arouse visual impact and interest, so that users have the urge to click.

At present, in the related art, the page style uses a feed stream to present the content to the user and continuously update the content, and the updated content is provided according to the program.

For the above problems, no effective solution has been proposed yet.

SUMMARY OF THE INVENTION

The present application provides a component configuration method, apparatus, device, and computer-readable medium to solve the technical problem of a single component configuration mode that does not match user requirements.

According to an aspect of the embodiments of the present application, the present application provides a component configuration method, including: acquiring first behavior data of a target object, where the first behavior data is generated by the operation of the target object on an Internet platform; according to the first behavior The data determines the first behavioral feature of the target object; configures the target component matching the first behavioral feature, and displays the target component to the target object.

Optionally, determining the first behavioral feature of the target object according to the first behavioral data includes: using a first neural network model to identify the first behavioral data; determining the target object according to a recognition result of the first neural network model on the first behavioral data. The first behavioral feature of the first neural network model is obtained after training the second neural network model by using the training data with labeling information. The labeling information is used to label the user behavioral characteristics corresponding to the training data, and the recognition result is used to indicate the first An association relationship between the behavior data and the first behavior feature.

Optionally, before using the first neural network model to identify the first behavioral data, the method further includes acquiring the first neural network model in the following manner: initializing each parameter in the second neural network model through the training data to obtain the first neural network model. Three neural network models; when the recognition accuracy of the test data by the third neural network model reaches the target threshold, the third neural network model is used as the first neural network model; when the recognition accuracy of the test data by the third neural network model is accurate If the degree of accuracy does not reach the target threshold, continue to use the training data to train the third neural network model to adjust the values of the parameters in the third neural network model until the recognition accuracy of the test data by the third neural network model reaches the target threshold.

Optionally, before using the third neural network model as the first neural network model, the method further includes training the third neural network model as follows until the third neural network model converges: inputting each training data into the third neural network model to obtain the training prediction value of user behavior characteristics; determine the loss value according to the difference between multiple training prediction values and the actual user behavior characteristics corresponding to the training data; use multiple loss values to modify the third neural network model until the third The accuracy of the output of the neural network model reaches the target threshold.

Optionally, configuring the target component that matches the first behavioral feature includes: acquiring a target code block that matches the first behavioral feature, where the target code block is an independent code block in the code warehouse; executing in the target frame corresponding to the target page The target code block is to generate the first component, the target page is the page currently browsed by the target object, and the target frame is the technical framework applied by the target page; in the case that the first component is adapted to the target display screen, the first component is used as the target component, and display the target component on the target page, and the target display screen is the display screen on the terminal used by the target object.

Optionally, when the first component is adapted to the target display screen, before using the first component as the target component, the method further includes adjusting the first component in the following manner: obtaining the first resolution of the target display screen; calculating A scaling factor between the first resolution and a preset resolution, where the preset resolution is the display screen resolution used by the first component in the original design; the first component is adjusted according to the scaling factor.

Optionally, when the target component runs abnormally, the method further includes: shielding the target code block to remove the target component; sending the target code block and exception information to an exception processing queue for processing.

According to another aspect of the embodiments of the present application, the present application provides a component configuration device, including: a data acquisition module configured to acquire first behavior data of a target object, where the first behavior data is an operation of the target object on an Internet platform generated; a feature determination module for determining a first behavioral feature of the target object according to the first behavioral data; a component configuration module for configuring a target component matching the first behavioral feature and displaying the target component to the target object.

According to another aspect of the embodiments of the present application, the present application provides an electronic device, including a memory, a processor, a communication interface, and a communication bus, the memory stores a computer program that can run on the processor, and the memory and the processor pass through The communication bus communicates with the communication interface, and the processor implements the steps of the above method when executing the computer program.

According to another aspect of the embodiments of the present application, the present application further provides a computer-readable medium having a non-volatile program code executable by a processor, the program code causing the processor to execute the above method.

Compared with the related art, the above-mentioned technical solutions provided in the embodiments of the present application have the following advantages:

The technical solution of the present application is to obtain the first behavior data of the target object, and the first behavior data is generated by the operation of the target object on the Internet platform; the first behavior feature of the target object is determined according to the first behavior data; the configuration and the first behavior feature The matching target component and present the target component to the target object. The application can intelligently analyze the user's preference characteristics according to the behavior data generated by the user on the e-commerce platform, and then intelligently display the page components that match the user's preference characteristics, which solves the problem that the component configuration mode is single and does not match the user's needs, resulting in the user's click conversion. low rate problem.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application.

In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the accompanying drawings required for describing the embodiments or related technologies will be briefly introduced below. Obviously, for those skilled in the art, On the premise of no creative labor, other drawings can also be obtained from these drawings.

FIG. 1 is a schematic diagram of a hardware environment of an optional component configuration method provided according to an embodiment of the present application;

FIG. 2 is a flowchart of an optional component configuration method provided according to an embodiment of the present application;

3 is a flowchart of an optional feature identification method provided according to an embodiment of the present application;

FIG. 4 is a flowchart of an optional decoupling component configuration method provided according to an embodiment of the present application;

FIG. 5 is a block diagram of an optional component configuration apparatus provided according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of an optional electronic device provided according to an embodiment of the present application.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, 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 It is a part of the embodiments of this application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present application.

In the following description, suffixes such as 'module', 'component' or 'unit' used to represent elements are used only to facilitate the description of the present application, and have no specific meaning per se. Therefore, "module" and "component" can be used interchangeably.

In the related art, the page style uses a feed stream to present the content to the user and continuously update the content. The updated content is provided according to the program, and the output mode of the component is relatively simple, which does not match the user's needs. And page dynamic components can only be developed in a framework such as a separate vue or react or native javascript, and the cross-framework is weak, which cannot guarantee page compatibility and page beauty.

In order to solve the problems mentioned in the background art, according to an aspect of the embodiments of the present application, an embodiment of a component configuration method is provided.

Optionally, in this embodiment of the present application, the foregoing component configuration method may be applied to a hardware environment composed of a terminal 101 and a server 102 as shown in FIG. 1 . As shown in FIG. 1 , the server 102 is connected to the terminal 101 through the network, which can be used to provide services for the terminal or the client installed on the terminal, and a database 103 can be set on the server or independent of the server to provide data storage for the server 102 Services, the above-mentioned network includes but is not limited to: wide area network, metropolitan area network or local area network, and the terminal 101 includes but is not limited to PC, mobile phone, tablet computer, etc.

A component configuration method in this embodiment of the present application may be performed by the server 102, or may be performed jointly by the server 102 and the terminal 101. As shown in FIG. 2, the method may include the following steps:

Step S201, acquiring first behavior data of the target object, where the first behavior data is generated by the operation of the target object on the Internet platform.

In the embodiment of the present application, the above-mentioned Internet platform may be a social media platform, an e-commerce shopping platform, etc., the above-mentioned target object is a user, and the first behavior data may be generated by a series of operations performed by the user on a social media platform or an e-commerce shopping platform Data, taking an e-commerce shopping platform as an example, the first behavior data can be the user's operations such as clicking, sliding, and long pressing on various components on the page. The above operations of the user on the components on the page are not only because the products corresponding to the components attract the users, but also because the visual effects of the components are consistent with the user's preferences, which makes the user interested and thus generates an impulse to click. Therefore, the behavior data generated by the user in the process of browsing the page can be obtained to further analyze the user's preferences, interest preferences, and the like.

In this embodiment of the present application, the length of time that the user stays on a single page may also be acquired. The length of time a user stays on a single page can reflect the user's interest in the products, component buttons, etc. on the page. In order to avoid misjudging that the user is far away from the device and the page stays for a long time as the user is more interested in the content on the page, the user operation can be monitored. The risk of judgment is improved, and the accuracy of user analysis is improved.

In this embodiment of the present application, the user's personal data, such as age, gender, etc., may also be acquired. Data such as age and gender can narrow the range of user groups to a certain extent and improve the accuracy of user analysis.

In this embodiment of the present application, adjustment data fed back by the user may also be obtained. In the process of page browsing, users can collect and like the products and activities they like very much, and can feedback the content they are not interested in to reduce the relevant content. The adjustment data fed back by these users can intuitively reflect the interests and preferences of users, thereby making user analysis more accurate.

Step S202, determining a first behavior feature of the target object according to the first behavior data.

In this embodiment of the present application, the user's interest preference may be located based on big data analysis. Specifically, a large amount of data can be collected to train the neural network model, and the features of user behavior data can be extracted by using the neural network model, so as to locate the user's interest preference. The above-mentioned neural network model may be a deep belief network model, a convolutional neural network model, a recurrent neural network model, or the like.

Step S203, configure a target component matching the first behavioral feature, and display the target component to the target object.

In this embodiment of the present application, after locating the user's interest preference, a component that matches the user's interest preference may be configured, so as to provide the user with a component that can arouse the user's interest, which may be different visual effects or content-oriented components. In the process of configuration and display to users, components can be switched in real time according to the analysis of users, so as to dynamically configure components that are more suitable for users' needs and improve the user's click conversion rate.

In this embodiment of the present application, the user's previous operation records can also be collected to generate a heat map of the page components. The more clicks the component has, the more points on the heat map will be denser, so that the same or similar components can be configured to be displayed to the user. , in order to attract users to click and improve the click conversion rate of users.

In the embodiments of the present application, taking an e-commerce shopping platform as an example, the ultimate purpose of improving the click conversion rate of users is to attract users to purchase commodities.

By adopting the technical solution of the present application, the user's preference characteristics can be intelligently analyzed according to the behavior data generated by the user on the e-commerce platform, and then the page components matching the user's preference characteristics can be intelligently displayed, which solves the problem that the component configuration mode is single and does not match the user's needs. Problems that lead to low user click conversion rates.

The present application provides a method for determining a user's interest preference feature using a neural network model, and the method is described in detail below with reference to the steps shown in FIG. 3 .

Optionally, determining the first behavioral feature of the target object according to the first behavioral data includes:

Step S301, using the first neural network model to identify the first behavior data.

In the embodiment of the present application, the above-mentioned first behavior data may be used as the input of the first neural network model, and after the first neural network model recognizes the first behavior data, the recognition result is output. The identification result includes the predicted value of each user's interest preference feature corresponding to the first behavior data.

Step S302, determining the first behavioral feature of the target object according to the recognition result of the first behavioral data by the first neural network model, where the first neural network model is obtained after training the second neural network model with training data with label information , the marking information is used to mark the user behavior feature corresponding to the training data, and the identification result is used to indicate the association relationship between the first behavior data and the first behavior feature.

In this embodiment of the present application, the user interest preference feature with the largest predicted value may be used as the first behavior feature matching the first behavior data.

In the embodiment of the present application, the above-mentioned first neural network model and the second neural network model are used as an example of a deep belief network model. A deep belief network model (DBN) is a probabilistic generative model that establishes a joint distribution between observed data and individual labels. In this embodiment of the present application, a joint distribution between user behavior data (observation data) and different user interest preference features (tags) is established.

Optionally, a joint distribution between the user's stay on a single page, age, gender, etc. (observation data) and user interest preference features (tags) of different device control parameters can also be established.

In the embodiment of the present application, the tag information at least identifies the user behavior data in each training data and the user interest preference feature corresponding to the user behavior data. Interesting features, marking the components that users often click on darker colors and the features that the user is interested in dark things, etc. The tag information can also identify the user's age, gender, length of stay on a single page, and corresponding user interest preference characteristics in each training data.

Optionally, before using the first neural network model to identify the first behavior data, the method further includes acquiring the first neural network model as follows:

The parameters in the second neural network model are initialized through the training data to obtain a third neural network model.

When the recognition accuracy of the test data by the third neural network model reaches the target threshold, the third neural network model is used as the first neural network model.

In the case that the recognition accuracy of the third neural network model on the test data does not reach the target threshold, continue to use the training data to train the third neural network model to adjust the values of the parameters in the third neural network model until the third The recognition accuracy of the neural network model on the test data reaches the target threshold.

In the embodiment of the present application, the training data can be used to initialize the untrained second neural network model to obtain a third neural network model, and then the third neural network model is trained. When the third neural network model is trained to convergence Next, the third neural network model is tested by using the test data, and when the accuracy of the test result reaches the target threshold, the third neural network model is used as the first neural network model and put into use. If the accuracy of the test result does not reach the target threshold, adjust the convergence threshold and continue to train the third neural network model.

Optionally, before using the third neural network model as the first neural network model, the method further includes training the third neural network model as follows until the third neural network model converges:

Input each training data into the third neural network model to obtain the training prediction value of user behavior characteristics;

Determine the loss value according to the difference between the multiple training prediction values and the actual household behavior characteristics corresponding to the training data;

The third neural network model is modified by using multiple loss values until the accuracy of the output result of the third neural network model reaches the target threshold.

In the embodiment of the present application, the model training phase is a phase in which the model parameters are continuously adjusted, and the adjustment is based on the continuous reduction of errors.

In the embodiment of the present application, a deep belief network model is taken as an example to illustrate an optional overall method of model training.

First, a large amount of data needs to be collected, including but not limited to the following parameters: the number of user clicks on each component, the sliding speed of the page, age, gender, and the length of stay on a single page, etc.

The collected parameters are then summarized and simply processed for timely use during model training. The simple processing may be performing data cleaning on the collected parameters. Data cleaning is the process of re-examining and verifying data in order to remove duplicate information, correct existing errors, and provide data consistency.

Then, principal component analysis method can be used to reduce the dimension of the collected data to select the main features and remove some redundant data. Input the dimension-reduced data into the deep belief network model (DBN), set the number of hidden layers N and learning rate ε of the deep belief network model, and determine the number of nodes in each hidden layer through the genetic algorithm, and use the Adam optimization algorithm to carry out Adaptive adjustment of the learning rate ε. Then use the error back propagation algorithm to adjust the weights and biases of the model to build a predictive model.

The present application provides a specific method of how to configure components, which will be described in detail below with reference to the steps shown in FIG. 4 .

Optionally, configuring a target component that matches the first behavioral feature includes:

Step S401, acquiring a target code block matching the first behavioral feature, where the target code block is an independent code block in the code warehouse.

Step S402, executing the target code block in the target frame corresponding to the target page to generate the first component, the target page is the page currently browsed by the target object, and the target frame is the technical framework applied by the target page;

Step S403, when the first component is adapted to the target display screen, the first component is used as the target component, and the target component is displayed on the target page, and the target display screen is the display screen on the terminal used by the target object.

In the embodiment of the present application, the code patch technology may be used, each code block may implement an independent function module, there is no dependency between each code block and the function module, and complete decoupling is realized. The above-mentioned independent function module is in the embodiment of the present application. is an independent component. Code can be written in a cross-platform code editor to run on different platforms and different frameworks when the above target code blocks need to be executed.

The above target framework may be a user interface framework commonly used in front-end development, such as vue, react, etc.

In the embodiment of the present application, according to the user's interest preference feature, the relevant code block can be called from the code warehouse to run, and the target component can be generated and displayed to the user, so as to provide the user's interest and visual impact component, and improve the conversion rate of the user's click. .

As shown in FIG. 5 , the present application also provides a method for component adaptation.

Optionally, when the first component is adapted to the target display screen, before using the first component as the target component, the method further includes adjusting the first component as follows:

Obtain the first resolution of the target display screen; calculate the scaling factor between the first resolution and the preset resolution, and the preset resolution is the display screen resolution used by the first component in the original design; A component to adjust.

In the embodiment of the present application, the display position and size of the components can be appropriately adjusted according to the device actually used by the user, thereby avoiding the problem of inconsistent styles of the components displayed by different devices. When adapting, the proportional scaling method can be adopted, and the horizontal spacing adjustment method can also be adopted. For example, the default resolution is 320*480 pixels. At this time, the component display uses a double image, that is, a point on the screen is represented by one pixel. The pixel density (Pixels Per Inch, PPI) of a screen with a resolution of 320*480 pixels is 163, that is, each inch of length contains 163 pixels. If the device used by the user has a resolution of 640*960 pixels, and the pixel density of the screen with a resolution of 640*960 pixels is 326, then from the above two pixel densities, the scaling factor can be obtained as 2, so it can be determined that the user's A double image is used to display components on the device, and the double image is that a point on the screen is represented by two pixels.

Optionally, when the target component runs abnormally, the method further includes: shielding the target code block to remove the target component; sending the target code block and exception information to an exception processing queue for processing.

In the embodiment of the present application, since the code patching technology is used for decoupling, there is no dependency between components. Therefore, when a component is abnormal, the component can be shielded and handed over to the staff for abnormal processing to reduce operational risks.

In this embodiment of the present application, through the code patch technology, not only can each component be decoupled, but also each floor of a long page can be decoupled. Once the floor data is abnormal, it will be automatically hidden, and the staff will handle the abnormality.

The technical solution of the present application is to obtain the first behavior data of the target object, and the first behavior data is generated by the operation of the target object on the Internet platform; the first behavior feature of the target object is determined according to the first behavior data; the configuration and the first behavior feature The matching target component and present the target component to the target object. The application can intelligently analyze the user's preference characteristics according to the behavior data generated by the user on the e-commerce platform, and then intelligently display the page components that match the user's preference characteristics, which solves the problem that the component configuration mode is single and does not match the user's needs, resulting in the user's click conversion. low rate problem.

According to another aspect of the embodiments of the present application, as shown in FIG. 5 , a component configuration device is provided, including: a data acquisition module 501 configured to acquire first behavior data of a target object, where the first behavior data is that the target object is in Generated by operations on the Internet platform; the feature determination module 502 is used to determine the first behavioral feature of the target object according to the first behavioral data; the component configuration module 503 is used to configure the target component that matches the first behavioral feature, and report to the target The object represents the target component.

It should be noted that the data acquisition module 501 in this embodiment may be used to perform step S201 in this embodiment of the present application, and the feature determination module 502 in this embodiment may be used to perform step S202 in this embodiment of the present application, the The component configuration module 503 in this embodiment may be used to execute step S203 in this embodiment of the present application.

It should be noted here that the examples and application scenarios implemented by the foregoing modules and corresponding steps are the same, but are not limited to the contents disclosed in the foregoing embodiments. It should be noted that, as a part of the device, the above modules may run in the hardware environment as shown in FIG. 1 , and may be implemented by software or hardware.

Optionally, the feature determination module is specifically configured to: identify the first behavior data by using the first neural network model; determine the first behavior feature of the target object according to the recognition result of the first behavior data by the first neural network model, The first neural network model is obtained after training the second neural network model by using training data with label information, the label information is used to label the user behavior characteristics corresponding to the training data, and the identification result is used to indicate that the first behavior data is related to the first behavior data. The relationship between behavioral characteristics.

Optionally, the component configuration device further includes a model training module for: initializing parameters in the second neural network model through training data to obtain a third neural network model; When the recognition accuracy reaches the target threshold, use the third neural network model as the first neural network model; when the recognition accuracy of the third neural network model on the test data does not reach the target threshold, continue to use the training data for the first neural network model. The three neural network models are trained to adjust the value of each parameter in the third neural network model until the recognition accuracy of the test data by the third neural network model reaches the target threshold.

Optionally, the model training module is also used to: input each training data into a third neural network model to obtain a training prediction value of user behavior characteristics; according to the actual user behavior characteristics corresponding to multiple training prediction values and training data The difference between them determines the loss value; the third neural network model is modified by using multiple loss values, until the accuracy of the output result of the third neural network model reaches the target threshold.

Optionally, the component configuration module is specifically used to: obtain a target code block that matches the first behavioral feature, where the target code block is an independent code block in the code warehouse; execute the target code block in the target frame corresponding to the target page , to generate the first component, the target page is the page currently browsed by the target object, and the target frame is the technical framework applied by the target page; in the case that the first component is adapted to the target display screen, the first component is used as the target component, and The target component is displayed on the target page, and the target display screen is the display screen on the terminal used by the target object.

Optionally, the component configuration device further includes an adaptation module for: acquiring the first resolution of the target display screen; calculating a scaling factor between the first resolution and a preset resolution, where the preset resolution is the The display resolution used by a component when it was originally designed; the first component is adjusted according to the scaling factor.

Optionally, the component configuration apparatus further includes an exception processing module, configured to: shield the target code block to remove the target component; send the target code block and exception information to an exception processing queue for processing.

According to another aspect of the embodiments of the present application, the present application provides an electronic device, as shown in FIG. 6 , including a memory 601 , a processor 602 , a communication interface 603 and a communication bus 604 . The computer program running on 602, the memory 601 and the processor 602 communicate through the communication interface 603 and the communication bus 604, and the processor 602 implements the steps of the above method when executing the computer program.

The memory and the processor in the above electronic device communicate through a communication bus and a communication interface. The communication bus may be a Peripheral Component Interconnect (PCI for short) bus or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA for short) bus or the like. The communication bus can be divided into an address bus, a data bus, a control bus, and the like.

The memory may include random access memory (Random Access Memory, RAM for short), and may also include non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

The above-mentioned processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc.; may also be a digital signal processor (Digital Signal Processing, referred to as DSP) , Application Specific Integrated Circuit (ASIC for short), Field-Programmable Gate Array (FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

According to yet another aspect of the embodiments of the present application, there is also provided a computer-readable medium having non-volatile program code executable by a processor.

Optionally, in this embodiment of the present application, a computer-readable medium is configured to store program codes for the processor to perform the following steps:

Obtain the first behavior data of the target object, and the first behavior data is generated by the operation of the target object on the Internet platform;

Determine the first behavioral feature of the target object according to the first behavioral data;

Configure the target component that matches the first behavioral feature, and display the target component to the target object.

Optionally, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments, and details are not described herein again in this embodiment.

When the embodiments of the present application are specifically implemented, reference may be made to the above-mentioned embodiments, which have corresponding technical effects.

It will be appreciated that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more Application Specific Integrated Circuits (ASIC), Digital Signal Processing (DSP), Digital Signal Processing Device (DSP Device, DSPD), programmable logic Devices (Programmable Logic Device, PLD), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in this application or a combination thereof.

For a software implementation, the techniques described herein may be implemented by means of units that perform the functions described herein. Software codes may be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In the embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products in essence, or the parts that make contributions to the prior art or the parts of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk and other mediums that can store program codes. It should be noted that, in this document, relational terms such as "first" and "second" etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these Any such actual relationship or sequence exists between entities or operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The above descriptions are only specific embodiments of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, this application is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims (10)

1. A method of component configuration, comprising:

acquiring first behavior data of a target object, wherein the first behavior data is generated by the operation of the target object on an internet platform;

determining a first behavior feature of the target object according to the first behavior data;

and configuring a target component matched with the first behavior feature, and showing the target component to the target object.

2. The method of claim 1, wherein determining a first behavioral feature of the target object from the first behavioral data comprises:

identifying the first behavior data using a first neural network model;

determining the first behavior feature of the target object according to a recognition result of the first neural network model on the first behavior data, wherein the first neural network model is obtained after training a second neural network model by using training data with marking information, the marking information is used for marking the user behavior feature corresponding to the training data, and the recognition result is used for indicating an association relationship between the first behavior data and the first behavior feature.

3. The method of claim 2, wherein prior to identifying the first behavioral data using a first neural network model, the method further comprises obtaining the first neural network model as follows:

initializing all parameters in the second neural network model through the training data to obtain a third neural network model;

taking the third neural network model as the first neural network model when the recognition accuracy of the third neural network model on the test data reaches a target threshold;

and under the condition that the recognition accuracy of the third neural network model on the test data does not reach the target threshold, continuing to train the third neural network model by using the training data to adjust the numerical values of all parameters in the third neural network model until the recognition accuracy of the third neural network model on the test data reaches the target threshold.

4. The method of claim 3, wherein prior to using the third neural network model as the first neural network model, the method further comprises training the third neural network model until the third neural network model converges as follows:

inputting each training data into the third neural network model to obtain a training predicted value of the user behavior characteristic;

determining a loss value according to a difference between the plurality of training predicted values and the actual user behavior characteristics corresponding to the training data;

and correcting the third neural network model by using a plurality of loss values until the precision of the output result of the third neural network model reaches the target threshold value.

5. The method of any of claims 1 to 4, wherein configuring the target component that matches the first behavioral feature comprises:

acquiring a target code block matched with the first behavior feature, wherein the target code block is an independent code block in a code warehouse;

executing the target code block in a target frame corresponding to a target page to generate a first component, wherein the target page is a page currently browsed by the target object, and the target frame is a technical frame applied by the target page;

and under the condition that the first component is matched with a target display screen, taking the first component as the target component, and displaying the target component on the target page, wherein the target display screen is a display screen on a terminal used by the target object.

6. The method of claim 5, wherein, in the case that the first component is adapted to a target display screen, prior to treating the first component as the target component, the method further comprises adjusting the first component as follows:

acquiring a first resolution of the target display screen;

calculating a scaling factor between the first resolution and a preset resolution, wherein the preset resolution is a display screen resolution used by the first assembly in original design;

and adjusting the first component according to the scaling factor.

7. The method of claim 5, wherein in the event that the target component is abnormally operational, the method further comprises:

masking the target code block to remove the target component;

and sending the target code block and the abnormal information to an abnormal processing queue for processing.

8. A component placement apparatus, comprising:

the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring first behavior data of a target object, and the first behavior data is generated by the operation of the target object on an internet platform;

the characteristic determining module is used for determining a first behavior characteristic of the target object according to the first behavior data;

and the component configuration module is used for configuring a target component matched with the first behavior characteristic and displaying the target component to the target object.

9. An electronic device comprising a memory, a processor, a communication interface and a communication bus, wherein the memory stores a computer program operable on the processor, and the memory and the processor communicate via the communication bus and the communication interface, wherein the processor implements the steps of the method according to any of the claims 1 to 7 when executing the computer program.

10. A computer-readable medium having non-volatile program code executable by a processor, wherein the program code causes the processor to perform the method of any of claims 1 to 7.

Images